1374 files changed, 86492 insertions, 26960 deletions

diff --git a/Documentation/ABI/testing/debugfs-hisi-hpre b/Documentation/ABI/testing/debugfs-hisi-hpre
new file mode 100644
index 000000000000..ec4a79e3a807
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-hisi-hpre
@@ -0,0 +1,57 @@
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/cluster[0-3]/regs
+Date:           Sep 2019
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump debug registers from the HPRE cluster.
+		Only available for PF.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/cluster[0-3]/cluster_ctrl
+Date:           Sep 2019
+Contact:        linux-crypto@vger.kernel.org
+Description:    Write the HPRE core selection in the cluster into this file,
+		and then we can read the debug information of the core.
+		Only available for PF.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/rdclr_en
+Date:           Sep 2019
+Contact:        linux-crypto@vger.kernel.org
+Description:    HPRE cores debug registers read clear control. 1 means enable
+		register read clear, otherwise 0. Writing to this file has no
+		functional effect, only enable or disable counters clear after
+		reading of these registers.
+		Only available for PF.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/current_qm
+Date:           Sep 2019
+Contact:        linux-crypto@vger.kernel.org
+Description:    One HPRE controller has one PF and multiple VFs, each function
+		has a QM. Select the QM which below qm refers to.
+		Only available for PF.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/regs
+Date:           Sep 2019
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump debug registers from the HPRE.
+		Only available for PF.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/qm/qm_regs
+Date:           Sep 2019
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump debug registers from the QM.
+		Available for PF and VF in host. VF in guest currently only
+		has one debug register.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/qm/current_q
+Date:           Sep 2019
+Contact:        linux-crypto@vger.kernel.org
+Description:    One QM may contain multiple queues. Select specific queue to
+		show its debug registers in above qm_regs.
+		Only available for PF.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/qm/clear_enable
+Date:           Sep 2019
+Contact:        linux-crypto@vger.kernel.org
+Description:    QM debug registers(qm_regs) read clear control. 1 means enable
+		register read clear, otherwise 0.
+		Writing to this file has no functional effect, only enable or
+		disable counters clear after reading of these registers.
+		Only available for PF.
diff --git a/Documentation/ABI/testing/debugfs-hisi-sec b/Documentation/ABI/testing/debugfs-hisi-sec
new file mode 100644
index 000000000000..06adb899495e
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-hisi-sec
@@ -0,0 +1,43 @@
+What:           /sys/kernel/debug/hisi_sec/<bdf>/sec_dfx
+Date:           Oct 2019
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the debug registers of SEC cores.
+		Only available for PF.
+
+What:           /sys/kernel/debug/hisi_sec/<bdf>/clear_enable
+Date:           Oct 2019
+Contact:        linux-crypto@vger.kernel.org
+Description:    Enabling/disabling of clear action after reading
+		the SEC debug registers.
+		0: disable, 1: enable.
+		Only available for PF, and take no other effect on SEC.
+
+What:           /sys/kernel/debug/hisi_sec/<bdf>/current_qm
+Date:           Oct 2019
+Contact:        linux-crypto@vger.kernel.org
+Description:    One SEC controller has one PF and multiple VFs, each function
+		has a QM. This file can be used to select the QM which below
+		qm refers to.
+		Only available for PF.
+
+What:           /sys/kernel/debug/hisi_sec/<bdf>/qm/qm_regs
+Date:           Oct 2019
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump of QM related debug registers.
+		Available for PF and VF in host. VF in guest currently only
+		has one debug register.
+
+What:           /sys/kernel/debug/hisi_sec/<bdf>/qm/current_q
+Date:           Oct 2019
+Contact:        linux-crypto@vger.kernel.org
+Description:    One QM of SEC may contain multiple queues. Select specific
+		queue to show its debug registers in above 'qm_regs'.
+		Only available for PF.
+
+What:           /sys/kernel/debug/hisi_sec/<bdf>/qm/clear_enable
+Date:           Oct 2019
+Contact:        linux-crypto@vger.kernel.org
+Description:    Enabling/disabling of clear action after reading
+		the SEC's QM debug registers.
+		0: disable, 1: enable.
+		Only available for PF, and take no other effect on SEC.
diff --git a/Documentation/ABI/testing/procfs-diskstats b/Documentation/ABI/testing/procfs-diskstats
index 2c44b4f1b060..70dcaf2481f4 100644
--- a/Documentation/ABI/testing/procfs-diskstats
+++ b/Documentation/ABI/testing/procfs-diskstats
@@ -29,4 +29,9 @@ Description:
 		17 - sectors discarded
 		18 - time spent discarding
 
+		Kernel 5.5+ appends two more fields for flush requests:
+
+		19 - flush requests completed successfully
+		20 - time spent flushing
+
 		For more details refer to Documentation/admin-guide/iostats.rst
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index f8c7c7126bb1..ed8c14f161ee 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -15,6 +15,12 @@ Description:
 		 9 - I/Os currently in progress
 		10 - time spent doing I/Os (ms)
 		11 - weighted time spent doing I/Os (ms)
+		12 - discards completed
+		13 - discards merged
+		14 - sectors discarded
+		15 - time spent discarding (ms)
+		16 - flush requests completed
+		17 - time spent flushing (ms)
 		For more details refer Documentation/admin-guide/iostats.rst
 
 
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 5361ebec3361..007ba86aef78 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1334,7 +1334,7 @@ PAGE_SIZE multiple when read back.
 
 	  pgdeactivate
 
-		Amount of pages moved to the inactive LRU lis
+		Amount of pages moved to the inactive LRU list
 
 	  pglazyfree
 
diff --git a/Documentation/admin-guide/device-mapper/dm-integrity.rst b/Documentation/admin-guide/device-mapper/dm-integrity.rst
index a30aa91b5fbe..594095b54b29 100644
--- a/Documentation/admin-guide/device-mapper/dm-integrity.rst
+++ b/Documentation/admin-guide/device-mapper/dm-integrity.rst
@@ -177,6 +177,11 @@ bitmap_flush_interval:number
 	The bitmap flush interval in milliseconds. The metadata buffers
 	are synchronized when this interval expires.
 
+fix_padding
+	Use a smaller padding of the tag area that is more
+	space-efficient. If this option is not present, large padding is
+	used - that is for compatibility with older kernels.
+
 
 The journal mode (D/J), buffer_sectors, journal_watermark, commit_time can
 be changed when reloading the target (load an inactive table and swap the
diff --git a/Documentation/admin-guide/device-mapper/dm-raid.rst b/Documentation/admin-guide/device-mapper/dm-raid.rst
index 2fe255b130fb..f6344675e395 100644
--- a/Documentation/admin-guide/device-mapper/dm-raid.rst
+++ b/Documentation/admin-guide/device-mapper/dm-raid.rst
@@ -417,3 +417,5 @@ Version History
 	deadlock/potential data corruption.  Update superblock when
 	specific devices are requested via rebuild.  Fix RAID leg
 	rebuild errors.
+ 1.15.0 Fix size extensions not being synchronized in case of new MD bitmap
+        pages allocated;  also fix those not occuring after previous reductions
diff --git a/Documentation/admin-guide/iostats.rst b/Documentation/admin-guide/iostats.rst
index 5d63b18bd6d1..4f0462af3ca7 100644
--- a/Documentation/admin-guide/iostats.rst
+++ b/Documentation/admin-guide/iostats.rst
@@ -121,6 +121,15 @@ Field 15 -- # of milliseconds spent discarding
     This is the total number of milliseconds spent by all discards (as
     measured from __make_request() to end_that_request_last()).
 
+Field 16 -- # of flush requests completed
+    This is the total number of flush requests completed successfully.
+
+    Block layer combines flush requests and executes at most one at a time.
+    This counts flush requests executed by disk. Not tracked for partitions.
+
+Field 17 -- # of milliseconds spent flushing
+    This is the total number of milliseconds spent by all flush requests.
+
 To avoid introducing performance bottlenecks, no locks are held while
 modifying these counters.  This implies that minor inaccuracies may be
 introduced when changes collide, so (for instance) adding up all the
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 8dee8f68fe15..9b847f06cb19 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3110,9 +3110,9 @@
 			[X86,PV_OPS] Disable paravirtualized VMware scheduler
 			clock and use the default one.
 
-	no-steal-acc	[X86,KVM] Disable paravirtualized steal time accounting.
-			steal time is computed, but won't influence scheduler
-			behaviour
+	no-steal-acc	[X86,KVM,ARM64] Disable paravirtualized steal time
+			accounting. steal time is computed, but won't
+			influence scheduler behaviour
 
 	nolapic		[X86-32,APIC] Do not enable or use the local APIC.
 
diff --git a/Documentation/admin-guide/perf/imx-ddr.rst b/Documentation/admin-guide/perf/imx-ddr.rst
index 517a205abad6..90056e4e8859 100644
--- a/Documentation/admin-guide/perf/imx-ddr.rst
+++ b/Documentation/admin-guide/perf/imx-ddr.rst
@@ -17,7 +17,8 @@ The "format" directory describes format of the config (event ID) and config1
 (AXI filtering) fields of the perf_event_attr structure, see /sys/bus/event_source/
 devices/imx8_ddr0/format/. The "events" directory describes the events types
 hardware supported that can be used with perf tool, see /sys/bus/event_source/
-devices/imx8_ddr0/events/.
+devices/imx8_ddr0/events/. The "caps" directory describes filter features implemented
+in DDR PMU, see /sys/bus/events_source/devices/imx8_ddr0/caps/.
   e.g.::
         perf stat -a -e imx8_ddr0/cycles/ cmd
         perf stat -a -e imx8_ddr0/read/,imx8_ddr0/write/ cmd
@@ -25,9 +26,12 @@ devices/imx8_ddr0/events/.
 AXI filtering is only used by CSV modes 0x41 (axid-read) and 0x42 (axid-write)
 to count reading or writing matches filter setting. Filter setting is various
 from different DRAM controller implementations, which is distinguished by quirks
-in the driver.
+in the driver. You also can dump info from userspace, filter in "caps" directory
+indicates whether PMU supports AXI ID filter or not; enhanced_filter indicates
+whether PMU supports enhanced AXI ID filter or not. Value 0 for un-supported, and
+value 1 for supported.
 
-* With DDR_CAP_AXI_ID_FILTER quirk.
+* With DDR_CAP_AXI_ID_FILTER quirk(filter: 1, enhanced_filter: 0).
   Filter is defined with two configuration parts:
   --AXI_ID defines AxID matching value.
   --AXI_MASKING defines which bits of AxID are meaningful for the matching.
@@ -50,3 +54,8 @@ in the driver.
   axi_id to monitor a specific id, rather than having to specify axi_mask.
   e.g.::
         perf stat -a -e imx8_ddr0/axid-read,axi_id=0x12/ cmd, which will monitor ARID=0x12
+
+* With DDR_CAP_AXI_ID_FILTER_ENHANCED quirk(filter: 1, enhanced_filter: 1).
+  This is an extension to the DDR_CAP_AXI_ID_FILTER quirk which permits
+  counting the number of bytes (as opposed to the number of bursts) from DDR
+  read and write transactions concurrently with another set of data counters.
diff --git a/Documentation/admin-guide/perf/thunderx2-pmu.rst b/Documentation/admin-guide/perf/thunderx2-pmu.rst
index 08e33675853a..01f158238ae1 100644
--- a/Documentation/admin-guide/perf/thunderx2-pmu.rst
+++ b/Documentation/admin-guide/perf/thunderx2-pmu.rst
@@ -3,24 +3,26 @@ Cavium ThunderX2 SoC Performance Monitoring Unit (PMU UNCORE)
 =============================================================
 
 The ThunderX2 SoC PMU consists of independent, system-wide, per-socket
-PMUs such as the Level 3 Cache (L3C) and DDR4 Memory Controller (DMC).
+PMUs such as the Level 3 Cache (L3C), DDR4 Memory Controller (DMC) and
+Cavium Coherent Processor Interconnect (CCPI2).
 
 The DMC has 8 interleaved channels and the L3C has 16 interleaved tiles.
 Events are counted for the default channel (i.e. channel 0) and prorated
 to the total number of channels/tiles.
 
-The DMC and L3C support up to 4 counters. Counters are independently
-programmable and can be started and stopped individually. Each counter
-can be set to a different event. Counters are 32-bit and do not support
-an overflow interrupt; they are read every 2 seconds.
+The DMC and L3C support up to 4 counters, while the CCPI2 supports up to 8
+counters. Counters are independently programmable to different events and
+can be started and stopped individually. None of the counters support an
+overflow interrupt. DMC and L3C counters are 32-bit and read every 2 seconds.
+The CCPI2 counters are 64-bit and assumed not to overflow in normal operation.
 
 PMU UNCORE (perf) driver:
 
 The thunderx2_pmu driver registers per-socket perf PMUs for the DMC and
-L3C devices.  Each PMU can be used to count up to 4 events
-simultaneously. The PMUs provide a description of their available events
-and configuration options under sysfs, see
-/sys/devices/uncore_<l3c_S/dmc_S/>; S is the socket id.
+L3C devices.  Each PMU can be used to count up to 4 (DMC/L3C) or up to 8
+(CCPI2) events simultaneously. The PMUs provide a description of their
+available events and configuration options under sysfs, see
+/sys/devices/uncore_<l3c_S/dmc_S/ccpi2_S/>; S is the socket id.
 
 The driver does not support sampling, therefore "perf record" will not
 work. Per-task perf sessions are also not supported.
diff --git a/Documentation/admin-guide/ras.rst b/Documentation/admin-guide/ras.rst
index 2b20f5f7380d..0310db624964 100644
--- a/Documentation/admin-guide/ras.rst
+++ b/Documentation/admin-guide/ras.rst
@@ -330,9 +330,12 @@ There can be multiple csrows and multiple channels.
 
 .. [#f4] Nowadays, the term DIMM (Dual In-line Memory Module) is widely
   used to refer to a memory module, although there are other memory
-  packaging alternatives, like SO-DIMM, SIMM, etc. Along this document,
-  and inside the EDAC system, the term "dimm" is used for all memory
-  modules, even when they use a different kind of packaging.
+  packaging alternatives, like SO-DIMM, SIMM, etc. The UEFI
+  specification (Version 2.7) defines a memory module in the Common
+  Platform Error Record (CPER) section to be an SMBIOS Memory Device
+  (Type 17). Along this document, and inside the EDAC subsystem, the term
+  "dimm" is used for all memory modules, even when they use a
+  different kind of packaging.
 
 Memory controllers allow for several csrows, with 8 csrows being a
 typical value. Yet, the actual number of csrows depends on the layout of
@@ -349,12 +352,14 @@ controllers. The following example will assume 2 channels:
 	|            |  ``ch0``  |  ``ch1``  |
 	+============+===========+===========+
 	| ``csrow0`` |  DIMM_A0  |  DIMM_B0  |
-	+------------+           |           |
-	| ``csrow1`` |           |           |
+	|            |   rank0   |   rank0   |
+	+------------+     -     |     -     |
+	| ``csrow1`` |   rank1   |   rank1   |
 	+------------+-----------+-----------+
 	| ``csrow2`` |  DIMM_A1  | DIMM_B1   |
-	+------------+           |           |
-	| ``csrow3`` |           |           |
+	|            |   rank0   |   rank0   |
+	+------------+     -     |     -     |
+	| ``csrow3`` |   rank1   |   rank1   |
 	+------------+-----------+-----------+
 
 In the above example, there are 4 physical slots on the motherboard
@@ -374,11 +379,13 @@ which the memory DIMM is placed. Thus, when 1 DIMM is placed in each
 Channel, the csrows cross both DIMMs.
 
 Memory DIMMs come single or dual "ranked". A rank is a populated csrow.
-Thus, 2 single ranked DIMMs, placed in slots DIMM_A0 and DIMM_B0 above
-will have just one csrow (csrow0). csrow1 will be empty. On the other
-hand, when 2 dual ranked DIMMs are similarly placed, then both csrow0
-and csrow1 will be populated. The pattern repeats itself for csrow2 and
-csrow3.
+In the example above 2 dual ranked DIMMs are similarly placed. Thus,
+both csrow0 and csrow1 are populated. On the other hand, when 2 single
+ranked DIMMs are placed in slots DIMM_A0 and DIMM_B0, then they will
+have just one csrow (csrow0) and csrow1 will be empty. The pattern
+repeats itself for csrow2 and csrow3. Also note that some memory
+controllers don't have any logic to identify the memory module, see
+``rankX`` directories below.
 
 The representation of the above is reflected in the directory
 tree in EDAC's sysfs interface. Starting in directory
diff --git a/Documentation/arm64/booting.rst b/Documentation/arm64/booting.rst
index d3f3a60fbf25..5d78a6f5b0ae 100644
--- a/Documentation/arm64/booting.rst
+++ b/Documentation/arm64/booting.rst
@@ -213,6 +213,9 @@ Before jumping into the kernel, the following conditions must be met:
 
       - ICC_SRE_EL3.Enable (bit 3) must be initialiased to 0b1.
       - ICC_SRE_EL3.SRE (bit 0) must be initialised to 0b1.
+      - ICC_CTLR_EL3.PMHE (bit 6) must be set to the same value across
+        all CPUs the kernel is executing on, and must stay constant
+        for the lifetime of the kernel.
 
   - If the kernel is entered at EL1:
 
diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst
index 2955287e9acc..b6e44884e3ad 100644
--- a/Documentation/arm64/cpu-feature-registers.rst
+++ b/Documentation/arm64/cpu-feature-registers.rst
@@ -168,8 +168,15 @@ infrastructure:
      +------------------------------+---------+---------+
 
 
-  3) MIDR_EL1 - Main ID Register
+  3) ID_AA64PFR1_EL1 - Processor Feature Register 1
+     +------------------------------+---------+---------+
+     | Name                         |  bits   | visible |
+     +------------------------------+---------+---------+
+     | SSBS                         | [7-4]   |    y    |
+     +------------------------------+---------+---------+
 
+
+  4) MIDR_EL1 - Main ID Register
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
      +------------------------------+---------+---------+
@@ -188,11 +195,15 @@ infrastructure:
    as available on the CPU where it is fetched and is not a system
    wide safe value.
 
-  4) ID_AA64ISAR1_EL1 - Instruction set attribute register 1
+  5) ID_AA64ISAR1_EL1 - Instruction set attribute register 1
 
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
      +------------------------------+---------+---------+
+     | SB                           | [39-36] |    y    |
+     +------------------------------+---------+---------+
+     | FRINTTS                      | [35-32] |    y    |
+     +------------------------------+---------+---------+
      | GPI                          | [31-28] |    y    |
      +------------------------------+---------+---------+
      | GPA                          | [27-24] |    y    |
@@ -210,7 +221,7 @@ infrastructure:
      | DPB                          | [3-0]   |    y    |
      +------------------------------+---------+---------+
 
-  5) ID_AA64MMFR2_EL1 - Memory model feature register 2
+  6) ID_AA64MMFR2_EL1 - Memory model feature register 2
 
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
@@ -218,7 +229,7 @@ infrastructure:
      | AT                           | [35-32] |    y    |
      +------------------------------+---------+---------+
 
-  6) ID_AA64ZFR0_EL1 - SVE feature ID register 0
+  7) ID_AA64ZFR0_EL1 - SVE feature ID register 0
 
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst
index 91f79529c58c..7fa3d215ae6a 100644
--- a/Documentation/arm64/elf_hwcaps.rst
+++ b/Documentation/arm64/elf_hwcaps.rst
@@ -119,10 +119,6 @@ HWCAP_LRCPC
 HWCAP_DCPOP
     Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0001.
 
-HWCAP2_DCPODP
-
-    Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0010.
-
 HWCAP_SHA3
     Functionality implied by ID_AA64ISAR0_EL1.SHA3 == 0b0001.
 
@@ -141,30 +137,6 @@ HWCAP_SHA512
 HWCAP_SVE
     Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001.
 
-HWCAP2_SVE2
-
-    Functionality implied by ID_AA64ZFR0_EL1.SVEVer == 0b0001.
-
-HWCAP2_SVEAES
-
-    Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0001.
-
-HWCAP2_SVEPMULL
-
-    Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0010.
-
-HWCAP2_SVEBITPERM
-
-    Functionality implied by ID_AA64ZFR0_EL1.BitPerm == 0b0001.
-
-HWCAP2_SVESHA3
-
-    Functionality implied by ID_AA64ZFR0_EL1.SHA3 == 0b0001.
-
-HWCAP2_SVESM4
-
-    Functionality implied by ID_AA64ZFR0_EL1.SM4 == 0b0001.
-
 HWCAP_ASIMDFHM
    Functionality implied by ID_AA64ISAR0_EL1.FHM == 0b0001.
 
@@ -180,13 +152,12 @@ HWCAP_ILRCPC
 HWCAP_FLAGM
     Functionality implied by ID_AA64ISAR0_EL1.TS == 0b0001.
 
-HWCAP2_FLAGM2
-
-    Functionality implied by ID_AA64ISAR0_EL1.TS == 0b0010.
-
 HWCAP_SSBS
     Functionality implied by ID_AA64PFR1_EL1.SSBS == 0b0010.
 
+HWCAP_SB
+    Functionality implied by ID_AA64ISAR1_EL1.SB == 0b0001.
+
 HWCAP_PACA
     Functionality implied by ID_AA64ISAR1_EL1.APA == 0b0001 or
     ID_AA64ISAR1_EL1.API == 0b0001, as described by
@@ -197,6 +168,38 @@ HWCAP_PACG
     ID_AA64ISAR1_EL1.GPI == 0b0001, as described by
     Documentation/arm64/pointer-authentication.rst.
 
+HWCAP2_DCPODP
+
+    Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0010.
+
+HWCAP2_SVE2
+
+    Functionality implied by ID_AA64ZFR0_EL1.SVEVer == 0b0001.
+
+HWCAP2_SVEAES
+
+    Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0001.
+
+HWCAP2_SVEPMULL
+
+    Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0010.
+
+HWCAP2_SVEBITPERM
+
+    Functionality implied by ID_AA64ZFR0_EL1.BitPerm == 0b0001.
+
+HWCAP2_SVESHA3
+
+    Functionality implied by ID_AA64ZFR0_EL1.SHA3 == 0b0001.
+
+HWCAP2_SVESM4
+
+    Functionality implied by ID_AA64ZFR0_EL1.SM4 == 0b0001.
+
+HWCAP2_FLAGM2
+
+    Functionality implied by ID_AA64ISAR0_EL1.TS == 0b0010.
+
 HWCAP2_FRINT
 
     Functionality implied by ID_AA64ISAR1_EL1.FRINTTS == 0b0001.
diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst
index 5a09661330fc..99b2545455ff 100644
--- a/Documentation/arm64/silicon-errata.rst
+++ b/Documentation/arm64/silicon-errata.rst
@@ -70,8 +70,12 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A57      | #834220         | ARM64_ERRATUM_834220        |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A57      | #1319537        | ARM64_ERRATUM_1319367       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A72      | #853709         | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A72      | #1319367        | ARM64_ERRATUM_1319367       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A73      | #858921         | ARM64_ERRATUM_858921        |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A55      | #1024718        | ARM64_ERRATUM_1024718       |
@@ -88,6 +92,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1349291        | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Neoverse-N1     | #1542419        | ARM64_ERRATUM_1542419       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-500         | #841119,826419  | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
diff --git a/Documentation/block/stat.rst b/Documentation/block/stat.rst
index 9c07bc22b0bc..77311335c08b 100644
--- a/Documentation/block/stat.rst
+++ b/Documentation/block/stat.rst
@@ -41,6 +41,8 @@ discard I/Os    requests      number of discard I/Os processed
 discard merges  requests      number of discard I/Os merged with in-queue I/O
 discard sectors sectors       number of sectors discarded
 discard ticks   milliseconds  total wait time for discard requests
+flush I/Os      requests      number of flush I/Os processed
+flush ticks     milliseconds  total wait time for flush requests
 =============== ============= =================================================
 
 read I/Os, write I/Os, discard I/0s
@@ -48,6 +50,14 @@ read I/Os, write I/Os, discard I/0s
 
 These values increment when an I/O request completes.
 
+flush I/Os
+==========
+
+These values increment when an flush I/O request completes.
+
+Block layer combines flush requests and executes at most one at a time.
+This counts flush requests executed by disk. Not tracked for partitions.
+
 read merges, write merges, discard merges
 =========================================
 
@@ -62,8 +72,8 @@ discarded from this block device.  The "sectors" in question are the
 standard UNIX 512-byte sectors, not any device- or filesystem-specific
 block size.  The counters are incremented when the I/O completes.
 
-read ticks, write ticks, discard ticks
-======================================
+read ticks, write ticks, discard ticks, flush ticks
+===================================================
 
 These values count the number of milliseconds that I/O requests have
 waited on this block device.  If there are multiple I/O requests waiting,
diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst
index ecbebf4ca8e7..050f34f3a70f 100644
--- a/Documentation/core-api/printk-formats.rst
+++ b/Documentation/core-api/printk-formats.rst
@@ -79,6 +79,18 @@ has the added benefit of providing a unique identifier. On 64-bit machines
 the first 32 bits are zeroed. The kernel will print ``(ptrval)`` until it
 gathers enough entropy. If you *really* want the address see %px below.
 
+Error Pointers
+--------------
+
+::
+
+	%pe	-ENOSPC
+
+For printing error pointers (i.e. a pointer for which IS_ERR() is true)
+as a symbolic error name. Error values for which no symbolic name is
+known are printed in decimal, while a non-ERR_PTR passed as the
+argument to %pe gets treated as ordinary %p.
+
 Symbols/Function Pointers
 -------------------------
 
diff --git a/Documentation/crypto/api-skcipher.rst b/Documentation/crypto/api-skcipher.rst
index 20ba08dddf2e..1aaf8985894b 100644
--- a/Documentation/crypto/api-skcipher.rst
+++ b/Documentation/crypto/api-skcipher.rst
@@ -5,7 +5,7 @@ Block Cipher Algorithm Definitions
    :doc: Block Cipher Algorithm Definitions
 
 .. kernel-doc:: include/linux/crypto.h
-   :functions: crypto_alg ablkcipher_alg blkcipher_alg cipher_alg compress_alg
+   :functions: crypto_alg cipher_alg compress_alg
 
 Symmetric Key Cipher API
 ------------------------
@@ -33,30 +33,3 @@ Single Block Cipher API
 
 .. kernel-doc:: include/linux/crypto.h
    :functions: crypto_alloc_cipher crypto_free_cipher crypto_has_cipher crypto_cipher_blocksize crypto_cipher_setkey crypto_cipher_encrypt_one crypto_cipher_decrypt_one
-
-Asynchronous Block Cipher API - Deprecated
-------------------------------------------
-
-.. kernel-doc:: include/linux/crypto.h
-   :doc: Asynchronous Block Cipher API
-
-.. kernel-doc:: include/linux/crypto.h
-   :functions: crypto_free_ablkcipher crypto_has_ablkcipher crypto_ablkcipher_ivsize crypto_ablkcipher_blocksize crypto_ablkcipher_setkey crypto_ablkcipher_reqtfm crypto_ablkcipher_encrypt crypto_ablkcipher_decrypt
-
-Asynchronous Cipher Request Handle - Deprecated
------------------------------------------------
-
-.. kernel-doc:: include/linux/crypto.h
-   :doc: Asynchronous Cipher Request Handle
-
-.. kernel-doc:: include/linux/crypto.h
-   :functions: crypto_ablkcipher_reqsize ablkcipher_request_set_tfm ablkcipher_request_alloc ablkcipher_request_free ablkcipher_request_set_callback ablkcipher_request_set_crypt
-
-Synchronous Block Cipher API - Deprecated
------------------------------------------
-
-.. kernel-doc:: include/linux/crypto.h
-   :doc: Synchronous Block Cipher API
-
-.. kernel-doc:: include/linux/crypto.h
-   :functions: crypto_alloc_blkcipher crypto_free_blkcipher crypto_has_blkcipher crypto_blkcipher_name crypto_blkcipher_ivsize crypto_blkcipher_blocksize crypto_blkcipher_setkey crypto_blkcipher_encrypt crypto_blkcipher_encrypt_iv crypto_blkcipher_decrypt crypto_blkcipher_decrypt_iv crypto_blkcipher_set_iv crypto_blkcipher_get_iv
diff --git a/Documentation/crypto/architecture.rst b/Documentation/crypto/architecture.rst
index 3eae1ae7f798..646c3380a7ed 100644
--- a/Documentation/crypto/architecture.rst
+++ b/Documentation/crypto/architecture.rst
@@ -201,10 +201,6 @@ the aforementioned cipher types:
 -  CRYPTO_ALG_TYPE_AEAD Authenticated Encryption with Associated Data
    (MAC)
 
--  CRYPTO_ALG_TYPE_BLKCIPHER Synchronous multi-block cipher
-
--  CRYPTO_ALG_TYPE_ABLKCIPHER Asynchronous multi-block cipher
-
 -  CRYPTO_ALG_TYPE_KPP Key-agreement Protocol Primitive (KPP) such as
    an ECDH or DH implementation
 
diff --git a/Documentation/crypto/crypto_engine.rst b/Documentation/crypto/crypto_engine.rst
index 3baa23c2cd08..25cf9836c336 100644
--- a/Documentation/crypto/crypto_engine.rst
+++ b/Documentation/crypto/crypto_engine.rst
@@ -63,8 +63,6 @@ request by using:
 When your driver receives a crypto_request, you must to transfer it to
 the crypto engine via one of:
 
-* crypto_transfer_ablkcipher_request_to_engine()
-
 * crypto_transfer_aead_request_to_engine()
 
 * crypto_transfer_akcipher_request_to_engine()
@@ -75,8 +73,6 @@ the crypto engine via one of:
 
 At the end of the request process, a call to one of the following functions is needed:
 
-* crypto_finalize_ablkcipher_request()
-
 * crypto_finalize_aead_request()
 
 * crypto_finalize_akcipher_request()
diff --git a/Documentation/crypto/devel-algos.rst b/Documentation/crypto/devel-algos.rst
index c45c6f400dbd..f9d288015acc 100644
--- a/Documentation/crypto/devel-algos.rst
+++ b/Documentation/crypto/devel-algos.rst
@@ -128,25 +128,20 @@ process requests that are unaligned. This implies, however, additional
 overhead as the kernel crypto API needs to perform the realignment of
 the data which may imply moving of data.
 
-Cipher Definition With struct blkcipher_alg and ablkcipher_alg
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Cipher Definition With struct skcipher_alg
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Struct blkcipher_alg defines a synchronous block cipher whereas struct
-ablkcipher_alg defines an asynchronous block cipher.
+Struct skcipher_alg defines a multi-block cipher, or more generally, a
+length-preserving symmetric cipher algorithm.
 
-Please refer to the single block cipher description for schematics of
-the block cipher usage.
+Scatterlist handling
+~~~~~~~~~~~~~~~~~~~~
 
-Specifics Of Asynchronous Multi-Block Cipher
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-There are a couple of specifics to the asynchronous interface.
-
-First of all, some of the drivers will want to use the Generic
-ScatterWalk in case the hardware needs to be fed separate chunks of the
-scatterlist which contains the plaintext and will contain the
-ciphertext. Please refer to the ScatterWalk interface offered by the
-Linux kernel scatter / gather list implementation.
+Some drivers will want to use the Generic ScatterWalk in case the
+hardware needs to be fed separate chunks of the scatterlist which
+contains the plaintext and will contain the ciphertext. Please refer
+to the ScatterWalk interface offered by the Linux kernel scatter /
+gather list implementation.
 
 Hashing [HASH]
 --------------
diff --git a/Documentation/dev-tools/index.rst b/Documentation/dev-tools/index.rst
index b0522a4dd107..09dee10d2592 100644
--- a/Documentation/dev-tools/index.rst
+++ b/Documentation/dev-tools/index.rst
@@ -24,6 +24,7 @@ whole; patches welcome!
    gdb-kernel-debugging
    kgdb
    kselftest
+   kunit/index
 
 
 .. only::  subproject and html
diff --git a/Documentation/dev-tools/kunit/api/index.rst b/Documentation/dev-tools/kunit/api/index.rst
new file mode 100644
index 000000000000..9b9bffe5d41a
--- /dev/null
+++ b/Documentation/dev-tools/kunit/api/index.rst
@@ -0,0 +1,16 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=============
+API Reference
+=============
+.. toctree::
+
+	test
+
+This section documents the KUnit kernel testing API. It is divided into the
+following sections:
+
+================================= ==============================================
+:doc:`test`                       documents all of the standard testing API
+                                  excluding mocking or mocking related features.
+================================= ==============================================
diff --git a/Documentation/dev-tools/kunit/api/test.rst b/Documentation/dev-tools/kunit/api/test.rst
new file mode 100644
index 000000000000..aaa97f17e5b3
--- /dev/null
+++ b/Documentation/dev-tools/kunit/api/test.rst
@@ -0,0 +1,11 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+========
+Test API
+========
+
+This file documents all of the standard testing API excluding mocking or mocking
+related features.
+
+.. kernel-doc:: include/kunit/test.h
+   :internal:
diff --git a/Documentation/dev-tools/kunit/faq.rst b/Documentation/dev-tools/kunit/faq.rst
new file mode 100644
index 000000000000..bf2095112d89
--- /dev/null
+++ b/Documentation/dev-tools/kunit/faq.rst
@@ -0,0 +1,62 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==========================
+Frequently Asked Questions
+==========================
+
+How is this different from Autotest, kselftest, etc?
+====================================================
+KUnit is a unit testing framework. Autotest, kselftest (and some others) are
+not.
+
+A `unit test <https://martinfowler.com/bliki/UnitTest.html>`_ is supposed to
+test a single unit of code in isolation, hence the name. A unit test should be
+the finest granularity of testing and as such should allow all possible code
+paths to be tested in the code under test; this is only possible if the code
+under test is very small and does not have any external dependencies outside of
+the test's control like hardware.
+
+There are no testing frameworks currently available for the kernel that do not
+require installing the kernel on a test machine or in a VM and all require
+tests to be written in userspace and run on the kernel under test; this is true
+for Autotest, kselftest, and some others, disqualifying any of them from being
+considered unit testing frameworks.
+
+Does KUnit support running on architectures other than UML?
+===========================================================
+
+Yes, well, mostly.
+
+For the most part, the KUnit core framework (what you use to write the tests)
+can compile to any architecture; it compiles like just another part of the
+kernel and runs when the kernel boots. However, there is some infrastructure,
+like the KUnit Wrapper (``tools/testing/kunit/kunit.py``) that does not support
+other architectures.
+
+In short, this means that, yes, you can run KUnit on other architectures, but
+it might require more work than using KUnit on UML.
+
+For more information, see :ref:`kunit-on-non-uml`.
+
+What is the difference between a unit test and these other kinds of tests?
+==========================================================================
+Most existing tests for the Linux kernel would be categorized as an integration
+test, or an end-to-end test.
+
+- A unit test is supposed to test a single unit of code in isolation, hence the
+  name. A unit test should be the finest granularity of testing and as such
+  should allow all possible code paths to be tested in the code under test; this
+  is only possible if the code under test is very small and does not have any
+  external dependencies outside of the test's control like hardware.
+- An integration test tests the interaction between a minimal set of components,
+  usually just two or three. For example, someone might write an integration
+  test to test the interaction between a driver and a piece of hardware, or to
+  test the interaction between the userspace libraries the kernel provides and
+  the kernel itself; however, one of these tests would probably not test the
+  entire kernel along with hardware interactions and interactions with the
+  userspace.
+- An end-to-end test usually tests the entire system from the perspective of the
+  code under test. For example, someone might write an end-to-end test for the
+  kernel by installing a production configuration of the kernel on production
+  hardware with a production userspace and then trying to exercise some behavior
+  that depends on interactions between the hardware, the kernel, and userspace.
diff --git a/Documentation/dev-tools/kunit/index.rst b/Documentation/dev-tools/kunit/index.rst
new file mode 100644
index 000000000000..26ffb46bdf99
--- /dev/null
+++ b/Documentation/dev-tools/kunit/index.rst
@@ -0,0 +1,79 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================================
+KUnit - Unit Testing for the Linux Kernel
+=========================================
+
+.. toctree::
+	:maxdepth: 2
+
+	start
+	usage
+	api/index
+	faq
+
+What is KUnit?
+==============
+
+KUnit is a lightweight unit testing and mocking framework for the Linux kernel.
+These tests are able to be run locally on a developer's workstation without a VM
+or special hardware.
+
+KUnit is heavily inspired by JUnit, Python's unittest.mock, and
+Googletest/Googlemock for C++. KUnit provides facilities for defining unit test
+cases, grouping related test cases into test suites, providing common
+infrastructure for running tests, and much more.
+
+Get started now: :doc:`start`
+
+Why KUnit?
+==========
+
+A unit test is supposed to test a single unit of code in isolation, hence the
+name. A unit test should be the finest granularity of testing and as such should
+allow all possible code paths to be tested in the code under test; this is only
+possible if the code under test is very small and does not have any external
+dependencies outside of the test's control like hardware.
+
+Outside of KUnit, there are no testing frameworks currently
+available for the kernel that do not require installing the kernel on a test
+machine or in a VM and all require tests to be written in userspace running on
+the kernel; this is true for Autotest, and kselftest, disqualifying
+any of them from being considered unit testing frameworks.
+
+KUnit addresses the problem of being able to run tests without needing a virtual
+machine or actual hardware with User Mode Linux. User Mode Linux is a Linux
+architecture, like ARM or x86; however, unlike other architectures it compiles
+to a standalone program that can be run like any other program directly inside
+of a host operating system; to be clear, it does not require any virtualization
+support; it is just a regular program.
+
+KUnit is fast. Excluding build time, from invocation to completion KUnit can run
+several dozen tests in only 10 to 20 seconds; this might not sound like a big
+deal to some people, but having such fast and easy to run tests fundamentally
+changes the way you go about testing and even writing code in the first place.
+Linus himself said in his `git talk at Google
+<https://gist.github.com/lorn/1272686/revisions#diff-53c65572127855f1b003db4064a94573R874>`_:
+
+	"... a lot of people seem to think that performance is about doing the
+	same thing, just doing it faster, and that is not true. That is not what
+	performance is all about. If you can do something really fast, really
+	well, people will start using it differently."
+
+In this context Linus was talking about branching and merging,
+but this point also applies to testing. If your tests are slow, unreliable, are
+difficult to write, and require a special setup or special hardware to run,
+then you wait a lot longer to write tests, and you wait a lot longer to run
+tests; this means that tests are likely to break, unlikely to test a lot of
+things, and are unlikely to be rerun once they pass. If your tests are really
+fast, you run them all the time, every time you make a change, and every time
+someone sends you some code. Why trust that someone ran all their tests
+correctly on every change when you can just run them yourself in less time than
+it takes to read their test log?
+
+How do I use it?
+================
+
+*   :doc:`start` - for new users of KUnit
+*   :doc:`usage` - for a more detailed explanation of KUnit features
+*   :doc:`api/index` - for the list of KUnit APIs used for testing
diff --git a/Documentation/dev-tools/kunit/start.rst b/Documentation/dev-tools/kunit/start.rst
new file mode 100644
index 000000000000..aeeddfafeea2
--- /dev/null
+++ b/Documentation/dev-tools/kunit/start.rst
@@ -0,0 +1,180 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============
+Getting Started
+===============
+
+Installing dependencies
+=======================
+KUnit has the same dependencies as the Linux kernel. As long as you can build
+the kernel, you can run KUnit.
+
+KUnit Wrapper
+=============
+Included with KUnit is a simple Python wrapper that helps format the output to
+easily use and read KUnit output. It handles building and running the kernel, as
+well as formatting the output.
+
+The wrapper can be run with:
+
+.. code-block:: bash
+
+   ./tools/testing/kunit/kunit.py run
+
+Creating a kunitconfig
+======================
+The Python script is a thin wrapper around Kbuild as such, it needs to be
+configured with a ``kunitconfig`` file. This file essentially contains the
+regular Kernel config, with the specific test targets as well.
+
+.. code-block:: bash
+
+	git clone -b master https://kunit.googlesource.com/kunitconfig $PATH_TO_KUNITCONFIG_REPO
+	cd $PATH_TO_LINUX_REPO
+	ln -s $PATH_TO_KUNIT_CONFIG_REPO/kunitconfig kunitconfig
+
+You may want to add kunitconfig to your local gitignore.
+
+Verifying KUnit Works
+---------------------
+
+To make sure that everything is set up correctly, simply invoke the Python
+wrapper from your kernel repo:
+
+.. code-block:: bash
+
+	./tools/testing/kunit/kunit.py run
+
+.. note::
+   You may want to run ``make mrproper`` first.
+
+If everything worked correctly, you should see the following:
+
+.. code-block:: bash
+
+	Generating .config ...
+	Building KUnit Kernel ...
+	Starting KUnit Kernel ...
+
+followed by a list of tests that are run. All of them should be passing.
+
+.. note::
+   Because it is building a lot of sources for the first time, the ``Building
+   kunit kernel`` step may take a while.
+
+Writing your first test
+=======================
+
+In your kernel repo let's add some code that we can test. Create a file
+``drivers/misc/example.h`` with the contents:
+
+.. code-block:: c
+
+	int misc_example_add(int left, int right);
+
+create a file ``drivers/misc/example.c``:
+
+.. code-block:: c
+
+	#include <linux/errno.h>
+
+	#include "example.h"
+
+	int misc_example_add(int left, int right)
+	{
+		return left + right;
+	}
+
+Now add the following lines to ``drivers/misc/Kconfig``:
+
+.. code-block:: kconfig
+
+	config MISC_EXAMPLE
+		bool "My example"
+
+and the following lines to ``drivers/misc/Makefile``:
+
+.. code-block:: make
+
+	obj-$(CONFIG_MISC_EXAMPLE) += example.o
+
+Now we are ready to write the test. The test will be in
+``drivers/misc/example-test.c``:
+
+.. code-block:: c
+
+	#include <kunit/test.h>
+	#include "example.h"
+
+	/* Define the test cases. */
+
+	static void misc_example_add_test_basic(struct kunit *test)
+	{
+		KUNIT_EXPECT_EQ(test, 1, misc_example_add(1, 0));
+		KUNIT_EXPECT_EQ(test, 2, misc_example_add(1, 1));
+		KUNIT_EXPECT_EQ(test, 0, misc_example_add(-1, 1));
+		KUNIT_EXPECT_EQ(test, INT_MAX, misc_example_add(0, INT_MAX));
+		KUNIT_EXPECT_EQ(test, -1, misc_example_add(INT_MAX, INT_MIN));
+	}
+
+	static void misc_example_test_failure(struct kunit *test)
+	{
+		KUNIT_FAIL(test, "This test never passes.");
+	}
+
+	static struct kunit_case misc_example_test_cases[] = {
+		KUNIT_CASE(misc_example_add_test_basic),
+		KUNIT_CASE(misc_example_test_failure),
+		{}
+	};
+
+	static struct kunit_suite misc_example_test_suite = {
+		.name = "misc-example",
+		.test_cases = misc_example_test_cases,
+	};
+	kunit_test_suite(misc_example_test_suite);
+
+Now add the following to ``drivers/misc/Kconfig``:
+
+.. code-block:: kconfig
+
+	config MISC_EXAMPLE_TEST
+		bool "Test for my example"
+		depends on MISC_EXAMPLE && KUNIT
+
+and the following to ``drivers/misc/Makefile``:
+
+.. code-block:: make
+
+	obj-$(CONFIG_MISC_EXAMPLE_TEST) += example-test.o
+
+Now add it to your ``kunitconfig``:
+
+.. code-block:: none
+
+	CONFIG_MISC_EXAMPLE=y
+	CONFIG_MISC_EXAMPLE_TEST=y
+
+Now you can run the test:
+
+.. code-block:: bash
+
+	./tools/testing/kunit/kunit.py
+
+You should see the following failure:
+
+.. code-block:: none
+
+	...
+	[16:08:57] [PASSED] misc-example:misc_example_add_test_basic
+	[16:08:57] [FAILED] misc-example:misc_example_test_failure
+	[16:08:57] EXPECTATION FAILED at drivers/misc/example-test.c:17
+	[16:08:57] 	This test never passes.
+	...
+
+Congrats! You just wrote your first KUnit test!
+
+Next Steps
+==========
+*   Check out the :doc:`usage` page for a more
+    in-depth explanation of KUnit.
diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst
new file mode 100644
index 000000000000..c6e69634e274
--- /dev/null
+++ b/Documentation/dev-tools/kunit/usage.rst
@@ -0,0 +1,576 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========
+Using KUnit
+===========
+
+The purpose of this document is to describe what KUnit is, how it works, how it
+is intended to be used, and all the concepts and terminology that are needed to
+understand it. This guide assumes a working knowledge of the Linux kernel and
+some basic knowledge of testing.
+
+For a high level introduction to KUnit, including setting up KUnit for your
+project, see :doc:`start`.
+
+Organization of this document
+=============================
+
+This document is organized into two main sections: Testing and Isolating
+Behavior. The first covers what a unit test is and how to use KUnit to write
+them. The second covers how to use KUnit to isolate code and make it possible
+to unit test code that was otherwise un-unit-testable.
+
+Testing
+=======
+
+What is KUnit?
+--------------
+
+"K" is short for "kernel" so "KUnit" is the "(Linux) Kernel Unit Testing
+Framework." KUnit is intended first and foremost for writing unit tests; it is
+general enough that it can be used to write integration tests; however, this is
+a secondary goal. KUnit has no ambition of being the only testing framework for
+the kernel; for example, it does not intend to be an end-to-end testing
+framework.
+
+What is Unit Testing?
+---------------------
+
+A `unit test <https://martinfowler.com/bliki/UnitTest.html>`_ is a test that
+tests code at the smallest possible scope, a *unit* of code. In the C
+programming language that's a function.
+
+Unit tests should be written for all the publicly exposed functions in a
+compilation unit; so that is all the functions that are exported in either a
+*class* (defined below) or all functions which are **not** static.
+
+Writing Tests
+-------------
+
+Test Cases
+~~~~~~~~~~
+
+The fundamental unit in KUnit is the test case. A test case is a function with
+the signature ``void (*)(struct kunit *test)``. It calls a function to be tested
+and then sets *expectations* for what should happen. For example:
+
+.. code-block:: c
+
+	void example_test_success(struct kunit *test)
+	{
+	}
+
+	void example_test_failure(struct kunit *test)
+	{
+		KUNIT_FAIL(test, "This test never passes.");
+	}
+
+In the above example ``example_test_success`` always passes because it does
+nothing; no expectations are set, so all expectations pass. On the other hand
+``example_test_failure`` always fails because it calls ``KUNIT_FAIL``, which is
+a special expectation that logs a message and causes the test case to fail.
+
+Expectations
+~~~~~~~~~~~~
+An *expectation* is a way to specify that you expect a piece of code to do
+something in a test. An expectation is called like a function. A test is made
+by setting expectations about the behavior of a piece of code under test; when
+one or more of the expectations fail, the test case fails and information about
+the failure is logged. For example:
+
+.. code-block:: c
+
+	void add_test_basic(struct kunit *test)
+	{
+		KUNIT_EXPECT_EQ(test, 1, add(1, 0));
+		KUNIT_EXPECT_EQ(test, 2, add(1, 1));
+	}
+
+In the above example ``add_test_basic`` makes a number of assertions about the
+behavior of a function called ``add``; the first parameter is always of type
+``struct kunit *``, which contains information about the current test context;
+the second parameter, in this case, is what the value is expected to be; the
+last value is what the value actually is. If ``add`` passes all of these
+expectations, the test case, ``add_test_basic`` will pass; if any one of these
+expectations fail, the test case will fail.
+
+It is important to understand that a test case *fails* when any expectation is
+violated; however, the test will continue running, potentially trying other
+expectations until the test case ends or is otherwise terminated. This is as
+opposed to *assertions* which are discussed later.
+
+To learn about more expectations supported by KUnit, see :doc:`api/test`.
+
+.. note::
+   A single test case should be pretty short, pretty easy to understand,
+   focused on a single behavior.
+
+For example, if we wanted to properly test the add function above, we would
+create additional tests cases which would each test a different property that an
+add function should have like this:
+
+.. code-block:: c
+
+	void add_test_basic(struct kunit *test)
+	{
+		KUNIT_EXPECT_EQ(test, 1, add(1, 0));
+		KUNIT_EXPECT_EQ(test, 2, add(1, 1));
+	}
+
+	void add_test_negative(struct kunit *test)
+	{
+		KUNIT_EXPECT_EQ(test, 0, add(-1, 1));
+	}
+
+	void add_test_max(struct kunit *test)
+	{
+		KUNIT_EXPECT_EQ(test, INT_MAX, add(0, INT_MAX));
+		KUNIT_EXPECT_EQ(test, -1, add(INT_MAX, INT_MIN));
+	}
+
+	void add_test_overflow(struct kunit *test)
+	{
+		KUNIT_EXPECT_EQ(test, INT_MIN, add(INT_MAX, 1));
+	}
+
+Notice how it is immediately obvious what all the properties that we are testing
+for are.
+
+Assertions
+~~~~~~~~~~
+
+KUnit also has the concept of an *assertion*. An assertion is just like an
+expectation except the assertion immediately terminates the test case if it is
+not satisfied.
+
+For example:
+
+.. code-block:: c
+
+	static void mock_test_do_expect_default_return(struct kunit *test)
+	{
+		struct mock_test_context *ctx = test->priv;
+		struct mock *mock = ctx->mock;
+		int param0 = 5, param1 = -5;
+		const char *two_param_types[] = {"int", "int"};
+		const void *two_params[] = {&param0, &param1};
+		const void *ret;
+
+		ret = mock->do_expect(mock,
+				      "test_printk", test_printk,
+				      two_param_types, two_params,
+				      ARRAY_SIZE(two_params));
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ret);
+		KUNIT_EXPECT_EQ(test, -4, *((int *) ret));
+	}
+
+In this example, the method under test should return a pointer to a value, so
+if the pointer returned by the method is null or an errno, we don't want to
+bother continuing the test since the following expectation could crash the test
+case. `ASSERT_NOT_ERR_OR_NULL(...)` allows us to bail out of the test case if
+the appropriate conditions have not been satisfied to complete the test.
+
+Test Suites
+~~~~~~~~~~~
+
+Now obviously one unit test isn't very helpful; the power comes from having
+many test cases covering all of your behaviors. Consequently it is common to
+have many *similar* tests; in order to reduce duplication in these closely
+related tests most unit testing frameworks provide the concept of a *test
+suite*, in KUnit we call it a *test suite*; all it is is just a collection of
+test cases for a unit of code with a set up function that gets invoked before
+every test cases and then a tear down function that gets invoked after every
+test case completes.
+
+Example:
+
+.. code-block:: c
+
+	static struct kunit_case example_test_cases[] = {
+		KUNIT_CASE(example_test_foo),
+		KUNIT_CASE(example_test_bar),
+		KUNIT_CASE(example_test_baz),
+		{}
+	};
+
+	static struct kunit_suite example_test_suite = {
+		.name = "example",
+		.init = example_test_init,
+		.exit = example_test_exit,
+		.test_cases = example_test_cases,
+	};
+	kunit_test_suite(example_test_suite);
+
+In the above example the test suite, ``example_test_suite``, would run the test
+cases ``example_test_foo``, ``example_test_bar``, and ``example_test_baz``,
+each would have ``example_test_init`` called immediately before it and would
+have ``example_test_exit`` called immediately after it.
+``kunit_test_suite(example_test_suite)`` registers the test suite with the
+KUnit test framework.
+
+.. note::
+   A test case will only be run if it is associated with a test suite.
+
+For a more information on these types of things see the :doc:`api/test`.
+
+Isolating Behavior
+==================
+
+The most important aspect of unit testing that other forms of testing do not
+provide is the ability to limit the amount of code under test to a single unit.
+In practice, this is only possible by being able to control what code gets run
+when the unit under test calls a function and this is usually accomplished
+through some sort of indirection where a function is exposed as part of an API
+such that the definition of that function can be changed without affecting the
+rest of the code base. In the kernel this primarily comes from two constructs,
+classes, structs that contain function pointers that are provided by the
+implementer, and architecture specific functions which have definitions selected
+at compile time.
+
+Classes
+-------
+
+Classes are not a construct that is built into the C programming language;
+however, it is an easily derived concept. Accordingly, pretty much every project
+that does not use a standardized object oriented library (like GNOME's GObject)
+has their own slightly different way of doing object oriented programming; the
+Linux kernel is no exception.
+
+The central concept in kernel object oriented programming is the class. In the
+kernel, a *class* is a struct that contains function pointers. This creates a
+contract between *implementers* and *users* since it forces them to use the
+same function signature without having to call the function directly. In order
+for it to truly be a class, the function pointers must specify that a pointer
+to the class, known as a *class handle*, be one of the parameters; this makes
+it possible for the member functions (also known as *methods*) to have access
+to member variables (more commonly known as *fields*) allowing the same
+implementation to have multiple *instances*.
+
+Typically a class can be *overridden* by *child classes* by embedding the
+*parent class* in the child class. Then when a method provided by the child
+class is called, the child implementation knows that the pointer passed to it is
+of a parent contained within the child; because of this, the child can compute
+the pointer to itself because the pointer to the parent is always a fixed offset
+from the pointer to the child; this offset is the offset of the parent contained
+in the child struct. For example:
+
+.. code-block:: c
+
+	struct shape {
+		int (*area)(struct shape *this);
+	};
+
+	struct rectangle {
+		struct shape parent;
+		int length;
+		int width;
+	};
+
+	int rectangle_area(struct shape *this)
+	{
+		struct rectangle *self = container_of(this, struct shape, parent);
+
+		return self->length * self->width;
+	};
+
+	void rectangle_new(struct rectangle *self, int length, int width)
+	{
+		self->parent.area = rectangle_area;
+		self->length = length;
+		self->width = width;
+	}
+
+In this example (as in most kernel code) the operation of computing the pointer
+to the child from the pointer to the parent is done by ``container_of``.
+
+Faking Classes
+~~~~~~~~~~~~~~
+
+In order to unit test a piece of code that calls a method in a class, the
+behavior of the method must be controllable, otherwise the test ceases to be a
+unit test and becomes an integration test.
+
+A fake just provides an implementation of a piece of code that is different than
+what runs in a production instance, but behaves identically from the standpoint
+of the callers; this is usually done to replace a dependency that is hard to
+deal with, or is slow.
+
+A good example for this might be implementing a fake EEPROM that just stores the
+"contents" in an internal buffer. For example, let's assume we have a class that
+represents an EEPROM:
+
+.. code-block:: c
+
+	struct eeprom {
+		ssize_t (*read)(struct eeprom *this, size_t offset, char *buffer, size_t count);
+		ssize_t (*write)(struct eeprom *this, size_t offset, const char *buffer, size_t count);
+	};
+
+And we want to test some code that buffers writes to the EEPROM:
+
+.. code-block:: c
+
+	struct eeprom_buffer {
+		ssize_t (*write)(struct eeprom_buffer *this, const char *buffer, size_t count);
+		int flush(struct eeprom_buffer *this);
+		size_t flush_count; /* Flushes when buffer exceeds flush_count. */
+	};
+
+	struct eeprom_buffer *new_eeprom_buffer(struct eeprom *eeprom);
+	void destroy_eeprom_buffer(struct eeprom *eeprom);
+
+We can easily test this code by *faking out* the underlying EEPROM:
+
+.. code-block:: c
+
+	struct fake_eeprom {
+		struct eeprom parent;
+		char contents[FAKE_EEPROM_CONTENTS_SIZE];
+	};
+
+	ssize_t fake_eeprom_read(struct eeprom *parent, size_t offset, char *buffer, size_t count)
+	{
+		struct fake_eeprom *this = container_of(parent, struct fake_eeprom, parent);
+
+		count = min(count, FAKE_EEPROM_CONTENTS_SIZE - offset);
+		memcpy(buffer, this->contents + offset, count);
+
+		return count;
+	}
+
+	ssize_t fake_eeprom_write(struct eeprom *this, size_t offset, const char *buffer, size_t count)
+	{
+		struct fake_eeprom *this = container_of(parent, struct fake_eeprom, parent);
+
+		count = min(count, FAKE_EEPROM_CONTENTS_SIZE - offset);
+		memcpy(this->contents + offset, buffer, count);
+
+		return count;
+	}
+
+	void fake_eeprom_init(struct fake_eeprom *this)
+	{
+		this->parent.read = fake_eeprom_read;
+		this->parent.write = fake_eeprom_write;
+		memset(this->contents, 0, FAKE_EEPROM_CONTENTS_SIZE);
+	}
+
+We can now use it to test ``struct eeprom_buffer``:
+
+.. code-block:: c
+
+	struct eeprom_buffer_test {
+		struct fake_eeprom *fake_eeprom;
+		struct eeprom_buffer *eeprom_buffer;
+	};
+
+	static void eeprom_buffer_test_does_not_write_until_flush(struct kunit *test)
+	{
+		struct eeprom_buffer_test *ctx = test->priv;
+		struct eeprom_buffer *eeprom_buffer = ctx->eeprom_buffer;
+		struct fake_eeprom *fake_eeprom = ctx->fake_eeprom;
+		char buffer[] = {0xff};
+
+		eeprom_buffer->flush_count = SIZE_MAX;
+
+		eeprom_buffer->write(eeprom_buffer, buffer, 1);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0);
+
+		eeprom_buffer->write(eeprom_buffer, buffer, 1);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[1], 0);
+
+		eeprom_buffer->flush(eeprom_buffer);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0xff);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[1], 0xff);
+	}
+
+	static void eeprom_buffer_test_flushes_after_flush_count_met(struct kunit *test)
+	{
+		struct eeprom_buffer_test *ctx = test->priv;
+		struct eeprom_buffer *eeprom_buffer = ctx->eeprom_buffer;
+		struct fake_eeprom *fake_eeprom = ctx->fake_eeprom;
+		char buffer[] = {0xff};
+
+		eeprom_buffer->flush_count = 2;
+
+		eeprom_buffer->write(eeprom_buffer, buffer, 1);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0);
+
+		eeprom_buffer->write(eeprom_buffer, buffer, 1);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0xff);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[1], 0xff);
+	}
+
+	static void eeprom_buffer_test_flushes_increments_of_flush_count(struct kunit *test)
+	{
+		struct eeprom_buffer_test *ctx = test->priv;
+		struct eeprom_buffer *eeprom_buffer = ctx->eeprom_buffer;
+		struct fake_eeprom *fake_eeprom = ctx->fake_eeprom;
+		char buffer[] = {0xff, 0xff};
+
+		eeprom_buffer->flush_count = 2;
+
+		eeprom_buffer->write(eeprom_buffer, buffer, 1);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0);
+
+		eeprom_buffer->write(eeprom_buffer, buffer, 2);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0xff);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[1], 0xff);
+		/* Should have only flushed the first two bytes. */
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[2], 0);
+	}
+
+	static int eeprom_buffer_test_init(struct kunit *test)
+	{
+		struct eeprom_buffer_test *ctx;
+
+		ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL);
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
+		ctx->fake_eeprom = kunit_kzalloc(test, sizeof(*ctx->fake_eeprom), GFP_KERNEL);
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx->fake_eeprom);
+		fake_eeprom_init(ctx->fake_eeprom);
+
+		ctx->eeprom_buffer = new_eeprom_buffer(&ctx->fake_eeprom->parent);
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx->eeprom_buffer);
+
+		test->priv = ctx;
+
+		return 0;
+	}
+
+	static void eeprom_buffer_test_exit(struct kunit *test)
+	{
+		struct eeprom_buffer_test *ctx = test->priv;
+
+		destroy_eeprom_buffer(ctx->eeprom_buffer);
+	}
+
+.. _kunit-on-non-uml:
+
+KUnit on non-UML architectures
+==============================
+
+By default KUnit uses UML as a way to provide dependencies for code under test.
+Under most circumstances KUnit's usage of UML should be treated as an
+implementation detail of how KUnit works under the hood. Nevertheless, there
+are instances where being able to run architecture specific code, or test
+against real hardware is desirable. For these reasons KUnit supports running on
+other architectures.
+
+Running existing KUnit tests on non-UML architectures
+-----------------------------------------------------
+
+There are some special considerations when running existing KUnit tests on
+non-UML architectures:
+
+*   Hardware may not be deterministic, so a test that always passes or fails
+    when run under UML may not always do so on real hardware.
+*   Hardware and VM environments may not be hermetic. KUnit tries its best to
+    provide a hermetic environment to run tests; however, it cannot manage state
+    that it doesn't know about outside of the kernel. Consequently, tests that
+    may be hermetic on UML may not be hermetic on other architectures.
+*   Some features and tooling may not be supported outside of UML.
+*   Hardware and VMs are slower than UML.
+
+None of these are reasons not to run your KUnit tests on real hardware; they are
+only things to be aware of when doing so.
+
+The biggest impediment will likely be that certain KUnit features and
+infrastructure may not support your target environment. For example, at this
+time the KUnit Wrapper (``tools/testing/kunit/kunit.py``) does not work outside
+of UML. Unfortunately, there is no way around this. Using UML (or even just a
+particular architecture) allows us to make a lot of assumptions that make it
+possible to do things which might otherwise be impossible.
+
+Nevertheless, all core KUnit framework features are fully supported on all
+architectures, and using them is straightforward: all you need to do is to take
+your kunitconfig, your Kconfig options for the tests you would like to run, and
+merge them into whatever config your are using for your platform. That's it!
+
+For example, let's say you have the following kunitconfig:
+
+.. code-block:: none
+
+	CONFIG_KUNIT=y
+	CONFIG_KUNIT_EXAMPLE_TEST=y
+
+If you wanted to run this test on an x86 VM, you might add the following config
+options to your ``.config``:
+
+.. code-block:: none
+
+	CONFIG_KUNIT=y
+	CONFIG_KUNIT_EXAMPLE_TEST=y
+	CONFIG_SERIAL_8250=y
+	CONFIG_SERIAL_8250_CONSOLE=y
+
+All these new options do is enable support for a common serial console needed
+for logging.
+
+Next, you could build a kernel with these tests as follows:
+
+
+.. code-block:: bash
+
+	make ARCH=x86 olddefconfig
+	make ARCH=x86
+
+Once you have built a kernel, you could run it on QEMU as follows:
+
+.. code-block:: bash
+
+	qemu-system-x86_64 -enable-kvm \
+			   -m 1024 \
+			   -kernel arch/x86_64/boot/bzImage \
+			   -append 'console=ttyS0' \
+			   --nographic
+
+Interspersed in the kernel logs you might see the following:
+
+.. code-block:: none
+
+	TAP version 14
+		# Subtest: example
+		1..1
+		# example_simple_test: initializing
+		ok 1 - example_simple_test
+	ok 1 - example
+
+Congratulations, you just ran a KUnit test on the x86 architecture!
+
+Writing new tests for other architectures
+-----------------------------------------
+
+The first thing you must do is ask yourself whether it is necessary to write a
+KUnit test for a specific architecture, and then whether it is necessary to
+write that test for a particular piece of hardware. In general, writing a test
+that depends on having access to a particular piece of hardware or software (not
+included in the Linux source repo) should be avoided at all costs.
+
+Even if you only ever plan on running your KUnit test on your hardware
+configuration, other people may want to run your tests and may not have access
+to your hardware. If you write your test to run on UML, then anyone can run your
+tests without knowing anything about your particular setup, and you can still
+run your tests on your hardware setup just by compiling for your architecture.
+
+.. important::
+   Always prefer tests that run on UML to tests that only run under a particular
+   architecture, and always prefer tests that run under QEMU or another easy
+   (and monitarily free) to obtain software environment to a specific piece of
+   hardware.
+
+Nevertheless, there are still valid reasons to write an architecture or hardware
+specific test: for example, you might want to test some code that really belongs
+in ``arch/some-arch/*``. Even so, try your best to write the test so that it
+does not depend on physical hardware: if some of your test cases don't need the
+hardware, only require the hardware for tests that actually need it.
+
+Now that you have narrowed down exactly what bits are hardware specific, the
+actual procedure for writing and running the tests is pretty much the same as
+writing normal KUnit tests. One special caveat is that you have to reset
+hardware state in between test cases; if this is not possible, you may only be
+able to run one test case per invocation.
+
+.. TODO(brendanhiggins@google.com): Add an actual example of an architecture
+   dependent KUnit test.
diff --git a/Documentation/devicetree/bindings/crypto/allwinner,sun8i-ss.yaml b/Documentation/devicetree/bindings/crypto/allwinner,sun8i-ss.yaml
new file mode 100644
index 000000000000..8a29d36edf26
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/allwinner,sun8i-ss.yaml
@@ -0,0 +1,60 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/crypto/allwinner,sun8i-ss.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner Security System v2 driver
+
+maintainers:
+  - Corentin Labbe <corentin.labbe@gmail.com>
+
+properties:
+  compatible:
+    enum:
+      - allwinner,sun8i-a83t-crypto
+      - allwinner,sun9i-a80-crypto
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: Bus clock
+      - description: Module clock
+
+  clock-names:
+    items:
+      - const: bus
+      - const: mod
+
+  resets:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/sun8i-a83t-ccu.h>
+    #include <dt-bindings/reset/sun8i-a83t-ccu.h>
+
+    crypto: crypto@1c15000 {
+      compatible = "allwinner,sun8i-a83t-crypto";
+      reg = <0x01c15000 0x1000>;
+      interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
+      resets = <&ccu RST_BUS_SS>;
+      clocks = <&ccu CLK_BUS_SS>, <&ccu CLK_SS>;
+      clock-names = "bus", "mod";
+    };
diff --git a/Documentation/devicetree/bindings/crypto/amlogic,gxl-crypto.yaml b/Documentation/devicetree/bindings/crypto/amlogic,gxl-crypto.yaml
new file mode 100644
index 000000000000..5becc60a0e28
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/amlogic,gxl-crypto.yaml
@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/crypto/amlogic,gxl-crypto.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Amlogic GXL Cryptographic Offloader
+
+maintainers:
+  - Corentin Labbe <clabbe@baylibre.com>
+
+properties:
+  compatible:
+    items:
+    - const: amlogic,gxl-crypto
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    items:
+      - description: "Interrupt for flow 0"
+      - description: "Interrupt for flow 1"
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    const: blkmv
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/gxbb-clkc.h>
+
+    crypto: crypto-engine@c883e000 {
+        compatible = "amlogic,gxl-crypto";
+        reg = <0x0 0xc883e000 0x0 0x36>;
+        interrupts = <GIC_SPI 188 IRQ_TYPE_EDGE_RISING>, <GIC_SPI 189 IRQ_TYPE_EDGE_RISING>;
+        clocks = <&clkc CLKID_BLKMV>;
+        clock-names = "blkmv";
+    };
diff --git a/Documentation/devicetree/bindings/mips/ralink.txt b/Documentation/devicetree/bindings/mips/ralink.txt
index a16e8d7fe56c..8cc0ab41578c 100644
--- a/Documentation/devicetree/bindings/mips/ralink.txt
+++ b/Documentation/devicetree/bindings/mips/ralink.txt
@@ -16,3 +16,17 @@ value must be one of the following values:
   ralink,mt7620a-soc
   ralink,mt7620n-soc
   ralink,mt7628a-soc
+  ralink,mt7688a-soc
+
+2. Boards
+
+GARDENA smart Gateway (MT7688)
+
+This board is based on the MediaTek MT7688 and equipped with 128 MiB
+of DDR and 8 MiB of flash (SPI NOR) and additional 128MiB SPI NAND
+storage.
+
+------------------------------
+Required root node properties:
+- compatible = "gardena,smart-gateway-mt7688", "ralink,mt7688a-soc",
+		"ralink,mt7628a-soc";
diff --git a/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt b/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt
new file mode 100644
index 000000000000..f3893c4d3c6a
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt
@@ -0,0 +1,53 @@
+* Cadence NAND controller
+
+Required properties:
+  - compatible : "cdns,hp-nfc"
+  - reg : Contains two entries, each of which is a tuple consisting of a
+	  physical address and length. The first entry is the address and
+	  length of the controller register set. The second entry is the
+	  address and length of the Slave DMA data port.
+  - reg-names: should contain "reg" and "sdma"
+  - #address-cells: should be 1. The cell encodes the chip select connection.
+  - #size-cells : should be 0.
+  - interrupts : The interrupt number.
+  - clocks: phandle of the controller core clock (nf_clk).
+
+Optional properties:
+  - dmas: shall reference DMA channel associated to the NAND controller
+  - cdns,board-delay-ps : Estimated Board delay. The value includes the total
+    round trip delay for the signals and is used for deciding on values
+    associated with data read capture. The example formula for SDR mode is
+    the following:
+    board delay = RE#PAD delay + PCB trace to device + PCB trace from device
+    + DQ PAD delay
+
+Child nodes represent the available NAND chips.
+
+Required properties of NAND chips:
+  - reg: shall contain the native Chip Select ids from 0 to max supported by
+    the cadence nand flash controller
+
+See Documentation/devicetree/bindings/mtd/nand.txt for more details on
+generic bindings.
+
+Example:
+
+nand_controller: nand-controller@60000000 {
+	  compatible = "cdns,hp-nfc";
+	  #address-cells = <1>;
+	  #size-cells = <0>;
+	  reg = <0x60000000 0x10000>, <0x80000000 0x10000>;
+	  reg-names = "reg", "sdma";
+	  clocks = <&nf_clk>;
+	  cdns,board-delay-ps = <4830>;
+	  interrupts = <2 0>;
+	  nand@0 {
+	      reg = <0>;
+	      label = "nand-1";
+	  };
+	  nand@1 {
+	      reg = <1>;
+	      label = "nand-2";
+	  };
+
+};
diff --git a/Documentation/devicetree/bindings/mtd/intel,ixp4xx-flash.txt b/Documentation/devicetree/bindings/mtd/intel,ixp4xx-flash.txt
new file mode 100644
index 000000000000..4bdcb92ae381
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/intel,ixp4xx-flash.txt
@@ -0,0 +1,22 @@
+Flash device on Intel IXP4xx SoC
+
+This flash is regular CFI compatible (Intel or AMD extended) flash chips with
+specific big-endian or mixed-endian memory access pattern.
+
+Required properties:
+- compatible : must be "intel,ixp4xx-flash", "cfi-flash";
+- reg : memory address for the flash chip
+- bank-width : width in bytes of flash interface, should be <2>
+
+For the rest of the properties, see mtd-physmap.txt.
+
+The device tree may optionally contain sub-nodes describing partitions of the
+address space. See partition.txt for more detail.
+
+Example:
+
+flash@50000000 {
+	compatible = "intel,ixp4xx-flash", "cfi-flash";
+	reg = <0x50000000 0x01000000>;
+	bank-width = <2>;
+};
diff --git a/Documentation/devicetree/bindings/perf/arm-ccn.txt b/Documentation/devicetree/bindings/perf/arm-ccn.txt
index 43b5a71a5a9d..1c53b5aa3317 100644
--- a/Documentation/devicetree/bindings/perf/arm-ccn.txt
+++ b/Documentation/devicetree/bindings/perf/arm-ccn.txt
@@ -6,6 +6,7 @@ Required properties:
 	"arm,ccn-502"
 	"arm,ccn-504"
 	"arm,ccn-508"
+	"arm,ccn-512"
 
 - reg: (standard registers property) physical address and size
 	(16MB) of the configuration registers block
diff --git a/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt b/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt
index d77e3f26f9e6..7822a806ea0a 100644
--- a/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt
+++ b/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt
@@ -5,6 +5,7 @@ Required properties:
 - compatible: should be one of:
 	"fsl,imx8-ddr-pmu"
 	"fsl,imx8m-ddr-pmu"
+	"fsl,imx8mp-ddr-pmu"
 
 - reg: physical address and size
 
diff --git a/Documentation/devicetree/bindings/rng/atmel-trng.txt b/Documentation/devicetree/bindings/rng/atmel-trng.txt
index 4ac5aaa2d024..3900ee4f3532 100644
--- a/Documentation/devicetree/bindings/rng/atmel-trng.txt
+++ b/Documentation/devicetree/bindings/rng/atmel-trng.txt
@@ -1,7 +1,7 @@
 Atmel TRNG (True Random Number Generator) block
 
 Required properties:
-- compatible : Should be "atmel,at91sam9g45-trng"
+- compatible : Should be "atmel,at91sam9g45-trng" or "microchip,sam9x60-trng"
 - reg : Offset and length of the register set of this block
 - interrupts : the interrupt number for the TRNG block
 - clocks: should contain the TRNG clk source
diff --git a/Documentation/devicetree/bindings/rng/nuvoton,npcm-rng.txt b/Documentation/devicetree/bindings/rng/nuvoton,npcm-rng.txt
new file mode 100644
index 000000000000..65c04172fc8c
--- /dev/null
+++ b/Documentation/devicetree/bindings/rng/nuvoton,npcm-rng.txt
@@ -0,0 +1,12 @@
+NPCM SoC Random Number Generator
+
+Required properties:
+- compatible  : "nuvoton,npcm750-rng" for the NPCM7XX BMC.
+- reg         : Specifies physical base address and size of the registers.
+
+Example:
+
+rng: rng@f000b000 {
+	compatible = "nuvoton,npcm750-rng";
+	reg = <0xf000b000 0x8>;
+};
diff --git a/Documentation/devicetree/bindings/rng/omap3_rom_rng.txt b/Documentation/devicetree/bindings/rng/omap3_rom_rng.txt
new file mode 100644
index 000000000000..f315c9723bd2
--- /dev/null
+++ b/Documentation/devicetree/bindings/rng/omap3_rom_rng.txt
@@ -0,0 +1,27 @@
+OMAP ROM RNG driver binding
+
+Secure SoCs may provide RNG via secure ROM calls like Nokia N900 does. The
+implementation can depend on the SoC secure ROM used.
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be "nokia,n900-rom-rng"
+
+- clocks:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: reference to the the RNG interface clock
+
+- clock-names:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "ick"
+
+Example:
+
+	rom_rng: rng {
+		compatible = "nokia,n900-rom-rng";
+		clocks = <&rng_ick>;
+		clock-names = "ick";
+	};
diff --git a/Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.txt b/Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.txt
new file mode 100644
index 000000000000..5a613a4ec780
--- /dev/null
+++ b/Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.txt
@@ -0,0 +1,17 @@
+Exynos True Random Number Generator
+
+Required properties:
+
+- compatible  : Should be "samsung,exynos5250-trng".
+- reg         : Specifies base physical address and size of the registers map.
+- clocks      : Phandle to clock-controller plus clock-specifier pair.
+- clock-names : "secss" as a clock name.
+
+Example:
+
+	rng@10830600 {
+		compatible = "samsung,exynos5250-trng";
+		reg = <0x10830600 0x100>;
+		clocks = <&clock CLK_SSS>;
+		clock-names = "secss";
+	};
diff --git a/Documentation/devicetree/bindings/security/tpm/google,cr50.txt b/Documentation/devicetree/bindings/security/tpm/google,cr50.txt
new file mode 100644
index 000000000000..cd69c2efdd37
--- /dev/null
+++ b/Documentation/devicetree/bindings/security/tpm/google,cr50.txt
@@ -0,0 +1,19 @@
+* H1 Secure Microcontroller with Cr50 Firmware on SPI Bus.
+
+H1 Secure Microcontroller running Cr50 firmware provides several
+functions, including TPM-like functionality. It communicates over
+SPI using the FIFO protocol described in the PTP Spec, section 6.
+
+Required properties:
+- compatible: Should be "google,cr50".
+- spi-max-frequency: Maximum SPI frequency.
+
+Example:
+
+&spi0 {
+	tpm@0 {
+		compatible = "google,cr50";
+		reg = <0>;
+		spi-max-frequency = <800000>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index 967e78c5ec0a..05b3904a995b 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -343,6 +343,8 @@ patternProperties:
     description: Freescale Semiconductor
   "^fujitsu,.*":
     description: Fujitsu Ltd.
+  "^gardena,.*":
+    description: GARDENA GmbH
   "^gateworks,.*":
     description: Gateworks Corporation
   "^gcw,.*":
diff --git a/Documentation/driver-api/libata.rst b/Documentation/driver-api/libata.rst
index 70e180e6b93d..207f0d24de69 100644
--- a/Documentation/driver-api/libata.rst
+++ b/Documentation/driver-api/libata.rst
@@ -250,23 +250,23 @@ High-level taskfile hooks
 
 ::
 
-    void (*qc_prep) (struct ata_queued_cmd *qc);
+    enum ata_completion_errors (*qc_prep) (struct ata_queued_cmd *qc);
     int (*qc_issue) (struct ata_queued_cmd *qc);
 
 
-Higher-level hooks, these two hooks can potentially supercede several of
+Higher-level hooks, these two hooks can potentially supersede several of
 the above taskfile/DMA engine hooks. ``->qc_prep`` is called after the
 buffers have been DMA-mapped, and is typically used to populate the
-hardware's DMA scatter-gather table. Most drivers use the standard
-:c:func:`ata_qc_prep` helper function, but more advanced drivers roll their
-own.
+hardware's DMA scatter-gather table. Some drivers use the standard
+:c:func:`ata_bmdma_qc_prep` and :c:func:`ata_bmdma_dumb_qc_prep` helper
+functions, but more advanced drivers roll their own.
 
 ``->qc_issue`` is used to make a command active, once the hardware and S/G
 tables have been prepared. IDE BMDMA drivers use the helper function
-:c:func:`ata_qc_issue_prot` for taskfile protocol-based dispatch. More
+:c:func:`ata_sff_qc_issue` for taskfile protocol-based dispatch. More
 advanced drivers implement their own ``->qc_issue``.
 
-:c:func:`ata_qc_issue_prot` calls ``->tf_load()``, ``->bmdma_setup()``, and
+:c:func:`ata_sff_qc_issue` calls ``->sff_tf_load()``, ``->bmdma_setup()``, and
 ``->bmdma_start()`` as necessary to initiate a transfer.
 
 Exception and probe handling (EH)
diff --git a/Documentation/driver-api/nvmem.rst b/Documentation/driver-api/nvmem.rst
index d9d958d5c824..287e86819640 100644
--- a/Documentation/driver-api/nvmem.rst
+++ b/Documentation/driver-api/nvmem.rst
@@ -129,6 +129,8 @@ To facilitate such consumers NVMEM framework provides below apis::
   struct nvmem_device *nvmem_device_get(struct device *dev, const char *name);
   struct nvmem_device *devm_nvmem_device_get(struct device *dev,
 					   const char *name);
+  struct nvmem_device *nvmem_device_find(void *data,
+			int (*match)(struct device *dev, const void *data));
   void nvmem_device_put(struct nvmem_device *nvmem);
   int nvmem_device_read(struct nvmem_device *nvmem, unsigned int offset,
 		      size_t bytes, void *buf);
diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst
index 8a0700af9596..471a511c7508 100644
--- a/Documentation/filesystems/fscrypt.rst
+++ b/Documentation/filesystems/fscrypt.rst
@@ -256,13 +256,8 @@ alternative master keys or to support rotating master keys.  Instead,
 the master keys may be wrapped in userspace, e.g. as is done by the
 `fscrypt <https://github.com/google/fscrypt>`_ tool.
 
-Including the inode number in the IVs was considered.  However, it was
-rejected as it would have prevented ext4 filesystems from being
-resized, and by itself still wouldn't have been sufficient to prevent
-the same key from being directly reused for both XTS and CTS-CBC.
-
-DIRECT_KEY and per-mode keys
-----------------------------
+DIRECT_KEY policies
+-------------------
 
 The Adiantum encryption mode (see `Encryption modes and usage`_) is
 suitable for both contents and filenames encryption, and it accepts
@@ -285,6 +280,21 @@ IV.  Moreover:
   key derived using the KDF.  Users may use the same master key for
   other v2 encryption policies.
 
+IV_INO_LBLK_64 policies
+-----------------------
+
+When FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 is set in the fscrypt policy,
+the encryption keys are derived from the master key, encryption mode
+number, and filesystem UUID.  This normally results in all files
+protected by the same master key sharing a single contents encryption
+key and a single filenames encryption key.  To still encrypt different
+files' data differently, inode numbers are included in the IVs.
+Consequently, shrinking the filesystem may not be allowed.
+
+This format is optimized for use with inline encryption hardware
+compliant with the UFS or eMMC standards, which support only 64 IV
+bits per I/O request and may have only a small number of keyslots.
+
 Key identifiers
 ---------------
 
@@ -308,8 +318,9 @@ If unsure, you should use the (AES-256-XTS, AES-256-CTS-CBC) pair.
 
 AES-128-CBC was added only for low-powered embedded devices with
 crypto accelerators such as CAAM or CESA that do not support XTS.  To
-use AES-128-CBC, CONFIG_CRYPTO_SHA256 (or another SHA-256
-implementation) must be enabled so that ESSIV can be used.
+use AES-128-CBC, CONFIG_CRYPTO_ESSIV and CONFIG_CRYPTO_SHA256 (or
+another SHA-256 implementation) must be enabled so that ESSIV can be
+used.
 
 Adiantum is a (primarily) stream cipher-based mode that is fast even
 on CPUs without dedicated crypto instructions.  It's also a true
@@ -341,10 +352,16 @@ a little endian number, except that:
   is encrypted with AES-256 where the AES-256 key is the SHA-256 hash
   of the file's data encryption key.
 
-- In the "direct key" configuration (FSCRYPT_POLICY_FLAG_DIRECT_KEY
-  set in the fscrypt_policy), the file's nonce is also appended to the
-  IV.  Currently this is only allowed with the Adiantum encryption
-  mode.
+- With `DIRECT_KEY policies`_, the file's nonce is appended to the IV.
+  Currently this is only allowed with the Adiantum encryption mode.
+
+- With `IV_INO_LBLK_64 policies`_, the logical block number is limited
+  to 32 bits and is placed in bits 0-31 of the IV.  The inode number
+  (which is also limited to 32 bits) is placed in bits 32-63.
+
+Note that because file logical block numbers are included in the IVs,
+filesystems must enforce that blocks are never shifted around within
+encrypted files, e.g. via "collapse range" or "insert range".
 
 Filenames encryption
 --------------------
@@ -354,10 +371,10 @@ the requirements to retain support for efficient directory lookups and
 filenames of up to 255 bytes, the same IV is used for every filename
 in a directory.
 
-However, each encrypted directory still uses a unique key; or
-alternatively (for the "direct key" configuration) has the file's
-nonce included in the IVs.  Thus, IV reuse is limited to within a
-single directory.
+However, each encrypted directory still uses a unique key, or
+alternatively has the file's nonce (for `DIRECT_KEY policies`_) or
+inode number (for `IV_INO_LBLK_64 policies`_) included in the IVs.
+Thus, IV reuse is limited to within a single directory.
 
 With CTS-CBC, the IV reuse means that when the plaintext filenames
 share a common prefix at least as long as the cipher block size (16
@@ -431,12 +448,15 @@ This structure must be initialized as follows:
   (1) for ``contents_encryption_mode`` and FSCRYPT_MODE_AES_256_CTS
   (4) for ``filenames_encryption_mode``.
 
-- ``flags`` must contain a value from ``<linux/fscrypt.h>`` which
-  identifies the amount of NUL-padding to use when encrypting
-  filenames.  If unsure, use FSCRYPT_POLICY_FLAGS_PAD_32 (0x3).
-  Additionally, if the encryption modes are both
-  FSCRYPT_MODE_ADIANTUM, this can contain
-  FSCRYPT_POLICY_FLAG_DIRECT_KEY; see `DIRECT_KEY and per-mode keys`_.
+- ``flags`` contains optional flags from ``<linux/fscrypt.h>``:
+
+  - FSCRYPT_POLICY_FLAGS_PAD_*: The amount of NUL padding to use when
+    encrypting filenames.  If unsure, use FSCRYPT_POLICY_FLAGS_PAD_32
+    (0x3).
+  - FSCRYPT_POLICY_FLAG_DIRECT_KEY: See `DIRECT_KEY policies`_.
+  - FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64: See `IV_INO_LBLK_64
+    policies`_.  This is mutually exclusive with DIRECT_KEY and is not
+    supported on v1 policies.
 
 - For v2 encryption policies, ``__reserved`` must be zeroed.
 
@@ -1089,7 +1109,7 @@ policy structs (see `Setting an encryption policy`_), except that the
 context structs also contain a nonce.  The nonce is randomly generated
 by the kernel and is used as KDF input or as a tweak to cause
 different files to be encrypted differently; see `Per-file keys`_ and
-`DIRECT_KEY and per-mode keys`_.
+`DIRECT_KEY policies`_.
 
 Data path changes
 -----------------
diff --git a/Documentation/filesystems/fsverity.rst b/Documentation/filesystems/fsverity.rst
index 42a0b6dd9e0b..a95536b6443c 100644
--- a/Documentation/filesystems/fsverity.rst
+++ b/Documentation/filesystems/fsverity.rst
@@ -226,6 +226,14 @@ To do so, check for FS_VERITY_FL (0x00100000) in the returned flags.
 The verity flag is not settable via FS_IOC_SETFLAGS.  You must use
 FS_IOC_ENABLE_VERITY instead, since parameters must be provided.
 
+statx
+-----
+
+Since Linux v5.5, the statx() system call sets STATX_ATTR_VERITY if
+the file has fs-verity enabled.  This can perform better than
+FS_IOC_GETFLAGS and FS_IOC_MEASURE_VERITY because it doesn't require
+opening the file, and opening verity files can be expensive.
+
 Accessing verity files
 ======================
 
@@ -398,7 +406,7 @@ pages have been read into the pagecache.  (See `Verifying data`_.)
 ext4
 ----
 
-ext4 supports fs-verity since Linux TODO and e2fsprogs v1.45.2.
+ext4 supports fs-verity since Linux v5.4 and e2fsprogs v1.45.2.
 
 To create verity files on an ext4 filesystem, the filesystem must have
 been formatted with ``-O verity`` or had ``tune2fs -O verity`` run on
@@ -434,7 +442,7 @@ also only supports extent-based files.
 f2fs
 ----
 
-f2fs supports fs-verity since Linux TODO and f2fs-tools v1.11.0.
+f2fs supports fs-verity since Linux v5.4 and f2fs-tools v1.11.0.
 
 To create verity files on an f2fs filesystem, the filesystem must have
 been formatted with ``-O verity``.
diff --git a/Documentation/ioctl/ioctl-number.rst b/Documentation/ioctl/ioctl-number.rst
index bef79cd4c6b4..4ef86433bd67 100644
--- a/Documentation/ioctl/ioctl-number.rst
+++ b/Documentation/ioctl/ioctl-number.rst
@@ -233,6 +233,7 @@ Code  Seq#    Include File                                           Comments
 'f'   00-0F  fs/ext4/ext4.h                                          conflict!
 'f'   00-0F  linux/fs.h                                              conflict!
 'f'   00-0F  fs/ocfs2/ocfs2_fs.h                                     conflict!
+'f'   13-27  linux/fscrypt.h
 'f'   81-8F  linux/fsverity.h
 'g'   00-0F  linux/usb/gadgetfs.h
 'g'   20-2F  linux/usb/g_printer.h
diff --git a/Documentation/livepatch/index.rst b/Documentation/livepatch/index.rst
index 17674a9e21b2..525944063be7 100644
--- a/Documentation/livepatch/index.rst
+++ b/Documentation/livepatch/index.rst
@@ -12,6 +12,7 @@ Kernel Livepatching
     cumulative-patches
     module-elf-format
     shadow-vars
+    system-state
 
 .. only::  subproject and html
 
diff --git a/Documentation/livepatch/system-state.rst b/Documentation/livepatch/system-state.rst
new file mode 100644
index 000000000000..c6d127c2d9aa
--- /dev/null
+++ b/Documentation/livepatch/system-state.rst
@@ -0,0 +1,167 @@
+====================
+System State Changes
+====================
+
+Some users are really reluctant to reboot a system. This brings the need
+to provide more livepatches and maintain some compatibility between them.
+
+Maintaining more livepatches is much easier with cumulative livepatches.
+Each new livepatch completely replaces any older one. It can keep,
+add, and even remove fixes. And it is typically safe to replace any version
+of the livepatch with any other one thanks to the atomic replace feature.
+
+The problems might come with shadow variables and callbacks. They might
+change the system behavior or state so that it is no longer safe to
+go back and use an older livepatch or the original kernel code. Also
+any new livepatch must be able to detect what changes have already been
+done by the already installed livepatches.
+
+This is where the livepatch system state tracking gets useful. It
+allows to:
+
+  - store data needed to manipulate and restore the system state
+
+  - define compatibility between livepatches using a change id
+    and version
+
+
+1. Livepatch system state API
+=============================
+
+The state of the system might get modified either by several livepatch callbacks
+or by the newly used code. Also it must be possible to find changes done by
+already installed livepatches.
+
+Each modified state is described by struct klp_state, see
+include/linux/livepatch.h.
+
+Each livepatch defines an array of struct klp_states. They mention
+all states that the livepatch modifies.
+
+The livepatch author must define the following two fields for each
+struct klp_state:
+
+  - *id*
+
+    - Non-zero number used to identify the affected system state.
+
+  - *version*
+
+    - Number describing the variant of the system state change that
+      is supported by the given livepatch.
+
+The state can be manipulated using two functions:
+
+  - *klp_get_state(patch, id)*
+
+    - Get struct klp_state associated with the given livepatch
+      and state id.
+
+  - *klp_get_prev_state(id)*
+
+    - Get struct klp_state associated with the given feature id and
+      already installed livepatches.
+
+2. Livepatch compatibility
+==========================
+
+The system state version is used to prevent loading incompatible livepatches.
+The check is done when the livepatch is enabled. The rules are:
+
+  - Any completely new system state modification is allowed.
+
+  - System state modifications with the same or higher version are allowed
+    for already modified system states.
+
+  - Cumulative livepatches must handle all system state modifications from
+    already installed livepatches.
+
+  - Non-cumulative livepatches are allowed to touch already modified
+    system states.
+
+3. Supported scenarios
+======================
+
+Livepatches have their life-cycle and the same is true for the system
+state changes. Every compatible livepatch has to support the following
+scenarios:
+
+  - Modify the system state when the livepatch gets enabled and the state
+    has not been already modified by a livepatches that are being
+    replaced.
+
+  - Take over or update the system state modification when is has already
+    been done by a livepatch that is being replaced.
+
+  - Restore the original state when the livepatch is disabled.
+
+  - Restore the previous state when the transition is reverted.
+    It might be the original system state or the state modification
+    done by livepatches that were being replaced.
+
+  - Remove any already made changes when error occurs and the livepatch
+    cannot get enabled.
+
+4. Expected usage
+=================
+
+System states are usually modified by livepatch callbacks. The expected
+role of each callback is as follows:
+
+*pre_patch()*
+
+  - Allocate *state->data* when necessary. The allocation might fail
+    and *pre_patch()* is the only callback that could stop loading
+    of the livepatch. The allocation is not needed when the data
+    are already provided by previously installed livepatches.
+
+  - Do any other preparatory action that is needed by
+    the new code even before the transition gets finished.
+    For example, initialize *state->data*.
+
+    The system state itself is typically modified in *post_patch()*
+    when the entire system is able to handle it.
+
+  - Clean up its own mess in case of error. It might be done by a custom
+    code or by calling *post_unpatch()* explicitly.
+
+*post_patch()*
+
+  - Copy *state->data* from the previous livepatch when they are
+    compatible.
+
+  - Do the actual system state modification. Eventually allow
+    the new code to use it.
+
+  - Make sure that *state->data* has all necessary information.
+
+  - Free *state->data* from replaces livepatches when they are
+    not longer needed.
+
+*pre_unpatch()*
+
+  - Prevent the code, added by the livepatch, relying on the system
+    state change.
+
+  - Revert the system state modification..
+
+*post_unpatch()*
+
+  - Distinguish transition reverse and livepatch disabling by
+    checking *klp_get_prev_state()*.
+
+  - In case of transition reverse, restore the previous system
+    state. It might mean doing nothing.
+
+  - Remove any not longer needed setting or data.
+
+.. note::
+
+   *pre_unpatch()* typically does symmetric operations to *post_patch()*.
+   Except that it is called only when the livepatch is being disabled.
+   Therefore it does not need to care about any previously installed
+   livepatch.
+
+   *post_unpatch()* typically does symmetric operations to *pre_patch()*.
+   It might be called also during the transition reverse. Therefore it
+   has to handle the state of the previously installed livepatches.
diff --git a/Documentation/virt/kvm/api.txt b/Documentation/virt/kvm/api.txt
index 4833904d32a5..49183add44e7 100644
--- a/Documentation/virt/kvm/api.txt
+++ b/Documentation/virt/kvm/api.txt
@@ -1002,12 +1002,18 @@ Specifying exception.has_esr on a system that does not support it will return
 -EINVAL. Setting anything other than the lower 24bits of exception.serror_esr
 will return -EINVAL.
 
+It is not possible to read back a pending external abort (injected via
+KVM_SET_VCPU_EVENTS or otherwise) because such an exception is always delivered
+directly to the virtual CPU).
+
+
 struct kvm_vcpu_events {
 	struct {
 		__u8 serror_pending;
 		__u8 serror_has_esr;
+		__u8 ext_dabt_pending;
 		/* Align it to 8 bytes */
-		__u8 pad[6];
+		__u8 pad[5];
 		__u64 serror_esr;
 	} exception;
 	__u32 reserved[12];
@@ -1051,9 +1057,23 @@ contain a valid state and shall be written into the VCPU.
 
 ARM/ARM64:
 
+User space may need to inject several types of events to the guest.
+
 Set the pending SError exception state for this VCPU. It is not possible to
 'cancel' an Serror that has been made pending.
 
+If the guest performed an access to I/O memory which could not be handled by
+userspace, for example because of missing instruction syndrome decode
+information or because there is no device mapped at the accessed IPA, then
+userspace can ask the kernel to inject an external abort using the address
+from the exiting fault on the VCPU. It is a programming error to set
+ext_dabt_pending after an exit which was not either KVM_EXIT_MMIO or
+KVM_EXIT_ARM_NISV. This feature is only available if the system supports
+KVM_CAP_ARM_INJECT_EXT_DABT. This is a helper which provides commonality in
+how userspace reports accesses for the above cases to guests, across different
+userspace implementations. Nevertheless, userspace can still emulate all Arm
+exceptions by manipulating individual registers using the KVM_SET_ONE_REG API.
+
 See KVM_GET_VCPU_EVENTS for the data structure.
 
 
@@ -2982,6 +3002,9 @@ can be determined by querying the KVM_CAP_GUEST_DEBUG_HW_BPS and
 KVM_CAP_GUEST_DEBUG_HW_WPS capabilities which return a positive number
 indicating the number of supported registers.
 
+For ppc, the KVM_CAP_PPC_GUEST_DEBUG_SSTEP capability indicates whether
+the single-step debug event (KVM_GUESTDBG_SINGLESTEP) is supported.
+
 When debug events exit the main run loop with the reason
 KVM_EXIT_DEBUG with the kvm_debug_exit_arch part of the kvm_run
 structure containing architecture specific debug information.
@@ -4468,6 +4491,39 @@ Hyper-V SynIC state change. Notification is used to remap SynIC
 event/message pages and to enable/disable SynIC messages/events processing
 in userspace.
 
+		/* KVM_EXIT_ARM_NISV */
+		struct {
+			__u64 esr_iss;
+			__u64 fault_ipa;
+		} arm_nisv;
+
+Used on arm and arm64 systems. If a guest accesses memory not in a memslot,
+KVM will typically return to userspace and ask it to do MMIO emulation on its
+behalf. However, for certain classes of instructions, no instruction decode
+(direction, length of memory access) is provided, and fetching and decoding
+the instruction from the VM is overly complicated to live in the kernel.
+
+Historically, when this situation occurred, KVM would print a warning and kill
+the VM. KVM assumed that if the guest accessed non-memslot memory, it was
+trying to do I/O, which just couldn't be emulated, and the warning message was
+phrased accordingly. However, what happened more often was that a guest bug
+caused access outside the guest memory areas which should lead to a more
+meaningful warning message and an external abort in the guest, if the access
+did not fall within an I/O window.
+
+Userspace implementations can query for KVM_CAP_ARM_NISV_TO_USER, and enable
+this capability at VM creation. Once this is done, these types of errors will
+instead return to userspace with KVM_EXIT_ARM_NISV, with the valid bits from
+the HSR (arm) and ESR_EL2 (arm64) in the esr_iss field, and the faulting IPA
+in the fault_ipa field. Userspace can either fix up the access if it's
+actually an I/O access by decoding the instruction from guest memory (if it's
+very brave) and continue executing the guest, or it can decide to suspend,
+dump, or restart the guest.
+
+Note that KVM does not skip the faulting instruction as it does for
+KVM_EXIT_MMIO, but userspace has to emulate any change to the processing state
+if it decides to decode and emulate the instruction.
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};
diff --git a/Documentation/virt/kvm/arm/pvtime.rst b/Documentation/virt/kvm/arm/pvtime.rst
new file mode 100644
index 000000000000..2357dd2d8655
--- /dev/null
+++ b/Documentation/virt/kvm/arm/pvtime.rst
@@ -0,0 +1,80 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Paravirtualized time support for arm64
+======================================
+
+Arm specification DEN0057/A defines a standard for paravirtualised time
+support for AArch64 guests:
+
+https://developer.arm.com/docs/den0057/a
+
+KVM/arm64 implements the stolen time part of this specification by providing
+some hypervisor service calls to support a paravirtualized guest obtaining a
+view of the amount of time stolen from its execution.
+
+Two new SMCCC compatible hypercalls are defined:
+
+* PV_TIME_FEATURES: 0xC5000020
+* PV_TIME_ST:       0xC5000021
+
+These are only available in the SMC64/HVC64 calling convention as
+paravirtualized time is not available to 32 bit Arm guests. The existence of
+the PV_FEATURES hypercall should be probed using the SMCCC 1.1 ARCH_FEATURES
+mechanism before calling it.
+
+PV_TIME_FEATURES
+    ============= ========    ==========
+    Function ID:  (uint32)    0xC5000020
+    PV_call_id:   (uint32)    The function to query for support.
+                              Currently only PV_TIME_ST is supported.
+    Return value: (int64)     NOT_SUPPORTED (-1) or SUCCESS (0) if the relevant
+                              PV-time feature is supported by the hypervisor.
+    ============= ========    ==========
+
+PV_TIME_ST
+    ============= ========    ==========
+    Function ID:  (uint32)    0xC5000021
+    Return value: (int64)     IPA of the stolen time data structure for this
+                              VCPU. On failure:
+                              NOT_SUPPORTED (-1)
+    ============= ========    ==========
+
+The IPA returned by PV_TIME_ST should be mapped by the guest as normal memory
+with inner and outer write back caching attributes, in the inner shareable
+domain. A total of 16 bytes from the IPA returned are guaranteed to be
+meaningfully filled by the hypervisor (see structure below).
+
+PV_TIME_ST returns the structure for the calling VCPU.
+
+Stolen Time
+-----------
+
+The structure pointed to by the PV_TIME_ST hypercall is as follows:
+
++-------------+-------------+-------------+----------------------------+
+| Field       | Byte Length | Byte Offset | Description                |
++=============+=============+=============+============================+
+| Revision    |      4      |      0      | Must be 0 for version 1.0  |
++-------------+-------------+-------------+----------------------------+
+| Attributes  |      4      |      4      | Must be 0                  |
++-------------+-------------+-------------+----------------------------+
+| Stolen time |      8      |      8      | Stolen time in unsigned    |
+|             |             |             | nanoseconds indicating how |
+|             |             |             | much time this VCPU thread |
+|             |             |             | was involuntarily not      |
+|             |             |             | running on a physical CPU. |
++-------------+-------------+-------------+----------------------------+
+
+All values in the structure are stored little-endian.
+
+The structure will be updated by the hypervisor prior to scheduling a VCPU. It
+will be present within a reserved region of the normal memory given to the
+guest. The guest should not attempt to write into this memory. There is a
+structure per VCPU of the guest.
+
+It is advisable that one or more 64k pages are set aside for the purpose of
+these structures and not used for other purposes, this enables the guest to map
+the region using 64k pages and avoids conflicting attributes with other memory.
+
+For the user space interface see Documentation/virt/kvm/devices/vcpu.txt
+section "3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL".
diff --git a/Documentation/virt/kvm/devices/vcpu.txt b/Documentation/virt/kvm/devices/vcpu.txt
index 2b5dab16c4f2..6f3bd64a05b0 100644
--- a/Documentation/virt/kvm/devices/vcpu.txt
+++ b/Documentation/virt/kvm/devices/vcpu.txt
@@ -60,3 +60,17 @@ time to use the number provided for a given timer, overwriting any previously
 configured values on other VCPUs.  Userspace should configure the interrupt
 numbers on at least one VCPU after creating all VCPUs and before running any
 VCPUs.
+
+3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL
+Architectures: ARM64
+
+3.1 ATTRIBUTE: KVM_ARM_VCPU_PVTIME_IPA
+Parameters: 64-bit base address
+Returns: -ENXIO:  Stolen time not implemented
+         -EEXIST: Base address already set for this VCPU
+         -EINVAL: Base address not 64 byte aligned
+
+Specifies the base address of the stolen time structure for this VCPU. The
+base address must be 64 byte aligned and exist within a valid guest memory
+region. See Documentation/virt/kvm/arm/pvtime.txt for more information
+including the layout of the stolen time structure.
diff --git a/Documentation/virt/kvm/devices/xics.txt b/Documentation/virt/kvm/devices/xics.txt
index 42864935ac5d..423332dda7bc 100644
--- a/Documentation/virt/kvm/devices/xics.txt
+++ b/Documentation/virt/kvm/devices/xics.txt
@@ -3,9 +3,19 @@ XICS interrupt controller
 Device type supported: KVM_DEV_TYPE_XICS
 
 Groups:
-  KVM_DEV_XICS_SOURCES
+  1. KVM_DEV_XICS_GRP_SOURCES
   Attributes: One per interrupt source, indexed by the source number.
 
+  2. KVM_DEV_XICS_GRP_CTRL
+  Attributes:
+    2.1 KVM_DEV_XICS_NR_SERVERS (write only)
+  The kvm_device_attr.addr points to a __u32 value which is the number of
+  interrupt server numbers (ie, highest possible vcpu id plus one).
+  Errors:
+    -EINVAL: Value greater than KVM_MAX_VCPU_ID.
+    -EFAULT: Invalid user pointer for attr->addr.
+    -EBUSY:  A vcpu is already connected to the device.
+
 This device emulates the XICS (eXternal Interrupt Controller
 Specification) defined in PAPR.  The XICS has a set of interrupt
 sources, each identified by a 20-bit source number, and a set of
@@ -38,7 +48,7 @@ least-significant end of the word:
 
 Each source has 64 bits of state that can be read and written using
 the KVM_GET_DEVICE_ATTR and KVM_SET_DEVICE_ATTR ioctls, specifying the
-KVM_DEV_XICS_SOURCES attribute group, with the attribute number being
+KVM_DEV_XICS_GRP_SOURCES attribute group, with the attribute number being
 the interrupt source number.  The 64 bit state word has the following
 bitfields, starting from the least-significant end of the word:
 
diff --git a/Documentation/virt/kvm/devices/xive.txt b/Documentation/virt/kvm/devices/xive.txt
index 9a24a4525253..f5d1d6b5af61 100644
--- a/Documentation/virt/kvm/devices/xive.txt
+++ b/Documentation/virt/kvm/devices/xive.txt
@@ -78,6 +78,14 @@ the legacy interrupt mode, referred as XICS (POWER7/8).
     migrating the VM.
     Errors: none
 
+    1.3 KVM_DEV_XIVE_NR_SERVERS (write only)
+    The kvm_device_attr.addr points to a __u32 value which is the number of
+    interrupt server numbers (ie, highest possible vcpu id plus one).
+    Errors:
+      -EINVAL: Value greater than KVM_MAX_VCPU_ID.
+      -EFAULT: Invalid user pointer for attr->addr.
+      -EBUSY:  A vCPU is already connected to the device.
+
   2. KVM_DEV_XIVE_GRP_SOURCE (write only)
   Initializes a new source in the XIVE device and mask it.
   Attributes:
diff --git a/MAINTAINERS b/MAINTAINERS
index 5e7f5980e75a..8576b2f873aa 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -682,11 +682,11 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/opp/sun50i-nvmem-cpufreq.txt
 F:	drivers/cpufreq/sun50i-cpufreq-nvmem.c
 
-ALLWINNER SECURITY SYSTEM
+ALLWINNER CRYPTO DRIVERS
 M:	Corentin Labbe <clabbe.montjoie@gmail.com>
 L:	linux-crypto@vger.kernel.org
 S:	Maintained
-F:	drivers/crypto/sunxi-ss/
+F:	drivers/crypto/allwinner/
 
 ALLWINNER VPU DRIVER
 M:	Maxime Ripard <mripard@kernel.org>
@@ -1477,6 +1477,14 @@ F:	drivers/soc/amlogic/
 F:	drivers/rtc/rtc-meson*
 N:	meson
 
+ARM/Amlogic Meson SoC Crypto Drivers
+M:	Corentin Labbe <clabbe@baylibre.com>
+L:	linux-crypto@vger.kernel.org
+L:	linux-amlogic@lists.infradead.org
+S:	Maintained
+F:	drivers/crypto/amlogic/
+F:	Documentation/devicetree/bindings/crypto/amlogic*
+
 ARM/Amlogic Meson SoC Sound Drivers
 M:	Jerome Brunet <jbrunet@baylibre.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
@@ -2618,6 +2626,7 @@ S:	Maintained
 F:	arch/arm64/
 X:	arch/arm64/boot/dts/
 F:	Documentation/arm64/
+F:	tools/testing/selftests/arm64/
 
 AS3645A LED FLASH CONTROLLER DRIVER
 M:	Sakari Ailus <sakari.ailus@iki.fi>
@@ -3602,6 +3611,13 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/media/cdns,*.txt
 F:	drivers/media/platform/cadence/cdns-csi2*
 
+CADENCE NAND DRIVER
+M:	Piotr Sroka <piotrs@cadence.com>
+L:	linux-mtd@lists.infradead.org
+S:	Maintained
+F:	drivers/mtd/nand/raw/cadence-nand-controller.c
+F:	Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt
+
 CADET FM/AM RADIO RECEIVER DRIVER
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
@@ -7377,6 +7393,25 @@ F:	include/uapi/linux/if_hippi.h
 F:	net/802/hippi.c
 F:	drivers/net/hippi/
 
+HISILICON SECURITY ENGINE V2 DRIVER (SEC2)
+M:	Zaibo Xu <xuzaibo@huawei.com>
+L:	linux-crypto@vger.kernel.org
+S:	Maintained
+F:	drivers/crypto/hisilicon/sec2/sec_crypto.c
+F:	drivers/crypto/hisilicon/sec2/sec_main.c
+F:	drivers/crypto/hisilicon/sec2/sec_crypto.h
+F:	drivers/crypto/hisilicon/sec2/sec.h
+F:	Documentation/ABI/testing/debugfs-hisi-sec
+
+HISILICON HIGH PERFORMANCE RSA ENGINE DRIVER (HPRE)
+M:	Zaibo Xu <xuzaibo@huawei.com>
+L:	linux-crypto@vger.kernel.org
+S:	Maintained
+F:	drivers/crypto/hisilicon/hpre/hpre_crypto.c
+F:	drivers/crypto/hisilicon/hpre/hpre_main.c
+F:	drivers/crypto/hisilicon/hpre/hpre.h
+F:	Documentation/ABI/testing/debugfs-hisi-hpre
+
 HISILICON NETWORK SUBSYSTEM 3 DRIVER (HNS3)
 M:	Yisen Zhuang <yisen.zhuang@huawei.com>
 M:	Salil Mehta <salil.mehta@huawei.com>
@@ -7385,6 +7420,11 @@ W:	http://www.hisilicon.com
 S:	Maintained
 F:	drivers/net/ethernet/hisilicon/hns3/
 
+HISILICON TRUE RANDOM NUMBER GENERATOR V2 SUPPORT
+M:	Zaibo Xu <xuzaibo@huawei.com>
+S:	Maintained
+F:	drivers/char/hw_random/hisi-trng-v2.c
+
 HISILICON LPC BUS DRIVER
 M:	john.garry@huawei.com
 W:	http://www.hisilicon.com
@@ -7430,7 +7470,6 @@ S:	Maintained
 F:	drivers/crypto/hisilicon/qm.c
 F:	drivers/crypto/hisilicon/qm.h
 F:	drivers/crypto/hisilicon/sgl.c
-F:	drivers/crypto/hisilicon/sgl.h
 F:	drivers/crypto/hisilicon/zip/
 F:	Documentation/ABI/testing/debugfs-hisi-zip
 
@@ -8577,12 +8616,13 @@ F:	include/linux/iova.h
 
 IO_URING
 M:	Jens Axboe <axboe@kernel.dk>
-L:	linux-block@vger.kernel.org
-L:	linux-fsdevel@vger.kernel.org
+L:	io-uring@vger.kernel.org
 T:	git git://git.kernel.dk/linux-block
 T:	git git://git.kernel.dk/liburing
 S:	Maintained
 F:	fs/io_uring.c
+F:	fs/io-wq.c
+F:	fs/io-wq.h
 F:	include/uapi/linux/io_uring.h
 
 IPMI SUBSYSTEM
@@ -8933,6 +8973,17 @@ S:	Maintained
 F:	tools/testing/selftests/
 F:	Documentation/dev-tools/kselftest*
 
+KERNEL UNIT TESTING FRAMEWORK (KUnit)
+M:	Brendan Higgins <brendanhiggins@google.com>
+L:	linux-kselftest@vger.kernel.org
+L:	kunit-dev@googlegroups.com
+W:	https://google.github.io/kunit-docs/third_party/kernel/docs/
+S:	Maintained
+F:	Documentation/dev-tools/kunit/
+F:	include/kunit/
+F:	lib/kunit/
+F:	tools/testing/kunit/
+
 KERNEL USERMODE HELPER
 M:	Luis Chamberlain <mcgrof@kernel.org>
 L:	linux-kernel@vger.kernel.org
@@ -9510,6 +9561,13 @@ F:	Documentation/misc-devices/lis3lv02d.rst
 F:	drivers/misc/lis3lv02d/
 F:	drivers/platform/x86/hp_accel.c
 
+LIST KUNIT TEST
+M:	David Gow <davidgow@google.com>
+L:	linux-kselftest@vger.kernel.org
+L:	kunit-dev@googlegroups.com
+S:	Maintained
+F:	lib/list-test.c
+
 LIVE PATCHING
 M:	Josh Poimboeuf <jpoimboe@redhat.com>
 M:	Jiri Kosina <jikos@kernel.org>
@@ -10550,15 +10608,13 @@ F:	include/linux/vmalloc.h
 F:	mm/
 
 MEMORY TECHNOLOGY DEVICES (MTD)
-M:	David Woodhouse <dwmw2@infradead.org>
-M:	Brian Norris <computersforpeace@gmail.com>
-M:	Marek Vasut <marek.vasut@gmail.com>
 M:	Miquel Raynal <miquel.raynal@bootlin.com>
 M:	Richard Weinberger <richard@nod.at>
 M:	Vignesh Raghavendra <vigneshr@ti.com>
 L:	linux-mtd@lists.infradead.org
 W:	http://www.linux-mtd.infradead.org/
 Q:	http://patchwork.ozlabs.org/project/linux-mtd/list/
+C:	irc://irc.oftc.net/mtd
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mtd/linux.git mtd/fixes
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mtd/linux.git mtd/next
 S:	Maintained
@@ -10890,18 +10946,18 @@ F:	arch/mips/include/asm/mach-loongson32/
 F:	drivers/*/*loongson1*
 F:	drivers/*/*/*loongson1*
 
-MIPS/LOONGSON2 ARCHITECTURE
+MIPS/LOONGSON2EF ARCHITECTURE
 M:	Jiaxun Yang <jiaxun.yang@flygoat.com>
 L:	linux-mips@vger.kernel.org
 S:	Maintained
-F:	arch/mips/loongson64/fuloong-2e/
-F:	arch/mips/loongson64/lemote-2f/
-F:	arch/mips/include/asm/mach-loongson64/
+F:	arch/mips/loongson2ef/
+F:	arch/mips/include/asm/mach-loongson2ef/
 F:	drivers/*/*loongson2*
 F:	drivers/*/*/*loongson2*
 
-MIPS/LOONGSON3 ARCHITECTURE
+MIPS/LOONGSON64 ARCHITECTURE
 M:	Huacai Chen <chenhc@lemote.com>
+M:	Jiaxun Yang <jiaxun.yang@flygoat.com>
 L:	linux-mips@vger.kernel.org
 S:	Maintained
 F:	arch/mips/loongson64/
@@ -11652,6 +11708,7 @@ F:	drivers/nvme/target/fcloop.c
 NVM EXPRESS TARGET DRIVER
 M:	Christoph Hellwig <hch@lst.de>
 M:	Sagi Grimberg <sagi@grimberg.me>
+M:	Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
 L:	linux-nvme@lists.infradead.org
 T:	git://git.infradead.org/nvme.git
 W:	http://git.infradead.org/nvme.git
@@ -12850,6 +12907,7 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux.git
 F:	samples/pidfd/
 F:	tools/testing/selftests/pidfd/
+F:	tools/testing/selftests/clone3/
 K:	(?i)pidfd
 K:	(?i)clone3
 K:	\b(clone_args|kernel_clone_args)\b
@@ -13147,12 +13205,14 @@ F:	Documentation/filesystems/proc.txt
 PROC SYSCTL
 M:	Luis Chamberlain <mcgrof@kernel.org>
 M:	Kees Cook <keescook@chromium.org>
+M:	Iurii Zaikin <yzaikin@google.com>
 L:	linux-kernel@vger.kernel.org
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
 F:	fs/proc/proc_sysctl.c
 F:	include/linux/sysctl.h
 F:	kernel/sysctl.c
+F:	kernel/sysctl-test.c
 F:	tools/testing/selftests/sysctl/
 
 PS3 NETWORK SUPPORT
@@ -15309,7 +15369,6 @@ F:	arch/arm/boot/dts/spear*
 F:	arch/arm/mach-spear/
 
 SPI NOR SUBSYSTEM
-M:	Marek Vasut <marek.vasut@gmail.com>
 M:	Tudor Ambarus <tudor.ambarus@microchip.com>
 L:	linux-mtd@lists.infradead.org
 W:	http://www.linux-mtd.infradead.org/
@@ -16606,10 +16665,9 @@ F:	drivers/media/pci/tw686x/
 
 UBI FILE SYSTEM (UBIFS)
 M:	Richard Weinberger <richard@nod.at>
-M:	Artem Bityutskiy <dedekind1@gmail.com>
-M:	Adrian Hunter <adrian.hunter@intel.com>
 L:	linux-mtd@lists.infradead.org
-T:	git git://git.infradead.org/ubifs-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs.git next
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs.git fixes
 W:	http://www.linux-mtd.infradead.org/doc/ubifs.html
 S:	Supported
 F:	Documentation/filesystems/ubifs.txt
@@ -16724,11 +16782,11 @@ S:	Maintained
 F:	drivers/scsi/ufs/ufs-mediatek*
 
 UNSORTED BLOCK IMAGES (UBI)
-M:	Artem Bityutskiy <dedekind1@gmail.com>
 M:	Richard Weinberger <richard@nod.at>
 W:	http://www.linux-mtd.infradead.org/
 L:	linux-mtd@lists.infradead.org
-T:	git git://git.infradead.org/ubifs-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs.git next
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs.git fixes
 S:	Supported
 F:	drivers/mtd/ubi/
 F:	include/linux/mtd/ubi.h
@@ -17470,6 +17528,18 @@ S:	Maintained
 F:	drivers/net/vrf.c
 F:	Documentation/networking/vrf.txt
 
+VSPRINTF
+M:	Petr Mladek <pmladek@suse.com>
+M:	Steven Rostedt <rostedt@goodmis.org>
+M:	Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+R:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+R:	Rasmus Villemoes <linux@rasmusvillemoes.dk>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pmladek/printk.git
+S:	Maintained
+F:	lib/vsprintf.c
+F:	lib/test_printf.c
+F:	Documentation/core-api/printk-formats.rst
+
 VT1211 HARDWARE MONITOR DRIVER
 M:	Juerg Haefliger <juergh@gmail.com>
 L:	linux-hwmon@vger.kernel.org
diff --git a/Makefile b/Makefile
index 9cd289196267..d4d36c61940b 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc8
+EXTRAVERSION =
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index 4341ccf5c0c4..e7a59d927d78 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -824,7 +824,7 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 	if (unlikely(la_ptr >= alpha_pmu->num_pmcs)) {
 		/* This should never occur! */
 		irq_err_count++;
-		pr_warning("PMI: silly index %ld\n", la_ptr);
+		pr_warn("PMI: silly index %ld\n", la_ptr);
 		wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask);
 		return;
 	}
@@ -847,7 +847,7 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 	if (unlikely(!event)) {
 		/* This should never occur! */
 		irq_err_count++;
-		pr_warning("PMI: No event at index %d!\n", idx);
+		pr_warn("PMI: No event at index %d!\n", idx);
 		wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask);
 		return;
 	}
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 84a5ade1e865..63659880eeb3 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -155,6 +155,12 @@
 		pwms = <&pwm9 0 26316 0>; /* 38000 Hz */
 	};
 
+	rom_rng: rng {
+		compatible = "nokia,n900-rom-rng";
+		clocks = <&rng_ick>;
+		clock-names = "ick";
+	};
+
 	/* controlled (enabled/disabled) directly by bcm2048 and wl1251 */
 	vctcxo: vctcxo {
 		compatible = "fixed-clock";
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 043b0b18bf7e..2674de6ada1f 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -30,7 +30,7 @@ config CRYPTO_SHA1_ARM_NEON
 
 config CRYPTO_SHA1_ARM_CE
 	tristate "SHA1 digest algorithm (ARM v8 Crypto Extensions)"
-	depends on KERNEL_MODE_NEON
+	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
 	select CRYPTO_SHA1_ARM
 	select CRYPTO_HASH
 	help
@@ -39,7 +39,7 @@ config CRYPTO_SHA1_ARM_CE
 
 config CRYPTO_SHA2_ARM_CE
 	tristate "SHA-224/256 digest algorithm (ARM v8 Crypto Extensions)"
-	depends on KERNEL_MODE_NEON
+	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
 	select CRYPTO_SHA256_ARM
 	select CRYPTO_HASH
 	help
@@ -81,7 +81,7 @@ config CRYPTO_AES_ARM
 config CRYPTO_AES_ARM_BS
 	tristate "Bit sliced AES using NEON instructions"
 	depends on KERNEL_MODE_NEON
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_AES
 	select CRYPTO_SIMD
 	help
@@ -96,8 +96,8 @@ config CRYPTO_AES_ARM_BS
 
 config CRYPTO_AES_ARM_CE
 	tristate "Accelerated AES using ARMv8 Crypto Extensions"
-	depends on KERNEL_MODE_NEON
-	select CRYPTO_BLKCIPHER
+	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
+	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_AES
 	select CRYPTO_SIMD
 	help
@@ -106,7 +106,7 @@ config CRYPTO_AES_ARM_CE
 
 config CRYPTO_GHASH_ARM_CE
 	tristate "PMULL-accelerated GHASH using NEON/ARMv8 Crypto Extensions"
-	depends on KERNEL_MODE_NEON
+	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
 	select CRYPTO_HASH
 	select CRYPTO_CRYPTD
 	select CRYPTO_GF128MUL
@@ -118,23 +118,35 @@ config CRYPTO_GHASH_ARM_CE
 
 config CRYPTO_CRCT10DIF_ARM_CE
 	tristate "CRCT10DIF digest algorithm using PMULL instructions"
-	depends on KERNEL_MODE_NEON && CRC_T10DIF
+	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
+	depends on CRC_T10DIF
 	select CRYPTO_HASH
 
 config CRYPTO_CRC32_ARM_CE
 	tristate "CRC32(C) digest algorithm using CRC and/or PMULL instructions"
-	depends on KERNEL_MODE_NEON && CRC32
+	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
+	depends on CRC32
 	select CRYPTO_HASH
 
 config CRYPTO_CHACHA20_NEON
-	tristate "NEON accelerated ChaCha stream cipher algorithms"
-	depends on KERNEL_MODE_NEON
-	select CRYPTO_BLKCIPHER
-	select CRYPTO_CHACHA20
+	tristate "NEON and scalar accelerated ChaCha stream cipher algorithms"
+	select CRYPTO_SKCIPHER
+	select CRYPTO_ARCH_HAVE_LIB_CHACHA
+
+config CRYPTO_POLY1305_ARM
+	tristate "Accelerated scalar and SIMD Poly1305 hash implementations"
+	select CRYPTO_HASH
+	select CRYPTO_ARCH_HAVE_LIB_POLY1305
 
 config CRYPTO_NHPOLY1305_NEON
 	tristate "NEON accelerated NHPoly1305 hash function (for Adiantum)"
 	depends on KERNEL_MODE_NEON
 	select CRYPTO_NHPOLY1305
 
+config CRYPTO_CURVE25519_NEON
+	tristate "NEON accelerated Curve25519 scalar multiplication library"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_LIB_CURVE25519_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_CURVE25519
+
 endif
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 4180f3a13512..b745c17d356f 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -10,34 +10,16 @@ obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
 obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
 obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
 obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
+obj-$(CONFIG_CRYPTO_POLY1305_ARM) += poly1305-arm.o
 obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
+obj-$(CONFIG_CRYPTO_CURVE25519_NEON) += curve25519-neon.o
 
-ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
-ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
-ce-obj-$(CONFIG_CRYPTO_SHA2_ARM_CE) += sha2-arm-ce.o
-ce-obj-$(CONFIG_CRYPTO_GHASH_ARM_CE) += ghash-arm-ce.o
-ce-obj-$(CONFIG_CRYPTO_CRCT10DIF_ARM_CE) += crct10dif-arm-ce.o
-crc-obj-$(CONFIG_CRYPTO_CRC32_ARM_CE) += crc32-arm-ce.o
-
-ifneq ($(crc-obj-y)$(crc-obj-m),)
-ifeq ($(call as-instr,.arch armv8-a\n.arch_extension crc,y,n),y)
-ce-obj-y += $(crc-obj-y)
-ce-obj-m += $(crc-obj-m)
-else
-$(warning These CRC Extensions modules need binutils 2.23 or higher)
-$(warning $(crc-obj-y) $(crc-obj-m))
-endif
-endif
-
-ifneq ($(ce-obj-y)$(ce-obj-m),)
-ifeq ($(call as-instr,.fpu crypto-neon-fp-armv8,y,n),y)
-obj-y += $(ce-obj-y)
-obj-m += $(ce-obj-m)
-else
-$(warning These ARMv8 Crypto Extensions modules need binutils 2.23 or higher)
-$(warning $(ce-obj-y) $(ce-obj-m))
-endif
-endif
+obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
+obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
+obj-$(CONFIG_CRYPTO_SHA2_ARM_CE) += sha2-arm-ce.o
+obj-$(CONFIG_CRYPTO_GHASH_ARM_CE) += ghash-arm-ce.o
+obj-$(CONFIG_CRYPTO_CRCT10DIF_ARM_CE) += crct10dif-arm-ce.o
+obj-$(CONFIG_CRYPTO_CRC32_ARM_CE) += crc32-arm-ce.o
 
 aes-arm-y	:= aes-cipher-core.o aes-cipher-glue.o
 aes-arm-bs-y	:= aes-neonbs-core.o aes-neonbs-glue.o
@@ -53,13 +35,19 @@ aes-arm-ce-y	:= aes-ce-core.o aes-ce-glue.o
 ghash-arm-ce-y	:= ghash-ce-core.o ghash-ce-glue.o
 crct10dif-arm-ce-y	:= crct10dif-ce-core.o crct10dif-ce-glue.o
 crc32-arm-ce-y:= crc32-ce-core.o crc32-ce-glue.o
-chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o
+chacha-neon-y := chacha-scalar-core.o chacha-glue.o
+chacha-neon-$(CONFIG_KERNEL_MODE_NEON) += chacha-neon-core.o
+poly1305-arm-y := poly1305-core.o poly1305-glue.o
 nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
+curve25519-neon-y := curve25519-core.o curve25519-glue.o
 
 ifdef REGENERATE_ARM_CRYPTO
 quiet_cmd_perl = PERL    $@
       cmd_perl = $(PERL) $(<) > $(@)
 
+$(src)/poly1305-core.S_shipped: $(src)/poly1305-armv4.pl
+	$(call cmd,perl)
+
 $(src)/sha256-core.S_shipped: $(src)/sha256-armv4.pl
 	$(call cmd,perl)
 
@@ -67,4 +55,9 @@ $(src)/sha512-core.S_shipped: $(src)/sha512-armv4.pl
 	$(call cmd,perl)
 endif
 
-clean-files += sha256-core.S sha512-core.S
+clean-files += poly1305-core.S sha256-core.S sha512-core.S
+
+# massage the perlasm code a bit so we only get the NEON routine if we need it
+poly1305-aflags-$(CONFIG_CPU_V7) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=5
+poly1305-aflags-$(CONFIG_KERNEL_MODE_NEON) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=7
+AFLAGS_poly1305-core.o += $(poly1305-aflags-y)
diff --git a/arch/arm/crypto/chacha-glue.c b/arch/arm/crypto/chacha-glue.c
new file mode 100644
index 000000000000..3f0c057aa050
--- /dev/null
+++ b/arch/arm/crypto/chacha-glue.c
@@ -0,0 +1,343 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM NEON accelerated ChaCha and XChaCha stream ciphers,
+ * including ChaCha20 (RFC7539)
+ *
+ * Copyright (C) 2016-2019 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2015 Martin Willi
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/chacha.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/cputype.h>
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+asmlinkage void chacha_block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
+				      int nrounds);
+asmlinkage void chacha_4block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
+				       int nrounds);
+asmlinkage void hchacha_block_arm(const u32 *state, u32 *out, int nrounds);
+asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds);
+
+asmlinkage void chacha_doarm(u8 *dst, const u8 *src, unsigned int bytes,
+			     const u32 *state, int nrounds);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(use_neon);
+
+static inline bool neon_usable(void)
+{
+	return static_branch_likely(&use_neon) && crypto_simd_usable();
+}
+
+static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
+			  unsigned int bytes, int nrounds)
+{
+	u8 buf[CHACHA_BLOCK_SIZE];
+
+	while (bytes >= CHACHA_BLOCK_SIZE * 4) {
+		chacha_4block_xor_neon(state, dst, src, nrounds);
+		bytes -= CHACHA_BLOCK_SIZE * 4;
+		src += CHACHA_BLOCK_SIZE * 4;
+		dst += CHACHA_BLOCK_SIZE * 4;
+		state[12] += 4;
+	}
+	while (bytes >= CHACHA_BLOCK_SIZE) {
+		chacha_block_xor_neon(state, dst, src, nrounds);
+		bytes -= CHACHA_BLOCK_SIZE;
+		src += CHACHA_BLOCK_SIZE;
+		dst += CHACHA_BLOCK_SIZE;
+		state[12]++;
+	}
+	if (bytes) {
+		memcpy(buf, src, bytes);
+		chacha_block_xor_neon(state, buf, buf, nrounds);
+		memcpy(dst, buf, bytes);
+	}
+}
+
+void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
+{
+	if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon_usable()) {
+		hchacha_block_arm(state, stream, nrounds);
+	} else {
+		kernel_neon_begin();
+		hchacha_block_neon(state, stream, nrounds);
+		kernel_neon_end();
+	}
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
+{
+	chacha_init_generic(state, key, iv);
+}
+EXPORT_SYMBOL(chacha_init_arch);
+
+void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
+		       int nrounds)
+{
+	if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon_usable() ||
+	    bytes <= CHACHA_BLOCK_SIZE) {
+		chacha_doarm(dst, src, bytes, state, nrounds);
+		state[12] += DIV_ROUND_UP(bytes, CHACHA_BLOCK_SIZE);
+		return;
+	}
+
+	kernel_neon_begin();
+	chacha_doneon(state, dst, src, bytes, nrounds);
+	kernel_neon_end();
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+static int chacha_stream_xor(struct skcipher_request *req,
+			     const struct chacha_ctx *ctx, const u8 *iv,
+			     bool neon)
+{
+	struct skcipher_walk walk;
+	u32 state[16];
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	chacha_init_generic(state, ctx->key, iv);
+
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
+
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, walk.stride);
+
+		if (!neon) {
+			chacha_doarm(walk.dst.virt.addr, walk.src.virt.addr,
+				     nbytes, state, ctx->nrounds);
+			state[12] += DIV_ROUND_UP(nbytes, CHACHA_BLOCK_SIZE);
+		} else {
+			kernel_neon_begin();
+			chacha_doneon(state, walk.dst.virt.addr,
+				      walk.src.virt.addr, nbytes, ctx->nrounds);
+			kernel_neon_end();
+		}
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+	}
+
+	return err;
+}
+
+static int do_chacha(struct skcipher_request *req, bool neon)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	return chacha_stream_xor(req, ctx, req->iv, neon);
+}
+
+static int chacha_arm(struct skcipher_request *req)
+{
+	return do_chacha(req, false);
+}
+
+static int chacha_neon(struct skcipher_request *req)
+{
+	return do_chacha(req, neon_usable());
+}
+
+static int do_xchacha(struct skcipher_request *req, bool neon)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct chacha_ctx subctx;
+	u32 state[16];
+	u8 real_iv[16];
+
+	chacha_init_generic(state, ctx->key, req->iv);
+
+	if (!neon) {
+		hchacha_block_arm(state, subctx.key, ctx->nrounds);
+	} else {
+		kernel_neon_begin();
+		hchacha_block_neon(state, subctx.key, ctx->nrounds);
+		kernel_neon_end();
+	}
+	subctx.nrounds = ctx->nrounds;
+
+	memcpy(&real_iv[0], req->iv + 24, 8);
+	memcpy(&real_iv[8], req->iv + 16, 8);
+	return chacha_stream_xor(req, &subctx, real_iv, neon);
+}
+
+static int xchacha_arm(struct skcipher_request *req)
+{
+	return do_xchacha(req, false);
+}
+
+static int xchacha_neon(struct skcipher_request *req)
+{
+	return do_xchacha(req, neon_usable());
+}
+
+static struct skcipher_alg arm_algs[] = {
+	{
+		.base.cra_name		= "chacha20",
+		.base.cra_driver_name	= "chacha20-arm",
+		.base.cra_priority	= 200,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= CHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.setkey			= chacha20_setkey,
+		.encrypt		= chacha_arm,
+		.decrypt		= chacha_arm,
+	}, {
+		.base.cra_name		= "xchacha20",
+		.base.cra_driver_name	= "xchacha20-arm",
+		.base.cra_priority	= 200,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= XCHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.setkey			= chacha20_setkey,
+		.encrypt		= xchacha_arm,
+		.decrypt		= xchacha_arm,
+	}, {
+		.base.cra_name		= "xchacha12",
+		.base.cra_driver_name	= "xchacha12-arm",
+		.base.cra_priority	= 200,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= XCHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.setkey			= chacha12_setkey,
+		.encrypt		= xchacha_arm,
+		.decrypt		= xchacha_arm,
+	},
+};
+
+static struct skcipher_alg neon_algs[] = {
+	{
+		.base.cra_name		= "chacha20",
+		.base.cra_driver_name	= "chacha20-neon",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= CHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.walksize		= 4 * CHACHA_BLOCK_SIZE,
+		.setkey			= chacha20_setkey,
+		.encrypt		= chacha_neon,
+		.decrypt		= chacha_neon,
+	}, {
+		.base.cra_name		= "xchacha20",
+		.base.cra_driver_name	= "xchacha20-neon",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= XCHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.walksize		= 4 * CHACHA_BLOCK_SIZE,
+		.setkey			= chacha20_setkey,
+		.encrypt		= xchacha_neon,
+		.decrypt		= xchacha_neon,
+	}, {
+		.base.cra_name		= "xchacha12",
+		.base.cra_driver_name	= "xchacha12-neon",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= XCHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.walksize		= 4 * CHACHA_BLOCK_SIZE,
+		.setkey			= chacha12_setkey,
+		.encrypt		= xchacha_neon,
+		.decrypt		= xchacha_neon,
+	}
+};
+
+static int __init chacha_simd_mod_init(void)
+{
+	int err;
+
+	err = crypto_register_skciphers(arm_algs, ARRAY_SIZE(arm_algs));
+	if (err)
+		return err;
+
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_NEON)) {
+		int i;
+
+		switch (read_cpuid_part()) {
+		case ARM_CPU_PART_CORTEX_A7:
+		case ARM_CPU_PART_CORTEX_A5:
+			/*
+			 * The Cortex-A7 and Cortex-A5 do not perform well with
+			 * the NEON implementation but do incredibly with the
+			 * scalar one and use less power.
+			 */
+			for (i = 0; i < ARRAY_SIZE(neon_algs); i++)
+				neon_algs[i].base.cra_priority = 0;
+			break;
+		default:
+			static_branch_enable(&use_neon);
+		}
+
+		err = crypto_register_skciphers(neon_algs, ARRAY_SIZE(neon_algs));
+		if (err)
+			crypto_unregister_skciphers(arm_algs, ARRAY_SIZE(arm_algs));
+	}
+	return err;
+}
+
+static void __exit chacha_simd_mod_fini(void)
+{
+	crypto_unregister_skciphers(arm_algs, ARRAY_SIZE(arm_algs));
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_NEON))
+		crypto_unregister_skciphers(neon_algs, ARRAY_SIZE(neon_algs));
+}
+
+module_init(chacha_simd_mod_init);
+module_exit(chacha_simd_mod_fini);
+
+MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (scalar and NEON accelerated)");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("chacha20");
+MODULE_ALIAS_CRYPTO("chacha20-arm");
+MODULE_ALIAS_CRYPTO("xchacha20");
+MODULE_ALIAS_CRYPTO("xchacha20-arm");
+MODULE_ALIAS_CRYPTO("xchacha12");
+MODULE_ALIAS_CRYPTO("xchacha12-arm");
+#ifdef CONFIG_KERNEL_MODE_NEON
+MODULE_ALIAS_CRYPTO("chacha20-neon");
+MODULE_ALIAS_CRYPTO("xchacha20-neon");
+MODULE_ALIAS_CRYPTO("xchacha12-neon");
+#endif
diff --git a/arch/arm/crypto/chacha-neon-glue.c b/arch/arm/crypto/chacha-neon-glue.c
deleted file mode 100644
index a8e9b534c8da..000000000000
--- a/arch/arm/crypto/chacha-neon-glue.c
+++ /dev/null
@@ -1,202 +0,0 @@
-/*
- * ARM NEON accelerated ChaCha and XChaCha stream ciphers,
- * including ChaCha20 (RFC7539)
- *
- * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Based on:
- * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
- *
- * Copyright (C) 2015 Martin Willi
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <crypto/algapi.h>
-#include <crypto/chacha.h>
-#include <crypto/internal/simd.h>
-#include <crypto/internal/skcipher.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-
-asmlinkage void chacha_block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
-				      int nrounds);
-asmlinkage void chacha_4block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
-				       int nrounds);
-asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds);
-
-static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
-			  unsigned int bytes, int nrounds)
-{
-	u8 buf[CHACHA_BLOCK_SIZE];
-
-	while (bytes >= CHACHA_BLOCK_SIZE * 4) {
-		chacha_4block_xor_neon(state, dst, src, nrounds);
-		bytes -= CHACHA_BLOCK_SIZE * 4;
-		src += CHACHA_BLOCK_SIZE * 4;
-		dst += CHACHA_BLOCK_SIZE * 4;
-		state[12] += 4;
-	}
-	while (bytes >= CHACHA_BLOCK_SIZE) {
-		chacha_block_xor_neon(state, dst, src, nrounds);
-		bytes -= CHACHA_BLOCK_SIZE;
-		src += CHACHA_BLOCK_SIZE;
-		dst += CHACHA_BLOCK_SIZE;
-		state[12]++;
-	}
-	if (bytes) {
-		memcpy(buf, src, bytes);
-		chacha_block_xor_neon(state, buf, buf, nrounds);
-		memcpy(dst, buf, bytes);
-	}
-}
-
-static int chacha_neon_stream_xor(struct skcipher_request *req,
-				  const struct chacha_ctx *ctx, const u8 *iv)
-{
-	struct skcipher_walk walk;
-	u32 state[16];
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	crypto_chacha_init(state, ctx, iv);
-
-	while (walk.nbytes > 0) {
-		unsigned int nbytes = walk.nbytes;
-
-		if (nbytes < walk.total)
-			nbytes = round_down(nbytes, walk.stride);
-
-		kernel_neon_begin();
-		chacha_doneon(state, walk.dst.virt.addr, walk.src.virt.addr,
-			      nbytes, ctx->nrounds);
-		kernel_neon_end();
-		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
-	}
-
-	return err;
-}
-
-static int chacha_neon(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
-		return crypto_chacha_crypt(req);
-
-	return chacha_neon_stream_xor(req, ctx, req->iv);
-}
-
-static int xchacha_neon(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct chacha_ctx subctx;
-	u32 state[16];
-	u8 real_iv[16];
-
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
-		return crypto_xchacha_crypt(req);
-
-	crypto_chacha_init(state, ctx, req->iv);
-
-	kernel_neon_begin();
-	hchacha_block_neon(state, subctx.key, ctx->nrounds);
-	kernel_neon_end();
-	subctx.nrounds = ctx->nrounds;
-
-	memcpy(&real_iv[0], req->iv + 24, 8);
-	memcpy(&real_iv[8], req->iv + 16, 8);
-	return chacha_neon_stream_xor(req, &subctx, real_iv);
-}
-
-static struct skcipher_alg algs[] = {
-	{
-		.base.cra_name		= "chacha20",
-		.base.cra_driver_name	= "chacha20-neon",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= CHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.walksize		= 4 * CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
-		.encrypt		= chacha_neon,
-		.decrypt		= chacha_neon,
-	}, {
-		.base.cra_name		= "xchacha20",
-		.base.cra_driver_name	= "xchacha20-neon",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= XCHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.walksize		= 4 * CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
-		.encrypt		= xchacha_neon,
-		.decrypt		= xchacha_neon,
-	}, {
-		.base.cra_name		= "xchacha12",
-		.base.cra_driver_name	= "xchacha12-neon",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= XCHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.walksize		= 4 * CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha12_setkey,
-		.encrypt		= xchacha_neon,
-		.decrypt		= xchacha_neon,
-	}
-};
-
-static int __init chacha_simd_mod_init(void)
-{
-	if (!(elf_hwcap & HWCAP_NEON))
-		return -ENODEV;
-
-	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
-}
-
-static void __exit chacha_simd_mod_fini(void)
-{
-	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
-}
-
-module_init(chacha_simd_mod_init);
-module_exit(chacha_simd_mod_fini);
-
-MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (NEON accelerated)");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("chacha20");
-MODULE_ALIAS_CRYPTO("chacha20-neon");
-MODULE_ALIAS_CRYPTO("xchacha20");
-MODULE_ALIAS_CRYPTO("xchacha20-neon");
-MODULE_ALIAS_CRYPTO("xchacha12");
-MODULE_ALIAS_CRYPTO("xchacha12-neon");
diff --git a/arch/arm/crypto/chacha-scalar-core.S b/arch/arm/crypto/chacha-scalar-core.S
new file mode 100644
index 000000000000..2985b80a45b5
--- /dev/null
+++ b/arch/arm/crypto/chacha-scalar-core.S
@@ -0,0 +1,460 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Google, Inc.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * Design notes:
+ *
+ * 16 registers would be needed to hold the state matrix, but only 14 are
+ * available because 'sp' and 'pc' cannot be used.  So we spill the elements
+ * (x8, x9) to the stack and swap them out with (x10, x11).  This adds one
+ * 'ldrd' and one 'strd' instruction per round.
+ *
+ * All rotates are performed using the implicit rotate operand accepted by the
+ * 'add' and 'eor' instructions.  This is faster than using explicit rotate
+ * instructions.  To make this work, we allow the values in the second and last
+ * rows of the ChaCha state matrix (rows 'b' and 'd') to temporarily have the
+ * wrong rotation amount.  The rotation amount is then fixed up just in time
+ * when the values are used.  'brot' is the number of bits the values in row 'b'
+ * need to be rotated right to arrive at the correct values, and 'drot'
+ * similarly for row 'd'.  (brot, drot) start out as (0, 0) but we make it such
+ * that they end up as (25, 24) after every round.
+ */
+
+	// ChaCha state registers
+	X0	.req	r0
+	X1	.req	r1
+	X2	.req	r2
+	X3	.req	r3
+	X4	.req	r4
+	X5	.req	r5
+	X6	.req	r6
+	X7	.req	r7
+	X8_X10	.req	r8	// shared by x8 and x10
+	X9_X11	.req	r9	// shared by x9 and x11
+	X12	.req	r10
+	X13	.req	r11
+	X14	.req	r12
+	X15	.req	r14
+
+.macro __rev		out, in,  t0, t1, t2
+.if __LINUX_ARM_ARCH__ >= 6
+	rev		\out, \in
+.else
+	lsl		\t0, \in, #24
+	and		\t1, \in, #0xff00
+	and		\t2, \in, #0xff0000
+	orr		\out, \t0, \in, lsr #24
+	orr		\out, \out, \t1, lsl #8
+	orr		\out, \out, \t2, lsr #8
+.endif
+.endm
+
+.macro _le32_bswap	x,  t0, t1, t2
+#ifdef __ARMEB__
+	__rev		\x, \x,  \t0, \t1, \t2
+#endif
+.endm
+
+.macro _le32_bswap_4x	a, b, c, d,  t0, t1, t2
+	_le32_bswap	\a,  \t0, \t1, \t2
+	_le32_bswap	\b,  \t0, \t1, \t2
+	_le32_bswap	\c,  \t0, \t1, \t2
+	_le32_bswap	\d,  \t0, \t1, \t2
+.endm
+
+.macro __ldrd		a, b, src, offset
+#if __LINUX_ARM_ARCH__ >= 6
+	ldrd		\a, \b, [\src, #\offset]
+#else
+	ldr		\a, [\src, #\offset]
+	ldr		\b, [\src, #\offset + 4]
+#endif
+.endm
+
+.macro __strd		a, b, dst, offset
+#if __LINUX_ARM_ARCH__ >= 6
+	strd		\a, \b, [\dst, #\offset]
+#else
+	str		\a, [\dst, #\offset]
+	str		\b, [\dst, #\offset + 4]
+#endif
+.endm
+
+.macro _halfround	a1, b1, c1, d1,  a2, b2, c2, d2
+
+	// a += b; d ^= a; d = rol(d, 16);
+	add		\a1, \a1, \b1, ror #brot
+	add		\a2, \a2, \b2, ror #brot
+	eor		\d1, \a1, \d1, ror #drot
+	eor		\d2, \a2, \d2, ror #drot
+	// drot == 32 - 16 == 16
+
+	// c += d; b ^= c; b = rol(b, 12);
+	add		\c1, \c1, \d1, ror #16
+	add		\c2, \c2, \d2, ror #16
+	eor		\b1, \c1, \b1, ror #brot
+	eor		\b2, \c2, \b2, ror #brot
+	// brot == 32 - 12 == 20
+
+	// a += b; d ^= a; d = rol(d, 8);
+	add		\a1, \a1, \b1, ror #20
+	add		\a2, \a2, \b2, ror #20
+	eor		\d1, \a1, \d1, ror #16
+	eor		\d2, \a2, \d2, ror #16
+	// drot == 32 - 8 == 24
+
+	// c += d; b ^= c; b = rol(b, 7);
+	add		\c1, \c1, \d1, ror #24
+	add		\c2, \c2, \d2, ror #24
+	eor		\b1, \c1, \b1, ror #20
+	eor		\b2, \c2, \b2, ror #20
+	// brot == 32 - 7 == 25
+.endm
+
+.macro _doubleround
+
+	// column round
+
+	// quarterrounds: (x0, x4, x8, x12) and (x1, x5, x9, x13)
+	_halfround	X0, X4, X8_X10, X12,  X1, X5, X9_X11, X13
+
+	// save (x8, x9); restore (x10, x11)
+	__strd		X8_X10, X9_X11, sp, 0
+	__ldrd		X8_X10, X9_X11, sp, 8
+
+	// quarterrounds: (x2, x6, x10, x14) and (x3, x7, x11, x15)
+	_halfround	X2, X6, X8_X10, X14,  X3, X7, X9_X11, X15
+
+	.set brot, 25
+	.set drot, 24
+
+	// diagonal round
+
+	// quarterrounds: (x0, x5, x10, x15) and (x1, x6, x11, x12)
+	_halfround	X0, X5, X8_X10, X15,  X1, X6, X9_X11, X12
+
+	// save (x10, x11); restore (x8, x9)
+	__strd		X8_X10, X9_X11, sp, 8
+	__ldrd		X8_X10, X9_X11, sp, 0
+
+	// quarterrounds: (x2, x7, x8, x13) and (x3, x4, x9, x14)
+	_halfround	X2, X7, X8_X10, X13,  X3, X4, X9_X11, X14
+.endm
+
+.macro _chacha_permute	nrounds
+	.set brot, 0
+	.set drot, 0
+	.rept \nrounds / 2
+	 _doubleround
+	.endr
+.endm
+
+.macro _chacha		nrounds
+
+.Lnext_block\@:
+	// Stack: unused0-unused1 x10-x11 x0-x15 OUT IN LEN
+	// Registers contain x0-x9,x12-x15.
+
+	// Do the core ChaCha permutation to update x0-x15.
+	_chacha_permute	\nrounds
+
+	add		sp, #8
+	// Stack: x10-x11 orig_x0-orig_x15 OUT IN LEN
+	// Registers contain x0-x9,x12-x15.
+	// x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
+
+	// Free up some registers (r8-r12,r14) by pushing (x8-x9,x12-x15).
+	push		{X8_X10, X9_X11, X12, X13, X14, X15}
+
+	// Load (OUT, IN, LEN).
+	ldr		r14, [sp, #96]
+	ldr		r12, [sp, #100]
+	ldr		r11, [sp, #104]
+
+	orr		r10, r14, r12
+
+	// Use slow path if fewer than 64 bytes remain.
+	cmp		r11, #64
+	blt		.Lxor_slowpath\@
+
+	// Use slow path if IN and/or OUT isn't 4-byte aligned.  Needed even on
+	// ARMv6+, since ldmia and stmia (used below) still require alignment.
+	tst		r10, #3
+	bne		.Lxor_slowpath\@
+
+	// Fast path: XOR 64 bytes of aligned data.
+
+	// Stack: x8-x9 x12-x15 x10-x11 orig_x0-orig_x15 OUT IN LEN
+	// Registers: r0-r7 are x0-x7; r8-r11 are free; r12 is IN; r14 is OUT.
+	// x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
+
+	// x0-x3
+	__ldrd		r8, r9, sp, 32
+	__ldrd		r10, r11, sp, 40
+	add		X0, X0, r8
+	add		X1, X1, r9
+	add		X2, X2, r10
+	add		X3, X3, r11
+	_le32_bswap_4x	X0, X1, X2, X3,  r8, r9, r10
+	ldmia		r12!, {r8-r11}
+	eor		X0, X0, r8
+	eor		X1, X1, r9
+	eor		X2, X2, r10
+	eor		X3, X3, r11
+	stmia		r14!, {X0-X3}
+
+	// x4-x7
+	__ldrd		r8, r9, sp, 48
+	__ldrd		r10, r11, sp, 56
+	add		X4, r8, X4, ror #brot
+	add		X5, r9, X5, ror #brot
+	ldmia		r12!, {X0-X3}
+	add		X6, r10, X6, ror #brot
+	add		X7, r11, X7, ror #brot
+	_le32_bswap_4x	X4, X5, X6, X7,  r8, r9, r10
+	eor		X4, X4, X0
+	eor		X5, X5, X1
+	eor		X6, X6, X2
+	eor		X7, X7, X3
+	stmia		r14!, {X4-X7}
+
+	// x8-x15
+	pop		{r0-r7}			// (x8-x9,x12-x15,x10-x11)
+	__ldrd		r8, r9, sp, 32
+	__ldrd		r10, r11, sp, 40
+	add		r0, r0, r8		// x8
+	add		r1, r1, r9		// x9
+	add		r6, r6, r10		// x10
+	add		r7, r7, r11		// x11
+	_le32_bswap_4x	r0, r1, r6, r7,  r8, r9, r10
+	ldmia		r12!, {r8-r11}
+	eor		r0, r0, r8		// x8
+	eor		r1, r1, r9		// x9
+	eor		r6, r6, r10		// x10
+	eor		r7, r7, r11		// x11
+	stmia		r14!, {r0,r1,r6,r7}
+	ldmia		r12!, {r0,r1,r6,r7}
+	__ldrd		r8, r9, sp, 48
+	__ldrd		r10, r11, sp, 56
+	add		r2, r8, r2, ror #drot	// x12
+	add		r3, r9, r3, ror #drot	// x13
+	add		r4, r10, r4, ror #drot	// x14
+	add		r5, r11, r5, ror #drot	// x15
+	_le32_bswap_4x	r2, r3, r4, r5,  r9, r10, r11
+	  ldr		r9, [sp, #72]		// load LEN
+	eor		r2, r2, r0		// x12
+	eor		r3, r3, r1		// x13
+	eor		r4, r4, r6		// x14
+	eor		r5, r5, r7		// x15
+	  subs		r9, #64			// decrement and check LEN
+	stmia		r14!, {r2-r5}
+
+	beq		.Ldone\@
+
+.Lprepare_for_next_block\@:
+
+	// Stack: x0-x15 OUT IN LEN
+
+	// Increment block counter (x12)
+	add		r8, #1
+
+	// Store updated (OUT, IN, LEN)
+	str		r14, [sp, #64]
+	str		r12, [sp, #68]
+	str		r9, [sp, #72]
+
+	  mov		r14, sp
+
+	// Store updated block counter (x12)
+	str		r8, [sp, #48]
+
+	  sub		sp, #16
+
+	// Reload state and do next block
+	ldmia		r14!, {r0-r11}		// load x0-x11
+	__strd		r10, r11, sp, 8		// store x10-x11 before state
+	ldmia		r14, {r10-r12,r14}	// load x12-x15
+	b		.Lnext_block\@
+
+.Lxor_slowpath\@:
+	// Slow path: < 64 bytes remaining, or unaligned input or output buffer.
+	// We handle it by storing the 64 bytes of keystream to the stack, then
+	// XOR-ing the needed portion with the data.
+
+	// Allocate keystream buffer
+	sub		sp, #64
+	mov		r14, sp
+
+	// Stack: ks0-ks15 x8-x9 x12-x15 x10-x11 orig_x0-orig_x15 OUT IN LEN
+	// Registers: r0-r7 are x0-x7; r8-r11 are free; r12 is IN; r14 is &ks0.
+	// x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
+
+	// Save keystream for x0-x3
+	__ldrd		r8, r9, sp, 96
+	__ldrd		r10, r11, sp, 104
+	add		X0, X0, r8
+	add		X1, X1, r9
+	add		X2, X2, r10
+	add		X3, X3, r11
+	_le32_bswap_4x	X0, X1, X2, X3,  r8, r9, r10
+	stmia		r14!, {X0-X3}
+
+	// Save keystream for x4-x7
+	__ldrd		r8, r9, sp, 112
+	__ldrd		r10, r11, sp, 120
+	add		X4, r8, X4, ror #brot
+	add		X5, r9, X5, ror #brot
+	add		X6, r10, X6, ror #brot
+	add		X7, r11, X7, ror #brot
+	_le32_bswap_4x	X4, X5, X6, X7,  r8, r9, r10
+	  add		r8, sp, #64
+	stmia		r14!, {X4-X7}
+
+	// Save keystream for x8-x15
+	ldm		r8, {r0-r7}		// (x8-x9,x12-x15,x10-x11)
+	__ldrd		r8, r9, sp, 128
+	__ldrd		r10, r11, sp, 136
+	add		r0, r0, r8		// x8
+	add		r1, r1, r9		// x9
+	add		r6, r6, r10		// x10
+	add		r7, r7, r11		// x11
+	_le32_bswap_4x	r0, r1, r6, r7,  r8, r9, r10
+	stmia		r14!, {r0,r1,r6,r7}
+	__ldrd		r8, r9, sp, 144
+	__ldrd		r10, r11, sp, 152
+	add		r2, r8, r2, ror #drot	// x12
+	add		r3, r9, r3, ror #drot	// x13
+	add		r4, r10, r4, ror #drot	// x14
+	add		r5, r11, r5, ror #drot	// x15
+	_le32_bswap_4x	r2, r3, r4, r5,  r9, r10, r11
+	stmia		r14, {r2-r5}
+
+	// Stack: ks0-ks15 unused0-unused7 x0-x15 OUT IN LEN
+	// Registers: r8 is block counter, r12 is IN.
+
+	ldr		r9, [sp, #168]		// LEN
+	ldr		r14, [sp, #160]		// OUT
+	cmp		r9, #64
+	  mov		r0, sp
+	movle		r1, r9
+	movgt		r1, #64
+	// r1 is number of bytes to XOR, in range [1, 64]
+
+.if __LINUX_ARM_ARCH__ < 6
+	orr		r2, r12, r14
+	tst		r2, #3			// IN or OUT misaligned?
+	bne		.Lxor_next_byte\@
+.endif
+
+	// XOR a word at a time
+.rept 16
+	subs		r1, #4
+	blt		.Lxor_words_done\@
+	ldr		r2, [r12], #4
+	ldr		r3, [r0], #4
+	eor		r2, r2, r3
+	str		r2, [r14], #4
+.endr
+	b		.Lxor_slowpath_done\@
+.Lxor_words_done\@:
+	ands		r1, r1, #3
+	beq		.Lxor_slowpath_done\@
+
+	// XOR a byte at a time
+.Lxor_next_byte\@:
+	ldrb		r2, [r12], #1
+	ldrb		r3, [r0], #1
+	eor		r2, r2, r3
+	strb		r2, [r14], #1
+	subs		r1, #1
+	bne		.Lxor_next_byte\@
+
+.Lxor_slowpath_done\@:
+	subs		r9, #64
+	add		sp, #96
+	bgt		.Lprepare_for_next_block\@
+
+.Ldone\@:
+.endm	// _chacha
+
+/*
+ * void chacha_doarm(u8 *dst, const u8 *src, unsigned int bytes,
+ *		     const u32 *state, int nrounds);
+ */
+ENTRY(chacha_doarm)
+	cmp		r2, #0			// len == 0?
+	reteq		lr
+
+	ldr		ip, [sp]
+	cmp		ip, #12
+
+	push		{r0-r2,r4-r11,lr}
+
+	// Push state x0-x15 onto stack.
+	// Also store an extra copy of x10-x11 just before the state.
+
+	add		X12, r3, #48
+	ldm		X12, {X12,X13,X14,X15}
+	push		{X12,X13,X14,X15}
+	sub		sp, sp, #64
+
+	__ldrd		X8_X10, X9_X11, r3, 40
+	__strd		X8_X10, X9_X11, sp, 8
+	__strd		X8_X10, X9_X11, sp, 56
+	ldm		r3, {X0-X9_X11}
+	__strd		X0, X1, sp, 16
+	__strd		X2, X3, sp, 24
+	__strd		X4, X5, sp, 32
+	__strd		X6, X7, sp, 40
+	__strd		X8_X10, X9_X11, sp, 48
+
+	beq		1f
+	_chacha		20
+
+0:	add		sp, #76
+	pop		{r4-r11, pc}
+
+1:	_chacha		12
+	b		0b
+ENDPROC(chacha_doarm)
+
+/*
+ * void hchacha_block_arm(const u32 state[16], u32 out[8], int nrounds);
+ */
+ENTRY(hchacha_block_arm)
+	push		{r1,r4-r11,lr}
+
+	cmp		r2, #12			// ChaCha12 ?
+
+	mov		r14, r0
+	ldmia		r14!, {r0-r11}		// load x0-x11
+	push		{r10-r11}		// store x10-x11 to stack
+	ldm		r14, {r10-r12,r14}	// load x12-x15
+	sub		sp, #8
+
+	beq		1f
+	_chacha_permute	20
+
+	// Skip over (unused0-unused1, x10-x11)
+0:	add		sp, #16
+
+	// Fix up rotations of x12-x15
+	ror		X12, X12, #drot
+	ror		X13, X13, #drot
+	  pop		{r4}			// load 'out'
+	ror		X14, X14, #drot
+	ror		X15, X15, #drot
+
+	// Store (x0-x3,x12-x15) to 'out'
+	stm		r4, {X0,X1,X2,X3,X12,X13,X14,X15}
+
+	pop		{r4-r11,pc}
+
+1:	_chacha_permute	12
+	b		0b
+ENDPROC(hchacha_block_arm)
diff --git a/arch/arm/crypto/crct10dif-ce-core.S b/arch/arm/crypto/crct10dif-ce-core.S
index 86be258a803f..46c02c518a30 100644
--- a/arch/arm/crypto/crct10dif-ce-core.S
+++ b/arch/arm/crypto/crct10dif-ce-core.S
@@ -72,7 +72,7 @@
 #endif
 
 	.text
-	.arch		armv7-a
+	.arch		armv8-a
 	.fpu		crypto-neon-fp-armv8
 
 	init_crc	.req	r0
diff --git a/arch/arm/crypto/curve25519-core.S b/arch/arm/crypto/curve25519-core.S
new file mode 100644
index 000000000000..be18af52e7dc
--- /dev/null
+++ b/arch/arm/crypto/curve25519-core.S
@@ -0,0 +1,2062 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * Based on public domain code from Daniel J. Bernstein and Peter Schwabe. This
+ * began from SUPERCOP's curve25519/neon2/scalarmult.s, but has subsequently been
+ * manually reworked for use in kernel space.
+ */
+
+#include <linux/linkage.h>
+
+.text
+.fpu neon
+.arch armv7-a
+.align 4
+
+ENTRY(curve25519_neon)
+	push		{r4-r11, lr}
+	mov		ip, sp
+	sub		r3, sp, #704
+	and		r3, r3, #0xfffffff0
+	mov		sp, r3
+	movw		r4, #0
+	movw		r5, #254
+	vmov.i32	q0, #1
+	vshr.u64	q1, q0, #7
+	vshr.u64	q0, q0, #8
+	vmov.i32	d4, #19
+	vmov.i32	d5, #38
+	add		r6, sp, #480
+	vst1.8		{d2-d3}, [r6, : 128]!
+	vst1.8		{d0-d1}, [r6, : 128]!
+	vst1.8		{d4-d5}, [r6, : 128]
+	add		r6, r3, #0
+	vmov.i32	q2, #0
+	vst1.8		{d4-d5}, [r6, : 128]!
+	vst1.8		{d4-d5}, [r6, : 128]!
+	vst1.8		d4, [r6, : 64]
+	add		r6, r3, #0
+	movw		r7, #960
+	sub		r7, r7, #2
+	neg		r7, r7
+	sub		r7, r7, r7, LSL #7
+	str		r7, [r6]
+	add		r6, sp, #672
+	vld1.8		{d4-d5}, [r1]!
+	vld1.8		{d6-d7}, [r1]
+	vst1.8		{d4-d5}, [r6, : 128]!
+	vst1.8		{d6-d7}, [r6, : 128]
+	sub		r1, r6, #16
+	ldrb		r6, [r1]
+	and		r6, r6, #248
+	strb		r6, [r1]
+	ldrb		r6, [r1, #31]
+	and		r6, r6, #127
+	orr		r6, r6, #64
+	strb		r6, [r1, #31]
+	vmov.i64	q2, #0xffffffff
+	vshr.u64	q3, q2, #7
+	vshr.u64	q2, q2, #6
+	vld1.8		{d8}, [r2]
+	vld1.8		{d10}, [r2]
+	add		r2, r2, #6
+	vld1.8		{d12}, [r2]
+	vld1.8		{d14}, [r2]
+	add		r2, r2, #6
+	vld1.8		{d16}, [r2]
+	add		r2, r2, #4
+	vld1.8		{d18}, [r2]
+	vld1.8		{d20}, [r2]
+	add		r2, r2, #6
+	vld1.8		{d22}, [r2]
+	add		r2, r2, #2
+	vld1.8		{d24}, [r2]
+	vld1.8		{d26}, [r2]
+	vshr.u64	q5, q5, #26
+	vshr.u64	q6, q6, #3
+	vshr.u64	q7, q7, #29
+	vshr.u64	q8, q8, #6
+	vshr.u64	q10, q10, #25
+	vshr.u64	q11, q11, #3
+	vshr.u64	q12, q12, #12
+	vshr.u64	q13, q13, #38
+	vand		q4, q4, q2
+	vand		q6, q6, q2
+	vand		q8, q8, q2
+	vand		q10, q10, q2
+	vand		q2, q12, q2
+	vand		q5, q5, q3
+	vand		q7, q7, q3
+	vand		q9, q9, q3
+	vand		q11, q11, q3
+	vand		q3, q13, q3
+	add		r2, r3, #48
+	vadd.i64	q12, q4, q1
+	vadd.i64	q13, q10, q1
+	vshr.s64	q12, q12, #26
+	vshr.s64	q13, q13, #26
+	vadd.i64	q5, q5, q12
+	vshl.i64	q12, q12, #26
+	vadd.i64	q14, q5, q0
+	vadd.i64	q11, q11, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q15, q11, q0
+	vsub.i64	q4, q4, q12
+	vshr.s64	q12, q14, #25
+	vsub.i64	q10, q10, q13
+	vshr.s64	q13, q15, #25
+	vadd.i64	q6, q6, q12
+	vshl.i64	q12, q12, #25
+	vadd.i64	q14, q6, q1
+	vadd.i64	q2, q2, q13
+	vsub.i64	q5, q5, q12
+	vshr.s64	q12, q14, #26
+	vshl.i64	q13, q13, #25
+	vadd.i64	q14, q2, q1
+	vadd.i64	q7, q7, q12
+	vshl.i64	q12, q12, #26
+	vadd.i64	q15, q7, q0
+	vsub.i64	q11, q11, q13
+	vshr.s64	q13, q14, #26
+	vsub.i64	q6, q6, q12
+	vshr.s64	q12, q15, #25
+	vadd.i64	q3, q3, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q14, q3, q0
+	vadd.i64	q8, q8, q12
+	vshl.i64	q12, q12, #25
+	vadd.i64	q15, q8, q1
+	add		r2, r2, #8
+	vsub.i64	q2, q2, q13
+	vshr.s64	q13, q14, #25
+	vsub.i64	q7, q7, q12
+	vshr.s64	q12, q15, #26
+	vadd.i64	q14, q13, q13
+	vadd.i64	q9, q9, q12
+	vtrn.32		d12, d14
+	vshl.i64	q12, q12, #26
+	vtrn.32		d13, d15
+	vadd.i64	q0, q9, q0
+	vadd.i64	q4, q4, q14
+	vst1.8		d12, [r2, : 64]!
+	vshl.i64	q6, q13, #4
+	vsub.i64	q7, q8, q12
+	vshr.s64	q0, q0, #25
+	vadd.i64	q4, q4, q6
+	vadd.i64	q6, q10, q0
+	vshl.i64	q0, q0, #25
+	vadd.i64	q8, q6, q1
+	vadd.i64	q4, q4, q13
+	vshl.i64	q10, q13, #25
+	vadd.i64	q1, q4, q1
+	vsub.i64	q0, q9, q0
+	vshr.s64	q8, q8, #26
+	vsub.i64	q3, q3, q10
+	vtrn.32		d14, d0
+	vshr.s64	q1, q1, #26
+	vtrn.32		d15, d1
+	vadd.i64	q0, q11, q8
+	vst1.8		d14, [r2, : 64]
+	vshl.i64	q7, q8, #26
+	vadd.i64	q5, q5, q1
+	vtrn.32		d4, d6
+	vshl.i64	q1, q1, #26
+	vtrn.32		d5, d7
+	vsub.i64	q3, q6, q7
+	add		r2, r2, #16
+	vsub.i64	q1, q4, q1
+	vst1.8		d4, [r2, : 64]
+	vtrn.32		d6, d0
+	vtrn.32		d7, d1
+	sub		r2, r2, #8
+	vtrn.32		d2, d10
+	vtrn.32		d3, d11
+	vst1.8		d6, [r2, : 64]
+	sub		r2, r2, #24
+	vst1.8		d2, [r2, : 64]
+	add		r2, r3, #96
+	vmov.i32	q0, #0
+	vmov.i64	d2, #0xff
+	vmov.i64	d3, #0
+	vshr.u32	q1, q1, #7
+	vst1.8		{d2-d3}, [r2, : 128]!
+	vst1.8		{d0-d1}, [r2, : 128]!
+	vst1.8		d0, [r2, : 64]
+	add		r2, r3, #144
+	vmov.i32	q0, #0
+	vst1.8		{d0-d1}, [r2, : 128]!
+	vst1.8		{d0-d1}, [r2, : 128]!
+	vst1.8		d0, [r2, : 64]
+	add		r2, r3, #240
+	vmov.i32	q0, #0
+	vmov.i64	d2, #0xff
+	vmov.i64	d3, #0
+	vshr.u32	q1, q1, #7
+	vst1.8		{d2-d3}, [r2, : 128]!
+	vst1.8		{d0-d1}, [r2, : 128]!
+	vst1.8		d0, [r2, : 64]
+	add		r2, r3, #48
+	add		r6, r3, #192
+	vld1.8		{d0-d1}, [r2, : 128]!
+	vld1.8		{d2-d3}, [r2, : 128]!
+	vld1.8		{d4}, [r2, : 64]
+	vst1.8		{d0-d1}, [r6, : 128]!
+	vst1.8		{d2-d3}, [r6, : 128]!
+	vst1.8		d4, [r6, : 64]
+.Lmainloop:
+	mov		r2, r5, LSR #3
+	and		r6, r5, #7
+	ldrb		r2, [r1, r2]
+	mov		r2, r2, LSR r6
+	and		r2, r2, #1
+	str		r5, [sp, #456]
+	eor		r4, r4, r2
+	str		r2, [sp, #460]
+	neg		r2, r4
+	add		r4, r3, #96
+	add		r5, r3, #192
+	add		r6, r3, #144
+	vld1.8		{d8-d9}, [r4, : 128]!
+	add		r7, r3, #240
+	vld1.8		{d10-d11}, [r5, : 128]!
+	veor		q6, q4, q5
+	vld1.8		{d14-d15}, [r6, : 128]!
+	vdup.i32	q8, r2
+	vld1.8		{d18-d19}, [r7, : 128]!
+	veor		q10, q7, q9
+	vld1.8		{d22-d23}, [r4, : 128]!
+	vand		q6, q6, q8
+	vld1.8		{d24-d25}, [r5, : 128]!
+	vand		q10, q10, q8
+	vld1.8		{d26-d27}, [r6, : 128]!
+	veor		q4, q4, q6
+	vld1.8		{d28-d29}, [r7, : 128]!
+	veor		q5, q5, q6
+	vld1.8		{d0}, [r4, : 64]
+	veor		q6, q7, q10
+	vld1.8		{d2}, [r5, : 64]
+	veor		q7, q9, q10
+	vld1.8		{d4}, [r6, : 64]
+	veor		q9, q11, q12
+	vld1.8		{d6}, [r7, : 64]
+	veor		q10, q0, q1
+	sub		r2, r4, #32
+	vand		q9, q9, q8
+	sub		r4, r5, #32
+	vand		q10, q10, q8
+	sub		r5, r6, #32
+	veor		q11, q11, q9
+	sub		r6, r7, #32
+	veor		q0, q0, q10
+	veor		q9, q12, q9
+	veor		q1, q1, q10
+	veor		q10, q13, q14
+	veor		q12, q2, q3
+	vand		q10, q10, q8
+	vand		q8, q12, q8
+	veor		q12, q13, q10
+	veor		q2, q2, q8
+	veor		q10, q14, q10
+	veor		q3, q3, q8
+	vadd.i32	q8, q4, q6
+	vsub.i32	q4, q4, q6
+	vst1.8		{d16-d17}, [r2, : 128]!
+	vadd.i32	q6, q11, q12
+	vst1.8		{d8-d9}, [r5, : 128]!
+	vsub.i32	q4, q11, q12
+	vst1.8		{d12-d13}, [r2, : 128]!
+	vadd.i32	q6, q0, q2
+	vst1.8		{d8-d9}, [r5, : 128]!
+	vsub.i32	q0, q0, q2
+	vst1.8		d12, [r2, : 64]
+	vadd.i32	q2, q5, q7
+	vst1.8		d0, [r5, : 64]
+	vsub.i32	q0, q5, q7
+	vst1.8		{d4-d5}, [r4, : 128]!
+	vadd.i32	q2, q9, q10
+	vst1.8		{d0-d1}, [r6, : 128]!
+	vsub.i32	q0, q9, q10
+	vst1.8		{d4-d5}, [r4, : 128]!
+	vadd.i32	q2, q1, q3
+	vst1.8		{d0-d1}, [r6, : 128]!
+	vsub.i32	q0, q1, q3
+	vst1.8		d4, [r4, : 64]
+	vst1.8		d0, [r6, : 64]
+	add		r2, sp, #512
+	add		r4, r3, #96
+	add		r5, r3, #144
+	vld1.8		{d0-d1}, [r2, : 128]
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vld1.8		{d4-d5}, [r5, : 128]!
+	vzip.i32	q1, q2
+	vld1.8		{d6-d7}, [r4, : 128]!
+	vld1.8		{d8-d9}, [r5, : 128]!
+	vshl.i32	q5, q1, #1
+	vzip.i32	q3, q4
+	vshl.i32	q6, q2, #1
+	vld1.8		{d14}, [r4, : 64]
+	vshl.i32	q8, q3, #1
+	vld1.8		{d15}, [r5, : 64]
+	vshl.i32	q9, q4, #1
+	vmul.i32	d21, d7, d1
+	vtrn.32		d14, d15
+	vmul.i32	q11, q4, q0
+	vmul.i32	q0, q7, q0
+	vmull.s32	q12, d2, d2
+	vmlal.s32	q12, d11, d1
+	vmlal.s32	q12, d12, d0
+	vmlal.s32	q12, d13, d23
+	vmlal.s32	q12, d16, d22
+	vmlal.s32	q12, d7, d21
+	vmull.s32	q10, d2, d11
+	vmlal.s32	q10, d4, d1
+	vmlal.s32	q10, d13, d0
+	vmlal.s32	q10, d6, d23
+	vmlal.s32	q10, d17, d22
+	vmull.s32	q13, d10, d4
+	vmlal.s32	q13, d11, d3
+	vmlal.s32	q13, d13, d1
+	vmlal.s32	q13, d16, d0
+	vmlal.s32	q13, d17, d23
+	vmlal.s32	q13, d8, d22
+	vmull.s32	q1, d10, d5
+	vmlal.s32	q1, d11, d4
+	vmlal.s32	q1, d6, d1
+	vmlal.s32	q1, d17, d0
+	vmlal.s32	q1, d8, d23
+	vmull.s32	q14, d10, d6
+	vmlal.s32	q14, d11, d13
+	vmlal.s32	q14, d4, d4
+	vmlal.s32	q14, d17, d1
+	vmlal.s32	q14, d18, d0
+	vmlal.s32	q14, d9, d23
+	vmull.s32	q11, d10, d7
+	vmlal.s32	q11, d11, d6
+	vmlal.s32	q11, d12, d5
+	vmlal.s32	q11, d8, d1
+	vmlal.s32	q11, d19, d0
+	vmull.s32	q15, d10, d8
+	vmlal.s32	q15, d11, d17
+	vmlal.s32	q15, d12, d6
+	vmlal.s32	q15, d13, d5
+	vmlal.s32	q15, d19, d1
+	vmlal.s32	q15, d14, d0
+	vmull.s32	q2, d10, d9
+	vmlal.s32	q2, d11, d8
+	vmlal.s32	q2, d12, d7
+	vmlal.s32	q2, d13, d6
+	vmlal.s32	q2, d14, d1
+	vmull.s32	q0, d15, d1
+	vmlal.s32	q0, d10, d14
+	vmlal.s32	q0, d11, d19
+	vmlal.s32	q0, d12, d8
+	vmlal.s32	q0, d13, d17
+	vmlal.s32	q0, d6, d6
+	add		r2, sp, #480
+	vld1.8		{d18-d19}, [r2, : 128]!
+	vmull.s32	q3, d16, d7
+	vmlal.s32	q3, d10, d15
+	vmlal.s32	q3, d11, d14
+	vmlal.s32	q3, d12, d9
+	vmlal.s32	q3, d13, d8
+	vld1.8		{d8-d9}, [r2, : 128]
+	vadd.i64	q5, q12, q9
+	vadd.i64	q6, q15, q9
+	vshr.s64	q5, q5, #26
+	vshr.s64	q6, q6, #26
+	vadd.i64	q7, q10, q5
+	vshl.i64	q5, q5, #26
+	vadd.i64	q8, q7, q4
+	vadd.i64	q2, q2, q6
+	vshl.i64	q6, q6, #26
+	vadd.i64	q10, q2, q4
+	vsub.i64	q5, q12, q5
+	vshr.s64	q8, q8, #25
+	vsub.i64	q6, q15, q6
+	vshr.s64	q10, q10, #25
+	vadd.i64	q12, q13, q8
+	vshl.i64	q8, q8, #25
+	vadd.i64	q13, q12, q9
+	vadd.i64	q0, q0, q10
+	vsub.i64	q7, q7, q8
+	vshr.s64	q8, q13, #26
+	vshl.i64	q10, q10, #25
+	vadd.i64	q13, q0, q9
+	vadd.i64	q1, q1, q8
+	vshl.i64	q8, q8, #26
+	vadd.i64	q15, q1, q4
+	vsub.i64	q2, q2, q10
+	vshr.s64	q10, q13, #26
+	vsub.i64	q8, q12, q8
+	vshr.s64	q12, q15, #25
+	vadd.i64	q3, q3, q10
+	vshl.i64	q10, q10, #26
+	vadd.i64	q13, q3, q4
+	vadd.i64	q14, q14, q12
+	add		r2, r3, #288
+	vshl.i64	q12, q12, #25
+	add		r4, r3, #336
+	vadd.i64	q15, q14, q9
+	add		r2, r2, #8
+	vsub.i64	q0, q0, q10
+	add		r4, r4, #8
+	vshr.s64	q10, q13, #25
+	vsub.i64	q1, q1, q12
+	vshr.s64	q12, q15, #26
+	vadd.i64	q13, q10, q10
+	vadd.i64	q11, q11, q12
+	vtrn.32		d16, d2
+	vshl.i64	q12, q12, #26
+	vtrn.32		d17, d3
+	vadd.i64	q1, q11, q4
+	vadd.i64	q4, q5, q13
+	vst1.8		d16, [r2, : 64]!
+	vshl.i64	q5, q10, #4
+	vst1.8		d17, [r4, : 64]!
+	vsub.i64	q8, q14, q12
+	vshr.s64	q1, q1, #25
+	vadd.i64	q4, q4, q5
+	vadd.i64	q5, q6, q1
+	vshl.i64	q1, q1, #25
+	vadd.i64	q6, q5, q9
+	vadd.i64	q4, q4, q10
+	vshl.i64	q10, q10, #25
+	vadd.i64	q9, q4, q9
+	vsub.i64	q1, q11, q1
+	vshr.s64	q6, q6, #26
+	vsub.i64	q3, q3, q10
+	vtrn.32		d16, d2
+	vshr.s64	q9, q9, #26
+	vtrn.32		d17, d3
+	vadd.i64	q1, q2, q6
+	vst1.8		d16, [r2, : 64]
+	vshl.i64	q2, q6, #26
+	vst1.8		d17, [r4, : 64]
+	vadd.i64	q6, q7, q9
+	vtrn.32		d0, d6
+	vshl.i64	q7, q9, #26
+	vtrn.32		d1, d7
+	vsub.i64	q2, q5, q2
+	add		r2, r2, #16
+	vsub.i64	q3, q4, q7
+	vst1.8		d0, [r2, : 64]
+	add		r4, r4, #16
+	vst1.8		d1, [r4, : 64]
+	vtrn.32		d4, d2
+	vtrn.32		d5, d3
+	sub		r2, r2, #8
+	sub		r4, r4, #8
+	vtrn.32		d6, d12
+	vtrn.32		d7, d13
+	vst1.8		d4, [r2, : 64]
+	vst1.8		d5, [r4, : 64]
+	sub		r2, r2, #24
+	sub		r4, r4, #24
+	vst1.8		d6, [r2, : 64]
+	vst1.8		d7, [r4, : 64]
+	add		r2, r3, #240
+	add		r4, r3, #96
+	vld1.8		{d0-d1}, [r4, : 128]!
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vld1.8		{d4}, [r4, : 64]
+	add		r4, r3, #144
+	vld1.8		{d6-d7}, [r4, : 128]!
+	vtrn.32		q0, q3
+	vld1.8		{d8-d9}, [r4, : 128]!
+	vshl.i32	q5, q0, #4
+	vtrn.32		q1, q4
+	vshl.i32	q6, q3, #4
+	vadd.i32	q5, q5, q0
+	vadd.i32	q6, q6, q3
+	vshl.i32	q7, q1, #4
+	vld1.8		{d5}, [r4, : 64]
+	vshl.i32	q8, q4, #4
+	vtrn.32		d4, d5
+	vadd.i32	q7, q7, q1
+	vadd.i32	q8, q8, q4
+	vld1.8		{d18-d19}, [r2, : 128]!
+	vshl.i32	q10, q2, #4
+	vld1.8		{d22-d23}, [r2, : 128]!
+	vadd.i32	q10, q10, q2
+	vld1.8		{d24}, [r2, : 64]
+	vadd.i32	q5, q5, q0
+	add		r2, r3, #192
+	vld1.8		{d26-d27}, [r2, : 128]!
+	vadd.i32	q6, q6, q3
+	vld1.8		{d28-d29}, [r2, : 128]!
+	vadd.i32	q8, q8, q4
+	vld1.8		{d25}, [r2, : 64]
+	vadd.i32	q10, q10, q2
+	vtrn.32		q9, q13
+	vadd.i32	q7, q7, q1
+	vadd.i32	q5, q5, q0
+	vtrn.32		q11, q14
+	vadd.i32	q6, q6, q3
+	add		r2, sp, #528
+	vadd.i32	q10, q10, q2
+	vtrn.32		d24, d25
+	vst1.8		{d12-d13}, [r2, : 128]!
+	vshl.i32	q6, q13, #1
+	vst1.8		{d20-d21}, [r2, : 128]!
+	vshl.i32	q10, q14, #1
+	vst1.8		{d12-d13}, [r2, : 128]!
+	vshl.i32	q15, q12, #1
+	vadd.i32	q8, q8, q4
+	vext.32		d10, d31, d30, #0
+	vadd.i32	q7, q7, q1
+	vst1.8		{d16-d17}, [r2, : 128]!
+	vmull.s32	q8, d18, d5
+	vmlal.s32	q8, d26, d4
+	vmlal.s32	q8, d19, d9
+	vmlal.s32	q8, d27, d3
+	vmlal.s32	q8, d22, d8
+	vmlal.s32	q8, d28, d2
+	vmlal.s32	q8, d23, d7
+	vmlal.s32	q8, d29, d1
+	vmlal.s32	q8, d24, d6
+	vmlal.s32	q8, d25, d0
+	vst1.8		{d14-d15}, [r2, : 128]!
+	vmull.s32	q2, d18, d4
+	vmlal.s32	q2, d12, d9
+	vmlal.s32	q2, d13, d8
+	vmlal.s32	q2, d19, d3
+	vmlal.s32	q2, d22, d2
+	vmlal.s32	q2, d23, d1
+	vmlal.s32	q2, d24, d0
+	vst1.8		{d20-d21}, [r2, : 128]!
+	vmull.s32	q7, d18, d9
+	vmlal.s32	q7, d26, d3
+	vmlal.s32	q7, d19, d8
+	vmlal.s32	q7, d27, d2
+	vmlal.s32	q7, d22, d7
+	vmlal.s32	q7, d28, d1
+	vmlal.s32	q7, d23, d6
+	vmlal.s32	q7, d29, d0
+	vst1.8		{d10-d11}, [r2, : 128]!
+	vmull.s32	q5, d18, d3
+	vmlal.s32	q5, d19, d2
+	vmlal.s32	q5, d22, d1
+	vmlal.s32	q5, d23, d0
+	vmlal.s32	q5, d12, d8
+	vst1.8		{d16-d17}, [r2, : 128]
+	vmull.s32	q4, d18, d8
+	vmlal.s32	q4, d26, d2
+	vmlal.s32	q4, d19, d7
+	vmlal.s32	q4, d27, d1
+	vmlal.s32	q4, d22, d6
+	vmlal.s32	q4, d28, d0
+	vmull.s32	q8, d18, d7
+	vmlal.s32	q8, d26, d1
+	vmlal.s32	q8, d19, d6
+	vmlal.s32	q8, d27, d0
+	add		r2, sp, #544
+	vld1.8		{d20-d21}, [r2, : 128]
+	vmlal.s32	q7, d24, d21
+	vmlal.s32	q7, d25, d20
+	vmlal.s32	q4, d23, d21
+	vmlal.s32	q4, d29, d20
+	vmlal.s32	q8, d22, d21
+	vmlal.s32	q8, d28, d20
+	vmlal.s32	q5, d24, d20
+	vst1.8		{d14-d15}, [r2, : 128]
+	vmull.s32	q7, d18, d6
+	vmlal.s32	q7, d26, d0
+	add		r2, sp, #624
+	vld1.8		{d30-d31}, [r2, : 128]
+	vmlal.s32	q2, d30, d21
+	vmlal.s32	q7, d19, d21
+	vmlal.s32	q7, d27, d20
+	add		r2, sp, #592
+	vld1.8		{d26-d27}, [r2, : 128]
+	vmlal.s32	q4, d25, d27
+	vmlal.s32	q8, d29, d27
+	vmlal.s32	q8, d25, d26
+	vmlal.s32	q7, d28, d27
+	vmlal.s32	q7, d29, d26
+	add		r2, sp, #576
+	vld1.8		{d28-d29}, [r2, : 128]
+	vmlal.s32	q4, d24, d29
+	vmlal.s32	q8, d23, d29
+	vmlal.s32	q8, d24, d28
+	vmlal.s32	q7, d22, d29
+	vmlal.s32	q7, d23, d28
+	vst1.8		{d8-d9}, [r2, : 128]
+	add		r2, sp, #528
+	vld1.8		{d8-d9}, [r2, : 128]
+	vmlal.s32	q7, d24, d9
+	vmlal.s32	q7, d25, d31
+	vmull.s32	q1, d18, d2
+	vmlal.s32	q1, d19, d1
+	vmlal.s32	q1, d22, d0
+	vmlal.s32	q1, d24, d27
+	vmlal.s32	q1, d23, d20
+	vmlal.s32	q1, d12, d7
+	vmlal.s32	q1, d13, d6
+	vmull.s32	q6, d18, d1
+	vmlal.s32	q6, d19, d0
+	vmlal.s32	q6, d23, d27
+	vmlal.s32	q6, d22, d20
+	vmlal.s32	q6, d24, d26
+	vmull.s32	q0, d18, d0
+	vmlal.s32	q0, d22, d27
+	vmlal.s32	q0, d23, d26
+	vmlal.s32	q0, d24, d31
+	vmlal.s32	q0, d19, d20
+	add		r2, sp, #608
+	vld1.8		{d18-d19}, [r2, : 128]
+	vmlal.s32	q2, d18, d7
+	vmlal.s32	q5, d18, d6
+	vmlal.s32	q1, d18, d21
+	vmlal.s32	q0, d18, d28
+	vmlal.s32	q6, d18, d29
+	vmlal.s32	q2, d19, d6
+	vmlal.s32	q5, d19, d21
+	vmlal.s32	q1, d19, d29
+	vmlal.s32	q0, d19, d9
+	vmlal.s32	q6, d19, d28
+	add		r2, sp, #560
+	vld1.8		{d18-d19}, [r2, : 128]
+	add		r2, sp, #480
+	vld1.8		{d22-d23}, [r2, : 128]
+	vmlal.s32	q5, d19, d7
+	vmlal.s32	q0, d18, d21
+	vmlal.s32	q0, d19, d29
+	vmlal.s32	q6, d18, d6
+	add		r2, sp, #496
+	vld1.8		{d6-d7}, [r2, : 128]
+	vmlal.s32	q6, d19, d21
+	add		r2, sp, #544
+	vld1.8		{d18-d19}, [r2, : 128]
+	vmlal.s32	q0, d30, d8
+	add		r2, sp, #640
+	vld1.8		{d20-d21}, [r2, : 128]
+	vmlal.s32	q5, d30, d29
+	add		r2, sp, #576
+	vld1.8		{d24-d25}, [r2, : 128]
+	vmlal.s32	q1, d30, d28
+	vadd.i64	q13, q0, q11
+	vadd.i64	q14, q5, q11
+	vmlal.s32	q6, d30, d9
+	vshr.s64	q4, q13, #26
+	vshr.s64	q13, q14, #26
+	vadd.i64	q7, q7, q4
+	vshl.i64	q4, q4, #26
+	vadd.i64	q14, q7, q3
+	vadd.i64	q9, q9, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q15, q9, q3
+	vsub.i64	q0, q0, q4
+	vshr.s64	q4, q14, #25
+	vsub.i64	q5, q5, q13
+	vshr.s64	q13, q15, #25
+	vadd.i64	q6, q6, q4
+	vshl.i64	q4, q4, #25
+	vadd.i64	q14, q6, q11
+	vadd.i64	q2, q2, q13
+	vsub.i64	q4, q7, q4
+	vshr.s64	q7, q14, #26
+	vshl.i64	q13, q13, #25
+	vadd.i64	q14, q2, q11
+	vadd.i64	q8, q8, q7
+	vshl.i64	q7, q7, #26
+	vadd.i64	q15, q8, q3
+	vsub.i64	q9, q9, q13
+	vshr.s64	q13, q14, #26
+	vsub.i64	q6, q6, q7
+	vshr.s64	q7, q15, #25
+	vadd.i64	q10, q10, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q14, q10, q3
+	vadd.i64	q1, q1, q7
+	add		r2, r3, #144
+	vshl.i64	q7, q7, #25
+	add		r4, r3, #96
+	vadd.i64	q15, q1, q11
+	add		r2, r2, #8
+	vsub.i64	q2, q2, q13
+	add		r4, r4, #8
+	vshr.s64	q13, q14, #25
+	vsub.i64	q7, q8, q7
+	vshr.s64	q8, q15, #26
+	vadd.i64	q14, q13, q13
+	vadd.i64	q12, q12, q8
+	vtrn.32		d12, d14
+	vshl.i64	q8, q8, #26
+	vtrn.32		d13, d15
+	vadd.i64	q3, q12, q3
+	vadd.i64	q0, q0, q14
+	vst1.8		d12, [r2, : 64]!
+	vshl.i64	q7, q13, #4
+	vst1.8		d13, [r4, : 64]!
+	vsub.i64	q1, q1, q8
+	vshr.s64	q3, q3, #25
+	vadd.i64	q0, q0, q7
+	vadd.i64	q5, q5, q3
+	vshl.i64	q3, q3, #25
+	vadd.i64	q6, q5, q11
+	vadd.i64	q0, q0, q13
+	vshl.i64	q7, q13, #25
+	vadd.i64	q8, q0, q11
+	vsub.i64	q3, q12, q3
+	vshr.s64	q6, q6, #26
+	vsub.i64	q7, q10, q7
+	vtrn.32		d2, d6
+	vshr.s64	q8, q8, #26
+	vtrn.32		d3, d7
+	vadd.i64	q3, q9, q6
+	vst1.8		d2, [r2, : 64]
+	vshl.i64	q6, q6, #26
+	vst1.8		d3, [r4, : 64]
+	vadd.i64	q1, q4, q8
+	vtrn.32		d4, d14
+	vshl.i64	q4, q8, #26
+	vtrn.32		d5, d15
+	vsub.i64	q5, q5, q6
+	add		r2, r2, #16
+	vsub.i64	q0, q0, q4
+	vst1.8		d4, [r2, : 64]
+	add		r4, r4, #16
+	vst1.8		d5, [r4, : 64]
+	vtrn.32		d10, d6
+	vtrn.32		d11, d7
+	sub		r2, r2, #8
+	sub		r4, r4, #8
+	vtrn.32		d0, d2
+	vtrn.32		d1, d3
+	vst1.8		d10, [r2, : 64]
+	vst1.8		d11, [r4, : 64]
+	sub		r2, r2, #24
+	sub		r4, r4, #24
+	vst1.8		d0, [r2, : 64]
+	vst1.8		d1, [r4, : 64]
+	add		r2, r3, #288
+	add		r4, r3, #336
+	vld1.8		{d0-d1}, [r2, : 128]!
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vsub.i32	q0, q0, q1
+	vld1.8		{d2-d3}, [r2, : 128]!
+	vld1.8		{d4-d5}, [r4, : 128]!
+	vsub.i32	q1, q1, q2
+	add		r5, r3, #240
+	vld1.8		{d4}, [r2, : 64]
+	vld1.8		{d6}, [r4, : 64]
+	vsub.i32	q2, q2, q3
+	vst1.8		{d0-d1}, [r5, : 128]!
+	vst1.8		{d2-d3}, [r5, : 128]!
+	vst1.8		d4, [r5, : 64]
+	add		r2, r3, #144
+	add		r4, r3, #96
+	add		r5, r3, #144
+	add		r6, r3, #192
+	vld1.8		{d0-d1}, [r2, : 128]!
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vsub.i32	q2, q0, q1
+	vadd.i32	q0, q0, q1
+	vld1.8		{d2-d3}, [r2, : 128]!
+	vld1.8		{d6-d7}, [r4, : 128]!
+	vsub.i32	q4, q1, q3
+	vadd.i32	q1, q1, q3
+	vld1.8		{d6}, [r2, : 64]
+	vld1.8		{d10}, [r4, : 64]
+	vsub.i32	q6, q3, q5
+	vadd.i32	q3, q3, q5
+	vst1.8		{d4-d5}, [r5, : 128]!
+	vst1.8		{d0-d1}, [r6, : 128]!
+	vst1.8		{d8-d9}, [r5, : 128]!
+	vst1.8		{d2-d3}, [r6, : 128]!
+	vst1.8		d12, [r5, : 64]
+	vst1.8		d6, [r6, : 64]
+	add		r2, r3, #0
+	add		r4, r3, #240
+	vld1.8		{d0-d1}, [r4, : 128]!
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vld1.8		{d4}, [r4, : 64]
+	add		r4, r3, #336
+	vld1.8		{d6-d7}, [r4, : 128]!
+	vtrn.32		q0, q3
+	vld1.8		{d8-d9}, [r4, : 128]!
+	vshl.i32	q5, q0, #4
+	vtrn.32		q1, q4
+	vshl.i32	q6, q3, #4
+	vadd.i32	q5, q5, q0
+	vadd.i32	q6, q6, q3
+	vshl.i32	q7, q1, #4
+	vld1.8		{d5}, [r4, : 64]
+	vshl.i32	q8, q4, #4
+	vtrn.32		d4, d5
+	vadd.i32	q7, q7, q1
+	vadd.i32	q8, q8, q4
+	vld1.8		{d18-d19}, [r2, : 128]!
+	vshl.i32	q10, q2, #4
+	vld1.8		{d22-d23}, [r2, : 128]!
+	vadd.i32	q10, q10, q2
+	vld1.8		{d24}, [r2, : 64]
+	vadd.i32	q5, q5, q0
+	add		r2, r3, #288
+	vld1.8		{d26-d27}, [r2, : 128]!
+	vadd.i32	q6, q6, q3
+	vld1.8		{d28-d29}, [r2, : 128]!
+	vadd.i32	q8, q8, q4
+	vld1.8		{d25}, [r2, : 64]
+	vadd.i32	q10, q10, q2
+	vtrn.32		q9, q13
+	vadd.i32	q7, q7, q1
+	vadd.i32	q5, q5, q0
+	vtrn.32		q11, q14
+	vadd.i32	q6, q6, q3
+	add		r2, sp, #528
+	vadd.i32	q10, q10, q2
+	vtrn.32		d24, d25
+	vst1.8		{d12-d13}, [r2, : 128]!
+	vshl.i32	q6, q13, #1
+	vst1.8		{d20-d21}, [r2, : 128]!
+	vshl.i32	q10, q14, #1
+	vst1.8		{d12-d13}, [r2, : 128]!
+	vshl.i32	q15, q12, #1
+	vadd.i32	q8, q8, q4
+	vext.32		d10, d31, d30, #0
+	vadd.i32	q7, q7, q1
+	vst1.8		{d16-d17}, [r2, : 128]!
+	vmull.s32	q8, d18, d5
+	vmlal.s32	q8, d26, d4
+	vmlal.s32	q8, d19, d9
+	vmlal.s32	q8, d27, d3
+	vmlal.s32	q8, d22, d8
+	vmlal.s32	q8, d28, d2
+	vmlal.s32	q8, d23, d7
+	vmlal.s32	q8, d29, d1
+	vmlal.s32	q8, d24, d6
+	vmlal.s32	q8, d25, d0
+	vst1.8		{d14-d15}, [r2, : 128]!
+	vmull.s32	q2, d18, d4
+	vmlal.s32	q2, d12, d9
+	vmlal.s32	q2, d13, d8
+	vmlal.s32	q2, d19, d3
+	vmlal.s32	q2, d22, d2
+	vmlal.s32	q2, d23, d1
+	vmlal.s32	q2, d24, d0
+	vst1.8		{d20-d21}, [r2, : 128]!
+	vmull.s32	q7, d18, d9
+	vmlal.s32	q7, d26, d3
+	vmlal.s32	q7, d19, d8
+	vmlal.s32	q7, d27, d2
+	vmlal.s32	q7, d22, d7
+	vmlal.s32	q7, d28, d1
+	vmlal.s32	q7, d23, d6
+	vmlal.s32	q7, d29, d0
+	vst1.8		{d10-d11}, [r2, : 128]!
+	vmull.s32	q5, d18, d3
+	vmlal.s32	q5, d19, d2
+	vmlal.s32	q5, d22, d1
+	vmlal.s32	q5, d23, d0
+	vmlal.s32	q5, d12, d8
+	vst1.8		{d16-d17}, [r2, : 128]!
+	vmull.s32	q4, d18, d8
+	vmlal.s32	q4, d26, d2
+	vmlal.s32	q4, d19, d7
+	vmlal.s32	q4, d27, d1
+	vmlal.s32	q4, d22, d6
+	vmlal.s32	q4, d28, d0
+	vmull.s32	q8, d18, d7
+	vmlal.s32	q8, d26, d1
+	vmlal.s32	q8, d19, d6
+	vmlal.s32	q8, d27, d0
+	add		r2, sp, #544
+	vld1.8		{d20-d21}, [r2, : 128]
+	vmlal.s32	q7, d24, d21
+	vmlal.s32	q7, d25, d20
+	vmlal.s32	q4, d23, d21
+	vmlal.s32	q4, d29, d20
+	vmlal.s32	q8, d22, d21
+	vmlal.s32	q8, d28, d20
+	vmlal.s32	q5, d24, d20
+	vst1.8		{d14-d15}, [r2, : 128]
+	vmull.s32	q7, d18, d6
+	vmlal.s32	q7, d26, d0
+	add		r2, sp, #624
+	vld1.8		{d30-d31}, [r2, : 128]
+	vmlal.s32	q2, d30, d21
+	vmlal.s32	q7, d19, d21
+	vmlal.s32	q7, d27, d20
+	add		r2, sp, #592
+	vld1.8		{d26-d27}, [r2, : 128]
+	vmlal.s32	q4, d25, d27
+	vmlal.s32	q8, d29, d27
+	vmlal.s32	q8, d25, d26
+	vmlal.s32	q7, d28, d27
+	vmlal.s32	q7, d29, d26
+	add		r2, sp, #576
+	vld1.8		{d28-d29}, [r2, : 128]
+	vmlal.s32	q4, d24, d29
+	vmlal.s32	q8, d23, d29
+	vmlal.s32	q8, d24, d28
+	vmlal.s32	q7, d22, d29
+	vmlal.s32	q7, d23, d28
+	vst1.8		{d8-d9}, [r2, : 128]
+	add		r2, sp, #528
+	vld1.8		{d8-d9}, [r2, : 128]
+	vmlal.s32	q7, d24, d9
+	vmlal.s32	q7, d25, d31
+	vmull.s32	q1, d18, d2
+	vmlal.s32	q1, d19, d1
+	vmlal.s32	q1, d22, d0
+	vmlal.s32	q1, d24, d27
+	vmlal.s32	q1, d23, d20
+	vmlal.s32	q1, d12, d7
+	vmlal.s32	q1, d13, d6
+	vmull.s32	q6, d18, d1
+	vmlal.s32	q6, d19, d0
+	vmlal.s32	q6, d23, d27
+	vmlal.s32	q6, d22, d20
+	vmlal.s32	q6, d24, d26
+	vmull.s32	q0, d18, d0
+	vmlal.s32	q0, d22, d27
+	vmlal.s32	q0, d23, d26
+	vmlal.s32	q0, d24, d31
+	vmlal.s32	q0, d19, d20
+	add		r2, sp, #608
+	vld1.8		{d18-d19}, [r2, : 128]
+	vmlal.s32	q2, d18, d7
+	vmlal.s32	q5, d18, d6
+	vmlal.s32	q1, d18, d21
+	vmlal.s32	q0, d18, d28
+	vmlal.s32	q6, d18, d29
+	vmlal.s32	q2, d19, d6
+	vmlal.s32	q5, d19, d21
+	vmlal.s32	q1, d19, d29
+	vmlal.s32	q0, d19, d9
+	vmlal.s32	q6, d19, d28
+	add		r2, sp, #560
+	vld1.8		{d18-d19}, [r2, : 128]
+	add		r2, sp, #480
+	vld1.8		{d22-d23}, [r2, : 128]
+	vmlal.s32	q5, d19, d7
+	vmlal.s32	q0, d18, d21
+	vmlal.s32	q0, d19, d29
+	vmlal.s32	q6, d18, d6
+	add		r2, sp, #496
+	vld1.8		{d6-d7}, [r2, : 128]
+	vmlal.s32	q6, d19, d21
+	add		r2, sp, #544
+	vld1.8		{d18-d19}, [r2, : 128]
+	vmlal.s32	q0, d30, d8
+	add		r2, sp, #640
+	vld1.8		{d20-d21}, [r2, : 128]
+	vmlal.s32	q5, d30, d29
+	add		r2, sp, #576
+	vld1.8		{d24-d25}, [r2, : 128]
+	vmlal.s32	q1, d30, d28
+	vadd.i64	q13, q0, q11
+	vadd.i64	q14, q5, q11
+	vmlal.s32	q6, d30, d9
+	vshr.s64	q4, q13, #26
+	vshr.s64	q13, q14, #26
+	vadd.i64	q7, q7, q4
+	vshl.i64	q4, q4, #26
+	vadd.i64	q14, q7, q3
+	vadd.i64	q9, q9, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q15, q9, q3
+	vsub.i64	q0, q0, q4
+	vshr.s64	q4, q14, #25
+	vsub.i64	q5, q5, q13
+	vshr.s64	q13, q15, #25
+	vadd.i64	q6, q6, q4
+	vshl.i64	q4, q4, #25
+	vadd.i64	q14, q6, q11
+	vadd.i64	q2, q2, q13
+	vsub.i64	q4, q7, q4
+	vshr.s64	q7, q14, #26
+	vshl.i64	q13, q13, #25
+	vadd.i64	q14, q2, q11
+	vadd.i64	q8, q8, q7
+	vshl.i64	q7, q7, #26
+	vadd.i64	q15, q8, q3
+	vsub.i64	q9, q9, q13
+	vshr.s64	q13, q14, #26
+	vsub.i64	q6, q6, q7
+	vshr.s64	q7, q15, #25
+	vadd.i64	q10, q10, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q14, q10, q3
+	vadd.i64	q1, q1, q7
+	add		r2, r3, #288
+	vshl.i64	q7, q7, #25
+	add		r4, r3, #96
+	vadd.i64	q15, q1, q11
+	add		r2, r2, #8
+	vsub.i64	q2, q2, q13
+	add		r4, r4, #8
+	vshr.s64	q13, q14, #25
+	vsub.i64	q7, q8, q7
+	vshr.s64	q8, q15, #26
+	vadd.i64	q14, q13, q13
+	vadd.i64	q12, q12, q8
+	vtrn.32		d12, d14
+	vshl.i64	q8, q8, #26
+	vtrn.32		d13, d15
+	vadd.i64	q3, q12, q3
+	vadd.i64	q0, q0, q14
+	vst1.8		d12, [r2, : 64]!
+	vshl.i64	q7, q13, #4
+	vst1.8		d13, [r4, : 64]!
+	vsub.i64	q1, q1, q8
+	vshr.s64	q3, q3, #25
+	vadd.i64	q0, q0, q7
+	vadd.i64	q5, q5, q3
+	vshl.i64	q3, q3, #25
+	vadd.i64	q6, q5, q11
+	vadd.i64	q0, q0, q13
+	vshl.i64	q7, q13, #25
+	vadd.i64	q8, q0, q11
+	vsub.i64	q3, q12, q3
+	vshr.s64	q6, q6, #26
+	vsub.i64	q7, q10, q7
+	vtrn.32		d2, d6
+	vshr.s64	q8, q8, #26
+	vtrn.32		d3, d7
+	vadd.i64	q3, q9, q6
+	vst1.8		d2, [r2, : 64]
+	vshl.i64	q6, q6, #26
+	vst1.8		d3, [r4, : 64]
+	vadd.i64	q1, q4, q8
+	vtrn.32		d4, d14
+	vshl.i64	q4, q8, #26
+	vtrn.32		d5, d15
+	vsub.i64	q5, q5, q6
+	add		r2, r2, #16
+	vsub.i64	q0, q0, q4
+	vst1.8		d4, [r2, : 64]
+	add		r4, r4, #16
+	vst1.8		d5, [r4, : 64]
+	vtrn.32		d10, d6
+	vtrn.32		d11, d7
+	sub		r2, r2, #8
+	sub		r4, r4, #8
+	vtrn.32		d0, d2
+	vtrn.32		d1, d3
+	vst1.8		d10, [r2, : 64]
+	vst1.8		d11, [r4, : 64]
+	sub		r2, r2, #24
+	sub		r4, r4, #24
+	vst1.8		d0, [r2, : 64]
+	vst1.8		d1, [r4, : 64]
+	add		r2, sp, #512
+	add		r4, r3, #144
+	add		r5, r3, #192
+	vld1.8		{d0-d1}, [r2, : 128]
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vld1.8		{d4-d5}, [r5, : 128]!
+	vzip.i32	q1, q2
+	vld1.8		{d6-d7}, [r4, : 128]!
+	vld1.8		{d8-d9}, [r5, : 128]!
+	vshl.i32	q5, q1, #1
+	vzip.i32	q3, q4
+	vshl.i32	q6, q2, #1
+	vld1.8		{d14}, [r4, : 64]
+	vshl.i32	q8, q3, #1
+	vld1.8		{d15}, [r5, : 64]
+	vshl.i32	q9, q4, #1
+	vmul.i32	d21, d7, d1
+	vtrn.32		d14, d15
+	vmul.i32	q11, q4, q0
+	vmul.i32	q0, q7, q0
+	vmull.s32	q12, d2, d2
+	vmlal.s32	q12, d11, d1
+	vmlal.s32	q12, d12, d0
+	vmlal.s32	q12, d13, d23
+	vmlal.s32	q12, d16, d22
+	vmlal.s32	q12, d7, d21
+	vmull.s32	q10, d2, d11
+	vmlal.s32	q10, d4, d1
+	vmlal.s32	q10, d13, d0
+	vmlal.s32	q10, d6, d23
+	vmlal.s32	q10, d17, d22
+	vmull.s32	q13, d10, d4
+	vmlal.s32	q13, d11, d3
+	vmlal.s32	q13, d13, d1
+	vmlal.s32	q13, d16, d0
+	vmlal.s32	q13, d17, d23
+	vmlal.s32	q13, d8, d22
+	vmull.s32	q1, d10, d5
+	vmlal.s32	q1, d11, d4
+	vmlal.s32	q1, d6, d1
+	vmlal.s32	q1, d17, d0
+	vmlal.s32	q1, d8, d23
+	vmull.s32	q14, d10, d6
+	vmlal.s32	q14, d11, d13
+	vmlal.s32	q14, d4, d4
+	vmlal.s32	q14, d17, d1
+	vmlal.s32	q14, d18, d0
+	vmlal.s32	q14, d9, d23
+	vmull.s32	q11, d10, d7
+	vmlal.s32	q11, d11, d6
+	vmlal.s32	q11, d12, d5
+	vmlal.s32	q11, d8, d1
+	vmlal.s32	q11, d19, d0
+	vmull.s32	q15, d10, d8
+	vmlal.s32	q15, d11, d17
+	vmlal.s32	q15, d12, d6
+	vmlal.s32	q15, d13, d5
+	vmlal.s32	q15, d19, d1
+	vmlal.s32	q15, d14, d0
+	vmull.s32	q2, d10, d9
+	vmlal.s32	q2, d11, d8
+	vmlal.s32	q2, d12, d7
+	vmlal.s32	q2, d13, d6
+	vmlal.s32	q2, d14, d1
+	vmull.s32	q0, d15, d1
+	vmlal.s32	q0, d10, d14
+	vmlal.s32	q0, d11, d19
+	vmlal.s32	q0, d12, d8
+	vmlal.s32	q0, d13, d17
+	vmlal.s32	q0, d6, d6
+	add		r2, sp, #480
+	vld1.8		{d18-d19}, [r2, : 128]!
+	vmull.s32	q3, d16, d7
+	vmlal.s32	q3, d10, d15
+	vmlal.s32	q3, d11, d14
+	vmlal.s32	q3, d12, d9
+	vmlal.s32	q3, d13, d8
+	vld1.8		{d8-d9}, [r2, : 128]
+	vadd.i64	q5, q12, q9
+	vadd.i64	q6, q15, q9
+	vshr.s64	q5, q5, #26
+	vshr.s64	q6, q6, #26
+	vadd.i64	q7, q10, q5
+	vshl.i64	q5, q5, #26
+	vadd.i64	q8, q7, q4
+	vadd.i64	q2, q2, q6
+	vshl.i64	q6, q6, #26
+	vadd.i64	q10, q2, q4
+	vsub.i64	q5, q12, q5
+	vshr.s64	q8, q8, #25
+	vsub.i64	q6, q15, q6
+	vshr.s64	q10, q10, #25
+	vadd.i64	q12, q13, q8
+	vshl.i64	q8, q8, #25
+	vadd.i64	q13, q12, q9
+	vadd.i64	q0, q0, q10
+	vsub.i64	q7, q7, q8
+	vshr.s64	q8, q13, #26
+	vshl.i64	q10, q10, #25
+	vadd.i64	q13, q0, q9
+	vadd.i64	q1, q1, q8
+	vshl.i64	q8, q8, #26
+	vadd.i64	q15, q1, q4
+	vsub.i64	q2, q2, q10
+	vshr.s64	q10, q13, #26
+	vsub.i64	q8, q12, q8
+	vshr.s64	q12, q15, #25
+	vadd.i64	q3, q3, q10
+	vshl.i64	q10, q10, #26
+	vadd.i64	q13, q3, q4
+	vadd.i64	q14, q14, q12
+	add		r2, r3, #144
+	vshl.i64	q12, q12, #25
+	add		r4, r3, #192
+	vadd.i64	q15, q14, q9
+	add		r2, r2, #8
+	vsub.i64	q0, q0, q10
+	add		r4, r4, #8
+	vshr.s64	q10, q13, #25
+	vsub.i64	q1, q1, q12
+	vshr.s64	q12, q15, #26
+	vadd.i64	q13, q10, q10
+	vadd.i64	q11, q11, q12
+	vtrn.32		d16, d2
+	vshl.i64	q12, q12, #26
+	vtrn.32		d17, d3
+	vadd.i64	q1, q11, q4
+	vadd.i64	q4, q5, q13
+	vst1.8		d16, [r2, : 64]!
+	vshl.i64	q5, q10, #4
+	vst1.8		d17, [r4, : 64]!
+	vsub.i64	q8, q14, q12
+	vshr.s64	q1, q1, #25
+	vadd.i64	q4, q4, q5
+	vadd.i64	q5, q6, q1
+	vshl.i64	q1, q1, #25
+	vadd.i64	q6, q5, q9
+	vadd.i64	q4, q4, q10
+	vshl.i64	q10, q10, #25
+	vadd.i64	q9, q4, q9
+	vsub.i64	q1, q11, q1
+	vshr.s64	q6, q6, #26
+	vsub.i64	q3, q3, q10
+	vtrn.32		d16, d2
+	vshr.s64	q9, q9, #26
+	vtrn.32		d17, d3
+	vadd.i64	q1, q2, q6
+	vst1.8		d16, [r2, : 64]
+	vshl.i64	q2, q6, #26
+	vst1.8		d17, [r4, : 64]
+	vadd.i64	q6, q7, q9
+	vtrn.32		d0, d6
+	vshl.i64	q7, q9, #26
+	vtrn.32		d1, d7
+	vsub.i64	q2, q5, q2
+	add		r2, r2, #16
+	vsub.i64	q3, q4, q7
+	vst1.8		d0, [r2, : 64]
+	add		r4, r4, #16
+	vst1.8		d1, [r4, : 64]
+	vtrn.32		d4, d2
+	vtrn.32		d5, d3
+	sub		r2, r2, #8
+	sub		r4, r4, #8
+	vtrn.32		d6, d12
+	vtrn.32		d7, d13
+	vst1.8		d4, [r2, : 64]
+	vst1.8		d5, [r4, : 64]
+	sub		r2, r2, #24
+	sub		r4, r4, #24
+	vst1.8		d6, [r2, : 64]
+	vst1.8		d7, [r4, : 64]
+	add		r2, r3, #336
+	add		r4, r3, #288
+	vld1.8		{d0-d1}, [r2, : 128]!
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vadd.i32	q0, q0, q1
+	vld1.8		{d2-d3}, [r2, : 128]!
+	vld1.8		{d4-d5}, [r4, : 128]!
+	vadd.i32	q1, q1, q2
+	add		r5, r3, #288
+	vld1.8		{d4}, [r2, : 64]
+	vld1.8		{d6}, [r4, : 64]
+	vadd.i32	q2, q2, q3
+	vst1.8		{d0-d1}, [r5, : 128]!
+	vst1.8		{d2-d3}, [r5, : 128]!
+	vst1.8		d4, [r5, : 64]
+	add		r2, r3, #48
+	add		r4, r3, #144
+	vld1.8		{d0-d1}, [r4, : 128]!
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vld1.8		{d4}, [r4, : 64]
+	add		r4, r3, #288
+	vld1.8		{d6-d7}, [r4, : 128]!
+	vtrn.32		q0, q3
+	vld1.8		{d8-d9}, [r4, : 128]!
+	vshl.i32	q5, q0, #4
+	vtrn.32		q1, q4
+	vshl.i32	q6, q3, #4
+	vadd.i32	q5, q5, q0
+	vadd.i32	q6, q6, q3
+	vshl.i32	q7, q1, #4
+	vld1.8		{d5}, [r4, : 64]
+	vshl.i32	q8, q4, #4
+	vtrn.32		d4, d5
+	vadd.i32	q7, q7, q1
+	vadd.i32	q8, q8, q4
+	vld1.8		{d18-d19}, [r2, : 128]!
+	vshl.i32	q10, q2, #4
+	vld1.8		{d22-d23}, [r2, : 128]!
+	vadd.i32	q10, q10, q2
+	vld1.8		{d24}, [r2, : 64]
+	vadd.i32	q5, q5, q0
+	add		r2, r3, #240
+	vld1.8		{d26-d27}, [r2, : 128]!
+	vadd.i32	q6, q6, q3
+	vld1.8		{d28-d29}, [r2, : 128]!
+	vadd.i32	q8, q8, q4
+	vld1.8		{d25}, [r2, : 64]
+	vadd.i32	q10, q10, q2
+	vtrn.32		q9, q13
+	vadd.i32	q7, q7, q1
+	vadd.i32	q5, q5, q0
+	vtrn.32		q11, q14
+	vadd.i32	q6, q6, q3
+	add		r2, sp, #528
+	vadd.i32	q10, q10, q2
+	vtrn.32		d24, d25
+	vst1.8		{d12-d13}, [r2, : 128]!
+	vshl.i32	q6, q13, #1
+	vst1.8		{d20-d21}, [r2, : 128]!
+	vshl.i32	q10, q14, #1
+	vst1.8		{d12-d13}, [r2, : 128]!
+	vshl.i32	q15, q12, #1
+	vadd.i32	q8, q8, q4
+	vext.32		d10, d31, d30, #0
+	vadd.i32	q7, q7, q1
+	vst1.8		{d16-d17}, [r2, : 128]!
+	vmull.s32	q8, d18, d5
+	vmlal.s32	q8, d26, d4
+	vmlal.s32	q8, d19, d9
+	vmlal.s32	q8, d27, d3
+	vmlal.s32	q8, d22, d8
+	vmlal.s32	q8, d28, d2
+	vmlal.s32	q8, d23, d7
+	vmlal.s32	q8, d29, d1
+	vmlal.s32	q8, d24, d6
+	vmlal.s32	q8, d25, d0
+	vst1.8		{d14-d15}, [r2, : 128]!
+	vmull.s32	q2, d18, d4
+	vmlal.s32	q2, d12, d9
+	vmlal.s32	q2, d13, d8
+	vmlal.s32	q2, d19, d3
+	vmlal.s32	q2, d22, d2
+	vmlal.s32	q2, d23, d1
+	vmlal.s32	q2, d24, d0
+	vst1.8		{d20-d21}, [r2, : 128]!
+	vmull.s32	q7, d18, d9
+	vmlal.s32	q7, d26, d3
+	vmlal.s32	q7, d19, d8
+	vmlal.s32	q7, d27, d2
+	vmlal.s32	q7, d22, d7
+	vmlal.s32	q7, d28, d1
+	vmlal.s32	q7, d23, d6
+	vmlal.s32	q7, d29, d0
+	vst1.8		{d10-d11}, [r2, : 128]!
+	vmull.s32	q5, d18, d3
+	vmlal.s32	q5, d19, d2
+	vmlal.s32	q5, d22, d1
+	vmlal.s32	q5, d23, d0
+	vmlal.s32	q5, d12, d8
+	vst1.8		{d16-d17}, [r2, : 128]!
+	vmull.s32	q4, d18, d8
+	vmlal.s32	q4, d26, d2
+	vmlal.s32	q4, d19, d7
+	vmlal.s32	q4, d27, d1
+	vmlal.s32	q4, d22, d6
+	vmlal.s32	q4, d28, d0
+	vmull.s32	q8, d18, d7
+	vmlal.s32	q8, d26, d1
+	vmlal.s32	q8, d19, d6
+	vmlal.s32	q8, d27, d0
+	add		r2, sp, #544
+	vld1.8		{d20-d21}, [r2, : 128]
+	vmlal.s32	q7, d24, d21
+	vmlal.s32	q7, d25, d20
+	vmlal.s32	q4, d23, d21
+	vmlal.s32	q4, d29, d20
+	vmlal.s32	q8, d22, d21
+	vmlal.s32	q8, d28, d20
+	vmlal.s32	q5, d24, d20
+	vst1.8		{d14-d15}, [r2, : 128]
+	vmull.s32	q7, d18, d6
+	vmlal.s32	q7, d26, d0
+	add		r2, sp, #624
+	vld1.8		{d30-d31}, [r2, : 128]
+	vmlal.s32	q2, d30, d21
+	vmlal.s32	q7, d19, d21
+	vmlal.s32	q7, d27, d20
+	add		r2, sp, #592
+	vld1.8		{d26-d27}, [r2, : 128]
+	vmlal.s32	q4, d25, d27
+	vmlal.s32	q8, d29, d27
+	vmlal.s32	q8, d25, d26
+	vmlal.s32	q7, d28, d27
+	vmlal.s32	q7, d29, d26
+	add		r2, sp, #576
+	vld1.8		{d28-d29}, [r2, : 128]
+	vmlal.s32	q4, d24, d29
+	vmlal.s32	q8, d23, d29
+	vmlal.s32	q8, d24, d28
+	vmlal.s32	q7, d22, d29
+	vmlal.s32	q7, d23, d28
+	vst1.8		{d8-d9}, [r2, : 128]
+	add		r2, sp, #528
+	vld1.8		{d8-d9}, [r2, : 128]
+	vmlal.s32	q7, d24, d9
+	vmlal.s32	q7, d25, d31
+	vmull.s32	q1, d18, d2
+	vmlal.s32	q1, d19, d1
+	vmlal.s32	q1, d22, d0
+	vmlal.s32	q1, d24, d27
+	vmlal.s32	q1, d23, d20
+	vmlal.s32	q1, d12, d7
+	vmlal.s32	q1, d13, d6
+	vmull.s32	q6, d18, d1
+	vmlal.s32	q6, d19, d0
+	vmlal.s32	q6, d23, d27
+	vmlal.s32	q6, d22, d20
+	vmlal.s32	q6, d24, d26
+	vmull.s32	q0, d18, d0
+	vmlal.s32	q0, d22, d27
+	vmlal.s32	q0, d23, d26
+	vmlal.s32	q0, d24, d31
+	vmlal.s32	q0, d19, d20
+	add		r2, sp, #608
+	vld1.8		{d18-d19}, [r2, : 128]
+	vmlal.s32	q2, d18, d7
+	vmlal.s32	q5, d18, d6
+	vmlal.s32	q1, d18, d21
+	vmlal.s32	q0, d18, d28
+	vmlal.s32	q6, d18, d29
+	vmlal.s32	q2, d19, d6
+	vmlal.s32	q5, d19, d21
+	vmlal.s32	q1, d19, d29
+	vmlal.s32	q0, d19, d9
+	vmlal.s32	q6, d19, d28
+	add		r2, sp, #560
+	vld1.8		{d18-d19}, [r2, : 128]
+	add		r2, sp, #480
+	vld1.8		{d22-d23}, [r2, : 128]
+	vmlal.s32	q5, d19, d7
+	vmlal.s32	q0, d18, d21
+	vmlal.s32	q0, d19, d29
+	vmlal.s32	q6, d18, d6
+	add		r2, sp, #496
+	vld1.8		{d6-d7}, [r2, : 128]
+	vmlal.s32	q6, d19, d21
+	add		r2, sp, #544
+	vld1.8		{d18-d19}, [r2, : 128]
+	vmlal.s32	q0, d30, d8
+	add		r2, sp, #640
+	vld1.8		{d20-d21}, [r2, : 128]
+	vmlal.s32	q5, d30, d29
+	add		r2, sp, #576
+	vld1.8		{d24-d25}, [r2, : 128]
+	vmlal.s32	q1, d30, d28
+	vadd.i64	q13, q0, q11
+	vadd.i64	q14, q5, q11
+	vmlal.s32	q6, d30, d9
+	vshr.s64	q4, q13, #26
+	vshr.s64	q13, q14, #26
+	vadd.i64	q7, q7, q4
+	vshl.i64	q4, q4, #26
+	vadd.i64	q14, q7, q3
+	vadd.i64	q9, q9, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q15, q9, q3
+	vsub.i64	q0, q0, q4
+	vshr.s64	q4, q14, #25
+	vsub.i64	q5, q5, q13
+	vshr.s64	q13, q15, #25
+	vadd.i64	q6, q6, q4
+	vshl.i64	q4, q4, #25
+	vadd.i64	q14, q6, q11
+	vadd.i64	q2, q2, q13
+	vsub.i64	q4, q7, q4
+	vshr.s64	q7, q14, #26
+	vshl.i64	q13, q13, #25
+	vadd.i64	q14, q2, q11
+	vadd.i64	q8, q8, q7
+	vshl.i64	q7, q7, #26
+	vadd.i64	q15, q8, q3
+	vsub.i64	q9, q9, q13
+	vshr.s64	q13, q14, #26
+	vsub.i64	q6, q6, q7
+	vshr.s64	q7, q15, #25
+	vadd.i64	q10, q10, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q14, q10, q3
+	vadd.i64	q1, q1, q7
+	add		r2, r3, #240
+	vshl.i64	q7, q7, #25
+	add		r4, r3, #144
+	vadd.i64	q15, q1, q11
+	add		r2, r2, #8
+	vsub.i64	q2, q2, q13
+	add		r4, r4, #8
+	vshr.s64	q13, q14, #25
+	vsub.i64	q7, q8, q7
+	vshr.s64	q8, q15, #26
+	vadd.i64	q14, q13, q13
+	vadd.i64	q12, q12, q8
+	vtrn.32		d12, d14
+	vshl.i64	q8, q8, #26
+	vtrn.32		d13, d15
+	vadd.i64	q3, q12, q3
+	vadd.i64	q0, q0, q14
+	vst1.8		d12, [r2, : 64]!
+	vshl.i64	q7, q13, #4
+	vst1.8		d13, [r4, : 64]!
+	vsub.i64	q1, q1, q8
+	vshr.s64	q3, q3, #25
+	vadd.i64	q0, q0, q7
+	vadd.i64	q5, q5, q3
+	vshl.i64	q3, q3, #25
+	vadd.i64	q6, q5, q11
+	vadd.i64	q0, q0, q13
+	vshl.i64	q7, q13, #25
+	vadd.i64	q8, q0, q11
+	vsub.i64	q3, q12, q3
+	vshr.s64	q6, q6, #26
+	vsub.i64	q7, q10, q7
+	vtrn.32		d2, d6
+	vshr.s64	q8, q8, #26
+	vtrn.32		d3, d7
+	vadd.i64	q3, q9, q6
+	vst1.8		d2, [r2, : 64]
+	vshl.i64	q6, q6, #26
+	vst1.8		d3, [r4, : 64]
+	vadd.i64	q1, q4, q8
+	vtrn.32		d4, d14
+	vshl.i64	q4, q8, #26
+	vtrn.32		d5, d15
+	vsub.i64	q5, q5, q6
+	add		r2, r2, #16
+	vsub.i64	q0, q0, q4
+	vst1.8		d4, [r2, : 64]
+	add		r4, r4, #16
+	vst1.8		d5, [r4, : 64]
+	vtrn.32		d10, d6
+	vtrn.32		d11, d7
+	sub		r2, r2, #8
+	sub		r4, r4, #8
+	vtrn.32		d0, d2
+	vtrn.32		d1, d3
+	vst1.8		d10, [r2, : 64]
+	vst1.8		d11, [r4, : 64]
+	sub		r2, r2, #24
+	sub		r4, r4, #24
+	vst1.8		d0, [r2, : 64]
+	vst1.8		d1, [r4, : 64]
+	ldr		r2, [sp, #456]
+	ldr		r4, [sp, #460]
+	subs		r5, r2, #1
+	bge		.Lmainloop
+	add		r1, r3, #144
+	add		r2, r3, #336
+	vld1.8		{d0-d1}, [r1, : 128]!
+	vld1.8		{d2-d3}, [r1, : 128]!
+	vld1.8		{d4}, [r1, : 64]
+	vst1.8		{d0-d1}, [r2, : 128]!
+	vst1.8		{d2-d3}, [r2, : 128]!
+	vst1.8		d4, [r2, : 64]
+	movw		r1, #0
+.Linvertloop:
+	add		r2, r3, #144
+	movw		r4, #0
+	movw		r5, #2
+	cmp		r1, #1
+	moveq		r5, #1
+	addeq		r2, r3, #336
+	addeq		r4, r3, #48
+	cmp		r1, #2
+	moveq		r5, #1
+	addeq		r2, r3, #48
+	cmp		r1, #3
+	moveq		r5, #5
+	addeq		r4, r3, #336
+	cmp		r1, #4
+	moveq		r5, #10
+	cmp		r1, #5
+	moveq		r5, #20
+	cmp		r1, #6
+	moveq		r5, #10
+	addeq		r2, r3, #336
+	addeq		r4, r3, #336
+	cmp		r1, #7
+	moveq		r5, #50
+	cmp		r1, #8
+	moveq		r5, #100
+	cmp		r1, #9
+	moveq		r5, #50
+	addeq		r2, r3, #336
+	cmp		r1, #10
+	moveq		r5, #5
+	addeq		r2, r3, #48
+	cmp		r1, #11
+	moveq		r5, #0
+	addeq		r2, r3, #96
+	add		r6, r3, #144
+	add		r7, r3, #288
+	vld1.8		{d0-d1}, [r6, : 128]!
+	vld1.8		{d2-d3}, [r6, : 128]!
+	vld1.8		{d4}, [r6, : 64]
+	vst1.8		{d0-d1}, [r7, : 128]!
+	vst1.8		{d2-d3}, [r7, : 128]!
+	vst1.8		d4, [r7, : 64]
+	cmp		r5, #0
+	beq		.Lskipsquaringloop
+.Lsquaringloop:
+	add		r6, r3, #288
+	add		r7, r3, #288
+	add		r8, r3, #288
+	vmov.i32	q0, #19
+	vmov.i32	q1, #0
+	vmov.i32	q2, #1
+	vzip.i32	q1, q2
+	vld1.8		{d4-d5}, [r7, : 128]!
+	vld1.8		{d6-d7}, [r7, : 128]!
+	vld1.8		{d9}, [r7, : 64]
+	vld1.8		{d10-d11}, [r6, : 128]!
+	add		r7, sp, #384
+	vld1.8		{d12-d13}, [r6, : 128]!
+	vmul.i32	q7, q2, q0
+	vld1.8		{d8}, [r6, : 64]
+	vext.32		d17, d11, d10, #1
+	vmul.i32	q9, q3, q0
+	vext.32		d16, d10, d8, #1
+	vshl.u32	q10, q5, q1
+	vext.32		d22, d14, d4, #1
+	vext.32		d24, d18, d6, #1
+	vshl.u32	q13, q6, q1
+	vshl.u32	d28, d8, d2
+	vrev64.i32	d22, d22
+	vmul.i32	d1, d9, d1
+	vrev64.i32	d24, d24
+	vext.32		d29, d8, d13, #1
+	vext.32		d0, d1, d9, #1
+	vrev64.i32	d0, d0
+	vext.32		d2, d9, d1, #1
+	vext.32		d23, d15, d5, #1
+	vmull.s32	q4, d20, d4
+	vrev64.i32	d23, d23
+	vmlal.s32	q4, d21, d1
+	vrev64.i32	d2, d2
+	vmlal.s32	q4, d26, d19
+	vext.32		d3, d5, d15, #1
+	vmlal.s32	q4, d27, d18
+	vrev64.i32	d3, d3
+	vmlal.s32	q4, d28, d15
+	vext.32		d14, d12, d11, #1
+	vmull.s32	q5, d16, d23
+	vext.32		d15, d13, d12, #1
+	vmlal.s32	q5, d17, d4
+	vst1.8		d8, [r7, : 64]!
+	vmlal.s32	q5, d14, d1
+	vext.32		d12, d9, d8, #0
+	vmlal.s32	q5, d15, d19
+	vmov.i64	d13, #0
+	vmlal.s32	q5, d29, d18
+	vext.32		d25, d19, d7, #1
+	vmlal.s32	q6, d20, d5
+	vrev64.i32	d25, d25
+	vmlal.s32	q6, d21, d4
+	vst1.8		d11, [r7, : 64]!
+	vmlal.s32	q6, d26, d1
+	vext.32		d9, d10, d10, #0
+	vmlal.s32	q6, d27, d19
+	vmov.i64	d8, #0
+	vmlal.s32	q6, d28, d18
+	vmlal.s32	q4, d16, d24
+	vmlal.s32	q4, d17, d5
+	vmlal.s32	q4, d14, d4
+	vst1.8		d12, [r7, : 64]!
+	vmlal.s32	q4, d15, d1
+	vext.32		d10, d13, d12, #0
+	vmlal.s32	q4, d29, d19
+	vmov.i64	d11, #0
+	vmlal.s32	q5, d20, d6
+	vmlal.s32	q5, d21, d5
+	vmlal.s32	q5, d26, d4
+	vext.32		d13, d8, d8, #0
+	vmlal.s32	q5, d27, d1
+	vmov.i64	d12, #0
+	vmlal.s32	q5, d28, d19
+	vst1.8		d9, [r7, : 64]!
+	vmlal.s32	q6, d16, d25
+	vmlal.s32	q6, d17, d6
+	vst1.8		d10, [r7, : 64]
+	vmlal.s32	q6, d14, d5
+	vext.32		d8, d11, d10, #0
+	vmlal.s32	q6, d15, d4
+	vmov.i64	d9, #0
+	vmlal.s32	q6, d29, d1
+	vmlal.s32	q4, d20, d7
+	vmlal.s32	q4, d21, d6
+	vmlal.s32	q4, d26, d5
+	vext.32		d11, d12, d12, #0
+	vmlal.s32	q4, d27, d4
+	vmov.i64	d10, #0
+	vmlal.s32	q4, d28, d1
+	vmlal.s32	q5, d16, d0
+	sub		r6, r7, #32
+	vmlal.s32	q5, d17, d7
+	vmlal.s32	q5, d14, d6
+	vext.32		d30, d9, d8, #0
+	vmlal.s32	q5, d15, d5
+	vld1.8		{d31}, [r6, : 64]!
+	vmlal.s32	q5, d29, d4
+	vmlal.s32	q15, d20, d0
+	vext.32		d0, d6, d18, #1
+	vmlal.s32	q15, d21, d25
+	vrev64.i32	d0, d0
+	vmlal.s32	q15, d26, d24
+	vext.32		d1, d7, d19, #1
+	vext.32		d7, d10, d10, #0
+	vmlal.s32	q15, d27, d23
+	vrev64.i32	d1, d1
+	vld1.8		{d6}, [r6, : 64]
+	vmlal.s32	q15, d28, d22
+	vmlal.s32	q3, d16, d4
+	add		r6, r6, #24
+	vmlal.s32	q3, d17, d2
+	vext.32		d4, d31, d30, #0
+	vmov		d17, d11
+	vmlal.s32	q3, d14, d1
+	vext.32		d11, d13, d13, #0
+	vext.32		d13, d30, d30, #0
+	vmlal.s32	q3, d15, d0
+	vext.32		d1, d8, d8, #0
+	vmlal.s32	q3, d29, d3
+	vld1.8		{d5}, [r6, : 64]
+	sub		r6, r6, #16
+	vext.32		d10, d6, d6, #0
+	vmov.i32	q1, #0xffffffff
+	vshl.i64	q4, q1, #25
+	add		r7, sp, #480
+	vld1.8		{d14-d15}, [r7, : 128]
+	vadd.i64	q9, q2, q7
+	vshl.i64	q1, q1, #26
+	vshr.s64	q10, q9, #26
+	vld1.8		{d0}, [r6, : 64]!
+	vadd.i64	q5, q5, q10
+	vand		q9, q9, q1
+	vld1.8		{d16}, [r6, : 64]!
+	add		r6, sp, #496
+	vld1.8		{d20-d21}, [r6, : 128]
+	vadd.i64	q11, q5, q10
+	vsub.i64	q2, q2, q9
+	vshr.s64	q9, q11, #25
+	vext.32		d12, d5, d4, #0
+	vand		q11, q11, q4
+	vadd.i64	q0, q0, q9
+	vmov		d19, d7
+	vadd.i64	q3, q0, q7
+	vsub.i64	q5, q5, q11
+	vshr.s64	q11, q3, #26
+	vext.32		d18, d11, d10, #0
+	vand		q3, q3, q1
+	vadd.i64	q8, q8, q11
+	vadd.i64	q11, q8, q10
+	vsub.i64	q0, q0, q3
+	vshr.s64	q3, q11, #25
+	vand		q11, q11, q4
+	vadd.i64	q3, q6, q3
+	vadd.i64	q6, q3, q7
+	vsub.i64	q8, q8, q11
+	vshr.s64	q11, q6, #26
+	vand		q6, q6, q1
+	vadd.i64	q9, q9, q11
+	vadd.i64	d25, d19, d21
+	vsub.i64	q3, q3, q6
+	vshr.s64	d23, d25, #25
+	vand		q4, q12, q4
+	vadd.i64	d21, d23, d23
+	vshl.i64	d25, d23, #4
+	vadd.i64	d21, d21, d23
+	vadd.i64	d25, d25, d21
+	vadd.i64	d4, d4, d25
+	vzip.i32	q0, q8
+	vadd.i64	d12, d4, d14
+	add		r6, r8, #8
+	vst1.8		d0, [r6, : 64]
+	vsub.i64	d19, d19, d9
+	add		r6, r6, #16
+	vst1.8		d16, [r6, : 64]
+	vshr.s64	d22, d12, #26
+	vand		q0, q6, q1
+	vadd.i64	d10, d10, d22
+	vzip.i32	q3, q9
+	vsub.i64	d4, d4, d0
+	sub		r6, r6, #8
+	vst1.8		d6, [r6, : 64]
+	add		r6, r6, #16
+	vst1.8		d18, [r6, : 64]
+	vzip.i32	q2, q5
+	sub		r6, r6, #32
+	vst1.8		d4, [r6, : 64]
+	subs		r5, r5, #1
+	bhi		.Lsquaringloop
+.Lskipsquaringloop:
+	mov		r2, r2
+	add		r5, r3, #288
+	add		r6, r3, #144
+	vmov.i32	q0, #19
+	vmov.i32	q1, #0
+	vmov.i32	q2, #1
+	vzip.i32	q1, q2
+	vld1.8		{d4-d5}, [r5, : 128]!
+	vld1.8		{d6-d7}, [r5, : 128]!
+	vld1.8		{d9}, [r5, : 64]
+	vld1.8		{d10-d11}, [r2, : 128]!
+	add		r5, sp, #384
+	vld1.8		{d12-d13}, [r2, : 128]!
+	vmul.i32	q7, q2, q0
+	vld1.8		{d8}, [r2, : 64]
+	vext.32		d17, d11, d10, #1
+	vmul.i32	q9, q3, q0
+	vext.32		d16, d10, d8, #1
+	vshl.u32	q10, q5, q1
+	vext.32		d22, d14, d4, #1
+	vext.32		d24, d18, d6, #1
+	vshl.u32	q13, q6, q1
+	vshl.u32	d28, d8, d2
+	vrev64.i32	d22, d22
+	vmul.i32	d1, d9, d1
+	vrev64.i32	d24, d24
+	vext.32		d29, d8, d13, #1
+	vext.32		d0, d1, d9, #1
+	vrev64.i32	d0, d0
+	vext.32		d2, d9, d1, #1
+	vext.32		d23, d15, d5, #1
+	vmull.s32	q4, d20, d4
+	vrev64.i32	d23, d23
+	vmlal.s32	q4, d21, d1
+	vrev64.i32	d2, d2
+	vmlal.s32	q4, d26, d19
+	vext.32		d3, d5, d15, #1
+	vmlal.s32	q4, d27, d18
+	vrev64.i32	d3, d3
+	vmlal.s32	q4, d28, d15
+	vext.32		d14, d12, d11, #1
+	vmull.s32	q5, d16, d23
+	vext.32		d15, d13, d12, #1
+	vmlal.s32	q5, d17, d4
+	vst1.8		d8, [r5, : 64]!
+	vmlal.s32	q5, d14, d1
+	vext.32		d12, d9, d8, #0
+	vmlal.s32	q5, d15, d19
+	vmov.i64	d13, #0
+	vmlal.s32	q5, d29, d18
+	vext.32		d25, d19, d7, #1
+	vmlal.s32	q6, d20, d5
+	vrev64.i32	d25, d25
+	vmlal.s32	q6, d21, d4
+	vst1.8		d11, [r5, : 64]!
+	vmlal.s32	q6, d26, d1
+	vext.32		d9, d10, d10, #0
+	vmlal.s32	q6, d27, d19
+	vmov.i64	d8, #0
+	vmlal.s32	q6, d28, d18
+	vmlal.s32	q4, d16, d24
+	vmlal.s32	q4, d17, d5
+	vmlal.s32	q4, d14, d4
+	vst1.8		d12, [r5, : 64]!
+	vmlal.s32	q4, d15, d1
+	vext.32		d10, d13, d12, #0
+	vmlal.s32	q4, d29, d19
+	vmov.i64	d11, #0
+	vmlal.s32	q5, d20, d6
+	vmlal.s32	q5, d21, d5
+	vmlal.s32	q5, d26, d4
+	vext.32		d13, d8, d8, #0
+	vmlal.s32	q5, d27, d1
+	vmov.i64	d12, #0
+	vmlal.s32	q5, d28, d19
+	vst1.8		d9, [r5, : 64]!
+	vmlal.s32	q6, d16, d25
+	vmlal.s32	q6, d17, d6
+	vst1.8		d10, [r5, : 64]
+	vmlal.s32	q6, d14, d5
+	vext.32		d8, d11, d10, #0
+	vmlal.s32	q6, d15, d4
+	vmov.i64	d9, #0
+	vmlal.s32	q6, d29, d1
+	vmlal.s32	q4, d20, d7
+	vmlal.s32	q4, d21, d6
+	vmlal.s32	q4, d26, d5
+	vext.32		d11, d12, d12, #0
+	vmlal.s32	q4, d27, d4
+	vmov.i64	d10, #0
+	vmlal.s32	q4, d28, d1
+	vmlal.s32	q5, d16, d0
+	sub		r2, r5, #32
+	vmlal.s32	q5, d17, d7
+	vmlal.s32	q5, d14, d6
+	vext.32		d30, d9, d8, #0
+	vmlal.s32	q5, d15, d5
+	vld1.8		{d31}, [r2, : 64]!
+	vmlal.s32	q5, d29, d4
+	vmlal.s32	q15, d20, d0
+	vext.32		d0, d6, d18, #1
+	vmlal.s32	q15, d21, d25
+	vrev64.i32	d0, d0
+	vmlal.s32	q15, d26, d24
+	vext.32		d1, d7, d19, #1
+	vext.32		d7, d10, d10, #0
+	vmlal.s32	q15, d27, d23
+	vrev64.i32	d1, d1
+	vld1.8		{d6}, [r2, : 64]
+	vmlal.s32	q15, d28, d22
+	vmlal.s32	q3, d16, d4
+	add		r2, r2, #24
+	vmlal.s32	q3, d17, d2
+	vext.32		d4, d31, d30, #0
+	vmov		d17, d11
+	vmlal.s32	q3, d14, d1
+	vext.32		d11, d13, d13, #0
+	vext.32		d13, d30, d30, #0
+	vmlal.s32	q3, d15, d0
+	vext.32		d1, d8, d8, #0
+	vmlal.s32	q3, d29, d3
+	vld1.8		{d5}, [r2, : 64]
+	sub		r2, r2, #16
+	vext.32		d10, d6, d6, #0
+	vmov.i32	q1, #0xffffffff
+	vshl.i64	q4, q1, #25
+	add		r5, sp, #480
+	vld1.8		{d14-d15}, [r5, : 128]
+	vadd.i64	q9, q2, q7
+	vshl.i64	q1, q1, #26
+	vshr.s64	q10, q9, #26
+	vld1.8		{d0}, [r2, : 64]!
+	vadd.i64	q5, q5, q10
+	vand		q9, q9, q1
+	vld1.8		{d16}, [r2, : 64]!
+	add		r2, sp, #496
+	vld1.8		{d20-d21}, [r2, : 128]
+	vadd.i64	q11, q5, q10
+	vsub.i64	q2, q2, q9
+	vshr.s64	q9, q11, #25
+	vext.32		d12, d5, d4, #0
+	vand		q11, q11, q4
+	vadd.i64	q0, q0, q9
+	vmov		d19, d7
+	vadd.i64	q3, q0, q7
+	vsub.i64	q5, q5, q11
+	vshr.s64	q11, q3, #26
+	vext.32		d18, d11, d10, #0
+	vand		q3, q3, q1
+	vadd.i64	q8, q8, q11
+	vadd.i64	q11, q8, q10
+	vsub.i64	q0, q0, q3
+	vshr.s64	q3, q11, #25
+	vand		q11, q11, q4
+	vadd.i64	q3, q6, q3
+	vadd.i64	q6, q3, q7
+	vsub.i64	q8, q8, q11
+	vshr.s64	q11, q6, #26
+	vand		q6, q6, q1
+	vadd.i64	q9, q9, q11
+	vadd.i64	d25, d19, d21
+	vsub.i64	q3, q3, q6
+	vshr.s64	d23, d25, #25
+	vand		q4, q12, q4
+	vadd.i64	d21, d23, d23
+	vshl.i64	d25, d23, #4
+	vadd.i64	d21, d21, d23
+	vadd.i64	d25, d25, d21
+	vadd.i64	d4, d4, d25
+	vzip.i32	q0, q8
+	vadd.i64	d12, d4, d14
+	add		r2, r6, #8
+	vst1.8		d0, [r2, : 64]
+	vsub.i64	d19, d19, d9
+	add		r2, r2, #16
+	vst1.8		d16, [r2, : 64]
+	vshr.s64	d22, d12, #26
+	vand		q0, q6, q1
+	vadd.i64	d10, d10, d22
+	vzip.i32	q3, q9
+	vsub.i64	d4, d4, d0
+	sub		r2, r2, #8
+	vst1.8		d6, [r2, : 64]
+	add		r2, r2, #16
+	vst1.8		d18, [r2, : 64]
+	vzip.i32	q2, q5
+	sub		r2, r2, #32
+	vst1.8		d4, [r2, : 64]
+	cmp		r4, #0
+	beq		.Lskippostcopy
+	add		r2, r3, #144
+	mov		r4, r4
+	vld1.8		{d0-d1}, [r2, : 128]!
+	vld1.8		{d2-d3}, [r2, : 128]!
+	vld1.8		{d4}, [r2, : 64]
+	vst1.8		{d0-d1}, [r4, : 128]!
+	vst1.8		{d2-d3}, [r4, : 128]!
+	vst1.8		d4, [r4, : 64]
+.Lskippostcopy:
+	cmp		r1, #1
+	bne		.Lskipfinalcopy
+	add		r2, r3, #288
+	add		r4, r3, #144
+	vld1.8		{d0-d1}, [r2, : 128]!
+	vld1.8		{d2-d3}, [r2, : 128]!
+	vld1.8		{d4}, [r2, : 64]
+	vst1.8		{d0-d1}, [r4, : 128]!
+	vst1.8		{d2-d3}, [r4, : 128]!
+	vst1.8		d4, [r4, : 64]
+.Lskipfinalcopy:
+	add		r1, r1, #1
+	cmp		r1, #12
+	blo		.Linvertloop
+	add		r1, r3, #144
+	ldr		r2, [r1], #4
+	ldr		r3, [r1], #4
+	ldr		r4, [r1], #4
+	ldr		r5, [r1], #4
+	ldr		r6, [r1], #4
+	ldr		r7, [r1], #4
+	ldr		r8, [r1], #4
+	ldr		r9, [r1], #4
+	ldr		r10, [r1], #4
+	ldr		r1, [r1]
+	add		r11, r1, r1, LSL #4
+	add		r11, r11, r1, LSL #1
+	add		r11, r11, #16777216
+	mov		r11, r11, ASR #25
+	add		r11, r11, r2
+	mov		r11, r11, ASR #26
+	add		r11, r11, r3
+	mov		r11, r11, ASR #25
+	add		r11, r11, r4
+	mov		r11, r11, ASR #26
+	add		r11, r11, r5
+	mov		r11, r11, ASR #25
+	add		r11, r11, r6
+	mov		r11, r11, ASR #26
+	add		r11, r11, r7
+	mov		r11, r11, ASR #25
+	add		r11, r11, r8
+	mov		r11, r11, ASR #26
+	add		r11, r11, r9
+	mov		r11, r11, ASR #25
+	add		r11, r11, r10
+	mov		r11, r11, ASR #26
+	add		r11, r11, r1
+	mov		r11, r11, ASR #25
+	add		r2, r2, r11
+	add		r2, r2, r11, LSL #1
+	add		r2, r2, r11, LSL #4
+	mov		r11, r2, ASR #26
+	add		r3, r3, r11
+	sub		r2, r2, r11, LSL #26
+	mov		r11, r3, ASR #25
+	add		r4, r4, r11
+	sub		r3, r3, r11, LSL #25
+	mov		r11, r4, ASR #26
+	add		r5, r5, r11
+	sub		r4, r4, r11, LSL #26
+	mov		r11, r5, ASR #25
+	add		r6, r6, r11
+	sub		r5, r5, r11, LSL #25
+	mov		r11, r6, ASR #26
+	add		r7, r7, r11
+	sub		r6, r6, r11, LSL #26
+	mov		r11, r7, ASR #25
+	add		r8, r8, r11
+	sub		r7, r7, r11, LSL #25
+	mov		r11, r8, ASR #26
+	add		r9, r9, r11
+	sub		r8, r8, r11, LSL #26
+	mov		r11, r9, ASR #25
+	add		r10, r10, r11
+	sub		r9, r9, r11, LSL #25
+	mov		r11, r10, ASR #26
+	add		r1, r1, r11
+	sub		r10, r10, r11, LSL #26
+	mov		r11, r1, ASR #25
+	sub		r1, r1, r11, LSL #25
+	add		r2, r2, r3, LSL #26
+	mov		r3, r3, LSR #6
+	add		r3, r3, r4, LSL #19
+	mov		r4, r4, LSR #13
+	add		r4, r4, r5, LSL #13
+	mov		r5, r5, LSR #19
+	add		r5, r5, r6, LSL #6
+	add		r6, r7, r8, LSL #25
+	mov		r7, r8, LSR #7
+	add		r7, r7, r9, LSL #19
+	mov		r8, r9, LSR #13
+	add		r8, r8, r10, LSL #12
+	mov		r9, r10, LSR #20
+	add		r1, r9, r1, LSL #6
+	str		r2, [r0]
+	str		r3, [r0, #4]
+	str		r4, [r0, #8]
+	str		r5, [r0, #12]
+	str		r6, [r0, #16]
+	str		r7, [r0, #20]
+	str		r8, [r0, #24]
+	str		r1, [r0, #28]
+	movw		r0, #0
+	mov		sp, ip
+	pop		{r4-r11, pc}
+ENDPROC(curve25519_neon)
diff --git a/arch/arm/crypto/curve25519-glue.c b/arch/arm/crypto/curve25519-glue.c
new file mode 100644
index 000000000000..2e9e12d2f642
--- /dev/null
+++ b/arch/arm/crypto/curve25519-glue.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * Based on public domain code from Daniel J. Bernstein and Peter Schwabe. This
+ * began from SUPERCOP's curve25519/neon2/scalarmult.s, but has subsequently been
+ * manually reworked for use in kernel space.
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/internal/kpp.h>
+#include <crypto/internal/simd.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/jump_label.h>
+#include <crypto/curve25519.h>
+
+asmlinkage void curve25519_neon(u8 mypublic[CURVE25519_KEY_SIZE],
+				const u8 secret[CURVE25519_KEY_SIZE],
+				const u8 basepoint[CURVE25519_KEY_SIZE]);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+void curve25519_arch(u8 out[CURVE25519_KEY_SIZE],
+		     const u8 scalar[CURVE25519_KEY_SIZE],
+		     const u8 point[CURVE25519_KEY_SIZE])
+{
+	if (static_branch_likely(&have_neon) && crypto_simd_usable()) {
+		kernel_neon_begin();
+		curve25519_neon(out, scalar, point);
+		kernel_neon_end();
+	} else {
+		curve25519_generic(out, scalar, point);
+	}
+}
+EXPORT_SYMBOL(curve25519_arch);
+
+static int curve25519_set_secret(struct crypto_kpp *tfm, const void *buf,
+				 unsigned int len)
+{
+	u8 *secret = kpp_tfm_ctx(tfm);
+
+	if (!len)
+		curve25519_generate_secret(secret);
+	else if (len == CURVE25519_KEY_SIZE &&
+		 crypto_memneq(buf, curve25519_null_point, CURVE25519_KEY_SIZE))
+		memcpy(secret, buf, CURVE25519_KEY_SIZE);
+	else
+		return -EINVAL;
+	return 0;
+}
+
+static int curve25519_compute_value(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	const u8 *secret = kpp_tfm_ctx(tfm);
+	u8 public_key[CURVE25519_KEY_SIZE];
+	u8 buf[CURVE25519_KEY_SIZE];
+	int copied, nbytes;
+	u8 const *bp;
+
+	if (req->src) {
+		copied = sg_copy_to_buffer(req->src,
+					   sg_nents_for_len(req->src,
+							    CURVE25519_KEY_SIZE),
+					   public_key, CURVE25519_KEY_SIZE);
+		if (copied != CURVE25519_KEY_SIZE)
+			return -EINVAL;
+		bp = public_key;
+	} else {
+		bp = curve25519_base_point;
+	}
+
+	curve25519_arch(buf, secret, bp);
+
+	/* might want less than we've got */
+	nbytes = min_t(size_t, CURVE25519_KEY_SIZE, req->dst_len);
+	copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst,
+								nbytes),
+				     buf, nbytes);
+	if (copied != nbytes)
+		return -EINVAL;
+	return 0;
+}
+
+static unsigned int curve25519_max_size(struct crypto_kpp *tfm)
+{
+	return CURVE25519_KEY_SIZE;
+}
+
+static struct kpp_alg curve25519_alg = {
+	.base.cra_name		= "curve25519",
+	.base.cra_driver_name	= "curve25519-neon",
+	.base.cra_priority	= 200,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_ctxsize	= CURVE25519_KEY_SIZE,
+
+	.set_secret		= curve25519_set_secret,
+	.generate_public_key	= curve25519_compute_value,
+	.compute_shared_secret	= curve25519_compute_value,
+	.max_size		= curve25519_max_size,
+};
+
+static int __init mod_init(void)
+{
+	if (elf_hwcap & HWCAP_NEON) {
+		static_branch_enable(&have_neon);
+		return crypto_register_kpp(&curve25519_alg);
+	}
+	return 0;
+}
+
+static void __exit mod_exit(void)
+{
+	if (elf_hwcap & HWCAP_NEON)
+		crypto_unregister_kpp(&curve25519_alg);
+}
+
+module_init(mod_init);
+module_exit(mod_exit);
+
+MODULE_ALIAS_CRYPTO("curve25519");
+MODULE_ALIAS_CRYPTO("curve25519-neon");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/arm/crypto/ghash-ce-core.S b/arch/arm/crypto/ghash-ce-core.S
index c47fe81abcb0..534c9647726d 100644
--- a/arch/arm/crypto/ghash-ce-core.S
+++ b/arch/arm/crypto/ghash-ce-core.S
@@ -88,6 +88,7 @@
 	T3_H		.req	d17
 
 	.text
+	.arch		armv8-a
 	.fpu		crypto-neon-fp-armv8
 
 	.macro		__pmull_p64, rd, rn, rm, b1, b2, b3, b4
diff --git a/arch/arm/crypto/poly1305-armv4.pl b/arch/arm/crypto/poly1305-armv4.pl
new file mode 100644
index 000000000000..6d79498d3115
--- /dev/null
+++ b/arch/arm/crypto/poly1305-armv4.pl
@@ -0,0 +1,1236 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-1.0+ OR BSD-3-Clause
+#
+# ====================================================================
+# Written by Andy Polyakov, @dot-asm, initially for the OpenSSL
+# project.
+# ====================================================================
+#
+#			IALU(*)/gcc-4.4		NEON
+#
+# ARM11xx(ARMv6)	7.78/+100%		-
+# Cortex-A5		6.35/+130%		3.00
+# Cortex-A8		6.25/+115%		2.36
+# Cortex-A9		5.10/+95%		2.55
+# Cortex-A15		3.85/+85%		1.25(**)
+# Snapdragon S4		5.70/+100%		1.48(**)
+#
+# (*)	this is for -march=armv6, i.e. with bunch of ldrb loading data;
+# (**)	these are trade-off results, they can be improved by ~8% but at
+#	the cost of 15/12% regression on Cortex-A5/A7, it's even possible
+#	to improve Cortex-A9 result, but then A5/A7 loose more than 20%;
+
+$flavour = shift;
+if ($flavour=~/\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {} }
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
+
+($ctx,$inp,$len,$padbit)=map("r$_",(0..3));
+
+$code.=<<___;
+#ifndef	__KERNEL__
+# include "arm_arch.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ __LINUX_ARM_ARCH__
+# define poly1305_init   poly1305_init_arm
+# define poly1305_blocks poly1305_blocks_arm
+# define poly1305_emit   poly1305_emit_arm
+.globl	poly1305_blocks_neon
+#endif
+
+#if defined(__thumb2__)
+.syntax	unified
+.thumb
+#else
+.code	32
+#endif
+
+.text
+
+.globl	poly1305_emit
+.globl	poly1305_blocks
+.globl	poly1305_init
+.type	poly1305_init,%function
+.align	5
+poly1305_init:
+.Lpoly1305_init:
+	stmdb	sp!,{r4-r11}
+
+	eor	r3,r3,r3
+	cmp	$inp,#0
+	str	r3,[$ctx,#0]		@ zero hash value
+	str	r3,[$ctx,#4]
+	str	r3,[$ctx,#8]
+	str	r3,[$ctx,#12]
+	str	r3,[$ctx,#16]
+	str	r3,[$ctx,#36]		@ clear is_base2_26
+	add	$ctx,$ctx,#20
+
+#ifdef	__thumb2__
+	it	eq
+#endif
+	moveq	r0,#0
+	beq	.Lno_key
+
+#if	__ARM_MAX_ARCH__>=7
+	mov	r3,#-1
+	str	r3,[$ctx,#28]		@ impossible key power value
+# ifndef __KERNEL__
+	adr	r11,.Lpoly1305_init
+	ldr	r12,.LOPENSSL_armcap
+# endif
+#endif
+	ldrb	r4,[$inp,#0]
+	mov	r10,#0x0fffffff
+	ldrb	r5,[$inp,#1]
+	and	r3,r10,#-4		@ 0x0ffffffc
+	ldrb	r6,[$inp,#2]
+	ldrb	r7,[$inp,#3]
+	orr	r4,r4,r5,lsl#8
+	ldrb	r5,[$inp,#4]
+	orr	r4,r4,r6,lsl#16
+	ldrb	r6,[$inp,#5]
+	orr	r4,r4,r7,lsl#24
+	ldrb	r7,[$inp,#6]
+	and	r4,r4,r10
+
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+# if !defined(_WIN32)
+	ldr	r12,[r11,r12]		@ OPENSSL_armcap_P
+# endif
+# if defined(__APPLE__) || defined(_WIN32)
+	ldr	r12,[r12]
+# endif
+#endif
+	ldrb	r8,[$inp,#7]
+	orr	r5,r5,r6,lsl#8
+	ldrb	r6,[$inp,#8]
+	orr	r5,r5,r7,lsl#16
+	ldrb	r7,[$inp,#9]
+	orr	r5,r5,r8,lsl#24
+	ldrb	r8,[$inp,#10]
+	and	r5,r5,r3
+
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	tst	r12,#ARMV7_NEON		@ check for NEON
+# ifdef	__thumb2__
+	adr	r9,.Lpoly1305_blocks_neon
+	adr	r11,.Lpoly1305_blocks
+	it	ne
+	movne	r11,r9
+	adr	r12,.Lpoly1305_emit
+	orr	r11,r11,#1		@ thumb-ify addresses
+	orr	r12,r12,#1
+# else
+	add	r12,r11,#(.Lpoly1305_emit-.Lpoly1305_init)
+	ite	eq
+	addeq	r11,r11,#(.Lpoly1305_blocks-.Lpoly1305_init)
+	addne	r11,r11,#(.Lpoly1305_blocks_neon-.Lpoly1305_init)
+# endif
+#endif
+	ldrb	r9,[$inp,#11]
+	orr	r6,r6,r7,lsl#8
+	ldrb	r7,[$inp,#12]
+	orr	r6,r6,r8,lsl#16
+	ldrb	r8,[$inp,#13]
+	orr	r6,r6,r9,lsl#24
+	ldrb	r9,[$inp,#14]
+	and	r6,r6,r3
+
+	ldrb	r10,[$inp,#15]
+	orr	r7,r7,r8,lsl#8
+	str	r4,[$ctx,#0]
+	orr	r7,r7,r9,lsl#16
+	str	r5,[$ctx,#4]
+	orr	r7,r7,r10,lsl#24
+	str	r6,[$ctx,#8]
+	and	r7,r7,r3
+	str	r7,[$ctx,#12]
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	stmia	r2,{r11,r12}		@ fill functions table
+	mov	r0,#1
+#else
+	mov	r0,#0
+#endif
+.Lno_key:
+	ldmia	sp!,{r4-r11}
+#if	__ARM_ARCH__>=5
+	ret				@ bx	lr
+#else
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	bx	lr			@ interoperable with Thumb ISA:-)
+#endif
+.size	poly1305_init,.-poly1305_init
+___
+{
+my ($h0,$h1,$h2,$h3,$h4,$r0,$r1,$r2,$r3)=map("r$_",(4..12));
+my ($s1,$s2,$s3)=($r1,$r2,$r3);
+
+$code.=<<___;
+.type	poly1305_blocks,%function
+.align	5
+poly1305_blocks:
+.Lpoly1305_blocks:
+	stmdb	sp!,{r3-r11,lr}
+
+	ands	$len,$len,#-16
+	beq	.Lno_data
+
+	add	$len,$len,$inp		@ end pointer
+	sub	sp,sp,#32
+
+#if __ARM_ARCH__<7
+	ldmia	$ctx,{$h0-$r3}		@ load context
+	add	$ctx,$ctx,#20
+	str	$len,[sp,#16]		@ offload stuff
+	str	$ctx,[sp,#12]
+#else
+	ldr	lr,[$ctx,#36]		@ is_base2_26
+	ldmia	$ctx!,{$h0-$h4}		@ load hash value
+	str	$len,[sp,#16]		@ offload stuff
+	str	$ctx,[sp,#12]
+
+	adds	$r0,$h0,$h1,lsl#26	@ base 2^26 -> base 2^32
+	mov	$r1,$h1,lsr#6
+	adcs	$r1,$r1,$h2,lsl#20
+	mov	$r2,$h2,lsr#12
+	adcs	$r2,$r2,$h3,lsl#14
+	mov	$r3,$h3,lsr#18
+	adcs	$r3,$r3,$h4,lsl#8
+	mov	$len,#0
+	teq	lr,#0
+	str	$len,[$ctx,#16]		@ clear is_base2_26
+	adc	$len,$len,$h4,lsr#24
+
+	itttt	ne
+	movne	$h0,$r0			@ choose between radixes
+	movne	$h1,$r1
+	movne	$h2,$r2
+	movne	$h3,$r3
+	ldmia	$ctx,{$r0-$r3}		@ load key
+	it	ne
+	movne	$h4,$len
+#endif
+
+	mov	lr,$inp
+	cmp	$padbit,#0
+	str	$r1,[sp,#20]
+	str	$r2,[sp,#24]
+	str	$r3,[sp,#28]
+	b	.Loop
+
+.align	4
+.Loop:
+#if __ARM_ARCH__<7
+	ldrb	r0,[lr],#16		@ load input
+# ifdef	__thumb2__
+	it	hi
+# endif
+	addhi	$h4,$h4,#1		@ 1<<128
+	ldrb	r1,[lr,#-15]
+	ldrb	r2,[lr,#-14]
+	ldrb	r3,[lr,#-13]
+	orr	r1,r0,r1,lsl#8
+	ldrb	r0,[lr,#-12]
+	orr	r2,r1,r2,lsl#16
+	ldrb	r1,[lr,#-11]
+	orr	r3,r2,r3,lsl#24
+	ldrb	r2,[lr,#-10]
+	adds	$h0,$h0,r3		@ accumulate input
+
+	ldrb	r3,[lr,#-9]
+	orr	r1,r0,r1,lsl#8
+	ldrb	r0,[lr,#-8]
+	orr	r2,r1,r2,lsl#16
+	ldrb	r1,[lr,#-7]
+	orr	r3,r2,r3,lsl#24
+	ldrb	r2,[lr,#-6]
+	adcs	$h1,$h1,r3
+
+	ldrb	r3,[lr,#-5]
+	orr	r1,r0,r1,lsl#8
+	ldrb	r0,[lr,#-4]
+	orr	r2,r1,r2,lsl#16
+	ldrb	r1,[lr,#-3]
+	orr	r3,r2,r3,lsl#24
+	ldrb	r2,[lr,#-2]
+	adcs	$h2,$h2,r3
+
+	ldrb	r3,[lr,#-1]
+	orr	r1,r0,r1,lsl#8
+	str	lr,[sp,#8]		@ offload input pointer
+	orr	r2,r1,r2,lsl#16
+	add	$s1,$r1,$r1,lsr#2
+	orr	r3,r2,r3,lsl#24
+#else
+	ldr	r0,[lr],#16		@ load input
+	it	hi
+	addhi	$h4,$h4,#1		@ padbit
+	ldr	r1,[lr,#-12]
+	ldr	r2,[lr,#-8]
+	ldr	r3,[lr,#-4]
+# ifdef	__ARMEB__
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+# endif
+	adds	$h0,$h0,r0		@ accumulate input
+	str	lr,[sp,#8]		@ offload input pointer
+	adcs	$h1,$h1,r1
+	add	$s1,$r1,$r1,lsr#2
+	adcs	$h2,$h2,r2
+#endif
+	add	$s2,$r2,$r2,lsr#2
+	adcs	$h3,$h3,r3
+	add	$s3,$r3,$r3,lsr#2
+
+	umull	r2,r3,$h1,$r0
+	 adc	$h4,$h4,#0
+	umull	r0,r1,$h0,$r0
+	umlal	r2,r3,$h4,$s1
+	umlal	r0,r1,$h3,$s1
+	ldr	$r1,[sp,#20]		@ reload $r1
+	umlal	r2,r3,$h2,$s3
+	umlal	r0,r1,$h1,$s3
+	umlal	r2,r3,$h3,$s2
+	umlal	r0,r1,$h2,$s2
+	umlal	r2,r3,$h0,$r1
+	str	r0,[sp,#0]		@ future $h0
+	 mul	r0,$s2,$h4
+	ldr	$r2,[sp,#24]		@ reload $r2
+	adds	r2,r2,r1		@ d1+=d0>>32
+	 eor	r1,r1,r1
+	adc	lr,r3,#0		@ future $h2
+	str	r2,[sp,#4]		@ future $h1
+
+	mul	r2,$s3,$h4
+	eor	r3,r3,r3
+	umlal	r0,r1,$h3,$s3
+	ldr	$r3,[sp,#28]		@ reload $r3
+	umlal	r2,r3,$h3,$r0
+	umlal	r0,r1,$h2,$r0
+	umlal	r2,r3,$h2,$r1
+	umlal	r0,r1,$h1,$r1
+	umlal	r2,r3,$h1,$r2
+	umlal	r0,r1,$h0,$r2
+	umlal	r2,r3,$h0,$r3
+	ldr	$h0,[sp,#0]
+	mul	$h4,$r0,$h4
+	ldr	$h1,[sp,#4]
+
+	adds	$h2,lr,r0		@ d2+=d1>>32
+	ldr	lr,[sp,#8]		@ reload input pointer
+	adc	r1,r1,#0
+	adds	$h3,r2,r1		@ d3+=d2>>32
+	ldr	r0,[sp,#16]		@ reload end pointer
+	adc	r3,r3,#0
+	add	$h4,$h4,r3		@ h4+=d3>>32
+
+	and	r1,$h4,#-4
+	and	$h4,$h4,#3
+	add	r1,r1,r1,lsr#2		@ *=5
+	adds	$h0,$h0,r1
+	adcs	$h1,$h1,#0
+	adcs	$h2,$h2,#0
+	adcs	$h3,$h3,#0
+	adc	$h4,$h4,#0
+
+	cmp	r0,lr			@ done yet?
+	bhi	.Loop
+
+	ldr	$ctx,[sp,#12]
+	add	sp,sp,#32
+	stmdb	$ctx,{$h0-$h4}		@ store the result
+
+.Lno_data:
+#if	__ARM_ARCH__>=5
+	ldmia	sp!,{r3-r11,pc}
+#else
+	ldmia	sp!,{r3-r11,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	bx	lr			@ interoperable with Thumb ISA:-)
+#endif
+.size	poly1305_blocks,.-poly1305_blocks
+___
+}
+{
+my ($ctx,$mac,$nonce)=map("r$_",(0..2));
+my ($h0,$h1,$h2,$h3,$h4,$g0,$g1,$g2,$g3)=map("r$_",(3..11));
+my $g4=$ctx;
+
+$code.=<<___;
+.type	poly1305_emit,%function
+.align	5
+poly1305_emit:
+.Lpoly1305_emit:
+	stmdb	sp!,{r4-r11}
+
+	ldmia	$ctx,{$h0-$h4}
+
+#if __ARM_ARCH__>=7
+	ldr	ip,[$ctx,#36]		@ is_base2_26
+
+	adds	$g0,$h0,$h1,lsl#26	@ base 2^26 -> base 2^32
+	mov	$g1,$h1,lsr#6
+	adcs	$g1,$g1,$h2,lsl#20
+	mov	$g2,$h2,lsr#12
+	adcs	$g2,$g2,$h3,lsl#14
+	mov	$g3,$h3,lsr#18
+	adcs	$g3,$g3,$h4,lsl#8
+	mov	$g4,#0
+	adc	$g4,$g4,$h4,lsr#24
+
+	tst	ip,ip
+	itttt	ne
+	movne	$h0,$g0
+	movne	$h1,$g1
+	movne	$h2,$g2
+	movne	$h3,$g3
+	it	ne
+	movne	$h4,$g4
+#endif
+
+	adds	$g0,$h0,#5		@ compare to modulus
+	adcs	$g1,$h1,#0
+	adcs	$g2,$h2,#0
+	adcs	$g3,$h3,#0
+	adc	$g4,$h4,#0
+	tst	$g4,#4			@ did it carry/borrow?
+
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	$h0,$g0
+	ldr	$g0,[$nonce,#0]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	$h1,$g1
+	ldr	$g1,[$nonce,#4]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	$h2,$g2
+	ldr	$g2,[$nonce,#8]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	$h3,$g3
+	ldr	$g3,[$nonce,#12]
+
+	adds	$h0,$h0,$g0
+	adcs	$h1,$h1,$g1
+	adcs	$h2,$h2,$g2
+	adc	$h3,$h3,$g3
+
+#if __ARM_ARCH__>=7
+# ifdef __ARMEB__
+	rev	$h0,$h0
+	rev	$h1,$h1
+	rev	$h2,$h2
+	rev	$h3,$h3
+# endif
+	str	$h0,[$mac,#0]
+	str	$h1,[$mac,#4]
+	str	$h2,[$mac,#8]
+	str	$h3,[$mac,#12]
+#else
+	strb	$h0,[$mac,#0]
+	mov	$h0,$h0,lsr#8
+	strb	$h1,[$mac,#4]
+	mov	$h1,$h1,lsr#8
+	strb	$h2,[$mac,#8]
+	mov	$h2,$h2,lsr#8
+	strb	$h3,[$mac,#12]
+	mov	$h3,$h3,lsr#8
+
+	strb	$h0,[$mac,#1]
+	mov	$h0,$h0,lsr#8
+	strb	$h1,[$mac,#5]
+	mov	$h1,$h1,lsr#8
+	strb	$h2,[$mac,#9]
+	mov	$h2,$h2,lsr#8
+	strb	$h3,[$mac,#13]
+	mov	$h3,$h3,lsr#8
+
+	strb	$h0,[$mac,#2]
+	mov	$h0,$h0,lsr#8
+	strb	$h1,[$mac,#6]
+	mov	$h1,$h1,lsr#8
+	strb	$h2,[$mac,#10]
+	mov	$h2,$h2,lsr#8
+	strb	$h3,[$mac,#14]
+	mov	$h3,$h3,lsr#8
+
+	strb	$h0,[$mac,#3]
+	strb	$h1,[$mac,#7]
+	strb	$h2,[$mac,#11]
+	strb	$h3,[$mac,#15]
+#endif
+	ldmia	sp!,{r4-r11}
+#if	__ARM_ARCH__>=5
+	ret				@ bx	lr
+#else
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	bx	lr			@ interoperable with Thumb ISA:-)
+#endif
+.size	poly1305_emit,.-poly1305_emit
+___
+{
+my ($R0,$R1,$S1,$R2,$S2,$R3,$S3,$R4,$S4) = map("d$_",(0..9));
+my ($D0,$D1,$D2,$D3,$D4, $H0,$H1,$H2,$H3,$H4) = map("q$_",(5..14));
+my ($T0,$T1,$MASK) = map("q$_",(15,4,0));
+
+my ($in2,$zeros,$tbl0,$tbl1) = map("r$_",(4..7));
+
+$code.=<<___;
+#if	__ARM_MAX_ARCH__>=7
+.fpu	neon
+
+.type	poly1305_init_neon,%function
+.align	5
+poly1305_init_neon:
+.Lpoly1305_init_neon:
+	ldr	r3,[$ctx,#48]		@ first table element
+	cmp	r3,#-1			@ is value impossible?
+	bne	.Lno_init_neon
+
+	ldr	r4,[$ctx,#20]		@ load key base 2^32
+	ldr	r5,[$ctx,#24]
+	ldr	r6,[$ctx,#28]
+	ldr	r7,[$ctx,#32]
+
+	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
+	mov	r3,r4,lsr#26
+	mov	r4,r5,lsr#20
+	orr	r3,r3,r5,lsl#6
+	mov	r5,r6,lsr#14
+	orr	r4,r4,r6,lsl#12
+	mov	r6,r7,lsr#8
+	orr	r5,r5,r7,lsl#18
+	and	r3,r3,#0x03ffffff
+	and	r4,r4,#0x03ffffff
+	and	r5,r5,#0x03ffffff
+
+	vdup.32	$R0,r2			@ r^1 in both lanes
+	add	r2,r3,r3,lsl#2		@ *5
+	vdup.32	$R1,r3
+	add	r3,r4,r4,lsl#2
+	vdup.32	$S1,r2
+	vdup.32	$R2,r4
+	add	r4,r5,r5,lsl#2
+	vdup.32	$S2,r3
+	vdup.32	$R3,r5
+	add	r5,r6,r6,lsl#2
+	vdup.32	$S3,r4
+	vdup.32	$R4,r6
+	vdup.32	$S4,r5
+
+	mov	$zeros,#2		@ counter
+
+.Lsquare_neon:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
+	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
+	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
+	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
+	@ d4 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4
+
+	vmull.u32	$D0,$R0,${R0}[1]
+	vmull.u32	$D1,$R1,${R0}[1]
+	vmull.u32	$D2,$R2,${R0}[1]
+	vmull.u32	$D3,$R3,${R0}[1]
+	vmull.u32	$D4,$R4,${R0}[1]
+
+	vmlal.u32	$D0,$R4,${S1}[1]
+	vmlal.u32	$D1,$R0,${R1}[1]
+	vmlal.u32	$D2,$R1,${R1}[1]
+	vmlal.u32	$D3,$R2,${R1}[1]
+	vmlal.u32	$D4,$R3,${R1}[1]
+
+	vmlal.u32	$D0,$R3,${S2}[1]
+	vmlal.u32	$D1,$R4,${S2}[1]
+	vmlal.u32	$D3,$R1,${R2}[1]
+	vmlal.u32	$D2,$R0,${R2}[1]
+	vmlal.u32	$D4,$R2,${R2}[1]
+
+	vmlal.u32	$D0,$R2,${S3}[1]
+	vmlal.u32	$D3,$R0,${R3}[1]
+	vmlal.u32	$D1,$R3,${S3}[1]
+	vmlal.u32	$D2,$R4,${S3}[1]
+	vmlal.u32	$D4,$R1,${R3}[1]
+
+	vmlal.u32	$D3,$R4,${S4}[1]
+	vmlal.u32	$D0,$R1,${S4}[1]
+	vmlal.u32	$D1,$R2,${S4}[1]
+	vmlal.u32	$D2,$R3,${S4}[1]
+	vmlal.u32	$D4,$R0,${R4}[1]
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
+	@ and P. Schwabe
+	@
+	@ H0>>+H1>>+H2>>+H3>>+H4
+	@ H3>>+H4>>*5+H0>>+H1
+	@
+	@ Trivia.
+	@
+	@ Result of multiplication of n-bit number by m-bit number is
+	@ n+m bits wide. However! Even though 2^n is a n+1-bit number,
+	@ m-bit number multiplied by 2^n is still n+m bits wide.
+	@
+	@ Sum of two n-bit numbers is n+1 bits wide, sum of three - n+2,
+	@ and so is sum of four. Sum of 2^m n-m-bit numbers and n-bit
+	@ one is n+1 bits wide.
+	@
+	@ >>+ denotes Hnext += Hn>>26, Hn &= 0x3ffffff. This means that
+	@ H0, H2, H3 are guaranteed to be 26 bits wide, while H1 and H4
+	@ can be 27. However! In cases when their width exceeds 26 bits
+	@ they are limited by 2^26+2^6. This in turn means that *sum*
+	@ of the products with these values can still be viewed as sum
+	@ of 52-bit numbers as long as the amount of addends is not a
+	@ power of 2. For example,
+	@
+	@ H4 = H4*R0 + H3*R1 + H2*R2 + H1*R3 + H0 * R4,
+	@
+	@ which can't be larger than 5 * (2^26 + 2^6) * (2^26 + 2^6), or
+	@ 5 * (2^52 + 2*2^32 + 2^12), which in turn is smaller than
+	@ 8 * (2^52) or 2^55. However, the value is then multiplied by
+	@ by 5, so we should be looking at 5 * 5 * (2^52 + 2^33 + 2^12),
+	@ which is less than 32 * (2^52) or 2^57. And when processing
+	@ data we are looking at triple as many addends...
+	@
+	@ In key setup procedure pre-reduced H0 is limited by 5*4+1 and
+	@ 5*H4 - by 5*5 52-bit addends, or 57 bits. But when hashing the
+	@ input H0 is limited by (5*4+1)*3 addends, or 58 bits, while
+	@ 5*H4 by 5*5*3, or 59[!] bits. How is this relevant? vmlal.u32
+	@ instruction accepts 2x32-bit input and writes 2x64-bit result.
+	@ This means that result of reduction have to be compressed upon
+	@ loop wrap-around. This can be done in the process of reduction
+	@ to minimize amount of instructions [as well as amount of
+	@ 128-bit instructions, which benefits low-end processors], but
+	@ one has to watch for H2 (which is narrower than H0) and 5*H4
+	@ not being wider than 58 bits, so that result of right shift
+	@ by 26 bits fits in 32 bits. This is also useful on x86,
+	@ because it allows to use paddd in place for paddq, which
+	@ benefits Atom, where paddq is ridiculously slow.
+
+	vshr.u64	$T0,$D3,#26
+	vmovn.i64	$D3#lo,$D3
+	 vshr.u64	$T1,$D0,#26
+	 vmovn.i64	$D0#lo,$D0
+	vadd.i64	$D4,$D4,$T0		@ h3 -> h4
+	vbic.i32	$D3#lo,#0xfc000000	@ &=0x03ffffff
+	 vadd.i64	$D1,$D1,$T1		@ h0 -> h1
+	 vbic.i32	$D0#lo,#0xfc000000
+
+	vshrn.u64	$T0#lo,$D4,#26
+	vmovn.i64	$D4#lo,$D4
+	 vshr.u64	$T1,$D1,#26
+	 vmovn.i64	$D1#lo,$D1
+	 vadd.i64	$D2,$D2,$T1		@ h1 -> h2
+	vbic.i32	$D4#lo,#0xfc000000
+	 vbic.i32	$D1#lo,#0xfc000000
+
+	vadd.i32	$D0#lo,$D0#lo,$T0#lo
+	vshl.u32	$T0#lo,$T0#lo,#2
+	 vshrn.u64	$T1#lo,$D2,#26
+	 vmovn.i64	$D2#lo,$D2
+	vadd.i32	$D0#lo,$D0#lo,$T0#lo	@ h4 -> h0
+	 vadd.i32	$D3#lo,$D3#lo,$T1#lo	@ h2 -> h3
+	 vbic.i32	$D2#lo,#0xfc000000
+
+	vshr.u32	$T0#lo,$D0#lo,#26
+	vbic.i32	$D0#lo,#0xfc000000
+	 vshr.u32	$T1#lo,$D3#lo,#26
+	 vbic.i32	$D3#lo,#0xfc000000
+	vadd.i32	$D1#lo,$D1#lo,$T0#lo	@ h0 -> h1
+	 vadd.i32	$D4#lo,$D4#lo,$T1#lo	@ h3 -> h4
+
+	subs		$zeros,$zeros,#1
+	beq		.Lsquare_break_neon
+
+	add		$tbl0,$ctx,#(48+0*9*4)
+	add		$tbl1,$ctx,#(48+1*9*4)
+
+	vtrn.32		$R0,$D0#lo		@ r^2:r^1
+	vtrn.32		$R2,$D2#lo
+	vtrn.32		$R3,$D3#lo
+	vtrn.32		$R1,$D1#lo
+	vtrn.32		$R4,$D4#lo
+
+	vshl.u32	$S2,$R2,#2		@ *5
+	vshl.u32	$S3,$R3,#2
+	vshl.u32	$S1,$R1,#2
+	vshl.u32	$S4,$R4,#2
+	vadd.i32	$S2,$S2,$R2
+	vadd.i32	$S1,$S1,$R1
+	vadd.i32	$S3,$S3,$R3
+	vadd.i32	$S4,$S4,$R4
+
+	vst4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!
+	vst4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!
+	vst4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+	vst4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+	vst1.32		{${S4}[0]},[$tbl0,:32]
+	vst1.32		{${S4}[1]},[$tbl1,:32]
+
+	b		.Lsquare_neon
+
+.align	4
+.Lsquare_break_neon:
+	add		$tbl0,$ctx,#(48+2*4*9)
+	add		$tbl1,$ctx,#(48+3*4*9)
+
+	vmov		$R0,$D0#lo		@ r^4:r^3
+	vshl.u32	$S1,$D1#lo,#2		@ *5
+	vmov		$R1,$D1#lo
+	vshl.u32	$S2,$D2#lo,#2
+	vmov		$R2,$D2#lo
+	vshl.u32	$S3,$D3#lo,#2
+	vmov		$R3,$D3#lo
+	vshl.u32	$S4,$D4#lo,#2
+	vmov		$R4,$D4#lo
+	vadd.i32	$S1,$S1,$D1#lo
+	vadd.i32	$S2,$S2,$D2#lo
+	vadd.i32	$S3,$S3,$D3#lo
+	vadd.i32	$S4,$S4,$D4#lo
+
+	vst4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!
+	vst4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!
+	vst4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+	vst4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+	vst1.32		{${S4}[0]},[$tbl0]
+	vst1.32		{${S4}[1]},[$tbl1]
+
+.Lno_init_neon:
+	ret				@ bx	lr
+.size	poly1305_init_neon,.-poly1305_init_neon
+
+.type	poly1305_blocks_neon,%function
+.align	5
+poly1305_blocks_neon:
+.Lpoly1305_blocks_neon:
+	ldr	ip,[$ctx,#36]		@ is_base2_26
+
+	cmp	$len,#64
+	blo	.Lpoly1305_blocks
+
+	stmdb	sp!,{r4-r7}
+	vstmdb	sp!,{d8-d15}		@ ABI specification says so
+
+	tst	ip,ip			@ is_base2_26?
+	bne	.Lbase2_26_neon
+
+	stmdb	sp!,{r1-r3,lr}
+	bl	.Lpoly1305_init_neon
+
+	ldr	r4,[$ctx,#0]		@ load hash value base 2^32
+	ldr	r5,[$ctx,#4]
+	ldr	r6,[$ctx,#8]
+	ldr	r7,[$ctx,#12]
+	ldr	ip,[$ctx,#16]
+
+	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
+	mov	r3,r4,lsr#26
+	 veor	$D0#lo,$D0#lo,$D0#lo
+	mov	r4,r5,lsr#20
+	orr	r3,r3,r5,lsl#6
+	 veor	$D1#lo,$D1#lo,$D1#lo
+	mov	r5,r6,lsr#14
+	orr	r4,r4,r6,lsl#12
+	 veor	$D2#lo,$D2#lo,$D2#lo
+	mov	r6,r7,lsr#8
+	orr	r5,r5,r7,lsl#18
+	 veor	$D3#lo,$D3#lo,$D3#lo
+	and	r3,r3,#0x03ffffff
+	orr	r6,r6,ip,lsl#24
+	 veor	$D4#lo,$D4#lo,$D4#lo
+	and	r4,r4,#0x03ffffff
+	mov	r1,#1
+	and	r5,r5,#0x03ffffff
+	str	r1,[$ctx,#36]		@ set is_base2_26
+
+	vmov.32	$D0#lo[0],r2
+	vmov.32	$D1#lo[0],r3
+	vmov.32	$D2#lo[0],r4
+	vmov.32	$D3#lo[0],r5
+	vmov.32	$D4#lo[0],r6
+	adr	$zeros,.Lzeros
+
+	ldmia	sp!,{r1-r3,lr}
+	b	.Lhash_loaded
+
+.align	4
+.Lbase2_26_neon:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ load hash value
+
+	veor		$D0#lo,$D0#lo,$D0#lo
+	veor		$D1#lo,$D1#lo,$D1#lo
+	veor		$D2#lo,$D2#lo,$D2#lo
+	veor		$D3#lo,$D3#lo,$D3#lo
+	veor		$D4#lo,$D4#lo,$D4#lo
+	vld4.32		{$D0#lo[0],$D1#lo[0],$D2#lo[0],$D3#lo[0]},[$ctx]!
+	adr		$zeros,.Lzeros
+	vld1.32		{$D4#lo[0]},[$ctx]
+	sub		$ctx,$ctx,#16		@ rewind
+
+.Lhash_loaded:
+	add		$in2,$inp,#32
+	mov		$padbit,$padbit,lsl#24
+	tst		$len,#31
+	beq		.Leven
+
+	vld4.32		{$H0#lo[0],$H1#lo[0],$H2#lo[0],$H3#lo[0]},[$inp]!
+	vmov.32		$H4#lo[0],$padbit
+	sub		$len,$len,#16
+	add		$in2,$inp,#32
+
+# ifdef	__ARMEB__
+	vrev32.8	$H0,$H0
+	vrev32.8	$H3,$H3
+	vrev32.8	$H1,$H1
+	vrev32.8	$H2,$H2
+# endif
+	vsri.u32	$H4#lo,$H3#lo,#8	@ base 2^32 -> base 2^26
+	vshl.u32	$H3#lo,$H3#lo,#18
+
+	vsri.u32	$H3#lo,$H2#lo,#14
+	vshl.u32	$H2#lo,$H2#lo,#12
+	vadd.i32	$H4#hi,$H4#lo,$D4#lo	@ add hash value and move to #hi
+
+	vbic.i32	$H3#lo,#0xfc000000
+	vsri.u32	$H2#lo,$H1#lo,#20
+	vshl.u32	$H1#lo,$H1#lo,#6
+
+	vbic.i32	$H2#lo,#0xfc000000
+	vsri.u32	$H1#lo,$H0#lo,#26
+	vadd.i32	$H3#hi,$H3#lo,$D3#lo
+
+	vbic.i32	$H0#lo,#0xfc000000
+	vbic.i32	$H1#lo,#0xfc000000
+	vadd.i32	$H2#hi,$H2#lo,$D2#lo
+
+	vadd.i32	$H0#hi,$H0#lo,$D0#lo
+	vadd.i32	$H1#hi,$H1#lo,$D1#lo
+
+	mov		$tbl1,$zeros
+	add		$tbl0,$ctx,#48
+
+	cmp		$len,$len
+	b		.Long_tail
+
+.align	4
+.Leven:
+	subs		$len,$len,#64
+	it		lo
+	movlo		$in2,$zeros
+
+	vmov.i32	$H4,#1<<24		@ padbit, yes, always
+	vld4.32		{$H0#lo,$H1#lo,$H2#lo,$H3#lo},[$inp]	@ inp[0:1]
+	add		$inp,$inp,#64
+	vld4.32		{$H0#hi,$H1#hi,$H2#hi,$H3#hi},[$in2]	@ inp[2:3] (or 0)
+	add		$in2,$in2,#64
+	itt		hi
+	addhi		$tbl1,$ctx,#(48+1*9*4)
+	addhi		$tbl0,$ctx,#(48+3*9*4)
+
+# ifdef	__ARMEB__
+	vrev32.8	$H0,$H0
+	vrev32.8	$H3,$H3
+	vrev32.8	$H1,$H1
+	vrev32.8	$H2,$H2
+# endif
+	vsri.u32	$H4,$H3,#8		@ base 2^32 -> base 2^26
+	vshl.u32	$H3,$H3,#18
+
+	vsri.u32	$H3,$H2,#14
+	vshl.u32	$H2,$H2,#12
+
+	vbic.i32	$H3,#0xfc000000
+	vsri.u32	$H2,$H1,#20
+	vshl.u32	$H1,$H1,#6
+
+	vbic.i32	$H2,#0xfc000000
+	vsri.u32	$H1,$H0,#26
+
+	vbic.i32	$H0,#0xfc000000
+	vbic.i32	$H1,#0xfc000000
+
+	bls		.Lskip_loop
+
+	vld4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!	@ load r^2
+	vld4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!	@ load r^4
+	vld4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+	vld4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+	b		.Loop_neon
+
+.align	5
+.Loop_neon:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
+	@ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
+	@   \___________________/
+	@ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
+	@ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
+	@   \___________________/ \____________________/
+	@
+	@ Note that we start with inp[2:3]*r^2. This is because it
+	@ doesn't depend on reduction in previous iteration.
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ d4 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4
+	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
+	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
+	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
+	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ inp[2:3]*r^2
+
+	vadd.i32	$H2#lo,$H2#lo,$D2#lo	@ accumulate inp[0:1]
+	vmull.u32	$D2,$H2#hi,${R0}[1]
+	vadd.i32	$H0#lo,$H0#lo,$D0#lo
+	vmull.u32	$D0,$H0#hi,${R0}[1]
+	vadd.i32	$H3#lo,$H3#lo,$D3#lo
+	vmull.u32	$D3,$H3#hi,${R0}[1]
+	vmlal.u32	$D2,$H1#hi,${R1}[1]
+	vadd.i32	$H1#lo,$H1#lo,$D1#lo
+	vmull.u32	$D1,$H1#hi,${R0}[1]
+
+	vadd.i32	$H4#lo,$H4#lo,$D4#lo
+	vmull.u32	$D4,$H4#hi,${R0}[1]
+	subs		$len,$len,#64
+	vmlal.u32	$D0,$H4#hi,${S1}[1]
+	it		lo
+	movlo		$in2,$zeros
+	vmlal.u32	$D3,$H2#hi,${R1}[1]
+	vld1.32		${S4}[1],[$tbl1,:32]
+	vmlal.u32	$D1,$H0#hi,${R1}[1]
+	vmlal.u32	$D4,$H3#hi,${R1}[1]
+
+	vmlal.u32	$D0,$H3#hi,${S2}[1]
+	vmlal.u32	$D3,$H1#hi,${R2}[1]
+	vmlal.u32	$D4,$H2#hi,${R2}[1]
+	vmlal.u32	$D1,$H4#hi,${S2}[1]
+	vmlal.u32	$D2,$H0#hi,${R2}[1]
+
+	vmlal.u32	$D3,$H0#hi,${R3}[1]
+	vmlal.u32	$D0,$H2#hi,${S3}[1]
+	vmlal.u32	$D4,$H1#hi,${R3}[1]
+	vmlal.u32	$D1,$H3#hi,${S3}[1]
+	vmlal.u32	$D2,$H4#hi,${S3}[1]
+
+	vmlal.u32	$D3,$H4#hi,${S4}[1]
+	vmlal.u32	$D0,$H1#hi,${S4}[1]
+	vmlal.u32	$D4,$H0#hi,${R4}[1]
+	vmlal.u32	$D1,$H2#hi,${S4}[1]
+	vmlal.u32	$D2,$H3#hi,${S4}[1]
+
+	vld4.32		{$H0#hi,$H1#hi,$H2#hi,$H3#hi},[$in2]	@ inp[2:3] (or 0)
+	add		$in2,$in2,#64
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ (hash+inp[0:1])*r^4 and accumulate
+
+	vmlal.u32	$D3,$H3#lo,${R0}[0]
+	vmlal.u32	$D0,$H0#lo,${R0}[0]
+	vmlal.u32	$D4,$H4#lo,${R0}[0]
+	vmlal.u32	$D1,$H1#lo,${R0}[0]
+	vmlal.u32	$D2,$H2#lo,${R0}[0]
+	vld1.32		${S4}[0],[$tbl0,:32]
+
+	vmlal.u32	$D3,$H2#lo,${R1}[0]
+	vmlal.u32	$D0,$H4#lo,${S1}[0]
+	vmlal.u32	$D4,$H3#lo,${R1}[0]
+	vmlal.u32	$D1,$H0#lo,${R1}[0]
+	vmlal.u32	$D2,$H1#lo,${R1}[0]
+
+	vmlal.u32	$D3,$H1#lo,${R2}[0]
+	vmlal.u32	$D0,$H3#lo,${S2}[0]
+	vmlal.u32	$D4,$H2#lo,${R2}[0]
+	vmlal.u32	$D1,$H4#lo,${S2}[0]
+	vmlal.u32	$D2,$H0#lo,${R2}[0]
+
+	vmlal.u32	$D3,$H0#lo,${R3}[0]
+	vmlal.u32	$D0,$H2#lo,${S3}[0]
+	vmlal.u32	$D4,$H1#lo,${R3}[0]
+	vmlal.u32	$D1,$H3#lo,${S3}[0]
+	vmlal.u32	$D3,$H4#lo,${S4}[0]
+
+	vmlal.u32	$D2,$H4#lo,${S3}[0]
+	vmlal.u32	$D0,$H1#lo,${S4}[0]
+	vmlal.u32	$D4,$H0#lo,${R4}[0]
+	vmov.i32	$H4,#1<<24		@ padbit, yes, always
+	vmlal.u32	$D1,$H2#lo,${S4}[0]
+	vmlal.u32	$D2,$H3#lo,${S4}[0]
+
+	vld4.32		{$H0#lo,$H1#lo,$H2#lo,$H3#lo},[$inp]	@ inp[0:1]
+	add		$inp,$inp,#64
+# ifdef	__ARMEB__
+	vrev32.8	$H0,$H0
+	vrev32.8	$H1,$H1
+	vrev32.8	$H2,$H2
+	vrev32.8	$H3,$H3
+# endif
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ lazy reduction interleaved with base 2^32 -> base 2^26 of
+	@ inp[0:3] previously loaded to $H0-$H3 and smashed to $H0-$H4.
+
+	vshr.u64	$T0,$D3,#26
+	vmovn.i64	$D3#lo,$D3
+	 vshr.u64	$T1,$D0,#26
+	 vmovn.i64	$D0#lo,$D0
+	vadd.i64	$D4,$D4,$T0		@ h3 -> h4
+	vbic.i32	$D3#lo,#0xfc000000
+	  vsri.u32	$H4,$H3,#8		@ base 2^32 -> base 2^26
+	 vadd.i64	$D1,$D1,$T1		@ h0 -> h1
+	  vshl.u32	$H3,$H3,#18
+	 vbic.i32	$D0#lo,#0xfc000000
+
+	vshrn.u64	$T0#lo,$D4,#26
+	vmovn.i64	$D4#lo,$D4
+	 vshr.u64	$T1,$D1,#26
+	 vmovn.i64	$D1#lo,$D1
+	 vadd.i64	$D2,$D2,$T1		@ h1 -> h2
+	  vsri.u32	$H3,$H2,#14
+	vbic.i32	$D4#lo,#0xfc000000
+	  vshl.u32	$H2,$H2,#12
+	 vbic.i32	$D1#lo,#0xfc000000
+
+	vadd.i32	$D0#lo,$D0#lo,$T0#lo
+	vshl.u32	$T0#lo,$T0#lo,#2
+	  vbic.i32	$H3,#0xfc000000
+	 vshrn.u64	$T1#lo,$D2,#26
+	 vmovn.i64	$D2#lo,$D2
+	vaddl.u32	$D0,$D0#lo,$T0#lo	@ h4 -> h0 [widen for a sec]
+	  vsri.u32	$H2,$H1,#20
+	 vadd.i32	$D3#lo,$D3#lo,$T1#lo	@ h2 -> h3
+	  vshl.u32	$H1,$H1,#6
+	 vbic.i32	$D2#lo,#0xfc000000
+	  vbic.i32	$H2,#0xfc000000
+
+	vshrn.u64	$T0#lo,$D0,#26		@ re-narrow
+	vmovn.i64	$D0#lo,$D0
+	  vsri.u32	$H1,$H0,#26
+	  vbic.i32	$H0,#0xfc000000
+	 vshr.u32	$T1#lo,$D3#lo,#26
+	 vbic.i32	$D3#lo,#0xfc000000
+	vbic.i32	$D0#lo,#0xfc000000
+	vadd.i32	$D1#lo,$D1#lo,$T0#lo	@ h0 -> h1
+	 vadd.i32	$D4#lo,$D4#lo,$T1#lo	@ h3 -> h4
+	  vbic.i32	$H1,#0xfc000000
+
+	bhi		.Loop_neon
+
+.Lskip_loop:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
+
+	add		$tbl1,$ctx,#(48+0*9*4)
+	add		$tbl0,$ctx,#(48+1*9*4)
+	adds		$len,$len,#32
+	it		ne
+	movne		$len,#0
+	bne		.Long_tail
+
+	vadd.i32	$H2#hi,$H2#lo,$D2#lo	@ add hash value and move to #hi
+	vadd.i32	$H0#hi,$H0#lo,$D0#lo
+	vadd.i32	$H3#hi,$H3#lo,$D3#lo
+	vadd.i32	$H1#hi,$H1#lo,$D1#lo
+	vadd.i32	$H4#hi,$H4#lo,$D4#lo
+
+.Long_tail:
+	vld4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!	@ load r^1
+	vld4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!	@ load r^2
+
+	vadd.i32	$H2#lo,$H2#lo,$D2#lo	@ can be redundant
+	vmull.u32	$D2,$H2#hi,$R0
+	vadd.i32	$H0#lo,$H0#lo,$D0#lo
+	vmull.u32	$D0,$H0#hi,$R0
+	vadd.i32	$H3#lo,$H3#lo,$D3#lo
+	vmull.u32	$D3,$H3#hi,$R0
+	vadd.i32	$H1#lo,$H1#lo,$D1#lo
+	vmull.u32	$D1,$H1#hi,$R0
+	vadd.i32	$H4#lo,$H4#lo,$D4#lo
+	vmull.u32	$D4,$H4#hi,$R0
+
+	vmlal.u32	$D0,$H4#hi,$S1
+	vld4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+	vmlal.u32	$D3,$H2#hi,$R1
+	vld4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+	vmlal.u32	$D1,$H0#hi,$R1
+	vmlal.u32	$D4,$H3#hi,$R1
+	vmlal.u32	$D2,$H1#hi,$R1
+
+	vmlal.u32	$D3,$H1#hi,$R2
+	vld1.32		${S4}[1],[$tbl1,:32]
+	vmlal.u32	$D0,$H3#hi,$S2
+	vld1.32		${S4}[0],[$tbl0,:32]
+	vmlal.u32	$D4,$H2#hi,$R2
+	vmlal.u32	$D1,$H4#hi,$S2
+	vmlal.u32	$D2,$H0#hi,$R2
+
+	vmlal.u32	$D3,$H0#hi,$R3
+	 it		ne
+	 addne		$tbl1,$ctx,#(48+2*9*4)
+	vmlal.u32	$D0,$H2#hi,$S3
+	 it		ne
+	 addne		$tbl0,$ctx,#(48+3*9*4)
+	vmlal.u32	$D4,$H1#hi,$R3
+	vmlal.u32	$D1,$H3#hi,$S3
+	vmlal.u32	$D2,$H4#hi,$S3
+
+	vmlal.u32	$D3,$H4#hi,$S4
+	 vorn		$MASK,$MASK,$MASK	@ all-ones, can be redundant
+	vmlal.u32	$D0,$H1#hi,$S4
+	 vshr.u64	$MASK,$MASK,#38
+	vmlal.u32	$D4,$H0#hi,$R4
+	vmlal.u32	$D1,$H2#hi,$S4
+	vmlal.u32	$D2,$H3#hi,$S4
+
+	beq		.Lshort_tail
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ (hash+inp[0:1])*r^4:r^3 and accumulate
+
+	vld4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!	@ load r^3
+	vld4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!	@ load r^4
+
+	vmlal.u32	$D2,$H2#lo,$R0
+	vmlal.u32	$D0,$H0#lo,$R0
+	vmlal.u32	$D3,$H3#lo,$R0
+	vmlal.u32	$D1,$H1#lo,$R0
+	vmlal.u32	$D4,$H4#lo,$R0
+
+	vmlal.u32	$D0,$H4#lo,$S1
+	vld4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+	vmlal.u32	$D3,$H2#lo,$R1
+	vld4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+	vmlal.u32	$D1,$H0#lo,$R1
+	vmlal.u32	$D4,$H3#lo,$R1
+	vmlal.u32	$D2,$H1#lo,$R1
+
+	vmlal.u32	$D3,$H1#lo,$R2
+	vld1.32		${S4}[1],[$tbl1,:32]
+	vmlal.u32	$D0,$H3#lo,$S2
+	vld1.32		${S4}[0],[$tbl0,:32]
+	vmlal.u32	$D4,$H2#lo,$R2
+	vmlal.u32	$D1,$H4#lo,$S2
+	vmlal.u32	$D2,$H0#lo,$R2
+
+	vmlal.u32	$D3,$H0#lo,$R3
+	vmlal.u32	$D0,$H2#lo,$S3
+	vmlal.u32	$D4,$H1#lo,$R3
+	vmlal.u32	$D1,$H3#lo,$S3
+	vmlal.u32	$D2,$H4#lo,$S3
+
+	vmlal.u32	$D3,$H4#lo,$S4
+	 vorn		$MASK,$MASK,$MASK	@ all-ones
+	vmlal.u32	$D0,$H1#lo,$S4
+	 vshr.u64	$MASK,$MASK,#38
+	vmlal.u32	$D4,$H0#lo,$R4
+	vmlal.u32	$D1,$H2#lo,$S4
+	vmlal.u32	$D2,$H3#lo,$S4
+
+.Lshort_tail:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ horizontal addition
+
+	vadd.i64	$D3#lo,$D3#lo,$D3#hi
+	vadd.i64	$D0#lo,$D0#lo,$D0#hi
+	vadd.i64	$D4#lo,$D4#lo,$D4#hi
+	vadd.i64	$D1#lo,$D1#lo,$D1#hi
+	vadd.i64	$D2#lo,$D2#lo,$D2#hi
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ lazy reduction, but without narrowing
+
+	vshr.u64	$T0,$D3,#26
+	vand.i64	$D3,$D3,$MASK
+	 vshr.u64	$T1,$D0,#26
+	 vand.i64	$D0,$D0,$MASK
+	vadd.i64	$D4,$D4,$T0		@ h3 -> h4
+	 vadd.i64	$D1,$D1,$T1		@ h0 -> h1
+
+	vshr.u64	$T0,$D4,#26
+	vand.i64	$D4,$D4,$MASK
+	 vshr.u64	$T1,$D1,#26
+	 vand.i64	$D1,$D1,$MASK
+	 vadd.i64	$D2,$D2,$T1		@ h1 -> h2
+
+	vadd.i64	$D0,$D0,$T0
+	vshl.u64	$T0,$T0,#2
+	 vshr.u64	$T1,$D2,#26
+	 vand.i64	$D2,$D2,$MASK
+	vadd.i64	$D0,$D0,$T0		@ h4 -> h0
+	 vadd.i64	$D3,$D3,$T1		@ h2 -> h3
+
+	vshr.u64	$T0,$D0,#26
+	vand.i64	$D0,$D0,$MASK
+	 vshr.u64	$T1,$D3,#26
+	 vand.i64	$D3,$D3,$MASK
+	vadd.i64	$D1,$D1,$T0		@ h0 -> h1
+	 vadd.i64	$D4,$D4,$T1		@ h3 -> h4
+
+	cmp		$len,#0
+	bne		.Leven
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ store hash value
+
+	vst4.32		{$D0#lo[0],$D1#lo[0],$D2#lo[0],$D3#lo[0]},[$ctx]!
+	vst1.32		{$D4#lo[0]},[$ctx]
+
+	vldmia	sp!,{d8-d15}			@ epilogue
+	ldmia	sp!,{r4-r7}
+	ret					@ bx	lr
+.size	poly1305_blocks_neon,.-poly1305_blocks_neon
+
+.align	5
+.Lzeros:
+.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
+#ifndef	__KERNEL__
+.LOPENSSL_armcap:
+# ifdef	_WIN32
+.word	OPENSSL_armcap_P
+# else
+.word	OPENSSL_armcap_P-.Lpoly1305_init
+# endif
+.comm	OPENSSL_armcap_P,4,4
+.hidden	OPENSSL_armcap_P
+#endif
+#endif
+___
+}	}
+$code.=<<___;
+.asciz	"Poly1305 for ARMv4/NEON, CRYPTOGAMS by \@dot-asm"
+.align	2
+___
+
+foreach (split("\n",$code)) {
+	s/\`([^\`]*)\`/eval $1/geo;
+
+	s/\bq([0-9]+)#(lo|hi)/sprintf "d%d",2*$1+($2 eq "hi")/geo	or
+	s/\bret\b/bx	lr/go						or
+	s/\bbx\s+lr\b/.word\t0xe12fff1e/go;	# make it possible to compile with -march=armv4
+
+	print $_,"\n";
+}
+close STDOUT; # enforce flush
diff --git a/arch/arm/crypto/poly1305-core.S_shipped b/arch/arm/crypto/poly1305-core.S_shipped
new file mode 100644
index 000000000000..37b71d990293
--- /dev/null
+++ b/arch/arm/crypto/poly1305-core.S_shipped
@@ -0,0 +1,1158 @@
+#ifndef	__KERNEL__
+# include "arm_arch.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ __LINUX_ARM_ARCH__
+# define poly1305_init   poly1305_init_arm
+# define poly1305_blocks poly1305_blocks_arm
+# define poly1305_emit   poly1305_emit_arm
+.globl	poly1305_blocks_neon
+#endif
+
+#if defined(__thumb2__)
+.syntax	unified
+.thumb
+#else
+.code	32
+#endif
+
+.text
+
+.globl	poly1305_emit
+.globl	poly1305_blocks
+.globl	poly1305_init
+.type	poly1305_init,%function
+.align	5
+poly1305_init:
+.Lpoly1305_init:
+	stmdb	sp!,{r4-r11}
+
+	eor	r3,r3,r3
+	cmp	r1,#0
+	str	r3,[r0,#0]		@ zero hash value
+	str	r3,[r0,#4]
+	str	r3,[r0,#8]
+	str	r3,[r0,#12]
+	str	r3,[r0,#16]
+	str	r3,[r0,#36]		@ clear is_base2_26
+	add	r0,r0,#20
+
+#ifdef	__thumb2__
+	it	eq
+#endif
+	moveq	r0,#0
+	beq	.Lno_key
+
+#if	__ARM_MAX_ARCH__>=7
+	mov	r3,#-1
+	str	r3,[r0,#28]		@ impossible key power value
+# ifndef __KERNEL__
+	adr	r11,.Lpoly1305_init
+	ldr	r12,.LOPENSSL_armcap
+# endif
+#endif
+	ldrb	r4,[r1,#0]
+	mov	r10,#0x0fffffff
+	ldrb	r5,[r1,#1]
+	and	r3,r10,#-4		@ 0x0ffffffc
+	ldrb	r6,[r1,#2]
+	ldrb	r7,[r1,#3]
+	orr	r4,r4,r5,lsl#8
+	ldrb	r5,[r1,#4]
+	orr	r4,r4,r6,lsl#16
+	ldrb	r6,[r1,#5]
+	orr	r4,r4,r7,lsl#24
+	ldrb	r7,[r1,#6]
+	and	r4,r4,r10
+
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+# if !defined(_WIN32)
+	ldr	r12,[r11,r12]		@ OPENSSL_armcap_P
+# endif
+# if defined(__APPLE__) || defined(_WIN32)
+	ldr	r12,[r12]
+# endif
+#endif
+	ldrb	r8,[r1,#7]
+	orr	r5,r5,r6,lsl#8
+	ldrb	r6,[r1,#8]
+	orr	r5,r5,r7,lsl#16
+	ldrb	r7,[r1,#9]
+	orr	r5,r5,r8,lsl#24
+	ldrb	r8,[r1,#10]
+	and	r5,r5,r3
+
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	tst	r12,#ARMV7_NEON		@ check for NEON
+# ifdef	__thumb2__
+	adr	r9,.Lpoly1305_blocks_neon
+	adr	r11,.Lpoly1305_blocks
+	it	ne
+	movne	r11,r9
+	adr	r12,.Lpoly1305_emit
+	orr	r11,r11,#1		@ thumb-ify addresses
+	orr	r12,r12,#1
+# else
+	add	r12,r11,#(.Lpoly1305_emit-.Lpoly1305_init)
+	ite	eq
+	addeq	r11,r11,#(.Lpoly1305_blocks-.Lpoly1305_init)
+	addne	r11,r11,#(.Lpoly1305_blocks_neon-.Lpoly1305_init)
+# endif
+#endif
+	ldrb	r9,[r1,#11]
+	orr	r6,r6,r7,lsl#8
+	ldrb	r7,[r1,#12]
+	orr	r6,r6,r8,lsl#16
+	ldrb	r8,[r1,#13]
+	orr	r6,r6,r9,lsl#24
+	ldrb	r9,[r1,#14]
+	and	r6,r6,r3
+
+	ldrb	r10,[r1,#15]
+	orr	r7,r7,r8,lsl#8
+	str	r4,[r0,#0]
+	orr	r7,r7,r9,lsl#16
+	str	r5,[r0,#4]
+	orr	r7,r7,r10,lsl#24
+	str	r6,[r0,#8]
+	and	r7,r7,r3
+	str	r7,[r0,#12]
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	stmia	r2,{r11,r12}		@ fill functions table
+	mov	r0,#1
+#else
+	mov	r0,#0
+#endif
+.Lno_key:
+	ldmia	sp!,{r4-r11}
+#if	__ARM_ARCH__>=5
+	bx	lr				@ bx	lr
+#else
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
+#endif
+.size	poly1305_init,.-poly1305_init
+.type	poly1305_blocks,%function
+.align	5
+poly1305_blocks:
+.Lpoly1305_blocks:
+	stmdb	sp!,{r3-r11,lr}
+
+	ands	r2,r2,#-16
+	beq	.Lno_data
+
+	add	r2,r2,r1		@ end pointer
+	sub	sp,sp,#32
+
+#if __ARM_ARCH__<7
+	ldmia	r0,{r4-r12}		@ load context
+	add	r0,r0,#20
+	str	r2,[sp,#16]		@ offload stuff
+	str	r0,[sp,#12]
+#else
+	ldr	lr,[r0,#36]		@ is_base2_26
+	ldmia	r0!,{r4-r8}		@ load hash value
+	str	r2,[sp,#16]		@ offload stuff
+	str	r0,[sp,#12]
+
+	adds	r9,r4,r5,lsl#26	@ base 2^26 -> base 2^32
+	mov	r10,r5,lsr#6
+	adcs	r10,r10,r6,lsl#20
+	mov	r11,r6,lsr#12
+	adcs	r11,r11,r7,lsl#14
+	mov	r12,r7,lsr#18
+	adcs	r12,r12,r8,lsl#8
+	mov	r2,#0
+	teq	lr,#0
+	str	r2,[r0,#16]		@ clear is_base2_26
+	adc	r2,r2,r8,lsr#24
+
+	itttt	ne
+	movne	r4,r9			@ choose between radixes
+	movne	r5,r10
+	movne	r6,r11
+	movne	r7,r12
+	ldmia	r0,{r9-r12}		@ load key
+	it	ne
+	movne	r8,r2
+#endif
+
+	mov	lr,r1
+	cmp	r3,#0
+	str	r10,[sp,#20]
+	str	r11,[sp,#24]
+	str	r12,[sp,#28]
+	b	.Loop
+
+.align	4
+.Loop:
+#if __ARM_ARCH__<7
+	ldrb	r0,[lr],#16		@ load input
+# ifdef	__thumb2__
+	it	hi
+# endif
+	addhi	r8,r8,#1		@ 1<<128
+	ldrb	r1,[lr,#-15]
+	ldrb	r2,[lr,#-14]
+	ldrb	r3,[lr,#-13]
+	orr	r1,r0,r1,lsl#8
+	ldrb	r0,[lr,#-12]
+	orr	r2,r1,r2,lsl#16
+	ldrb	r1,[lr,#-11]
+	orr	r3,r2,r3,lsl#24
+	ldrb	r2,[lr,#-10]
+	adds	r4,r4,r3		@ accumulate input
+
+	ldrb	r3,[lr,#-9]
+	orr	r1,r0,r1,lsl#8
+	ldrb	r0,[lr,#-8]
+	orr	r2,r1,r2,lsl#16
+	ldrb	r1,[lr,#-7]
+	orr	r3,r2,r3,lsl#24
+	ldrb	r2,[lr,#-6]
+	adcs	r5,r5,r3
+
+	ldrb	r3,[lr,#-5]
+	orr	r1,r0,r1,lsl#8
+	ldrb	r0,[lr,#-4]
+	orr	r2,r1,r2,lsl#16
+	ldrb	r1,[lr,#-3]
+	orr	r3,r2,r3,lsl#24
+	ldrb	r2,[lr,#-2]
+	adcs	r6,r6,r3
+
+	ldrb	r3,[lr,#-1]
+	orr	r1,r0,r1,lsl#8
+	str	lr,[sp,#8]		@ offload input pointer
+	orr	r2,r1,r2,lsl#16
+	add	r10,r10,r10,lsr#2
+	orr	r3,r2,r3,lsl#24
+#else
+	ldr	r0,[lr],#16		@ load input
+	it	hi
+	addhi	r8,r8,#1		@ padbit
+	ldr	r1,[lr,#-12]
+	ldr	r2,[lr,#-8]
+	ldr	r3,[lr,#-4]
+# ifdef	__ARMEB__
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+# endif
+	adds	r4,r4,r0		@ accumulate input
+	str	lr,[sp,#8]		@ offload input pointer
+	adcs	r5,r5,r1
+	add	r10,r10,r10,lsr#2
+	adcs	r6,r6,r2
+#endif
+	add	r11,r11,r11,lsr#2
+	adcs	r7,r7,r3
+	add	r12,r12,r12,lsr#2
+
+	umull	r2,r3,r5,r9
+	 adc	r8,r8,#0
+	umull	r0,r1,r4,r9
+	umlal	r2,r3,r8,r10
+	umlal	r0,r1,r7,r10
+	ldr	r10,[sp,#20]		@ reload r10
+	umlal	r2,r3,r6,r12
+	umlal	r0,r1,r5,r12
+	umlal	r2,r3,r7,r11
+	umlal	r0,r1,r6,r11
+	umlal	r2,r3,r4,r10
+	str	r0,[sp,#0]		@ future r4
+	 mul	r0,r11,r8
+	ldr	r11,[sp,#24]		@ reload r11
+	adds	r2,r2,r1		@ d1+=d0>>32
+	 eor	r1,r1,r1
+	adc	lr,r3,#0		@ future r6
+	str	r2,[sp,#4]		@ future r5
+
+	mul	r2,r12,r8
+	eor	r3,r3,r3
+	umlal	r0,r1,r7,r12
+	ldr	r12,[sp,#28]		@ reload r12
+	umlal	r2,r3,r7,r9
+	umlal	r0,r1,r6,r9
+	umlal	r2,r3,r6,r10
+	umlal	r0,r1,r5,r10
+	umlal	r2,r3,r5,r11
+	umlal	r0,r1,r4,r11
+	umlal	r2,r3,r4,r12
+	ldr	r4,[sp,#0]
+	mul	r8,r9,r8
+	ldr	r5,[sp,#4]
+
+	adds	r6,lr,r0		@ d2+=d1>>32
+	ldr	lr,[sp,#8]		@ reload input pointer
+	adc	r1,r1,#0
+	adds	r7,r2,r1		@ d3+=d2>>32
+	ldr	r0,[sp,#16]		@ reload end pointer
+	adc	r3,r3,#0
+	add	r8,r8,r3		@ h4+=d3>>32
+
+	and	r1,r8,#-4
+	and	r8,r8,#3
+	add	r1,r1,r1,lsr#2		@ *=5
+	adds	r4,r4,r1
+	adcs	r5,r5,#0
+	adcs	r6,r6,#0
+	adcs	r7,r7,#0
+	adc	r8,r8,#0
+
+	cmp	r0,lr			@ done yet?
+	bhi	.Loop
+
+	ldr	r0,[sp,#12]
+	add	sp,sp,#32
+	stmdb	r0,{r4-r8}		@ store the result
+
+.Lno_data:
+#if	__ARM_ARCH__>=5
+	ldmia	sp!,{r3-r11,pc}
+#else
+	ldmia	sp!,{r3-r11,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
+#endif
+.size	poly1305_blocks,.-poly1305_blocks
+.type	poly1305_emit,%function
+.align	5
+poly1305_emit:
+.Lpoly1305_emit:
+	stmdb	sp!,{r4-r11}
+
+	ldmia	r0,{r3-r7}
+
+#if __ARM_ARCH__>=7
+	ldr	ip,[r0,#36]		@ is_base2_26
+
+	adds	r8,r3,r4,lsl#26	@ base 2^26 -> base 2^32
+	mov	r9,r4,lsr#6
+	adcs	r9,r9,r5,lsl#20
+	mov	r10,r5,lsr#12
+	adcs	r10,r10,r6,lsl#14
+	mov	r11,r6,lsr#18
+	adcs	r11,r11,r7,lsl#8
+	mov	r0,#0
+	adc	r0,r0,r7,lsr#24
+
+	tst	ip,ip
+	itttt	ne
+	movne	r3,r8
+	movne	r4,r9
+	movne	r5,r10
+	movne	r6,r11
+	it	ne
+	movne	r7,r0
+#endif
+
+	adds	r8,r3,#5		@ compare to modulus
+	adcs	r9,r4,#0
+	adcs	r10,r5,#0
+	adcs	r11,r6,#0
+	adc	r0,r7,#0
+	tst	r0,#4			@ did it carry/borrow?
+
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	r3,r8
+	ldr	r8,[r2,#0]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	r4,r9
+	ldr	r9,[r2,#4]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	r5,r10
+	ldr	r10,[r2,#8]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	r6,r11
+	ldr	r11,[r2,#12]
+
+	adds	r3,r3,r8
+	adcs	r4,r4,r9
+	adcs	r5,r5,r10
+	adc	r6,r6,r11
+
+#if __ARM_ARCH__>=7
+# ifdef __ARMEB__
+	rev	r3,r3
+	rev	r4,r4
+	rev	r5,r5
+	rev	r6,r6
+# endif
+	str	r3,[r1,#0]
+	str	r4,[r1,#4]
+	str	r5,[r1,#8]
+	str	r6,[r1,#12]
+#else
+	strb	r3,[r1,#0]
+	mov	r3,r3,lsr#8
+	strb	r4,[r1,#4]
+	mov	r4,r4,lsr#8
+	strb	r5,[r1,#8]
+	mov	r5,r5,lsr#8
+	strb	r6,[r1,#12]
+	mov	r6,r6,lsr#8
+
+	strb	r3,[r1,#1]
+	mov	r3,r3,lsr#8
+	strb	r4,[r1,#5]
+	mov	r4,r4,lsr#8
+	strb	r5,[r1,#9]
+	mov	r5,r5,lsr#8
+	strb	r6,[r1,#13]
+	mov	r6,r6,lsr#8
+
+	strb	r3,[r1,#2]
+	mov	r3,r3,lsr#8
+	strb	r4,[r1,#6]
+	mov	r4,r4,lsr#8
+	strb	r5,[r1,#10]
+	mov	r5,r5,lsr#8
+	strb	r6,[r1,#14]
+	mov	r6,r6,lsr#8
+
+	strb	r3,[r1,#3]
+	strb	r4,[r1,#7]
+	strb	r5,[r1,#11]
+	strb	r6,[r1,#15]
+#endif
+	ldmia	sp!,{r4-r11}
+#if	__ARM_ARCH__>=5
+	bx	lr				@ bx	lr
+#else
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
+#endif
+.size	poly1305_emit,.-poly1305_emit
+#if	__ARM_MAX_ARCH__>=7
+.fpu	neon
+
+.type	poly1305_init_neon,%function
+.align	5
+poly1305_init_neon:
+.Lpoly1305_init_neon:
+	ldr	r3,[r0,#48]		@ first table element
+	cmp	r3,#-1			@ is value impossible?
+	bne	.Lno_init_neon
+
+	ldr	r4,[r0,#20]		@ load key base 2^32
+	ldr	r5,[r0,#24]
+	ldr	r6,[r0,#28]
+	ldr	r7,[r0,#32]
+
+	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
+	mov	r3,r4,lsr#26
+	mov	r4,r5,lsr#20
+	orr	r3,r3,r5,lsl#6
+	mov	r5,r6,lsr#14
+	orr	r4,r4,r6,lsl#12
+	mov	r6,r7,lsr#8
+	orr	r5,r5,r7,lsl#18
+	and	r3,r3,#0x03ffffff
+	and	r4,r4,#0x03ffffff
+	and	r5,r5,#0x03ffffff
+
+	vdup.32	d0,r2			@ r^1 in both lanes
+	add	r2,r3,r3,lsl#2		@ *5
+	vdup.32	d1,r3
+	add	r3,r4,r4,lsl#2
+	vdup.32	d2,r2
+	vdup.32	d3,r4
+	add	r4,r5,r5,lsl#2
+	vdup.32	d4,r3
+	vdup.32	d5,r5
+	add	r5,r6,r6,lsl#2
+	vdup.32	d6,r4
+	vdup.32	d7,r6
+	vdup.32	d8,r5
+
+	mov	r5,#2		@ counter
+
+.Lsquare_neon:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
+	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
+	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
+	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
+	@ d4 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4
+
+	vmull.u32	q5,d0,d0[1]
+	vmull.u32	q6,d1,d0[1]
+	vmull.u32	q7,d3,d0[1]
+	vmull.u32	q8,d5,d0[1]
+	vmull.u32	q9,d7,d0[1]
+
+	vmlal.u32	q5,d7,d2[1]
+	vmlal.u32	q6,d0,d1[1]
+	vmlal.u32	q7,d1,d1[1]
+	vmlal.u32	q8,d3,d1[1]
+	vmlal.u32	q9,d5,d1[1]
+
+	vmlal.u32	q5,d5,d4[1]
+	vmlal.u32	q6,d7,d4[1]
+	vmlal.u32	q8,d1,d3[1]
+	vmlal.u32	q7,d0,d3[1]
+	vmlal.u32	q9,d3,d3[1]
+
+	vmlal.u32	q5,d3,d6[1]
+	vmlal.u32	q8,d0,d5[1]
+	vmlal.u32	q6,d5,d6[1]
+	vmlal.u32	q7,d7,d6[1]
+	vmlal.u32	q9,d1,d5[1]
+
+	vmlal.u32	q8,d7,d8[1]
+	vmlal.u32	q5,d1,d8[1]
+	vmlal.u32	q6,d3,d8[1]
+	vmlal.u32	q7,d5,d8[1]
+	vmlal.u32	q9,d0,d7[1]
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
+	@ and P. Schwabe
+	@
+	@ H0>>+H1>>+H2>>+H3>>+H4
+	@ H3>>+H4>>*5+H0>>+H1
+	@
+	@ Trivia.
+	@
+	@ Result of multiplication of n-bit number by m-bit number is
+	@ n+m bits wide. However! Even though 2^n is a n+1-bit number,
+	@ m-bit number multiplied by 2^n is still n+m bits wide.
+	@
+	@ Sum of two n-bit numbers is n+1 bits wide, sum of three - n+2,
+	@ and so is sum of four. Sum of 2^m n-m-bit numbers and n-bit
+	@ one is n+1 bits wide.
+	@
+	@ >>+ denotes Hnext += Hn>>26, Hn &= 0x3ffffff. This means that
+	@ H0, H2, H3 are guaranteed to be 26 bits wide, while H1 and H4
+	@ can be 27. However! In cases when their width exceeds 26 bits
+	@ they are limited by 2^26+2^6. This in turn means that *sum*
+	@ of the products with these values can still be viewed as sum
+	@ of 52-bit numbers as long as the amount of addends is not a
+	@ power of 2. For example,
+	@
+	@ H4 = H4*R0 + H3*R1 + H2*R2 + H1*R3 + H0 * R4,
+	@
+	@ which can't be larger than 5 * (2^26 + 2^6) * (2^26 + 2^6), or
+	@ 5 * (2^52 + 2*2^32 + 2^12), which in turn is smaller than
+	@ 8 * (2^52) or 2^55. However, the value is then multiplied by
+	@ by 5, so we should be looking at 5 * 5 * (2^52 + 2^33 + 2^12),
+	@ which is less than 32 * (2^52) or 2^57. And when processing
+	@ data we are looking at triple as many addends...
+	@
+	@ In key setup procedure pre-reduced H0 is limited by 5*4+1 and
+	@ 5*H4 - by 5*5 52-bit addends, or 57 bits. But when hashing the
+	@ input H0 is limited by (5*4+1)*3 addends, or 58 bits, while
+	@ 5*H4 by 5*5*3, or 59[!] bits. How is this relevant? vmlal.u32
+	@ instruction accepts 2x32-bit input and writes 2x64-bit result.
+	@ This means that result of reduction have to be compressed upon
+	@ loop wrap-around. This can be done in the process of reduction
+	@ to minimize amount of instructions [as well as amount of
+	@ 128-bit instructions, which benefits low-end processors], but
+	@ one has to watch for H2 (which is narrower than H0) and 5*H4
+	@ not being wider than 58 bits, so that result of right shift
+	@ by 26 bits fits in 32 bits. This is also useful on x86,
+	@ because it allows to use paddd in place for paddq, which
+	@ benefits Atom, where paddq is ridiculously slow.
+
+	vshr.u64	q15,q8,#26
+	vmovn.i64	d16,q8
+	 vshr.u64	q4,q5,#26
+	 vmovn.i64	d10,q5
+	vadd.i64	q9,q9,q15		@ h3 -> h4
+	vbic.i32	d16,#0xfc000000	@ &=0x03ffffff
+	 vadd.i64	q6,q6,q4		@ h0 -> h1
+	 vbic.i32	d10,#0xfc000000
+
+	vshrn.u64	d30,q9,#26
+	vmovn.i64	d18,q9
+	 vshr.u64	q4,q6,#26
+	 vmovn.i64	d12,q6
+	 vadd.i64	q7,q7,q4		@ h1 -> h2
+	vbic.i32	d18,#0xfc000000
+	 vbic.i32	d12,#0xfc000000
+
+	vadd.i32	d10,d10,d30
+	vshl.u32	d30,d30,#2
+	 vshrn.u64	d8,q7,#26
+	 vmovn.i64	d14,q7
+	vadd.i32	d10,d10,d30	@ h4 -> h0
+	 vadd.i32	d16,d16,d8	@ h2 -> h3
+	 vbic.i32	d14,#0xfc000000
+
+	vshr.u32	d30,d10,#26
+	vbic.i32	d10,#0xfc000000
+	 vshr.u32	d8,d16,#26
+	 vbic.i32	d16,#0xfc000000
+	vadd.i32	d12,d12,d30	@ h0 -> h1
+	 vadd.i32	d18,d18,d8	@ h3 -> h4
+
+	subs		r5,r5,#1
+	beq		.Lsquare_break_neon
+
+	add		r6,r0,#(48+0*9*4)
+	add		r7,r0,#(48+1*9*4)
+
+	vtrn.32		d0,d10		@ r^2:r^1
+	vtrn.32		d3,d14
+	vtrn.32		d5,d16
+	vtrn.32		d1,d12
+	vtrn.32		d7,d18
+
+	vshl.u32	d4,d3,#2		@ *5
+	vshl.u32	d6,d5,#2
+	vshl.u32	d2,d1,#2
+	vshl.u32	d8,d7,#2
+	vadd.i32	d4,d4,d3
+	vadd.i32	d2,d2,d1
+	vadd.i32	d6,d6,d5
+	vadd.i32	d8,d8,d7
+
+	vst4.32		{d0[0],d1[0],d2[0],d3[0]},[r6]!
+	vst4.32		{d0[1],d1[1],d2[1],d3[1]},[r7]!
+	vst4.32		{d4[0],d5[0],d6[0],d7[0]},[r6]!
+	vst4.32		{d4[1],d5[1],d6[1],d7[1]},[r7]!
+	vst1.32		{d8[0]},[r6,:32]
+	vst1.32		{d8[1]},[r7,:32]
+
+	b		.Lsquare_neon
+
+.align	4
+.Lsquare_break_neon:
+	add		r6,r0,#(48+2*4*9)
+	add		r7,r0,#(48+3*4*9)
+
+	vmov		d0,d10		@ r^4:r^3
+	vshl.u32	d2,d12,#2		@ *5
+	vmov		d1,d12
+	vshl.u32	d4,d14,#2
+	vmov		d3,d14
+	vshl.u32	d6,d16,#2
+	vmov		d5,d16
+	vshl.u32	d8,d18,#2
+	vmov		d7,d18
+	vadd.i32	d2,d2,d12
+	vadd.i32	d4,d4,d14
+	vadd.i32	d6,d6,d16
+	vadd.i32	d8,d8,d18
+
+	vst4.32		{d0[0],d1[0],d2[0],d3[0]},[r6]!
+	vst4.32		{d0[1],d1[1],d2[1],d3[1]},[r7]!
+	vst4.32		{d4[0],d5[0],d6[0],d7[0]},[r6]!
+	vst4.32		{d4[1],d5[1],d6[1],d7[1]},[r7]!
+	vst1.32		{d8[0]},[r6]
+	vst1.32		{d8[1]},[r7]
+
+.Lno_init_neon:
+	bx	lr				@ bx	lr
+.size	poly1305_init_neon,.-poly1305_init_neon
+
+.type	poly1305_blocks_neon,%function
+.align	5
+poly1305_blocks_neon:
+.Lpoly1305_blocks_neon:
+	ldr	ip,[r0,#36]		@ is_base2_26
+
+	cmp	r2,#64
+	blo	.Lpoly1305_blocks
+
+	stmdb	sp!,{r4-r7}
+	vstmdb	sp!,{d8-d15}		@ ABI specification says so
+
+	tst	ip,ip			@ is_base2_26?
+	bne	.Lbase2_26_neon
+
+	stmdb	sp!,{r1-r3,lr}
+	bl	.Lpoly1305_init_neon
+
+	ldr	r4,[r0,#0]		@ load hash value base 2^32
+	ldr	r5,[r0,#4]
+	ldr	r6,[r0,#8]
+	ldr	r7,[r0,#12]
+	ldr	ip,[r0,#16]
+
+	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
+	mov	r3,r4,lsr#26
+	 veor	d10,d10,d10
+	mov	r4,r5,lsr#20
+	orr	r3,r3,r5,lsl#6
+	 veor	d12,d12,d12
+	mov	r5,r6,lsr#14
+	orr	r4,r4,r6,lsl#12
+	 veor	d14,d14,d14
+	mov	r6,r7,lsr#8
+	orr	r5,r5,r7,lsl#18
+	 veor	d16,d16,d16
+	and	r3,r3,#0x03ffffff
+	orr	r6,r6,ip,lsl#24
+	 veor	d18,d18,d18
+	and	r4,r4,#0x03ffffff
+	mov	r1,#1
+	and	r5,r5,#0x03ffffff
+	str	r1,[r0,#36]		@ set is_base2_26
+
+	vmov.32	d10[0],r2
+	vmov.32	d12[0],r3
+	vmov.32	d14[0],r4
+	vmov.32	d16[0],r5
+	vmov.32	d18[0],r6
+	adr	r5,.Lzeros
+
+	ldmia	sp!,{r1-r3,lr}
+	b	.Lhash_loaded
+
+.align	4
+.Lbase2_26_neon:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ load hash value
+
+	veor		d10,d10,d10
+	veor		d12,d12,d12
+	veor		d14,d14,d14
+	veor		d16,d16,d16
+	veor		d18,d18,d18
+	vld4.32		{d10[0],d12[0],d14[0],d16[0]},[r0]!
+	adr		r5,.Lzeros
+	vld1.32		{d18[0]},[r0]
+	sub		r0,r0,#16		@ rewind
+
+.Lhash_loaded:
+	add		r4,r1,#32
+	mov		r3,r3,lsl#24
+	tst		r2,#31
+	beq		.Leven
+
+	vld4.32		{d20[0],d22[0],d24[0],d26[0]},[r1]!
+	vmov.32		d28[0],r3
+	sub		r2,r2,#16
+	add		r4,r1,#32
+
+# ifdef	__ARMEB__
+	vrev32.8	q10,q10
+	vrev32.8	q13,q13
+	vrev32.8	q11,q11
+	vrev32.8	q12,q12
+# endif
+	vsri.u32	d28,d26,#8	@ base 2^32 -> base 2^26
+	vshl.u32	d26,d26,#18
+
+	vsri.u32	d26,d24,#14
+	vshl.u32	d24,d24,#12
+	vadd.i32	d29,d28,d18	@ add hash value and move to #hi
+
+	vbic.i32	d26,#0xfc000000
+	vsri.u32	d24,d22,#20
+	vshl.u32	d22,d22,#6
+
+	vbic.i32	d24,#0xfc000000
+	vsri.u32	d22,d20,#26
+	vadd.i32	d27,d26,d16
+
+	vbic.i32	d20,#0xfc000000
+	vbic.i32	d22,#0xfc000000
+	vadd.i32	d25,d24,d14
+
+	vadd.i32	d21,d20,d10
+	vadd.i32	d23,d22,d12
+
+	mov		r7,r5
+	add		r6,r0,#48
+
+	cmp		r2,r2
+	b		.Long_tail
+
+.align	4
+.Leven:
+	subs		r2,r2,#64
+	it		lo
+	movlo		r4,r5
+
+	vmov.i32	q14,#1<<24		@ padbit, yes, always
+	vld4.32		{d20,d22,d24,d26},[r1]	@ inp[0:1]
+	add		r1,r1,#64
+	vld4.32		{d21,d23,d25,d27},[r4]	@ inp[2:3] (or 0)
+	add		r4,r4,#64
+	itt		hi
+	addhi		r7,r0,#(48+1*9*4)
+	addhi		r6,r0,#(48+3*9*4)
+
+# ifdef	__ARMEB__
+	vrev32.8	q10,q10
+	vrev32.8	q13,q13
+	vrev32.8	q11,q11
+	vrev32.8	q12,q12
+# endif
+	vsri.u32	q14,q13,#8		@ base 2^32 -> base 2^26
+	vshl.u32	q13,q13,#18
+
+	vsri.u32	q13,q12,#14
+	vshl.u32	q12,q12,#12
+
+	vbic.i32	q13,#0xfc000000
+	vsri.u32	q12,q11,#20
+	vshl.u32	q11,q11,#6
+
+	vbic.i32	q12,#0xfc000000
+	vsri.u32	q11,q10,#26
+
+	vbic.i32	q10,#0xfc000000
+	vbic.i32	q11,#0xfc000000
+
+	bls		.Lskip_loop
+
+	vld4.32		{d0[1],d1[1],d2[1],d3[1]},[r7]!	@ load r^2
+	vld4.32		{d0[0],d1[0],d2[0],d3[0]},[r6]!	@ load r^4
+	vld4.32		{d4[1],d5[1],d6[1],d7[1]},[r7]!
+	vld4.32		{d4[0],d5[0],d6[0],d7[0]},[r6]!
+	b		.Loop_neon
+
+.align	5
+.Loop_neon:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
+	@ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
+	@   ___________________/
+	@ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
+	@ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
+	@   ___________________/ ____________________/
+	@
+	@ Note that we start with inp[2:3]*r^2. This is because it
+	@ doesn't depend on reduction in previous iteration.
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ d4 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4
+	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
+	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
+	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
+	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ inp[2:3]*r^2
+
+	vadd.i32	d24,d24,d14	@ accumulate inp[0:1]
+	vmull.u32	q7,d25,d0[1]
+	vadd.i32	d20,d20,d10
+	vmull.u32	q5,d21,d0[1]
+	vadd.i32	d26,d26,d16
+	vmull.u32	q8,d27,d0[1]
+	vmlal.u32	q7,d23,d1[1]
+	vadd.i32	d22,d22,d12
+	vmull.u32	q6,d23,d0[1]
+
+	vadd.i32	d28,d28,d18
+	vmull.u32	q9,d29,d0[1]
+	subs		r2,r2,#64
+	vmlal.u32	q5,d29,d2[1]
+	it		lo
+	movlo		r4,r5
+	vmlal.u32	q8,d25,d1[1]
+	vld1.32		d8[1],[r7,:32]
+	vmlal.u32	q6,d21,d1[1]
+	vmlal.u32	q9,d27,d1[1]
+
+	vmlal.u32	q5,d27,d4[1]
+	vmlal.u32	q8,d23,d3[1]
+	vmlal.u32	q9,d25,d3[1]
+	vmlal.u32	q6,d29,d4[1]
+	vmlal.u32	q7,d21,d3[1]
+
+	vmlal.u32	q8,d21,d5[1]
+	vmlal.u32	q5,d25,d6[1]
+	vmlal.u32	q9,d23,d5[1]
+	vmlal.u32	q6,d27,d6[1]
+	vmlal.u32	q7,d29,d6[1]
+
+	vmlal.u32	q8,d29,d8[1]
+	vmlal.u32	q5,d23,d8[1]
+	vmlal.u32	q9,d21,d7[1]
+	vmlal.u32	q6,d25,d8[1]
+	vmlal.u32	q7,d27,d8[1]
+
+	vld4.32		{d21,d23,d25,d27},[r4]	@ inp[2:3] (or 0)
+	add		r4,r4,#64
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ (hash+inp[0:1])*r^4 and accumulate
+
+	vmlal.u32	q8,d26,d0[0]
+	vmlal.u32	q5,d20,d0[0]
+	vmlal.u32	q9,d28,d0[0]
+	vmlal.u32	q6,d22,d0[0]
+	vmlal.u32	q7,d24,d0[0]
+	vld1.32		d8[0],[r6,:32]
+
+	vmlal.u32	q8,d24,d1[0]
+	vmlal.u32	q5,d28,d2[0]
+	vmlal.u32	q9,d26,d1[0]
+	vmlal.u32	q6,d20,d1[0]
+	vmlal.u32	q7,d22,d1[0]
+
+	vmlal.u32	q8,d22,d3[0]
+	vmlal.u32	q5,d26,d4[0]
+	vmlal.u32	q9,d24,d3[0]
+	vmlal.u32	q6,d28,d4[0]
+	vmlal.u32	q7,d20,d3[0]
+
+	vmlal.u32	q8,d20,d5[0]
+	vmlal.u32	q5,d24,d6[0]
+	vmlal.u32	q9,d22,d5[0]
+	vmlal.u32	q6,d26,d6[0]
+	vmlal.u32	q8,d28,d8[0]
+
+	vmlal.u32	q7,d28,d6[0]
+	vmlal.u32	q5,d22,d8[0]
+	vmlal.u32	q9,d20,d7[0]
+	vmov.i32	q14,#1<<24		@ padbit, yes, always
+	vmlal.u32	q6,d24,d8[0]
+	vmlal.u32	q7,d26,d8[0]
+
+	vld4.32		{d20,d22,d24,d26},[r1]	@ inp[0:1]
+	add		r1,r1,#64
+# ifdef	__ARMEB__
+	vrev32.8	q10,q10
+	vrev32.8	q11,q11
+	vrev32.8	q12,q12
+	vrev32.8	q13,q13
+# endif
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ lazy reduction interleaved with base 2^32 -> base 2^26 of
+	@ inp[0:3] previously loaded to q10-q13 and smashed to q10-q14.
+
+	vshr.u64	q15,q8,#26
+	vmovn.i64	d16,q8
+	 vshr.u64	q4,q5,#26
+	 vmovn.i64	d10,q5
+	vadd.i64	q9,q9,q15		@ h3 -> h4
+	vbic.i32	d16,#0xfc000000
+	  vsri.u32	q14,q13,#8		@ base 2^32 -> base 2^26
+	 vadd.i64	q6,q6,q4		@ h0 -> h1
+	  vshl.u32	q13,q13,#18
+	 vbic.i32	d10,#0xfc000000
+
+	vshrn.u64	d30,q9,#26
+	vmovn.i64	d18,q9
+	 vshr.u64	q4,q6,#26
+	 vmovn.i64	d12,q6
+	 vadd.i64	q7,q7,q4		@ h1 -> h2
+	  vsri.u32	q13,q12,#14
+	vbic.i32	d18,#0xfc000000
+	  vshl.u32	q12,q12,#12
+	 vbic.i32	d12,#0xfc000000
+
+	vadd.i32	d10,d10,d30
+	vshl.u32	d30,d30,#2
+	  vbic.i32	q13,#0xfc000000
+	 vshrn.u64	d8,q7,#26
+	 vmovn.i64	d14,q7
+	vaddl.u32	q5,d10,d30	@ h4 -> h0 [widen for a sec]
+	  vsri.u32	q12,q11,#20
+	 vadd.i32	d16,d16,d8	@ h2 -> h3
+	  vshl.u32	q11,q11,#6
+	 vbic.i32	d14,#0xfc000000
+	  vbic.i32	q12,#0xfc000000
+
+	vshrn.u64	d30,q5,#26		@ re-narrow
+	vmovn.i64	d10,q5
+	  vsri.u32	q11,q10,#26
+	  vbic.i32	q10,#0xfc000000
+	 vshr.u32	d8,d16,#26
+	 vbic.i32	d16,#0xfc000000
+	vbic.i32	d10,#0xfc000000
+	vadd.i32	d12,d12,d30	@ h0 -> h1
+	 vadd.i32	d18,d18,d8	@ h3 -> h4
+	  vbic.i32	q11,#0xfc000000
+
+	bhi		.Loop_neon
+
+.Lskip_loop:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
+
+	add		r7,r0,#(48+0*9*4)
+	add		r6,r0,#(48+1*9*4)
+	adds		r2,r2,#32
+	it		ne
+	movne		r2,#0
+	bne		.Long_tail
+
+	vadd.i32	d25,d24,d14	@ add hash value and move to #hi
+	vadd.i32	d21,d20,d10
+	vadd.i32	d27,d26,d16
+	vadd.i32	d23,d22,d12
+	vadd.i32	d29,d28,d18
+
+.Long_tail:
+	vld4.32		{d0[1],d1[1],d2[1],d3[1]},[r7]!	@ load r^1
+	vld4.32		{d0[0],d1[0],d2[0],d3[0]},[r6]!	@ load r^2
+
+	vadd.i32	d24,d24,d14	@ can be redundant
+	vmull.u32	q7,d25,d0
+	vadd.i32	d20,d20,d10
+	vmull.u32	q5,d21,d0
+	vadd.i32	d26,d26,d16
+	vmull.u32	q8,d27,d0
+	vadd.i32	d22,d22,d12
+	vmull.u32	q6,d23,d0
+	vadd.i32	d28,d28,d18
+	vmull.u32	q9,d29,d0
+
+	vmlal.u32	q5,d29,d2
+	vld4.32		{d4[1],d5[1],d6[1],d7[1]},[r7]!
+	vmlal.u32	q8,d25,d1
+	vld4.32		{d4[0],d5[0],d6[0],d7[0]},[r6]!
+	vmlal.u32	q6,d21,d1
+	vmlal.u32	q9,d27,d1
+	vmlal.u32	q7,d23,d1
+
+	vmlal.u32	q8,d23,d3
+	vld1.32		d8[1],[r7,:32]
+	vmlal.u32	q5,d27,d4
+	vld1.32		d8[0],[r6,:32]
+	vmlal.u32	q9,d25,d3
+	vmlal.u32	q6,d29,d4
+	vmlal.u32	q7,d21,d3
+
+	vmlal.u32	q8,d21,d5
+	 it		ne
+	 addne		r7,r0,#(48+2*9*4)
+	vmlal.u32	q5,d25,d6
+	 it		ne
+	 addne		r6,r0,#(48+3*9*4)
+	vmlal.u32	q9,d23,d5
+	vmlal.u32	q6,d27,d6
+	vmlal.u32	q7,d29,d6
+
+	vmlal.u32	q8,d29,d8
+	 vorn		q0,q0,q0	@ all-ones, can be redundant
+	vmlal.u32	q5,d23,d8
+	 vshr.u64	q0,q0,#38
+	vmlal.u32	q9,d21,d7
+	vmlal.u32	q6,d25,d8
+	vmlal.u32	q7,d27,d8
+
+	beq		.Lshort_tail
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ (hash+inp[0:1])*r^4:r^3 and accumulate
+
+	vld4.32		{d0[1],d1[1],d2[1],d3[1]},[r7]!	@ load r^3
+	vld4.32		{d0[0],d1[0],d2[0],d3[0]},[r6]!	@ load r^4
+
+	vmlal.u32	q7,d24,d0
+	vmlal.u32	q5,d20,d0
+	vmlal.u32	q8,d26,d0
+	vmlal.u32	q6,d22,d0
+	vmlal.u32	q9,d28,d0
+
+	vmlal.u32	q5,d28,d2
+	vld4.32		{d4[1],d5[1],d6[1],d7[1]},[r7]!
+	vmlal.u32	q8,d24,d1
+	vld4.32		{d4[0],d5[0],d6[0],d7[0]},[r6]!
+	vmlal.u32	q6,d20,d1
+	vmlal.u32	q9,d26,d1
+	vmlal.u32	q7,d22,d1
+
+	vmlal.u32	q8,d22,d3
+	vld1.32		d8[1],[r7,:32]
+	vmlal.u32	q5,d26,d4
+	vld1.32		d8[0],[r6,:32]
+	vmlal.u32	q9,d24,d3
+	vmlal.u32	q6,d28,d4
+	vmlal.u32	q7,d20,d3
+
+	vmlal.u32	q8,d20,d5
+	vmlal.u32	q5,d24,d6
+	vmlal.u32	q9,d22,d5
+	vmlal.u32	q6,d26,d6
+	vmlal.u32	q7,d28,d6
+
+	vmlal.u32	q8,d28,d8
+	 vorn		q0,q0,q0	@ all-ones
+	vmlal.u32	q5,d22,d8
+	 vshr.u64	q0,q0,#38
+	vmlal.u32	q9,d20,d7
+	vmlal.u32	q6,d24,d8
+	vmlal.u32	q7,d26,d8
+
+.Lshort_tail:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ horizontal addition
+
+	vadd.i64	d16,d16,d17
+	vadd.i64	d10,d10,d11
+	vadd.i64	d18,d18,d19
+	vadd.i64	d12,d12,d13
+	vadd.i64	d14,d14,d15
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ lazy reduction, but without narrowing
+
+	vshr.u64	q15,q8,#26
+	vand.i64	q8,q8,q0
+	 vshr.u64	q4,q5,#26
+	 vand.i64	q5,q5,q0
+	vadd.i64	q9,q9,q15		@ h3 -> h4
+	 vadd.i64	q6,q6,q4		@ h0 -> h1
+
+	vshr.u64	q15,q9,#26
+	vand.i64	q9,q9,q0
+	 vshr.u64	q4,q6,#26
+	 vand.i64	q6,q6,q0
+	 vadd.i64	q7,q7,q4		@ h1 -> h2
+
+	vadd.i64	q5,q5,q15
+	vshl.u64	q15,q15,#2
+	 vshr.u64	q4,q7,#26
+	 vand.i64	q7,q7,q0
+	vadd.i64	q5,q5,q15		@ h4 -> h0
+	 vadd.i64	q8,q8,q4		@ h2 -> h3
+
+	vshr.u64	q15,q5,#26
+	vand.i64	q5,q5,q0
+	 vshr.u64	q4,q8,#26
+	 vand.i64	q8,q8,q0
+	vadd.i64	q6,q6,q15		@ h0 -> h1
+	 vadd.i64	q9,q9,q4		@ h3 -> h4
+
+	cmp		r2,#0
+	bne		.Leven
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ store hash value
+
+	vst4.32		{d10[0],d12[0],d14[0],d16[0]},[r0]!
+	vst1.32		{d18[0]},[r0]
+
+	vldmia	sp!,{d8-d15}			@ epilogue
+	ldmia	sp!,{r4-r7}
+	bx	lr					@ bx	lr
+.size	poly1305_blocks_neon,.-poly1305_blocks_neon
+
+.align	5
+.Lzeros:
+.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
+#ifndef	__KERNEL__
+.LOPENSSL_armcap:
+# ifdef	_WIN32
+.word	OPENSSL_armcap_P
+# else
+.word	OPENSSL_armcap_P-.Lpoly1305_init
+# endif
+.comm	OPENSSL_armcap_P,4,4
+.hidden	OPENSSL_armcap_P
+#endif
+#endif
+.asciz	"Poly1305 for ARMv4/NEON, CRYPTOGAMS by @dot-asm"
+.align	2
diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c
new file mode 100644
index 000000000000..74a725ac89c9
--- /dev/null
+++ b/arch/arm/crypto/poly1305-glue.c
@@ -0,0 +1,276 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * OpenSSL/Cryptogams accelerated Poly1305 transform for ARM
+ *
+ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/poly1305.h>
+#include <crypto/internal/simd.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/jump_label.h>
+#include <linux/module.h>
+
+void poly1305_init_arm(void *state, const u8 *key);
+void poly1305_blocks_arm(void *state, const u8 *src, u32 len, u32 hibit);
+void poly1305_emit_arm(void *state, __le32 *digest, const u32 *nonce);
+
+void __weak poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit)
+{
+}
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key)
+{
+	poly1305_init_arm(&dctx->h, key);
+	dctx->s[0] = get_unaligned_le32(key + 16);
+	dctx->s[1] = get_unaligned_le32(key + 20);
+	dctx->s[2] = get_unaligned_le32(key + 24);
+	dctx->s[3] = get_unaligned_le32(key + 28);
+	dctx->buflen = 0;
+}
+EXPORT_SYMBOL(poly1305_init_arch);
+
+static int arm_poly1305_init(struct shash_desc *desc)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	dctx->buflen = 0;
+	dctx->rset = 0;
+	dctx->sset = false;
+
+	return 0;
+}
+
+static void arm_poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
+				 u32 len, u32 hibit, bool do_neon)
+{
+	if (unlikely(!dctx->sset)) {
+		if (!dctx->rset) {
+			poly1305_init_arm(&dctx->h, src);
+			src += POLY1305_BLOCK_SIZE;
+			len -= POLY1305_BLOCK_SIZE;
+			dctx->rset = 1;
+		}
+		if (len >= POLY1305_BLOCK_SIZE) {
+			dctx->s[0] = get_unaligned_le32(src +  0);
+			dctx->s[1] = get_unaligned_le32(src +  4);
+			dctx->s[2] = get_unaligned_le32(src +  8);
+			dctx->s[3] = get_unaligned_le32(src + 12);
+			src += POLY1305_BLOCK_SIZE;
+			len -= POLY1305_BLOCK_SIZE;
+			dctx->sset = true;
+		}
+		if (len < POLY1305_BLOCK_SIZE)
+			return;
+	}
+
+	len &= ~(POLY1305_BLOCK_SIZE - 1);
+
+	if (static_branch_likely(&have_neon) && likely(do_neon))
+		poly1305_blocks_neon(&dctx->h, src, len, hibit);
+	else
+		poly1305_blocks_arm(&dctx->h, src, len, hibit);
+}
+
+static void arm_poly1305_do_update(struct poly1305_desc_ctx *dctx,
+				    const u8 *src, u32 len, bool do_neon)
+{
+	if (unlikely(dctx->buflen)) {
+		u32 bytes = min(len, POLY1305_BLOCK_SIZE - dctx->buflen);
+
+		memcpy(dctx->buf + dctx->buflen, src, bytes);
+		src += bytes;
+		len -= bytes;
+		dctx->buflen += bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			arm_poly1305_blocks(dctx, dctx->buf,
+					    POLY1305_BLOCK_SIZE, 1, false);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (likely(len >= POLY1305_BLOCK_SIZE)) {
+		arm_poly1305_blocks(dctx, src, len, 1, do_neon);
+		src += round_down(len, POLY1305_BLOCK_SIZE);
+		len %= POLY1305_BLOCK_SIZE;
+	}
+
+	if (unlikely(len)) {
+		dctx->buflen = len;
+		memcpy(dctx->buf, src, len);
+	}
+}
+
+static int arm_poly1305_update(struct shash_desc *desc,
+			       const u8 *src, unsigned int srclen)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	arm_poly1305_do_update(dctx, src, srclen, false);
+	return 0;
+}
+
+static int __maybe_unused arm_poly1305_update_neon(struct shash_desc *desc,
+						   const u8 *src,
+						   unsigned int srclen)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+	bool do_neon = crypto_simd_usable() && srclen > 128;
+
+	if (static_branch_likely(&have_neon) && do_neon)
+		kernel_neon_begin();
+	arm_poly1305_do_update(dctx, src, srclen, do_neon);
+	if (static_branch_likely(&have_neon) && do_neon)
+		kernel_neon_end();
+	return 0;
+}
+
+void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
+			  unsigned int nbytes)
+{
+	bool do_neon = IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+		       crypto_simd_usable();
+
+	if (unlikely(dctx->buflen)) {
+		u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);
+
+		memcpy(dctx->buf + dctx->buflen, src, bytes);
+		src += bytes;
+		nbytes -= bytes;
+		dctx->buflen += bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			poly1305_blocks_arm(&dctx->h, dctx->buf,
+					    POLY1305_BLOCK_SIZE, 1);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
+		unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);
+
+		if (static_branch_likely(&have_neon) && do_neon) {
+			kernel_neon_begin();
+			poly1305_blocks_neon(&dctx->h, src, len, 1);
+			kernel_neon_end();
+		} else {
+			poly1305_blocks_arm(&dctx->h, src, len, 1);
+		}
+		src += len;
+		nbytes %= POLY1305_BLOCK_SIZE;
+	}
+
+	if (unlikely(nbytes)) {
+		dctx->buflen = nbytes;
+		memcpy(dctx->buf, src, nbytes);
+	}
+}
+EXPORT_SYMBOL(poly1305_update_arch);
+
+void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
+{
+	__le32 digest[4];
+	u64 f = 0;
+
+	if (unlikely(dctx->buflen)) {
+		dctx->buf[dctx->buflen++] = 1;
+		memset(dctx->buf + dctx->buflen, 0,
+		       POLY1305_BLOCK_SIZE - dctx->buflen);
+		poly1305_blocks_arm(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
+	}
+
+	poly1305_emit_arm(&dctx->h, digest, dctx->s);
+
+	/* mac = (h + s) % (2^128) */
+	f = (f >> 32) + le32_to_cpu(digest[0]);
+	put_unaligned_le32(f, dst);
+	f = (f >> 32) + le32_to_cpu(digest[1]);
+	put_unaligned_le32(f, dst + 4);
+	f = (f >> 32) + le32_to_cpu(digest[2]);
+	put_unaligned_le32(f, dst + 8);
+	f = (f >> 32) + le32_to_cpu(digest[3]);
+	put_unaligned_le32(f, dst + 12);
+
+	*dctx = (struct poly1305_desc_ctx){};
+}
+EXPORT_SYMBOL(poly1305_final_arch);
+
+static int arm_poly1305_final(struct shash_desc *desc, u8 *dst)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (unlikely(!dctx->sset))
+		return -ENOKEY;
+
+	poly1305_final_arch(dctx, dst);
+	return 0;
+}
+
+static struct shash_alg arm_poly1305_algs[] = {{
+	.init			= arm_poly1305_init,
+	.update			= arm_poly1305_update,
+	.final			= arm_poly1305_final,
+	.digestsize		= POLY1305_DIGEST_SIZE,
+	.descsize		= sizeof(struct poly1305_desc_ctx),
+
+	.base.cra_name		= "poly1305",
+	.base.cra_driver_name	= "poly1305-arm",
+	.base.cra_priority	= 150,
+	.base.cra_blocksize	= POLY1305_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+#ifdef CONFIG_KERNEL_MODE_NEON
+}, {
+	.init			= arm_poly1305_init,
+	.update			= arm_poly1305_update_neon,
+	.final			= arm_poly1305_final,
+	.digestsize		= POLY1305_DIGEST_SIZE,
+	.descsize		= sizeof(struct poly1305_desc_ctx),
+
+	.base.cra_name		= "poly1305",
+	.base.cra_driver_name	= "poly1305-neon",
+	.base.cra_priority	= 200,
+	.base.cra_blocksize	= POLY1305_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+#endif
+}};
+
+static int __init arm_poly1305_mod_init(void)
+{
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+	    (elf_hwcap & HWCAP_NEON))
+		static_branch_enable(&have_neon);
+	else
+		/* register only the first entry */
+		return crypto_register_shash(&arm_poly1305_algs[0]);
+
+	return crypto_register_shashes(arm_poly1305_algs,
+				       ARRAY_SIZE(arm_poly1305_algs));
+}
+
+static void __exit arm_poly1305_mod_exit(void)
+{
+	if (!static_branch_likely(&have_neon)) {
+		crypto_unregister_shash(&arm_poly1305_algs[0]);
+		return;
+	}
+	crypto_unregister_shashes(arm_poly1305_algs,
+				  ARRAY_SIZE(arm_poly1305_algs));
+}
+
+module_init(arm_poly1305_mod_init);
+module_exit(arm_poly1305_mod_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("poly1305");
+MODULE_ALIAS_CRYPTO("poly1305-arm");
+MODULE_ALIAS_CRYPTO("poly1305-neon");
diff --git a/arch/arm/crypto/sha1-ce-core.S b/arch/arm/crypto/sha1-ce-core.S
index 49a74a441aec..8a702e051738 100644
--- a/arch/arm/crypto/sha1-ce-core.S
+++ b/arch/arm/crypto/sha1-ce-core.S
@@ -10,6 +10,7 @@
 #include <asm/assembler.h>
 
 	.text
+	.arch		armv8-a
 	.fpu		crypto-neon-fp-armv8
 
 	k0		.req	q0
diff --git a/arch/arm/crypto/sha2-ce-core.S b/arch/arm/crypto/sha2-ce-core.S
index 4ad517577e23..b6369d2440a1 100644
--- a/arch/arm/crypto/sha2-ce-core.S
+++ b/arch/arm/crypto/sha2-ce-core.S
@@ -10,6 +10,7 @@
 #include <asm/assembler.h>
 
 	.text
+	.arch		armv8-a
 	.fpu		crypto-neon-fp-armv8
 
 	k0		.req	q7
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index 0125aa059d5b..9c04bd810d07 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -162,6 +162,7 @@
 #define HSR_ISV		(_AC(1, UL) << HSR_ISV_SHIFT)
 #define HSR_SRT_SHIFT	(16)
 #define HSR_SRT_MASK	(0xf << HSR_SRT_SHIFT)
+#define HSR_CM		(1 << 8)
 #define HSR_FSC		(0x3f)
 #define HSR_FSC_TYPE	(0x3c)
 #define HSR_SSE		(1 << 21)
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 40002416efec..9b118516d2db 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -95,12 +95,12 @@ static inline unsigned long *vcpu_hcr(const struct kvm_vcpu *vcpu)
 	return (unsigned long *)&vcpu->arch.hcr;
 }
 
-static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr &= ~HCR_TWE;
 }
 
-static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr |= HCR_TWE;
 }
@@ -167,6 +167,11 @@ static inline bool kvm_vcpu_dabt_isvalid(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & HSR_ISV;
 }
 
+static inline unsigned long kvm_vcpu_dabt_iss_nisv_sanitized(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & (HSR_CM | HSR_WNR | HSR_FSC);
+}
+
 static inline bool kvm_vcpu_dabt_iswrite(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_hsr(vcpu) & HSR_WNR;
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 8a37c8e89777..556cd818eccf 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -7,6 +7,7 @@
 #ifndef __ARM_KVM_HOST_H__
 #define __ARM_KVM_HOST_H__
 
+#include <linux/arm-smccc.h>
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/kvm_types.h>
@@ -38,6 +39,7 @@
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
 #define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
+#define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
 
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
@@ -76,6 +78,14 @@ struct kvm_arch {
 
 	/* Mandated version of PSCI */
 	u32 psci_version;
+
+	/*
+	 * If we encounter a data abort without valid instruction syndrome
+	 * information, report this to user space.  User space can (and
+	 * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is
+	 * supported.
+	 */
+	bool return_nisv_io_abort_to_user;
 };
 
 #define KVM_NR_MEM_OBJS     40
@@ -323,6 +333,29 @@ static inline int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
+static inline long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
+{
+	return SMCCC_RET_NOT_SUPPORTED;
+}
+
+static inline gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
+{
+	return GPA_INVALID;
+}
+
+static inline void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
+{
+}
+
+static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch)
+{
+	return false;
+}
+
 void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
 
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index 2769360f195c..03cd7c19a683 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -131,8 +131,9 @@ struct kvm_vcpu_events {
 	struct {
 		__u8 serror_pending;
 		__u8 serror_has_esr;
+		__u8 ext_dabt_pending;
 		/* Align it to 8 bytes */
-		__u8 pad[6];
+		__u8 pad[5];
 		__u64 serror_esr;
 	} exception;
 	__u32 reserved[12];
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index b76b75bd9e00..e442d82821df 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -24,7 +24,7 @@ obj-y += kvm-arm.o init.o interrupts.o
 obj-y += handle_exit.o guest.o emulate.o reset.o
 obj-y += coproc.o coproc_a15.o coproc_a7.o   vgic-v3-coproc.o
 obj-y += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o
-obj-y += $(KVM)/arm/psci.o $(KVM)/arm/perf.o
+obj-y += $(KVM)/arm/psci.o $(KVM)/arm/perf.o $(KVM)/arm/hypercalls.o
 obj-y += $(KVM)/arm/aarch32.o
 
 obj-y += $(KVM)/arm/vgic/vgic.o
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 684cf64b4033..0e6f23504c26 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -21,6 +21,10 @@
 #define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU }
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
+	VCPU_STAT(halt_successful_poll),
+	VCPU_STAT(halt_attempted_poll),
+	VCPU_STAT(halt_poll_invalid),
+	VCPU_STAT(halt_wakeup),
 	VCPU_STAT(hvc_exit_stat),
 	VCPU_STAT(wfe_exit_stat),
 	VCPU_STAT(wfi_exit_stat),
@@ -255,6 +259,12 @@ int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
 {
 	events->exception.serror_pending = !!(*vcpu_hcr(vcpu) & HCR_VA);
 
+	/*
+	 * We never return a pending ext_dabt here because we deliver it to
+	 * the virtual CPU directly when setting the event and it's no longer
+	 * 'pending' at this point.
+	 */
+
 	return 0;
 }
 
@@ -263,12 +273,16 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 {
 	bool serror_pending = events->exception.serror_pending;
 	bool has_esr = events->exception.serror_has_esr;
+	bool ext_dabt_pending = events->exception.ext_dabt_pending;
 
 	if (serror_pending && has_esr)
 		return -EINVAL;
 	else if (serror_pending)
 		kvm_inject_vabt(vcpu);
 
+	if (ext_dabt_pending)
+		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+
 	return 0;
 }
 
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 2a6a1394d26e..e58a89d2f13f 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -9,7 +9,7 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_mmu.h>
-#include <kvm/arm_psci.h>
+#include <kvm/arm_hypercalls.h>
 #include <trace/events/kvm.h>
 
 #include "trace.h"
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 2efd18e8824c..de8c54034a5a 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -269,21 +269,13 @@ static void __init am3517_evm_legacy_init(void)
 	am35xx_emac_reset();
 }
 
-static struct platform_device omap3_rom_rng_device = {
-	.name		= "omap3-rom-rng",
-	.id		= -1,
-	.dev	= {
-		.platform_data	= rx51_secure_rng_call,
-	},
-};
-
 static void __init nokia_n900_legacy_init(void)
 {
 	hsmmc2_internal_input_clk();
 	mmc_pdata[0].name = "external";
 	mmc_pdata[1].name = "internal";
 
-	if (omap_type() == OMAP2_DEVICE_TYPE_SEC) {
+	if (omap_type() != OMAP2_DEVICE_TYPE_GP) {
 		if (IS_ENABLED(CONFIG_ARM_ERRATA_430973)) {
 			pr_info("RX-51: Enabling ARM errata 430973 workaround\n");
 			/* set IBE to 1 */
@@ -292,9 +284,6 @@ static void __init nokia_n900_legacy_init(void)
 			pr_warn("RX-51: Not enabling ARM errata 430973 workaround\n");
 			pr_warn("Thumb binaries may crash randomly without this workaround\n");
 		}
-
-		pr_info("RX-51: Registering OMAP3 HWRNG device\n");
-		platform_device_register(&omap3_rom_rng_device);
 	}
 }
 
@@ -638,6 +627,7 @@ static struct of_dev_auxdata omap_auxdata_lookup[] = {
 	OF_DEV_AUXDATA("ti,davinci_mdio", 0x5c030000, "davinci_mdio.0", NULL),
 	OF_DEV_AUXDATA("ti,am3517-emac", 0x5c000000, "davinci_emac.0",
 		       &am35xx_emac_pdata),
+	OF_DEV_AUXDATA("nokia,n900-rom-rng", 0, NULL, rx51_secure_rng_call),
 	/* McBSP modules with sidetone core */
 #if IS_ENABLED(CONFIG_SND_SOC_OMAP_MCBSP)
 	OF_DEV_AUXDATA("ti,omap3-mcbsp", 0x49022000, "49022000.mcbsp", &mcbsp_pdata),
diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c
index 9a07916af8dd..7c90b4c615a5 100644
--- a/arch/arm/mm/proc-v7-bugs.c
+++ b/arch/arm/mm/proc-v7-bugs.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/arm-smccc.h>
 #include <linux/kernel.h>
-#include <linux/psci.h>
 #include <linux/smp.h>
 
 #include <asm/cp15.h>
@@ -75,26 +74,20 @@ static void cpu_v7_spectre_init(void)
 	case ARM_CPU_PART_CORTEX_A72: {
 		struct arm_smccc_res res;
 
-		if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
-			break;
+		arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+				     ARM_SMCCC_ARCH_WORKAROUND_1, &res);
+		if ((int)res.a0 != 0)
+			return;
 
-		switch (psci_ops.conduit) {
-		case PSCI_CONDUIT_HVC:
-			arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-					  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-			if ((int)res.a0 != 0)
-				break;
+		switch (arm_smccc_1_1_get_conduit()) {
+		case SMCCC_CONDUIT_HVC:
 			per_cpu(harden_branch_predictor_fn, cpu) =
 				call_hvc_arch_workaround_1;
 			cpu_do_switch_mm = cpu_v7_hvc_switch_mm;
 			spectre_v2_method = "hypervisor";
 			break;
 
-		case PSCI_CONDUIT_SMC:
-			arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-					  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-			if ((int)res.a0 != 0)
-				break;
+		case SMCCC_CONDUIT_SMC:
 			per_cpu(harden_branch_predictor_fn, cpu) =
 				call_smc_arch_workaround_1;
 			cpu_do_switch_mm = cpu_v7_smc_switch_mm;
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 38fa917c8585..3c7645d7b9b4 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -15,6 +15,7 @@
 #include <xen/interface/grant_table.h>
 #include <xen/interface/memory.h>
 #include <xen/page.h>
+#include <xen/xen-ops.h>
 #include <xen/swiotlb-xen.h>
 
 #include <asm/cacheflush.h>
@@ -133,7 +134,7 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 	return;
 }
 
-int __init xen_mm_init(void)
+static int __init xen_mm_init(void)
 {
 	struct gnttab_cache_flush cflush;
 	if (!xen_initial_domain())
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3f047afb982c..fcc6635666b4 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -67,7 +67,7 @@ config ARM64
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select ARCH_SUPPORTS_ATOMIC_RMW
-	select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000 || CC_IS_CLANG
+	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG)
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
@@ -143,6 +143,8 @@ config ARM64
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS \
+		if $(cc-option,-fpatchable-function-entry=2)
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_FAST_GUP
 	select HAVE_FTRACE_MCOUNT_RECORD
@@ -266,6 +268,10 @@ config GENERIC_CSUM
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
+config ZONE_DMA
+	bool "Support DMA zone" if EXPERT
+	default y
+
 config ZONE_DMA32
 	bool "Support DMA32 zone" if EXPERT
 	default y
@@ -538,6 +544,16 @@ config ARM64_ERRATUM_1286807
 	  invalidated has been observed by other observers. The
 	  workaround repeats the TLBI+DSB operation.
 
+config ARM64_ERRATUM_1319367
+	bool "Cortex-A57/A72: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
+	default y
+	help
+	  This option adds work arounds for ARM Cortex-A57 erratum 1319537
+	  and A72 erratum 1319367
+
+	  Cortex-A57 and A72 cores could end-up with corrupted TLBs by
+	  speculating an AT instruction during a guest context switch.
+
 	  If unsure, say Y.
 
 config ARM64_ERRATUM_1463225
@@ -558,6 +574,22 @@ config ARM64_ERRATUM_1463225
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_1542419
+	bool "Neoverse-N1: workaround mis-ordering of instruction fetches"
+	default y
+	help
+	  This option adds a workaround for ARM Neoverse-N1 erratum
+	  1542419.
+
+	  Affected Neoverse-N1 cores could execute a stale instruction when
+	  modified by another CPU. The workaround depends on a firmware
+	  counterpart.
+
+	  Workaround the issue by hiding the DIC feature from EL0. This
+	  forces user-space to perform cache maintenance.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
@@ -845,10 +877,26 @@ config ARM64_PA_BITS
 	default 48 if ARM64_PA_BITS_48
 	default 52 if ARM64_PA_BITS_52
 
+choice
+	prompt "Endianness"
+	default CPU_LITTLE_ENDIAN
+	help
+	  Select the endianness of data accesses performed by the CPU. Userspace
+	  applications will need to be compiled and linked for the endianness
+	  that is selected here.
+
 config CPU_BIG_ENDIAN
        bool "Build big-endian kernel"
        help
-         Say Y if you plan on running a kernel in big-endian mode.
+	  Say Y if you plan on running a kernel with a big-endian userspace.
+
+config CPU_LITTLE_ENDIAN
+	bool "Build little-endian kernel"
+	help
+	  Say Y if you plan on running a kernel with a little-endian userspace.
+	  This is usually the case for distributions targeting arm64.
+
+endchoice
 
 config SCHED_MC
 	bool "Multi-core scheduler support"
@@ -1597,6 +1645,7 @@ config CMDLINE
 
 config CMDLINE_FORCE
 	bool "Always use the default kernel command string"
+	depends on CMDLINE != ""
 	help
 	  Always use the default kernel command string, even if the boot
 	  loader passes other arguments to the kernel.
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 2c0238ce0551..1fbe24d4fdb6 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -95,6 +95,11 @@ ifeq ($(CONFIG_ARM64_MODULE_PLTS),y)
 KBUILD_LDS_MODULE	+= $(srctree)/arch/arm64/kernel/module.lds
 endif
 
+ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y)
+  KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
+  CC_FLAGS_FTRACE := -fpatchable-function-entry=2
+endif
+
 # Default value
 head-y		:= arch/arm64/kernel/head.o
 
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 4922c4451e7c..b8eb0453123d 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -86,7 +86,7 @@ config CRYPTO_AES_ARM64_CE_CCM
 config CRYPTO_AES_ARM64_CE_BLK
 	tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions"
 	depends on KERNEL_MODE_NEON
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_AES_ARM64_CE
 	select CRYPTO_AES_ARM64
 	select CRYPTO_SIMD
@@ -94,7 +94,7 @@ config CRYPTO_AES_ARM64_CE_BLK
 config CRYPTO_AES_ARM64_NEON_BLK
 	tristate "AES in ECB/CBC/CTR/XTS modes using NEON instructions"
 	depends on KERNEL_MODE_NEON
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_AES_ARM64
 	select CRYPTO_LIB_AES
 	select CRYPTO_SIMD
@@ -102,8 +102,15 @@ config CRYPTO_AES_ARM64_NEON_BLK
 config CRYPTO_CHACHA20_NEON
 	tristate "ChaCha20, XChaCha20, and XChaCha12 stream ciphers using NEON instructions"
 	depends on KERNEL_MODE_NEON
-	select CRYPTO_BLKCIPHER
-	select CRYPTO_CHACHA20
+	select CRYPTO_SKCIPHER
+	select CRYPTO_LIB_CHACHA_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_CHACHA
+
+config CRYPTO_POLY1305_NEON
+	tristate "Poly1305 hash function using scalar or NEON instructions"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_HASH
+	select CRYPTO_ARCH_HAVE_LIB_POLY1305
 
 config CRYPTO_NHPOLY1305_NEON
 	tristate "NHPoly1305 hash function using NEON instructions (for Adiantum)"
@@ -113,7 +120,7 @@ config CRYPTO_NHPOLY1305_NEON
 config CRYPTO_AES_ARM64_BS
 	tristate "AES in ECB/CBC/CTR/XTS modes using bit-sliced NEON algorithm"
 	depends on KERNEL_MODE_NEON
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_AES_ARM64_NEON_BLK
 	select CRYPTO_AES_ARM64
 	select CRYPTO_LIB_AES
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index 0435f2a0610e..d0901e610df3 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -50,6 +50,10 @@ sha512-arm64-y := sha512-glue.o sha512-core.o
 obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
 chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o
 
+obj-$(CONFIG_CRYPTO_POLY1305_NEON) += poly1305-neon.o
+poly1305-neon-y := poly1305-core.o poly1305-glue.o
+AFLAGS_poly1305-core.o += -Dpoly1305_init=poly1305_init_arm64
+
 obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
 nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
 
@@ -68,11 +72,15 @@ ifdef REGENERATE_ARM64_CRYPTO
 quiet_cmd_perlasm = PERLASM $@
       cmd_perlasm = $(PERL) $(<) void $(@)
 
+$(src)/poly1305-core.S_shipped: $(src)/poly1305-armv8.pl
+	$(call cmd,perlasm)
+
 $(src)/sha256-core.S_shipped: $(src)/sha512-armv8.pl
 	$(call cmd,perlasm)
 
 $(src)/sha512-core.S_shipped: $(src)/sha512-armv8.pl
 	$(call cmd,perlasm)
+
 endif
 
-clean-files += sha256-core.S sha512-core.S
+clean-files += poly1305-core.S sha256-core.S sha512-core.S
diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
index ea873b8904c4..e3e27349a9fe 100644
--- a/arch/arm64/crypto/aes-neonbs-glue.c
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -384,7 +384,7 @@ static int __xts_crypt(struct skcipher_request *req, bool encrypt,
 			goto xts_tail;
 
 		kernel_neon_end();
-		skcipher_walk_done(&walk, nbytes);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	if (err || likely(!tail))
diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c
index 1495d2b18518..b08029d7bde6 100644
--- a/arch/arm64/crypto/chacha-neon-glue.c
+++ b/arch/arm64/crypto/chacha-neon-glue.c
@@ -1,5 +1,5 @@
 /*
- * ARM NEON accelerated ChaCha and XChaCha stream ciphers,
+ * ARM NEON and scalar accelerated ChaCha and XChaCha stream ciphers,
  * including ChaCha20 (RFC7539)
  *
  * Copyright (C) 2016 - 2017 Linaro, Ltd. <ard.biesheuvel@linaro.org>
@@ -20,9 +20,10 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
+#include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 
@@ -36,6 +37,8 @@ asmlinkage void chacha_4block_xor_neon(u32 *state, u8 *dst, const u8 *src,
 				       int nrounds, int bytes);
 asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds);
 
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
 static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
 			  int bytes, int nrounds)
 {
@@ -59,6 +62,37 @@ static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
 	}
 }
 
+void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
+{
+	if (!static_branch_likely(&have_neon) || !crypto_simd_usable()) {
+		hchacha_block_generic(state, stream, nrounds);
+	} else {
+		kernel_neon_begin();
+		hchacha_block_neon(state, stream, nrounds);
+		kernel_neon_end();
+	}
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
+{
+	chacha_init_generic(state, key, iv);
+}
+EXPORT_SYMBOL(chacha_init_arch);
+
+void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
+		       int nrounds)
+{
+	if (!static_branch_likely(&have_neon) || bytes <= CHACHA_BLOCK_SIZE ||
+	    !crypto_simd_usable())
+		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+
+	kernel_neon_begin();
+	chacha_doneon(state, dst, src, bytes, nrounds);
+	kernel_neon_end();
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
 static int chacha_neon_stream_xor(struct skcipher_request *req,
 				  const struct chacha_ctx *ctx, const u8 *iv)
 {
@@ -68,7 +102,7 @@ static int chacha_neon_stream_xor(struct skcipher_request *req,
 
 	err = skcipher_walk_virt(&walk, req, false);
 
-	crypto_chacha_init(state, ctx, iv);
+	chacha_init_generic(state, ctx->key, iv);
 
 	while (walk.nbytes > 0) {
 		unsigned int nbytes = walk.nbytes;
@@ -76,10 +110,17 @@ static int chacha_neon_stream_xor(struct skcipher_request *req,
 		if (nbytes < walk.total)
 			nbytes = rounddown(nbytes, walk.stride);
 
-		kernel_neon_begin();
-		chacha_doneon(state, walk.dst.virt.addr, walk.src.virt.addr,
-			      nbytes, ctx->nrounds);
-		kernel_neon_end();
+		if (!static_branch_likely(&have_neon) ||
+		    !crypto_simd_usable()) {
+			chacha_crypt_generic(state, walk.dst.virt.addr,
+					     walk.src.virt.addr, nbytes,
+					     ctx->nrounds);
+		} else {
+			kernel_neon_begin();
+			chacha_doneon(state, walk.dst.virt.addr,
+				      walk.src.virt.addr, nbytes, ctx->nrounds);
+			kernel_neon_end();
+		}
 		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
@@ -91,9 +132,6 @@ static int chacha_neon(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
-		return crypto_chacha_crypt(req);
-
 	return chacha_neon_stream_xor(req, ctx, req->iv);
 }
 
@@ -105,14 +143,8 @@ static int xchacha_neon(struct skcipher_request *req)
 	u32 state[16];
 	u8 real_iv[16];
 
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
-		return crypto_xchacha_crypt(req);
-
-	crypto_chacha_init(state, ctx, req->iv);
-
-	kernel_neon_begin();
-	hchacha_block_neon(state, subctx.key, ctx->nrounds);
-	kernel_neon_end();
+	chacha_init_generic(state, ctx->key, req->iv);
+	hchacha_block_arch(state, subctx.key, ctx->nrounds);
 	subctx.nrounds = ctx->nrounds;
 
 	memcpy(&real_iv[0], req->iv + 24, 8);
@@ -134,7 +166,7 @@ static struct skcipher_alg algs[] = {
 		.ivsize			= CHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
 		.walksize		= 5 * CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
+		.setkey			= chacha20_setkey,
 		.encrypt		= chacha_neon,
 		.decrypt		= chacha_neon,
 	}, {
@@ -150,7 +182,7 @@ static struct skcipher_alg algs[] = {
 		.ivsize			= XCHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
 		.walksize		= 5 * CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
+		.setkey			= chacha20_setkey,
 		.encrypt		= xchacha_neon,
 		.decrypt		= xchacha_neon,
 	}, {
@@ -166,7 +198,7 @@ static struct skcipher_alg algs[] = {
 		.ivsize			= XCHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
 		.walksize		= 5 * CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha12_setkey,
+		.setkey			= chacha12_setkey,
 		.encrypt		= xchacha_neon,
 		.decrypt		= xchacha_neon,
 	}
@@ -175,14 +207,17 @@ static struct skcipher_alg algs[] = {
 static int __init chacha_simd_mod_init(void)
 {
 	if (!cpu_have_named_feature(ASIMD))
-		return -ENODEV;
+		return 0;
+
+	static_branch_enable(&have_neon);
 
 	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
 }
 
 static void __exit chacha_simd_mod_fini(void)
 {
-	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
+	if (cpu_have_named_feature(ASIMD))
+		crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
 }
 
 module_init(chacha_simd_mod_init);
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index 410e8afcf5a7..a791c4adf8e6 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -13,8 +13,8 @@
 	T1		.req	v2
 	T2		.req	v3
 	MASK		.req	v4
-	XL		.req	v5
-	XM		.req	v6
+	XM		.req	v5
+	XL		.req	v6
 	XH		.req	v7
 	IN1		.req	v7
 
@@ -358,20 +358,37 @@ ENTRY(pmull_ghash_update_p8)
 	__pmull_ghash	p8
 ENDPROC(pmull_ghash_update_p8)
 
-	KS0		.req	v12
-	KS1		.req	v13
-	INP0		.req	v14
-	INP1		.req	v15
-
-	.macro		load_round_keys, rounds, rk
-	cmp		\rounds, #12
-	blo		2222f		/* 128 bits */
-	beq		1111f		/* 192 bits */
-	ld1		{v17.4s-v18.4s}, [\rk], #32
-1111:	ld1		{v19.4s-v20.4s}, [\rk], #32
-2222:	ld1		{v21.4s-v24.4s}, [\rk], #64
-	ld1		{v25.4s-v28.4s}, [\rk], #64
-	ld1		{v29.4s-v31.4s}, [\rk]
+	KS0		.req	v8
+	KS1		.req	v9
+	KS2		.req	v10
+	KS3		.req	v11
+
+	INP0		.req	v21
+	INP1		.req	v22
+	INP2		.req	v23
+	INP3		.req	v24
+
+	K0		.req	v25
+	K1		.req	v26
+	K2		.req	v27
+	K3		.req	v28
+	K4		.req	v12
+	K5		.req	v13
+	K6		.req	v4
+	K7		.req	v5
+	K8		.req	v14
+	K9		.req	v15
+	KK		.req	v29
+	KL		.req	v30
+	KM		.req	v31
+
+	.macro		load_round_keys, rounds, rk, tmp
+	add		\tmp, \rk, #64
+	ld1		{K0.4s-K3.4s}, [\rk]
+	ld1		{K4.4s-K5.4s}, [\tmp]
+	add		\tmp, \rk, \rounds, lsl #4
+	sub		\tmp, \tmp, #32
+	ld1		{KK.4s-KM.4s}, [\tmp]
 	.endm
 
 	.macro		enc_round, state, key
@@ -379,197 +396,367 @@ ENDPROC(pmull_ghash_update_p8)
 	aesmc		\state\().16b, \state\().16b
 	.endm
 
-	.macro		enc_block, state, rounds
-	cmp		\rounds, #12
-	b.lo		2222f		/* 128 bits */
-	b.eq		1111f		/* 192 bits */
-	enc_round	\state, v17
-	enc_round	\state, v18
-1111:	enc_round	\state, v19
-	enc_round	\state, v20
-2222:	.irp		key, v21, v22, v23, v24, v25, v26, v27, v28, v29
+	.macro		enc_qround, s0, s1, s2, s3, key
+	enc_round	\s0, \key
+	enc_round	\s1, \key
+	enc_round	\s2, \key
+	enc_round	\s3, \key
+	.endm
+
+	.macro		enc_block, state, rounds, rk, tmp
+	add		\tmp, \rk, #96
+	ld1		{K6.4s-K7.4s}, [\tmp], #32
+	.irp		key, K0, K1, K2, K3, K4 K5
 	enc_round	\state, \key
 	.endr
-	aese		\state\().16b, v30.16b
-	eor		\state\().16b, \state\().16b, v31.16b
+
+	tbnz		\rounds, #2, .Lnot128_\@
+.Lout256_\@:
+	enc_round	\state, K6
+	enc_round	\state, K7
+
+.Lout192_\@:
+	enc_round	\state, KK
+	aese		\state\().16b, KL.16b
+	eor		\state\().16b, \state\().16b, KM.16b
+
+	.subsection	1
+.Lnot128_\@:
+	ld1		{K8.4s-K9.4s}, [\tmp], #32
+	enc_round	\state, K6
+	enc_round	\state, K7
+	ld1		{K6.4s-K7.4s}, [\tmp]
+	enc_round	\state, K8
+	enc_round	\state, K9
+	tbz		\rounds, #1, .Lout192_\@
+	b		.Lout256_\@
+	.previous
 	.endm
 
+	.align		6
 	.macro		pmull_gcm_do_crypt, enc
-	ld1		{SHASH.2d}, [x4], #16
-	ld1		{HH.2d}, [x4]
-	ld1		{XL.2d}, [x1]
-	ldr		x8, [x5, #8]			// load lower counter
+	stp		x29, x30, [sp, #-32]!
+	mov		x29, sp
+	str		x19, [sp, #24]
+
+	load_round_keys	x7, x6, x8
+
+	ld1		{SHASH.2d}, [x3], #16
+	ld1		{HH.2d-HH4.2d}, [x3]
 
-	movi		MASK.16b, #0xe1
 	trn1		SHASH2.2d, SHASH.2d, HH.2d
 	trn2		T1.2d, SHASH.2d, HH.2d
-CPU_LE(	rev		x8, x8		)
-	shl		MASK.2d, MASK.2d, #57
 	eor		SHASH2.16b, SHASH2.16b, T1.16b
 
-	.if		\enc == 1
-	ldr		x10, [sp]
-	ld1		{KS0.16b-KS1.16b}, [x10]
-	.endif
+	trn1		HH34.2d, HH3.2d, HH4.2d
+	trn2		T1.2d, HH3.2d, HH4.2d
+	eor		HH34.16b, HH34.16b, T1.16b
 
-	cbnz		x6, 4f
+	ld1		{XL.2d}, [x4]
 
-0:	ld1		{INP0.16b-INP1.16b}, [x3], #32
+	cbz		x0, 3f				// tag only?
 
-	rev		x9, x8
-	add		x11, x8, #1
-	add		x8, x8, #2
+	ldr		w8, [x5, #12]			// load lower counter
+CPU_LE(	rev		w8, w8		)
 
-	.if		\enc == 1
-	eor		INP0.16b, INP0.16b, KS0.16b	// encrypt input
-	eor		INP1.16b, INP1.16b, KS1.16b
+0:	mov		w9, #4				// max blocks per round
+	add		x10, x0, #0xf
+	lsr		x10, x10, #4			// remaining blocks
+
+	subs		x0, x0, #64
+	csel		w9, w10, w9, mi
+	add		w8, w8, w9
+
+	bmi		1f
+	ld1		{INP0.16b-INP3.16b}, [x2], #64
+	.subsection	1
+	/*
+	 * Populate the four input registers right to left with up to 63 bytes
+	 * of data, using overlapping loads to avoid branches.
+	 *
+	 *                INP0     INP1     INP2     INP3
+	 *  1 byte     |        |        |        |x       |
+	 * 16 bytes    |        |        |        |xxxxxxxx|
+	 * 17 bytes    |        |        |xxxxxxxx|x       |
+	 * 47 bytes    |        |xxxxxxxx|xxxxxxxx|xxxxxxx |
+	 * etc etc
+	 *
+	 * Note that this code may read up to 15 bytes before the start of
+	 * the input. It is up to the calling code to ensure this is safe if
+	 * this happens in the first iteration of the loop (i.e., when the
+	 * input size is < 16 bytes)
+	 */
+1:	mov		x15, #16
+	ands		x19, x0, #0xf
+	csel		x19, x19, x15, ne
+	adr_l		x17, .Lpermute_table + 16
+
+	sub		x11, x15, x19
+	add		x12, x17, x11
+	sub		x17, x17, x11
+	ld1		{T1.16b}, [x12]
+	sub		x10, x1, x11
+	sub		x11, x2, x11
+
+	cmp		x0, #-16
+	csel		x14, x15, xzr, gt
+	cmp		x0, #-32
+	csel		x15, x15, xzr, gt
+	cmp		x0, #-48
+	csel		x16, x19, xzr, gt
+	csel		x1, x1, x10, gt
+	csel		x2, x2, x11, gt
+
+	ld1		{INP0.16b}, [x2], x14
+	ld1		{INP1.16b}, [x2], x15
+	ld1		{INP2.16b}, [x2], x16
+	ld1		{INP3.16b}, [x2]
+	tbl		INP3.16b, {INP3.16b}, T1.16b
+	b		2f
+	.previous
+
+2:	.if		\enc == 0
+	bl		pmull_gcm_ghash_4x
 	.endif
 
-	ld1		{KS0.8b}, [x5]			// load upper counter
-	rev		x11, x11
-	sub		w0, w0, #2
-	mov		KS1.8b, KS0.8b
-	ins		KS0.d[1], x9			// set lower counter
-	ins		KS1.d[1], x11
+	bl		pmull_gcm_enc_4x
 
-	rev64		T1.16b, INP1.16b
+	tbnz		x0, #63, 6f
+	st1		{INP0.16b-INP3.16b}, [x1], #64
+	.if		\enc == 1
+	bl		pmull_gcm_ghash_4x
+	.endif
+	bne		0b
 
-	cmp		w7, #12
-	b.ge		2f				// AES-192/256?
+3:	ldp		x19, x10, [sp, #24]
+	cbz		x10, 5f				// output tag?
 
-1:	enc_round	KS0, v21
-	ext		IN1.16b, T1.16b, T1.16b, #8
+	ld1		{INP3.16b}, [x10]		// load lengths[]
+	mov		w9, #1
+	bl		pmull_gcm_ghash_4x
 
-	enc_round	KS1, v21
-	pmull2		XH2.1q, SHASH.2d, IN1.2d	// a1 * b1
+	mov		w11, #(0x1 << 24)		// BE '1U'
+	ld1		{KS0.16b}, [x5]
+	mov		KS0.s[3], w11
 
-	enc_round	KS0, v22
-	eor		T1.16b, T1.16b, IN1.16b
+	enc_block	KS0, x7, x6, x12
 
-	enc_round	KS1, v22
-	pmull		XL2.1q, SHASH.1d, IN1.1d	// a0 * b0
+	ext		XL.16b, XL.16b, XL.16b, #8
+	rev64		XL.16b, XL.16b
+	eor		XL.16b, XL.16b, KS0.16b
+	st1		{XL.16b}, [x10]			// store tag
 
-	enc_round	KS0, v23
-	pmull		XM2.1q, SHASH2.1d, T1.1d	// (a1 + a0)(b1 + b0)
+4:	ldp		x29, x30, [sp], #32
+	ret
 
-	enc_round	KS1, v23
-	rev64		T1.16b, INP0.16b
-	ext		T2.16b, XL.16b, XL.16b, #8
+5:
+CPU_LE(	rev		w8, w8		)
+	str		w8, [x5, #12]			// store lower counter
+	st1		{XL.2d}, [x4]
+	b		4b
+
+6:	ld1		{T1.16b-T2.16b}, [x17], #32	// permute vectors
+	sub		x17, x17, x19, lsl #1
+
+	cmp		w9, #1
+	beq		7f
+	.subsection	1
+7:	ld1		{INP2.16b}, [x1]
+	tbx		INP2.16b, {INP3.16b}, T1.16b
+	mov		INP3.16b, INP2.16b
+	b		8f
+	.previous
+
+	st1		{INP0.16b}, [x1], x14
+	st1		{INP1.16b}, [x1], x15
+	st1		{INP2.16b}, [x1], x16
+	tbl		INP3.16b, {INP3.16b}, T1.16b
+	tbx		INP3.16b, {INP2.16b}, T2.16b
+8:	st1		{INP3.16b}, [x1]
 
-	enc_round	KS0, v24
-	ext		IN1.16b, T1.16b, T1.16b, #8
-	eor		T1.16b, T1.16b, T2.16b
+	.if		\enc == 1
+	ld1		{T1.16b}, [x17]
+	tbl		INP3.16b, {INP3.16b}, T1.16b	// clear non-data bits
+	bl		pmull_gcm_ghash_4x
+	.endif
+	b		3b
+	.endm
 
-	enc_round	KS1, v24
-	eor		XL.16b, XL.16b, IN1.16b
+	/*
+	 * void pmull_gcm_encrypt(int blocks, u8 dst[], const u8 src[],
+	 *			  struct ghash_key const *k, u64 dg[], u8 ctr[],
+	 *			  int rounds, u8 tag)
+	 */
+ENTRY(pmull_gcm_encrypt)
+	pmull_gcm_do_crypt	1
+ENDPROC(pmull_gcm_encrypt)
 
-	enc_round	KS0, v25
-	eor		T1.16b, T1.16b, XL.16b
+	/*
+	 * void pmull_gcm_decrypt(int blocks, u8 dst[], const u8 src[],
+	 *			  struct ghash_key const *k, u64 dg[], u8 ctr[],
+	 *			  int rounds, u8 tag)
+	 */
+ENTRY(pmull_gcm_decrypt)
+	pmull_gcm_do_crypt	0
+ENDPROC(pmull_gcm_decrypt)
 
-	enc_round	KS1, v25
-	pmull2		XH.1q, HH.2d, XL.2d		// a1 * b1
+pmull_gcm_ghash_4x:
+	movi		MASK.16b, #0xe1
+	shl		MASK.2d, MASK.2d, #57
 
-	enc_round	KS0, v26
-	pmull		XL.1q, HH.1d, XL.1d		// a0 * b0
+	rev64		T1.16b, INP0.16b
+	rev64		T2.16b, INP1.16b
+	rev64		TT3.16b, INP2.16b
+	rev64		TT4.16b, INP3.16b
 
-	enc_round	KS1, v26
-	pmull2		XM.1q, SHASH2.2d, T1.2d		// (a1 + a0)(b1 + b0)
+	ext		XL.16b, XL.16b, XL.16b, #8
 
-	enc_round	KS0, v27
-	eor		XL.16b, XL.16b, XL2.16b
-	eor		XH.16b, XH.16b, XH2.16b
+	tbz		w9, #2, 0f			// <4 blocks?
+	.subsection	1
+0:	movi		XH2.16b, #0
+	movi		XM2.16b, #0
+	movi		XL2.16b, #0
 
-	enc_round	KS1, v27
-	eor		XM.16b, XM.16b, XM2.16b
-	ext		T1.16b, XL.16b, XH.16b, #8
+	tbz		w9, #0, 1f			// 2 blocks?
+	tbz		w9, #1, 2f			// 1 block?
 
-	enc_round	KS0, v28
-	eor		T2.16b, XL.16b, XH.16b
-	eor		XM.16b, XM.16b, T1.16b
+	eor		T2.16b, T2.16b, XL.16b
+	ext		T1.16b, T2.16b, T2.16b, #8
+	b		.Lgh3
 
-	enc_round	KS1, v28
-	eor		XM.16b, XM.16b, T2.16b
+1:	eor		TT3.16b, TT3.16b, XL.16b
+	ext		T2.16b, TT3.16b, TT3.16b, #8
+	b		.Lgh2
 
-	enc_round	KS0, v29
-	pmull		T2.1q, XL.1d, MASK.1d
+2:	eor		TT4.16b, TT4.16b, XL.16b
+	ext		IN1.16b, TT4.16b, TT4.16b, #8
+	b		.Lgh1
+	.previous
 
-	enc_round	KS1, v29
-	mov		XH.d[0], XM.d[1]
-	mov		XM.d[1], XL.d[0]
+	eor		T1.16b, T1.16b, XL.16b
+	ext		IN1.16b, T1.16b, T1.16b, #8
 
-	aese		KS0.16b, v30.16b
-	eor		XL.16b, XM.16b, T2.16b
+	pmull2		XH2.1q, HH4.2d, IN1.2d		// a1 * b1
+	eor		T1.16b, T1.16b, IN1.16b
+	pmull		XL2.1q, HH4.1d, IN1.1d		// a0 * b0
+	pmull2		XM2.1q, HH34.2d, T1.2d		// (a1 + a0)(b1 + b0)
 
-	aese		KS1.16b, v30.16b
-	ext		T2.16b, XL.16b, XL.16b, #8
+	ext		T1.16b, T2.16b, T2.16b, #8
+.Lgh3:	eor		T2.16b, T2.16b, T1.16b
+	pmull2		XH.1q, HH3.2d, T1.2d		// a1 * b1
+	pmull		XL.1q, HH3.1d, T1.1d		// a0 * b0
+	pmull		XM.1q, HH34.1d, T2.1d		// (a1 + a0)(b1 + b0)
 
-	eor		KS0.16b, KS0.16b, v31.16b
-	pmull		XL.1q, XL.1d, MASK.1d
-	eor		T2.16b, T2.16b, XH.16b
+	eor		XH2.16b, XH2.16b, XH.16b
+	eor		XL2.16b, XL2.16b, XL.16b
+	eor		XM2.16b, XM2.16b, XM.16b
 
-	eor		KS1.16b, KS1.16b, v31.16b
-	eor		XL.16b, XL.16b, T2.16b
+	ext		T2.16b, TT3.16b, TT3.16b, #8
+.Lgh2:	eor		TT3.16b, TT3.16b, T2.16b
+	pmull2		XH.1q, HH.2d, T2.2d		// a1 * b1
+	pmull		XL.1q, HH.1d, T2.1d		// a0 * b0
+	pmull2		XM.1q, SHASH2.2d, TT3.2d	// (a1 + a0)(b1 + b0)
 
-	.if		\enc == 0
-	eor		INP0.16b, INP0.16b, KS0.16b
-	eor		INP1.16b, INP1.16b, KS1.16b
-	.endif
+	eor		XH2.16b, XH2.16b, XH.16b
+	eor		XL2.16b, XL2.16b, XL.16b
+	eor		XM2.16b, XM2.16b, XM.16b
 
-	st1		{INP0.16b-INP1.16b}, [x2], #32
+	ext		IN1.16b, TT4.16b, TT4.16b, #8
+.Lgh1:	eor		TT4.16b, TT4.16b, IN1.16b
+	pmull		XL.1q, SHASH.1d, IN1.1d		// a0 * b0
+	pmull2		XH.1q, SHASH.2d, IN1.2d		// a1 * b1
+	pmull		XM.1q, SHASH2.1d, TT4.1d	// (a1 + a0)(b1 + b0)
 
-	cbnz		w0, 0b
+	eor		XH.16b, XH.16b, XH2.16b
+	eor		XL.16b, XL.16b, XL2.16b
+	eor		XM.16b, XM.16b, XM2.16b
 
-CPU_LE(	rev		x8, x8		)
-	st1		{XL.2d}, [x1]
-	str		x8, [x5, #8]			// store lower counter
+	eor		T2.16b, XL.16b, XH.16b
+	ext		T1.16b, XL.16b, XH.16b, #8
+	eor		XM.16b, XM.16b, T2.16b
 
-	.if		\enc == 1
-	st1		{KS0.16b-KS1.16b}, [x10]
-	.endif
+	__pmull_reduce_p64
+
+	eor		T2.16b, T2.16b, XH.16b
+	eor		XL.16b, XL.16b, T2.16b
 
 	ret
+ENDPROC(pmull_gcm_ghash_4x)
+
+pmull_gcm_enc_4x:
+	ld1		{KS0.16b}, [x5]			// load upper counter
+	sub		w10, w8, #4
+	sub		w11, w8, #3
+	sub		w12, w8, #2
+	sub		w13, w8, #1
+	rev		w10, w10
+	rev		w11, w11
+	rev		w12, w12
+	rev		w13, w13
+	mov		KS1.16b, KS0.16b
+	mov		KS2.16b, KS0.16b
+	mov		KS3.16b, KS0.16b
+	ins		KS0.s[3], w10			// set lower counter
+	ins		KS1.s[3], w11
+	ins		KS2.s[3], w12
+	ins		KS3.s[3], w13
+
+	add		x10, x6, #96			// round key pointer
+	ld1		{K6.4s-K7.4s}, [x10], #32
+	.irp		key, K0, K1, K2, K3, K4, K5
+	enc_qround	KS0, KS1, KS2, KS3, \key
+	.endr
 
-2:	b.eq		3f				// AES-192?
-	enc_round	KS0, v17
-	enc_round	KS1, v17
-	enc_round	KS0, v18
-	enc_round	KS1, v18
-3:	enc_round	KS0, v19
-	enc_round	KS1, v19
-	enc_round	KS0, v20
-	enc_round	KS1, v20
-	b		1b
+	tbnz		x7, #2, .Lnot128
+	.subsection	1
+.Lnot128:
+	ld1		{K8.4s-K9.4s}, [x10], #32
+	.irp		key, K6, K7
+	enc_qround	KS0, KS1, KS2, KS3, \key
+	.endr
+	ld1		{K6.4s-K7.4s}, [x10]
+	.irp		key, K8, K9
+	enc_qround	KS0, KS1, KS2, KS3, \key
+	.endr
+	tbz		x7, #1, .Lout192
+	b		.Lout256
+	.previous
 
-4:	load_round_keys	w7, x6
-	b		0b
-	.endm
+.Lout256:
+	.irp		key, K6, K7
+	enc_qround	KS0, KS1, KS2, KS3, \key
+	.endr
 
-	/*
-	 * void pmull_gcm_encrypt(int blocks, u64 dg[], u8 dst[], const u8 src[],
-	 *			  struct ghash_key const *k, u8 ctr[],
-	 *			  int rounds, u8 ks[])
-	 */
-ENTRY(pmull_gcm_encrypt)
-	pmull_gcm_do_crypt	1
-ENDPROC(pmull_gcm_encrypt)
+.Lout192:
+	enc_qround	KS0, KS1, KS2, KS3, KK
 
-	/*
-	 * void pmull_gcm_decrypt(int blocks, u64 dg[], u8 dst[], const u8 src[],
-	 *			  struct ghash_key const *k, u8 ctr[],
-	 *			  int rounds)
-	 */
-ENTRY(pmull_gcm_decrypt)
-	pmull_gcm_do_crypt	0
-ENDPROC(pmull_gcm_decrypt)
+	aese		KS0.16b, KL.16b
+	aese		KS1.16b, KL.16b
+	aese		KS2.16b, KL.16b
+	aese		KS3.16b, KL.16b
+
+	eor		KS0.16b, KS0.16b, KM.16b
+	eor		KS1.16b, KS1.16b, KM.16b
+	eor		KS2.16b, KS2.16b, KM.16b
+	eor		KS3.16b, KS3.16b, KM.16b
+
+	eor		INP0.16b, INP0.16b, KS0.16b
+	eor		INP1.16b, INP1.16b, KS1.16b
+	eor		INP2.16b, INP2.16b, KS2.16b
+	eor		INP3.16b, INP3.16b, KS3.16b
 
-	/*
-	 * void pmull_gcm_encrypt_block(u8 dst[], u8 src[], u8 rk[], int rounds)
-	 */
-ENTRY(pmull_gcm_encrypt_block)
-	cbz		x2, 0f
-	load_round_keys	w3, x2
-0:	ld1		{v0.16b}, [x1]
-	enc_block	v0, w3
-	st1		{v0.16b}, [x0]
 	ret
-ENDPROC(pmull_gcm_encrypt_block)
+ENDPROC(pmull_gcm_enc_4x)
+
+	.section	".rodata", "a"
+	.align		6
+.Lpermute_table:
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		 0x0,  0x1,  0x2,  0x3,  0x4,  0x5,  0x6,  0x7
+	.byte		 0x8,  0x9,  0xa,  0xb,  0xc,  0xd,  0xe,  0xf
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		 0x0,  0x1,  0x2,  0x3,  0x4,  0x5,  0x6,  0x7
+	.byte		 0x8,  0x9,  0xa,  0xb,  0xc,  0xd,  0xe,  0xf
+	.previous
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 70b1469783f9..522cf004ce65 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -58,17 +58,15 @@ asmlinkage void pmull_ghash_update_p8(int blocks, u64 dg[], const char *src,
 				      struct ghash_key const *k,
 				      const char *head);
 
-asmlinkage void pmull_gcm_encrypt(int blocks, u64 dg[], u8 dst[],
-				  const u8 src[], struct ghash_key const *k,
+asmlinkage void pmull_gcm_encrypt(int bytes, u8 dst[], const u8 src[],
+				  struct ghash_key const *k, u64 dg[],
 				  u8 ctr[], u32 const rk[], int rounds,
-				  u8 ks[]);
+				  u8 tag[]);
 
-asmlinkage void pmull_gcm_decrypt(int blocks, u64 dg[], u8 dst[],
-				  const u8 src[], struct ghash_key const *k,
-				  u8 ctr[], u32 const rk[], int rounds);
-
-asmlinkage void pmull_gcm_encrypt_block(u8 dst[], u8 const src[],
-					u32 const rk[], int rounds);
+asmlinkage void pmull_gcm_decrypt(int bytes, u8 dst[], const u8 src[],
+				  struct ghash_key const *k, u64 dg[],
+				  u8 ctr[], u32 const rk[], int rounds,
+				  u8 tag[]);
 
 static int ghash_init(struct shash_desc *desc)
 {
@@ -85,7 +83,7 @@ static void ghash_do_update(int blocks, u64 dg[], const char *src,
 						struct ghash_key const *k,
 						const char *head))
 {
-	if (likely(crypto_simd_usable())) {
+	if (likely(crypto_simd_usable() && simd_update)) {
 		kernel_neon_begin();
 		simd_update(blocks, dg, src, key, head);
 		kernel_neon_end();
@@ -398,136 +396,112 @@ static void gcm_calculate_auth_mac(struct aead_request *req, u64 dg[])
 	}
 }
 
-static void gcm_final(struct aead_request *req, struct gcm_aes_ctx *ctx,
-		      u64 dg[], u8 tag[], int cryptlen)
-{
-	u8 mac[AES_BLOCK_SIZE];
-	u128 lengths;
-
-	lengths.a = cpu_to_be64(req->assoclen * 8);
-	lengths.b = cpu_to_be64(cryptlen * 8);
-
-	ghash_do_update(1, dg, (void *)&lengths, &ctx->ghash_key, NULL,
-			pmull_ghash_update_p64);
-
-	put_unaligned_be64(dg[1], mac);
-	put_unaligned_be64(dg[0], mac + 8);
-
-	crypto_xor(tag, mac, AES_BLOCK_SIZE);
-}
-
 static int gcm_encrypt(struct aead_request *req)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct gcm_aes_ctx *ctx = crypto_aead_ctx(aead);
+	int nrounds = num_rounds(&ctx->aes_key);
 	struct skcipher_walk walk;
+	u8 buf[AES_BLOCK_SIZE];
 	u8 iv[AES_BLOCK_SIZE];
-	u8 ks[2 * AES_BLOCK_SIZE];
-	u8 tag[AES_BLOCK_SIZE];
 	u64 dg[2] = {};
-	int nrounds = num_rounds(&ctx->aes_key);
+	u128 lengths;
+	u8 *tag;
 	int err;
 
+	lengths.a = cpu_to_be64(req->assoclen * 8);
+	lengths.b = cpu_to_be64(req->cryptlen * 8);
+
 	if (req->assoclen)
 		gcm_calculate_auth_mac(req, dg);
 
 	memcpy(iv, req->iv, GCM_IV_SIZE);
-	put_unaligned_be32(1, iv + GCM_IV_SIZE);
+	put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
 	err = skcipher_walk_aead_encrypt(&walk, req, false);
 
-	if (likely(crypto_simd_usable() && walk.total >= 2 * AES_BLOCK_SIZE)) {
-		u32 const *rk = NULL;
-
-		kernel_neon_begin();
-		pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc, nrounds);
-		put_unaligned_be32(2, iv + GCM_IV_SIZE);
-		pmull_gcm_encrypt_block(ks, iv, NULL, nrounds);
-		put_unaligned_be32(3, iv + GCM_IV_SIZE);
-		pmull_gcm_encrypt_block(ks + AES_BLOCK_SIZE, iv, NULL, nrounds);
-		put_unaligned_be32(4, iv + GCM_IV_SIZE);
-
+	if (likely(crypto_simd_usable())) {
 		do {
-			int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
+			const u8 *src = walk.src.virt.addr;
+			u8 *dst = walk.dst.virt.addr;
+			int nbytes = walk.nbytes;
+
+			tag = (u8 *)&lengths;
 
-			if (rk)
-				kernel_neon_begin();
+			if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE)) {
+				src = dst = memcpy(buf + sizeof(buf) - nbytes,
+						   src, nbytes);
+			} else if (nbytes < walk.total) {
+				nbytes &= ~(AES_BLOCK_SIZE - 1);
+				tag = NULL;
+			}
 
-			pmull_gcm_encrypt(blocks, dg, walk.dst.virt.addr,
-					  walk.src.virt.addr, &ctx->ghash_key,
-					  iv, rk, nrounds, ks);
+			kernel_neon_begin();
+			pmull_gcm_encrypt(nbytes, dst, src, &ctx->ghash_key, dg,
+					  iv, ctx->aes_key.key_enc, nrounds,
+					  tag);
 			kernel_neon_end();
 
-			err = skcipher_walk_done(&walk,
-					walk.nbytes % (2 * AES_BLOCK_SIZE));
+			if (unlikely(!nbytes))
+				break;
 
-			rk = ctx->aes_key.key_enc;
-		} while (walk.nbytes >= 2 * AES_BLOCK_SIZE);
-	} else {
-		aes_encrypt(&ctx->aes_key, tag, iv);
-		put_unaligned_be32(2, iv + GCM_IV_SIZE);
+			if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE))
+				memcpy(walk.dst.virt.addr,
+				       buf + sizeof(buf) - nbytes, nbytes);
 
-		while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) {
-			const int blocks =
-				walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
+			err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+		} while (walk.nbytes);
+	} else {
+		while (walk.nbytes >= AES_BLOCK_SIZE) {
+			int blocks = walk.nbytes / AES_BLOCK_SIZE;
+			const u8 *src = walk.src.virt.addr;
 			u8 *dst = walk.dst.virt.addr;
-			u8 *src = walk.src.virt.addr;
 			int remaining = blocks;
 
 			do {
-				aes_encrypt(&ctx->aes_key, ks, iv);
-				crypto_xor_cpy(dst, src, ks, AES_BLOCK_SIZE);
+				aes_encrypt(&ctx->aes_key, buf, iv);
+				crypto_xor_cpy(dst, src, buf, AES_BLOCK_SIZE);
 				crypto_inc(iv, AES_BLOCK_SIZE);
 
 				dst += AES_BLOCK_SIZE;
 				src += AES_BLOCK_SIZE;
 			} while (--remaining > 0);
 
-			ghash_do_update(blocks, dg,
-					walk.dst.virt.addr, &ctx->ghash_key,
-					NULL, pmull_ghash_update_p64);
+			ghash_do_update(blocks, dg, walk.dst.virt.addr,
+					&ctx->ghash_key, NULL, NULL);
 
 			err = skcipher_walk_done(&walk,
-						 walk.nbytes % (2 * AES_BLOCK_SIZE));
-		}
-		if (walk.nbytes) {
-			aes_encrypt(&ctx->aes_key, ks, iv);
-			if (walk.nbytes > AES_BLOCK_SIZE) {
-				crypto_inc(iv, AES_BLOCK_SIZE);
-				aes_encrypt(&ctx->aes_key, ks + AES_BLOCK_SIZE, iv);
-			}
+						 walk.nbytes % AES_BLOCK_SIZE);
 		}
-	}
 
-	/* handle the tail */
-	if (walk.nbytes) {
-		u8 buf[GHASH_BLOCK_SIZE];
-		unsigned int nbytes = walk.nbytes;
-		u8 *dst = walk.dst.virt.addr;
-		u8 *head = NULL;
+		/* handle the tail */
+		if (walk.nbytes) {
+			aes_encrypt(&ctx->aes_key, buf, iv);
 
-		crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, ks,
-			       walk.nbytes);
+			crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr,
+				       buf, walk.nbytes);
 
-		if (walk.nbytes > GHASH_BLOCK_SIZE) {
-			head = dst;
-			dst += GHASH_BLOCK_SIZE;
-			nbytes %= GHASH_BLOCK_SIZE;
+			memcpy(buf, walk.dst.virt.addr, walk.nbytes);
+			memset(buf + walk.nbytes, 0, sizeof(buf) - walk.nbytes);
 		}
 
-		memcpy(buf, dst, nbytes);
-		memset(buf + nbytes, 0, GHASH_BLOCK_SIZE - nbytes);
-		ghash_do_update(!!nbytes, dg, buf, &ctx->ghash_key, head,
-				pmull_ghash_update_p64);
+		tag = (u8 *)&lengths;
+		ghash_do_update(1, dg, tag, &ctx->ghash_key,
+				walk.nbytes ? buf : NULL, NULL);
 
-		err = skcipher_walk_done(&walk, 0);
+		if (walk.nbytes)
+			err = skcipher_walk_done(&walk, 0);
+
+		put_unaligned_be64(dg[1], tag);
+		put_unaligned_be64(dg[0], tag + 8);
+		put_unaligned_be32(1, iv + GCM_IV_SIZE);
+		aes_encrypt(&ctx->aes_key, iv, iv);
+		crypto_xor(tag, iv, AES_BLOCK_SIZE);
 	}
 
 	if (err)
 		return err;
 
-	gcm_final(req, ctx, dg, tag, req->cryptlen);
-
 	/* copy authtag to end of dst */
 	scatterwalk_map_and_copy(tag, req->dst, req->assoclen + req->cryptlen,
 				 crypto_aead_authsize(aead), 1);
@@ -540,75 +514,65 @@ static int gcm_decrypt(struct aead_request *req)
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct gcm_aes_ctx *ctx = crypto_aead_ctx(aead);
 	unsigned int authsize = crypto_aead_authsize(aead);
+	int nrounds = num_rounds(&ctx->aes_key);
 	struct skcipher_walk walk;
-	u8 iv[2 * AES_BLOCK_SIZE];
-	u8 tag[AES_BLOCK_SIZE];
-	u8 buf[2 * GHASH_BLOCK_SIZE];
+	u8 buf[AES_BLOCK_SIZE];
+	u8 iv[AES_BLOCK_SIZE];
 	u64 dg[2] = {};
-	int nrounds = num_rounds(&ctx->aes_key);
+	u128 lengths;
+	u8 *tag;
 	int err;
 
+	lengths.a = cpu_to_be64(req->assoclen * 8);
+	lengths.b = cpu_to_be64((req->cryptlen - authsize) * 8);
+
 	if (req->assoclen)
 		gcm_calculate_auth_mac(req, dg);
 
 	memcpy(iv, req->iv, GCM_IV_SIZE);
-	put_unaligned_be32(1, iv + GCM_IV_SIZE);
+	put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
 	err = skcipher_walk_aead_decrypt(&walk, req, false);
 
-	if (likely(crypto_simd_usable() && walk.total >= 2 * AES_BLOCK_SIZE)) {
-		u32 const *rk = NULL;
-
-		kernel_neon_begin();
-		pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc, nrounds);
-		put_unaligned_be32(2, iv + GCM_IV_SIZE);
-
+	if (likely(crypto_simd_usable())) {
 		do {
-			int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
-			int rem = walk.total - blocks * AES_BLOCK_SIZE;
-
-			if (rk)
-				kernel_neon_begin();
-
-			pmull_gcm_decrypt(blocks, dg, walk.dst.virt.addr,
-					  walk.src.virt.addr, &ctx->ghash_key,
-					  iv, rk, nrounds);
-
-			/* check if this is the final iteration of the loop */
-			if (rem < (2 * AES_BLOCK_SIZE)) {
-				u8 *iv2 = iv + AES_BLOCK_SIZE;
-
-				if (rem > AES_BLOCK_SIZE) {
-					memcpy(iv2, iv, AES_BLOCK_SIZE);
-					crypto_inc(iv2, AES_BLOCK_SIZE);
-				}
+			const u8 *src = walk.src.virt.addr;
+			u8 *dst = walk.dst.virt.addr;
+			int nbytes = walk.nbytes;
 
-				pmull_gcm_encrypt_block(iv, iv, NULL, nrounds);
+			tag = (u8 *)&lengths;
 
-				if (rem > AES_BLOCK_SIZE)
-					pmull_gcm_encrypt_block(iv2, iv2, NULL,
-								nrounds);
+			if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE)) {
+				src = dst = memcpy(buf + sizeof(buf) - nbytes,
+						   src, nbytes);
+			} else if (nbytes < walk.total) {
+				nbytes &= ~(AES_BLOCK_SIZE - 1);
+				tag = NULL;
 			}
 
+			kernel_neon_begin();
+			pmull_gcm_decrypt(nbytes, dst, src, &ctx->ghash_key, dg,
+					  iv, ctx->aes_key.key_enc, nrounds,
+					  tag);
 			kernel_neon_end();
 
-			err = skcipher_walk_done(&walk,
-					walk.nbytes % (2 * AES_BLOCK_SIZE));
+			if (unlikely(!nbytes))
+				break;
 
-			rk = ctx->aes_key.key_enc;
-		} while (walk.nbytes >= 2 * AES_BLOCK_SIZE);
-	} else {
-		aes_encrypt(&ctx->aes_key, tag, iv);
-		put_unaligned_be32(2, iv + GCM_IV_SIZE);
+			if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE))
+				memcpy(walk.dst.virt.addr,
+				       buf + sizeof(buf) - nbytes, nbytes);
 
-		while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) {
-			int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
+			err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+		} while (walk.nbytes);
+	} else {
+		while (walk.nbytes >= AES_BLOCK_SIZE) {
+			int blocks = walk.nbytes / AES_BLOCK_SIZE;
+			const u8 *src = walk.src.virt.addr;
 			u8 *dst = walk.dst.virt.addr;
-			u8 *src = walk.src.virt.addr;
 
 			ghash_do_update(blocks, dg, walk.src.virt.addr,
-					&ctx->ghash_key, NULL,
-					pmull_ghash_update_p64);
+					&ctx->ghash_key, NULL, NULL);
 
 			do {
 				aes_encrypt(&ctx->aes_key, buf, iv);
@@ -620,49 +584,38 @@ static int gcm_decrypt(struct aead_request *req)
 			} while (--blocks > 0);
 
 			err = skcipher_walk_done(&walk,
-						 walk.nbytes % (2 * AES_BLOCK_SIZE));
+						 walk.nbytes % AES_BLOCK_SIZE);
 		}
-		if (walk.nbytes) {
-			if (walk.nbytes > AES_BLOCK_SIZE) {
-				u8 *iv2 = iv + AES_BLOCK_SIZE;
-
-				memcpy(iv2, iv, AES_BLOCK_SIZE);
-				crypto_inc(iv2, AES_BLOCK_SIZE);
 
-				aes_encrypt(&ctx->aes_key, iv2, iv2);
-			}
-			aes_encrypt(&ctx->aes_key, iv, iv);
+		/* handle the tail */
+		if (walk.nbytes) {
+			memcpy(buf, walk.src.virt.addr, walk.nbytes);
+			memset(buf + walk.nbytes, 0, sizeof(buf) - walk.nbytes);
 		}
-	}
 
-	/* handle the tail */
-	if (walk.nbytes) {
-		const u8 *src = walk.src.virt.addr;
-		const u8 *head = NULL;
-		unsigned int nbytes = walk.nbytes;
+		tag = (u8 *)&lengths;
+		ghash_do_update(1, dg, tag, &ctx->ghash_key,
+				walk.nbytes ? buf : NULL, NULL);
 
-		if (walk.nbytes > GHASH_BLOCK_SIZE) {
-			head = src;
-			src += GHASH_BLOCK_SIZE;
-			nbytes %= GHASH_BLOCK_SIZE;
-		}
+		if (walk.nbytes) {
+			aes_encrypt(&ctx->aes_key, buf, iv);
 
-		memcpy(buf, src, nbytes);
-		memset(buf + nbytes, 0, GHASH_BLOCK_SIZE - nbytes);
-		ghash_do_update(!!nbytes, dg, buf, &ctx->ghash_key, head,
-				pmull_ghash_update_p64);
+			crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr,
+				       buf, walk.nbytes);
 
-		crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, iv,
-			       walk.nbytes);
+			err = skcipher_walk_done(&walk, 0);
+		}
 
-		err = skcipher_walk_done(&walk, 0);
+		put_unaligned_be64(dg[1], tag);
+		put_unaligned_be64(dg[0], tag + 8);
+		put_unaligned_be32(1, iv + GCM_IV_SIZE);
+		aes_encrypt(&ctx->aes_key, iv, iv);
+		crypto_xor(tag, iv, AES_BLOCK_SIZE);
 	}
 
 	if (err)
 		return err;
 
-	gcm_final(req, ctx, dg, tag, req->cryptlen - authsize);
-
 	/* compare calculated auth tag with the stored one */
 	scatterwalk_map_and_copy(buf, req->src,
 				 req->assoclen + req->cryptlen - authsize,
@@ -675,7 +628,7 @@ static int gcm_decrypt(struct aead_request *req)
 
 static struct aead_alg gcm_aes_alg = {
 	.ivsize			= GCM_IV_SIZE,
-	.chunksize		= 2 * AES_BLOCK_SIZE,
+	.chunksize		= AES_BLOCK_SIZE,
 	.maxauthsize		= AES_BLOCK_SIZE,
 	.setkey			= gcm_setkey,
 	.setauthsize		= gcm_setauthsize,
diff --git a/arch/arm64/crypto/poly1305-armv8.pl b/arch/arm64/crypto/poly1305-armv8.pl
new file mode 100644
index 000000000000..6e5576d19af8
--- /dev/null
+++ b/arch/arm64/crypto/poly1305-armv8.pl
@@ -0,0 +1,913 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-1.0+ OR BSD-3-Clause
+#
+# ====================================================================
+# Written by Andy Polyakov, @dot-asm, initially for the OpenSSL
+# project.
+# ====================================================================
+#
+# This module implements Poly1305 hash for ARMv8.
+#
+# June 2015
+#
+# Numbers are cycles per processed byte with poly1305_blocks alone.
+#
+#		IALU/gcc-4.9	NEON
+#
+# Apple A7	1.86/+5%	0.72
+# Cortex-A53	2.69/+58%	1.47
+# Cortex-A57	2.70/+7%	1.14
+# Denver	1.64/+50%	1.18(*)
+# X-Gene	2.13/+68%	2.27
+# Mongoose	1.77/+75%	1.12
+# Kryo		2.70/+55%	1.13
+# ThunderX2	1.17/+95%	1.36
+#
+# (*)	estimate based on resources availability is less than 1.0,
+#	i.e. measured result is worse than expected, presumably binary
+#	translator is not almighty;
+
+$flavour=shift;
+$output=shift;
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
+
+my ($ctx,$inp,$len,$padbit) = map("x$_",(0..3));
+my ($mac,$nonce)=($inp,$len);
+
+my ($h0,$h1,$h2,$r0,$r1,$s1,$t0,$t1,$d0,$d1,$d2) = map("x$_",(4..14));
+
+$code.=<<___;
+#ifndef __KERNEL__
+# include "arm_arch.h"
+.extern	OPENSSL_armcap_P
+#endif
+
+.text
+
+// forward "declarations" are required for Apple
+.globl	poly1305_blocks
+.globl	poly1305_emit
+
+.globl	poly1305_init
+.type	poly1305_init,%function
+.align	5
+poly1305_init:
+	cmp	$inp,xzr
+	stp	xzr,xzr,[$ctx]		// zero hash value
+	stp	xzr,xzr,[$ctx,#16]	// [along with is_base2_26]
+
+	csel	x0,xzr,x0,eq
+	b.eq	.Lno_key
+
+#ifndef	__KERNEL__
+	adrp	x17,OPENSSL_armcap_P
+	ldr	w17,[x17,#:lo12:OPENSSL_armcap_P]
+#endif
+
+	ldp	$r0,$r1,[$inp]		// load key
+	mov	$s1,#0xfffffffc0fffffff
+	movk	$s1,#0x0fff,lsl#48
+#ifdef	__AARCH64EB__
+	rev	$r0,$r0			// flip bytes
+	rev	$r1,$r1
+#endif
+	and	$r0,$r0,$s1		// &=0ffffffc0fffffff
+	and	$s1,$s1,#-4
+	and	$r1,$r1,$s1		// &=0ffffffc0ffffffc
+	mov	w#$s1,#-1
+	stp	$r0,$r1,[$ctx,#32]	// save key value
+	str	w#$s1,[$ctx,#48]	// impossible key power value
+
+#ifndef	__KERNEL__
+	tst	w17,#ARMV7_NEON
+
+	adr	$d0,.Lpoly1305_blocks
+	adr	$r0,.Lpoly1305_blocks_neon
+	adr	$d1,.Lpoly1305_emit
+
+	csel	$d0,$d0,$r0,eq
+
+# ifdef	__ILP32__
+	stp	w#$d0,w#$d1,[$len]
+# else
+	stp	$d0,$d1,[$len]
+# endif
+#endif
+	mov	x0,#1
+.Lno_key:
+	ret
+.size	poly1305_init,.-poly1305_init
+
+.type	poly1305_blocks,%function
+.align	5
+poly1305_blocks:
+.Lpoly1305_blocks:
+	ands	$len,$len,#-16
+	b.eq	.Lno_data
+
+	ldp	$h0,$h1,[$ctx]		// load hash value
+	ldp	$h2,x17,[$ctx,#16]	// [along with is_base2_26]
+	ldp	$r0,$r1,[$ctx,#32]	// load key value
+
+#ifdef	__AARCH64EB__
+	lsr	$d0,$h0,#32
+	mov	w#$d1,w#$h0
+	lsr	$d2,$h1,#32
+	mov	w15,w#$h1
+	lsr	x16,$h2,#32
+#else
+	mov	w#$d0,w#$h0
+	lsr	$d1,$h0,#32
+	mov	w#$d2,w#$h1
+	lsr	x15,$h1,#32
+	mov	w16,w#$h2
+#endif
+
+	add	$d0,$d0,$d1,lsl#26	// base 2^26 -> base 2^64
+	lsr	$d1,$d2,#12
+	adds	$d0,$d0,$d2,lsl#52
+	add	$d1,$d1,x15,lsl#14
+	adc	$d1,$d1,xzr
+	lsr	$d2,x16,#24
+	adds	$d1,$d1,x16,lsl#40
+	adc	$d2,$d2,xzr
+
+	cmp	x17,#0			// is_base2_26?
+	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)
+	csel	$h0,$h0,$d0,eq		// choose between radixes
+	csel	$h1,$h1,$d1,eq
+	csel	$h2,$h2,$d2,eq
+
+.Loop:
+	ldp	$t0,$t1,[$inp],#16	// load input
+	sub	$len,$len,#16
+#ifdef	__AARCH64EB__
+	rev	$t0,$t0
+	rev	$t1,$t1
+#endif
+	adds	$h0,$h0,$t0		// accumulate input
+	adcs	$h1,$h1,$t1
+
+	mul	$d0,$h0,$r0		// h0*r0
+	adc	$h2,$h2,$padbit
+	umulh	$d1,$h0,$r0
+
+	mul	$t0,$h1,$s1		// h1*5*r1
+	umulh	$t1,$h1,$s1
+
+	adds	$d0,$d0,$t0
+	mul	$t0,$h0,$r1		// h0*r1
+	adc	$d1,$d1,$t1
+	umulh	$d2,$h0,$r1
+
+	adds	$d1,$d1,$t0
+	mul	$t0,$h1,$r0		// h1*r0
+	adc	$d2,$d2,xzr
+	umulh	$t1,$h1,$r0
+
+	adds	$d1,$d1,$t0
+	mul	$t0,$h2,$s1		// h2*5*r1
+	adc	$d2,$d2,$t1
+	mul	$t1,$h2,$r0		// h2*r0
+
+	adds	$d1,$d1,$t0
+	adc	$d2,$d2,$t1
+
+	and	$t0,$d2,#-4		// final reduction
+	and	$h2,$d2,#3
+	add	$t0,$t0,$d2,lsr#2
+	adds	$h0,$d0,$t0
+	adcs	$h1,$d1,xzr
+	adc	$h2,$h2,xzr
+
+	cbnz	$len,.Loop
+
+	stp	$h0,$h1,[$ctx]		// store hash value
+	stp	$h2,xzr,[$ctx,#16]	// [and clear is_base2_26]
+
+.Lno_data:
+	ret
+.size	poly1305_blocks,.-poly1305_blocks
+
+.type	poly1305_emit,%function
+.align	5
+poly1305_emit:
+.Lpoly1305_emit:
+	ldp	$h0,$h1,[$ctx]		// load hash base 2^64
+	ldp	$h2,$r0,[$ctx,#16]	// [along with is_base2_26]
+	ldp	$t0,$t1,[$nonce]	// load nonce
+
+#ifdef	__AARCH64EB__
+	lsr	$d0,$h0,#32
+	mov	w#$d1,w#$h0
+	lsr	$d2,$h1,#32
+	mov	w15,w#$h1
+	lsr	x16,$h2,#32
+#else
+	mov	w#$d0,w#$h0
+	lsr	$d1,$h0,#32
+	mov	w#$d2,w#$h1
+	lsr	x15,$h1,#32
+	mov	w16,w#$h2
+#endif
+
+	add	$d0,$d0,$d1,lsl#26	// base 2^26 -> base 2^64
+	lsr	$d1,$d2,#12
+	adds	$d0,$d0,$d2,lsl#52
+	add	$d1,$d1,x15,lsl#14
+	adc	$d1,$d1,xzr
+	lsr	$d2,x16,#24
+	adds	$d1,$d1,x16,lsl#40
+	adc	$d2,$d2,xzr
+
+	cmp	$r0,#0			// is_base2_26?
+	csel	$h0,$h0,$d0,eq		// choose between radixes
+	csel	$h1,$h1,$d1,eq
+	csel	$h2,$h2,$d2,eq
+
+	adds	$d0,$h0,#5		// compare to modulus
+	adcs	$d1,$h1,xzr
+	adc	$d2,$h2,xzr
+
+	tst	$d2,#-4			// see if it's carried/borrowed
+
+	csel	$h0,$h0,$d0,eq
+	csel	$h1,$h1,$d1,eq
+
+#ifdef	__AARCH64EB__
+	ror	$t0,$t0,#32		// flip nonce words
+	ror	$t1,$t1,#32
+#endif
+	adds	$h0,$h0,$t0		// accumulate nonce
+	adc	$h1,$h1,$t1
+#ifdef	__AARCH64EB__
+	rev	$h0,$h0			// flip output bytes
+	rev	$h1,$h1
+#endif
+	stp	$h0,$h1,[$mac]		// write result
+
+	ret
+.size	poly1305_emit,.-poly1305_emit
+___
+my ($R0,$R1,$S1,$R2,$S2,$R3,$S3,$R4,$S4) = map("v$_.4s",(0..8));
+my ($IN01_0,$IN01_1,$IN01_2,$IN01_3,$IN01_4) = map("v$_.2s",(9..13));
+my ($IN23_0,$IN23_1,$IN23_2,$IN23_3,$IN23_4) = map("v$_.2s",(14..18));
+my ($ACC0,$ACC1,$ACC2,$ACC3,$ACC4) = map("v$_.2d",(19..23));
+my ($H0,$H1,$H2,$H3,$H4) = map("v$_.2s",(24..28));
+my ($T0,$T1,$MASK) = map("v$_",(29..31));
+
+my ($in2,$zeros)=("x16","x17");
+my $is_base2_26 = $zeros;		# borrow
+
+$code.=<<___;
+.type	poly1305_mult,%function
+.align	5
+poly1305_mult:
+	mul	$d0,$h0,$r0		// h0*r0
+	umulh	$d1,$h0,$r0
+
+	mul	$t0,$h1,$s1		// h1*5*r1
+	umulh	$t1,$h1,$s1
+
+	adds	$d0,$d0,$t0
+	mul	$t0,$h0,$r1		// h0*r1
+	adc	$d1,$d1,$t1
+	umulh	$d2,$h0,$r1
+
+	adds	$d1,$d1,$t0
+	mul	$t0,$h1,$r0		// h1*r0
+	adc	$d2,$d2,xzr
+	umulh	$t1,$h1,$r0
+
+	adds	$d1,$d1,$t0
+	mul	$t0,$h2,$s1		// h2*5*r1
+	adc	$d2,$d2,$t1
+	mul	$t1,$h2,$r0		// h2*r0
+
+	adds	$d1,$d1,$t0
+	adc	$d2,$d2,$t1
+
+	and	$t0,$d2,#-4		// final reduction
+	and	$h2,$d2,#3
+	add	$t0,$t0,$d2,lsr#2
+	adds	$h0,$d0,$t0
+	adcs	$h1,$d1,xzr
+	adc	$h2,$h2,xzr
+
+	ret
+.size	poly1305_mult,.-poly1305_mult
+
+.type	poly1305_splat,%function
+.align	4
+poly1305_splat:
+	and	x12,$h0,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x13,$h0,#26,#26
+	extr	x14,$h1,$h0,#52
+	and	x14,x14,#0x03ffffff
+	ubfx	x15,$h1,#14,#26
+	extr	x16,$h2,$h1,#40
+
+	str	w12,[$ctx,#16*0]	// r0
+	add	w12,w13,w13,lsl#2	// r1*5
+	str	w13,[$ctx,#16*1]	// r1
+	add	w13,w14,w14,lsl#2	// r2*5
+	str	w12,[$ctx,#16*2]	// s1
+	str	w14,[$ctx,#16*3]	// r2
+	add	w14,w15,w15,lsl#2	// r3*5
+	str	w13,[$ctx,#16*4]	// s2
+	str	w15,[$ctx,#16*5]	// r3
+	add	w15,w16,w16,lsl#2	// r4*5
+	str	w14,[$ctx,#16*6]	// s3
+	str	w16,[$ctx,#16*7]	// r4
+	str	w15,[$ctx,#16*8]	// s4
+
+	ret
+.size	poly1305_splat,.-poly1305_splat
+
+#ifdef	__KERNEL__
+.globl	poly1305_blocks_neon
+#endif
+.type	poly1305_blocks_neon,%function
+.align	5
+poly1305_blocks_neon:
+.Lpoly1305_blocks_neon:
+	ldr	$is_base2_26,[$ctx,#24]
+	cmp	$len,#128
+	b.lo	.Lpoly1305_blocks
+
+	.inst	0xd503233f		// paciasp
+	stp	x29,x30,[sp,#-80]!
+	add	x29,sp,#0
+
+	stp	d8,d9,[sp,#16]		// meet ABI requirements
+	stp	d10,d11,[sp,#32]
+	stp	d12,d13,[sp,#48]
+	stp	d14,d15,[sp,#64]
+
+	cbz	$is_base2_26,.Lbase2_64_neon
+
+	ldp	w10,w11,[$ctx]		// load hash value base 2^26
+	ldp	w12,w13,[$ctx,#8]
+	ldr	w14,[$ctx,#16]
+
+	tst	$len,#31
+	b.eq	.Leven_neon
+
+	ldp	$r0,$r1,[$ctx,#32]	// load key value
+
+	add	$h0,x10,x11,lsl#26	// base 2^26 -> base 2^64
+	lsr	$h1,x12,#12
+	adds	$h0,$h0,x12,lsl#52
+	add	$h1,$h1,x13,lsl#14
+	adc	$h1,$h1,xzr
+	lsr	$h2,x14,#24
+	adds	$h1,$h1,x14,lsl#40
+	adc	$d2,$h2,xzr		// can be partially reduced...
+
+	ldp	$d0,$d1,[$inp],#16	// load input
+	sub	$len,$len,#16
+	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)
+
+#ifdef	__AARCH64EB__
+	rev	$d0,$d0
+	rev	$d1,$d1
+#endif
+	adds	$h0,$h0,$d0		// accumulate input
+	adcs	$h1,$h1,$d1
+	adc	$h2,$h2,$padbit
+
+	bl	poly1305_mult
+
+	and	x10,$h0,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x11,$h0,#26,#26
+	extr	x12,$h1,$h0,#52
+	and	x12,x12,#0x03ffffff
+	ubfx	x13,$h1,#14,#26
+	extr	x14,$h2,$h1,#40
+
+	b	.Leven_neon
+
+.align	4
+.Lbase2_64_neon:
+	ldp	$r0,$r1,[$ctx,#32]	// load key value
+
+	ldp	$h0,$h1,[$ctx]		// load hash value base 2^64
+	ldr	$h2,[$ctx,#16]
+
+	tst	$len,#31
+	b.eq	.Linit_neon
+
+	ldp	$d0,$d1,[$inp],#16	// load input
+	sub	$len,$len,#16
+	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)
+#ifdef	__AARCH64EB__
+	rev	$d0,$d0
+	rev	$d1,$d1
+#endif
+	adds	$h0,$h0,$d0		// accumulate input
+	adcs	$h1,$h1,$d1
+	adc	$h2,$h2,$padbit
+
+	bl	poly1305_mult
+
+.Linit_neon:
+	ldr	w17,[$ctx,#48]		// first table element
+	and	x10,$h0,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x11,$h0,#26,#26
+	extr	x12,$h1,$h0,#52
+	and	x12,x12,#0x03ffffff
+	ubfx	x13,$h1,#14,#26
+	extr	x14,$h2,$h1,#40
+
+	cmp	w17,#-1			// is value impossible?
+	b.ne	.Leven_neon
+
+	fmov	${H0},x10
+	fmov	${H1},x11
+	fmov	${H2},x12
+	fmov	${H3},x13
+	fmov	${H4},x14
+
+	////////////////////////////////// initialize r^n table
+	mov	$h0,$r0			// r^1
+	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)
+	mov	$h1,$r1
+	mov	$h2,xzr
+	add	$ctx,$ctx,#48+12
+	bl	poly1305_splat
+
+	bl	poly1305_mult		// r^2
+	sub	$ctx,$ctx,#4
+	bl	poly1305_splat
+
+	bl	poly1305_mult		// r^3
+	sub	$ctx,$ctx,#4
+	bl	poly1305_splat
+
+	bl	poly1305_mult		// r^4
+	sub	$ctx,$ctx,#4
+	bl	poly1305_splat
+	sub	$ctx,$ctx,#48		// restore original $ctx
+	b	.Ldo_neon
+
+.align	4
+.Leven_neon:
+	fmov	${H0},x10
+	fmov	${H1},x11
+	fmov	${H2},x12
+	fmov	${H3},x13
+	fmov	${H4},x14
+
+.Ldo_neon:
+	ldp	x8,x12,[$inp,#32]	// inp[2:3]
+	subs	$len,$len,#64
+	ldp	x9,x13,[$inp,#48]
+	add	$in2,$inp,#96
+	adr	$zeros,.Lzeros
+
+	lsl	$padbit,$padbit,#24
+	add	x15,$ctx,#48
+
+#ifdef	__AARCH64EB__
+	rev	x8,x8
+	rev	x12,x12
+	rev	x9,x9
+	rev	x13,x13
+#endif
+	and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	and	x5,x9,#0x03ffffff
+	ubfx	x6,x8,#26,#26
+	ubfx	x7,x9,#26,#26
+	add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	extr	x8,x12,x8,#52
+	extr	x9,x13,x9,#52
+	add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	fmov	$IN23_0,x4
+	and	x8,x8,#0x03ffffff
+	and	x9,x9,#0x03ffffff
+	ubfx	x10,x12,#14,#26
+	ubfx	x11,x13,#14,#26
+	add	x12,$padbit,x12,lsr#40
+	add	x13,$padbit,x13,lsr#40
+	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	fmov	$IN23_1,x6
+	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	fmov	$IN23_2,x8
+	fmov	$IN23_3,x10
+	fmov	$IN23_4,x12
+
+	ldp	x8,x12,[$inp],#16	// inp[0:1]
+	ldp	x9,x13,[$inp],#48
+
+	ld1	{$R0,$R1,$S1,$R2},[x15],#64
+	ld1	{$S2,$R3,$S3,$R4},[x15],#64
+	ld1	{$S4},[x15]
+
+#ifdef	__AARCH64EB__
+	rev	x8,x8
+	rev	x12,x12
+	rev	x9,x9
+	rev	x13,x13
+#endif
+	and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	and	x5,x9,#0x03ffffff
+	ubfx	x6,x8,#26,#26
+	ubfx	x7,x9,#26,#26
+	add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	extr	x8,x12,x8,#52
+	extr	x9,x13,x9,#52
+	add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	fmov	$IN01_0,x4
+	and	x8,x8,#0x03ffffff
+	and	x9,x9,#0x03ffffff
+	ubfx	x10,x12,#14,#26
+	ubfx	x11,x13,#14,#26
+	add	x12,$padbit,x12,lsr#40
+	add	x13,$padbit,x13,lsr#40
+	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	fmov	$IN01_1,x6
+	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	movi	$MASK.2d,#-1
+	fmov	$IN01_2,x8
+	fmov	$IN01_3,x10
+	fmov	$IN01_4,x12
+	ushr	$MASK.2d,$MASK.2d,#38
+
+	b.ls	.Lskip_loop
+
+.align	4
+.Loop_neon:
+	////////////////////////////////////////////////////////////////
+	// ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
+	// ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
+	//   \___________________/
+	// ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
+	// ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
+	//   \___________________/ \____________________/
+	//
+	// Note that we start with inp[2:3]*r^2. This is because it
+	// doesn't depend on reduction in previous iteration.
+	////////////////////////////////////////////////////////////////
+	// d4 = h0*r4 + h1*r3   + h2*r2   + h3*r1   + h4*r0
+	// d3 = h0*r3 + h1*r2   + h2*r1   + h3*r0   + h4*5*r4
+	// d2 = h0*r2 + h1*r1   + h2*r0   + h3*5*r4 + h4*5*r3
+	// d1 = h0*r1 + h1*r0   + h2*5*r4 + h3*5*r3 + h4*5*r2
+	// d0 = h0*r0 + h1*5*r4 + h2*5*r3 + h3*5*r2 + h4*5*r1
+
+	subs	$len,$len,#64
+	umull	$ACC4,$IN23_0,${R4}[2]
+	csel	$in2,$zeros,$in2,lo
+	umull	$ACC3,$IN23_0,${R3}[2]
+	umull	$ACC2,$IN23_0,${R2}[2]
+	 ldp	x8,x12,[$in2],#16	// inp[2:3] (or zero)
+	umull	$ACC1,$IN23_0,${R1}[2]
+	 ldp	x9,x13,[$in2],#48
+	umull	$ACC0,$IN23_0,${R0}[2]
+#ifdef	__AARCH64EB__
+	 rev	x8,x8
+	 rev	x12,x12
+	 rev	x9,x9
+	 rev	x13,x13
+#endif
+
+	umlal	$ACC4,$IN23_1,${R3}[2]
+	 and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	umlal	$ACC3,$IN23_1,${R2}[2]
+	 and	x5,x9,#0x03ffffff
+	umlal	$ACC2,$IN23_1,${R1}[2]
+	 ubfx	x6,x8,#26,#26
+	umlal	$ACC1,$IN23_1,${R0}[2]
+	 ubfx	x7,x9,#26,#26
+	umlal	$ACC0,$IN23_1,${S4}[2]
+	 add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+
+	umlal	$ACC4,$IN23_2,${R2}[2]
+	 extr	x8,x12,x8,#52
+	umlal	$ACC3,$IN23_2,${R1}[2]
+	 extr	x9,x13,x9,#52
+	umlal	$ACC2,$IN23_2,${R0}[2]
+	 add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	umlal	$ACC1,$IN23_2,${S4}[2]
+	 fmov	$IN23_0,x4
+	umlal	$ACC0,$IN23_2,${S3}[2]
+	 and	x8,x8,#0x03ffffff
+
+	umlal	$ACC4,$IN23_3,${R1}[2]
+	 and	x9,x9,#0x03ffffff
+	umlal	$ACC3,$IN23_3,${R0}[2]
+	 ubfx	x10,x12,#14,#26
+	umlal	$ACC2,$IN23_3,${S4}[2]
+	 ubfx	x11,x13,#14,#26
+	umlal	$ACC1,$IN23_3,${S3}[2]
+	 add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	umlal	$ACC0,$IN23_3,${S2}[2]
+	 fmov	$IN23_1,x6
+
+	add	$IN01_2,$IN01_2,$H2
+	 add	x12,$padbit,x12,lsr#40
+	umlal	$ACC4,$IN23_4,${R0}[2]
+	 add	x13,$padbit,x13,lsr#40
+	umlal	$ACC3,$IN23_4,${S4}[2]
+	 add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	umlal	$ACC2,$IN23_4,${S3}[2]
+	 add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	umlal	$ACC1,$IN23_4,${S2}[2]
+	 fmov	$IN23_2,x8
+	umlal	$ACC0,$IN23_4,${S1}[2]
+	 fmov	$IN23_3,x10
+
+	////////////////////////////////////////////////////////////////
+	// (hash+inp[0:1])*r^4 and accumulate
+
+	add	$IN01_0,$IN01_0,$H0
+	 fmov	$IN23_4,x12
+	umlal	$ACC3,$IN01_2,${R1}[0]
+	 ldp	x8,x12,[$inp],#16	// inp[0:1]
+	umlal	$ACC0,$IN01_2,${S3}[0]
+	 ldp	x9,x13,[$inp],#48
+	umlal	$ACC4,$IN01_2,${R2}[0]
+	umlal	$ACC1,$IN01_2,${S4}[0]
+	umlal	$ACC2,$IN01_2,${R0}[0]
+#ifdef	__AARCH64EB__
+	 rev	x8,x8
+	 rev	x12,x12
+	 rev	x9,x9
+	 rev	x13,x13
+#endif
+
+	add	$IN01_1,$IN01_1,$H1
+	umlal	$ACC3,$IN01_0,${R3}[0]
+	umlal	$ACC4,$IN01_0,${R4}[0]
+	 and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	umlal	$ACC2,$IN01_0,${R2}[0]
+	 and	x5,x9,#0x03ffffff
+	umlal	$ACC0,$IN01_0,${R0}[0]
+	 ubfx	x6,x8,#26,#26
+	umlal	$ACC1,$IN01_0,${R1}[0]
+	 ubfx	x7,x9,#26,#26
+
+	add	$IN01_3,$IN01_3,$H3
+	 add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	umlal	$ACC3,$IN01_1,${R2}[0]
+	 extr	x8,x12,x8,#52
+	umlal	$ACC4,$IN01_1,${R3}[0]
+	 extr	x9,x13,x9,#52
+	umlal	$ACC0,$IN01_1,${S4}[0]
+	 add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	umlal	$ACC2,$IN01_1,${R1}[0]
+	 fmov	$IN01_0,x4
+	umlal	$ACC1,$IN01_1,${R0}[0]
+	 and	x8,x8,#0x03ffffff
+
+	add	$IN01_4,$IN01_4,$H4
+	 and	x9,x9,#0x03ffffff
+	umlal	$ACC3,$IN01_3,${R0}[0]
+	 ubfx	x10,x12,#14,#26
+	umlal	$ACC0,$IN01_3,${S2}[0]
+	 ubfx	x11,x13,#14,#26
+	umlal	$ACC4,$IN01_3,${R1}[0]
+	 add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	umlal	$ACC1,$IN01_3,${S3}[0]
+	 fmov	$IN01_1,x6
+	umlal	$ACC2,$IN01_3,${S4}[0]
+	 add	x12,$padbit,x12,lsr#40
+
+	umlal	$ACC3,$IN01_4,${S4}[0]
+	 add	x13,$padbit,x13,lsr#40
+	umlal	$ACC0,$IN01_4,${S1}[0]
+	 add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	umlal	$ACC4,$IN01_4,${R0}[0]
+	 add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	umlal	$ACC1,$IN01_4,${S2}[0]
+	 fmov	$IN01_2,x8
+	umlal	$ACC2,$IN01_4,${S3}[0]
+	 fmov	$IN01_3,x10
+	 fmov	$IN01_4,x12
+
+	/////////////////////////////////////////////////////////////////
+	// lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
+	// and P. Schwabe
+	//
+	// [see discussion in poly1305-armv4 module]
+
+	ushr	$T0.2d,$ACC3,#26
+	xtn	$H3,$ACC3
+	 ushr	$T1.2d,$ACC0,#26
+	 and	$ACC0,$ACC0,$MASK.2d
+	add	$ACC4,$ACC4,$T0.2d	// h3 -> h4
+	bic	$H3,#0xfc,lsl#24	// &=0x03ffffff
+	 add	$ACC1,$ACC1,$T1.2d	// h0 -> h1
+
+	ushr	$T0.2d,$ACC4,#26
+	xtn	$H4,$ACC4
+	 ushr	$T1.2d,$ACC1,#26
+	 xtn	$H1,$ACC1
+	bic	$H4,#0xfc,lsl#24
+	 add	$ACC2,$ACC2,$T1.2d	// h1 -> h2
+
+	add	$ACC0,$ACC0,$T0.2d
+	shl	$T0.2d,$T0.2d,#2
+	 shrn	$T1.2s,$ACC2,#26
+	 xtn	$H2,$ACC2
+	add	$ACC0,$ACC0,$T0.2d	// h4 -> h0
+	 bic	$H1,#0xfc,lsl#24
+	 add	$H3,$H3,$T1.2s		// h2 -> h3
+	 bic	$H2,#0xfc,lsl#24
+
+	shrn	$T0.2s,$ACC0,#26
+	xtn	$H0,$ACC0
+	 ushr	$T1.2s,$H3,#26
+	 bic	$H3,#0xfc,lsl#24
+	 bic	$H0,#0xfc,lsl#24
+	add	$H1,$H1,$T0.2s		// h0 -> h1
+	 add	$H4,$H4,$T1.2s		// h3 -> h4
+
+	b.hi	.Loop_neon
+
+.Lskip_loop:
+	dup	$IN23_2,${IN23_2}[0]
+	add	$IN01_2,$IN01_2,$H2
+
+	////////////////////////////////////////////////////////////////
+	// multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
+
+	adds	$len,$len,#32
+	b.ne	.Long_tail
+
+	dup	$IN23_2,${IN01_2}[0]
+	add	$IN23_0,$IN01_0,$H0
+	add	$IN23_3,$IN01_3,$H3
+	add	$IN23_1,$IN01_1,$H1
+	add	$IN23_4,$IN01_4,$H4
+
+.Long_tail:
+	dup	$IN23_0,${IN23_0}[0]
+	umull2	$ACC0,$IN23_2,${S3}
+	umull2	$ACC3,$IN23_2,${R1}
+	umull2	$ACC4,$IN23_2,${R2}
+	umull2	$ACC2,$IN23_2,${R0}
+	umull2	$ACC1,$IN23_2,${S4}
+
+	dup	$IN23_1,${IN23_1}[0]
+	umlal2	$ACC0,$IN23_0,${R0}
+	umlal2	$ACC2,$IN23_0,${R2}
+	umlal2	$ACC3,$IN23_0,${R3}
+	umlal2	$ACC4,$IN23_0,${R4}
+	umlal2	$ACC1,$IN23_0,${R1}
+
+	dup	$IN23_3,${IN23_3}[0]
+	umlal2	$ACC0,$IN23_1,${S4}
+	umlal2	$ACC3,$IN23_1,${R2}
+	umlal2	$ACC2,$IN23_1,${R1}
+	umlal2	$ACC4,$IN23_1,${R3}
+	umlal2	$ACC1,$IN23_1,${R0}
+
+	dup	$IN23_4,${IN23_4}[0]
+	umlal2	$ACC3,$IN23_3,${R0}
+	umlal2	$ACC4,$IN23_3,${R1}
+	umlal2	$ACC0,$IN23_3,${S2}
+	umlal2	$ACC1,$IN23_3,${S3}
+	umlal2	$ACC2,$IN23_3,${S4}
+
+	umlal2	$ACC3,$IN23_4,${S4}
+	umlal2	$ACC0,$IN23_4,${S1}
+	umlal2	$ACC4,$IN23_4,${R0}
+	umlal2	$ACC1,$IN23_4,${S2}
+	umlal2	$ACC2,$IN23_4,${S3}
+
+	b.eq	.Lshort_tail
+
+	////////////////////////////////////////////////////////////////
+	// (hash+inp[0:1])*r^4:r^3 and accumulate
+
+	add	$IN01_0,$IN01_0,$H0
+	umlal	$ACC3,$IN01_2,${R1}
+	umlal	$ACC0,$IN01_2,${S3}
+	umlal	$ACC4,$IN01_2,${R2}
+	umlal	$ACC1,$IN01_2,${S4}
+	umlal	$ACC2,$IN01_2,${R0}
+
+	add	$IN01_1,$IN01_1,$H1
+	umlal	$ACC3,$IN01_0,${R3}
+	umlal	$ACC0,$IN01_0,${R0}
+	umlal	$ACC4,$IN01_0,${R4}
+	umlal	$ACC1,$IN01_0,${R1}
+	umlal	$ACC2,$IN01_0,${R2}
+
+	add	$IN01_3,$IN01_3,$H3
+	umlal	$ACC3,$IN01_1,${R2}
+	umlal	$ACC0,$IN01_1,${S4}
+	umlal	$ACC4,$IN01_1,${R3}
+	umlal	$ACC1,$IN01_1,${R0}
+	umlal	$ACC2,$IN01_1,${R1}
+
+	add	$IN01_4,$IN01_4,$H4
+	umlal	$ACC3,$IN01_3,${R0}
+	umlal	$ACC0,$IN01_3,${S2}
+	umlal	$ACC4,$IN01_3,${R1}
+	umlal	$ACC1,$IN01_3,${S3}
+	umlal	$ACC2,$IN01_3,${S4}
+
+	umlal	$ACC3,$IN01_4,${S4}
+	umlal	$ACC0,$IN01_4,${S1}
+	umlal	$ACC4,$IN01_4,${R0}
+	umlal	$ACC1,$IN01_4,${S2}
+	umlal	$ACC2,$IN01_4,${S3}
+
+.Lshort_tail:
+	////////////////////////////////////////////////////////////////
+	// horizontal add
+
+	addp	$ACC3,$ACC3,$ACC3
+	 ldp	d8,d9,[sp,#16]		// meet ABI requirements
+	addp	$ACC0,$ACC0,$ACC0
+	 ldp	d10,d11,[sp,#32]
+	addp	$ACC4,$ACC4,$ACC4
+	 ldp	d12,d13,[sp,#48]
+	addp	$ACC1,$ACC1,$ACC1
+	 ldp	d14,d15,[sp,#64]
+	addp	$ACC2,$ACC2,$ACC2
+	 ldr	x30,[sp,#8]
+	 .inst	0xd50323bf		// autiasp
+
+	////////////////////////////////////////////////////////////////
+	// lazy reduction, but without narrowing
+
+	ushr	$T0.2d,$ACC3,#26
+	and	$ACC3,$ACC3,$MASK.2d
+	 ushr	$T1.2d,$ACC0,#26
+	 and	$ACC0,$ACC0,$MASK.2d
+
+	add	$ACC4,$ACC4,$T0.2d	// h3 -> h4
+	 add	$ACC1,$ACC1,$T1.2d	// h0 -> h1
+
+	ushr	$T0.2d,$ACC4,#26
+	and	$ACC4,$ACC4,$MASK.2d
+	 ushr	$T1.2d,$ACC1,#26
+	 and	$ACC1,$ACC1,$MASK.2d
+	 add	$ACC2,$ACC2,$T1.2d	// h1 -> h2
+
+	add	$ACC0,$ACC0,$T0.2d
+	shl	$T0.2d,$T0.2d,#2
+	 ushr	$T1.2d,$ACC2,#26
+	 and	$ACC2,$ACC2,$MASK.2d
+	add	$ACC0,$ACC0,$T0.2d	// h4 -> h0
+	 add	$ACC3,$ACC3,$T1.2d	// h2 -> h3
+
+	ushr	$T0.2d,$ACC0,#26
+	and	$ACC0,$ACC0,$MASK.2d
+	 ushr	$T1.2d,$ACC3,#26
+	 and	$ACC3,$ACC3,$MASK.2d
+	add	$ACC1,$ACC1,$T0.2d	// h0 -> h1
+	 add	$ACC4,$ACC4,$T1.2d	// h3 -> h4
+
+	////////////////////////////////////////////////////////////////
+	// write the result, can be partially reduced
+
+	st4	{$ACC0,$ACC1,$ACC2,$ACC3}[0],[$ctx],#16
+	mov	x4,#1
+	st1	{$ACC4}[0],[$ctx]
+	str	x4,[$ctx,#8]		// set is_base2_26
+
+	ldr	x29,[sp],#80
+	ret
+.size	poly1305_blocks_neon,.-poly1305_blocks_neon
+
+.align	5
+.Lzeros:
+.long	0,0,0,0,0,0,0,0
+.asciz	"Poly1305 for ARMv8, CRYPTOGAMS by \@dot-asm"
+.align	2
+#if !defined(__KERNEL__) && !defined(_WIN64)
+.comm	OPENSSL_armcap_P,4,4
+.hidden	OPENSSL_armcap_P
+#endif
+___
+
+foreach (split("\n",$code)) {
+	s/\b(shrn\s+v[0-9]+)\.[24]d/$1.2s/			or
+	s/\b(fmov\s+)v([0-9]+)[^,]*,\s*x([0-9]+)/$1d$2,x$3/	or
+	(m/\bdup\b/ and (s/\.[24]s/.2d/g or 1))			or
+	(m/\b(eor|and)/ and (s/\.[248][sdh]/.16b/g or 1))	or
+	(m/\bum(ul|la)l\b/ and (s/\.4s/.2s/g or 1))		or
+	(m/\bum(ul|la)l2\b/ and (s/\.2s/.4s/g or 1))		or
+	(m/\bst[1-4]\s+{[^}]+}\[/ and (s/\.[24]d/.s/g or 1));
+
+	s/\.[124]([sd])\[/.$1\[/;
+	s/w#x([0-9]+)/w$1/g;
+
+	print $_,"\n";
+}
+close STDOUT;
diff --git a/arch/arm64/crypto/poly1305-core.S_shipped b/arch/arm64/crypto/poly1305-core.S_shipped
new file mode 100644
index 000000000000..8d1c4e420ccd
--- /dev/null
+++ b/arch/arm64/crypto/poly1305-core.S_shipped
@@ -0,0 +1,835 @@
+#ifndef __KERNEL__
+# include "arm_arch.h"
+.extern	OPENSSL_armcap_P
+#endif
+
+.text
+
+// forward "declarations" are required for Apple
+.globl	poly1305_blocks
+.globl	poly1305_emit
+
+.globl	poly1305_init
+.type	poly1305_init,%function
+.align	5
+poly1305_init:
+	cmp	x1,xzr
+	stp	xzr,xzr,[x0]		// zero hash value
+	stp	xzr,xzr,[x0,#16]	// [along with is_base2_26]
+
+	csel	x0,xzr,x0,eq
+	b.eq	.Lno_key
+
+#ifndef	__KERNEL__
+	adrp	x17,OPENSSL_armcap_P
+	ldr	w17,[x17,#:lo12:OPENSSL_armcap_P]
+#endif
+
+	ldp	x7,x8,[x1]		// load key
+	mov	x9,#0xfffffffc0fffffff
+	movk	x9,#0x0fff,lsl#48
+#ifdef	__AARCH64EB__
+	rev	x7,x7			// flip bytes
+	rev	x8,x8
+#endif
+	and	x7,x7,x9		// &=0ffffffc0fffffff
+	and	x9,x9,#-4
+	and	x8,x8,x9		// &=0ffffffc0ffffffc
+	mov	w9,#-1
+	stp	x7,x8,[x0,#32]	// save key value
+	str	w9,[x0,#48]	// impossible key power value
+
+#ifndef	__KERNEL__
+	tst	w17,#ARMV7_NEON
+
+	adr	x12,.Lpoly1305_blocks
+	adr	x7,.Lpoly1305_blocks_neon
+	adr	x13,.Lpoly1305_emit
+
+	csel	x12,x12,x7,eq
+
+# ifdef	__ILP32__
+	stp	w12,w13,[x2]
+# else
+	stp	x12,x13,[x2]
+# endif
+#endif
+	mov	x0,#1
+.Lno_key:
+	ret
+.size	poly1305_init,.-poly1305_init
+
+.type	poly1305_blocks,%function
+.align	5
+poly1305_blocks:
+.Lpoly1305_blocks:
+	ands	x2,x2,#-16
+	b.eq	.Lno_data
+
+	ldp	x4,x5,[x0]		// load hash value
+	ldp	x6,x17,[x0,#16]	// [along with is_base2_26]
+	ldp	x7,x8,[x0,#32]	// load key value
+
+#ifdef	__AARCH64EB__
+	lsr	x12,x4,#32
+	mov	w13,w4
+	lsr	x14,x5,#32
+	mov	w15,w5
+	lsr	x16,x6,#32
+#else
+	mov	w12,w4
+	lsr	x13,x4,#32
+	mov	w14,w5
+	lsr	x15,x5,#32
+	mov	w16,w6
+#endif
+
+	add	x12,x12,x13,lsl#26	// base 2^26 -> base 2^64
+	lsr	x13,x14,#12
+	adds	x12,x12,x14,lsl#52
+	add	x13,x13,x15,lsl#14
+	adc	x13,x13,xzr
+	lsr	x14,x16,#24
+	adds	x13,x13,x16,lsl#40
+	adc	x14,x14,xzr
+
+	cmp	x17,#0			// is_base2_26?
+	add	x9,x8,x8,lsr#2	// s1 = r1 + (r1 >> 2)
+	csel	x4,x4,x12,eq		// choose between radixes
+	csel	x5,x5,x13,eq
+	csel	x6,x6,x14,eq
+
+.Loop:
+	ldp	x10,x11,[x1],#16	// load input
+	sub	x2,x2,#16
+#ifdef	__AARCH64EB__
+	rev	x10,x10
+	rev	x11,x11
+#endif
+	adds	x4,x4,x10		// accumulate input
+	adcs	x5,x5,x11
+
+	mul	x12,x4,x7		// h0*r0
+	adc	x6,x6,x3
+	umulh	x13,x4,x7
+
+	mul	x10,x5,x9		// h1*5*r1
+	umulh	x11,x5,x9
+
+	adds	x12,x12,x10
+	mul	x10,x4,x8		// h0*r1
+	adc	x13,x13,x11
+	umulh	x14,x4,x8
+
+	adds	x13,x13,x10
+	mul	x10,x5,x7		// h1*r0
+	adc	x14,x14,xzr
+	umulh	x11,x5,x7
+
+	adds	x13,x13,x10
+	mul	x10,x6,x9		// h2*5*r1
+	adc	x14,x14,x11
+	mul	x11,x6,x7		// h2*r0
+
+	adds	x13,x13,x10
+	adc	x14,x14,x11
+
+	and	x10,x14,#-4		// final reduction
+	and	x6,x14,#3
+	add	x10,x10,x14,lsr#2
+	adds	x4,x12,x10
+	adcs	x5,x13,xzr
+	adc	x6,x6,xzr
+
+	cbnz	x2,.Loop
+
+	stp	x4,x5,[x0]		// store hash value
+	stp	x6,xzr,[x0,#16]	// [and clear is_base2_26]
+
+.Lno_data:
+	ret
+.size	poly1305_blocks,.-poly1305_blocks
+
+.type	poly1305_emit,%function
+.align	5
+poly1305_emit:
+.Lpoly1305_emit:
+	ldp	x4,x5,[x0]		// load hash base 2^64
+	ldp	x6,x7,[x0,#16]	// [along with is_base2_26]
+	ldp	x10,x11,[x2]	// load nonce
+
+#ifdef	__AARCH64EB__
+	lsr	x12,x4,#32
+	mov	w13,w4
+	lsr	x14,x5,#32
+	mov	w15,w5
+	lsr	x16,x6,#32
+#else
+	mov	w12,w4
+	lsr	x13,x4,#32
+	mov	w14,w5
+	lsr	x15,x5,#32
+	mov	w16,w6
+#endif
+
+	add	x12,x12,x13,lsl#26	// base 2^26 -> base 2^64
+	lsr	x13,x14,#12
+	adds	x12,x12,x14,lsl#52
+	add	x13,x13,x15,lsl#14
+	adc	x13,x13,xzr
+	lsr	x14,x16,#24
+	adds	x13,x13,x16,lsl#40
+	adc	x14,x14,xzr
+
+	cmp	x7,#0			// is_base2_26?
+	csel	x4,x4,x12,eq		// choose between radixes
+	csel	x5,x5,x13,eq
+	csel	x6,x6,x14,eq
+
+	adds	x12,x4,#5		// compare to modulus
+	adcs	x13,x5,xzr
+	adc	x14,x6,xzr
+
+	tst	x14,#-4			// see if it's carried/borrowed
+
+	csel	x4,x4,x12,eq
+	csel	x5,x5,x13,eq
+
+#ifdef	__AARCH64EB__
+	ror	x10,x10,#32		// flip nonce words
+	ror	x11,x11,#32
+#endif
+	adds	x4,x4,x10		// accumulate nonce
+	adc	x5,x5,x11
+#ifdef	__AARCH64EB__
+	rev	x4,x4			// flip output bytes
+	rev	x5,x5
+#endif
+	stp	x4,x5,[x1]		// write result
+
+	ret
+.size	poly1305_emit,.-poly1305_emit
+.type	poly1305_mult,%function
+.align	5
+poly1305_mult:
+	mul	x12,x4,x7		// h0*r0
+	umulh	x13,x4,x7
+
+	mul	x10,x5,x9		// h1*5*r1
+	umulh	x11,x5,x9
+
+	adds	x12,x12,x10
+	mul	x10,x4,x8		// h0*r1
+	adc	x13,x13,x11
+	umulh	x14,x4,x8
+
+	adds	x13,x13,x10
+	mul	x10,x5,x7		// h1*r0
+	adc	x14,x14,xzr
+	umulh	x11,x5,x7
+
+	adds	x13,x13,x10
+	mul	x10,x6,x9		// h2*5*r1
+	adc	x14,x14,x11
+	mul	x11,x6,x7		// h2*r0
+
+	adds	x13,x13,x10
+	adc	x14,x14,x11
+
+	and	x10,x14,#-4		// final reduction
+	and	x6,x14,#3
+	add	x10,x10,x14,lsr#2
+	adds	x4,x12,x10
+	adcs	x5,x13,xzr
+	adc	x6,x6,xzr
+
+	ret
+.size	poly1305_mult,.-poly1305_mult
+
+.type	poly1305_splat,%function
+.align	4
+poly1305_splat:
+	and	x12,x4,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x13,x4,#26,#26
+	extr	x14,x5,x4,#52
+	and	x14,x14,#0x03ffffff
+	ubfx	x15,x5,#14,#26
+	extr	x16,x6,x5,#40
+
+	str	w12,[x0,#16*0]	// r0
+	add	w12,w13,w13,lsl#2	// r1*5
+	str	w13,[x0,#16*1]	// r1
+	add	w13,w14,w14,lsl#2	// r2*5
+	str	w12,[x0,#16*2]	// s1
+	str	w14,[x0,#16*3]	// r2
+	add	w14,w15,w15,lsl#2	// r3*5
+	str	w13,[x0,#16*4]	// s2
+	str	w15,[x0,#16*5]	// r3
+	add	w15,w16,w16,lsl#2	// r4*5
+	str	w14,[x0,#16*6]	// s3
+	str	w16,[x0,#16*7]	// r4
+	str	w15,[x0,#16*8]	// s4
+
+	ret
+.size	poly1305_splat,.-poly1305_splat
+
+#ifdef	__KERNEL__
+.globl	poly1305_blocks_neon
+#endif
+.type	poly1305_blocks_neon,%function
+.align	5
+poly1305_blocks_neon:
+.Lpoly1305_blocks_neon:
+	ldr	x17,[x0,#24]
+	cmp	x2,#128
+	b.lo	.Lpoly1305_blocks
+
+	.inst	0xd503233f		// paciasp
+	stp	x29,x30,[sp,#-80]!
+	add	x29,sp,#0
+
+	stp	d8,d9,[sp,#16]		// meet ABI requirements
+	stp	d10,d11,[sp,#32]
+	stp	d12,d13,[sp,#48]
+	stp	d14,d15,[sp,#64]
+
+	cbz	x17,.Lbase2_64_neon
+
+	ldp	w10,w11,[x0]		// load hash value base 2^26
+	ldp	w12,w13,[x0,#8]
+	ldr	w14,[x0,#16]
+
+	tst	x2,#31
+	b.eq	.Leven_neon
+
+	ldp	x7,x8,[x0,#32]	// load key value
+
+	add	x4,x10,x11,lsl#26	// base 2^26 -> base 2^64
+	lsr	x5,x12,#12
+	adds	x4,x4,x12,lsl#52
+	add	x5,x5,x13,lsl#14
+	adc	x5,x5,xzr
+	lsr	x6,x14,#24
+	adds	x5,x5,x14,lsl#40
+	adc	x14,x6,xzr		// can be partially reduced...
+
+	ldp	x12,x13,[x1],#16	// load input
+	sub	x2,x2,#16
+	add	x9,x8,x8,lsr#2	// s1 = r1 + (r1 >> 2)
+
+#ifdef	__AARCH64EB__
+	rev	x12,x12
+	rev	x13,x13
+#endif
+	adds	x4,x4,x12		// accumulate input
+	adcs	x5,x5,x13
+	adc	x6,x6,x3
+
+	bl	poly1305_mult
+
+	and	x10,x4,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x11,x4,#26,#26
+	extr	x12,x5,x4,#52
+	and	x12,x12,#0x03ffffff
+	ubfx	x13,x5,#14,#26
+	extr	x14,x6,x5,#40
+
+	b	.Leven_neon
+
+.align	4
+.Lbase2_64_neon:
+	ldp	x7,x8,[x0,#32]	// load key value
+
+	ldp	x4,x5,[x0]		// load hash value base 2^64
+	ldr	x6,[x0,#16]
+
+	tst	x2,#31
+	b.eq	.Linit_neon
+
+	ldp	x12,x13,[x1],#16	// load input
+	sub	x2,x2,#16
+	add	x9,x8,x8,lsr#2	// s1 = r1 + (r1 >> 2)
+#ifdef	__AARCH64EB__
+	rev	x12,x12
+	rev	x13,x13
+#endif
+	adds	x4,x4,x12		// accumulate input
+	adcs	x5,x5,x13
+	adc	x6,x6,x3
+
+	bl	poly1305_mult
+
+.Linit_neon:
+	ldr	w17,[x0,#48]		// first table element
+	and	x10,x4,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x11,x4,#26,#26
+	extr	x12,x5,x4,#52
+	and	x12,x12,#0x03ffffff
+	ubfx	x13,x5,#14,#26
+	extr	x14,x6,x5,#40
+
+	cmp	w17,#-1			// is value impossible?
+	b.ne	.Leven_neon
+
+	fmov	d24,x10
+	fmov	d25,x11
+	fmov	d26,x12
+	fmov	d27,x13
+	fmov	d28,x14
+
+	////////////////////////////////// initialize r^n table
+	mov	x4,x7			// r^1
+	add	x9,x8,x8,lsr#2	// s1 = r1 + (r1 >> 2)
+	mov	x5,x8
+	mov	x6,xzr
+	add	x0,x0,#48+12
+	bl	poly1305_splat
+
+	bl	poly1305_mult		// r^2
+	sub	x0,x0,#4
+	bl	poly1305_splat
+
+	bl	poly1305_mult		// r^3
+	sub	x0,x0,#4
+	bl	poly1305_splat
+
+	bl	poly1305_mult		// r^4
+	sub	x0,x0,#4
+	bl	poly1305_splat
+	sub	x0,x0,#48		// restore original x0
+	b	.Ldo_neon
+
+.align	4
+.Leven_neon:
+	fmov	d24,x10
+	fmov	d25,x11
+	fmov	d26,x12
+	fmov	d27,x13
+	fmov	d28,x14
+
+.Ldo_neon:
+	ldp	x8,x12,[x1,#32]	// inp[2:3]
+	subs	x2,x2,#64
+	ldp	x9,x13,[x1,#48]
+	add	x16,x1,#96
+	adr	x17,.Lzeros
+
+	lsl	x3,x3,#24
+	add	x15,x0,#48
+
+#ifdef	__AARCH64EB__
+	rev	x8,x8
+	rev	x12,x12
+	rev	x9,x9
+	rev	x13,x13
+#endif
+	and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	and	x5,x9,#0x03ffffff
+	ubfx	x6,x8,#26,#26
+	ubfx	x7,x9,#26,#26
+	add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	extr	x8,x12,x8,#52
+	extr	x9,x13,x9,#52
+	add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	fmov	d14,x4
+	and	x8,x8,#0x03ffffff
+	and	x9,x9,#0x03ffffff
+	ubfx	x10,x12,#14,#26
+	ubfx	x11,x13,#14,#26
+	add	x12,x3,x12,lsr#40
+	add	x13,x3,x13,lsr#40
+	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	fmov	d15,x6
+	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	fmov	d16,x8
+	fmov	d17,x10
+	fmov	d18,x12
+
+	ldp	x8,x12,[x1],#16	// inp[0:1]
+	ldp	x9,x13,[x1],#48
+
+	ld1	{v0.4s,v1.4s,v2.4s,v3.4s},[x15],#64
+	ld1	{v4.4s,v5.4s,v6.4s,v7.4s},[x15],#64
+	ld1	{v8.4s},[x15]
+
+#ifdef	__AARCH64EB__
+	rev	x8,x8
+	rev	x12,x12
+	rev	x9,x9
+	rev	x13,x13
+#endif
+	and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	and	x5,x9,#0x03ffffff
+	ubfx	x6,x8,#26,#26
+	ubfx	x7,x9,#26,#26
+	add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	extr	x8,x12,x8,#52
+	extr	x9,x13,x9,#52
+	add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	fmov	d9,x4
+	and	x8,x8,#0x03ffffff
+	and	x9,x9,#0x03ffffff
+	ubfx	x10,x12,#14,#26
+	ubfx	x11,x13,#14,#26
+	add	x12,x3,x12,lsr#40
+	add	x13,x3,x13,lsr#40
+	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	fmov	d10,x6
+	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	movi	v31.2d,#-1
+	fmov	d11,x8
+	fmov	d12,x10
+	fmov	d13,x12
+	ushr	v31.2d,v31.2d,#38
+
+	b.ls	.Lskip_loop
+
+.align	4
+.Loop_neon:
+	////////////////////////////////////////////////////////////////
+	// ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
+	// ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
+	//   ___________________/
+	// ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
+	// ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
+	//   ___________________/ ____________________/
+	//
+	// Note that we start with inp[2:3]*r^2. This is because it
+	// doesn't depend on reduction in previous iteration.
+	////////////////////////////////////////////////////////////////
+	// d4 = h0*r4 + h1*r3   + h2*r2   + h3*r1   + h4*r0
+	// d3 = h0*r3 + h1*r2   + h2*r1   + h3*r0   + h4*5*r4
+	// d2 = h0*r2 + h1*r1   + h2*r0   + h3*5*r4 + h4*5*r3
+	// d1 = h0*r1 + h1*r0   + h2*5*r4 + h3*5*r3 + h4*5*r2
+	// d0 = h0*r0 + h1*5*r4 + h2*5*r3 + h3*5*r2 + h4*5*r1
+
+	subs	x2,x2,#64
+	umull	v23.2d,v14.2s,v7.s[2]
+	csel	x16,x17,x16,lo
+	umull	v22.2d,v14.2s,v5.s[2]
+	umull	v21.2d,v14.2s,v3.s[2]
+	 ldp	x8,x12,[x16],#16	// inp[2:3] (or zero)
+	umull	v20.2d,v14.2s,v1.s[2]
+	 ldp	x9,x13,[x16],#48
+	umull	v19.2d,v14.2s,v0.s[2]
+#ifdef	__AARCH64EB__
+	 rev	x8,x8
+	 rev	x12,x12
+	 rev	x9,x9
+	 rev	x13,x13
+#endif
+
+	umlal	v23.2d,v15.2s,v5.s[2]
+	 and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	umlal	v22.2d,v15.2s,v3.s[2]
+	 and	x5,x9,#0x03ffffff
+	umlal	v21.2d,v15.2s,v1.s[2]
+	 ubfx	x6,x8,#26,#26
+	umlal	v20.2d,v15.2s,v0.s[2]
+	 ubfx	x7,x9,#26,#26
+	umlal	v19.2d,v15.2s,v8.s[2]
+	 add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+
+	umlal	v23.2d,v16.2s,v3.s[2]
+	 extr	x8,x12,x8,#52
+	umlal	v22.2d,v16.2s,v1.s[2]
+	 extr	x9,x13,x9,#52
+	umlal	v21.2d,v16.2s,v0.s[2]
+	 add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	umlal	v20.2d,v16.2s,v8.s[2]
+	 fmov	d14,x4
+	umlal	v19.2d,v16.2s,v6.s[2]
+	 and	x8,x8,#0x03ffffff
+
+	umlal	v23.2d,v17.2s,v1.s[2]
+	 and	x9,x9,#0x03ffffff
+	umlal	v22.2d,v17.2s,v0.s[2]
+	 ubfx	x10,x12,#14,#26
+	umlal	v21.2d,v17.2s,v8.s[2]
+	 ubfx	x11,x13,#14,#26
+	umlal	v20.2d,v17.2s,v6.s[2]
+	 add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	umlal	v19.2d,v17.2s,v4.s[2]
+	 fmov	d15,x6
+
+	add	v11.2s,v11.2s,v26.2s
+	 add	x12,x3,x12,lsr#40
+	umlal	v23.2d,v18.2s,v0.s[2]
+	 add	x13,x3,x13,lsr#40
+	umlal	v22.2d,v18.2s,v8.s[2]
+	 add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	umlal	v21.2d,v18.2s,v6.s[2]
+	 add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	umlal	v20.2d,v18.2s,v4.s[2]
+	 fmov	d16,x8
+	umlal	v19.2d,v18.2s,v2.s[2]
+	 fmov	d17,x10
+
+	////////////////////////////////////////////////////////////////
+	// (hash+inp[0:1])*r^4 and accumulate
+
+	add	v9.2s,v9.2s,v24.2s
+	 fmov	d18,x12
+	umlal	v22.2d,v11.2s,v1.s[0]
+	 ldp	x8,x12,[x1],#16	// inp[0:1]
+	umlal	v19.2d,v11.2s,v6.s[0]
+	 ldp	x9,x13,[x1],#48
+	umlal	v23.2d,v11.2s,v3.s[0]
+	umlal	v20.2d,v11.2s,v8.s[0]
+	umlal	v21.2d,v11.2s,v0.s[0]
+#ifdef	__AARCH64EB__
+	 rev	x8,x8
+	 rev	x12,x12
+	 rev	x9,x9
+	 rev	x13,x13
+#endif
+
+	add	v10.2s,v10.2s,v25.2s
+	umlal	v22.2d,v9.2s,v5.s[0]
+	umlal	v23.2d,v9.2s,v7.s[0]
+	 and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	umlal	v21.2d,v9.2s,v3.s[0]
+	 and	x5,x9,#0x03ffffff
+	umlal	v19.2d,v9.2s,v0.s[0]
+	 ubfx	x6,x8,#26,#26
+	umlal	v20.2d,v9.2s,v1.s[0]
+	 ubfx	x7,x9,#26,#26
+
+	add	v12.2s,v12.2s,v27.2s
+	 add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	umlal	v22.2d,v10.2s,v3.s[0]
+	 extr	x8,x12,x8,#52
+	umlal	v23.2d,v10.2s,v5.s[0]
+	 extr	x9,x13,x9,#52
+	umlal	v19.2d,v10.2s,v8.s[0]
+	 add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	umlal	v21.2d,v10.2s,v1.s[0]
+	 fmov	d9,x4
+	umlal	v20.2d,v10.2s,v0.s[0]
+	 and	x8,x8,#0x03ffffff
+
+	add	v13.2s,v13.2s,v28.2s
+	 and	x9,x9,#0x03ffffff
+	umlal	v22.2d,v12.2s,v0.s[0]
+	 ubfx	x10,x12,#14,#26
+	umlal	v19.2d,v12.2s,v4.s[0]
+	 ubfx	x11,x13,#14,#26
+	umlal	v23.2d,v12.2s,v1.s[0]
+	 add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	umlal	v20.2d,v12.2s,v6.s[0]
+	 fmov	d10,x6
+	umlal	v21.2d,v12.2s,v8.s[0]
+	 add	x12,x3,x12,lsr#40
+
+	umlal	v22.2d,v13.2s,v8.s[0]
+	 add	x13,x3,x13,lsr#40
+	umlal	v19.2d,v13.2s,v2.s[0]
+	 add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	umlal	v23.2d,v13.2s,v0.s[0]
+	 add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	umlal	v20.2d,v13.2s,v4.s[0]
+	 fmov	d11,x8
+	umlal	v21.2d,v13.2s,v6.s[0]
+	 fmov	d12,x10
+	 fmov	d13,x12
+
+	/////////////////////////////////////////////////////////////////
+	// lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
+	// and P. Schwabe
+	//
+	// [see discussion in poly1305-armv4 module]
+
+	ushr	v29.2d,v22.2d,#26
+	xtn	v27.2s,v22.2d
+	 ushr	v30.2d,v19.2d,#26
+	 and	v19.16b,v19.16b,v31.16b
+	add	v23.2d,v23.2d,v29.2d	// h3 -> h4
+	bic	v27.2s,#0xfc,lsl#24	// &=0x03ffffff
+	 add	v20.2d,v20.2d,v30.2d	// h0 -> h1
+
+	ushr	v29.2d,v23.2d,#26
+	xtn	v28.2s,v23.2d
+	 ushr	v30.2d,v20.2d,#26
+	 xtn	v25.2s,v20.2d
+	bic	v28.2s,#0xfc,lsl#24
+	 add	v21.2d,v21.2d,v30.2d	// h1 -> h2
+
+	add	v19.2d,v19.2d,v29.2d
+	shl	v29.2d,v29.2d,#2
+	 shrn	v30.2s,v21.2d,#26
+	 xtn	v26.2s,v21.2d
+	add	v19.2d,v19.2d,v29.2d	// h4 -> h0
+	 bic	v25.2s,#0xfc,lsl#24
+	 add	v27.2s,v27.2s,v30.2s		// h2 -> h3
+	 bic	v26.2s,#0xfc,lsl#24
+
+	shrn	v29.2s,v19.2d,#26
+	xtn	v24.2s,v19.2d
+	 ushr	v30.2s,v27.2s,#26
+	 bic	v27.2s,#0xfc,lsl#24
+	 bic	v24.2s,#0xfc,lsl#24
+	add	v25.2s,v25.2s,v29.2s		// h0 -> h1
+	 add	v28.2s,v28.2s,v30.2s		// h3 -> h4
+
+	b.hi	.Loop_neon
+
+.Lskip_loop:
+	dup	v16.2d,v16.d[0]
+	add	v11.2s,v11.2s,v26.2s
+
+	////////////////////////////////////////////////////////////////
+	// multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
+
+	adds	x2,x2,#32
+	b.ne	.Long_tail
+
+	dup	v16.2d,v11.d[0]
+	add	v14.2s,v9.2s,v24.2s
+	add	v17.2s,v12.2s,v27.2s
+	add	v15.2s,v10.2s,v25.2s
+	add	v18.2s,v13.2s,v28.2s
+
+.Long_tail:
+	dup	v14.2d,v14.d[0]
+	umull2	v19.2d,v16.4s,v6.4s
+	umull2	v22.2d,v16.4s,v1.4s
+	umull2	v23.2d,v16.4s,v3.4s
+	umull2	v21.2d,v16.4s,v0.4s
+	umull2	v20.2d,v16.4s,v8.4s
+
+	dup	v15.2d,v15.d[0]
+	umlal2	v19.2d,v14.4s,v0.4s
+	umlal2	v21.2d,v14.4s,v3.4s
+	umlal2	v22.2d,v14.4s,v5.4s
+	umlal2	v23.2d,v14.4s,v7.4s
+	umlal2	v20.2d,v14.4s,v1.4s
+
+	dup	v17.2d,v17.d[0]
+	umlal2	v19.2d,v15.4s,v8.4s
+	umlal2	v22.2d,v15.4s,v3.4s
+	umlal2	v21.2d,v15.4s,v1.4s
+	umlal2	v23.2d,v15.4s,v5.4s
+	umlal2	v20.2d,v15.4s,v0.4s
+
+	dup	v18.2d,v18.d[0]
+	umlal2	v22.2d,v17.4s,v0.4s
+	umlal2	v23.2d,v17.4s,v1.4s
+	umlal2	v19.2d,v17.4s,v4.4s
+	umlal2	v20.2d,v17.4s,v6.4s
+	umlal2	v21.2d,v17.4s,v8.4s
+
+	umlal2	v22.2d,v18.4s,v8.4s
+	umlal2	v19.2d,v18.4s,v2.4s
+	umlal2	v23.2d,v18.4s,v0.4s
+	umlal2	v20.2d,v18.4s,v4.4s
+	umlal2	v21.2d,v18.4s,v6.4s
+
+	b.eq	.Lshort_tail
+
+	////////////////////////////////////////////////////////////////
+	// (hash+inp[0:1])*r^4:r^3 and accumulate
+
+	add	v9.2s,v9.2s,v24.2s
+	umlal	v22.2d,v11.2s,v1.2s
+	umlal	v19.2d,v11.2s,v6.2s
+	umlal	v23.2d,v11.2s,v3.2s
+	umlal	v20.2d,v11.2s,v8.2s
+	umlal	v21.2d,v11.2s,v0.2s
+
+	add	v10.2s,v10.2s,v25.2s
+	umlal	v22.2d,v9.2s,v5.2s
+	umlal	v19.2d,v9.2s,v0.2s
+	umlal	v23.2d,v9.2s,v7.2s
+	umlal	v20.2d,v9.2s,v1.2s
+	umlal	v21.2d,v9.2s,v3.2s
+
+	add	v12.2s,v12.2s,v27.2s
+	umlal	v22.2d,v10.2s,v3.2s
+	umlal	v19.2d,v10.2s,v8.2s
+	umlal	v23.2d,v10.2s,v5.2s
+	umlal	v20.2d,v10.2s,v0.2s
+	umlal	v21.2d,v10.2s,v1.2s
+
+	add	v13.2s,v13.2s,v28.2s
+	umlal	v22.2d,v12.2s,v0.2s
+	umlal	v19.2d,v12.2s,v4.2s
+	umlal	v23.2d,v12.2s,v1.2s
+	umlal	v20.2d,v12.2s,v6.2s
+	umlal	v21.2d,v12.2s,v8.2s
+
+	umlal	v22.2d,v13.2s,v8.2s
+	umlal	v19.2d,v13.2s,v2.2s
+	umlal	v23.2d,v13.2s,v0.2s
+	umlal	v20.2d,v13.2s,v4.2s
+	umlal	v21.2d,v13.2s,v6.2s
+
+.Lshort_tail:
+	////////////////////////////////////////////////////////////////
+	// horizontal add
+
+	addp	v22.2d,v22.2d,v22.2d
+	 ldp	d8,d9,[sp,#16]		// meet ABI requirements
+	addp	v19.2d,v19.2d,v19.2d
+	 ldp	d10,d11,[sp,#32]
+	addp	v23.2d,v23.2d,v23.2d
+	 ldp	d12,d13,[sp,#48]
+	addp	v20.2d,v20.2d,v20.2d
+	 ldp	d14,d15,[sp,#64]
+	addp	v21.2d,v21.2d,v21.2d
+	 ldr	x30,[sp,#8]
+	 .inst	0xd50323bf		// autiasp
+
+	////////////////////////////////////////////////////////////////
+	// lazy reduction, but without narrowing
+
+	ushr	v29.2d,v22.2d,#26
+	and	v22.16b,v22.16b,v31.16b
+	 ushr	v30.2d,v19.2d,#26
+	 and	v19.16b,v19.16b,v31.16b
+
+	add	v23.2d,v23.2d,v29.2d	// h3 -> h4
+	 add	v20.2d,v20.2d,v30.2d	// h0 -> h1
+
+	ushr	v29.2d,v23.2d,#26
+	and	v23.16b,v23.16b,v31.16b
+	 ushr	v30.2d,v20.2d,#26
+	 and	v20.16b,v20.16b,v31.16b
+	 add	v21.2d,v21.2d,v30.2d	// h1 -> h2
+
+	add	v19.2d,v19.2d,v29.2d
+	shl	v29.2d,v29.2d,#2
+	 ushr	v30.2d,v21.2d,#26
+	 and	v21.16b,v21.16b,v31.16b
+	add	v19.2d,v19.2d,v29.2d	// h4 -> h0
+	 add	v22.2d,v22.2d,v30.2d	// h2 -> h3
+
+	ushr	v29.2d,v19.2d,#26
+	and	v19.16b,v19.16b,v31.16b
+	 ushr	v30.2d,v22.2d,#26
+	 and	v22.16b,v22.16b,v31.16b
+	add	v20.2d,v20.2d,v29.2d	// h0 -> h1
+	 add	v23.2d,v23.2d,v30.2d	// h3 -> h4
+
+	////////////////////////////////////////////////////////////////
+	// write the result, can be partially reduced
+
+	st4	{v19.s,v20.s,v21.s,v22.s}[0],[x0],#16
+	mov	x4,#1
+	st1	{v23.s}[0],[x0]
+	str	x4,[x0,#8]		// set is_base2_26
+
+	ldr	x29,[sp],#80
+	ret
+.size	poly1305_blocks_neon,.-poly1305_blocks_neon
+
+.align	5
+.Lzeros:
+.long	0,0,0,0,0,0,0,0
+.asciz	"Poly1305 for ARMv8, CRYPTOGAMS by @dot-asm"
+.align	2
+#if !defined(__KERNEL__) && !defined(_WIN64)
+.comm	OPENSSL_armcap_P,4,4
+.hidden	OPENSSL_armcap_P
+#endif
diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c
new file mode 100644
index 000000000000..dd843d0ee83a
--- /dev/null
+++ b/arch/arm64/crypto/poly1305-glue.c
@@ -0,0 +1,237 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * OpenSSL/Cryptogams accelerated Poly1305 transform for arm64
+ *
+ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/poly1305.h>
+#include <crypto/internal/simd.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/jump_label.h>
+#include <linux/module.h>
+
+asmlinkage void poly1305_init_arm64(void *state, const u8 *key);
+asmlinkage void poly1305_blocks(void *state, const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_emit(void *state, __le32 *digest, const u32 *nonce);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key)
+{
+	poly1305_init_arm64(&dctx->h, key);
+	dctx->s[0] = get_unaligned_le32(key + 16);
+	dctx->s[1] = get_unaligned_le32(key + 20);
+	dctx->s[2] = get_unaligned_le32(key + 24);
+	dctx->s[3] = get_unaligned_le32(key + 28);
+	dctx->buflen = 0;
+}
+EXPORT_SYMBOL(poly1305_init_arch);
+
+static int neon_poly1305_init(struct shash_desc *desc)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	dctx->buflen = 0;
+	dctx->rset = 0;
+	dctx->sset = false;
+
+	return 0;
+}
+
+static void neon_poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
+				 u32 len, u32 hibit, bool do_neon)
+{
+	if (unlikely(!dctx->sset)) {
+		if (!dctx->rset) {
+			poly1305_init_arch(dctx, src);
+			src += POLY1305_BLOCK_SIZE;
+			len -= POLY1305_BLOCK_SIZE;
+			dctx->rset = 1;
+		}
+		if (len >= POLY1305_BLOCK_SIZE) {
+			dctx->s[0] = get_unaligned_le32(src +  0);
+			dctx->s[1] = get_unaligned_le32(src +  4);
+			dctx->s[2] = get_unaligned_le32(src +  8);
+			dctx->s[3] = get_unaligned_le32(src + 12);
+			src += POLY1305_BLOCK_SIZE;
+			len -= POLY1305_BLOCK_SIZE;
+			dctx->sset = true;
+		}
+		if (len < POLY1305_BLOCK_SIZE)
+			return;
+	}
+
+	len &= ~(POLY1305_BLOCK_SIZE - 1);
+
+	if (static_branch_likely(&have_neon) && likely(do_neon))
+		poly1305_blocks_neon(&dctx->h, src, len, hibit);
+	else
+		poly1305_blocks(&dctx->h, src, len, hibit);
+}
+
+static void neon_poly1305_do_update(struct poly1305_desc_ctx *dctx,
+				    const u8 *src, u32 len, bool do_neon)
+{
+	if (unlikely(dctx->buflen)) {
+		u32 bytes = min(len, POLY1305_BLOCK_SIZE - dctx->buflen);
+
+		memcpy(dctx->buf + dctx->buflen, src, bytes);
+		src += bytes;
+		len -= bytes;
+		dctx->buflen += bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			neon_poly1305_blocks(dctx, dctx->buf,
+					     POLY1305_BLOCK_SIZE, 1, false);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (likely(len >= POLY1305_BLOCK_SIZE)) {
+		neon_poly1305_blocks(dctx, src, len, 1, do_neon);
+		src += round_down(len, POLY1305_BLOCK_SIZE);
+		len %= POLY1305_BLOCK_SIZE;
+	}
+
+	if (unlikely(len)) {
+		dctx->buflen = len;
+		memcpy(dctx->buf, src, len);
+	}
+}
+
+static int neon_poly1305_update(struct shash_desc *desc,
+				const u8 *src, unsigned int srclen)
+{
+	bool do_neon = crypto_simd_usable() && srclen > 128;
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (static_branch_likely(&have_neon) && do_neon)
+		kernel_neon_begin();
+	neon_poly1305_do_update(dctx, src, srclen, do_neon);
+	if (static_branch_likely(&have_neon) && do_neon)
+		kernel_neon_end();
+	return 0;
+}
+
+void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
+			  unsigned int nbytes)
+{
+	if (unlikely(dctx->buflen)) {
+		u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);
+
+		memcpy(dctx->buf + dctx->buflen, src, bytes);
+		src += bytes;
+		nbytes -= bytes;
+		dctx->buflen += bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 1);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
+		unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);
+
+		if (static_branch_likely(&have_neon) && crypto_simd_usable()) {
+			kernel_neon_begin();
+			poly1305_blocks_neon(&dctx->h, src, len, 1);
+			kernel_neon_end();
+		} else {
+			poly1305_blocks(&dctx->h, src, len, 1);
+		}
+		src += len;
+		nbytes %= POLY1305_BLOCK_SIZE;
+	}
+
+	if (unlikely(nbytes)) {
+		dctx->buflen = nbytes;
+		memcpy(dctx->buf, src, nbytes);
+	}
+}
+EXPORT_SYMBOL(poly1305_update_arch);
+
+void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
+{
+	__le32 digest[4];
+	u64 f = 0;
+
+	if (unlikely(dctx->buflen)) {
+		dctx->buf[dctx->buflen++] = 1;
+		memset(dctx->buf + dctx->buflen, 0,
+		       POLY1305_BLOCK_SIZE - dctx->buflen);
+		poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
+	}
+
+	poly1305_emit(&dctx->h, digest, dctx->s);
+
+	/* mac = (h + s) % (2^128) */
+	f = (f >> 32) + le32_to_cpu(digest[0]);
+	put_unaligned_le32(f, dst);
+	f = (f >> 32) + le32_to_cpu(digest[1]);
+	put_unaligned_le32(f, dst + 4);
+	f = (f >> 32) + le32_to_cpu(digest[2]);
+	put_unaligned_le32(f, dst + 8);
+	f = (f >> 32) + le32_to_cpu(digest[3]);
+	put_unaligned_le32(f, dst + 12);
+
+	*dctx = (struct poly1305_desc_ctx){};
+}
+EXPORT_SYMBOL(poly1305_final_arch);
+
+static int neon_poly1305_final(struct shash_desc *desc, u8 *dst)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (unlikely(!dctx->sset))
+		return -ENOKEY;
+
+	poly1305_final_arch(dctx, dst);
+	return 0;
+}
+
+static struct shash_alg neon_poly1305_alg = {
+	.init			= neon_poly1305_init,
+	.update			= neon_poly1305_update,
+	.final			= neon_poly1305_final,
+	.digestsize		= POLY1305_DIGEST_SIZE,
+	.descsize		= sizeof(struct poly1305_desc_ctx),
+
+	.base.cra_name		= "poly1305",
+	.base.cra_driver_name	= "poly1305-neon",
+	.base.cra_priority	= 200,
+	.base.cra_blocksize	= POLY1305_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+};
+
+static int __init neon_poly1305_mod_init(void)
+{
+	if (!cpu_have_named_feature(ASIMD))
+		return 0;
+
+	static_branch_enable(&have_neon);
+
+	return crypto_register_shash(&neon_poly1305_alg);
+}
+
+static void __exit neon_poly1305_mod_exit(void)
+{
+	if (cpu_have_named_feature(ASIMD))
+		crypto_unregister_shash(&neon_poly1305_alg);
+}
+
+module_init(neon_poly1305_mod_init);
+module_exit(neon_poly1305_mod_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("poly1305");
+MODULE_ALIAS_CRYPTO("poly1305-neon");
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
index c764cc8fb3b6..f68a0e64482a 100644
--- a/arch/arm64/include/asm/asm-uaccess.h
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -58,12 +58,4 @@ alternative_else_nop_endif
 	.endm
 #endif
 
-/*
- * Remove the address tag from a virtual address, if present.
- */
-	.macro	untagged_addr, dst, addr
-	sbfx	\dst, \addr, #0, #56
-	and	\dst, \dst, \addr
-	.endm
-
 #endif
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index e0e2b1946f42..7d9cc5ec4971 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -29,6 +29,18 @@
 						 SB_BARRIER_INSN"nop\n",	\
 						 ARM64_HAS_SB))
 
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+#define pmr_sync()						\
+	do {							\
+		extern struct static_key_false gic_pmr_sync;	\
+								\
+		if (static_branch_unlikely(&gic_pmr_sync))	\
+			dsb(sy);				\
+	} while(0)
+#else
+#define pmr_sync()	do {} while (0)
+#endif
+
 #define mb()		dsb(sy)
 #define rmb()		dsb(ld)
 #define wmb()		dsb(st)
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index 43da6dd29592..806e9dc2a852 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -11,6 +11,7 @@
 #define CTR_L1IP_MASK		3
 #define CTR_DMINLINE_SHIFT	16
 #define CTR_IMINLINE_SHIFT	0
+#define CTR_IMINLINE_MASK	0xf
 #define CTR_ERG_SHIFT		20
 #define CTR_CWG_SHIFT		24
 #define CTR_CWG_MASK		15
@@ -18,7 +19,7 @@
 #define CTR_DIC_SHIFT		29
 
 #define CTR_CACHE_MINLINE_MASK	\
-	(0xf << CTR_DMINLINE_SHIFT | 0xf << CTR_IMINLINE_SHIFT)
+	(0xf << CTR_DMINLINE_SHIFT | CTR_IMINLINE_MASK << CTR_IMINLINE_SHIFT)
 
 #define CTR_L1IP(ctr)		(((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
 
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index ac1dbca3d0cd..b92683871119 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -54,7 +54,9 @@
 #define ARM64_WORKAROUND_1463225		44
 #define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM	45
 #define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM	46
+#define ARM64_WORKAROUND_1542419		47
+#define ARM64_WORKAROUND_1319367		48
 
-#define ARM64_NCAPS				47
+#define ARM64_NCAPS				49
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 9cde5d2e768f..4261d55e8506 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -659,6 +659,20 @@ static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange)
 	default: return CONFIG_ARM64_PA_BITS;
 	}
 }
+
+/* Check whether hardware update of the Access flag is supported */
+static inline bool cpu_has_hw_af(void)
+{
+	u64 mmfr1;
+
+	if (!IS_ENABLED(CONFIG_ARM64_HW_AFDBM))
+		return false;
+
+	mmfr1 = read_cpuid(ID_AA64MMFR1_EL1);
+	return cpuid_feature_extract_unsigned_field(mmfr1,
+						ID_AA64MMFR1_HADBS_SHIFT);
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h
index 063c964af705..72acd2db167f 100644
--- a/arch/arm64/include/asm/daifflags.h
+++ b/arch/arm64/include/asm/daifflags.h
@@ -8,7 +8,9 @@
 #include <linux/irqflags.h>
 
 #include <asm/arch_gicv3.h>
+#include <asm/barrier.h>
 #include <asm/cpufeature.h>
+#include <asm/ptrace.h>
 
 #define DAIF_PROCCTX		0
 #define DAIF_PROCCTX_NOIRQ	PSR_I_BIT
@@ -65,7 +67,7 @@ static inline void local_daif_restore(unsigned long flags)
 
 		if (system_uses_irq_prio_masking()) {
 			gic_write_pmr(GIC_PRIO_IRQON);
-			dsb(sy);
+			pmr_sync();
 		}
 	} else if (system_uses_irq_prio_masking()) {
 		u64 pmr;
@@ -109,4 +111,19 @@ static inline void local_daif_restore(unsigned long flags)
 		trace_hardirqs_off();
 }
 
+/*
+ * Called by synchronous exception handlers to restore the DAIF bits that were
+ * modified by taking an exception.
+ */
+static inline void local_daif_inherit(struct pt_regs *regs)
+{
+	unsigned long flags = regs->pstate & DAIF_MASK;
+
+	/*
+	 * We can't use local_daif_restore(regs->pstate) here as
+	 * system_has_prio_mask_debugging() won't restore the I bit if it can
+	 * use the pmr instead.
+	 */
+	write_sysreg(flags, daif);
+}
 #endif
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index a17393ff6677..4d5f3b5f50cd 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -8,14 +8,15 @@
 #define __ASM_EXCEPTION_H
 
 #include <asm/esr.h>
+#include <asm/kprobes.h>
+#include <asm/ptrace.h>
 
 #include <linux/interrupt.h>
 
-#define __exception	__attribute__((section(".exception.text")))
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 #define __exception_irq_entry	__irq_entry
 #else
-#define __exception_irq_entry	__exception
+#define __exception_irq_entry	__kprobes
 #endif
 
 static inline u32 disr_to_esr(u64 disr)
@@ -31,5 +32,22 @@ static inline u32 disr_to_esr(u64 disr)
 }
 
 asmlinkage void enter_from_user_mode(void);
+void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
+void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
+void do_undefinstr(struct pt_regs *regs);
+asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr);
+void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
+			struct pt_regs *regs);
+void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs);
+void do_sve_acc(unsigned int esr, struct pt_regs *regs);
+void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs);
+void do_sysinstr(unsigned int esr, struct pt_regs *regs);
+void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
+void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr);
+void do_cp15instr(unsigned int esr, struct pt_regs *regs);
+void el0_svc_handler(struct pt_regs *regs);
+void el0_svc_compat_handler(struct pt_regs *regs);
+void do_el0_ia_bp_hardening(unsigned long addr,  unsigned int esr,
+			    struct pt_regs *regs);
 
 #endif	/* __ASM_EXCEPTION_H */
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
index d48667b04c41..91fa4baa1a93 100644
--- a/arch/arm64/include/asm/ftrace.h
+++ b/arch/arm64/include/asm/ftrace.h
@@ -11,9 +11,20 @@
 #include <asm/insn.h>
 
 #define HAVE_FUNCTION_GRAPH_FP_TEST
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+#else
 #define MCOUNT_ADDR		((unsigned long)_mcount)
+#endif
+
+/* The BL at the callsite's adjusted rec->ip */
 #define MCOUNT_INSN_SIZE	AARCH64_INSN_SIZE
 
+#define FTRACE_PLT_IDX		0
+#define FTRACE_REGS_PLT_IDX	1
+#define NR_FTRACE_PLTS		2
+
 /*
  * Currently, gcc tends to save the link register after the local variables
  * on the stack. This causes the max stack tracer to report the function
@@ -44,12 +55,24 @@ extern void return_to_handler(void);
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
 	/*
+	 * Adjust addr to point at the BL in the callsite.
+	 * See ftrace_init_nop() for the callsite sequence.
+	 */
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+		return addr + AARCH64_INSN_SIZE;
+	/*
 	 * addr is the address of the mcount call instruction.
 	 * recordmcount does the necessary offset calculation.
 	 */
 	return addr;
 }
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+struct dyn_ftrace;
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
+#define ftrace_init_nop ftrace_init_nop
+#endif
+
 #define ftrace_return_address(n) return_address(n)
 
 /*
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 39e7780bedd6..bb313dde58a4 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -440,6 +440,9 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
 					 int shift,
 					 enum aarch64_insn_variant variant,
 					 enum aarch64_insn_logic_type type);
+u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst,
+			      enum aarch64_insn_register src,
+			      enum aarch64_insn_variant variant);
 u32 aarch64_insn_gen_logical_immediate(enum aarch64_insn_logic_type type,
 				       enum aarch64_insn_variant variant,
 				       enum aarch64_insn_register Rn,
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index 1a59f0ed1ae3..aa4b6521ef14 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -6,6 +6,7 @@
 #define __ASM_IRQFLAGS_H
 
 #include <asm/alternative.h>
+#include <asm/barrier.h>
 #include <asm/ptrace.h>
 #include <asm/sysreg.h>
 
@@ -34,14 +35,14 @@ static inline void arch_local_irq_enable(void)
 	}
 
 	asm volatile(ALTERNATIVE(
-		"msr	daifclr, #2		// arch_local_irq_enable\n"
-		"nop",
-		__msr_s(SYS_ICC_PMR_EL1, "%0")
-		"dsb	sy",
+		"msr	daifclr, #2		// arch_local_irq_enable",
+		__msr_s(SYS_ICC_PMR_EL1, "%0"),
 		ARM64_HAS_IRQ_PRIO_MASKING)
 		:
 		: "r" ((unsigned long) GIC_PRIO_IRQON)
 		: "memory");
+
+	pmr_sync();
 }
 
 static inline void arch_local_irq_disable(void)
@@ -116,14 +117,14 @@ static inline unsigned long arch_local_irq_save(void)
 static inline void arch_local_irq_restore(unsigned long flags)
 {
 	asm volatile(ALTERNATIVE(
-			"msr	daif, %0\n"
-			"nop",
-			__msr_s(SYS_ICC_PMR_EL1, "%0")
-			"dsb	sy",
-			ARM64_HAS_IRQ_PRIO_MASKING)
+		"msr	daif, %0",
+		__msr_s(SYS_ICC_PMR_EL1, "%0"),
+		ARM64_HAS_IRQ_PRIO_MASKING)
 		:
 		: "r" (flags)
 		: "memory");
+
+	pmr_sync();
 }
 
 #endif /* __ASM_IRQFLAGS_H */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index ddf9d762ac62..6e5d839f42b5 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -61,7 +61,6 @@
  * RW:		64bit by default, can be overridden for 32bit VMs
  * TAC:		Trap ACTLR
  * TSC:		Trap SMC
- * TVM:		Trap VM ops (until M+C set in SCTLR_EL1)
  * TSW:		Trap cache operations by set/way
  * TWE:		Trap WFE
  * TWI:		Trap WFI
@@ -74,7 +73,7 @@
  * SWIO:	Turn set/way invalidates into set/way clean+invalidate
  */
 #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
-			 HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \
+			 HCR_BSU_IS | HCR_FB | HCR_TAC | \
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
 			 HCR_FMO | HCR_IMO)
 #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index d69c1efc63e7..5efe5ca8fecf 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -53,8 +53,18 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 		/* trap error record accesses */
 		vcpu->arch.hcr_el2 |= HCR_TERR;
 	}
-	if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB))
+
+	if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) {
 		vcpu->arch.hcr_el2 |= HCR_FWB;
+	} else {
+		/*
+		 * For non-FWB CPUs, we trap VM ops (HCR_EL2.TVM) until M+C
+		 * get set in SCTLR_EL1 such that we can detect when the guest
+		 * MMU gets turned on and do the necessary cache maintenance
+		 * then.
+		 */
+		vcpu->arch.hcr_el2 |= HCR_TVM;
+	}
 
 	if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
 		vcpu->arch.hcr_el2 &= ~HCR_RW;
@@ -77,14 +87,19 @@ static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu)
 	return (unsigned long *)&vcpu->arch.hcr_el2;
 }
 
-static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr_el2 &= ~HCR_TWE;
+	if (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count))
+		vcpu->arch.hcr_el2 &= ~HCR_TWI;
+	else
+		vcpu->arch.hcr_el2 |= HCR_TWI;
 }
 
-static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr_el2 |= HCR_TWE;
+	vcpu->arch.hcr_el2 |= HCR_TWI;
 }
 
 static inline void vcpu_ptrauth_enable(struct kvm_vcpu *vcpu)
@@ -258,6 +273,11 @@ static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu)
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV);
 }
 
+static inline unsigned long kvm_vcpu_dabt_iss_nisv_sanitized(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & (ESR_ELx_CM | ESR_ELx_WNR | ESR_ELx_FSC);
+}
+
 static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE);
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f656169db8c3..c61260cf63c5 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -44,6 +44,7 @@
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
 #define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
+#define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
 
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
@@ -83,6 +84,14 @@ struct kvm_arch {
 
 	/* Mandated version of PSCI */
 	u32 psci_version;
+
+	/*
+	 * If we encounter a data abort without valid instruction syndrome
+	 * information, report this to user space.  User space can (and
+	 * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is
+	 * supported.
+	 */
+	bool return_nisv_io_abort_to_user;
 };
 
 #define KVM_NR_MEM_OBJS     40
@@ -338,6 +347,13 @@ struct kvm_vcpu_arch {
 	/* True when deferrable sysregs are loaded on the physical CPU,
 	 * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */
 	bool sysregs_loaded_on_cpu;
+
+	/* Guest PV state */
+	struct {
+		u64 steal;
+		u64 last_steal;
+		gpa_t base;
+	} steal;
 };
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
@@ -478,6 +494,27 @@ void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
+long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu);
+gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);
+void kvm_update_stolen_time(struct kvm_vcpu *vcpu);
+
+int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+
+static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
+{
+	vcpu_arch->steal.base = GPA_INVALID;
+}
+
+static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch)
+{
+	return (vcpu_arch->steal.base != GPA_INVALID);
+}
+
 void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome);
 
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
@@ -600,8 +637,7 @@ static inline void kvm_arm_vhe_guest_enter(void)
 	 * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a
 	 * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU.
 	 */
-	if (system_uses_irq_prio_masking())
-		dsb(sy);
+	pmr_sync();
 }
 
 static inline void kvm_arm_vhe_guest_exit(void)
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index c23c47360664..a4f9ca5479b0 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -69,12 +69,6 @@
 #define KERNEL_START		_text
 #define KERNEL_END		_end
 
-#ifdef CONFIG_ARM64_VA_BITS_52
-#define MAX_USER_VA_BITS	52
-#else
-#define MAX_USER_VA_BITS	VA_BITS
-#endif
-
 /*
  * Generic and tag-based KASAN require 1/8th and 1/16th of the kernel virtual
  * address space for the shadow region respectively. They can bloat the stack
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index f80e13cbf8ec..1e93de68c044 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -21,7 +21,7 @@ struct mod_arch_specific {
 	struct mod_plt_sec	init;
 
 	/* for CONFIG_DYNAMIC_FTRACE */
-	struct plt_entry 	*ftrace_trampoline;
+	struct plt_entry	*ftrace_trampolines;
 };
 #endif
 
diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h
index 799d9dd6f7cc..cf3a0fd7c1a7 100644
--- a/arch/arm64/include/asm/paravirt.h
+++ b/arch/arm64/include/asm/paravirt.h
@@ -21,6 +21,13 @@ static inline u64 paravirt_steal_clock(int cpu)
 {
 	return pv_ops.time.steal_clock(cpu);
 }
-#endif
+
+int __init pv_time_init(void);
+
+#else
+
+#define pv_time_init() do {} while (0)
+
+#endif // CONFIG_PARAVIRT
 
 #endif
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 3df60f97da1f..d9fbd433cc17 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -69,7 +69,7 @@
 #define PGDIR_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS)
 #define PGDIR_SIZE		(_AC(1, UL) << PGDIR_SHIFT)
 #define PGDIR_MASK		(~(PGDIR_SIZE-1))
-#define PTRS_PER_PGD		(1 << (MAX_USER_VA_BITS - PGDIR_SHIFT))
+#define PTRS_PER_PGD		(1 << (VA_BITS - PGDIR_SHIFT))
 
 /*
  * Section address mask and size definitions.
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 565aa45ef134..5d15b4735a0e 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -17,7 +17,7 @@
  * VMALLOC range.
  *
  * VMALLOC_START: beginning of the kernel vmalloc space
- * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space
+ * VMALLOC_END: extends to the available space below vmemmap, PCI I/O space
  *	and fixed mappings
  */
 #define VMALLOC_START		(MODULES_END)
@@ -865,6 +865,20 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 #define phys_to_ttbr(addr)	(addr)
 #endif
 
+/*
+ * On arm64 without hardware Access Flag, copying from user will fail because
+ * the pte is old and cannot be marked young. So we always end up with zeroed
+ * page after fork() + CoW for pfn mappings. We don't always have a
+ * hardware-managed access flag on arm64.
+ */
+static inline bool arch_faults_on_old_pte(void)
+{
+	WARN_ON(preemptible());
+
+	return !cpu_has_hw_af();
+}
+#define arch_faults_on_old_pte arch_faults_on_old_pte
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_PGTABLE_H */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 5623685c7d13..5ba63204d078 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -9,7 +9,7 @@
 #define __ASM_PROCESSOR_H
 
 #define KERNEL_DS		UL(-1)
-#define USER_DS			((UL(1) << MAX_USER_VA_BITS) - 1)
+#define USER_DS			((UL(1) << VA_BITS) - 1)
 
 /*
  * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is
@@ -26,10 +26,12 @@
 #include <linux/init.h>
 #include <linux/stddef.h>
 #include <linux/string.h>
+#include <linux/thread_info.h>
 
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
 #include <asm/hw_breakpoint.h>
+#include <asm/kasan.h>
 #include <asm/lse.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pointer_auth.h>
@@ -214,6 +216,18 @@ static inline void start_thread(struct pt_regs *regs, unsigned long pc,
 	regs->sp = sp;
 }
 
+static inline bool is_ttbr0_addr(unsigned long addr)
+{
+	/* entry assembly clears tags for TTBR0 addrs */
+	return addr < TASK_SIZE;
+}
+
+static inline bool is_ttbr1_addr(unsigned long addr)
+{
+	/* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */
+	return arch_kasan_reset_tag(addr) >= PAGE_OFFSET;
+}
+
 #ifdef CONFIG_COMPAT
 static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc,
 				       unsigned long sp)
diff --git a/arch/arm64/include/asm/pvclock-abi.h b/arch/arm64/include/asm/pvclock-abi.h
new file mode 100644
index 000000000000..c4f1c0a0789c
--- /dev/null
+++ b/arch/arm64/include/asm/pvclock-abi.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 Arm Ltd. */
+
+#ifndef __ASM_PVCLOCK_ABI_H
+#define __ASM_PVCLOCK_ABI_H
+
+/* The below structure is defined in ARM DEN0057A */
+
+struct pvclock_vcpu_stolen_time {
+	__le32 revision;
+	__le32 attributes;
+	__le64 stolen_time;
+	/* Structure must be 64 byte aligned, pad to that size */
+	u8 padding[48];
+} __packed;
+
+#endif
diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h
index 06d880b3526c..b383b4802a7b 100644
--- a/arch/arm64/include/asm/syscall_wrapper.h
+++ b/arch/arm64/include/asm/syscall_wrapper.h
@@ -66,24 +66,18 @@ struct pt_regs;
 	}									\
 	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 
-#ifndef SYSCALL_DEFINE0
 #define SYSCALL_DEFINE0(sname)							\
 	SYSCALL_METADATA(_##sname, 0);						\
 	asmlinkage long __arm64_sys_##sname(const struct pt_regs *__unused);	\
 	ALLOW_ERROR_INJECTION(__arm64_sys_##sname, ERRNO);			\
 	asmlinkage long __arm64_sys_##sname(const struct pt_regs *__unused)
-#endif
 
-#ifndef COND_SYSCALL
 #define COND_SYSCALL(name)							\
 	asmlinkage long __weak __arm64_sys_##name(const struct pt_regs *regs)	\
 	{									\
 		return sys_ni_syscall();					\
 	}
-#endif
 
-#ifndef SYS_NI
 #define SYS_NI(name) SYSCALL_ALIAS(__arm64_sys_##name, sys_ni_posix_timers);
-#endif
 
 #endif /* __ASM_SYSCALL_WRAPPER_H */
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 59690613ac31..cee5928e1b7d 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -42,16 +42,6 @@ static inline int __in_irqentry_text(unsigned long ptr)
 	       ptr < (unsigned long)&__irqentry_text_end;
 }
 
-static inline int in_exception_text(unsigned long ptr)
-{
-	int in;
-
-	in = ptr >= (unsigned long)&__exception_text_start &&
-	     ptr < (unsigned long)&__exception_text_end;
-
-	return in ? : __in_irqentry_text(ptr);
-}
-
 static inline int in_entry_text(unsigned long ptr)
 {
 	return ptr >= (unsigned long)&__entry_text_start &&
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 67c21f9bdbad..820e5751ada7 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -164,8 +164,9 @@ struct kvm_vcpu_events {
 	struct {
 		__u8 serror_pending;
 		__u8 serror_has_esr;
+		__u8 ext_dabt_pending;
 		/* Align it to 8 bytes */
-		__u8 pad[6];
+		__u8 pad[5];
 		__u64 serror_esr;
 	} exception;
 	__u32 reserved[12];
@@ -323,6 +324,8 @@ struct kvm_vcpu_events {
 #define KVM_ARM_VCPU_TIMER_CTRL		1
 #define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER		0
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1
+#define KVM_ARM_VCPU_PVTIME_CTRL	2
+#define   KVM_ARM_VCPU_PVTIME_IPA	0
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_VCPU2_SHIFT		28
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 478491f07b4f..fc6488660f64 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -13,9 +13,9 @@ CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE)
 
 # Object file lists.
 obj-y			:= debug-monitors.o entry.o irq.o fpsimd.o		\
-			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
-			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
-			   hyp-stub.o psci.o cpu_ops.o insn.o	\
+			   entry-common.o entry-fpsimd.o process.o ptrace.o	\
+			   setup.o signal.o sys.o stacktrace.o time.o traps.o	\
+			   io.o vdso.o hyp-stub.o psci.o cpu_ops.o insn.o	\
 			   return_address.o cpuinfo.o cpu_errata.o		\
 			   cpufeature.o alternative.o cacheinfo.o		\
 			   smp.o smp_spin_table.o topology.o smccc-call.o	\
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 214685760e1c..a5bdce8af65b 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -56,6 +56,7 @@ int main(void)
   DEFINE(S_X24,			offsetof(struct pt_regs, regs[24]));
   DEFINE(S_X26,			offsetof(struct pt_regs, regs[26]));
   DEFINE(S_X28,			offsetof(struct pt_regs, regs[28]));
+  DEFINE(S_FP,			offsetof(struct pt_regs, regs[29]));
   DEFINE(S_LR,			offsetof(struct pt_regs, regs[30]));
   DEFINE(S_SP,			offsetof(struct pt_regs, sp));
   DEFINE(S_PSTATE,		offsetof(struct pt_regs, pstate));
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 93f34b4eca25..6a09ca7644ea 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -6,7 +6,6 @@
  */
 
 #include <linux/arm-smccc.h>
-#include <linux/psci.h>
 #include <linux/types.h>
 #include <linux/cpu.h>
 #include <asm/cpu.h>
@@ -88,13 +87,21 @@ has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry,
 }
 
 static void
-cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
+cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *cap)
 {
 	u64 mask = arm64_ftr_reg_ctrel0.strict_mask;
+	bool enable_uct_trap = false;
 
 	/* Trap CTR_EL0 access on this CPU, only if it has a mismatch */
 	if ((read_cpuid_cachetype() & mask) !=
 	    (arm64_ftr_reg_ctrel0.sys_val & mask))
+		enable_uct_trap = true;
+
+	/* ... or if the system is affected by an erratum */
+	if (cap->capability == ARM64_WORKAROUND_1542419)
+		enable_uct_trap = true;
+
+	if (enable_uct_trap)
 		sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
 }
 
@@ -167,9 +174,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 }
 #endif	/* CONFIG_KVM_INDIRECT_VECTORS */
 
-#include <uapi/linux/psci.h>
 #include <linux/arm-smccc.h>
-#include <linux/psci.h>
 
 static void call_smc_arch_workaround_1(void)
 {
@@ -213,43 +218,31 @@ static int detect_harden_bp_fw(void)
 	struct arm_smccc_res res;
 	u32 midr = read_cpuid_id();
 
-	if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
+	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+			     ARM_SMCCC_ARCH_WORKAROUND_1, &res);
+
+	switch ((int)res.a0) {
+	case 1:
+		/* Firmware says we're just fine */
+		return 0;
+	case 0:
+		break;
+	default:
 		return -1;
+	}
 
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
-		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		switch ((int)res.a0) {
-		case 1:
-			/* Firmware says we're just fine */
-			return 0;
-		case 0:
-			cb = call_hvc_arch_workaround_1;
-			/* This is a guest, no need to patch KVM vectors */
-			smccc_start = NULL;
-			smccc_end = NULL;
-			break;
-		default:
-			return -1;
-		}
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
+		cb = call_hvc_arch_workaround_1;
+		/* This is a guest, no need to patch KVM vectors */
+		smccc_start = NULL;
+		smccc_end = NULL;
 		break;
 
-	case PSCI_CONDUIT_SMC:
-		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		switch ((int)res.a0) {
-		case 1:
-			/* Firmware says we're just fine */
-			return 0;
-		case 0:
-			cb = call_smc_arch_workaround_1;
-			smccc_start = __smccc_workaround_1_smc_start;
-			smccc_end = __smccc_workaround_1_smc_end;
-			break;
-		default:
-			return -1;
-		}
+	case SMCCC_CONDUIT_SMC:
+		cb = call_smc_arch_workaround_1;
+		smccc_start = __smccc_workaround_1_smc_start;
+		smccc_end = __smccc_workaround_1_smc_end;
 		break;
 
 	default:
@@ -309,11 +302,11 @@ void __init arm64_update_smccc_conduit(struct alt_instr *alt,
 
 	BUG_ON(nr_inst != 1);
 
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
 		insn = aarch64_insn_get_hvc_value();
 		break;
-	case PSCI_CONDUIT_SMC:
+	case SMCCC_CONDUIT_SMC:
 		insn = aarch64_insn_get_smc_value();
 		break;
 	default:
@@ -339,6 +332,8 @@ void __init arm64_enable_wa2_handling(struct alt_instr *alt,
 
 void arm64_set_ssbd_mitigation(bool state)
 {
+	int conduit;
+
 	if (!IS_ENABLED(CONFIG_ARM64_SSBD)) {
 		pr_info_once("SSBD disabled by kernel configuration\n");
 		return;
@@ -352,19 +347,10 @@ void arm64_set_ssbd_mitigation(bool state)
 		return;
 	}
 
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
-		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
-		break;
-
-	case PSCI_CONDUIT_SMC:
-		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
-		break;
+	conduit = arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_WORKAROUND_2, state,
+				       NULL);
 
-	default:
-		WARN_ON_ONCE(1);
-		break;
-	}
+	WARN_ON_ONCE(conduit == SMCCC_CONDUIT_NONE);
 }
 
 static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
@@ -374,6 +360,7 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 	bool required = true;
 	s32 val;
 	bool this_cpu_safe = false;
+	int conduit;
 
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
 
@@ -391,25 +378,10 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 		goto out_printmsg;
 	}
 
-	if (psci_ops.smccc_version == SMCCC_VERSION_1_0) {
-		ssbd_state = ARM64_SSBD_UNKNOWN;
-		if (!this_cpu_safe)
-			__ssb_safe = false;
-		return false;
-	}
-
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
-		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-				  ARM_SMCCC_ARCH_WORKAROUND_2, &res);
-		break;
-
-	case PSCI_CONDUIT_SMC:
-		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-				  ARM_SMCCC_ARCH_WORKAROUND_2, &res);
-		break;
+	conduit = arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+				       ARM_SMCCC_ARCH_WORKAROUND_2, &res);
 
-	default:
+	if (conduit == SMCCC_CONDUIT_NONE) {
 		ssbd_state = ARM64_SSBD_UNKNOWN;
 		if (!this_cpu_safe)
 			__ssb_safe = false;
@@ -650,9 +622,21 @@ needs_tx2_tvm_workaround(const struct arm64_cpu_capabilities *entry,
 	return false;
 }
 
-#ifdef CONFIG_HARDEN_EL2_VECTORS
+static bool __maybe_unused
+has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
+				int scope)
+{
+	u32 midr = read_cpuid_id();
+	bool has_dic = read_cpuid_cachetype() & BIT(CTR_DIC_SHIFT);
+	const struct midr_range range = MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1);
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+	return is_midr_in_range(midr, &range) && has_dic;
+}
+
+#if defined(CONFIG_HARDEN_EL2_VECTORS) || defined(CONFIG_ARM64_ERRATUM_1319367)
 
-static const struct midr_range arm64_harden_el2_vectors[] = {
+static const struct midr_range ca57_a72[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
 	{},
@@ -881,7 +865,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	{
 		.desc = "EL2 vector hardening",
 		.capability = ARM64_HARDEN_EL2_VECTORS,
-		ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors),
+		ERRATA_MIDR_RANGE_LIST(ca57_a72),
 	},
 #endif
 	{
@@ -927,6 +911,23 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_RANGE_LIST(tx2_family_cpus),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_1542419
+	{
+		/* we depend on the firmware portion for correctness */
+		.desc = "ARM erratum 1542419 (kernel portion)",
+		.capability = ARM64_WORKAROUND_1542419,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = has_neoverse_n1_erratum_1542419,
+		.cpu_enable = cpu_enable_trap_ctr_access,
+	},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_1319367
+	{
+		.desc = "ARM erratum 1319367",
+		.capability = ARM64_WORKAROUND_1319367,
+		ERRATA_MIDR_RANGE_LIST(ca57_a72),
+	},
+#endif
 	{
 	}
 };
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 80f459ad0190..04cf64e9f0c9 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -982,6 +982,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
 		MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
+		MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
 		{ /* sentinel */ }
 	};
 	char const *str = "kpti command line option";
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 05933c065732..56bba746da1c 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -329,7 +329,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_cntfrq = arch_timer_get_cntfrq();
 	/*
 	 * Use the effective value of the CTR_EL0 than the raw value
-	 * exposed by the CPU. CTR_E0.IDC field value must be interpreted
+	 * exposed by the CPU. CTR_EL0.IDC field value must be interpreted
 	 * with the CLIDR_EL1 fields to avoid triggering false warnings
 	 * when there is a mismatch across the CPUs. Keep track of the
 	 * effective value of the CTR_EL0 in our internal records for
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
new file mode 100644
index 000000000000..5dce5e56995a
--- /dev/null
+++ b/arch/arm64/kernel/entry-common.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Exception handling code
+ *
+ * Copyright (C) 2019 ARM Ltd.
+ */
+
+#include <linux/context_tracking.h>
+#include <linux/ptrace.h>
+#include <linux/thread_info.h>
+
+#include <asm/cpufeature.h>
+#include <asm/daifflags.h>
+#include <asm/esr.h>
+#include <asm/exception.h>
+#include <asm/kprobes.h>
+#include <asm/mmu.h>
+#include <asm/sysreg.h>
+
+static void notrace el1_abort(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	local_daif_inherit(regs);
+	far = untagged_addr(far);
+	do_mem_abort(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el1_abort);
+
+static void notrace el1_pc(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	local_daif_inherit(regs);
+	do_sp_pc_abort(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el1_pc);
+
+static void el1_undef(struct pt_regs *regs)
+{
+	local_daif_inherit(regs);
+	do_undefinstr(regs);
+}
+NOKPROBE_SYMBOL(el1_undef);
+
+static void el1_inv(struct pt_regs *regs, unsigned long esr)
+{
+	local_daif_inherit(regs);
+	bad_mode(regs, 0, esr);
+}
+NOKPROBE_SYMBOL(el1_inv);
+
+static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	/*
+	 * The CPU masked interrupts, and we are leaving them masked during
+	 * do_debug_exception(). Update PMR as if we had called
+	 * local_mask_daif().
+	 */
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
+	do_debug_exception(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el1_dbg);
+
+asmlinkage void notrace el1_sync_handler(struct pt_regs *regs)
+{
+	unsigned long esr = read_sysreg(esr_el1);
+
+	switch (ESR_ELx_EC(esr)) {
+	case ESR_ELx_EC_DABT_CUR:
+	case ESR_ELx_EC_IABT_CUR:
+		el1_abort(regs, esr);
+		break;
+	/*
+	 * We don't handle ESR_ELx_EC_SP_ALIGN, since we will have hit a
+	 * recursive exception when trying to push the initial pt_regs.
+	 */
+	case ESR_ELx_EC_PC_ALIGN:
+		el1_pc(regs, esr);
+		break;
+	case ESR_ELx_EC_SYS64:
+	case ESR_ELx_EC_UNKNOWN:
+		el1_undef(regs);
+		break;
+	case ESR_ELx_EC_BREAKPT_CUR:
+	case ESR_ELx_EC_SOFTSTP_CUR:
+	case ESR_ELx_EC_WATCHPT_CUR:
+	case ESR_ELx_EC_BRK64:
+		el1_dbg(regs, esr);
+		break;
+	default:
+		el1_inv(regs, esr);
+	};
+}
+NOKPROBE_SYMBOL(el1_sync_handler);
+
+static void notrace el0_da(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	far = untagged_addr(far);
+	do_mem_abort(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el0_da);
+
+static void notrace el0_ia(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	/*
+	 * We've taken an instruction abort from userspace and not yet
+	 * re-enabled IRQs. If the address is a kernel address, apply
+	 * BP hardening prior to enabling IRQs and pre-emption.
+	 */
+	if (!is_ttbr0_addr(far))
+		arm64_apply_bp_hardening();
+
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_mem_abort(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el0_ia);
+
+static void notrace el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_fpsimd_acc(esr, regs);
+}
+NOKPROBE_SYMBOL(el0_fpsimd_acc);
+
+static void notrace el0_sve_acc(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_sve_acc(esr, regs);
+}
+NOKPROBE_SYMBOL(el0_sve_acc);
+
+static void notrace el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_fpsimd_exc(esr, regs);
+}
+NOKPROBE_SYMBOL(el0_fpsimd_exc);
+
+static void notrace el0_sys(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_sysinstr(esr, regs);
+}
+NOKPROBE_SYMBOL(el0_sys);
+
+static void notrace el0_pc(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	if (!is_ttbr0_addr(instruction_pointer(regs)))
+		arm64_apply_bp_hardening();
+
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_sp_pc_abort(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el0_pc);
+
+static void notrace el0_sp(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX_NOIRQ);
+	do_sp_pc_abort(regs->sp, esr, regs);
+}
+NOKPROBE_SYMBOL(el0_sp);
+
+static void notrace el0_undef(struct pt_regs *regs)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_undefinstr(regs);
+}
+NOKPROBE_SYMBOL(el0_undef);
+
+static void notrace el0_inv(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	bad_el0_sync(regs, 0, esr);
+}
+NOKPROBE_SYMBOL(el0_inv);
+
+static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr)
+{
+	/* Only watchpoints write FAR_EL1, otherwise its UNKNOWN */
+	unsigned long far = read_sysreg(far_el1);
+
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
+	user_exit_irqoff();
+	do_debug_exception(far, esr, regs);
+	local_daif_restore(DAIF_PROCCTX_NOIRQ);
+}
+NOKPROBE_SYMBOL(el0_dbg);
+
+static void notrace el0_svc(struct pt_regs *regs)
+{
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
+	el0_svc_handler(regs);
+}
+NOKPROBE_SYMBOL(el0_svc);
+
+asmlinkage void notrace el0_sync_handler(struct pt_regs *regs)
+{
+	unsigned long esr = read_sysreg(esr_el1);
+
+	switch (ESR_ELx_EC(esr)) {
+	case ESR_ELx_EC_SVC64:
+		el0_svc(regs);
+		break;
+	case ESR_ELx_EC_DABT_LOW:
+		el0_da(regs, esr);
+		break;
+	case ESR_ELx_EC_IABT_LOW:
+		el0_ia(regs, esr);
+		break;
+	case ESR_ELx_EC_FP_ASIMD:
+		el0_fpsimd_acc(regs, esr);
+		break;
+	case ESR_ELx_EC_SVE:
+		el0_sve_acc(regs, esr);
+		break;
+	case ESR_ELx_EC_FP_EXC64:
+		el0_fpsimd_exc(regs, esr);
+		break;
+	case ESR_ELx_EC_SYS64:
+	case ESR_ELx_EC_WFx:
+		el0_sys(regs, esr);
+		break;
+	case ESR_ELx_EC_SP_ALIGN:
+		el0_sp(regs, esr);
+		break;
+	case ESR_ELx_EC_PC_ALIGN:
+		el0_pc(regs, esr);
+		break;
+	case ESR_ELx_EC_UNKNOWN:
+		el0_undef(regs);
+		break;
+	case ESR_ELx_EC_BREAKPT_LOW:
+	case ESR_ELx_EC_SOFTSTP_LOW:
+	case ESR_ELx_EC_WATCHPT_LOW:
+	case ESR_ELx_EC_BRK64:
+		el0_dbg(regs, esr);
+		break;
+	default:
+		el0_inv(regs, esr);
+	}
+}
+NOKPROBE_SYMBOL(el0_sync_handler);
+
+#ifdef CONFIG_COMPAT
+static void notrace el0_cp15(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_cp15instr(esr, regs);
+}
+NOKPROBE_SYMBOL(el0_cp15);
+
+static void notrace el0_svc_compat(struct pt_regs *regs)
+{
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
+	el0_svc_compat_handler(regs);
+}
+NOKPROBE_SYMBOL(el0_svc_compat);
+
+asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs)
+{
+	unsigned long esr = read_sysreg(esr_el1);
+
+	switch (ESR_ELx_EC(esr)) {
+	case ESR_ELx_EC_SVC32:
+		el0_svc_compat(regs);
+		break;
+	case ESR_ELx_EC_DABT_LOW:
+		el0_da(regs, esr);
+		break;
+	case ESR_ELx_EC_IABT_LOW:
+		el0_ia(regs, esr);
+		break;
+	case ESR_ELx_EC_FP_ASIMD:
+		el0_fpsimd_acc(regs, esr);
+		break;
+	case ESR_ELx_EC_FP_EXC32:
+		el0_fpsimd_exc(regs, esr);
+		break;
+	case ESR_ELx_EC_PC_ALIGN:
+		el0_pc(regs, esr);
+		break;
+	case ESR_ELx_EC_UNKNOWN:
+	case ESR_ELx_EC_CP14_MR:
+	case ESR_ELx_EC_CP14_LS:
+	case ESR_ELx_EC_CP14_64:
+		el0_undef(regs);
+		break;
+	case ESR_ELx_EC_CP15_32:
+	case ESR_ELx_EC_CP15_64:
+		el0_cp15(regs, esr);
+		break;
+	case ESR_ELx_EC_BREAKPT_LOW:
+	case ESR_ELx_EC_SOFTSTP_LOW:
+	case ESR_ELx_EC_WATCHPT_LOW:
+	case ESR_ELx_EC_BKPT32:
+		el0_dbg(regs, esr);
+		break;
+	default:
+		el0_inv(regs, esr);
+	}
+}
+NOKPROBE_SYMBOL(el0_sync_compat_handler);
+#endif /* CONFIG_COMPAT */
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 33d003d80121..4fe1514fcbfd 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -7,10 +7,137 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/asm-offsets.h>
 #include <asm/assembler.h>
 #include <asm/ftrace.h>
 #include <asm/insn.h>
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+/*
+ * Due to -fpatchable-function-entry=2, the compiler has placed two NOPs before
+ * the regular function prologue. For an enabled callsite, ftrace_init_nop() and
+ * ftrace_make_call() have patched those NOPs to:
+ *
+ * 	MOV	X9, LR
+ * 	BL	<entry>
+ *
+ * ... where <entry> is either ftrace_caller or ftrace_regs_caller.
+ *
+ * Each instrumented function follows the AAPCS, so here x0-x8 and x19-x30 are
+ * live, and x9-x18 are safe to clobber.
+ *
+ * We save the callsite's context into a pt_regs before invoking any ftrace
+ * callbacks. So that we can get a sensible backtrace, we create a stack record
+ * for the callsite and the ftrace entry assembly. This is not sufficient for
+ * reliable stacktrace: until we create the callsite stack record, its caller
+ * is missing from the LR and existing chain of frame records.
+ */
+	.macro  ftrace_regs_entry, allregs=0
+	/* Make room for pt_regs, plus a callee frame */
+	sub	sp, sp, #(S_FRAME_SIZE + 16)
+
+	/* Save function arguments (and x9 for simplicity) */
+	stp	x0, x1, [sp, #S_X0]
+	stp	x2, x3, [sp, #S_X2]
+	stp	x4, x5, [sp, #S_X4]
+	stp	x6, x7, [sp, #S_X6]
+	stp	x8, x9, [sp, #S_X8]
+
+	/* Optionally save the callee-saved registers, always save the FP */
+	.if \allregs == 1
+	stp	x10, x11, [sp, #S_X10]
+	stp	x12, x13, [sp, #S_X12]
+	stp	x14, x15, [sp, #S_X14]
+	stp	x16, x17, [sp, #S_X16]
+	stp	x18, x19, [sp, #S_X18]
+	stp	x20, x21, [sp, #S_X20]
+	stp	x22, x23, [sp, #S_X22]
+	stp	x24, x25, [sp, #S_X24]
+	stp	x26, x27, [sp, #S_X26]
+	stp	x28, x29, [sp, #S_X28]
+	.else
+	str	x29, [sp, #S_FP]
+	.endif
+
+	/* Save the callsite's SP and LR */
+	add	x10, sp, #(S_FRAME_SIZE + 16)
+	stp	x9, x10, [sp, #S_LR]
+
+	/* Save the PC after the ftrace callsite */
+	str	x30, [sp, #S_PC]
+
+	/* Create a frame record for the callsite above pt_regs */
+	stp	x29, x9, [sp, #S_FRAME_SIZE]
+	add	x29, sp, #S_FRAME_SIZE
+
+	/* Create our frame record within pt_regs. */
+	stp	x29, x30, [sp, #S_STACKFRAME]
+	add	x29, sp, #S_STACKFRAME
+	.endm
+
+ENTRY(ftrace_regs_caller)
+	ftrace_regs_entry	1
+	b	ftrace_common
+ENDPROC(ftrace_regs_caller)
+
+ENTRY(ftrace_caller)
+	ftrace_regs_entry	0
+	b	ftrace_common
+ENDPROC(ftrace_caller)
+
+ENTRY(ftrace_common)
+	sub	x0, x30, #AARCH64_INSN_SIZE	// ip (callsite's BL insn)
+	mov	x1, x9				// parent_ip (callsite's LR)
+	ldr_l	x2, function_trace_op		// op
+	mov	x3, sp				// regs
+
+GLOBAL(ftrace_call)
+	bl	ftrace_stub
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+GLOBAL(ftrace_graph_call)		// ftrace_graph_caller();
+	nop				// If enabled, this will be replaced
+					// "b ftrace_graph_caller"
+#endif
+
+/*
+ * At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved
+ * x19-x29 per the AAPCS, and we created frame records upon entry, so we need
+ * to restore x0-x8, x29, and x30.
+ */
+ftrace_common_return:
+	/* Restore function arguments */
+	ldp	x0, x1, [sp]
+	ldp	x2, x3, [sp, #S_X2]
+	ldp	x4, x5, [sp, #S_X4]
+	ldp	x6, x7, [sp, #S_X6]
+	ldr	x8, [sp, #S_X8]
+
+	/* Restore the callsite's FP, LR, PC */
+	ldr	x29, [sp, #S_FP]
+	ldr	x30, [sp, #S_LR]
+	ldr	x9, [sp, #S_PC]
+
+	/* Restore the callsite's SP */
+	add	sp, sp, #S_FRAME_SIZE + 16
+
+	ret	x9
+ENDPROC(ftrace_common)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+	ldr	x0, [sp, #S_PC]
+	sub	x0, x0, #AARCH64_INSN_SIZE	// ip (callsite's BL insn)
+	add	x1, sp, #S_LR			// parent_ip (callsite's LR)
+	ldr	x2, [sp, #S_FRAME_SIZE]	   	// parent fp (callsite's FP)
+	bl	prepare_ftrace_return
+	b	ftrace_common_return
+ENDPROC(ftrace_graph_caller)
+#else
+#endif
+
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
 /*
  * Gcc with -pg will put the following code in the beginning of each function:
  *      mov x0, x30
@@ -160,11 +287,6 @@ GLOBAL(ftrace_graph_call)		// ftrace_graph_caller();
 
 	mcount_exit
 ENDPROC(ftrace_caller)
-#endif /* CONFIG_DYNAMIC_FTRACE */
-
-ENTRY(ftrace_stub)
-	ret
-ENDPROC(ftrace_stub)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
@@ -184,7 +306,15 @@ ENTRY(ftrace_graph_caller)
 
 	mcount_exit
 ENDPROC(ftrace_graph_caller)
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
+ENTRY(ftrace_stub)
+	ret
+ENDPROC(ftrace_stub)
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
  * void return_to_handler(void)
  *
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index cf3bd2976e57..583f71abbe98 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -269,8 +269,10 @@ alternative_else_nop_endif
 alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	ldr	x20, [sp, #S_PMR_SAVE]
 	msr_s	SYS_ICC_PMR_EL1, x20
-	/* Ensure priority change is seen by redistributor */
-	dsb	sy
+	mrs_s	x21, SYS_ICC_CTLR_EL1
+	tbz	x21, #6, .L__skip_pmr_sync\@	// Check for ICC_CTLR_EL1.PMHE
+	dsb	sy				// Ensure priority change is seen by redistributor
+.L__skip_pmr_sync\@:
 alternative_else_nop_endif
 
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
@@ -578,76 +580,9 @@ ENDPROC(el1_error_invalid)
 	.align	6
 el1_sync:
 	kernel_entry 1
-	mrs	x1, esr_el1			// read the syndrome register
-	lsr	x24, x1, #ESR_ELx_EC_SHIFT	// exception class
-	cmp	x24, #ESR_ELx_EC_DABT_CUR	// data abort in EL1
-	b.eq	el1_da
-	cmp	x24, #ESR_ELx_EC_IABT_CUR	// instruction abort in EL1
-	b.eq	el1_ia
-	cmp	x24, #ESR_ELx_EC_SYS64		// configurable trap
-	b.eq	el1_undef
-	cmp	x24, #ESR_ELx_EC_PC_ALIGN	// pc alignment exception
-	b.eq	el1_pc
-	cmp	x24, #ESR_ELx_EC_UNKNOWN	// unknown exception in EL1
-	b.eq	el1_undef
-	cmp	x24, #ESR_ELx_EC_BREAKPT_CUR	// debug exception in EL1
-	b.ge	el1_dbg
-	b	el1_inv
-
-el1_ia:
-	/*
-	 * Fall through to the Data abort case
-	 */
-el1_da:
-	/*
-	 * Data abort handling
-	 */
-	mrs	x3, far_el1
-	inherit_daif	pstate=x23, tmp=x2
-	untagged_addr	x0, x3
-	mov	x2, sp				// struct pt_regs
-	bl	do_mem_abort
-
-	kernel_exit 1
-el1_pc:
-	/*
-	 * PC alignment exception handling. We don't handle SP alignment faults,
-	 * since we will have hit a recursive exception when trying to push the
-	 * initial pt_regs.
-	 */
-	mrs	x0, far_el1
-	inherit_daif	pstate=x23, tmp=x2
-	mov	x2, sp
-	bl	do_sp_pc_abort
-	ASM_BUG()
-el1_undef:
-	/*
-	 * Undefined instruction
-	 */
-	inherit_daif	pstate=x23, tmp=x2
 	mov	x0, sp
-	bl	do_undefinstr
+	bl	el1_sync_handler
 	kernel_exit 1
-el1_dbg:
-	/*
-	 * Debug exception handling
-	 */
-	cmp	x24, #ESR_ELx_EC_BRK64		// if BRK64
-	cinc	x24, x24, eq			// set bit '0'
-	tbz	x24, #0, el1_inv		// EL1 only
-	gic_prio_kentry_setup tmp=x3
-	mrs	x0, far_el1
-	mov	x2, sp				// struct pt_regs
-	bl	do_debug_exception
-	kernel_exit 1
-el1_inv:
-	// TODO: add support for undefined instructions in kernel mode
-	inherit_daif	pstate=x23, tmp=x2
-	mov	x0, sp
-	mov	x2, x1
-	mov	x1, #BAD_SYNC
-	bl	bad_mode
-	ASM_BUG()
 ENDPROC(el1_sync)
 
 	.align	6
@@ -714,71 +649,18 @@ ENDPROC(el1_irq)
 	.align	6
 el0_sync:
 	kernel_entry 0
-	mrs	x25, esr_el1			// read the syndrome register
-	lsr	x24, x25, #ESR_ELx_EC_SHIFT	// exception class
-	cmp	x24, #ESR_ELx_EC_SVC64		// SVC in 64-bit state
-	b.eq	el0_svc
-	cmp	x24, #ESR_ELx_EC_DABT_LOW	// data abort in EL0
-	b.eq	el0_da
-	cmp	x24, #ESR_ELx_EC_IABT_LOW	// instruction abort in EL0
-	b.eq	el0_ia
-	cmp	x24, #ESR_ELx_EC_FP_ASIMD	// FP/ASIMD access
-	b.eq	el0_fpsimd_acc
-	cmp	x24, #ESR_ELx_EC_SVE		// SVE access
-	b.eq	el0_sve_acc
-	cmp	x24, #ESR_ELx_EC_FP_EXC64	// FP/ASIMD exception
-	b.eq	el0_fpsimd_exc
-	cmp	x24, #ESR_ELx_EC_SYS64		// configurable trap
-	ccmp	x24, #ESR_ELx_EC_WFx, #4, ne
-	b.eq	el0_sys
-	cmp	x24, #ESR_ELx_EC_SP_ALIGN	// stack alignment exception
-	b.eq	el0_sp
-	cmp	x24, #ESR_ELx_EC_PC_ALIGN	// pc alignment exception
-	b.eq	el0_pc
-	cmp	x24, #ESR_ELx_EC_UNKNOWN	// unknown exception in EL0
-	b.eq	el0_undef
-	cmp	x24, #ESR_ELx_EC_BREAKPT_LOW	// debug exception in EL0
-	b.ge	el0_dbg
-	b	el0_inv
+	mov	x0, sp
+	bl	el0_sync_handler
+	b	ret_to_user
 
 #ifdef CONFIG_COMPAT
 	.align	6
 el0_sync_compat:
 	kernel_entry 0, 32
-	mrs	x25, esr_el1			// read the syndrome register
-	lsr	x24, x25, #ESR_ELx_EC_SHIFT	// exception class
-	cmp	x24, #ESR_ELx_EC_SVC32		// SVC in 32-bit state
-	b.eq	el0_svc_compat
-	cmp	x24, #ESR_ELx_EC_DABT_LOW	// data abort in EL0
-	b.eq	el0_da
-	cmp	x24, #ESR_ELx_EC_IABT_LOW	// instruction abort in EL0
-	b.eq	el0_ia
-	cmp	x24, #ESR_ELx_EC_FP_ASIMD	// FP/ASIMD access
-	b.eq	el0_fpsimd_acc
-	cmp	x24, #ESR_ELx_EC_FP_EXC32	// FP/ASIMD exception
-	b.eq	el0_fpsimd_exc
-	cmp	x24, #ESR_ELx_EC_PC_ALIGN	// pc alignment exception
-	b.eq	el0_pc
-	cmp	x24, #ESR_ELx_EC_UNKNOWN	// unknown exception in EL0
-	b.eq	el0_undef
-	cmp	x24, #ESR_ELx_EC_CP15_32	// CP15 MRC/MCR trap
-	b.eq	el0_cp15
-	cmp	x24, #ESR_ELx_EC_CP15_64	// CP15 MRRC/MCRR trap
-	b.eq	el0_cp15
-	cmp	x24, #ESR_ELx_EC_CP14_MR	// CP14 MRC/MCR trap
-	b.eq	el0_undef
-	cmp	x24, #ESR_ELx_EC_CP14_LS	// CP14 LDC/STC trap
-	b.eq	el0_undef
-	cmp	x24, #ESR_ELx_EC_CP14_64	// CP14 MRRC/MCRR trap
-	b.eq	el0_undef
-	cmp	x24, #ESR_ELx_EC_BREAKPT_LOW	// debug exception in EL0
-	b.ge	el0_dbg
-	b	el0_inv
-el0_svc_compat:
-	gic_prio_kentry_setup tmp=x1
 	mov	x0, sp
-	bl	el0_svc_compat_handler
+	bl	el0_sync_compat_handler
 	b	ret_to_user
+ENDPROC(el0_sync)
 
 	.align	6
 el0_irq_compat:
@@ -788,139 +670,7 @@ el0_irq_compat:
 el0_error_compat:
 	kernel_entry 0, 32
 	b	el0_error_naked
-
-el0_cp15:
-	/*
-	 * Trapped CP15 (MRC, MCR, MRRC, MCRR) instructions
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, x25
-	mov	x1, sp
-	bl	do_cp15instr
-	b	ret_to_user
-#endif
-
-el0_da:
-	/*
-	 * Data abort handling
-	 */
-	mrs	x26, far_el1
-	ct_user_exit_irqoff
-	enable_daif
-	untagged_addr	x0, x26
-	mov	x1, x25
-	mov	x2, sp
-	bl	do_mem_abort
-	b	ret_to_user
-el0_ia:
-	/*
-	 * Instruction abort handling
-	 */
-	mrs	x26, far_el1
-	gic_prio_kentry_setup tmp=x0
-	ct_user_exit_irqoff
-	enable_da_f
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bl	trace_hardirqs_off
-#endif
-	mov	x0, x26
-	mov	x1, x25
-	mov	x2, sp
-	bl	do_el0_ia_bp_hardening
-	b	ret_to_user
-el0_fpsimd_acc:
-	/*
-	 * Floating Point or Advanced SIMD access
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, x25
-	mov	x1, sp
-	bl	do_fpsimd_acc
-	b	ret_to_user
-el0_sve_acc:
-	/*
-	 * Scalable Vector Extension access
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, x25
-	mov	x1, sp
-	bl	do_sve_acc
-	b	ret_to_user
-el0_fpsimd_exc:
-	/*
-	 * Floating Point, Advanced SIMD or SVE exception
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, x25
-	mov	x1, sp
-	bl	do_fpsimd_exc
-	b	ret_to_user
-el0_sp:
-	ldr	x26, [sp, #S_SP]
-	b	el0_sp_pc
-el0_pc:
-	mrs	x26, far_el1
-el0_sp_pc:
-	/*
-	 * Stack or PC alignment exception handling
-	 */
-	gic_prio_kentry_setup tmp=x0
-	ct_user_exit_irqoff
-	enable_da_f
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bl	trace_hardirqs_off
 #endif
-	mov	x0, x26
-	mov	x1, x25
-	mov	x2, sp
-	bl	do_sp_pc_abort
-	b	ret_to_user
-el0_undef:
-	/*
-	 * Undefined instruction
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, sp
-	bl	do_undefinstr
-	b	ret_to_user
-el0_sys:
-	/*
-	 * System instructions, for trapped cache maintenance instructions
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, x25
-	mov	x1, sp
-	bl	do_sysinstr
-	b	ret_to_user
-el0_dbg:
-	/*
-	 * Debug exception handling
-	 */
-	tbnz	x24, #0, el0_inv		// EL0 only
-	mrs	x24, far_el1
-	gic_prio_kentry_setup tmp=x3
-	ct_user_exit_irqoff
-	mov	x0, x24
-	mov	x1, x25
-	mov	x2, sp
-	bl	do_debug_exception
-	enable_da_f
-	b	ret_to_user
-el0_inv:
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, sp
-	mov	x1, #BAD_SYNC
-	mov	x2, x25
-	bl	bad_el0_sync
-	b	ret_to_user
-ENDPROC(el0_sync)
 
 	.align	6
 el0_irq:
@@ -999,17 +749,6 @@ finish_ret_to_user:
 	kernel_exit 0
 ENDPROC(ret_to_user)
 
-/*
- * SVC handler.
- */
-	.align	6
-el0_svc:
-	gic_prio_kentry_setup tmp=x1
-	mov	x0, sp
-	bl	el0_svc_handler
-	b	ret_to_user
-ENDPROC(el0_svc)
-
 	.popsection				// .entry.text
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 37d3912cfe06..3eb338f14386 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -920,7 +920,7 @@ void fpsimd_release_task(struct task_struct *dead_task)
  * would have disabled the SVE access trap for userspace during
  * ret_to_user, making an SVE access trap impossible in that case.
  */
-asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs)
+void do_sve_acc(unsigned int esr, struct pt_regs *regs)
 {
 	/* Even if we chose not to use SVE, the hardware could still trap: */
 	if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) {
@@ -947,7 +947,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs)
 /*
  * Trapped FP/ASIMD access.
  */
-asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
+void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
 {
 	/* TODO: implement lazy context saving/restoring */
 	WARN_ON(1);
@@ -956,7 +956,7 @@ asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
 /*
  * Raise a SIGFPE for the current process.
  */
-asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
+void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
 {
 	unsigned int si_code = FPE_FLTUNK;
 
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 06e56b470315..8618faa82e6d 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -62,6 +62,19 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ftrace_modify_code(pc, 0, new, false);
 }
 
+static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
+{
+#ifdef CONFIG_ARM64_MODULE_PLTS
+	struct plt_entry *plt = mod->arch.ftrace_trampolines;
+
+	if (addr == FTRACE_ADDR)
+		return &plt[FTRACE_PLT_IDX];
+	if (addr == FTRACE_REGS_ADDR && IS_ENABLED(CONFIG_FTRACE_WITH_REGS))
+		return &plt[FTRACE_REGS_PLT_IDX];
+#endif
+	return NULL;
+}
+
 /*
  * Turn on the call to ftrace_caller() in instrumented function
  */
@@ -72,9 +85,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	long offset = (long)pc - (long)addr;
 
 	if (offset < -SZ_128M || offset >= SZ_128M) {
-#ifdef CONFIG_ARM64_MODULE_PLTS
-		struct plt_entry trampoline, *dst;
 		struct module *mod;
+		struct plt_entry *plt;
+
+		if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
+			return -EINVAL;
 
 		/*
 		 * On kernels that support module PLTs, the offset between the
@@ -93,49 +108,13 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		if (WARN_ON(!mod))
 			return -EINVAL;
 
-		/*
-		 * There is only one ftrace trampoline per module. For now,
-		 * this is not a problem since on arm64, all dynamic ftrace
-		 * invocations are routed via ftrace_caller(). This will need
-		 * to be revisited if support for multiple ftrace entry points
-		 * is added in the future, but for now, the pr_err() below
-		 * deals with a theoretical issue only.
-		 *
-		 * Note that PLTs are place relative, and plt_entries_equal()
-		 * checks whether they point to the same target. Here, we need
-		 * to check if the actual opcodes are in fact identical,
-		 * regardless of the offset in memory so use memcmp() instead.
-		 */
-		dst = mod->arch.ftrace_trampoline;
-		trampoline = get_plt_entry(addr, dst);
-		if (memcmp(dst, &trampoline, sizeof(trampoline))) {
-			if (plt_entry_is_initialized(dst)) {
-				pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
-				return -EINVAL;
-			}
-
-			/* point the trampoline to our ftrace entry point */
-			module_disable_ro(mod);
-			*dst = trampoline;
-			module_enable_ro(mod, true);
-
-			/*
-			 * Ensure updated trampoline is visible to instruction
-			 * fetch before we patch in the branch. Although the
-			 * architecture doesn't require an IPI in this case,
-			 * Neoverse-N1 erratum #1542419 does require one
-			 * if the TLB maintenance in module_enable_ro() is
-			 * skipped due to rodata_enabled. It doesn't seem worth
-			 * it to make it conditional given that this is
-			 * certainly not a fast-path.
-			 */
-			flush_icache_range((unsigned long)&dst[0],
-					   (unsigned long)&dst[1]);
+		plt = get_ftrace_plt(mod, addr);
+		if (!plt) {
+			pr_err("ftrace: no module PLT for %ps\n", (void *)addr);
+			return -EINVAL;
 		}
-		addr = (unsigned long)dst;
-#else /* CONFIG_ARM64_MODULE_PLTS */
-		return -EINVAL;
-#endif /* CONFIG_ARM64_MODULE_PLTS */
+
+		addr = (unsigned long)plt;
 	}
 
 	old = aarch64_insn_gen_nop();
@@ -144,6 +123,55 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	return ftrace_modify_code(pc, old, new, true);
 }
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+			unsigned long addr)
+{
+	unsigned long pc = rec->ip;
+	u32 old, new;
+
+	old = aarch64_insn_gen_branch_imm(pc, old_addr,
+					  AARCH64_INSN_BRANCH_LINK);
+	new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
+
+	return ftrace_modify_code(pc, old, new, true);
+}
+
+/*
+ * The compiler has inserted two NOPs before the regular function prologue.
+ * All instrumented functions follow the AAPCS, so x0-x8 and x19-x30 are live,
+ * and x9-x18 are free for our use.
+ *
+ * At runtime we want to be able to swing a single NOP <-> BL to enable or
+ * disable the ftrace call. The BL requires us to save the original LR value,
+ * so here we insert a <MOV X9, LR> over the first NOP so the instructions
+ * before the regular prologue are:
+ *
+ * | Compiled | Disabled   | Enabled    |
+ * +----------+------------+------------+
+ * | NOP      | MOV X9, LR | MOV X9, LR |
+ * | NOP      | NOP        | BL <entry> |
+ *
+ * The LR value will be recovered by ftrace_regs_entry, and restored into LR
+ * before returning to the regular function prologue. When a function is not
+ * being traced, the MOV is not harmful given x9 is not live per the AAPCS.
+ *
+ * Note: ftrace_process_locs() has pre-adjusted rec->ip to be the address of
+ * the BL.
+ */
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
+{
+	unsigned long pc = rec->ip - AARCH64_INSN_SIZE;
+	u32 old, new;
+
+	old = aarch64_insn_gen_nop();
+	new = aarch64_insn_gen_move_reg(AARCH64_INSN_REG_9,
+					AARCH64_INSN_REG_LR,
+					AARCH64_INSN_VARIANT_64BIT);
+	return ftrace_modify_code(pc, old, new, true);
+}
+#endif
+
 /*
  * Turn off the call to ftrace_caller() in instrumented function
  */
@@ -156,9 +184,11 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 	long offset = (long)pc - (long)addr;
 
 	if (offset < -SZ_128M || offset >= SZ_128M) {
-#ifdef CONFIG_ARM64_MODULE_PLTS
 		u32 replaced;
 
+		if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
+			return -EINVAL;
+
 		/*
 		 * 'mod' is only set at module load time, but if we end up
 		 * dealing with an out-of-range condition, we can assume it
@@ -189,9 +219,6 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 			return -EINVAL;
 
 		validate = false;
-#else /* CONFIG_ARM64_MODULE_PLTS */
-		return -EINVAL;
-#endif /* CONFIG_ARM64_MODULE_PLTS */
 	} else {
 		old = aarch64_insn_gen_branch_imm(pc, addr,
 						  AARCH64_INSN_BRANCH_LINK);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 38ee1514cd9c..0b727edf4104 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -51,7 +51,7 @@ int hw_breakpoint_slots(int type)
 	case TYPE_DATA:
 		return get_num_wrps();
 	default:
-		pr_warning("unknown slot type: %d\n", type);
+		pr_warn("unknown slot type: %d\n", type);
 		return 0;
 	}
 }
@@ -112,7 +112,7 @@ static u64 read_wb_reg(int reg, int n)
 	GEN_READ_WB_REG_CASES(AARCH64_DBG_REG_WVR, AARCH64_DBG_REG_NAME_WVR, val);
 	GEN_READ_WB_REG_CASES(AARCH64_DBG_REG_WCR, AARCH64_DBG_REG_NAME_WCR, val);
 	default:
-		pr_warning("attempt to read from unknown breakpoint register %d\n", n);
+		pr_warn("attempt to read from unknown breakpoint register %d\n", n);
 	}
 
 	return val;
@@ -127,7 +127,7 @@ static void write_wb_reg(int reg, int n, u64 val)
 	GEN_WRITE_WB_REG_CASES(AARCH64_DBG_REG_WVR, AARCH64_DBG_REG_NAME_WVR, val);
 	GEN_WRITE_WB_REG_CASES(AARCH64_DBG_REG_WCR, AARCH64_DBG_REG_NAME_WCR, val);
 	default:
-		pr_warning("attempt to write to unknown breakpoint register %d\n", n);
+		pr_warn("attempt to write to unknown breakpoint register %d\n", n);
 	}
 	isb();
 }
@@ -145,7 +145,7 @@ static enum dbg_active_el debug_exception_level(int privilege)
 	case AARCH64_BREAKPOINT_EL1:
 		return DBG_ACTIVE_EL1;
 	default:
-		pr_warning("invalid breakpoint privilege level %d\n", privilege);
+		pr_warn("invalid breakpoint privilege level %d\n", privilege);
 		return -EINVAL;
 	}
 }
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index d801a7094076..513b29c3e735 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -1268,6 +1268,19 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
 	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift);
 }
 
+/*
+ * MOV (register) is architecturally an alias of ORR (shifted register) where
+ * MOV <*d>, <*m> is equivalent to ORR <*d>, <*ZR>, <*m>
+ */
+u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst,
+			      enum aarch64_insn_register src,
+			      enum aarch64_insn_variant variant)
+{
+	return aarch64_insn_gen_logical_shifted_reg(dst, AARCH64_INSN_REG_ZR,
+						    src, 0, variant,
+						    AARCH64_INSN_LOGIC_ORR);
+}
+
 u32 aarch64_insn_gen_adr(unsigned long pc, unsigned long addr,
 			 enum aarch64_insn_register reg,
 			 enum aarch64_insn_adr_type type)
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 416f537bf614..2a11a962e571 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -19,6 +19,14 @@
 #include <asm/pgtable.h>
 #include <asm/sections.h>
 
+enum kaslr_status {
+	KASLR_ENABLED,
+	KASLR_DISABLED_CMDLINE,
+	KASLR_DISABLED_NO_SEED,
+	KASLR_DISABLED_FDT_REMAP,
+};
+
+static enum kaslr_status __initdata kaslr_status;
 u64 __ro_after_init module_alloc_base;
 u16 __initdata memstart_offset_seed;
 
@@ -91,15 +99,15 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 */
 	early_fixmap_init();
 	fdt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
-	if (!fdt)
+	if (!fdt) {
+		kaslr_status = KASLR_DISABLED_FDT_REMAP;
 		return 0;
+	}
 
 	/*
 	 * Retrieve (and wipe) the seed from the FDT
 	 */
 	seed = get_kaslr_seed(fdt);
-	if (!seed)
-		return 0;
 
 	/*
 	 * Check if 'nokaslr' appears on the command line, and
@@ -107,8 +115,15 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 */
 	cmdline = kaslr_get_cmdline(fdt);
 	str = strstr(cmdline, "nokaslr");
-	if (str == cmdline || (str > cmdline && *(str - 1) == ' '))
+	if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) {
+		kaslr_status = KASLR_DISABLED_CMDLINE;
+		return 0;
+	}
+
+	if (!seed) {
+		kaslr_status = KASLR_DISABLED_NO_SEED;
 		return 0;
+	}
 
 	/*
 	 * OK, so we are proceeding with KASLR enabled. Calculate a suitable
@@ -170,3 +185,24 @@ u64 __init kaslr_early_init(u64 dt_phys)
 
 	return offset;
 }
+
+static int __init kaslr_init(void)
+{
+	switch (kaslr_status) {
+	case KASLR_ENABLED:
+		pr_info("KASLR enabled\n");
+		break;
+	case KASLR_DISABLED_CMDLINE:
+		pr_info("KASLR disabled on command line\n");
+		break;
+	case KASLR_DISABLED_NO_SEED:
+		pr_warn("KASLR disabled due to lack of seed\n");
+		break;
+	case KASLR_DISABLED_FDT_REMAP:
+		pr_warn("KASLR disabled due to FDT remapping failure\n");
+		break;
+	}
+
+	return 0;
+}
+core_initcall(kaslr_init)
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index b182442b87a3..65b08a74aec6 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/elf.h>
+#include <linux/ftrace.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sort.h>
@@ -330,7 +331,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 		tramp->sh_type = SHT_NOBITS;
 		tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
 		tramp->sh_addralign = __alignof__(struct plt_entry);
-		tramp->sh_size = sizeof(struct plt_entry);
+		tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry);
 	}
 
 	return 0;
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 03ff15bffbb6..1cd1a4d0ed30 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -9,6 +9,7 @@
 
 #include <linux/bitops.h>
 #include <linux/elf.h>
+#include <linux/ftrace.h>
 #include <linux/gfp.h>
 #include <linux/kasan.h>
 #include <linux/kernel.h>
@@ -470,22 +471,58 @@ overflow:
 	return -ENOEXEC;
 }
 
-int module_finalize(const Elf_Ehdr *hdr,
-		    const Elf_Shdr *sechdrs,
-		    struct module *me)
+static const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
+				    const Elf_Shdr *sechdrs,
+				    const char *name)
 {
 	const Elf_Shdr *s, *se;
 	const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
 	for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
-		if (strcmp(".altinstructions", secstrs + s->sh_name) == 0)
-			apply_alternatives_module((void *)s->sh_addr, s->sh_size);
-#ifdef CONFIG_ARM64_MODULE_PLTS
-		if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
-		    !strcmp(".text.ftrace_trampoline", secstrs + s->sh_name))
-			me->arch.ftrace_trampoline = (void *)s->sh_addr;
-#endif
+		if (strcmp(name, secstrs + s->sh_name) == 0)
+			return s;
 	}
 
+	return NULL;
+}
+
+static inline void __init_plt(struct plt_entry *plt, unsigned long addr)
+{
+	*plt = get_plt_entry(addr, plt);
+}
+
+static int module_init_ftrace_plt(const Elf_Ehdr *hdr,
+				  const Elf_Shdr *sechdrs,
+				  struct module *mod)
+{
+#if defined(CONFIG_ARM64_MODULE_PLTS) && defined(CONFIG_DYNAMIC_FTRACE)
+	const Elf_Shdr *s;
+	struct plt_entry *plts;
+
+	s = find_section(hdr, sechdrs, ".text.ftrace_trampoline");
+	if (!s)
+		return -ENOEXEC;
+
+	plts = (void *)s->sh_addr;
+
+	__init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR);
+
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+		__init_plt(&plts[FTRACE_REGS_PLT_IDX], FTRACE_REGS_ADDR);
+
+	mod->arch.ftrace_trampolines = plts;
+#endif
 	return 0;
 }
+
+int module_finalize(const Elf_Ehdr *hdr,
+		    const Elf_Shdr *sechdrs,
+		    struct module *me)
+{
+	const Elf_Shdr *s;
+	s = find_section(hdr, sechdrs, ".altinstructions");
+	if (s)
+		apply_alternatives_module((void *)s->sh_addr, s->sh_size);
+
+	return module_init_ftrace_plt(hdr, sechdrs, me);
+}
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
index 4cfed91fe256..1ef702b0be2d 100644
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -6,13 +6,153 @@
  * Author: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
  */
 
+#define pr_fmt(fmt) "arm-pv: " fmt
+
+#include <linux/arm-smccc.h>
+#include <linux/cpuhotplug.h>
 #include <linux/export.h>
+#include <linux/io.h>
 #include <linux/jump_label.h>
+#include <linux/printk.h>
+#include <linux/psci.h>
+#include <linux/reboot.h>
+#include <linux/slab.h>
 #include <linux/types.h>
+
 #include <asm/paravirt.h>
+#include <asm/pvclock-abi.h>
+#include <asm/smp_plat.h>
 
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
 struct paravirt_patch_template pv_ops;
 EXPORT_SYMBOL_GPL(pv_ops);
+
+struct pv_time_stolen_time_region {
+	struct pvclock_vcpu_stolen_time *kaddr;
+};
+
+static DEFINE_PER_CPU(struct pv_time_stolen_time_region, stolen_time_region);
+
+static bool steal_acc = true;
+static int __init parse_no_stealacc(char *arg)
+{
+	steal_acc = false;
+	return 0;
+}
+
+early_param("no-steal-acc", parse_no_stealacc);
+
+/* return stolen time in ns by asking the hypervisor */
+static u64 pv_steal_clock(int cpu)
+{
+	struct pv_time_stolen_time_region *reg;
+
+	reg = per_cpu_ptr(&stolen_time_region, cpu);
+	if (!reg->kaddr) {
+		pr_warn_once("stolen time enabled but not configured for cpu %d\n",
+			     cpu);
+		return 0;
+	}
+
+	return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time));
+}
+
+static int stolen_time_dying_cpu(unsigned int cpu)
+{
+	struct pv_time_stolen_time_region *reg;
+
+	reg = this_cpu_ptr(&stolen_time_region);
+	if (!reg->kaddr)
+		return 0;
+
+	memunmap(reg->kaddr);
+	memset(reg, 0, sizeof(*reg));
+
+	return 0;
+}
+
+static int init_stolen_time_cpu(unsigned int cpu)
+{
+	struct pv_time_stolen_time_region *reg;
+	struct arm_smccc_res res;
+
+	reg = this_cpu_ptr(&stolen_time_region);
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_HV_PV_TIME_ST, &res);
+
+	if (res.a0 == SMCCC_RET_NOT_SUPPORTED)
+		return -EINVAL;
+
+	reg->kaddr = memremap(res.a0,
+			      sizeof(struct pvclock_vcpu_stolen_time),
+			      MEMREMAP_WB);
+
+	if (!reg->kaddr) {
+		pr_warn("Failed to map stolen time data structure\n");
+		return -ENOMEM;
+	}
+
+	if (le32_to_cpu(reg->kaddr->revision) != 0 ||
+	    le32_to_cpu(reg->kaddr->attributes) != 0) {
+		pr_warn_once("Unexpected revision or attributes in stolen time data\n");
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static int pv_time_init_stolen_time(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING,
+				"hypervisor/arm/pvtime:starting",
+				init_stolen_time_cpu, stolen_time_dying_cpu);
+	if (ret < 0)
+		return ret;
+	return 0;
+}
+
+static bool has_pv_steal_clock(void)
+{
+	struct arm_smccc_res res;
+
+	/* To detect the presence of PV time support we require SMCCC 1.1+ */
+	if (psci_ops.smccc_version < SMCCC_VERSION_1_1)
+		return false;
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+			     ARM_SMCCC_HV_PV_TIME_FEATURES, &res);
+
+	if (res.a0 != SMCCC_RET_SUCCESS)
+		return false;
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_HV_PV_TIME_FEATURES,
+			     ARM_SMCCC_HV_PV_TIME_ST, &res);
+
+	return (res.a0 == SMCCC_RET_SUCCESS);
+}
+
+int __init pv_time_init(void)
+{
+	int ret;
+
+	if (!has_pv_steal_clock())
+		return 0;
+
+	ret = pv_time_init_stolen_time();
+	if (ret)
+		return ret;
+
+	pv_ops.time.steal_clock = pv_steal_clock;
+
+	static_key_slow_inc(&paravirt_steal_enabled);
+	if (steal_acc)
+		static_key_slow_inc(&paravirt_steal_rq_enabled);
+
+	pr_info("using stolen time PV\n");
+
+	return 0;
+}
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index a0b4f1bca491..e40b65645c86 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -158,133 +158,74 @@ armv8pmu_events_sysfs_show(struct device *dev,
 	return sprintf(page, "event=0x%03llx\n", pmu_attr->id);
 }
 
-#define ARMV8_EVENT_ATTR(name, config) \
-	PMU_EVENT_ATTR(name, armv8_event_attr_##name, \
-		       config, armv8pmu_events_sysfs_show)
-
-ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR);
-ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL);
-ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL);
-ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL);
-ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE);
-ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL);
-ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED);
-ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED);
-ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED);
-ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN);
-ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN);
-ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED);
-ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED);
-ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED);
-ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED);
-ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED);
-ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED);
-ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES);
-ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED);
-ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS);
-ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE);
-ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB);
-ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE);
-ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL);
-ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB);
-ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS);
-ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR);
-ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC);
-ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED);
-ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES);
-/* Don't expose the chain event in /sys, since it's useless in isolation */
-ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE);
-ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE);
-ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED);
-ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED);
-ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND);
-ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND);
-ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB);
-ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB);
-ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE);
-ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL);
-ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE);
-ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL);
-ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE);
-ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB);
-ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL);
-ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL);
-ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB);
-ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB);
-ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS);
-ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE);
-ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS);
-ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK);
-ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK);
-ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD);
-ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD);
-ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD);
-ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP);
-ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED);
-ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE);
-ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION);
+#define ARMV8_EVENT_ATTR(name, config)						\
+	(&((struct perf_pmu_events_attr) {					\
+		.attr = __ATTR(name, 0444, armv8pmu_events_sysfs_show, NULL),	\
+		.id = config,							\
+	}).attr.attr)
 
 static struct attribute *armv8_pmuv3_event_attrs[] = {
-	&armv8_event_attr_sw_incr.attr.attr,
-	&armv8_event_attr_l1i_cache_refill.attr.attr,
-	&armv8_event_attr_l1i_tlb_refill.attr.attr,
-	&armv8_event_attr_l1d_cache_refill.attr.attr,
-	&armv8_event_attr_l1d_cache.attr.attr,
-	&armv8_event_attr_l1d_tlb_refill.attr.attr,
-	&armv8_event_attr_ld_retired.attr.attr,
-	&armv8_event_attr_st_retired.attr.attr,
-	&armv8_event_attr_inst_retired.attr.attr,
-	&armv8_event_attr_exc_taken.attr.attr,
-	&armv8_event_attr_exc_return.attr.attr,
-	&armv8_event_attr_cid_write_retired.attr.attr,
-	&armv8_event_attr_pc_write_retired.attr.attr,
-	&armv8_event_attr_br_immed_retired.attr.attr,
-	&armv8_event_attr_br_return_retired.attr.attr,
-	&armv8_event_attr_unaligned_ldst_retired.attr.attr,
-	&armv8_event_attr_br_mis_pred.attr.attr,
-	&armv8_event_attr_cpu_cycles.attr.attr,
-	&armv8_event_attr_br_pred.attr.attr,
-	&armv8_event_attr_mem_access.attr.attr,
-	&armv8_event_attr_l1i_cache.attr.attr,
-	&armv8_event_attr_l1d_cache_wb.attr.attr,
-	&armv8_event_attr_l2d_cache.attr.attr,
-	&armv8_event_attr_l2d_cache_refill.attr.attr,
-	&armv8_event_attr_l2d_cache_wb.attr.attr,
-	&armv8_event_attr_bus_access.attr.attr,
-	&armv8_event_attr_memory_error.attr.attr,
-	&armv8_event_attr_inst_spec.attr.attr,
-	&armv8_event_attr_ttbr_write_retired.attr.attr,
-	&armv8_event_attr_bus_cycles.attr.attr,
-	&armv8_event_attr_l1d_cache_allocate.attr.attr,
-	&armv8_event_attr_l2d_cache_allocate.attr.attr,
-	&armv8_event_attr_br_retired.attr.attr,
-	&armv8_event_attr_br_mis_pred_retired.attr.attr,
-	&armv8_event_attr_stall_frontend.attr.attr,
-	&armv8_event_attr_stall_backend.attr.attr,
-	&armv8_event_attr_l1d_tlb.attr.attr,
-	&armv8_event_attr_l1i_tlb.attr.attr,
-	&armv8_event_attr_l2i_cache.attr.attr,
-	&armv8_event_attr_l2i_cache_refill.attr.attr,
-	&armv8_event_attr_l3d_cache_allocate.attr.attr,
-	&armv8_event_attr_l3d_cache_refill.attr.attr,
-	&armv8_event_attr_l3d_cache.attr.attr,
-	&armv8_event_attr_l3d_cache_wb.attr.attr,
-	&armv8_event_attr_l2d_tlb_refill.attr.attr,
-	&armv8_event_attr_l2i_tlb_refill.attr.attr,
-	&armv8_event_attr_l2d_tlb.attr.attr,
-	&armv8_event_attr_l2i_tlb.attr.attr,
-	&armv8_event_attr_remote_access.attr.attr,
-	&armv8_event_attr_ll_cache.attr.attr,
-	&armv8_event_attr_ll_cache_miss.attr.attr,
-	&armv8_event_attr_dtlb_walk.attr.attr,
-	&armv8_event_attr_itlb_walk.attr.attr,
-	&armv8_event_attr_ll_cache_rd.attr.attr,
-	&armv8_event_attr_ll_cache_miss_rd.attr.attr,
-	&armv8_event_attr_remote_access_rd.attr.attr,
-	&armv8_event_attr_sample_pop.attr.attr,
-	&armv8_event_attr_sample_feed.attr.attr,
-	&armv8_event_attr_sample_filtrate.attr.attr,
-	&armv8_event_attr_sample_collision.attr.attr,
+	ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR),
+	ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL),
+	ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE),
+	ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL),
+	ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED),
+	ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED),
+	ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED),
+	ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN),
+	ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN),
+	ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED),
+	ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED),
+	ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED),
+	ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED),
+	ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED),
+	ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED),
+	ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES),
+	ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED),
+	ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS),
+	ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE),
+	ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB),
+	ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE),
+	ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB),
+	ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS),
+	ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR),
+	ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC),
+	ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED),
+	ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES),
+	/* Don't expose the chain event in /sys, since it's useless in isolation */
+	ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE),
+	ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE),
+	ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED),
+	ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED),
+	ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND),
+	ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND),
+	ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB),
+	ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB),
+	ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE),
+	ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE),
+	ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE),
+	ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB),
+	ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL),
+	ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL),
+	ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB),
+	ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB),
+	ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS),
+	ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE),
+	ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS),
+	ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK),
+	ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK),
+	ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD),
+	ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD),
+	ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD),
+	ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP),
+	ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED),
+	ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE),
+	ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION),
 	NULL,
 };
 
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index c4452827419b..d1c95dcf1d78 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -455,10 +455,6 @@ int __init arch_populate_kprobe_blacklist(void)
 					(unsigned long)__irqentry_text_end);
 	if (ret)
 		return ret;
-	ret = kprobe_add_area_blacklist((unsigned long)__exception_text_start,
-					(unsigned long)__exception_text_end);
-	if (ret)
-		return ret;
 	ret = kprobe_add_area_blacklist((unsigned long)__idmap_text_start,
 					(unsigned long)__idmap_text_end);
 	if (ret)
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index c9f72b2665f1..43ae4e0c968f 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -81,7 +81,8 @@ static void cpu_psci_cpu_die(unsigned int cpu)
 
 static int cpu_psci_cpu_kill(unsigned int cpu)
 {
-	int err, i;
+	int err;
+	unsigned long start, end;
 
 	if (!psci_ops.affinity_info)
 		return 0;
@@ -91,16 +92,18 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 	 * while it is dying. So, try again a few times.
 	 */
 
-	for (i = 0; i < 10; i++) {
+	start = jiffies;
+	end = start + msecs_to_jiffies(100);
+	do {
 		err = psci_ops.affinity_info(cpu_logical_map(cpu), 0);
 		if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) {
-			pr_info("CPU%d killed.\n", cpu);
+			pr_info("CPU%d killed (polled %d ms)\n", cpu,
+				jiffies_to_msecs(jiffies - start));
 			return 0;
 		}
 
-		msleep(10);
-		pr_info("Retrying again to check for CPU kill\n");
-	}
+		usleep_range(100, 1000);
+	} while (time_before(jiffies, end));
 
 	pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n",
 			cpu, err);
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index ea94cf8f9dc6..d6259dac62b6 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -2,6 +2,7 @@
 // Copyright (C) 2017 Arm Ltd.
 #define pr_fmt(fmt) "sdei: " fmt
 
+#include <linux/arm-smccc.h>
 #include <linux/arm_sdei.h>
 #include <linux/hardirq.h>
 #include <linux/irqflags.h>
@@ -161,7 +162,7 @@ unsigned long sdei_arch_get_entry_point(int conduit)
 			return 0;
 	}
 
-	sdei_exit_mode = (conduit == CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC;
+	sdei_exit_mode = (conduit == SMCCC_CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC;
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	if (arm64_kernel_unmapped_at_el0()) {
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index dc9fe879c279..ab149bcc3dc7 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -345,8 +345,7 @@ void __cpu_die(unsigned int cpu)
 	 */
 	err = op_cpu_kill(cpu);
 	if (err)
-		pr_warn("CPU%d may not have shut down cleanly: %d\n",
-			cpu, err);
+		pr_warn("CPU%d may not have shut down cleanly: %d\n", cpu, err);
 }
 
 /*
@@ -976,8 +975,8 @@ void smp_send_stop(void)
 		udelay(1);
 
 	if (num_online_cpus() > 1)
-		pr_warning("SMP: failed to stop secondary CPUs %*pbl\n",
-			   cpumask_pr_args(cpu_online_mask));
+		pr_warn("SMP: failed to stop secondary CPUs %*pbl\n",
+			cpumask_pr_args(cpu_online_mask));
 
 	sdei_mask_local_cpu();
 }
@@ -1017,8 +1016,8 @@ void crash_smp_send_stop(void)
 		udelay(1);
 
 	if (atomic_read(&waiting_for_crash_ipi) > 0)
-		pr_warning("SMP: failed to stop secondary CPUs %*pbl\n",
-			   cpumask_pr_args(&mask));
+		pr_warn("SMP: failed to stop secondary CPUs %*pbl\n",
+			cpumask_pr_args(&mask));
 
 	sdei_mask_local_cpu();
 }
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index f1cb64959427..3c18c2454089 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/compat.h>
+#include <linux/cpufeature.h>
 #include <linux/personality.h>
 #include <linux/sched.h>
 #include <linux/sched/signal.h>
@@ -17,6 +18,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/system_misc.h>
+#include <asm/tlbflush.h>
 #include <asm/unistd.h>
 
 static long
@@ -30,6 +32,15 @@ __do_compat_cache_op(unsigned long start, unsigned long end)
 		if (fatal_signal_pending(current))
 			return 0;
 
+		if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+			/*
+			 * The workaround requires an inner-shareable tlbi.
+			 * We pick the reserved-ASID to minimise the impact.
+			 */
+			__tlbi(aside1is, __TLBI_VADDR(0, 0));
+			dsb(ish);
+		}
+
 		ret = __flush_cache_user_range(start, start + chunk);
 		if (ret)
 			return ret;
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 871c739f060a..9a9d98a443fc 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -154,14 +154,14 @@ static inline void sve_user_discard(void)
 	sve_user_disable();
 }
 
-asmlinkage void el0_svc_handler(struct pt_regs *regs)
+void el0_svc_handler(struct pt_regs *regs)
 {
 	sve_user_discard();
 	el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table);
 }
 
 #ifdef CONFIG_COMPAT
-asmlinkage void el0_svc_compat_handler(struct pt_regs *regs)
+void el0_svc_compat_handler(struct pt_regs *regs)
 {
 	el0_svc_common(regs, regs->regs[7], __NR_compat_syscalls,
 		       compat_sys_call_table);
diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c
index 0b2946414dc9..73f06d4b3aae 100644
--- a/arch/arm64/kernel/time.c
+++ b/arch/arm64/kernel/time.c
@@ -30,6 +30,7 @@
 
 #include <asm/thread_info.h>
 #include <asm/stacktrace.h>
+#include <asm/paravirt.h>
 
 unsigned long profile_pc(struct pt_regs *regs)
 {
@@ -65,4 +66,6 @@ void __init time_init(void)
 
 	/* Calibrate the delay loop directly */
 	lpj_fine = arch_timer_rate / HZ;
+
+	pv_time_init();
 }
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 34739e80211b..73caf35c2262 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -35,6 +35,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
 #include <asm/insn.h>
+#include <asm/kprobes.h>
 #include <asm/traps.h>
 #include <asm/smp.h>
 #include <asm/stack_pointer.h>
@@ -393,7 +394,7 @@ void arm64_notify_segfault(unsigned long addr)
 	force_signal_inject(SIGSEGV, code, addr);
 }
 
-asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
+void do_undefinstr(struct pt_regs *regs)
 {
 	/* check for AArch32 breakpoint instructions */
 	if (!aarch32_break_handler(regs))
@@ -405,6 +406,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 	BUG_ON(!user_mode(regs));
 	force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
 }
+NOKPROBE_SYMBOL(do_undefinstr);
 
 #define __user_cache_maint(insn, address, res)			\
 	if (address >= user_addr_max()) {			\
@@ -470,6 +472,15 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
 	int rt = ESR_ELx_SYS64_ISS_RT(esr);
 	unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0);
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+		/* Hide DIC so that we can trap the unnecessary maintenance...*/
+		val &= ~BIT(CTR_DIC_SHIFT);
+
+		/* ... and fake IminLine to reduce the number of traps. */
+		val &= ~CTR_IMINLINE_MASK;
+		val |= (PAGE_SHIFT - 2) & CTR_IMINLINE_MASK;
+	}
+
 	pt_regs_write_reg(regs, rt, val);
 
 	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
@@ -667,7 +678,7 @@ static const struct sys64_hook cp15_64_hooks[] = {
 	{},
 };
 
-asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs)
+void do_cp15instr(unsigned int esr, struct pt_regs *regs)
 {
 	const struct sys64_hook *hook, *hook_base;
 
@@ -705,9 +716,10 @@ asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs)
 	 */
 	do_undefinstr(regs);
 }
+NOKPROBE_SYMBOL(do_cp15instr);
 #endif
 
-asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
+void do_sysinstr(unsigned int esr, struct pt_regs *regs)
 {
 	const struct sys64_hook *hook;
 
@@ -724,6 +736,7 @@ asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
 	 */
 	do_undefinstr(regs);
 }
+NOKPROBE_SYMBOL(do_sysinstr);
 
 static const char *esr_class_str[] = {
 	[0 ... ESR_ELx_EC_MAX]		= "UNRECOGNIZED EC",
@@ -793,7 +806,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
  * bad_el0_sync handles unexpected, but potentially recoverable synchronous
  * exceptions taken from EL0. Unlike bad_mode, this returns.
  */
-asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
+void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
 {
 	void __user *pc = (void __user *)instruction_pointer(regs);
 
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index aa76f7259668..009057517bdd 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -111,9 +111,6 @@ SECTIONS
 	}
 	.text : {			/* Real text segment		*/
 		_stext = .;		/* Text and read-only data	*/
-			__exception_text_start = .;
-			*(.exception.text)
-			__exception_text_end = .;
 			IRQENTRY_TEXT
 			SOFTIRQENTRY_TEXT
 			ENTRY_TEXT
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index a67121d419a2..a475c68cbfec 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -21,6 +21,8 @@ if VIRTUALIZATION
 config KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
 	depends on OF
+	# for TASKSTATS/TASK_DELAY_ACCT:
+	depends on NET && MULTIUSER
 	select MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
@@ -39,6 +41,8 @@ config KVM
 	select IRQ_BYPASS_MANAGER
 	select HAVE_KVM_IRQ_BYPASS
 	select HAVE_KVM_VCPU_RUN_PID_CHANGE
+	select TASKSTATS
+	select TASK_DELAY_ACCT
 	---help---
 	  Support hosting virtualized guest machines.
 	  We don't support KVM with 16K page tables yet, due to the multiple
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 3ac1a64d2fb9..5ffbdc39e780 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -13,6 +13,8 @@ obj-$(CONFIG_KVM_ARM_HOST) += hyp/
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/psci.o $(KVM)/arm/perf.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hypercalls.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/pvtime.o
 
 kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o va_layout.o
 kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index dfd626447482..2fff06114a8f 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -34,6 +34,10 @@
 #define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU }
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
+	VCPU_STAT(halt_successful_poll),
+	VCPU_STAT(halt_attempted_poll),
+	VCPU_STAT(halt_poll_invalid),
+	VCPU_STAT(halt_wakeup),
 	VCPU_STAT(hvc_exit_stat),
 	VCPU_STAT(wfe_exit_stat),
 	VCPU_STAT(wfi_exit_stat),
@@ -712,6 +716,12 @@ int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
 	if (events->exception.serror_pending && events->exception.serror_has_esr)
 		events->exception.serror_esr = vcpu_get_vsesr(vcpu);
 
+	/*
+	 * We never return a pending ext_dabt here because we deliver it to
+	 * the virtual CPU directly when setting the event and it's no longer
+	 * 'pending' at this point.
+	 */
+
 	return 0;
 }
 
@@ -720,6 +730,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 {
 	bool serror_pending = events->exception.serror_pending;
 	bool has_esr = events->exception.serror_has_esr;
+	bool ext_dabt_pending = events->exception.ext_dabt_pending;
 
 	if (serror_pending && has_esr) {
 		if (!cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
@@ -733,6 +744,9 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 		kvm_inject_vabt(vcpu);
 	}
 
+	if (ext_dabt_pending)
+		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+
 	return 0;
 }
 
@@ -858,6 +872,9 @@ int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
 	case KVM_ARM_VCPU_TIMER_CTRL:
 		ret = kvm_arm_timer_set_attr(vcpu, attr);
 		break;
+	case KVM_ARM_VCPU_PVTIME_CTRL:
+		ret = kvm_arm_pvtime_set_attr(vcpu, attr);
+		break;
 	default:
 		ret = -ENXIO;
 		break;
@@ -878,6 +895,9 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
 	case KVM_ARM_VCPU_TIMER_CTRL:
 		ret = kvm_arm_timer_get_attr(vcpu, attr);
 		break;
+	case KVM_ARM_VCPU_PVTIME_CTRL:
+		ret = kvm_arm_pvtime_get_attr(vcpu, attr);
+		break;
 	default:
 		ret = -ENXIO;
 		break;
@@ -898,6 +918,9 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
 	case KVM_ARM_VCPU_TIMER_CTRL:
 		ret = kvm_arm_timer_has_attr(vcpu, attr);
 		break;
+	case KVM_ARM_VCPU_PVTIME_CTRL:
+		ret = kvm_arm_pvtime_has_attr(vcpu, attr);
+		break;
 	default:
 		ret = -ENXIO;
 		break;
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 706cca23f0d2..aacfc55de44c 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -11,8 +11,6 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 
-#include <kvm/arm_psci.h>
-
 #include <asm/esr.h>
 #include <asm/exception.h>
 #include <asm/kvm_asm.h>
@@ -22,6 +20,8 @@
 #include <asm/debug-monitors.h>
 #include <asm/traps.h>
 
+#include <kvm/arm_hypercalls.h>
+
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 799e84a40335..72fbbd86eb5e 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -12,7 +12,7 @@
 
 #include <kvm/arm_psci.h>
 
-#include <asm/arch_gicv3.h>
+#include <asm/barrier.h>
 #include <asm/cpufeature.h>
 #include <asm/kprobes.h>
 #include <asm/kvm_asm.h>
@@ -118,6 +118,20 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
 	}
 
 	write_sysreg(val, cptr_el2);
+
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
+
+		isb();
+		/*
+		 * At this stage, and thanks to the above isb(), S2 is
+		 * configured and enabled. We can now restore the guest's S1
+		 * configuration: SCTLR, and only then TCR.
+		 */
+		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		isb();
+		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+	}
 }
 
 static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
@@ -159,6 +173,23 @@ static void __hyp_text __deactivate_traps_nvhe(void)
 {
 	u64 mdcr_el2 = read_sysreg(mdcr_el2);
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+		u64 val;
+
+		/*
+		 * Set the TCR and SCTLR registers in the exact opposite
+		 * sequence as __activate_traps_nvhe (first prevent walks,
+		 * then force the MMU on). A generous sprinkling of isb()
+		 * ensure that things happen in this exact order.
+		 */
+		val = read_sysreg_el1(SYS_TCR);
+		write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR);
+		isb();
+		val = read_sysreg_el1(SYS_SCTLR);
+		write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR);
+		isb();
+	}
+
 	__deactivate_traps_common();
 
 	mdcr_el2 &= MDCR_EL2_HPMN_MASK;
@@ -657,7 +688,7 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
 	 */
 	if (system_uses_irq_prio_masking()) {
 		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
-		dsb(sy);
+		pmr_sync();
 	}
 
 	vcpu = kern_hyp_va(vcpu);
@@ -670,18 +701,23 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
 
 	__sysreg_save_state_nvhe(host_ctxt);
 
-	__activate_vm(kern_hyp_va(vcpu->kvm));
-	__activate_traps(vcpu);
-
-	__hyp_vgic_restore_state(vcpu);
-	__timer_enable_traps(vcpu);
-
 	/*
 	 * We must restore the 32-bit state before the sysregs, thanks
 	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
+	 *
+	 * Also, and in order to be able to deal with erratum #1319537 (A57)
+	 * and #1319367 (A72), we must ensure that all VM-related sysreg are
+	 * restored before we enable S2 translation.
 	 */
 	__sysreg32_restore_state(vcpu);
 	__sysreg_restore_state_nvhe(guest_ctxt);
+
+	__activate_vm(kern_hyp_va(vcpu->kvm));
+	__activate_traps(vcpu);
+
+	__hyp_vgic_restore_state(vcpu);
+	__timer_enable_traps(vcpu);
+
 	__debug_switch_to_guest(vcpu);
 
 	__set_guest_arch_workaround_state(vcpu);
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 7ddbc849b580..22b8128d19f6 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -117,12 +117,26 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
 	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
-	write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+
+	if (!cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+	} else	if (!ctxt->__hyp_running_vcpu) {
+		/*
+		 * Must only be done for guest registers, hence the context
+		 * test. We're coming from the host, so SCTLR.M is already
+		 * set. Pairs with __activate_traps_nvhe().
+		 */
+		write_sysreg_el1((ctxt->sys_regs[TCR_EL1] |
+				  TCR_EPD1_MASK | TCR_EPD0_MASK),
+				 SYS_TCR);
+		isb();
+	}
+
 	write_sysreg(ctxt->sys_regs[ACTLR_EL1],		actlr_el1);
 	write_sysreg_el1(ctxt->sys_regs[CPACR_EL1],	SYS_CPACR);
 	write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1],	SYS_TTBR0);
 	write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1],	SYS_TTBR1);
-	write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
 	write_sysreg_el1(ctxt->sys_regs[ESR_EL1],	SYS_ESR);
 	write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1],	SYS_AFSR0);
 	write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1],	SYS_AFSR1);
@@ -135,6 +149,23 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
 	write_sysreg(ctxt->sys_regs[TPIDR_EL1],		tpidr_el1);
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367) &&
+	    ctxt->__hyp_running_vcpu) {
+		/*
+		 * Must only be done for host registers, hence the context
+		 * test. Pairs with __deactivate_traps_nvhe().
+		 */
+		isb();
+		/*
+		 * At this stage, and thanks to the above isb(), S2 is
+		 * deconfigured and disabled. We can now restore the host's
+		 * S1 configuration: SCTLR, and only then TCR.
+		 */
+		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		isb();
+		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+	}
+
 	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
 	write_sysreg_el1(ctxt->gp_regs.elr_el1,		SYS_ELR);
 	write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR);
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index eb0efc5557f3..c2bc17ca6430 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -63,6 +63,22 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
 static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
 						  struct tlb_inv_context *cxt)
 {
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+		u64 val;
+
+		/*
+		 * For CPUs that are affected by ARM 1319367, we need to
+		 * avoid a host Stage-1 walk while we have the guest's
+		 * VMID set in the VTTBR in order to invalidate TLBs.
+		 * We're guaranteed that the S1 MMU is enabled, so we can
+		 * simply set the EPD bits to avoid any further TLB fill.
+		 */
+		val = cxt->tcr = read_sysreg_el1(SYS_TCR);
+		val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
+		write_sysreg_el1(val, SYS_TCR);
+		isb();
+	}
+
 	__load_guest_stage2(kvm);
 	isb();
 }
@@ -100,6 +116,13 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
 						 struct tlb_inv_context *cxt)
 {
 	write_sysreg(0, vttbr_el2);
+
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+		/* Ensure write of the host VMID */
+		isb();
+		/* Restore the host's TCR_EL1 */
+		write_sysreg_el1(cxt->tcr, SYS_TCR);
+	}
 }
 
 static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index a9d25a305af5..ccdb6a051ab2 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -109,7 +109,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 
 /**
  * kvm_inject_dabt - inject a data abort into the guest
- * @vcpu: The VCPU to receive the undefined exception
+ * @vcpu: The VCPU to receive the data abort
  * @addr: The address to report in the DFAR
  *
  * It is assumed that this code is called from the VCPU thread and that the
@@ -125,7 +125,7 @@ void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr)
 
 /**
  * kvm_inject_pabt - inject a prefetch abort into the guest
- * @vcpu: The VCPU to receive the undefined exception
+ * @vcpu: The VCPU to receive the prefetch abort
  * @addr: The address to report in the DFAR
  *
  * It is assumed that this code is called from the VCPU thread and that the
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 9fc6db0bcbad..077b02a2d4d3 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -32,7 +32,8 @@
 #include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
-#include <asm/kasan.h>
+#include <asm/kprobes.h>
+#include <asm/processor.h>
 #include <asm/sysreg.h>
 #include <asm/system_misc.h>
 #include <asm/pgtable.h>
@@ -101,18 +102,6 @@ static void mem_abort_decode(unsigned int esr)
 		data_abort_decode(esr);
 }
 
-static inline bool is_ttbr0_addr(unsigned long addr)
-{
-	/* entry assembly clears tags for TTBR0 addrs */
-	return addr < TASK_SIZE;
-}
-
-static inline bool is_ttbr1_addr(unsigned long addr)
-{
-	/* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */
-	return arch_kasan_reset_tag(addr) >= PAGE_OFFSET;
-}
-
 static inline unsigned long mm_to_pgd_phys(struct mm_struct *mm)
 {
 	/* Either init_pg_dir or swapper_pg_dir */
@@ -318,6 +307,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 	if (is_el1_permission_fault(addr, esr, regs)) {
 		if (esr & ESR_ELx_WNR)
 			msg = "write to read-only memory";
+		else if (is_el1_instruction_abort(esr))
+			msg = "execute from non-executable memory";
 		else
 			msg = "read from unreadable memory";
 	} else if (addr < PAGE_SIZE) {
@@ -736,8 +727,7 @@ static const struct fault_info fault_info[] = {
 	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 63"			},
 };
 
-asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
-					 struct pt_regs *regs)
+void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 {
 	const struct fault_info *inf = esr_to_fault_info(esr);
 
@@ -753,43 +743,21 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 	arm64_notify_die(inf->name, regs,
 			 inf->sig, inf->code, (void __user *)addr, esr);
 }
+NOKPROBE_SYMBOL(do_mem_abort);
 
-asmlinkage void __exception do_el0_irq_bp_hardening(void)
+void do_el0_irq_bp_hardening(void)
 {
 	/* PC has already been checked in entry.S */
 	arm64_apply_bp_hardening();
 }
+NOKPROBE_SYMBOL(do_el0_irq_bp_hardening);
 
-asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr,
-						   unsigned int esr,
-						   struct pt_regs *regs)
-{
-	/*
-	 * We've taken an instruction abort from userspace and not yet
-	 * re-enabled IRQs. If the address is a kernel address, apply
-	 * BP hardening prior to enabling IRQs and pre-emption.
-	 */
-	if (!is_ttbr0_addr(addr))
-		arm64_apply_bp_hardening();
-
-	local_daif_restore(DAIF_PROCCTX);
-	do_mem_abort(addr, esr, regs);
-}
-
-
-asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
-					   unsigned int esr,
-					   struct pt_regs *regs)
+void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 {
-	if (user_mode(regs)) {
-		if (!is_ttbr0_addr(instruction_pointer(regs)))
-			arm64_apply_bp_hardening();
-		local_daif_restore(DAIF_PROCCTX);
-	}
-
 	arm64_notify_die("SP/PC alignment exception", regs,
 			 SIGBUS, BUS_ADRALN, (void __user *)addr, esr);
 }
+NOKPROBE_SYMBOL(do_sp_pc_abort);
 
 int __init early_brk64(unsigned long addr, unsigned int esr,
 		       struct pt_regs *regs);
@@ -872,8 +840,7 @@ NOKPROBE_SYMBOL(debug_exception_exit);
 #ifdef CONFIG_ARM64_ERRATUM_1463225
 DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
 
-static int __exception
-cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
+static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
 {
 	if (user_mode(regs))
 		return 0;
@@ -892,16 +859,15 @@ cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
 	return 1;
 }
 #else
-static int __exception
-cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
+static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
 {
 	return 0;
 }
 #endif /* CONFIG_ARM64_ERRATUM_1463225 */
+NOKPROBE_SYMBOL(cortex_a76_erratum_1463225_debug_handler);
 
-asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint,
-					       unsigned int esr,
-					       struct pt_regs *regs)
+void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
+			struct pt_regs *regs)
 {
 	const struct fault_info *inf = esr_to_debug_fault_info(esr);
 	unsigned long pc = instruction_pointer(regs);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 45c00a54909c..be9481cdf3b9 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -20,6 +20,7 @@
 #include <linux/sort.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
+#include <linux/dma-direct.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 #include <linux/efi.h>
@@ -41,6 +42,8 @@
 #include <asm/tlb.h>
 #include <asm/alternative.h>
 
+#define ARM64_ZONE_DMA_BITS	30
+
 /*
  * We need to be able to catch inadvertent references to memstart_addr
  * that occur (potentially in generic code) before arm64_memblock_init()
@@ -56,7 +59,14 @@ EXPORT_SYMBOL(physvirt_offset);
 struct page *vmemmap __ro_after_init;
 EXPORT_SYMBOL(vmemmap);
 
+/*
+ * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of
+ * memory as some devices, namely the Raspberry Pi 4, have peripherals with
+ * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32
+ * bit addressable memory area.
+ */
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
+static phys_addr_t arm64_dma32_phys_limit __ro_after_init;
 
 #ifdef CONFIG_KEXEC_CORE
 /*
@@ -81,7 +91,7 @@ static void __init reserve_crashkernel(void)
 
 	if (crash_base == 0) {
 		/* Current arm64 boot protocol requires 2MB alignment */
-		crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT,
+		crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
 				crash_size, SZ_2M);
 		if (crash_base == 0) {
 			pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
@@ -169,15 +179,16 @@ static void __init reserve_elfcorehdr(void)
 {
 }
 #endif /* CONFIG_CRASH_DUMP */
+
 /*
- * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)). It
- * currently assumes that for memory starting above 4G, 32-bit devices will
- * use a DMA offset.
+ * Return the maximum physical address for a zone with a given address size
+ * limit. It currently assumes that for memory starting above 4G, 32-bit
+ * devices will use a DMA offset.
  */
-static phys_addr_t __init max_zone_dma_phys(void)
+static phys_addr_t __init max_zone_phys(unsigned int zone_bits)
 {
-	phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32);
-	return min(offset + (1ULL << 32), memblock_end_of_DRAM());
+	phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, zone_bits);
+	return min(offset + (1ULL << zone_bits), memblock_end_of_DRAM());
 }
 
 #ifdef CONFIG_NUMA
@@ -186,8 +197,11 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
 
+#ifdef CONFIG_ZONE_DMA
+	max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
+#endif
 #ifdef CONFIG_ZONE_DMA32
-	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys());
+	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit);
 #endif
 	max_zone_pfns[ZONE_NORMAL] = max;
 
@@ -200,16 +214,21 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	struct memblock_region *reg;
 	unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
-	unsigned long max_dma = min;
+	unsigned long max_dma32 = min;
+	unsigned long __maybe_unused max_dma = min;
 
 	memset(zone_size, 0, sizeof(zone_size));
 
-	/* 4GB maximum for 32-bit only capable devices */
-#ifdef CONFIG_ZONE_DMA32
+#ifdef CONFIG_ZONE_DMA
 	max_dma = PFN_DOWN(arm64_dma_phys_limit);
-	zone_size[ZONE_DMA32] = max_dma - min;
+	zone_size[ZONE_DMA] = max_dma - min;
+	max_dma32 = max_dma;
+#endif
+#ifdef CONFIG_ZONE_DMA32
+	max_dma32 = PFN_DOWN(arm64_dma32_phys_limit);
+	zone_size[ZONE_DMA32] = max_dma32 - max_dma;
 #endif
-	zone_size[ZONE_NORMAL] = max - max_dma;
+	zone_size[ZONE_NORMAL] = max - max_dma32;
 
 	memcpy(zhole_size, zone_size, sizeof(zhole_size));
 
@@ -219,16 +238,22 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 
 		if (start >= max)
 			continue;
-
-#ifdef CONFIG_ZONE_DMA32
+#ifdef CONFIG_ZONE_DMA
 		if (start < max_dma) {
-			unsigned long dma_end = min(end, max_dma);
-			zhole_size[ZONE_DMA32] -= dma_end - start;
+			unsigned long dma_end = min_not_zero(end, max_dma);
+			zhole_size[ZONE_DMA] -= dma_end - start;
 		}
 #endif
-		if (end > max_dma) {
+#ifdef CONFIG_ZONE_DMA32
+		if (start < max_dma32) {
+			unsigned long dma32_end = min(end, max_dma32);
+			unsigned long dma32_start = max(start, max_dma);
+			zhole_size[ZONE_DMA32] -= dma32_end - dma32_start;
+		}
+#endif
+		if (end > max_dma32) {
 			unsigned long normal_end = min(end, max);
-			unsigned long normal_start = max(start, max_dma);
+			unsigned long normal_start = max(start, max_dma32);
 			zhole_size[ZONE_NORMAL] -= normal_end - normal_start;
 		}
 	}
@@ -418,11 +443,15 @@ void __init arm64_memblock_init(void)
 
 	early_init_fdt_scan_reserved_mem();
 
-	/* 4GB maximum for 32-bit only capable devices */
+	if (IS_ENABLED(CONFIG_ZONE_DMA)) {
+		zone_dma_bits = ARM64_ZONE_DMA_BITS;
+		arm64_dma_phys_limit = max_zone_phys(ARM64_ZONE_DMA_BITS);
+	}
+
 	if (IS_ENABLED(CONFIG_ZONE_DMA32))
-		arm64_dma_phys_limit = max_zone_dma_phys();
+		arm64_dma32_phys_limit = max_zone_phys(32);
 	else
-		arm64_dma_phys_limit = PHYS_MASK + 1;
+		arm64_dma32_phys_limit = PHYS_MASK + 1;
 
 	reserve_crashkernel();
 
@@ -430,7 +459,7 @@ void __init arm64_memblock_init(void)
 
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 
-	dma_contiguous_reserve(arm64_dma_phys_limit);
+	dma_contiguous_reserve(arm64_dma32_phys_limit);
 }
 
 void __init bootmem_init(void)
@@ -534,7 +563,7 @@ static void __init free_unused_memmap(void)
 void __init mem_init(void)
 {
 	if (swiotlb_force == SWIOTLB_FORCE ||
-	    max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+	    max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit))
 		swiotlb_init(1);
 	else
 		swiotlb_force = SWIOTLB_NO_FORCE;
@@ -571,7 +600,7 @@ void free_initmem(void)
 {
 	free_reserved_area(lm_alias(__init_begin),
 			   lm_alias(__init_end),
-			   0, "unused kernel");
+			   POISON_FREE_INITMEM, "unused kernel");
 	/*
 	 * Unmap the __init region but leave the VM area in place. This
 	 * prevents the region from being reused for kernel modules, which
@@ -580,18 +609,6 @@ void free_initmem(void)
 	unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init free_initrd_mem(unsigned long start, unsigned long end)
-{
-	unsigned long aligned_start, aligned_end;
-
-	aligned_start = __virt_to_phys(start) & PAGE_MASK;
-	aligned_end = PAGE_ALIGN(__virt_to_phys(end));
-	memblock_free(aligned_start, aligned_end - aligned_start);
-	free_reserved_area((void *)start, (void *)end, 0, "initrd");
-}
-#endif
-
 /*
  * Dump out memory limit information on panic.
  */
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 60c929f3683b..a9f541912289 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -338,7 +338,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 				 phys_addr_t (*pgtable_alloc)(int),
 				 int flags)
 {
-	unsigned long addr, length, end, next;
+	unsigned long addr, end, next;
 	pgd_t *pgdp = pgd_offset_raw(pgdir, virt);
 
 	/*
@@ -350,9 +350,8 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 
 	phys &= PAGE_MASK;
 	addr = virt & PAGE_MASK;
-	length = PAGE_ALIGN(size + (virt & ~PAGE_MASK));
+	end = PAGE_ALIGN(virt + size);
 
-	end = addr + length;
 	do {
 		next = pgd_addr_end(addr, end);
 		alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc,
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index bb320c6d0cc9..c49fcef754de 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -289,7 +289,7 @@ static void __init setup_crashkernel(unsigned long total, int *n)
 		}
 
 		if (!check_crashkernel_memory(base, size)) {
-			pr_warning("crashkernel: There would be kdump memory "
+			pr_warn("crashkernel: There would be kdump memory "
 				"at %ld GB but this is unusable because it "
 				"must\nbe below 4 GB. Change the memory "
 				"configuration of the machine.\n",
diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c
index 73bf5ea9ee1b..7ec3161e8517 100644
--- a/arch/m68k/atari/config.c
+++ b/arch/m68k/atari/config.c
@@ -869,8 +869,28 @@ static const struct resource atari_scsi_tt_rsrc[] __initconst = {
 };
 #endif
 
+/*
+ * Falcon IDE interface
+ */
+
+#define FALCON_IDE_BASE	0xfff00000
+
+static const struct resource atari_falconide_rsrc[] __initconst = {
+	{
+		.flags = IORESOURCE_MEM,
+		.start = FALCON_IDE_BASE,
+		.end   = FALCON_IDE_BASE + 0x39,
+	},
+	{
+		.flags = IORESOURCE_IRQ,
+		.start = IRQ_MFP_FSCSI,
+		.end   = IRQ_MFP_FSCSI,
+	},
+};
+
 int __init atari_platform_init(void)
 {
+	struct platform_device *pdev;
 	int rv = 0;
 
 	if (!MACH_IS_ATARI)
@@ -912,6 +932,13 @@ int __init atari_platform_init(void)
 			atari_scsi_tt_rsrc, ARRAY_SIZE(atari_scsi_tt_rsrc));
 #endif
 
+	if (ATARIHW_PRESENT(IDE)) {
+		pdev = platform_device_register_simple("atari-falcon-ide", -1,
+			atari_falconide_rsrc, ARRAY_SIZE(atari_falconide_rsrc));
+		if (IS_ERR(pdev))
+			rv = PTR_ERR(pdev);
+	}
+
 	return rv;
 }
 
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 9a33c1c006a1..619d30d663a2 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -355,6 +355,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -420,11 +421,15 @@ CONFIG_INPUT_M68K_BEEP=m
 # CONFIG_LEGACY_PTYS is not set
 CONFIG_PRINTER=m
 # CONFIG_HW_RANDOM is not set
+CONFIG_I2C=m
+CONFIG_I2C_CHARDEV=m
+CONFIG_I2C_ICY=m
 CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PPS_CLIENT_PARPORT=m
 CONFIG_PTP_1588_CLOCK=m
-# CONFIG_HWMON is not set
+CONFIG_HWMON=m
+CONFIG_SENSORS_LTC2990=m
 CONFIG_FB=y
 CONFIG_FB_CIRRUS=y
 CONFIG_FB_AMIGA=y
@@ -432,8 +437,6 @@ CONFIG_FB_AMIGA_OCS=y
 CONFIG_FB_AMIGA_ECS=y
 CONFIG_FB_AMIGA_AGA=y
 CONFIG_FB_FM2=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
@@ -490,6 +493,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -560,10 +564,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 7fdbc797a05d..caa0558abcdb 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -334,6 +334,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -393,8 +394,6 @@ CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_VGA16 is not set
@@ -450,6 +449,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -520,10 +520,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index f1763405a539..2551c7e9ac54 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -350,6 +350,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -417,8 +418,6 @@ CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
 CONFIG_FB=y
 CONFIG_FB_ATARI=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
@@ -472,6 +471,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -542,10 +542,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 91154d6acb31..4ffc1e5646d5 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -332,6 +332,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -390,8 +391,6 @@ CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
@@ -443,6 +442,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -513,10 +513,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index c398c4a94d95..806da3d97ca4 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -333,6 +333,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -395,8 +396,6 @@ CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
@@ -452,6 +451,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -522,10 +522,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 350d004559be..250da20e291c 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -342,6 +342,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -419,8 +420,6 @@ CONFIG_PTP_1588_CLOCK=m
 CONFIG_FB=y
 CONFIG_FB_VALKYRIE=y
 CONFIG_FB_MAC=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_HID=m
@@ -474,6 +473,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -544,10 +544,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index b838dd820348..b764a0368a56 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -386,6 +386,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -480,11 +481,15 @@ CONFIG_SERIAL_PMACZILOG_TTYS=y
 CONFIG_SERIAL_PMACZILOG_CONSOLE=y
 CONFIG_PRINTER=m
 # CONFIG_HW_RANDOM is not set
+CONFIG_I2C=m
+CONFIG_I2C_CHARDEV=m
+CONFIG_I2C_ICY=m
 CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PPS_CLIENT_PARPORT=m
 CONFIG_PTP_1588_CLOCK=m
-# CONFIG_HWMON is not set
+CONFIG_HWMON=m
+CONFIG_SENSORS_LTC2990=m
 CONFIG_FB=y
 CONFIG_FB_CIRRUS=y
 CONFIG_FB_AMIGA=y
@@ -495,8 +500,6 @@ CONFIG_FB_FM2=y
 CONFIG_FB_ATARI=y
 CONFIG_FB_VALKYRIE=y
 CONFIG_FB_MAC=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
@@ -556,6 +559,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -626,10 +630,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 3f8dd61559cf..7800d3a8d46e 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -331,6 +331,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -389,8 +390,6 @@ CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
@@ -442,6 +441,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -512,10 +512,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index ae3b2d4f636c..c32dc2d2058d 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -332,6 +332,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -390,8 +391,6 @@ CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
@@ -443,6 +442,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -513,10 +513,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index cd61ef14b582..bf0a65ce57e0 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -339,6 +339,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -404,8 +405,6 @@ CONFIG_PPS_CLIENT_PARPORT=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
@@ -461,6 +460,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -531,10 +531,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 151f5371cd3d..5f3cfa2926d2 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -329,6 +329,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -390,8 +391,6 @@ CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_HID=m
@@ -445,6 +444,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -515,10 +515,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 1dcb0ee1fe98..58354d2018d5 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -329,6 +329,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -389,8 +390,6 @@ CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_HID=m
@@ -444,6 +443,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -514,10 +514,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index e63eb5f06999..f31890078197 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -264,6 +264,7 @@ static int q40_get_rtc_pll(struct rtc_pll_info *pll)
 {
 	int tmp = Q40_RTC_CTRL;
 
+	pll->pll_ctrl = 0;
 	pll->pll_value = tmp & Q40_RTC_PLL_MASK;
 	if (tmp & Q40_RTC_PLL_SIGN)
 		pll->pll_value = -pll->pll_value;
diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms
index 0de839882106..a69b272a3ab0 100644
--- a/arch/mips/Kbuild.platforms
+++ b/arch/mips/Kbuild.platforms
@@ -17,6 +17,7 @@ platforms += jazz
 platforms += jz4740
 platforms += lantiq
 platforms += lasat
+platforms += loongson2ef
 platforms += loongson32
 platforms += loongson64
 platforms += mti-malta
@@ -30,6 +31,7 @@ platforms += ralink
 platforms += rb532
 platforms += sgi-ip22
 platforms += sgi-ip27
+platforms += sgi-ip30
 platforms += sgi-ip32
 platforms += sibyte
 platforms += sni
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index a0bd9bdb5f83..c86be02b6d89 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -7,6 +7,7 @@ config MIPS
 	select ARCH_CLOCKSOURCE_DATA
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_SUPPORTS_UPROBES
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF if 64BIT
@@ -86,6 +87,8 @@ config MIPS
 	select SYSCTL_EXCEPTION_TRACE
 	select VIRT_TO_BUS
 	select ARCH_HAS_PTE_SPECIAL if !(32BIT && CPU_HAS_RIXI)
+	select ARCH_HAS_KCOV
+	select HAVE_GCC_PLUGINS
 
 menu "Machine selection"
 
@@ -359,6 +362,8 @@ config MACH_DECSTATION
 
 config MACH_JAZZ
 	bool "Jazz family of machines"
+	select ARC_MEMORY
+	select ARC_PROMLIB
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select FW_ARC
@@ -441,7 +446,7 @@ config LASAT
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 
 config MACH_LOONGSON32
-	bool "Loongson-1 family of machines"
+	bool "Loongson 32-bit family of machines"
 	select SYS_SUPPORTS_ZBOOT
 	help
 	  This enables support for the Loongson-1 family of machines.
@@ -450,18 +455,48 @@ config MACH_LOONGSON32
 	  the Institute of Computing Technology (ICT), Chinese Academy of
 	  Sciences (CAS).
 
+config MACH_LOONGSON2EF
+	bool "Loongson-2E/F family of machines"
+	select SYS_SUPPORTS_ZBOOT
+	help
+	  This enables the support of early Loongson-2E/F family of machines.
+
 config MACH_LOONGSON64
-	bool "Loongson-2/3 family of machines"
+	bool "Loongson 64-bit family of machines"
+	select ARCH_SPARSEMEM_ENABLE
+	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_MIGHT_HAVE_PC_SERIO
+	select GENERIC_ISA_DMA_SUPPORT_BROKEN
+	select BOOT_ELF32
+	select BOARD_SCACHE
+	select CSRC_R4K
+	select CEVT_R4K
+	select CPU_HAS_WB
+	select FORCE_PCI
+	select ISA
+	select I8259
+	select IRQ_MIPS_CPU
+	select NR_CPUS_DEFAULT_4
+	select USE_GENERIC_EARLY_PRINTK_8250
+	select SYS_HAS_CPU_LOONGSON64
+	select SYS_HAS_EARLY_PRINTK
+	select SYS_SUPPORTS_SMP
+	select SYS_SUPPORTS_HOTPLUG_CPU
+	select SYS_SUPPORTS_NUMA
+	select SYS_SUPPORTS_64BIT_KERNEL
+	select SYS_SUPPORTS_HIGHMEM
+	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select SYS_SUPPORTS_ZBOOT
+	select LOONGSON_MC146818
+	select ZONE_DMA32
+	select NUMA
 	help
 	  This enables the support of Loongson-2/3 family of machines.
 
-	  Loongson-2 is a family of single-core CPUs and Loongson-3 is a
-	  family of multi-core CPUs. They are both 64-bit general-purpose
-	  MIPS-compatible CPUs. Loongson-2/3 are developed by the Institute
-	  of Computing Technology (ICT), Chinese Academy of Sciences (CAS)
-	  in the People's Republic of China. The chief architect is Professor
-	  Weiwu Hu.
+	  Loongson-2 and Loongson-3 are 64-bit general-purpose processors with
+	  GS264/GS464/GS464E/GS464V microarchitecture (except old Loongson-2E
+	  and Loongson-2F which will be removed), developed by the Institute
+	  of Computing Technology (ICT), Chinese Academy of Sciences (CAS).
 
 config MACH_PISTACHIO
 	bool "IMG Pistachio SoC based boards"
@@ -631,6 +666,8 @@ config RALINK
 
 config SGI_IP22
 	bool "SGI IP22 (Indy/Indigo2)"
+	select ARC_MEMORY
+	select ARC_PROMLIB
 	select FW_ARC
 	select FW_ARC32
 	select ARCH_MIGHT_HAVE_PC_SERIO
@@ -654,14 +691,7 @@ config SGI_IP22
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_R4X00
 	select SYS_HAS_CPU_R5000
-	#
-	# Disable EARLY_PRINTK for now since it leads to overwritten prom
-	# memory during early boot on some machines.
-	#
-	# See http://www.linux-mips.org/cgi-bin/mesg.cgi?a=linux-mips&i=20091119164009.GA15038%40deprecation.cyrius.com
-	# for a more details discussion
-	#
-	# select SYS_HAS_EARLY_PRINTK
+	select SYS_HAS_EARLY_PRINTK
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
@@ -674,8 +704,10 @@ config SGI_IP22
 config SGI_IP27
 	bool "SGI IP27 (Origin200/2000)"
 	select ARCH_HAS_PHYS_TO_DMA
+	select ARCH_SPARSEMEM_ENABLE
 	select FW_ARC
 	select FW_ARC64
+	select ARC_CMDLINE_ONLY
 	select BOOT_ELF64
 	select DEFAULT_SGI_PARTITION
 	select SYS_HAS_EARLY_PRINTK
@@ -698,6 +730,8 @@ config SGI_IP27
 
 config SGI_IP28
 	bool "SGI IP28 (Indigo2 R10k)"
+	select ARC_MEMORY
+	select ARC_PROMLIB
 	select FW_ARC
 	select FW_ARC64
 	select ARCH_MIGHT_HAVE_PC_SERIO
@@ -719,14 +753,7 @@ config SGI_IP28
 	select SGI_HAS_ZILOG
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_R10000
-	#
-	# Disable EARLY_PRINTK for now since it leads to overwritten prom
-	# memory during early boot on some machines.
-	#
-	# See http://www.linux-mips.org/cgi-bin/mesg.cgi?a=linux-mips&i=20091119164009.GA15038%40deprecation.cyrius.com
-	# for a more details discussion
-	#
-	# select SYS_HAS_EARLY_PRINTK
+	select SYS_HAS_EARLY_PRINTK
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select MIPS_L1_CACHE_SHIFT_7
@@ -734,8 +761,37 @@ config SGI_IP28
 	  This is the SGI Indigo2 with R10000 processor.  To compile a Linux
 	  kernel that runs on these, say Y here.
 
+config SGI_IP30
+	bool "SGI IP30 (Octane/Octane2)"
+	select ARCH_HAS_PHYS_TO_DMA
+	select FW_ARC
+	select FW_ARC64
+	select BOOT_ELF64
+	select CEVT_R4K
+	select CSRC_R4K
+	select SYNC_R4K if SMP
+	select ZONE_DMA32
+	select HAVE_PCI
+	select IRQ_MIPS_CPU
+	select IRQ_DOMAIN_HIERARCHY
+	select NR_CPUS_DEFAULT_2
+	select PCI_DRIVERS_GENERIC
+	select PCI_XTALK_BRIDGE
+	select SYS_HAS_EARLY_PRINTK
+	select SYS_HAS_CPU_R10000
+	select SYS_SUPPORTS_64BIT_KERNEL
+	select SYS_SUPPORTS_BIG_ENDIAN
+	select SYS_SUPPORTS_SMP
+	select MIPS_L1_CACHE_SHIFT_7
+	select ARC_MEMORY
+	help
+	  These are the SGI Octane and Octane2 graphics workstations.  To
+	  compile a Linux kernel that runs on these, say Y here.
+
 config SGI_IP32
 	bool "SGI IP32 (O2)"
+	select ARC_MEMORY
+	select ARC_PROMLIB
 	select ARCH_HAS_PHYS_TO_DMA
 	select FW_ARC
 	select FW_ARC32
@@ -843,6 +899,8 @@ config SIBYTE_BIGSUR
 
 config SNI_RM
 	bool "SNI RM200/300/400"
+	select ARC_MEMORY
+	select ARC_PROMLIB
 	select FW_ARC if CPU_LITTLE_ENDIAN
 	select FW_ARC32 if CPU_LITTLE_ENDIAN
 	select FW_SNIPROM if CPU_BIG_ENDIAN
@@ -1038,6 +1096,7 @@ source "arch/mips/sibyte/Kconfig"
 source "arch/mips/txx9/Kconfig"
 source "arch/mips/vr41xx/Kconfig"
 source "arch/mips/cavium-octeon/Kconfig"
+source "arch/mips/loongson2ef/Kconfig"
 source "arch/mips/loongson32/Kconfig"
 source "arch/mips/loongson64/Kconfig"
 source "arch/mips/netlogic/Kconfig"
@@ -1353,19 +1412,18 @@ config MIPS_L1_CACHE_SHIFT
 config HAVE_STD_PC_SERIAL_PORT
 	bool
 
+config ARC_CMDLINE_ONLY
+	bool
+
 config ARC_CONSOLE
 	bool "ARC console support"
 	depends on SGI_IP22 || SGI_IP28 || (SNI_RM && CPU_LITTLE_ENDIAN)
 
 config ARC_MEMORY
 	bool
-	depends on MACH_JAZZ || SNI_RM || SGI_IP32
-	default y
 
 config ARC_PROMLIB
 	bool
-	depends on MACH_JAZZ || SNI_RM || SGI_IP22 || SGI_IP28 || SGI_IP32
-	default y
 
 config FW_ARC64
 	bool
@@ -1379,51 +1437,56 @@ choice
 	prompt "CPU type"
 	default CPU_R4X00
 
-config CPU_LOONGSON3
-	bool "Loongson 3 CPU"
-	depends on SYS_HAS_CPU_LOONGSON3
+config CPU_LOONGSON64
+	bool "Loongson 64-bit CPU"
+	depends on SYS_HAS_CPU_LOONGSON64
 	select ARCH_HAS_PHYS_TO_DMA
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_HUGEPAGES
+	select CPU_SUPPORTS_MSA
 	select CPU_HAS_LOAD_STORE_LR
 	select WEAK_ORDERING
 	select WEAK_REORDERING_BEYOND_LLSC
+	select MIPS_ASID_BITS_VARIABLE
 	select MIPS_PGD_C0_CONTEXT
 	select MIPS_L1_CACHE_SHIFT_6
 	select GPIOLIB
 	select SWIOTLB
 	help
-		The Loongson 3 processor implements the MIPS64R2 instruction
-		set with many extensions.
+		The Loongson GSx64(GS264/GS464/GS464E/GS464V) series of processor
+		cores implements the MIPS64R2 instruction set with many extensions,
+		including most 64-bit Loongson-2 (2H, 2K) and Loongson-3 (3A1000,
+		3B1000, 3B1500, 3A2000, 3A3000 and 3A4000) processors. However, old
+		Loongson-2E/2F is not covered here and will be removed in future.
 
 config LOONGSON3_ENHANCEMENT
-	bool "New Loongson 3 CPU Enhancements"
+	bool "New Loongson-3 CPU Enhancements"
 	default n
 	select CPU_MIPSR2
 	select CPU_HAS_PREFETCH
-	depends on CPU_LOONGSON3
+	depends on CPU_LOONGSON64
 	help
-	  New Loongson 3 CPU (since Loongson-3A R2, as opposed to Loongson-3A
+	  New Loongson-3 cores (since Loongson-3A R2, as opposed to Loongson-3A
 	  R1, Loongson-3B R1 and Loongson-3B R2) has many enhancements, such as
-	  FTLB, L1-VCache, EI/DI/Wait/Prefetch instruction, DSP/DSPv2 ASE, User
+	  FTLB, L1-VCache, EI/DI/Wait/Prefetch instruction, DSP/DSPr2 ASE, User
 	  Local register, Read-Inhibit/Execute-Inhibit, SFB (Store Fill Buffer),
 	  Fast TLB refill support, etc.
 
 	  This option enable those enhancements which are not probed at run
 	  time. If you want a generic kernel to run on all Loongson 3 machines,
 	  please say 'N' here. If you want a high-performance kernel to run on
-	  new Loongson 3 machines only, please say 'Y' here.
+	  new Loongson-3 machines only, please say 'Y' here.
 
 config CPU_LOONGSON3_WORKAROUNDS
-	bool "Old Loongson 3 LLSC Workarounds"
+	bool "Old Loongson-3 LLSC Workarounds"
 	default y if SMP
-	depends on CPU_LOONGSON3
+	depends on CPU_LOONGSON64
 	help
-	  Loongson 3 processors have the llsc issues which require workarounds.
+	  Loongson-3 processors have the llsc issues which require workarounds.
 	  Without workarounds the system may hang unexpectedly.
 
-	  Newer Loongson 3 will fix these issues and no workarounds are needed.
+	  Newer Loongson-3 will fix these issues and no workarounds are needed.
 	  The workarounds have no significant side effect on them but may
 	  decrease the performance of the system so this option should be
 	  disabled unless the kernel is intended to be run on old systems.
@@ -1433,7 +1496,7 @@ config CPU_LOONGSON3_WORKAROUNDS
 config CPU_LOONGSON2E
 	bool "Loongson 2E"
 	depends on SYS_HAS_CPU_LOONGSON2E
-	select CPU_LOONGSON2
+	select CPU_LOONGSON2EF
 	help
 	  The Loongson 2E processor implements the MIPS III instruction set
 	  with many extensions.
@@ -1444,7 +1507,7 @@ config CPU_LOONGSON2E
 config CPU_LOONGSON2F
 	bool "Loongson 2F"
 	depends on SYS_HAS_CPU_LOONGSON2F
-	select CPU_LOONGSON2
+	select CPU_LOONGSON2EF
 	select GPIOLIB
 	help
 	  The Loongson 2F processor implements the MIPS III instruction set
@@ -1457,7 +1520,7 @@ config CPU_LOONGSON2F
 config CPU_LOONGSON1B
 	bool "Loongson 1B"
 	depends on SYS_HAS_CPU_LOONGSON1B
-	select CPU_LOONGSON1
+	select CPU_LOONGSON32
 	select LEDS_GPIO_REGISTER
 	help
 	  The Loongson 1B is a 32-bit SoC, which implements the MIPS32
@@ -1467,7 +1530,7 @@ config CPU_LOONGSON1B
 config CPU_LOONGSON1C
 	bool "Loongson 1C"
 	depends on SYS_HAS_CPU_LOONGSON1C
-	select CPU_LOONGSON1
+	select CPU_LOONGSON32
 	select LEDS_GPIO_REGISTER
 	help
 	  The Loongson 1C is a 32-bit SoC, which implements the MIPS32
@@ -1857,7 +1920,7 @@ config SYS_SUPPORTS_ZBOOT_UART_PROM
 	bool
 	select SYS_SUPPORTS_ZBOOT
 
-config CPU_LOONGSON2
+config CPU_LOONGSON2EF
 	bool
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
@@ -1866,7 +1929,7 @@ config CPU_LOONGSON2
 	select ARCH_HAS_PHYS_TO_DMA
 	select CPU_HAS_LOAD_STORE_LR
 
-config CPU_LOONGSON1
+config CPU_LOONGSON32
 	bool
 	select CPU_MIPS32
 	select CPU_MIPSR2
@@ -1900,7 +1963,7 @@ config CPU_BMIPS5000
 	select SYS_SUPPORTS_HOTPLUG_CPU
 	select CPU_HAS_RIXI
 
-config SYS_HAS_CPU_LOONGSON3
+config SYS_HAS_CPU_LOONGSON64
 	bool
 	select CPU_SUPPORTS_CPUFREQ
 	select CPU_HAS_RIXI
@@ -1912,7 +1975,6 @@ config SYS_HAS_CPU_LOONGSON2F
 	bool
 	select CPU_SUPPORTS_CPUFREQ
 	select CPU_SUPPORTS_ADDRWINCFG if 64BIT
-	select CPU_SUPPORTS_UNCACHED_ACCELERATED
 
 config SYS_HAS_CPU_LOONGSON1B
 	bool
@@ -2089,8 +2151,6 @@ config CPU_SUPPORTS_ADDRWINCFG
 config CPU_SUPPORTS_HUGEPAGES
 	bool
 	depends on !(32BIT && (ARCH_PHYS_ADDR_T_64BIT || EVA))
-config CPU_SUPPORTS_UNCACHED_ACCELERATED
-	bool
 config MIPS_PGD_C0_CONTEXT
 	bool
 	default y if 64BIT && (CPU_MIPSR2 || CPU_MIPSR6) && !CPU_XLP
@@ -2162,7 +2222,7 @@ choice
 
 config PAGE_SIZE_4KB
 	bool "4kB"
-	depends on !CPU_LOONGSON2 && !CPU_LOONGSON3
+	depends on !CPU_LOONGSON2EF && !CPU_LOONGSON64
 	help
 	  This option select the standard 4kB Linux page size.  On some
 	  R3000-family processors this is the only available page size.  Using
@@ -2554,6 +2614,10 @@ config CPU_R4000_WORKAROUNDS
 config CPU_R4400_WORKAROUNDS
 	bool
 
+config CPU_R4X00_BUGS64
+	bool
+	default y if SYS_HAS_CPU_R4X00 && 64BIT && (TARGET_ISA_REV < 1)
+
 config MIPS_ASID_SHIFT
 	int
 	default 6 if CPU_R3000 || CPU_TX39XX
@@ -2612,20 +2676,11 @@ config CPU_SUPPORTS_MSA
 
 config ARCH_FLATMEM_ENABLE
 	def_bool y
-	depends on !NUMA && !CPU_LOONGSON2
-
-config ARCH_DISCONTIGMEM_ENABLE
-	bool
-	default y if SGI_IP27
-	help
-	  Say Y to support efficient handling of discontiguous physical memory,
-	  for architectures which are either NUMA (Non-Uniform Memory Access)
-	  or have huge holes in the physical address space for other reasons.
-	  See <file:Documentation/vm/numa.rst> for more.
+	depends on !NUMA && !CPU_LOONGSON2EF
 
 config ARCH_SPARSEMEM_ENABLE
 	bool
-	select SPARSEMEM_STATIC
+	select SPARSEMEM_STATIC if !SGI_IP27
 
 config NUMA
 	bool "NUMA Support"
@@ -2702,7 +2757,7 @@ config NODES_SHIFT
 
 config HW_PERF_EVENTS
 	bool "Enable hardware performance counter support for perf events"
-	depends on PERF_EVENTS && !OPROFILE && (CPU_MIPS32 || CPU_MIPS64 || CPU_R10000 || CPU_SB1 || CPU_CAVIUM_OCTEON || CPU_XLP || CPU_LOONGSON3)
+	depends on PERF_EVENTS && !OPROFILE && (CPU_MIPS32 || CPU_MIPS64 || CPU_R10000 || CPU_SB1 || CPU_CAVIUM_OCTEON || CPU_XLP || CPU_LOONGSON64)
 	default y
 	help
 	  Enable hardware performance counter support for perf events. If
diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug
index 0c86b2a2adfc..93a2974d2ab7 100644
--- a/arch/mips/Kconfig.debug
+++ b/arch/mips/Kconfig.debug
@@ -32,7 +32,6 @@ config USE_GENERIC_EARLY_PRINTK_8250
 
 config CMDLINE_BOOL
 	bool "Built-in kernel command line"
-	default n
 	help
 	  For most systems, it is firmware or second stage bootloader that
 	  by default specifies the kernel command line options.  However,
@@ -53,7 +52,6 @@ config CMDLINE_BOOL
 config CMDLINE
 	string "Default kernel command string"
 	depends on CMDLINE_BOOL
-	default ""
 	help
 	  On some platforms, there is currently no way for the boot loader to
 	  pass arguments to the kernel.  For these platforms, and for the cases
@@ -68,7 +66,6 @@ config CMDLINE
 
 config CMDLINE_OVERRIDE
 	bool "Built-in command line overrides firmware arguments"
-	default n
 	depends on CMDLINE_BOOL
 	help
 	  By setting this option to 'Y' you will have your kernel ignore
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index cdc09b71febe..e1c44aed8156 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -14,6 +14,9 @@
 
 archscripts: scripts_basic
 	$(Q)$(MAKE) $(build)=arch/mips/tools elf-entry
+ifeq ($(CONFIG_CPU_LOONGSON3_WORKAROUNDS),y)
+	$(Q)$(MAKE) $(build)=arch/mips/tools loongson3-llsc-check
+endif
 	$(Q)$(MAKE) $(build)=arch/mips/boot/tools relocs
 
 KBUILD_DEFCONFIG := 32r2el_defconfig
@@ -323,7 +326,7 @@ libs-$(CONFIG_MIPS_FP_SUPPORT) += arch/mips/math-emu/
 # See arch/mips/Kbuild for content of core part of the kernel
 core-y += arch/mips/
 
-drivers-$(CONFIG_MIPS_CRC_SUPPORT) += arch/mips/crypto/
+drivers-y			+= arch/mips/crypto/
 drivers-$(CONFIG_OPROFILE)	+= arch/mips/oprofile/
 
 # suspend and hibernation support
diff --git a/arch/mips/Makefile.postlink b/arch/mips/Makefile.postlink
index 4eea4188cb20..f03fdc95143e 100644
--- a/arch/mips/Makefile.postlink
+++ b/arch/mips/Makefile.postlink
@@ -3,7 +3,8 @@
 # Post-link MIPS pass
 # ===========================================================================
 #
-# 1. Insert relocations into vmlinux
+# 1. Check that Loongson3 LL/SC workarounds are applied correctly
+# 2. Insert relocations into vmlinux
 
 PHONY := __archpost
 __archpost:
@@ -11,6 +12,10 @@ __archpost:
 -include include/config/auto.conf
 include scripts/Kbuild.include
 
+CMD_LS3_LLSC = arch/mips/tools/loongson3-llsc-check
+quiet_cmd_ls3_llsc = LLSCCHK $@
+      cmd_ls3_llsc = $(CMD_LS3_LLSC) $@
+
 CMD_RELOCS = arch/mips/boot/tools/relocs
 quiet_cmd_relocs = RELOCS $@
       cmd_relocs = $(CMD_RELOCS) $@
@@ -19,6 +24,9 @@ quiet_cmd_relocs = RELOCS $@
 
 vmlinux: FORCE
 	@true
+ifeq ($(CONFIG_CPU_LOONGSON3_WORKAROUNDS),y)
+	$(call if_changed,ls3_llsc)
+endif
 ifeq ($(CONFIG_RELOCATABLE),y)
 	$(call if_changed,relocs)
 endif
diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts
index 2e9952311ecd..37b93166bf22 100644
--- a/arch/mips/boot/dts/ingenic/ci20.dts
+++ b/arch/mips/boot/dts/ingenic/ci20.dts
@@ -25,12 +25,47 @@
 		       0x30000000 0x30000000>;
 	};
 
+	leds {
+		compatible = "gpio-leds";
+
+		led0 {
+			label = "ci20:red:led0";
+			gpios = <&gpc 3 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "none";
+		};
+
+		led1 {
+			label = "ci20:red:led1";
+			gpios = <&gpc 2 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "nand-disk";
+		};
+
+		led2 {
+			label = "ci20:red:led2";
+			gpios = <&gpc 1 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "cpu1";
+		};
+
+		led3 {
+			label = "ci20:red:led3";
+			gpios = <&gpc 0 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "cpu0";
+		};
+	};
+
 	eth0_power: fixedregulator@0 {
 		compatible = "regulator-fixed";
 		regulator-name = "eth0_power";
 		gpio = <&gpb 25 GPIO_ACTIVE_LOW>;
 		enable-active-high;
 	};
+
+	wlan0_power: fixedregulator@1 {
+		compatible = "regulator-fixed";
+		regulator-name = "wlan0_power";
+		gpio = <&gpb 19 GPIO_ACTIVE_LOW>;
+		enable-active-high;
+	};
 };
 
 &ext {
@@ -54,9 +89,18 @@
 
 	bus-width = <4>;
 	max-frequency = <50000000>;
+	non-removable;
 
 	pinctrl-names = "default";
 	pinctrl-0 = <&pins_mmc1>;
+
+	brcmf: wifi@1 {
+/*		reg = <4>;*/
+		compatible = "brcm,bcm4330-fmac";
+		vcc-supply = <&wlan0_power>;
+		device-wakeup-gpios = <&gpd 9 GPIO_ACTIVE_HIGH>;
+		shutdown-gpios = <&gpf 7 GPIO_ACTIVE_LOW>;
+	};
 };
 
 &uart0 {
@@ -73,6 +117,23 @@
 	pinctrl-0 = <&pins_uart1>;
 };
 
+&uart2 {
+	status = "okay";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pins_uart2>;
+	uart-has-rtscts;
+
+	bluetooth {
+		compatible = "brcm,bcm4330-bt";
+		reset-gpios = <&gpf 8 GPIO_ACTIVE_HIGH>;
+		vcc-supply = <&wlan0_power>;
+		device-wakeup-gpios = <&gpf 5 GPIO_ACTIVE_HIGH>;
+		host-wakeup-gpios = <&gpf 6 GPIO_ACTIVE_HIGH>;
+		shutdown-gpios = <&gpf 4 GPIO_ACTIVE_LOW>;
+	};
+};
+
 &uart3 {
 	status = "okay";
 
@@ -87,6 +148,123 @@
 	pinctrl-0 = <&pins_uart4>;
 };
 
+&i2c0 {
+	status = "okay";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pins_i2c0>;
+
+	clock-frequency = <400000>;
+
+	act8600: act8600@5a {
+		compatible = "active-semi,act8600";
+		reg = <0x5a>;
+		status = "okay";
+
+		regulators {
+			vddcore: SUDCDC1 {
+				regulator-name = "VDDCORE";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-always-on;
+			};
+			vddmem: SUDCDC2 {
+				regulator-name = "VDDMEM";
+				regulator-min-microvolt = <1500000>;
+				regulator-max-microvolt = <1500000>;
+				regulator-always-on;
+			};
+			vcc_33: SUDCDC3 {
+				regulator-name = "VCC33";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+			vcc_50: SUDCDC4 {
+				regulator-name = "VCC50";
+				regulator-min-microvolt = <5000000>;
+				regulator-max-microvolt = <5000000>;
+				regulator-always-on;
+			};
+			vcc_25: LDO_REG5 {
+				regulator-name = "VCC25";
+				regulator-min-microvolt = <2500000>;
+				regulator-max-microvolt = <2500000>;
+				regulator-always-on;
+			};
+			wifi_io: LDO_REG6 {
+				regulator-name = "WIFIIO";
+				regulator-min-microvolt = <2500000>;
+				regulator-max-microvolt = <2500000>;
+				regulator-always-on;
+			};
+			vcc_28: LDO_REG7 {
+				regulator-name = "VCC28";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-always-on;
+			};
+			vcc_15: LDO_REG8 {
+				regulator-name = "VCC15";
+				regulator-min-microvolt = <1500000>;
+				regulator-max-microvolt = <1500000>;
+				regulator-always-on;
+			};
+			vcc_18: LDO_REG9 {
+				regulator-name = "VCC18";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+			};
+			vcc_11: LDO_REG10 {
+				regulator-name = "VCC11";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-always-on;
+			};
+		};
+	};
+};
+
+&i2c1 {
+	status = "okay";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pins_i2c1>;
+
+};
+
+&i2c2 {
+	status = "okay";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pins_i2c2>;
+
+};
+
+&i2c3 {
+	status = "okay";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pins_i2c3>;
+
+};
+
+&i2c4 {
+	status = "okay";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pins_i2c4>;
+
+	clock-frequency = <400000>;
+
+		rtc@51 {
+			compatible = "nxp,pcf8563";
+			reg = <0x51>;
+			interrupts = <110>;
+		};
+};
+
 &nemc {
 	status = "okay";
 
@@ -197,6 +375,12 @@
 		bias-disable;
 	};
 
+	pins_uart2: uart2 {
+		function = "uart2";
+		groups = "uart2-data", "uart2-hwflow";
+		bias-disable;
+	};
+
 	pins_uart3: uart3 {
 		function = "uart3";
 		groups = "uart3-data", "uart3-hwflow";
@@ -209,6 +393,36 @@
 		bias-disable;
 	};
 
+	pins_i2c0: i2c0 {
+		function = "i2c0";
+		groups = "i2c0-data";
+		bias-disable;
+	};
+
+	pins_i2c1: i2c1 {
+		function = "i2c1";
+		groups = "i2c1-data";
+		bias-disable;
+	};
+
+	pins_i2c2: i2c2 {
+		function = "i2c2";
+		groups = "i2c2-data";
+		bias-disable;
+	};
+
+	pins_i2c3: i2c3 {
+		function = "i2c3";
+		groups = "i2c3-data";
+		bias-disable;
+	};
+
+	pins_i2c4: i2c4 {
+		function = "i2c4";
+		groups = "i2c4-data-e";
+		bias-disable;
+	};
+
 	pins_nemc: nemc {
 		function = "nemc";
 		groups = "nemc-data", "nemc-cle-ale", "nemc-rd-we", "nemc-frd-fwe";
diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi
index c54bd7cfec55..f928329b034b 100644
--- a/arch/mips/boot/dts/ingenic/jz4780.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi
@@ -262,6 +262,92 @@
 		status = "disabled";
 	};
 
+	i2c0: i2c@10050000 {
+		compatible = "ingenic,jz4780-i2c";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		reg = <0x10050000 0x1000>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <60>;
+
+		clocks = <&cgu JZ4780_CLK_SMB0>;
+		clock-frequency = <100000>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pins_i2c0_data>;
+
+		status = "disabled";
+	};
+
+	i2c1: i2c@10051000 {
+		compatible = "ingenic,jz4780-i2c";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x10051000 0x1000>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <59>;
+
+		clocks = <&cgu JZ4780_CLK_SMB1>;
+		clock-frequency = <100000>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pins_i2c1_data>;
+
+		status = "disabled";
+	};
+
+	i2c2: i2c@10052000 {
+		compatible = "ingenic,jz4780-i2c";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x10052000 0x1000>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <58>;
+
+		clocks = <&cgu JZ4780_CLK_SMB2>;
+		clock-frequency = <100000>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pins_i2c2_data>;
+
+		status = "disabled";
+	};
+
+	i2c3: i2c@10053000 {
+		compatible = "ingenic,jz4780-i2c";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x10053000 0x1000>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <57>;
+
+		clocks = <&cgu JZ4780_CLK_SMB3>;
+		clock-frequency = <100000>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pins_i2c3_data>;
+
+		status = "disabled";
+	};
+
+	i2c4: i2c@10054000 {
+		compatible = "ingenic,jz4780-i2c";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x10054000 0x1000>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <56>;
+
+		clocks = <&cgu JZ4780_CLK_SMB4>;
+		clock-frequency = <100000>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pins_i2c4_data>;
+
+		status = "disabled";
+	};
+
 	watchdog: watchdog@10002000 {
 		compatible = "ingenic,jz4780-watchdog";
 		reg = <0x10002000 0x10>;
diff --git a/arch/mips/boot/dts/ralink/gardena_smart_gateway_mt7688.dts b/arch/mips/boot/dts/ralink/gardena_smart_gateway_mt7688.dts
new file mode 100644
index 000000000000..aa5caaa31104
--- /dev/null
+++ b/arch/mips/boot/dts/ralink/gardena_smart_gateway_mt7688.dts
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019 Stefan Roese <sr@denx.de>
+ */
+
+/dts-v1/;
+
+/include/ "mt7628a.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+
+/ {
+	compatible = "gardena,smart-gateway-mt7688", "ralink,mt7688a-soc",
+		     "ralink,mt7628a-soc";
+	model = "GARDENA smart Gateway (MT7688)";
+
+	memory@0 {
+		device_type = "memory";
+		reg = <0x0 0x8000000>;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinmux_gpio_gpio>;	/* GPIO11 */
+
+		user_btn1 {
+			label = "USER_BTN1";
+			gpios = <&gpio 11 GPIO_ACTIVE_LOW>;
+			linux,code =<KEY_PROG1> ;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinmux_pwm0_gpio>,	/* GPIO18 */
+			    <&pinmux_pwm1_gpio>,	/* GPIO19 */
+			    <&pinmux_sdmode_gpio>,	/* GPIO22..29 */
+			    <&pinmux_p0led_an_gpio>;	/* GPIO43 */
+		/*
+		 * <&pinmux_i2s_gpio> (covers GPIO0..3) is needed here as
+		 * well for GPIO3. But this is already claimed for uart1
+		 * (see below). So we can't include it in this LED node.
+		 */
+
+		power_blue {
+			label = "smartgw:power:blue";
+			gpios = <&gpio 18 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		power_green {
+			label = "smartgw:power:green";
+			gpios = <&gpio 19 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		power_red {
+			label = "smartgw:power:red";
+			gpios = <&gpio 22 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		radio_blue {
+			label = "smartgw:radio:blue";
+			gpios = <&gpio 23 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		radio_green {
+			label = "smartgw:radio:green";
+			gpios = <&gpio 24 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		radio_red {
+			label = "smartgw:radio:red";
+			gpios = <&gpio 25 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		internet_blue {
+			label = "smartgw:internet:blue";
+			gpios = <&gpio 26 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		internet_green {
+			label = "smartgw:internet:green";
+			gpios = <&gpio 27 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		internet_red {
+			label = "smartgw:internet:red";
+			gpios = <&gpio 28 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		ethernet_link {
+			label = "smartgw:eth:link";
+			gpios = <&gpio 3 GPIO_ACTIVE_LOW>;
+			linux,default-trigger = "netdev";
+		};
+
+		ethernet_activity {
+			label = "smartgw:eth:act";
+			gpios = <&gpio 43 GPIO_ACTIVE_LOW>;
+			linux,default-trigger = "netdev";
+		};
+	};
+
+	aliases {
+		serial0 = &uart0;
+	};
+};
+
+&i2c {
+	status = "okay";
+};
+
+&spi {
+	status = "okay";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinmux_spi_spi>, <&pinmux_spi_cs1_cs>;
+
+	m25p80@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <40000000>;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			partition@0 {
+				label = "uboot";
+				reg = <0x0 0xa0000>;
+				read-only;
+			};
+
+			partition@a0000 {
+				label = "uboot_env0";
+				reg = <0xa0000 0x10000>;
+			};
+
+			partition@b0000 {
+				label = "uboot_env1";
+				reg = <0xb0000 0x10000>;
+			};
+
+			factory: partition@c0000 {
+				label = "factory";
+				reg = <0xc0000 0x10000>;
+				read-only;
+			};
+		};
+	};
+
+	nand_flash@1 {
+		compatible = "spi-nand";
+		linux,mtd-name = "gd5f";
+		reg = <1>;
+		spi-max-frequency = <40000000>;
+	};
+};
+
+&uart1 {
+	status = "okay";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinmux_i2s_gpio>;		/* GPIO0..3 */
+
+	rts-gpios = <&gpio 1 GPIO_ACTIVE_LOW>;
+	cts-gpios = <&gpio 2 GPIO_ACTIVE_LOW>;
+};
+
+&uart2 {
+	status = "okay";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinmux_p2led_an_gpio>,	/* GPIO41 */
+		    <&pinmux_p3led_an_gpio>;	/* GPIO40 */
+
+	rts-gpios = <&gpio 40 GPIO_ACTIVE_LOW>;
+	cts-gpios = <&gpio 41 GPIO_ACTIVE_LOW>;
+};
+
+&watchdog {
+	status = "okay";
+};
diff --git a/arch/mips/boot/dts/ralink/mt7628a.dtsi b/arch/mips/boot/dts/ralink/mt7628a.dtsi
index 61f8621e88b3..742bcc1dc2e0 100644
--- a/arch/mips/boot/dts/ralink/mt7628a.dtsi
+++ b/arch/mips/boot/dts/ralink/mt7628a.dtsi
@@ -199,6 +199,22 @@
 			status = "disabled";
 		};
 
+		i2c: i2c@900 {
+			compatible = "mediatek,mt7621-i2c";
+			reg = <0x900 0x100>;
+
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinmux_i2c_i2c>;
+
+			resets = <&resetc 16>;
+			reset-names = "i2c";
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			status = "disabled";
+		};
+
 		uart0: uartlite@c00 {
 			compatible = "ns16550a";
 			reg = <0xc00 0x100>;
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 95034bf5ca83..1f742c32a883 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -844,7 +844,7 @@ void __init prom_init(void)
 	 * BIST should always be enabled when doing a soft reset. L2
 	 * Cache locking for instance is not cleared unless BIST is
 	 * enabled.  Unfortunately due to a chip errata G-200 for
-	 * Cn38XX and CN31XX, BIST msut be disabled on these parts.
+	 * Cn38XX and CN31XX, BIST must be disabled on these parts.
 	 */
 	if (OCTEON_IS_MODEL(OCTEON_CN38XX_PASS2) ||
 	    OCTEON_IS_MODEL(OCTEON_CN31XX))
diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig
index 7a7af706e898..1788ae23bff9 100644
--- a/arch/mips/configs/fuloong2e_defconfig
+++ b/arch/mips/configs/fuloong2e_defconfig
@@ -15,7 +15,7 @@ CONFIG_EXPERT=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
-CONFIG_MACH_LOONGSON64=y
+CONFIG_MACH_LOONGSON2EF=y
 CONFIG_PCI=y
 CONFIG_MIPS32_O32=y
 CONFIG_MIPS32_N32=y
diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig
index d44f1469cf64..f9f93427c9bd 100644
--- a/arch/mips/configs/lemote2f_defconfig
+++ b/arch/mips/configs/lemote2f_defconfig
@@ -12,7 +12,7 @@ CONFIG_LOG_BUF_SHIFT=15
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 CONFIG_PROFILING=y
-CONFIG_MACH_LOONGSON64=y
+CONFIG_MACH_LOONGSON2EF=y
 CONFIG_LEMOTE_MACH2F=y
 CONFIG_KEXEC=y
 # CONFIG_SECCOMP is not set
diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig
index 90ee0084d786..c16a2330e84d 100644
--- a/arch/mips/configs/loongson3_defconfig
+++ b/arch/mips/configs/loongson3_defconfig
@@ -12,7 +12,6 @@ CONFIG_TASKSTATS=y
 CONFIG_TASK_DELAY_ACCT=y
 CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_LOG_BUF_SHIFT=14
 CONFIG_MEMCG=y
 CONFIG_MEMCG_SWAP=y
 CONFIG_BLK_CGROUP=y
@@ -24,7 +23,6 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_SYSCTL_SYSCALL=y
 CONFIG_EMBEDDED=y
 CONFIG_MACH_LOONGSON64=y
-CONFIG_LOONGSON_MACH3X=y
 CONFIG_SMP=y
 CONFIG_HZ_256=y
 CONFIG_KEXEC=y
diff --git a/arch/mips/crypto/Makefile b/arch/mips/crypto/Makefile
index e07aca572c2e..8e1deaf00e0c 100644
--- a/arch/mips/crypto/Makefile
+++ b/arch/mips/crypto/Makefile
@@ -4,3 +4,21 @@
 #
 
 obj-$(CONFIG_CRYPTO_CRC32_MIPS) += crc32-mips.o
+
+obj-$(CONFIG_CRYPTO_CHACHA_MIPS) += chacha-mips.o
+chacha-mips-y := chacha-core.o chacha-glue.o
+AFLAGS_chacha-core.o += -O2 # needed to fill branch delay slots
+
+obj-$(CONFIG_CRYPTO_POLY1305_MIPS) += poly1305-mips.o
+poly1305-mips-y := poly1305-core.o poly1305-glue.o
+
+perlasm-flavour-$(CONFIG_CPU_MIPS32) := o32
+perlasm-flavour-$(CONFIG_CPU_MIPS64) := 64
+
+quiet_cmd_perlasm = PERLASM $@
+      cmd_perlasm = $(PERL) $(<) $(perlasm-flavour-y) $(@)
+
+$(obj)/poly1305-core.S: $(src)/poly1305-mips.pl FORCE
+	$(call if_changed,perlasm)
+
+targets += poly1305-core.S
diff --git a/arch/mips/crypto/chacha-core.S b/arch/mips/crypto/chacha-core.S
new file mode 100644
index 000000000000..5755f69cfe00
--- /dev/null
+++ b/arch/mips/crypto/chacha-core.S
@@ -0,0 +1,497 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/*
+ * Copyright (C) 2016-2018 René van Dorst <opensource@vdorst.com>. All Rights Reserved.
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#define MASK_U32		0x3c
+#define CHACHA20_BLOCK_SIZE	64
+#define STACK_SIZE		32
+
+#define X0	$t0
+#define X1	$t1
+#define X2	$t2
+#define X3	$t3
+#define X4	$t4
+#define X5	$t5
+#define X6	$t6
+#define X7	$t7
+#define X8	$t8
+#define X9	$t9
+#define X10	$v1
+#define X11	$s6
+#define X12	$s5
+#define X13	$s4
+#define X14	$s3
+#define X15	$s2
+/* Use regs which are overwritten on exit for Tx so we don't leak clear data. */
+#define T0	$s1
+#define T1	$s0
+#define T(n)	T ## n
+#define X(n)	X ## n
+
+/* Input arguments */
+#define STATE		$a0
+#define OUT		$a1
+#define IN		$a2
+#define BYTES		$a3
+
+/* Output argument */
+/* NONCE[0] is kept in a register and not in memory.
+ * We don't want to touch original value in memory.
+ * Must be incremented every loop iteration.
+ */
+#define NONCE_0		$v0
+
+/* SAVED_X and SAVED_CA are set in the jump table.
+ * Use regs which are overwritten on exit else we don't leak clear data.
+ * They are used to handling the last bytes which are not multiple of 4.
+ */
+#define SAVED_X		X15
+#define SAVED_CA	$s7
+
+#define IS_UNALIGNED	$s7
+
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+#define MSB 0
+#define LSB 3
+#define ROTx rotl
+#define ROTR(n) rotr n, 24
+#define	CPU_TO_LE32(n) \
+	wsbh	n; \
+	rotr	n, 16;
+#else
+#define MSB 3
+#define LSB 0
+#define ROTx rotr
+#define CPU_TO_LE32(n)
+#define ROTR(n)
+#endif
+
+#define FOR_EACH_WORD(x) \
+	x( 0); \
+	x( 1); \
+	x( 2); \
+	x( 3); \
+	x( 4); \
+	x( 5); \
+	x( 6); \
+	x( 7); \
+	x( 8); \
+	x( 9); \
+	x(10); \
+	x(11); \
+	x(12); \
+	x(13); \
+	x(14); \
+	x(15);
+
+#define FOR_EACH_WORD_REV(x) \
+	x(15); \
+	x(14); \
+	x(13); \
+	x(12); \
+	x(11); \
+	x(10); \
+	x( 9); \
+	x( 8); \
+	x( 7); \
+	x( 6); \
+	x( 5); \
+	x( 4); \
+	x( 3); \
+	x( 2); \
+	x( 1); \
+	x( 0);
+
+#define PLUS_ONE_0	 1
+#define PLUS_ONE_1	 2
+#define PLUS_ONE_2	 3
+#define PLUS_ONE_3	 4
+#define PLUS_ONE_4	 5
+#define PLUS_ONE_5	 6
+#define PLUS_ONE_6	 7
+#define PLUS_ONE_7	 8
+#define PLUS_ONE_8	 9
+#define PLUS_ONE_9	10
+#define PLUS_ONE_10	11
+#define PLUS_ONE_11	12
+#define PLUS_ONE_12	13
+#define PLUS_ONE_13	14
+#define PLUS_ONE_14	15
+#define PLUS_ONE_15	16
+#define PLUS_ONE(x)	PLUS_ONE_ ## x
+#define _CONCAT3(a,b,c)	a ## b ## c
+#define CONCAT3(a,b,c)	_CONCAT3(a,b,c)
+
+#define STORE_UNALIGNED(x) \
+CONCAT3(.Lchacha_mips_xor_unaligned_, PLUS_ONE(x), _b: ;) \
+	.if (x != 12); \
+		lw	T0, (x*4)(STATE); \
+	.endif; \
+	lwl	T1, (x*4)+MSB ## (IN); \
+	lwr	T1, (x*4)+LSB ## (IN); \
+	.if (x == 12); \
+		addu	X ## x, NONCE_0; \
+	.else; \
+		addu	X ## x, T0; \
+	.endif; \
+	CPU_TO_LE32(X ## x); \
+	xor	X ## x, T1; \
+	swl	X ## x, (x*4)+MSB ## (OUT); \
+	swr	X ## x, (x*4)+LSB ## (OUT);
+
+#define STORE_ALIGNED(x) \
+CONCAT3(.Lchacha_mips_xor_aligned_, PLUS_ONE(x), _b: ;) \
+	.if (x != 12); \
+		lw	T0, (x*4)(STATE); \
+	.endif; \
+	lw	T1, (x*4) ## (IN); \
+	.if (x == 12); \
+		addu	X ## x, NONCE_0; \
+	.else; \
+		addu	X ## x, T0; \
+	.endif; \
+	CPU_TO_LE32(X ## x); \
+	xor	X ## x, T1; \
+	sw	X ## x, (x*4) ## (OUT);
+
+/* Jump table macro.
+ * Used for setup and handling the last bytes, which are not multiple of 4.
+ * X15 is free to store Xn
+ * Every jumptable entry must be equal in size.
+ */
+#define JMPTBL_ALIGNED(x) \
+.Lchacha_mips_jmptbl_aligned_ ## x: ; \
+	.set	noreorder; \
+	b	.Lchacha_mips_xor_aligned_ ## x ## _b; \
+	.if (x == 12); \
+		addu	SAVED_X, X ## x, NONCE_0; \
+	.else; \
+		addu	SAVED_X, X ## x, SAVED_CA; \
+	.endif; \
+	.set	reorder
+
+#define JMPTBL_UNALIGNED(x) \
+.Lchacha_mips_jmptbl_unaligned_ ## x: ; \
+	.set	noreorder; \
+	b	.Lchacha_mips_xor_unaligned_ ## x ## _b; \
+	.if (x == 12); \
+		addu	SAVED_X, X ## x, NONCE_0; \
+	.else; \
+		addu	SAVED_X, X ## x, SAVED_CA; \
+	.endif; \
+	.set	reorder
+
+#define AXR(A, B, C, D,  K, L, M, N,  V, W, Y, Z,  S) \
+	addu	X(A), X(K); \
+	addu	X(B), X(L); \
+	addu	X(C), X(M); \
+	addu	X(D), X(N); \
+	xor	X(V), X(A); \
+	xor	X(W), X(B); \
+	xor	X(Y), X(C); \
+	xor	X(Z), X(D); \
+	rotl	X(V), S;    \
+	rotl	X(W), S;    \
+	rotl	X(Y), S;    \
+	rotl	X(Z), S;
+
+.text
+.set	reorder
+.set	noat
+.globl	chacha_crypt_arch
+.ent	chacha_crypt_arch
+chacha_crypt_arch:
+	.frame	$sp, STACK_SIZE, $ra
+
+	/* Load number of rounds */
+	lw	$at, 16($sp)
+
+	addiu	$sp, -STACK_SIZE
+
+	/* Return bytes = 0. */
+	beqz	BYTES, .Lchacha_mips_end
+
+	lw	NONCE_0, 48(STATE)
+
+	/* Save s0-s7 */
+	sw	$s0,  0($sp)
+	sw	$s1,  4($sp)
+	sw	$s2,  8($sp)
+	sw	$s3, 12($sp)
+	sw	$s4, 16($sp)
+	sw	$s5, 20($sp)
+	sw	$s6, 24($sp)
+	sw	$s7, 28($sp)
+
+	/* Test IN or OUT is unaligned.
+	 * IS_UNALIGNED = ( IN | OUT ) & 0x00000003
+	 */
+	or	IS_UNALIGNED, IN, OUT
+	andi	IS_UNALIGNED, 0x3
+
+	b	.Lchacha_rounds_start
+
+.align 4
+.Loop_chacha_rounds:
+	addiu	IN,  CHACHA20_BLOCK_SIZE
+	addiu	OUT, CHACHA20_BLOCK_SIZE
+	addiu	NONCE_0, 1
+
+.Lchacha_rounds_start:
+	lw	X0,  0(STATE)
+	lw	X1,  4(STATE)
+	lw	X2,  8(STATE)
+	lw	X3,  12(STATE)
+
+	lw	X4,  16(STATE)
+	lw	X5,  20(STATE)
+	lw	X6,  24(STATE)
+	lw	X7,  28(STATE)
+	lw	X8,  32(STATE)
+	lw	X9,  36(STATE)
+	lw	X10, 40(STATE)
+	lw	X11, 44(STATE)
+
+	move	X12, NONCE_0
+	lw	X13, 52(STATE)
+	lw	X14, 56(STATE)
+	lw	X15, 60(STATE)
+
+.Loop_chacha_xor_rounds:
+	addiu	$at, -2
+	AXR( 0, 1, 2, 3,  4, 5, 6, 7, 12,13,14,15, 16);
+	AXR( 8, 9,10,11, 12,13,14,15,  4, 5, 6, 7, 12);
+	AXR( 0, 1, 2, 3,  4, 5, 6, 7, 12,13,14,15,  8);
+	AXR( 8, 9,10,11, 12,13,14,15,  4, 5, 6, 7,  7);
+	AXR( 0, 1, 2, 3,  5, 6, 7, 4, 15,12,13,14, 16);
+	AXR(10,11, 8, 9, 15,12,13,14,  5, 6, 7, 4, 12);
+	AXR( 0, 1, 2, 3,  5, 6, 7, 4, 15,12,13,14,  8);
+	AXR(10,11, 8, 9, 15,12,13,14,  5, 6, 7, 4,  7);
+	bnez	$at, .Loop_chacha_xor_rounds
+
+	addiu	BYTES, -(CHACHA20_BLOCK_SIZE)
+
+	/* Is data src/dst unaligned? Jump */
+	bnez	IS_UNALIGNED, .Loop_chacha_unaligned
+
+	/* Set number rounds here to fill delayslot. */
+	lw	$at, (STACK_SIZE+16)($sp)
+
+	/* BYTES < 0, it has no full block. */
+	bltz	BYTES, .Lchacha_mips_no_full_block_aligned
+
+	FOR_EACH_WORD_REV(STORE_ALIGNED)
+
+	/* BYTES > 0? Loop again. */
+	bgtz	BYTES, .Loop_chacha_rounds
+
+	/* Place this here to fill delay slot */
+	addiu	NONCE_0, 1
+
+	/* BYTES < 0? Handle last bytes */
+	bltz	BYTES, .Lchacha_mips_xor_bytes
+
+.Lchacha_mips_xor_done:
+	/* Restore used registers */
+	lw	$s0,  0($sp)
+	lw	$s1,  4($sp)
+	lw	$s2,  8($sp)
+	lw	$s3, 12($sp)
+	lw	$s4, 16($sp)
+	lw	$s5, 20($sp)
+	lw	$s6, 24($sp)
+	lw	$s7, 28($sp)
+
+	/* Write NONCE_0 back to right location in state */
+	sw	NONCE_0, 48(STATE)
+
+.Lchacha_mips_end:
+	addiu	$sp, STACK_SIZE
+	jr	$ra
+
+.Lchacha_mips_no_full_block_aligned:
+	/* Restore the offset on BYTES */
+	addiu	BYTES, CHACHA20_BLOCK_SIZE
+
+	/* Get number of full WORDS */
+	andi	$at, BYTES, MASK_U32
+
+	/* Load upper half of jump table addr */
+	lui	T0, %hi(.Lchacha_mips_jmptbl_aligned_0)
+
+	/* Calculate lower half jump table offset */
+	ins	T0, $at, 1, 6
+
+	/* Add offset to STATE */
+	addu	T1, STATE, $at
+
+	/* Add lower half jump table addr */
+	addiu	T0, %lo(.Lchacha_mips_jmptbl_aligned_0)
+
+	/* Read value from STATE */
+	lw	SAVED_CA, 0(T1)
+
+	/* Store remaining bytecounter as negative value */
+	subu	BYTES, $at, BYTES
+
+	jr	T0
+
+	/* Jump table */
+	FOR_EACH_WORD(JMPTBL_ALIGNED)
+
+
+.Loop_chacha_unaligned:
+	/* Set number rounds here to fill delayslot. */
+	lw	$at, (STACK_SIZE+16)($sp)
+
+	/* BYTES > 0, it has no full block. */
+	bltz	BYTES, .Lchacha_mips_no_full_block_unaligned
+
+	FOR_EACH_WORD_REV(STORE_UNALIGNED)
+
+	/* BYTES > 0? Loop again. */
+	bgtz	BYTES, .Loop_chacha_rounds
+
+	/* Write NONCE_0 back to right location in state */
+	sw	NONCE_0, 48(STATE)
+
+	.set noreorder
+	/* Fall through to byte handling */
+	bgez	BYTES, .Lchacha_mips_xor_done
+.Lchacha_mips_xor_unaligned_0_b:
+.Lchacha_mips_xor_aligned_0_b:
+	/* Place this here to fill delay slot */
+	addiu	NONCE_0, 1
+	.set reorder
+
+.Lchacha_mips_xor_bytes:
+	addu	IN, $at
+	addu	OUT, $at
+	/* First byte */
+	lbu	T1, 0(IN)
+	addiu	$at, BYTES, 1
+	CPU_TO_LE32(SAVED_X)
+	ROTR(SAVED_X)
+	xor	T1, SAVED_X
+	sb	T1, 0(OUT)
+	beqz	$at, .Lchacha_mips_xor_done
+	/* Second byte */
+	lbu	T1, 1(IN)
+	addiu	$at, BYTES, 2
+	ROTx	SAVED_X, 8
+	xor	T1, SAVED_X
+	sb	T1, 1(OUT)
+	beqz	$at, .Lchacha_mips_xor_done
+	/* Third byte */
+	lbu	T1, 2(IN)
+	ROTx	SAVED_X, 8
+	xor	T1, SAVED_X
+	sb	T1, 2(OUT)
+	b	.Lchacha_mips_xor_done
+
+.Lchacha_mips_no_full_block_unaligned:
+	/* Restore the offset on BYTES */
+	addiu	BYTES, CHACHA20_BLOCK_SIZE
+
+	/* Get number of full WORDS */
+	andi	$at, BYTES, MASK_U32
+
+	/* Load upper half of jump table addr */
+	lui	T0, %hi(.Lchacha_mips_jmptbl_unaligned_0)
+
+	/* Calculate lower half jump table offset */
+	ins	T0, $at, 1, 6
+
+	/* Add offset to STATE */
+	addu	T1, STATE, $at
+
+	/* Add lower half jump table addr */
+	addiu	T0, %lo(.Lchacha_mips_jmptbl_unaligned_0)
+
+	/* Read value from STATE */
+	lw	SAVED_CA, 0(T1)
+
+	/* Store remaining bytecounter as negative value */
+	subu	BYTES, $at, BYTES
+
+	jr	T0
+
+	/* Jump table */
+	FOR_EACH_WORD(JMPTBL_UNALIGNED)
+.end chacha_crypt_arch
+.set at
+
+/* Input arguments
+ * STATE	$a0
+ * OUT		$a1
+ * NROUND	$a2
+ */
+
+#undef X12
+#undef X13
+#undef X14
+#undef X15
+
+#define X12	$a3
+#define X13	$at
+#define X14	$v0
+#define X15	STATE
+
+.set noat
+.globl	hchacha_block_arch
+.ent	hchacha_block_arch
+hchacha_block_arch:
+	.frame	$sp, STACK_SIZE, $ra
+
+	addiu	$sp, -STACK_SIZE
+
+	/* Save X11(s6) */
+	sw	X11, 0($sp)
+
+	lw	X0,  0(STATE)
+	lw	X1,  4(STATE)
+	lw	X2,  8(STATE)
+	lw	X3,  12(STATE)
+	lw	X4,  16(STATE)
+	lw	X5,  20(STATE)
+	lw	X6,  24(STATE)
+	lw	X7,  28(STATE)
+	lw	X8,  32(STATE)
+	lw	X9,  36(STATE)
+	lw	X10, 40(STATE)
+	lw	X11, 44(STATE)
+	lw	X12, 48(STATE)
+	lw	X13, 52(STATE)
+	lw	X14, 56(STATE)
+	lw	X15, 60(STATE)
+
+.Loop_hchacha_xor_rounds:
+	addiu	$a2, -2
+	AXR( 0, 1, 2, 3,  4, 5, 6, 7, 12,13,14,15, 16);
+	AXR( 8, 9,10,11, 12,13,14,15,  4, 5, 6, 7, 12);
+	AXR( 0, 1, 2, 3,  4, 5, 6, 7, 12,13,14,15,  8);
+	AXR( 8, 9,10,11, 12,13,14,15,  4, 5, 6, 7,  7);
+	AXR( 0, 1, 2, 3,  5, 6, 7, 4, 15,12,13,14, 16);
+	AXR(10,11, 8, 9, 15,12,13,14,  5, 6, 7, 4, 12);
+	AXR( 0, 1, 2, 3,  5, 6, 7, 4, 15,12,13,14,  8);
+	AXR(10,11, 8, 9, 15,12,13,14,  5, 6, 7, 4,  7);
+	bnez	$a2, .Loop_hchacha_xor_rounds
+
+	/* Restore used register */
+	lw	X11, 0($sp)
+
+	sw	X0,  0(OUT)
+	sw	X1,  4(OUT)
+	sw	X2,  8(OUT)
+	sw	X3,  12(OUT)
+	sw	X12, 16(OUT)
+	sw	X13, 20(OUT)
+	sw	X14, 24(OUT)
+	sw	X15, 28(OUT)
+
+	addiu	$sp, STACK_SIZE
+	jr	$ra
+.end hchacha_block_arch
+.set at
diff --git a/arch/mips/crypto/chacha-glue.c b/arch/mips/crypto/chacha-glue.c
new file mode 100644
index 000000000000..779e399c9bef
--- /dev/null
+++ b/arch/mips/crypto/chacha-glue.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * MIPS accelerated ChaCha and XChaCha stream ciphers,
+ * including ChaCha20 (RFC7539)
+ *
+ * Copyright (C) 2019 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/byteorder.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/chacha.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+asmlinkage void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src,
+				  unsigned int bytes, int nrounds);
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+asmlinkage void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds);
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
+{
+	chacha_init_generic(state, key, iv);
+}
+EXPORT_SYMBOL(chacha_init_arch);
+
+static int chacha_mips_stream_xor(struct skcipher_request *req,
+				  const struct chacha_ctx *ctx, const u8 *iv)
+{
+	struct skcipher_walk walk;
+	u32 state[16];
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	chacha_init_generic(state, ctx->key, iv);
+
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
+
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, walk.stride);
+
+		chacha_crypt(state, walk.dst.virt.addr, walk.src.virt.addr,
+			     nbytes, ctx->nrounds);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+	}
+
+	return err;
+}
+
+static int chacha_mips(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	return chacha_mips_stream_xor(req, ctx, req->iv);
+}
+
+static int xchacha_mips(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct chacha_ctx subctx;
+	u32 state[16];
+	u8 real_iv[16];
+
+	chacha_init_generic(state, ctx->key, req->iv);
+
+	hchacha_block(state, subctx.key, ctx->nrounds);
+	subctx.nrounds = ctx->nrounds;
+
+	memcpy(&real_iv[0], req->iv + 24, 8);
+	memcpy(&real_iv[8], req->iv + 16, 8);
+	return chacha_mips_stream_xor(req, &subctx, real_iv);
+}
+
+static struct skcipher_alg algs[] = {
+	{
+		.base.cra_name		= "chacha20",
+		.base.cra_driver_name	= "chacha20-mips",
+		.base.cra_priority	= 200,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= CHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.setkey			= chacha20_setkey,
+		.encrypt		= chacha_mips,
+		.decrypt		= chacha_mips,
+	}, {
+		.base.cra_name		= "xchacha20",
+		.base.cra_driver_name	= "xchacha20-mips",
+		.base.cra_priority	= 200,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= XCHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.setkey			= chacha20_setkey,
+		.encrypt		= xchacha_mips,
+		.decrypt		= xchacha_mips,
+	}, {
+		.base.cra_name		= "xchacha12",
+		.base.cra_driver_name	= "xchacha12-mips",
+		.base.cra_priority	= 200,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= XCHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.setkey			= chacha12_setkey,
+		.encrypt		= xchacha_mips,
+		.decrypt		= xchacha_mips,
+	}
+};
+
+static int __init chacha_simd_mod_init(void)
+{
+	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit chacha_simd_mod_fini(void)
+{
+	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
+}
+
+module_init(chacha_simd_mod_init);
+module_exit(chacha_simd_mod_fini);
+
+MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (MIPS accelerated)");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("chacha20");
+MODULE_ALIAS_CRYPTO("chacha20-mips");
+MODULE_ALIAS_CRYPTO("xchacha20");
+MODULE_ALIAS_CRYPTO("xchacha20-mips");
+MODULE_ALIAS_CRYPTO("xchacha12");
+MODULE_ALIAS_CRYPTO("xchacha12-mips");
diff --git a/arch/mips/crypto/poly1305-glue.c b/arch/mips/crypto/poly1305-glue.c
new file mode 100644
index 000000000000..b759b6ccc361
--- /dev/null
+++ b/arch/mips/crypto/poly1305-glue.c
@@ -0,0 +1,203 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * OpenSSL/Cryptogams accelerated Poly1305 transform for MIPS
+ *
+ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/unaligned.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/poly1305.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+asmlinkage void poly1305_init_mips(void *state, const u8 *key);
+asmlinkage void poly1305_blocks_mips(void *state, const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_emit_mips(void *state, __le32 *digest, const u32 *nonce);
+
+void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key)
+{
+	poly1305_init_mips(&dctx->h, key);
+	dctx->s[0] = get_unaligned_le32(key + 16);
+	dctx->s[1] = get_unaligned_le32(key + 20);
+	dctx->s[2] = get_unaligned_le32(key + 24);
+	dctx->s[3] = get_unaligned_le32(key + 28);
+	dctx->buflen = 0;
+}
+EXPORT_SYMBOL(poly1305_init_arch);
+
+static int mips_poly1305_init(struct shash_desc *desc)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	dctx->buflen = 0;
+	dctx->rset = 0;
+	dctx->sset = false;
+
+	return 0;
+}
+
+static void mips_poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
+				 u32 len, u32 hibit)
+{
+	if (unlikely(!dctx->sset)) {
+		if (!dctx->rset) {
+			poly1305_init_mips(&dctx->h, src);
+			src += POLY1305_BLOCK_SIZE;
+			len -= POLY1305_BLOCK_SIZE;
+			dctx->rset = 1;
+		}
+		if (len >= POLY1305_BLOCK_SIZE) {
+			dctx->s[0] = get_unaligned_le32(src +  0);
+			dctx->s[1] = get_unaligned_le32(src +  4);
+			dctx->s[2] = get_unaligned_le32(src +  8);
+			dctx->s[3] = get_unaligned_le32(src + 12);
+			src += POLY1305_BLOCK_SIZE;
+			len -= POLY1305_BLOCK_SIZE;
+			dctx->sset = true;
+		}
+		if (len < POLY1305_BLOCK_SIZE)
+			return;
+	}
+
+	len &= ~(POLY1305_BLOCK_SIZE - 1);
+
+	poly1305_blocks_mips(&dctx->h, src, len, hibit);
+}
+
+static int mips_poly1305_update(struct shash_desc *desc, const u8 *src,
+				unsigned int len)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (unlikely(dctx->buflen)) {
+		u32 bytes = min(len, POLY1305_BLOCK_SIZE - dctx->buflen);
+
+		memcpy(dctx->buf + dctx->buflen, src, bytes);
+		src += bytes;
+		len -= bytes;
+		dctx->buflen += bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			mips_poly1305_blocks(dctx, dctx->buf, POLY1305_BLOCK_SIZE, 1);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (likely(len >= POLY1305_BLOCK_SIZE)) {
+		mips_poly1305_blocks(dctx, src, len, 1);
+		src += round_down(len, POLY1305_BLOCK_SIZE);
+		len %= POLY1305_BLOCK_SIZE;
+	}
+
+	if (unlikely(len)) {
+		dctx->buflen = len;
+		memcpy(dctx->buf, src, len);
+	}
+	return 0;
+}
+
+void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
+			  unsigned int nbytes)
+{
+	if (unlikely(dctx->buflen)) {
+		u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);
+
+		memcpy(dctx->buf + dctx->buflen, src, bytes);
+		src += bytes;
+		nbytes -= bytes;
+		dctx->buflen += bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			poly1305_blocks_mips(&dctx->h, dctx->buf,
+					     POLY1305_BLOCK_SIZE, 1);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
+		unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);
+
+		poly1305_blocks_mips(&dctx->h, src, len, 1);
+		src += len;
+		nbytes %= POLY1305_BLOCK_SIZE;
+	}
+
+	if (unlikely(nbytes)) {
+		dctx->buflen = nbytes;
+		memcpy(dctx->buf, src, nbytes);
+	}
+}
+EXPORT_SYMBOL(poly1305_update_arch);
+
+void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
+{
+	__le32 digest[4];
+	u64 f = 0;
+
+	if (unlikely(dctx->buflen)) {
+		dctx->buf[dctx->buflen++] = 1;
+		memset(dctx->buf + dctx->buflen, 0,
+		       POLY1305_BLOCK_SIZE - dctx->buflen);
+		poly1305_blocks_mips(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
+	}
+
+	poly1305_emit_mips(&dctx->h, digest, dctx->s);
+
+	/* mac = (h + s) % (2^128) */
+	f = (f >> 32) + le32_to_cpu(digest[0]);
+	put_unaligned_le32(f, dst);
+	f = (f >> 32) + le32_to_cpu(digest[1]);
+	put_unaligned_le32(f, dst + 4);
+	f = (f >> 32) + le32_to_cpu(digest[2]);
+	put_unaligned_le32(f, dst + 8);
+	f = (f >> 32) + le32_to_cpu(digest[3]);
+	put_unaligned_le32(f, dst + 12);
+
+	*dctx = (struct poly1305_desc_ctx){};
+}
+EXPORT_SYMBOL(poly1305_final_arch);
+
+static int mips_poly1305_final(struct shash_desc *desc, u8 *dst)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (unlikely(!dctx->sset))
+		return -ENOKEY;
+
+	poly1305_final_arch(dctx, dst);
+	return 0;
+}
+
+static struct shash_alg mips_poly1305_alg = {
+	.init			= mips_poly1305_init,
+	.update			= mips_poly1305_update,
+	.final			= mips_poly1305_final,
+	.digestsize		= POLY1305_DIGEST_SIZE,
+	.descsize		= sizeof(struct poly1305_desc_ctx),
+
+	.base.cra_name		= "poly1305",
+	.base.cra_driver_name	= "poly1305-mips",
+	.base.cra_priority	= 200,
+	.base.cra_blocksize	= POLY1305_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+};
+
+static int __init mips_poly1305_mod_init(void)
+{
+	return crypto_register_shash(&mips_poly1305_alg);
+}
+
+static void __exit mips_poly1305_mod_exit(void)
+{
+	crypto_unregister_shash(&mips_poly1305_alg);
+}
+
+module_init(mips_poly1305_mod_init);
+module_exit(mips_poly1305_mod_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("poly1305");
+MODULE_ALIAS_CRYPTO("poly1305-mips");
diff --git a/arch/mips/crypto/poly1305-mips.pl b/arch/mips/crypto/poly1305-mips.pl
new file mode 100644
index 000000000000..b05bab884ed2
--- /dev/null
+++ b/arch/mips/crypto/poly1305-mips.pl
@@ -0,0 +1,1273 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-1.0+ OR BSD-3-Clause
+#
+# ====================================================================
+# Written by Andy Polyakov, @dot-asm, originally for the OpenSSL
+# project.
+# ====================================================================
+
+# Poly1305 hash for MIPS.
+#
+# May 2016
+#
+# Numbers are cycles per processed byte with poly1305_blocks alone.
+#
+#		IALU/gcc
+# R1x000	~5.5/+130%	(big-endian)
+# Octeon II	2.50/+70%	(little-endian)
+#
+# March 2019
+#
+# Add 32-bit code path.
+#
+# October 2019
+#
+# Modulo-scheduling reduction allows to omit dependency chain at the
+# end of inner loop and improve performance. Also optimize MIPS32R2
+# code path for MIPS 1004K core. Per René von Dorst's suggestions.
+#
+#		IALU/gcc
+# R1x000	~9.8/?		(big-endian)
+# Octeon II	3.65/+140%	(little-endian)
+# MT7621/1004K	4.75/?		(little-endian)
+#
+######################################################################
+# There is a number of MIPS ABI in use, O32 and N32/64 are most
+# widely used. Then there is a new contender: NUBI. It appears that if
+# one picks the latter, it's possible to arrange code in ABI neutral
+# manner. Therefore let's stick to NUBI register layout:
+#
+($zero,$at,$t0,$t1,$t2)=map("\$$_",(0..2,24,25));
+($a0,$a1,$a2,$a3,$a4,$a5,$a6,$a7)=map("\$$_",(4..11));
+($s0,$s1,$s2,$s3,$s4,$s5,$s6,$s7,$s8,$s9,$s10,$s11)=map("\$$_",(12..23));
+($gp,$tp,$sp,$fp,$ra)=map("\$$_",(3,28..31));
+#
+# The return value is placed in $a0. Following coding rules facilitate
+# interoperability:
+#
+# - never ever touch $tp, "thread pointer", former $gp [o32 can be
+#   excluded from the rule, because it's specified volatile];
+# - copy return value to $t0, former $v0 [or to $a0 if you're adapting
+#   old code];
+# - on O32 populate $a4-$a7 with 'lw $aN,4*N($sp)' if necessary;
+#
+# For reference here is register layout for N32/64 MIPS ABIs:
+#
+# ($zero,$at,$v0,$v1)=map("\$$_",(0..3));
+# ($a0,$a1,$a2,$a3,$a4,$a5,$a6,$a7)=map("\$$_",(4..11));
+# ($t0,$t1,$t2,$t3,$t8,$t9)=map("\$$_",(12..15,24,25));
+# ($s0,$s1,$s2,$s3,$s4,$s5,$s6,$s7)=map("\$$_",(16..23));
+# ($gp,$sp,$fp,$ra)=map("\$$_",(28..31));
+#
+# <appro@openssl.org>
+#
+######################################################################
+
+$flavour = shift || "64"; # supported flavours are o32,n32,64,nubi32,nubi64
+
+$v0 = ($flavour =~ /nubi/i) ? $a0 : $t0;
+
+if ($flavour =~ /64|n32/i) {{{
+######################################################################
+# 64-bit code path
+#
+
+my ($ctx,$inp,$len,$padbit) = ($a0,$a1,$a2,$a3);
+my ($in0,$in1,$tmp0,$tmp1,$tmp2,$tmp3,$tmp4) = ($a4,$a5,$a6,$a7,$at,$t0,$t1);
+
+$code.=<<___;
+#if (defined(_MIPS_ARCH_MIPS64R3) || defined(_MIPS_ARCH_MIPS64R5) || \\
+     defined(_MIPS_ARCH_MIPS64R6)) \\
+     && !defined(_MIPS_ARCH_MIPS64R2)
+# define _MIPS_ARCH_MIPS64R2
+#endif
+
+#if defined(_MIPS_ARCH_MIPS64R6)
+# define dmultu(rs,rt)
+# define mflo(rd,rs,rt)	dmulu	rd,rs,rt
+# define mfhi(rd,rs,rt)	dmuhu	rd,rs,rt
+#else
+# define dmultu(rs,rt)		dmultu	rs,rt
+# define mflo(rd,rs,rt)	mflo	rd
+# define mfhi(rd,rs,rt)	mfhi	rd
+#endif
+
+#ifdef	__KERNEL__
+# define poly1305_init   poly1305_init_mips
+# define poly1305_blocks poly1305_blocks_mips
+# define poly1305_emit   poly1305_emit_mips
+#endif
+
+#if defined(__MIPSEB__) && !defined(MIPSEB)
+# define MIPSEB
+#endif
+
+#ifdef MIPSEB
+# define MSB 0
+# define LSB 7
+#else
+# define MSB 7
+# define LSB 0
+#endif
+
+.text
+.set	noat
+.set	noreorder
+
+.align	5
+.globl	poly1305_init
+.ent	poly1305_init
+poly1305_init:
+	.frame	$sp,0,$ra
+	.set	reorder
+
+	sd	$zero,0($ctx)
+	sd	$zero,8($ctx)
+	sd	$zero,16($ctx)
+
+	beqz	$inp,.Lno_key
+
+#if defined(_MIPS_ARCH_MIPS64R6)
+	andi	$tmp0,$inp,7		# $inp % 8
+	dsubu	$inp,$inp,$tmp0		# align $inp
+	sll	$tmp0,$tmp0,3		# byte to bit offset
+	ld	$in0,0($inp)
+	ld	$in1,8($inp)
+	beqz	$tmp0,.Laligned_key
+	ld	$tmp2,16($inp)
+
+	subu	$tmp1,$zero,$tmp0
+# ifdef	MIPSEB
+	dsllv	$in0,$in0,$tmp0
+	dsrlv	$tmp3,$in1,$tmp1
+	dsllv	$in1,$in1,$tmp0
+	dsrlv	$tmp2,$tmp2,$tmp1
+# else
+	dsrlv	$in0,$in0,$tmp0
+	dsllv	$tmp3,$in1,$tmp1
+	dsrlv	$in1,$in1,$tmp0
+	dsllv	$tmp2,$tmp2,$tmp1
+# endif
+	or	$in0,$in0,$tmp3
+	or	$in1,$in1,$tmp2
+.Laligned_key:
+#else
+	ldl	$in0,0+MSB($inp)
+	ldl	$in1,8+MSB($inp)
+	ldr	$in0,0+LSB($inp)
+	ldr	$in1,8+LSB($inp)
+#endif
+#ifdef	MIPSEB
+# if defined(_MIPS_ARCH_MIPS64R2)
+	dsbh	$in0,$in0		# byte swap
+	 dsbh	$in1,$in1
+	dshd	$in0,$in0
+	 dshd	$in1,$in1
+# else
+	ori	$tmp0,$zero,0xFF
+	dsll	$tmp2,$tmp0,32
+	or	$tmp0,$tmp2		# 0x000000FF000000FF
+
+	and	$tmp1,$in0,$tmp0	# byte swap
+	 and	$tmp3,$in1,$tmp0
+	dsrl	$tmp2,$in0,24
+	 dsrl	$tmp4,$in1,24
+	dsll	$tmp1,24
+	 dsll	$tmp3,24
+	and	$tmp2,$tmp0
+	 and	$tmp4,$tmp0
+	dsll	$tmp0,8			# 0x0000FF000000FF00
+	or	$tmp1,$tmp2
+	 or	$tmp3,$tmp4
+	and	$tmp2,$in0,$tmp0
+	 and	$tmp4,$in1,$tmp0
+	dsrl	$in0,8
+	 dsrl	$in1,8
+	dsll	$tmp2,8
+	 dsll	$tmp4,8
+	and	$in0,$tmp0
+	 and	$in1,$tmp0
+	or	$tmp1,$tmp2
+	 or	$tmp3,$tmp4
+	or	$in0,$tmp1
+	 or	$in1,$tmp3
+	dsrl	$tmp1,$in0,32
+	 dsrl	$tmp3,$in1,32
+	dsll	$in0,32
+	 dsll	$in1,32
+	or	$in0,$tmp1
+	 or	$in1,$tmp3
+# endif
+#endif
+	li	$tmp0,1
+	dsll	$tmp0,32		# 0x0000000100000000
+	daddiu	$tmp0,-63		# 0x00000000ffffffc1
+	dsll	$tmp0,28		# 0x0ffffffc10000000
+	daddiu	$tmp0,-1		# 0x0ffffffc0fffffff
+
+	and	$in0,$tmp0
+	daddiu	$tmp0,-3		# 0x0ffffffc0ffffffc
+	and	$in1,$tmp0
+
+	sd	$in0,24($ctx)
+	dsrl	$tmp0,$in1,2
+	sd	$in1,32($ctx)
+	daddu	$tmp0,$in1		# s1 = r1 + (r1 >> 2)
+	sd	$tmp0,40($ctx)
+
+.Lno_key:
+	li	$v0,0			# return 0
+	jr	$ra
+.end	poly1305_init
+___
+{
+my $SAVED_REGS_MASK = ($flavour =~ /nubi/i) ? "0x0003f000" : "0x00030000";
+
+my ($h0,$h1,$h2,$r0,$r1,$rs1,$d0,$d1,$d2) =
+   ($s0,$s1,$s2,$s3,$s4,$s5,$in0,$in1,$t2);
+my ($shr,$shl) = ($s6,$s7);		# used on R6
+
+$code.=<<___;
+.align	5
+.globl	poly1305_blocks
+.ent	poly1305_blocks
+poly1305_blocks:
+	.set	noreorder
+	dsrl	$len,4			# number of complete blocks
+	bnez	$len,poly1305_blocks_internal
+	nop
+	jr	$ra
+	nop
+.end	poly1305_blocks
+
+.align	5
+.ent	poly1305_blocks_internal
+poly1305_blocks_internal:
+	.set	noreorder
+#if defined(_MIPS_ARCH_MIPS64R6)
+	.frame	$sp,8*8,$ra
+	.mask	$SAVED_REGS_MASK|0x000c0000,-8
+	dsubu	$sp,8*8
+	sd	$s7,56($sp)
+	sd	$s6,48($sp)
+#else
+	.frame	$sp,6*8,$ra
+	.mask	$SAVED_REGS_MASK,-8
+	dsubu	$sp,6*8
+#endif
+	sd	$s5,40($sp)
+	sd	$s4,32($sp)
+___
+$code.=<<___ if ($flavour =~ /nubi/i);	# optimize non-nubi prologue
+	sd	$s3,24($sp)
+	sd	$s2,16($sp)
+	sd	$s1,8($sp)
+	sd	$s0,0($sp)
+___
+$code.=<<___;
+	.set	reorder
+
+#if defined(_MIPS_ARCH_MIPS64R6)
+	andi	$shr,$inp,7
+	dsubu	$inp,$inp,$shr		# align $inp
+	sll	$shr,$shr,3		# byte to bit offset
+	subu	$shl,$zero,$shr
+#endif
+
+	ld	$h0,0($ctx)		# load hash value
+	ld	$h1,8($ctx)
+	ld	$h2,16($ctx)
+
+	ld	$r0,24($ctx)		# load key
+	ld	$r1,32($ctx)
+	ld	$rs1,40($ctx)
+
+	dsll	$len,4
+	daddu	$len,$inp		# end of buffer
+	b	.Loop
+
+.align	4
+.Loop:
+#if defined(_MIPS_ARCH_MIPS64R6)
+	ld	$in0,0($inp)		# load input
+	ld	$in1,8($inp)
+	beqz	$shr,.Laligned_inp
+
+	ld	$tmp2,16($inp)
+# ifdef	MIPSEB
+	dsllv	$in0,$in0,$shr
+	dsrlv	$tmp3,$in1,$shl
+	dsllv	$in1,$in1,$shr
+	dsrlv	$tmp2,$tmp2,$shl
+# else
+	dsrlv	$in0,$in0,$shr
+	dsllv	$tmp3,$in1,$shl
+	dsrlv	$in1,$in1,$shr
+	dsllv	$tmp2,$tmp2,$shl
+# endif
+	or	$in0,$in0,$tmp3
+	or	$in1,$in1,$tmp2
+.Laligned_inp:
+#else
+	ldl	$in0,0+MSB($inp)	# load input
+	ldl	$in1,8+MSB($inp)
+	ldr	$in0,0+LSB($inp)
+	ldr	$in1,8+LSB($inp)
+#endif
+	daddiu	$inp,16
+#ifdef	MIPSEB
+# if defined(_MIPS_ARCH_MIPS64R2)
+	dsbh	$in0,$in0		# byte swap
+	 dsbh	$in1,$in1
+	dshd	$in0,$in0
+	 dshd	$in1,$in1
+# else
+	ori	$tmp0,$zero,0xFF
+	dsll	$tmp2,$tmp0,32
+	or	$tmp0,$tmp2		# 0x000000FF000000FF
+
+	and	$tmp1,$in0,$tmp0	# byte swap
+	 and	$tmp3,$in1,$tmp0
+	dsrl	$tmp2,$in0,24
+	 dsrl	$tmp4,$in1,24
+	dsll	$tmp1,24
+	 dsll	$tmp3,24
+	and	$tmp2,$tmp0
+	 and	$tmp4,$tmp0
+	dsll	$tmp0,8			# 0x0000FF000000FF00
+	or	$tmp1,$tmp2
+	 or	$tmp3,$tmp4
+	and	$tmp2,$in0,$tmp0
+	 and	$tmp4,$in1,$tmp0
+	dsrl	$in0,8
+	 dsrl	$in1,8
+	dsll	$tmp2,8
+	 dsll	$tmp4,8
+	and	$in0,$tmp0
+	 and	$in1,$tmp0
+	or	$tmp1,$tmp2
+	 or	$tmp3,$tmp4
+	or	$in0,$tmp1
+	 or	$in1,$tmp3
+	dsrl	$tmp1,$in0,32
+	 dsrl	$tmp3,$in1,32
+	dsll	$in0,32
+	 dsll	$in1,32
+	or	$in0,$tmp1
+	 or	$in1,$tmp3
+# endif
+#endif
+	dsrl	$tmp1,$h2,2		# modulo-scheduled reduction
+	andi	$h2,$h2,3
+	dsll	$tmp0,$tmp1,2
+
+	daddu	$d0,$h0,$in0		# accumulate input
+	 daddu	$tmp1,$tmp0
+	sltu	$tmp0,$d0,$h0
+	daddu	$d0,$d0,$tmp1		# ... and residue
+	sltu	$tmp1,$d0,$tmp1
+	daddu	$d1,$h1,$in1
+	daddu	$tmp0,$tmp1
+	sltu	$tmp1,$d1,$h1
+	daddu	$d1,$tmp0
+
+	dmultu	($r0,$d0)		# h0*r0
+	 daddu	$d2,$h2,$padbit
+	 sltu	$tmp0,$d1,$tmp0
+	mflo	($h0,$r0,$d0)
+	mfhi	($h1,$r0,$d0)
+
+	dmultu	($rs1,$d1)		# h1*5*r1
+	 daddu	$d2,$tmp1
+	 daddu	$d2,$tmp0
+	mflo	($tmp0,$rs1,$d1)
+	mfhi	($tmp1,$rs1,$d1)
+
+	dmultu	($r1,$d0)		# h0*r1
+	mflo	($tmp2,$r1,$d0)
+	mfhi	($h2,$r1,$d0)
+	 daddu	$h0,$tmp0
+	 daddu	$h1,$tmp1
+	 sltu	$tmp0,$h0,$tmp0
+
+	dmultu	($r0,$d1)		# h1*r0
+	 daddu	$h1,$tmp0
+	 daddu	$h1,$tmp2
+	mflo	($tmp0,$r0,$d1)
+	mfhi	($tmp1,$r0,$d1)
+
+	dmultu	($rs1,$d2)		# h2*5*r1
+	 sltu	$tmp2,$h1,$tmp2
+	 daddu	$h2,$tmp2
+	mflo	($tmp2,$rs1,$d2)
+
+	dmultu	($r0,$d2)		# h2*r0
+	 daddu	$h1,$tmp0
+	 daddu	$h2,$tmp1
+	mflo	($tmp3,$r0,$d2)
+	 sltu	$tmp0,$h1,$tmp0
+	 daddu	$h2,$tmp0
+
+	daddu	$h1,$tmp2
+	sltu	$tmp2,$h1,$tmp2
+	daddu	$h2,$tmp2
+	daddu	$h2,$tmp3
+
+	bne	$inp,$len,.Loop
+
+	sd	$h0,0($ctx)		# store hash value
+	sd	$h1,8($ctx)
+	sd	$h2,16($ctx)
+
+	.set	noreorder
+#if defined(_MIPS_ARCH_MIPS64R6)
+	ld	$s7,56($sp)
+	ld	$s6,48($sp)
+#endif
+	ld	$s5,40($sp)		# epilogue
+	ld	$s4,32($sp)
+___
+$code.=<<___ if ($flavour =~ /nubi/i);	# optimize non-nubi epilogue
+	ld	$s3,24($sp)
+	ld	$s2,16($sp)
+	ld	$s1,8($sp)
+	ld	$s0,0($sp)
+___
+$code.=<<___;
+	jr	$ra
+#if defined(_MIPS_ARCH_MIPS64R6)
+	daddu	$sp,8*8
+#else
+	daddu	$sp,6*8
+#endif
+.end	poly1305_blocks_internal
+___
+}
+{
+my ($ctx,$mac,$nonce) = ($a0,$a1,$a2);
+
+$code.=<<___;
+.align	5
+.globl	poly1305_emit
+.ent	poly1305_emit
+poly1305_emit:
+	.frame	$sp,0,$ra
+	.set	reorder
+
+	ld	$tmp2,16($ctx)
+	ld	$tmp0,0($ctx)
+	ld	$tmp1,8($ctx)
+
+	li	$in0,-4			# final reduction
+	dsrl	$in1,$tmp2,2
+	and	$in0,$tmp2
+	andi	$tmp2,$tmp2,3
+	daddu	$in0,$in1
+
+	daddu	$tmp0,$tmp0,$in0
+	sltu	$in1,$tmp0,$in0
+	 daddiu	$in0,$tmp0,5		# compare to modulus
+	daddu	$tmp1,$tmp1,$in1
+	 sltiu	$tmp3,$in0,5
+	sltu	$tmp4,$tmp1,$in1
+	 daddu	$in1,$tmp1,$tmp3
+	daddu	$tmp2,$tmp2,$tmp4
+	 sltu	$tmp3,$in1,$tmp3
+	 daddu	$tmp2,$tmp2,$tmp3
+
+	dsrl	$tmp2,2			# see if it carried/borrowed
+	dsubu	$tmp2,$zero,$tmp2
+
+	xor	$in0,$tmp0
+	xor	$in1,$tmp1
+	and	$in0,$tmp2
+	and	$in1,$tmp2
+	xor	$in0,$tmp0
+	xor	$in1,$tmp1
+
+	lwu	$tmp0,0($nonce)		# load nonce
+	lwu	$tmp1,4($nonce)
+	lwu	$tmp2,8($nonce)
+	lwu	$tmp3,12($nonce)
+	dsll	$tmp1,32
+	dsll	$tmp3,32
+	or	$tmp0,$tmp1
+	or	$tmp2,$tmp3
+
+	daddu	$in0,$tmp0		# accumulate nonce
+	daddu	$in1,$tmp2
+	sltu	$tmp0,$in0,$tmp0
+	daddu	$in1,$tmp0
+
+	dsrl	$tmp0,$in0,8		# write mac value
+	dsrl	$tmp1,$in0,16
+	dsrl	$tmp2,$in0,24
+	sb	$in0,0($mac)
+	dsrl	$tmp3,$in0,32
+	sb	$tmp0,1($mac)
+	dsrl	$tmp0,$in0,40
+	sb	$tmp1,2($mac)
+	dsrl	$tmp1,$in0,48
+	sb	$tmp2,3($mac)
+	dsrl	$tmp2,$in0,56
+	sb	$tmp3,4($mac)
+	dsrl	$tmp3,$in1,8
+	sb	$tmp0,5($mac)
+	dsrl	$tmp0,$in1,16
+	sb	$tmp1,6($mac)
+	dsrl	$tmp1,$in1,24
+	sb	$tmp2,7($mac)
+
+	sb	$in1,8($mac)
+	dsrl	$tmp2,$in1,32
+	sb	$tmp3,9($mac)
+	dsrl	$tmp3,$in1,40
+	sb	$tmp0,10($mac)
+	dsrl	$tmp0,$in1,48
+	sb	$tmp1,11($mac)
+	dsrl	$tmp1,$in1,56
+	sb	$tmp2,12($mac)
+	sb	$tmp3,13($mac)
+	sb	$tmp0,14($mac)
+	sb	$tmp1,15($mac)
+
+	jr	$ra
+.end	poly1305_emit
+.rdata
+.asciiz	"Poly1305 for MIPS64, CRYPTOGAMS by \@dot-asm"
+.align	2
+___
+}
+}}} else {{{
+######################################################################
+# 32-bit code path
+#
+
+my ($ctx,$inp,$len,$padbit) = ($a0,$a1,$a2,$a3);
+my ($in0,$in1,$in2,$in3,$tmp0,$tmp1,$tmp2,$tmp3) =
+   ($a4,$a5,$a6,$a7,$at,$t0,$t1,$t2);
+
+$code.=<<___;
+#if (defined(_MIPS_ARCH_MIPS32R3) || defined(_MIPS_ARCH_MIPS32R5) || \\
+     defined(_MIPS_ARCH_MIPS32R6)) \\
+     && !defined(_MIPS_ARCH_MIPS32R2)
+# define _MIPS_ARCH_MIPS32R2
+#endif
+
+#if defined(_MIPS_ARCH_MIPS32R6)
+# define multu(rs,rt)
+# define mflo(rd,rs,rt)	mulu	rd,rs,rt
+# define mfhi(rd,rs,rt)	muhu	rd,rs,rt
+#else
+# define multu(rs,rt)	multu	rs,rt
+# define mflo(rd,rs,rt)	mflo	rd
+# define mfhi(rd,rs,rt)	mfhi	rd
+#endif
+
+#ifdef	__KERNEL__
+# define poly1305_init   poly1305_init_mips
+# define poly1305_blocks poly1305_blocks_mips
+# define poly1305_emit   poly1305_emit_mips
+#endif
+
+#if defined(__MIPSEB__) && !defined(MIPSEB)
+# define MIPSEB
+#endif
+
+#ifdef MIPSEB
+# define MSB 0
+# define LSB 3
+#else
+# define MSB 3
+# define LSB 0
+#endif
+
+.text
+.set	noat
+.set	noreorder
+
+.align	5
+.globl	poly1305_init
+.ent	poly1305_init
+poly1305_init:
+	.frame	$sp,0,$ra
+	.set	reorder
+
+	sw	$zero,0($ctx)
+	sw	$zero,4($ctx)
+	sw	$zero,8($ctx)
+	sw	$zero,12($ctx)
+	sw	$zero,16($ctx)
+
+	beqz	$inp,.Lno_key
+
+#if defined(_MIPS_ARCH_MIPS32R6)
+	andi	$tmp0,$inp,3		# $inp % 4
+	subu	$inp,$inp,$tmp0		# align $inp
+	sll	$tmp0,$tmp0,3		# byte to bit offset
+	lw	$in0,0($inp)
+	lw	$in1,4($inp)
+	lw	$in2,8($inp)
+	lw	$in3,12($inp)
+	beqz	$tmp0,.Laligned_key
+
+	lw	$tmp2,16($inp)
+	subu	$tmp1,$zero,$tmp0
+# ifdef	MIPSEB
+	sllv	$in0,$in0,$tmp0
+	srlv	$tmp3,$in1,$tmp1
+	sllv	$in1,$in1,$tmp0
+	or	$in0,$in0,$tmp3
+	srlv	$tmp3,$in2,$tmp1
+	sllv	$in2,$in2,$tmp0
+	or	$in1,$in1,$tmp3
+	srlv	$tmp3,$in3,$tmp1
+	sllv	$in3,$in3,$tmp0
+	or	$in2,$in2,$tmp3
+	srlv	$tmp2,$tmp2,$tmp1
+	or	$in3,$in3,$tmp2
+# else
+	srlv	$in0,$in0,$tmp0
+	sllv	$tmp3,$in1,$tmp1
+	srlv	$in1,$in1,$tmp0
+	or	$in0,$in0,$tmp3
+	sllv	$tmp3,$in2,$tmp1
+	srlv	$in2,$in2,$tmp0
+	or	$in1,$in1,$tmp3
+	sllv	$tmp3,$in3,$tmp1
+	srlv	$in3,$in3,$tmp0
+	or	$in2,$in2,$tmp3
+	sllv	$tmp2,$tmp2,$tmp1
+	or	$in3,$in3,$tmp2
+# endif
+.Laligned_key:
+#else
+	lwl	$in0,0+MSB($inp)
+	lwl	$in1,4+MSB($inp)
+	lwl	$in2,8+MSB($inp)
+	lwl	$in3,12+MSB($inp)
+	lwr	$in0,0+LSB($inp)
+	lwr	$in1,4+LSB($inp)
+	lwr	$in2,8+LSB($inp)
+	lwr	$in3,12+LSB($inp)
+#endif
+#ifdef	MIPSEB
+# if defined(_MIPS_ARCH_MIPS32R2)
+	wsbh	$in0,$in0		# byte swap
+	wsbh	$in1,$in1
+	wsbh	$in2,$in2
+	wsbh	$in3,$in3
+	rotr	$in0,$in0,16
+	rotr	$in1,$in1,16
+	rotr	$in2,$in2,16
+	rotr	$in3,$in3,16
+# else
+	srl	$tmp0,$in0,24		# byte swap
+	srl	$tmp1,$in0,8
+	andi	$tmp2,$in0,0xFF00
+	sll	$in0,$in0,24
+	andi	$tmp1,0xFF00
+	sll	$tmp2,$tmp2,8
+	or	$in0,$tmp0
+	 srl	$tmp0,$in1,24
+	or	$tmp1,$tmp2
+	 srl	$tmp2,$in1,8
+	or	$in0,$tmp1
+	 andi	$tmp1,$in1,0xFF00
+	 sll	$in1,$in1,24
+	 andi	$tmp2,0xFF00
+	 sll	$tmp1,$tmp1,8
+	 or	$in1,$tmp0
+	srl	$tmp0,$in2,24
+	 or	$tmp2,$tmp1
+	srl	$tmp1,$in2,8
+	 or	$in1,$tmp2
+	andi	$tmp2,$in2,0xFF00
+	sll	$in2,$in2,24
+	andi	$tmp1,0xFF00
+	sll	$tmp2,$tmp2,8
+	or	$in2,$tmp0
+	 srl	$tmp0,$in3,24
+	or	$tmp1,$tmp2
+	 srl	$tmp2,$in3,8
+	or	$in2,$tmp1
+	 andi	$tmp1,$in3,0xFF00
+	 sll	$in3,$in3,24
+	 andi	$tmp2,0xFF00
+	 sll	$tmp1,$tmp1,8
+	 or	$in3,$tmp0
+	 or	$tmp2,$tmp1
+	 or	$in3,$tmp2
+# endif
+#endif
+	lui	$tmp0,0x0fff
+	ori	$tmp0,0xffff		# 0x0fffffff
+	and	$in0,$in0,$tmp0
+	subu	$tmp0,3			# 0x0ffffffc
+	and	$in1,$in1,$tmp0
+	and	$in2,$in2,$tmp0
+	and	$in3,$in3,$tmp0
+
+	sw	$in0,20($ctx)
+	sw	$in1,24($ctx)
+	sw	$in2,28($ctx)
+	sw	$in3,32($ctx)
+
+	srl	$tmp1,$in1,2
+	srl	$tmp2,$in2,2
+	srl	$tmp3,$in3,2
+	addu	$in1,$in1,$tmp1		# s1 = r1 + (r1 >> 2)
+	addu	$in2,$in2,$tmp2
+	addu	$in3,$in3,$tmp3
+	sw	$in1,36($ctx)
+	sw	$in2,40($ctx)
+	sw	$in3,44($ctx)
+.Lno_key:
+	li	$v0,0
+	jr	$ra
+.end	poly1305_init
+___
+{
+my $SAVED_REGS_MASK = ($flavour =~ /nubi/i) ? "0x00fff000" : "0x00ff0000";
+
+my ($h0,$h1,$h2,$h3,$h4, $r0,$r1,$r2,$r3, $rs1,$rs2,$rs3) =
+   ($s0,$s1,$s2,$s3,$s4, $s5,$s6,$s7,$s8, $s9,$s10,$s11);
+my ($d0,$d1,$d2,$d3) =
+   ($a4,$a5,$a6,$a7);
+my $shr = $t2;		# used on R6
+my $one = $t2;		# used on R2
+
+$code.=<<___;
+.globl	poly1305_blocks
+.align	5
+.ent	poly1305_blocks
+poly1305_blocks:
+	.frame	$sp,16*4,$ra
+	.mask	$SAVED_REGS_MASK,-4
+	.set	noreorder
+	subu	$sp, $sp,4*12
+	sw	$s11,4*11($sp)
+	sw	$s10,4*10($sp)
+	sw	$s9, 4*9($sp)
+	sw	$s8, 4*8($sp)
+	sw	$s7, 4*7($sp)
+	sw	$s6, 4*6($sp)
+	sw	$s5, 4*5($sp)
+	sw	$s4, 4*4($sp)
+___
+$code.=<<___ if ($flavour =~ /nubi/i);	# optimize non-nubi prologue
+	sw	$s3, 4*3($sp)
+	sw	$s2, 4*2($sp)
+	sw	$s1, 4*1($sp)
+	sw	$s0, 4*0($sp)
+___
+$code.=<<___;
+	.set	reorder
+
+	srl	$len,4			# number of complete blocks
+	li	$one,1
+	beqz	$len,.Labort
+
+#if defined(_MIPS_ARCH_MIPS32R6)
+	andi	$shr,$inp,3
+	subu	$inp,$inp,$shr		# align $inp
+	sll	$shr,$shr,3		# byte to bit offset
+#endif
+
+	lw	$h0,0($ctx)		# load hash value
+	lw	$h1,4($ctx)
+	lw	$h2,8($ctx)
+	lw	$h3,12($ctx)
+	lw	$h4,16($ctx)
+
+	lw	$r0,20($ctx)		# load key
+	lw	$r1,24($ctx)
+	lw	$r2,28($ctx)
+	lw	$r3,32($ctx)
+	lw	$rs1,36($ctx)
+	lw	$rs2,40($ctx)
+	lw	$rs3,44($ctx)
+
+	sll	$len,4
+	addu	$len,$len,$inp		# end of buffer
+	b	.Loop
+
+.align	4
+.Loop:
+#if defined(_MIPS_ARCH_MIPS32R6)
+	lw	$d0,0($inp)		# load input
+	lw	$d1,4($inp)
+	lw	$d2,8($inp)
+	lw	$d3,12($inp)
+	beqz	$shr,.Laligned_inp
+
+	lw	$t0,16($inp)
+	subu	$t1,$zero,$shr
+# ifdef	MIPSEB
+	sllv	$d0,$d0,$shr
+	srlv	$at,$d1,$t1
+	sllv	$d1,$d1,$shr
+	or	$d0,$d0,$at
+	srlv	$at,$d2,$t1
+	sllv	$d2,$d2,$shr
+	or	$d1,$d1,$at
+	srlv	$at,$d3,$t1
+	sllv	$d3,$d3,$shr
+	or	$d2,$d2,$at
+	srlv	$t0,$t0,$t1
+	or	$d3,$d3,$t0
+# else
+	srlv	$d0,$d0,$shr
+	sllv	$at,$d1,$t1
+	srlv	$d1,$d1,$shr
+	or	$d0,$d0,$at
+	sllv	$at,$d2,$t1
+	srlv	$d2,$d2,$shr
+	or	$d1,$d1,$at
+	sllv	$at,$d3,$t1
+	srlv	$d3,$d3,$shr
+	or	$d2,$d2,$at
+	sllv	$t0,$t0,$t1
+	or	$d3,$d3,$t0
+# endif
+.Laligned_inp:
+#else
+	lwl	$d0,0+MSB($inp)		# load input
+	lwl	$d1,4+MSB($inp)
+	lwl	$d2,8+MSB($inp)
+	lwl	$d3,12+MSB($inp)
+	lwr	$d0,0+LSB($inp)
+	lwr	$d1,4+LSB($inp)
+	lwr	$d2,8+LSB($inp)
+	lwr	$d3,12+LSB($inp)
+#endif
+#ifdef	MIPSEB
+# if defined(_MIPS_ARCH_MIPS32R2)
+	wsbh	$d0,$d0			# byte swap
+	wsbh	$d1,$d1
+	wsbh	$d2,$d2
+	wsbh	$d3,$d3
+	rotr	$d0,$d0,16
+	rotr	$d1,$d1,16
+	rotr	$d2,$d2,16
+	rotr	$d3,$d3,16
+# else
+	srl	$at,$d0,24		# byte swap
+	srl	$t0,$d0,8
+	andi	$t1,$d0,0xFF00
+	sll	$d0,$d0,24
+	andi	$t0,0xFF00
+	sll	$t1,$t1,8
+	or	$d0,$at
+	 srl	$at,$d1,24
+	or	$t0,$t1
+	 srl	$t1,$d1,8
+	or	$d0,$t0
+	 andi	$t0,$d1,0xFF00
+	 sll	$d1,$d1,24
+	 andi	$t1,0xFF00
+	 sll	$t0,$t0,8
+	 or	$d1,$at
+	srl	$at,$d2,24
+	 or	$t1,$t0
+	srl	$t0,$d2,8
+	 or	$d1,$t1
+	andi	$t1,$d2,0xFF00
+	sll	$d2,$d2,24
+	andi	$t0,0xFF00
+	sll	$t1,$t1,8
+	or	$d2,$at
+	 srl	$at,$d3,24
+	or	$t0,$t1
+	 srl	$t1,$d3,8
+	or	$d2,$t0
+	 andi	$t0,$d3,0xFF00
+	 sll	$d3,$d3,24
+	 andi	$t1,0xFF00
+	 sll	$t0,$t0,8
+	 or	$d3,$at
+	 or	$t1,$t0
+	 or	$d3,$t1
+# endif
+#endif
+	srl	$t0,$h4,2		# modulo-scheduled reduction
+	andi	$h4,$h4,3
+	sll	$at,$t0,2
+
+	addu	$d0,$d0,$h0		# accumulate input
+	 addu	$t0,$t0,$at
+	sltu	$h0,$d0,$h0
+	addu	$d0,$d0,$t0		# ... and residue
+	sltu	$at,$d0,$t0
+
+	addu	$d1,$d1,$h1
+	 addu	$h0,$h0,$at		# carry
+	sltu	$h1,$d1,$h1
+	addu	$d1,$d1,$h0
+	sltu	$h0,$d1,$h0
+
+	addu	$d2,$d2,$h2
+	 addu	$h1,$h1,$h0		# carry
+	sltu	$h2,$d2,$h2
+	addu	$d2,$d2,$h1
+	sltu	$h1,$d2,$h1
+
+	addu	$d3,$d3,$h3
+	 addu	$h2,$h2,$h1		# carry
+	sltu	$h3,$d3,$h3
+	addu	$d3,$d3,$h2
+
+#if defined(_MIPS_ARCH_MIPS32R2) && !defined(_MIPS_ARCH_MIPS32R6)
+	multu	$r0,$d0			# d0*r0
+	 sltu	$h2,$d3,$h2
+	maddu	$rs3,$d1		# d1*s3
+	 addu	$h3,$h3,$h2		# carry
+	maddu	$rs2,$d2		# d2*s2
+	 addu	$h4,$h4,$padbit
+	maddu	$rs1,$d3		# d3*s1
+	 addu	$h4,$h4,$h3
+	mfhi	$at
+	mflo	$h0
+
+	multu	$r1,$d0			# d0*r1
+	maddu	$r0,$d1			# d1*r0
+	maddu	$rs3,$d2		# d2*s3
+	maddu	$rs2,$d3		# d3*s2
+	maddu	$rs1,$h4		# h4*s1
+	maddu	$at,$one		# hi*1
+	mfhi	$at
+	mflo	$h1
+
+	multu	$r2,$d0			# d0*r2
+	maddu	$r1,$d1			# d1*r1
+	maddu	$r0,$d2			# d2*r0
+	maddu	$rs3,$d3		# d3*s3
+	maddu	$rs2,$h4		# h4*s2
+	maddu	$at,$one		# hi*1
+	mfhi	$at
+	mflo	$h2
+
+	mul	$t0,$r0,$h4		# h4*r0
+
+	multu	$r3,$d0			# d0*r3
+	maddu	$r2,$d1			# d1*r2
+	maddu	$r1,$d2			# d2*r1
+	maddu	$r0,$d3			# d3*r0
+	maddu	$rs3,$h4		# h4*s3
+	maddu	$at,$one		# hi*1
+	mfhi	$at
+	mflo	$h3
+
+	 addiu	$inp,$inp,16
+
+	addu	$h4,$t0,$at
+#else
+	multu	($r0,$d0)		# d0*r0
+	mflo	($h0,$r0,$d0)
+	mfhi	($h1,$r0,$d0)
+
+	 sltu	$h2,$d3,$h2
+	 addu	$h3,$h3,$h2		# carry
+
+	multu	($rs3,$d1)		# d1*s3
+	mflo	($at,$rs3,$d1)
+	mfhi	($t0,$rs3,$d1)
+
+	 addu	$h4,$h4,$padbit
+	 addiu	$inp,$inp,16
+	 addu	$h4,$h4,$h3
+
+	multu	($rs2,$d2)		# d2*s2
+	mflo	($a3,$rs2,$d2)
+	mfhi	($t1,$rs2,$d2)
+	 addu	$h0,$h0,$at
+	 addu	$h1,$h1,$t0
+	multu	($rs1,$d3)		# d3*s1
+	 sltu	$at,$h0,$at
+	 addu	$h1,$h1,$at
+
+	mflo	($at,$rs1,$d3)
+	mfhi	($t0,$rs1,$d3)
+	 addu	$h0,$h0,$a3
+	 addu	$h1,$h1,$t1
+	multu	($r1,$d0)		# d0*r1
+	 sltu	$a3,$h0,$a3
+	 addu	$h1,$h1,$a3
+
+
+	mflo	($a3,$r1,$d0)
+	mfhi	($h2,$r1,$d0)
+	 addu	$h0,$h0,$at
+	 addu	$h1,$h1,$t0
+	multu	($r0,$d1)		# d1*r0
+	 sltu	$at,$h0,$at
+	 addu	$h1,$h1,$at
+
+	mflo	($at,$r0,$d1)
+	mfhi	($t0,$r0,$d1)
+	 addu	$h1,$h1,$a3
+	 sltu	$a3,$h1,$a3
+	multu	($rs3,$d2)		# d2*s3
+	 addu	$h2,$h2,$a3
+
+	mflo	($a3,$rs3,$d2)
+	mfhi	($t1,$rs3,$d2)
+	 addu	$h1,$h1,$at
+	 addu	$h2,$h2,$t0
+	multu	($rs2,$d3)		# d3*s2
+	 sltu	$at,$h1,$at
+	 addu	$h2,$h2,$at
+
+	mflo	($at,$rs2,$d3)
+	mfhi	($t0,$rs2,$d3)
+	 addu	$h1,$h1,$a3
+	 addu	$h2,$h2,$t1
+	multu	($rs1,$h4)		# h4*s1
+	 sltu	$a3,$h1,$a3
+	 addu	$h2,$h2,$a3
+
+	mflo	($a3,$rs1,$h4)
+	 addu	$h1,$h1,$at
+	 addu	$h2,$h2,$t0
+	multu	($r2,$d0)		# d0*r2
+	 sltu	$at,$h1,$at
+	 addu	$h2,$h2,$at
+
+
+	mflo	($at,$r2,$d0)
+	mfhi	($h3,$r2,$d0)
+	 addu	$h1,$h1,$a3
+	 sltu	$a3,$h1,$a3
+	multu	($r1,$d1)		# d1*r1
+	 addu	$h2,$h2,$a3
+
+	mflo	($a3,$r1,$d1)
+	mfhi	($t1,$r1,$d1)
+	 addu	$h2,$h2,$at
+	 sltu	$at,$h2,$at
+	multu	($r0,$d2)		# d2*r0
+	 addu	$h3,$h3,$at
+
+	mflo	($at,$r0,$d2)
+	mfhi	($t0,$r0,$d2)
+	 addu	$h2,$h2,$a3
+	 addu	$h3,$h3,$t1
+	multu	($rs3,$d3)		# d3*s3
+	 sltu	$a3,$h2,$a3
+	 addu	$h3,$h3,$a3
+
+	mflo	($a3,$rs3,$d3)
+	mfhi	($t1,$rs3,$d3)
+	 addu	$h2,$h2,$at
+	 addu	$h3,$h3,$t0
+	multu	($rs2,$h4)		# h4*s2
+	 sltu	$at,$h2,$at
+	 addu	$h3,$h3,$at
+
+	mflo	($at,$rs2,$h4)
+	 addu	$h2,$h2,$a3
+	 addu	$h3,$h3,$t1
+	multu	($r3,$d0)		# d0*r3
+	 sltu	$a3,$h2,$a3
+	 addu	$h3,$h3,$a3
+
+
+	mflo	($a3,$r3,$d0)
+	mfhi	($t1,$r3,$d0)
+	 addu	$h2,$h2,$at
+	 sltu	$at,$h2,$at
+	multu	($r2,$d1)		# d1*r2
+	 addu	$h3,$h3,$at
+
+	mflo	($at,$r2,$d1)
+	mfhi	($t0,$r2,$d1)
+	 addu	$h3,$h3,$a3
+	 sltu	$a3,$h3,$a3
+	multu	($r0,$d3)		# d3*r0
+	 addu	$t1,$t1,$a3
+
+	mflo	($a3,$r0,$d3)
+	mfhi	($d3,$r0,$d3)
+	 addu	$h3,$h3,$at
+	 addu	$t1,$t1,$t0
+	multu	($r1,$d2)		# d2*r1
+	 sltu	$at,$h3,$at
+	 addu	$t1,$t1,$at
+
+	mflo	($at,$r1,$d2)
+	mfhi	($t0,$r1,$d2)
+	 addu	$h3,$h3,$a3
+	 addu	$t1,$t1,$d3
+	multu	($rs3,$h4)		# h4*s3
+	 sltu	$a3,$h3,$a3
+	 addu	$t1,$t1,$a3
+
+	mflo	($a3,$rs3,$h4)
+	 addu	$h3,$h3,$at
+	 addu	$t1,$t1,$t0
+	multu	($r0,$h4)		# h4*r0
+	 sltu	$at,$h3,$at
+	 addu	$t1,$t1,$at
+
+
+	mflo	($h4,$r0,$h4)
+	 addu	$h3,$h3,$a3
+	 sltu	$a3,$h3,$a3
+	 addu	$t1,$t1,$a3
+	addu	$h4,$h4,$t1
+
+	li	$padbit,1		# if we loop, padbit is 1
+#endif
+	bne	$inp,$len,.Loop
+
+	sw	$h0,0($ctx)		# store hash value
+	sw	$h1,4($ctx)
+	sw	$h2,8($ctx)
+	sw	$h3,12($ctx)
+	sw	$h4,16($ctx)
+
+	.set	noreorder
+.Labort:
+	lw	$s11,4*11($sp)
+	lw	$s10,4*10($sp)
+	lw	$s9, 4*9($sp)
+	lw	$s8, 4*8($sp)
+	lw	$s7, 4*7($sp)
+	lw	$s6, 4*6($sp)
+	lw	$s5, 4*5($sp)
+	lw	$s4, 4*4($sp)
+___
+$code.=<<___ if ($flavour =~ /nubi/i);	# optimize non-nubi prologue
+	lw	$s3, 4*3($sp)
+	lw	$s2, 4*2($sp)
+	lw	$s1, 4*1($sp)
+	lw	$s0, 4*0($sp)
+___
+$code.=<<___;
+	jr	$ra
+	addu	$sp,$sp,4*12
+.end	poly1305_blocks
+___
+}
+{
+my ($ctx,$mac,$nonce,$tmp4) = ($a0,$a1,$a2,$a3);
+
+$code.=<<___;
+.align	5
+.globl	poly1305_emit
+.ent	poly1305_emit
+poly1305_emit:
+	.frame	$sp,0,$ra
+	.set	reorder
+
+	lw	$tmp4,16($ctx)
+	lw	$tmp0,0($ctx)
+	lw	$tmp1,4($ctx)
+	lw	$tmp2,8($ctx)
+	lw	$tmp3,12($ctx)
+
+	li	$in0,-4			# final reduction
+	srl	$ctx,$tmp4,2
+	and	$in0,$in0,$tmp4
+	andi	$tmp4,$tmp4,3
+	addu	$ctx,$ctx,$in0
+
+	addu	$tmp0,$tmp0,$ctx
+	sltu	$ctx,$tmp0,$ctx
+	 addiu	$in0,$tmp0,5		# compare to modulus
+	addu	$tmp1,$tmp1,$ctx
+	 sltiu	$in1,$in0,5
+	sltu	$ctx,$tmp1,$ctx
+	 addu	$in1,$in1,$tmp1
+	addu	$tmp2,$tmp2,$ctx
+	 sltu	$in2,$in1,$tmp1
+	sltu	$ctx,$tmp2,$ctx
+	 addu	$in2,$in2,$tmp2
+	addu	$tmp3,$tmp3,$ctx
+	 sltu	$in3,$in2,$tmp2
+	sltu	$ctx,$tmp3,$ctx
+	 addu	$in3,$in3,$tmp3
+	addu	$tmp4,$tmp4,$ctx
+	 sltu	$ctx,$in3,$tmp3
+	 addu	$ctx,$tmp4
+
+	srl	$ctx,2			# see if it carried/borrowed
+	subu	$ctx,$zero,$ctx
+
+	xor	$in0,$tmp0
+	xor	$in1,$tmp1
+	xor	$in2,$tmp2
+	xor	$in3,$tmp3
+	and	$in0,$ctx
+	and	$in1,$ctx
+	and	$in2,$ctx
+	and	$in3,$ctx
+	xor	$in0,$tmp0
+	xor	$in1,$tmp1
+	xor	$in2,$tmp2
+	xor	$in3,$tmp3
+
+	lw	$tmp0,0($nonce)		# load nonce
+	lw	$tmp1,4($nonce)
+	lw	$tmp2,8($nonce)
+	lw	$tmp3,12($nonce)
+
+	addu	$in0,$tmp0		# accumulate nonce
+	sltu	$ctx,$in0,$tmp0
+
+	addu	$in1,$tmp1
+	sltu	$tmp1,$in1,$tmp1
+	addu	$in1,$ctx
+	sltu	$ctx,$in1,$ctx
+	addu	$ctx,$tmp1
+
+	addu	$in2,$tmp2
+	sltu	$tmp2,$in2,$tmp2
+	addu	$in2,$ctx
+	sltu	$ctx,$in2,$ctx
+	addu	$ctx,$tmp2
+
+	addu	$in3,$tmp3
+	addu	$in3,$ctx
+
+	srl	$tmp0,$in0,8		# write mac value
+	srl	$tmp1,$in0,16
+	srl	$tmp2,$in0,24
+	sb	$in0, 0($mac)
+	sb	$tmp0,1($mac)
+	srl	$tmp0,$in1,8
+	sb	$tmp1,2($mac)
+	srl	$tmp1,$in1,16
+	sb	$tmp2,3($mac)
+	srl	$tmp2,$in1,24
+	sb	$in1, 4($mac)
+	sb	$tmp0,5($mac)
+	srl	$tmp0,$in2,8
+	sb	$tmp1,6($mac)
+	srl	$tmp1,$in2,16
+	sb	$tmp2,7($mac)
+	srl	$tmp2,$in2,24
+	sb	$in2, 8($mac)
+	sb	$tmp0,9($mac)
+	srl	$tmp0,$in3,8
+	sb	$tmp1,10($mac)
+	srl	$tmp1,$in3,16
+	sb	$tmp2,11($mac)
+	srl	$tmp2,$in3,24
+	sb	$in3, 12($mac)
+	sb	$tmp0,13($mac)
+	sb	$tmp1,14($mac)
+	sb	$tmp2,15($mac)
+
+	jr	$ra
+.end	poly1305_emit
+.rdata
+.asciiz	"Poly1305 for MIPS32, CRYPTOGAMS by \@dot-asm"
+.align	2
+___
+}
+}}}
+
+$output=pop and open STDOUT,">$output";
+print $code;
+close STDOUT;
diff --git a/arch/mips/fw/arc/Makefile b/arch/mips/fw/arc/Makefile
index 31dd7305d643..64d685efcc77 100644
--- a/arch/mips/fw/arc/Makefile
+++ b/arch/mips/fw/arc/Makefile
@@ -3,8 +3,12 @@
 # Makefile for the ARC prom monitor library routines under Linux.
 #
 
+ifdef CONFIG_ARC_CMDLINE_ONLY
+lib-y				+= cmdline.o
+else
 lib-y				+= cmdline.o env.o file.o identify.o init.o \
-				   misc.o salone.o time.o tree.o
+				   misc.o
+endif
 
 lib-$(CONFIG_ARC_MEMORY)	+= memory.o
 lib-$(CONFIG_ARC_CONSOLE)	+= arc_con.o
diff --git a/arch/mips/fw/arc/cmdline.c b/arch/mips/fw/arc/cmdline.c
index c0122a1dc587..155c5e911723 100644
--- a/arch/mips/fw/arc/cmdline.c
+++ b/arch/mips/fw/arc/cmdline.c
@@ -17,6 +17,12 @@
 
 #undef DEBUG_CMDLINE
 
+/*
+ * A 32-bit ARC PROM pass arguments and environment as 32-bit pointer.
+ * These macro take care of sign extension.
+ */
+#define prom_argv(index) ((char *) (long)argv[(index)])
+
 static char *ignored[] = {
 	"ConsoleIn=",
 	"ConsoleOut=",
@@ -32,14 +38,14 @@ static char *used_arc[][2] = {
 	{ "OSLoadOptions=", "" }
 };
 
-static char * __init move_firmware_args(char* cp)
+static char __init *move_firmware_args(int argc, LONG *argv, char *cp)
 {
 	char *s;
 	int actr, i;
 
 	actr = 1; /* Always ignore argv[0] */
 
-	while (actr < prom_argc) {
+	while (actr < argc) {
 		for(i = 0; i < ARRAY_SIZE(used_arc); i++) {
 			int len = strlen(used_arc[i][0]);
 
@@ -64,7 +70,7 @@ static char * __init move_firmware_args(char* cp)
 	return cp;
 }
 
-void __init prom_init_cmdline(void)
+void __init prom_init_cmdline(int argc, LONG *argv)
 {
 	char *cp;
 	int actr, i;
@@ -76,9 +82,9 @@ void __init prom_init_cmdline(void)
 	 * Move ARC variables to the beginning to make sure they can be
 	 * overridden by later arguments.
 	 */
-	cp = move_firmware_args(cp);
+	cp = move_firmware_args(argc, argv, cp);
 
-	while (actr < prom_argc) {
+	while (actr < argc) {
 		for (i = 0; i < ARRAY_SIZE(ignored); i++) {
 			int len = strlen(ignored[i]);
 
diff --git a/arch/mips/fw/arc/env.c b/arch/mips/fw/arc/env.c
index 1118a26b32ee..02407a7bb38e 100644
--- a/arch/mips/fw/arc/env.c
+++ b/arch/mips/fw/arc/env.c
@@ -19,9 +19,3 @@ ArcGetEnvironmentVariable(CHAR *name)
 {
 	return (CHAR *) ARC_CALL1(get_evar, name);
 }
-
-LONG __init
-ArcSetEnvironmentVariable(PCHAR name, PCHAR value)
-{
-	return ARC_CALL2(set_evar, name, value);
-}
diff --git a/arch/mips/fw/arc/file.c b/arch/mips/fw/arc/file.c
index 49fd3ff13fe5..b0d8535c80cc 100644
--- a/arch/mips/fw/arc/file.c
+++ b/arch/mips/fw/arc/file.c
@@ -13,62 +13,13 @@
 #include <asm/sgialib.h>
 
 LONG
-ArcGetDirectoryEntry(ULONG FileID, struct linux_vdirent *Buffer,
-		     ULONG N, ULONG *Count)
-{
-	return ARC_CALL4(get_vdirent, FileID, Buffer, N, Count);
-}
-
-LONG
-ArcOpen(CHAR *Path, enum linux_omode OpenMode, ULONG *FileID)
-{
-	return ARC_CALL3(open, Path, OpenMode, FileID);
-}
-
-LONG
-ArcClose(ULONG FileID)
-{
-	return ARC_CALL1(close, FileID);
-}
-
-LONG
 ArcRead(ULONG FileID, VOID *Buffer, ULONG N, ULONG *Count)
 {
 	return ARC_CALL4(read, FileID, Buffer, N, Count);
 }
 
 LONG
-ArcGetReadStatus(ULONG FileID)
-{
-	return ARC_CALL1(get_rstatus, FileID);
-}
-
-LONG
 ArcWrite(ULONG FileID, PVOID Buffer, ULONG N, PULONG Count)
 {
 	return ARC_CALL4(write, FileID, Buffer, N, Count);
 }
-
-LONG
-ArcSeek(ULONG FileID, struct linux_bigint *Position, enum linux_seekmode SeekMode)
-{
-	return ARC_CALL3(seek, FileID, Position, SeekMode);
-}
-
-LONG
-ArcMount(char *name, enum linux_mountops op)
-{
-	return ARC_CALL2(mount, name, op);
-}
-
-LONG
-ArcGetFileInformation(ULONG FileID, struct linux_finfo *Information)
-{
-	return ARC_CALL2(get_finfo, FileID, Information);
-}
-
-LONG ArcSetFileInformation(ULONG FileID, ULONG AttributeFlags,
-			   ULONG AttributeMask)
-{
-	return ARC_CALL3(set_finfo, FileID, AttributeFlags, AttributeMask);
-}
diff --git a/arch/mips/fw/arc/identify.c b/arch/mips/fw/arc/identify.c
index f90266c02c9d..5527e0f54079 100644
--- a/arch/mips/fw/arc/identify.c
+++ b/arch/mips/fw/arc/identify.c
@@ -32,10 +32,6 @@ static struct smatch mach_table[] = {
 		.liname		= "SGI Indy",
 		.flags		= PROM_FLAG_ARCS,
 	}, {
-		.arcname	= "SGI-IP27",
-		.liname		= "SGI Origin",
-		.flags		= PROM_FLAG_ARCS,
-	}, {
 		.arcname	= "SGI-IP28",
 		.liname		= "SGI IP28",
 		.flags		= PROM_FLAG_ARCS,
@@ -87,6 +83,11 @@ const char *get_system_type(void)
 	return system_type;
 }
 
+static pcomponent * __init ArcGetChild(pcomponent *Current)
+{
+	return (pcomponent *) ARC_CALL1(child_component, Current);
+}
+
 void __init prom_identify_arch(void)
 {
 	pcomponent *p;
@@ -98,13 +99,7 @@ void __init prom_identify_arch(void)
 	 */
 	p = ArcGetChild(PROM_NULL_COMPONENT);
 	if (p == NULL) {
-#ifdef CONFIG_SGI_IP27
-		/* IP27 PROM misbehaves, seems to not implement ARC
-		   GetChild().	So we just assume it's an IP27.	 */
-		iname = "SGI-IP27";
-#else
 		iname = "Unknown";
-#endif
 	} else
 		iname = (char *) (long) p->iname;
 
diff --git a/arch/mips/fw/arc/init.c b/arch/mips/fw/arc/init.c
index 008555969534..f9d1dea9b2ca 100644
--- a/arch/mips/fw/arc/init.c
+++ b/arch/mips/fw/arc/init.c
@@ -18,8 +18,11 @@
 
 /* Master romvec interface. */
 struct linux_romvec *romvec;
-int prom_argc;
-LONG *_prom_argv, *_prom_envp;
+
+#if defined(CONFIG_64BIT) && defined(CONFIG_FW_ARC32)
+/* stack for calling 32bit ARC prom */
+u64 o32_stk[4096];
+#endif
 
 void __init prom_init(void)
 {
@@ -27,10 +30,6 @@ void __init prom_init(void)
 
 	romvec = ROMVECTOR;
 
-	prom_argc = fw_arg0;
-	_prom_argv = (LONG *) fw_arg1;
-	_prom_envp = (LONG *) fw_arg2;
-
 	if (pb->magic != 0x53435241) {
 		printk(KERN_CRIT "Aieee, bad prom vector magic %08lx\n",
 		       (unsigned long) pb->magic);
@@ -38,7 +37,7 @@ void __init prom_init(void)
 			;
 	}
 
-	prom_init_cmdline();
+	prom_init_cmdline(fw_arg0, (LONG *)fw_arg1);
 	prom_identify_arch();
 	printk(KERN_INFO "PROMLIB: ARC firmware Version %d Revision %d\n",
 	       pb->ver, pb->rev);
@@ -49,11 +48,4 @@ void __init prom_init(void)
 	ArcRead(0, &c, 1, &cnt);
 	ArcEnterInteractiveMode();
 #endif
-#ifdef CONFIG_SGI_IP27
-	{
-		extern const struct plat_smp_ops ip27_smp_ops;
-
-		register_smp_ops(&ip27_smp_ops);
-	}
-#endif
 }
diff --git a/arch/mips/fw/arc/memory.c b/arch/mips/fw/arc/memory.c
index b4328b3b5288..dbbcddc82823 100644
--- a/arch/mips/fw/arc/memory.c
+++ b/arch/mips/fw/arc/memory.c
@@ -158,6 +158,10 @@ void __init prom_meminit(void)
 	}
 }
 
+void __weak __init prom_cleanup(void)
+{
+}
+
 void __init prom_free_prom_memory(void)
 {
 	int i;
@@ -169,4 +173,9 @@ void __init prom_free_prom_memory(void)
 		free_init_pages("prom memory",
 			prom_mem_base[i], prom_mem_base[i] + prom_mem_size[i]);
 	}
+	/*
+	 * at this point it isn't safe to call PROM functions
+	 * give platforms a way to do PROM cleanups
+	 */
+	prom_cleanup();
 }
diff --git a/arch/mips/fw/arc/misc.c b/arch/mips/fw/arc/misc.c
index 19f710117d97..d5b2d5901324 100644
--- a/arch/mips/fw/arc/misc.c
+++ b/arch/mips/fw/arc/misc.c
@@ -21,47 +21,6 @@
 #include <asm/bootinfo.h>
 
 VOID __noreturn
-ArcHalt(VOID)
-{
-	bc_disable();
-	local_irq_disable();
-	ARC_CALL0(halt);
-
-	unreachable();
-}
-
-VOID __noreturn
-ArcPowerDown(VOID)
-{
-	bc_disable();
-	local_irq_disable();
-	ARC_CALL0(pdown);
-
-	unreachable();
-}
-
-/* XXX is this a soft reset basically? XXX */
-VOID __noreturn
-ArcRestart(VOID)
-{
-	bc_disable();
-	local_irq_disable();
-	ARC_CALL0(restart);
-
-	unreachable();
-}
-
-VOID __noreturn
-ArcReboot(VOID)
-{
-	bc_disable();
-	local_irq_disable();
-	ARC_CALL0(reboot);
-
-	unreachable();
-}
-
-VOID __noreturn
 ArcEnterInteractiveMode(VOID)
 {
 	bc_disable();
@@ -71,24 +30,6 @@ ArcEnterInteractiveMode(VOID)
 	unreachable();
 }
 
-LONG
-ArcSaveConfiguration(VOID)
-{
-	return ARC_CALL0(cfg_save);
-}
-
-struct linux_sysid *
-ArcGetSystemId(VOID)
-{
-	return (struct linux_sysid *) ARC_CALL0(get_sysid);
-}
-
-VOID __init
-ArcFlushAllCaches(VOID)
-{
-	ARC_CALL0(cache_flush);
-}
-
 DISPLAY_STATUS * __init ArcGetDisplayStatus(ULONG FileID)
 {
 	return (DISPLAY_STATUS *) ARC_CALL1(GetDisplayStatus, FileID);
diff --git a/arch/mips/fw/arc/promlib.c b/arch/mips/fw/arc/promlib.c
index be381307fbb0..5e9e840a9314 100644
--- a/arch/mips/fw/arc/promlib.c
+++ b/arch/mips/fw/arc/promlib.c
@@ -11,6 +11,21 @@
 #include <asm/bcache.h>
 #include <asm/setup.h>
 
+#if defined(CONFIG_64BIT) && defined(CONFIG_FW_ARC32)
+/*
+ * For 64bit kernels working with a 32bit ARC PROM pointer arguments
+ * for ARC calls need to reside in CKEG0/1. But as soon as the kernel
+ * switches to it's first kernel thread stack is set to an address in
+ * XKPHYS, so anything on stack can't be used anymore. This is solved
+ * by using a * static declartion variables are put into BSS, which is
+ * linked to a CKSEG0 address. Since this is only used on UP platforms
+ * there is not spinlock needed
+ */
+#define O32_STATIC	static
+#else
+#define O32_STATIC
+#endif
+
 /*
  * IP22 boardcache is not compatible with board caches.	 Thus we disable it
  * during romvec action.  Since r4xx0.c is always compiled and linked with your
@@ -23,8 +38,10 @@
 
 void prom_putchar(char c)
 {
-	ULONG cnt;
-	CHAR it = c;
+	O32_STATIC ULONG cnt;
+	O32_STATIC CHAR it;
+
+	it = c;
 
 	bc_disable();
 	ArcWrite(1, &it, 1, &cnt);
@@ -33,8 +50,8 @@ void prom_putchar(char c)
 
 char prom_getchar(void)
 {
-	ULONG cnt;
-	CHAR c;
+	O32_STATIC ULONG cnt;
+	O32_STATIC CHAR c;
 
 	bc_disable();
 	ArcRead(0, &c, 1, &cnt);
diff --git a/arch/mips/fw/arc/salone.c b/arch/mips/fw/arc/salone.c
deleted file mode 100644
index 2d99f44d5576..000000000000
--- a/arch/mips/fw/arc/salone.c
+++ /dev/null
@@ -1,25 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Routines to load into memory and execute stand-along program images using
- * ARCS PROM firmware.
- *
- * Copyright (C) 1996 David S. Miller (davem@davemloft.net)
- */
-#include <linux/init.h>
-#include <asm/sgialib.h>
-
-LONG __init ArcLoad(CHAR *Path, ULONG TopAddr, ULONG *ExecAddr, ULONG *LowAddr)
-{
-	return ARC_CALL4(load, Path, TopAddr, ExecAddr, LowAddr);
-}
-
-LONG __init ArcInvoke(ULONG ExecAddr, ULONG StackAddr, ULONG Argc, CHAR *Argv[],
-	CHAR *Envp[])
-{
-	return ARC_CALL5(invoke, ExecAddr, StackAddr, Argc, Argv, Envp);
-}
-
-LONG __init ArcExecute(CHAR *Path, LONG Argc, CHAR *Argv[], CHAR *Envp[])
-{
-	return ARC_CALL4(exec, Path, Argc, Argv, Envp);
-}
diff --git a/arch/mips/fw/arc/time.c b/arch/mips/fw/arc/time.c
deleted file mode 100644
index 190cdb50b895..000000000000
--- a/arch/mips/fw/arc/time.c
+++ /dev/null
@@ -1,25 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Extracting time information from ARCS prom.
- *
- * Copyright (C) 1996 David S. Miller (davem@davemloft.net)
- */
-#include <linux/init.h>
-
-#include <asm/fw/arc/types.h>
-#include <asm/sgialib.h>
-
-struct linux_tinfo * __init
-ArcGetTime(VOID)
-{
-	return (struct linux_tinfo *) ARC_CALL0(get_tinfo);
-}
-
-ULONG __init
-ArcGetRelativeTime(VOID)
-{
-	return ARC_CALL0(get_rtime);
-}
diff --git a/arch/mips/fw/arc/tree.c b/arch/mips/fw/arc/tree.c
deleted file mode 100644
index 924a37dc2569..000000000000
--- a/arch/mips/fw/arc/tree.c
+++ /dev/null
@@ -1,127 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * PROM component device tree code.
- *
- * Copyright (C) 1996 David S. Miller (davem@davemloft.net)
- * Copyright (C) 1999 Ralf Baechle (ralf@gnu.org)
- * Copyright (C) 1999 Silicon Graphics, Inc.
- */
-#include <linux/init.h>
-#include <asm/fw/arc/types.h>
-#include <asm/sgialib.h>
-
-#undef DEBUG_PROM_TREE
-
-pcomponent * __init
-ArcGetPeer(pcomponent *Current)
-{
-	if (Current == PROM_NULL_COMPONENT)
-		return PROM_NULL_COMPONENT;
-
-	return (pcomponent *) ARC_CALL1(next_component, Current);
-}
-
-pcomponent * __init
-ArcGetChild(pcomponent *Current)
-{
-	return (pcomponent *) ARC_CALL1(child_component, Current);
-}
-
-pcomponent * __init
-ArcGetParent(pcomponent *Current)
-{
-	if (Current == PROM_NULL_COMPONENT)
-		return PROM_NULL_COMPONENT;
-
-	return (pcomponent *) ARC_CALL1(parent_component, Current);
-}
-
-LONG __init
-ArcGetConfigurationData(VOID *Buffer, pcomponent *Current)
-{
-	return ARC_CALL2(component_data, Buffer, Current);
-}
-
-pcomponent * __init
-ArcAddChild(pcomponent *Current, pcomponent *Template, VOID *ConfigurationData)
-{
-	return (pcomponent *)
-	       ARC_CALL3(child_add, Current, Template, ConfigurationData);
-}
-
-LONG __init
-ArcDeleteComponent(pcomponent *ComponentToDelete)
-{
-	return ARC_CALL1(comp_del, ComponentToDelete);
-}
-
-pcomponent * __init
-ArcGetComponent(CHAR *Path)
-{
-	return (pcomponent *)ARC_CALL1(component_by_path, Path);
-}
-
-#ifdef DEBUG_PROM_TREE
-
-static char *classes[] = {
-	"system", "processor", "cache", "adapter", "controller", "peripheral",
-	"memory"
-};
-
-static char *types[] = {
-	"arc", "cpu", "fpu", "picache", "pdcache", "sicache", "sdcache",
-	"sccache", "memdev", "eisa adapter", "tc adapter", "scsi adapter",
-	"dti adapter", "multi-func adapter", "disk controller",
-	"tp controller", "cdrom controller", "worm controller",
-	"serial controller", "net controller", "display controller",
-	"parallel controller", "pointer controller", "keyboard controller",
-	"audio controller", "misc controller", "disk peripheral",
-	"floppy peripheral", "tp peripheral", "modem peripheral",
-	"monitor peripheral", "printer peripheral", "pointer peripheral",
-	"keyboard peripheral", "terminal peripheral", "line peripheral",
-	"net peripheral", "misc peripheral", "anonymous"
-};
-
-static char *iflags[] = {
-	"bogus", "read only", "removable", "console in", "console out",
-	"input", "output"
-};
-
-static void __init
-dump_component(pcomponent *p)
-{
-	printk("[%p]:class<%s>type<%s>flags<%s>ver<%d>rev<%d>",
-	       p, classes[p->class], types[p->type],
-	       iflags[p->iflags], p->vers, p->rev);
-	printk("key<%08lx>\n\tamask<%08lx>cdsize<%d>ilen<%d>iname<%s>\n",
-	       p->key, p->amask, (int)p->cdsize, (int)p->ilen, p->iname);
-}
-
-static void __init
-traverse(pcomponent *p, int op)
-{
-	dump_component(p);
-	if(ArcGetChild(p))
-		traverse(ArcGetChild(p), 1);
-	if(ArcGetPeer(p) && op)
-		traverse(ArcGetPeer(p), 1);
-}
-
-void __init
-prom_testtree(void)
-{
-	pcomponent *p;
-
-	p = ArcGetChild(PROM_NULL_COMPONENT);
-	dump_component(p);
-	p = ArcGetChild(p);
-	while(p) {
-		dump_component(p);
-		p = ArcGetPeer(p);
-	}
-}
-
-#endif /* DEBUG_PROM_TREE  */
diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c
index d5b8c4717ded..1de215b283d6 100644
--- a/arch/mips/generic/init.c
+++ b/arch/mips/generic/init.c
@@ -20,9 +20,9 @@
 #include <asm/smp-ops.h>
 #include <asm/time.h>
 
-static __initdata const void *fdt;
-static __initdata const struct mips_machine *mach;
-static __initdata const void *mach_match_data;
+static __initconst const void *fdt;
+static __initconst const struct mips_machine *mach;
+static __initconst const void *mach_match_data;
 
 void __init prom_init(void)
 {
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index bb8658cc7f12..e5ac88392d1f 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -20,157 +20,176 @@
 #include <asm/compiler.h>
 #include <asm/cpu-features.h>
 #include <asm/cmpxchg.h>
+#include <asm/llsc.h>
+#include <asm/sync.h>
 #include <asm/war.h>
 
-/*
- * Using a branch-likely instruction to check the result of an sc instruction
- * works around a bug present in R10000 CPUs prior to revision 3.0 that could
- * cause ll-sc sequences to execute non-atomically.
- */
-#if R10000_LLSC_WAR
-# define __scbeqz "beqzl"
-#else
-# define __scbeqz "beqz"
-#endif
-
-#define ATOMIC_INIT(i)	  { (i) }
+#define ATOMIC_OPS(pfx, type)						\
+static __always_inline type pfx##_read(const pfx##_t *v)		\
+{									\
+	return READ_ONCE(v->counter);					\
+}									\
+									\
+static __always_inline void pfx##_set(pfx##_t *v, type i)		\
+{									\
+	WRITE_ONCE(v->counter, i);					\
+}									\
+									\
+static __always_inline type pfx##_cmpxchg(pfx##_t *v, type o, type n)	\
+{									\
+	return cmpxchg(&v->counter, o, n);				\
+}									\
+									\
+static __always_inline type pfx##_xchg(pfx##_t *v, type n)		\
+{									\
+	return xchg(&v->counter, n);					\
+}
 
-/*
- * atomic_read - read atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically reads the value of @v.
- */
-#define atomic_read(v)		READ_ONCE((v)->counter)
+#define ATOMIC_INIT(i)		{ (i) }
+ATOMIC_OPS(atomic, int)
 
-/*
- * atomic_set - set atomic variable
- * @v: pointer of type atomic_t
- * @i: required value
- *
- * Atomically sets the value of @v to @i.
- */
-#define atomic_set(v, i)	WRITE_ONCE((v)->counter, (i))
+#ifdef CONFIG_64BIT
+# define ATOMIC64_INIT(i)	{ (i) }
+ATOMIC_OPS(atomic64, s64)
+#endif
 
-#define ATOMIC_OP(op, c_op, asm_op)					      \
-static __inline__ void atomic_##op(int i, atomic_t * v)			      \
-{									      \
-	if (kernel_uses_llsc) {						      \
-		int temp;						      \
-									      \
-		loongson_llsc_mb();					      \
-		__asm__ __volatile__(					      \
-		"	.set	push					\n"   \
-		"	.set	"MIPS_ISA_LEVEL"			\n"   \
-		"1:	ll	%0, %1		# atomic_" #op "	\n"   \
-		"	" #asm_op " %0, %2				\n"   \
-		"	sc	%0, %1					\n"   \
-		"\t" __scbeqz "	%0, 1b					\n"   \
-		"	.set	pop					\n"   \
-		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)	      \
-		: "Ir" (i) : __LLSC_CLOBBER);				      \
-	} else {							      \
-		unsigned long flags;					      \
-									      \
-		raw_local_irq_save(flags);				      \
-		v->counter c_op i;					      \
-		raw_local_irq_restore(flags);				      \
-	}								      \
+#define ATOMIC_OP(pfx, op, type, c_op, asm_op, ll, sc)			\
+static __inline__ void pfx##_##op(type i, pfx##_t * v)			\
+{									\
+	type temp;							\
+									\
+	if (!kernel_uses_llsc) {					\
+		unsigned long flags;					\
+									\
+		raw_local_irq_save(flags);				\
+		v->counter c_op i;					\
+		raw_local_irq_restore(flags);				\
+		return;							\
+	}								\
+									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	" MIPS_ISA_LEVEL "			\n"	\
+	"	" __SYNC(full, loongson3_war) "			\n"	\
+	"1:	" #ll "	%0, %1		# " #pfx "_" #op "	\n"	\
+	"	" #asm_op " %0, %2				\n"	\
+	"	" #sc "	%0, %1					\n"	\
+	"\t" __SC_BEQZ "%0, 1b					\n"	\
+	"	.set	pop					\n"	\
+	: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)		\
+	: "Ir" (i) : __LLSC_CLOBBER);					\
 }
 
-#define ATOMIC_OP_RETURN(op, c_op, asm_op)				      \
-static __inline__ int atomic_##op##_return_relaxed(int i, atomic_t * v)	      \
-{									      \
-	int result;							      \
-									      \
-	if (kernel_uses_llsc) {						      \
-		int temp;						      \
-									      \
-		loongson_llsc_mb();					      \
-		__asm__ __volatile__(					      \
-		"	.set	push					\n"   \
-		"	.set	"MIPS_ISA_LEVEL"			\n"   \
-		"1:	ll	%1, %2		# atomic_" #op "_return	\n"   \
-		"	" #asm_op " %0, %1, %3				\n"   \
-		"	sc	%0, %2					\n"   \
-		"\t" __scbeqz "	%0, 1b					\n"   \
-		"	" #asm_op " %0, %1, %3				\n"   \
-		"	.set	pop					\n"   \
-		: "=&r" (result), "=&r" (temp),				      \
-		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
-		: "Ir" (i) : __LLSC_CLOBBER);				      \
-	} else {							      \
-		unsigned long flags;					      \
-									      \
-		raw_local_irq_save(flags);				      \
-		result = v->counter;					      \
-		result c_op i;						      \
-		v->counter = result;					      \
-		raw_local_irq_restore(flags);				      \
-	}								      \
-									      \
-	return result;							      \
+#define ATOMIC_OP_RETURN(pfx, op, type, c_op, asm_op, ll, sc)		\
+static __inline__ type pfx##_##op##_return_relaxed(type i, pfx##_t * v)	\
+{									\
+	type temp, result;						\
+									\
+	if (!kernel_uses_llsc) {					\
+		unsigned long flags;					\
+									\
+		raw_local_irq_save(flags);				\
+		result = v->counter;					\
+		result c_op i;						\
+		v->counter = result;					\
+		raw_local_irq_restore(flags);				\
+		return result;						\
+	}								\
+									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	" MIPS_ISA_LEVEL "			\n"	\
+	"	" __SYNC(full, loongson3_war) "			\n"	\
+	"1:	" #ll "	%1, %2		# " #pfx "_" #op "_return\n"	\
+	"	" #asm_op " %0, %1, %3				\n"	\
+	"	" #sc "	%0, %2					\n"	\
+	"\t" __SC_BEQZ "%0, 1b					\n"	\
+	"	" #asm_op " %0, %1, %3				\n"	\
+	"	.set	pop					\n"	\
+	: "=&r" (result), "=&r" (temp),					\
+	  "+" GCC_OFF_SMALL_ASM() (v->counter)				\
+	: "Ir" (i) : __LLSC_CLOBBER);					\
+									\
+	return result;							\
 }
 
-#define ATOMIC_FETCH_OP(op, c_op, asm_op)				      \
-static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v)	      \
-{									      \
-	int result;							      \
-									      \
-	if (kernel_uses_llsc) {						      \
-		int temp;						      \
-									      \
-		loongson_llsc_mb();					      \
-		__asm__ __volatile__(					      \
-		"	.set	push					\n"   \
-		"	.set	"MIPS_ISA_LEVEL"			\n"   \
-		"1:	ll	%1, %2		# atomic_fetch_" #op "	\n"   \
-		"	" #asm_op " %0, %1, %3				\n"   \
-		"	sc	%0, %2					\n"   \
-		"\t" __scbeqz "	%0, 1b					\n"   \
-		"	.set	pop					\n"   \
-		"	move	%0, %1					\n"   \
-		: "=&r" (result), "=&r" (temp),				      \
-		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
-		: "Ir" (i) : __LLSC_CLOBBER);				      \
-	} else {							      \
-		unsigned long flags;					      \
-									      \
-		raw_local_irq_save(flags);				      \
-		result = v->counter;					      \
-		v->counter c_op i;					      \
-		raw_local_irq_restore(flags);				      \
-	}								      \
-									      \
-	return result;							      \
+#define ATOMIC_FETCH_OP(pfx, op, type, c_op, asm_op, ll, sc)		\
+static __inline__ type pfx##_fetch_##op##_relaxed(type i, pfx##_t * v)	\
+{									\
+	int temp, result;						\
+									\
+	if (!kernel_uses_llsc) {					\
+		unsigned long flags;					\
+									\
+		raw_local_irq_save(flags);				\
+		result = v->counter;					\
+		v->counter c_op i;					\
+		raw_local_irq_restore(flags);				\
+		return result;						\
+	}								\
+									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	" MIPS_ISA_LEVEL "			\n"	\
+	"	" __SYNC(full, loongson3_war) "			\n"	\
+	"1:	" #ll "	%1, %2		# " #pfx "_fetch_" #op "\n"	\
+	"	" #asm_op " %0, %1, %3				\n"	\
+	"	" #sc "	%0, %2					\n"	\
+	"\t" __SC_BEQZ "%0, 1b					\n"	\
+	"	.set	pop					\n"	\
+	"	move	%0, %1					\n"	\
+	: "=&r" (result), "=&r" (temp),					\
+	  "+" GCC_OFF_SMALL_ASM() (v->counter)				\
+	: "Ir" (i) : __LLSC_CLOBBER);					\
+									\
+	return result;							\
 }
 
-#define ATOMIC_OPS(op, c_op, asm_op)					      \
-	ATOMIC_OP(op, c_op, asm_op)					      \
-	ATOMIC_OP_RETURN(op, c_op, asm_op)				      \
-	ATOMIC_FETCH_OP(op, c_op, asm_op)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(pfx, op, type, c_op, asm_op, ll, sc)			\
+	ATOMIC_OP(pfx, op, type, c_op, asm_op, ll, sc)			\
+	ATOMIC_OP_RETURN(pfx, op, type, c_op, asm_op, ll, sc)		\
+	ATOMIC_FETCH_OP(pfx, op, type, c_op, asm_op, ll, sc)
 
-ATOMIC_OPS(add, +=, addu)
-ATOMIC_OPS(sub, -=, subu)
+ATOMIC_OPS(atomic, add, int, +=, addu, ll, sc)
+ATOMIC_OPS(atomic, sub, int, -=, subu, ll, sc)
 
 #define atomic_add_return_relaxed	atomic_add_return_relaxed
 #define atomic_sub_return_relaxed	atomic_sub_return_relaxed
 #define atomic_fetch_add_relaxed	atomic_fetch_add_relaxed
 #define atomic_fetch_sub_relaxed	atomic_fetch_sub_relaxed
 
+#ifdef CONFIG_64BIT
+ATOMIC_OPS(atomic64, add, s64, +=, daddu, lld, scd)
+ATOMIC_OPS(atomic64, sub, s64, -=, dsubu, lld, scd)
+# define atomic64_add_return_relaxed	atomic64_add_return_relaxed
+# define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
+# define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
+# define atomic64_fetch_sub_relaxed	atomic64_fetch_sub_relaxed
+#endif /* CONFIG_64BIT */
+
 #undef ATOMIC_OPS
-#define ATOMIC_OPS(op, c_op, asm_op)					      \
-	ATOMIC_OP(op, c_op, asm_op)					      \
-	ATOMIC_FETCH_OP(op, c_op, asm_op)
+#define ATOMIC_OPS(pfx, op, type, c_op, asm_op, ll, sc)			\
+	ATOMIC_OP(pfx, op, type, c_op, asm_op, ll, sc)			\
+	ATOMIC_FETCH_OP(pfx, op, type, c_op, asm_op, ll, sc)
 
-ATOMIC_OPS(and, &=, and)
-ATOMIC_OPS(or, |=, or)
-ATOMIC_OPS(xor, ^=, xor)
+ATOMIC_OPS(atomic, and, int, &=, and, ll, sc)
+ATOMIC_OPS(atomic, or, int, |=, or, ll, sc)
+ATOMIC_OPS(atomic, xor, int, ^=, xor, ll, sc)
 
 #define atomic_fetch_and_relaxed	atomic_fetch_and_relaxed
 #define atomic_fetch_or_relaxed		atomic_fetch_or_relaxed
 #define atomic_fetch_xor_relaxed	atomic_fetch_xor_relaxed
 
+#ifdef CONFIG_64BIT
+ATOMIC_OPS(atomic64, and, s64, &=, and, lld, scd)
+ATOMIC_OPS(atomic64, or, s64, |=, or, lld, scd)
+ATOMIC_OPS(atomic64, xor, s64, ^=, xor, lld, scd)
+# define atomic64_fetch_and_relaxed	atomic64_fetch_and_relaxed
+# define atomic64_fetch_or_relaxed	atomic64_fetch_or_relaxed
+# define atomic64_fetch_xor_relaxed	atomic64_fetch_xor_relaxed
+#endif
+
 #undef ATOMIC_OPS
 #undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
@@ -184,258 +203,66 @@ ATOMIC_OPS(xor, ^=, xor)
  * Atomically test @v and subtract @i if @v is greater or equal than @i.
  * The function returns the old value of @v minus @i.
  */
-static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
-{
-	int result;
-
-	smp_mb__before_llsc();
-
-	if (kernel_uses_llsc) {
-		int temp;
-
-		loongson_llsc_mb();
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	"MIPS_ISA_LEVEL"			\n"
-		"1:	ll	%1, %2		# atomic_sub_if_positive\n"
-		"	.set	pop					\n"
-		"	subu	%0, %1, %3				\n"
-		"	move	%1, %0					\n"
-		"	bltz	%0, 2f					\n"
-		"	.set	push					\n"
-		"	.set	"MIPS_ISA_LEVEL"			\n"
-		"	sc	%1, %2					\n"
-		"\t" __scbeqz "	%1, 1b					\n"
-		"2:							\n"
-		"	.set	pop					\n"
-		: "=&r" (result), "=&r" (temp),
-		  "+" GCC_OFF_SMALL_ASM() (v->counter)
-		: "Ir" (i) : __LLSC_CLOBBER);
-	} else {
-		unsigned long flags;
-
-		raw_local_irq_save(flags);
-		result = v->counter;
-		result -= i;
-		if (result >= 0)
-			v->counter = result;
-		raw_local_irq_restore(flags);
-	}
-
-	smp_llsc_mb();
-
-	return result;
+#define ATOMIC_SIP_OP(pfx, type, op, ll, sc)				\
+static __inline__ int pfx##_sub_if_positive(type i, pfx##_t * v)	\
+{									\
+	type temp, result;						\
+									\
+	smp_mb__before_atomic();					\
+									\
+	if (!kernel_uses_llsc) {					\
+		unsigned long flags;					\
+									\
+		raw_local_irq_save(flags);				\
+		result = v->counter;					\
+		result -= i;						\
+		if (result >= 0)					\
+			v->counter = result;				\
+		raw_local_irq_restore(flags);				\
+		smp_mb__after_atomic();					\
+		return result;						\
+	}								\
+									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	" MIPS_ISA_LEVEL "			\n"	\
+	"	" __SYNC(full, loongson3_war) "			\n"	\
+	"1:	" #ll "	%1, %2		# atomic_sub_if_positive\n"	\
+	"	.set	pop					\n"	\
+	"	" #op "	%0, %1, %3				\n"	\
+	"	move	%1, %0					\n"	\
+	"	bltz	%0, 2f					\n"	\
+	"	.set	push					\n"	\
+	"	.set	" MIPS_ISA_LEVEL "			\n"	\
+	"	" #sc "	%1, %2					\n"	\
+	"	" __SC_BEQZ "%1, 1b				\n"	\
+	"2:	" __SYNC(full, loongson3_war) "			\n"	\
+	"	.set	pop					\n"	\
+	: "=&r" (result), "=&r" (temp),					\
+	  "+" GCC_OFF_SMALL_ASM() (v->counter)				\
+	: "Ir" (i)							\
+	: __LLSC_CLOBBER);						\
+									\
+	/*								\
+	 * In the Loongson3 workaround case we already have a		\
+	 * completion barrier at 2: above, which is needed due to the	\
+	 * bltz that can branch	to code outside of the LL/SC loop. As	\
+	 * such, we don't need to emit another barrier here.		\
+	 */								\
+	if (!__SYNC_loongson3_war)					\
+		smp_mb__after_atomic();					\
+									\
+	return result;							\
 }
 
-#define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
-#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
-
-/*
- * atomic_dec_if_positive - decrement by 1 if old value positive
- * @v: pointer of type atomic_t
- */
+ATOMIC_SIP_OP(atomic, int, subu, ll, sc)
 #define atomic_dec_if_positive(v)	atomic_sub_if_positive(1, v)
 
 #ifdef CONFIG_64BIT
-
-#define ATOMIC64_INIT(i)    { (i) }
-
-/*
- * atomic64_read - read atomic variable
- * @v: pointer of type atomic64_t
- *
- */
-#define atomic64_read(v)	READ_ONCE((v)->counter)
-
-/*
- * atomic64_set - set atomic variable
- * @v: pointer of type atomic64_t
- * @i: required value
- */
-#define atomic64_set(v, i)	WRITE_ONCE((v)->counter, (i))
-
-#define ATOMIC64_OP(op, c_op, asm_op)					      \
-static __inline__ void atomic64_##op(s64 i, atomic64_t * v)		      \
-{									      \
-	if (kernel_uses_llsc) {						      \
-		s64 temp;						      \
-									      \
-		loongson_llsc_mb();					      \
-		__asm__ __volatile__(					      \
-		"	.set	push					\n"   \
-		"	.set	"MIPS_ISA_LEVEL"			\n"   \
-		"1:	lld	%0, %1		# atomic64_" #op "	\n"   \
-		"	" #asm_op " %0, %2				\n"   \
-		"	scd	%0, %1					\n"   \
-		"\t" __scbeqz "	%0, 1b					\n"   \
-		"	.set	pop					\n"   \
-		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)	      \
-		: "Ir" (i) : __LLSC_CLOBBER);				      \
-	} else {							      \
-		unsigned long flags;					      \
-									      \
-		raw_local_irq_save(flags);				      \
-		v->counter c_op i;					      \
-		raw_local_irq_restore(flags);				      \
-	}								      \
-}
-
-#define ATOMIC64_OP_RETURN(op, c_op, asm_op)				      \
-static __inline__ s64 atomic64_##op##_return_relaxed(s64 i, atomic64_t * v)   \
-{									      \
-	s64 result;							      \
-									      \
-	if (kernel_uses_llsc) {						      \
-		s64 temp;						      \
-									      \
-		loongson_llsc_mb();					      \
-		__asm__ __volatile__(					      \
-		"	.set	push					\n"   \
-		"	.set	"MIPS_ISA_LEVEL"			\n"   \
-		"1:	lld	%1, %2		# atomic64_" #op "_return\n"  \
-		"	" #asm_op " %0, %1, %3				\n"   \
-		"	scd	%0, %2					\n"   \
-		"\t" __scbeqz "	%0, 1b					\n"   \
-		"	" #asm_op " %0, %1, %3				\n"   \
-		"	.set	pop					\n"   \
-		: "=&r" (result), "=&r" (temp),				      \
-		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
-		: "Ir" (i) : __LLSC_CLOBBER);				      \
-	} else {							      \
-		unsigned long flags;					      \
-									      \
-		raw_local_irq_save(flags);				      \
-		result = v->counter;					      \
-		result c_op i;						      \
-		v->counter = result;					      \
-		raw_local_irq_restore(flags);				      \
-	}								      \
-									      \
-	return result;							      \
-}
-
-#define ATOMIC64_FETCH_OP(op, c_op, asm_op)				      \
-static __inline__ s64 atomic64_fetch_##op##_relaxed(s64 i, atomic64_t * v)    \
-{									      \
-	s64 result;							      \
-									      \
-	if (kernel_uses_llsc) {						      \
-		s64 temp;						      \
-									      \
-		loongson_llsc_mb();					      \
-		__asm__ __volatile__(					      \
-		"	.set	push					\n"   \
-		"	.set	"MIPS_ISA_LEVEL"			\n"   \
-		"1:	lld	%1, %2		# atomic64_fetch_" #op "\n"   \
-		"	" #asm_op " %0, %1, %3				\n"   \
-		"	scd	%0, %2					\n"   \
-		"\t" __scbeqz "	%0, 1b					\n"   \
-		"	move	%0, %1					\n"   \
-		"	.set	pop					\n"   \
-		: "=&r" (result), "=&r" (temp),				      \
-		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
-		: "Ir" (i) : __LLSC_CLOBBER);				      \
-	} else {							      \
-		unsigned long flags;					      \
-									      \
-		raw_local_irq_save(flags);				      \
-		result = v->counter;					      \
-		v->counter c_op i;					      \
-		raw_local_irq_restore(flags);				      \
-	}								      \
-									      \
-	return result;							      \
-}
-
-#define ATOMIC64_OPS(op, c_op, asm_op)					      \
-	ATOMIC64_OP(op, c_op, asm_op)					      \
-	ATOMIC64_OP_RETURN(op, c_op, asm_op)				      \
-	ATOMIC64_FETCH_OP(op, c_op, asm_op)
-
-ATOMIC64_OPS(add, +=, daddu)
-ATOMIC64_OPS(sub, -=, dsubu)
-
-#define atomic64_add_return_relaxed	atomic64_add_return_relaxed
-#define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
-#define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
-#define atomic64_fetch_sub_relaxed	atomic64_fetch_sub_relaxed
-
-#undef ATOMIC64_OPS
-#define ATOMIC64_OPS(op, c_op, asm_op)					      \
-	ATOMIC64_OP(op, c_op, asm_op)					      \
-	ATOMIC64_FETCH_OP(op, c_op, asm_op)
-
-ATOMIC64_OPS(and, &=, and)
-ATOMIC64_OPS(or, |=, or)
-ATOMIC64_OPS(xor, ^=, xor)
-
-#define atomic64_fetch_and_relaxed	atomic64_fetch_and_relaxed
-#define atomic64_fetch_or_relaxed	atomic64_fetch_or_relaxed
-#define atomic64_fetch_xor_relaxed	atomic64_fetch_xor_relaxed
-
-#undef ATOMIC64_OPS
-#undef ATOMIC64_FETCH_OP
-#undef ATOMIC64_OP_RETURN
-#undef ATOMIC64_OP
-
-/*
- * atomic64_sub_if_positive - conditionally subtract integer from atomic
- *                            variable
- * @i: integer value to subtract
- * @v: pointer of type atomic64_t
- *
- * Atomically test @v and subtract @i if @v is greater or equal than @i.
- * The function returns the old value of @v minus @i.
- */
-static __inline__ s64 atomic64_sub_if_positive(s64 i, atomic64_t * v)
-{
-	s64 result;
-
-	smp_mb__before_llsc();
-
-	if (kernel_uses_llsc) {
-		s64 temp;
-
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	"MIPS_ISA_LEVEL"			\n"
-		"1:	lld	%1, %2		# atomic64_sub_if_positive\n"
-		"	dsubu	%0, %1, %3				\n"
-		"	move	%1, %0					\n"
-		"	bltz	%0, 1f					\n"
-		"	scd	%1, %2					\n"
-		"\t" __scbeqz "	%1, 1b					\n"
-		"1:							\n"
-		"	.set	pop					\n"
-		: "=&r" (result), "=&r" (temp),
-		  "+" GCC_OFF_SMALL_ASM() (v->counter)
-		: "Ir" (i));
-	} else {
-		unsigned long flags;
-
-		raw_local_irq_save(flags);
-		result = v->counter;
-		result -= i;
-		if (result >= 0)
-			v->counter = result;
-		raw_local_irq_restore(flags);
-	}
-
-	smp_llsc_mb();
-
-	return result;
-}
-
-#define atomic64_cmpxchg(v, o, n) \
-	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
-#define atomic64_xchg(v, new) (xchg(&((v)->counter), (new)))
-
-/*
- * atomic64_dec_if_positive - decrement by 1 if old value positive
- * @v: pointer of type atomic64_t
- */
+ATOMIC_SIP_OP(atomic64, s64, dsubu, lld, scd)
 #define atomic64_dec_if_positive(v)	atomic64_sub_if_positive(1, v)
+#endif
 
-#endif /* CONFIG_64BIT */
+#undef ATOMIC_SIP_OP
 
 #endif /* _ASM_ATOMIC_H */
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index 9228f7386220..49ff172a72b9 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -9,131 +9,26 @@
 #define __ASM_BARRIER_H
 
 #include <asm/addrspace.h>
+#include <asm/sync.h>
 
-/*
- * Sync types defined by the MIPS architecture (document MD00087 table 6.5)
- * These values are used with the sync instruction to perform memory barriers.
- * Types of ordering guarantees available through the SYNC instruction:
- * - Completion Barriers
- * - Ordering Barriers
- * As compared to the completion barrier, the ordering barrier is a
- * lighter-weight operation as it does not require the specified instructions
- * before the SYNC to be already completed. Instead it only requires that those
- * specified instructions which are subsequent to the SYNC in the instruction
- * stream are never re-ordered for processing ahead of the specified
- * instructions which are before the SYNC in the instruction stream.
- * This potentially reduces how many cycles the barrier instruction must stall
- * before it completes.
- * Implementations that do not use any of the non-zero values of stype to define
- * different barriers, such as ordering barriers, must make those stype values
- * act the same as stype zero.
- */
-
-/*
- * Completion barriers:
- * - Every synchronizable specified memory instruction (loads or stores or both)
- *   that occurs in the instruction stream before the SYNC instruction must be
- *   already globally performed before any synchronizable specified memory
- *   instructions that occur after the SYNC are allowed to be performed, with
- *   respect to any other processor or coherent I/O module.
- *
- * - The barrier does not guarantee the order in which instruction fetches are
- *   performed.
- *
- * - A stype value of zero will always be defined such that it performs the most
- *   complete set of synchronization operations that are defined.This means
- *   stype zero always does a completion barrier that affects both loads and
- *   stores preceding the SYNC instruction and both loads and stores that are
- *   subsequent to the SYNC instruction. Non-zero values of stype may be defined
- *   by the architecture or specific implementations to perform synchronization
- *   behaviors that are less complete than that of stype zero. If an
- *   implementation does not use one of these non-zero values to define a
- *   different synchronization behavior, then that non-zero value of stype must
- *   act the same as stype zero completion barrier. This allows software written
- *   for an implementation with a lighter-weight barrier to work on another
- *   implementation which only implements the stype zero completion barrier.
- *
- * - A completion barrier is required, potentially in conjunction with SSNOP (in
- *   Release 1 of the Architecture) or EHB (in Release 2 of the Architecture),
- *   to guarantee that memory reference results are visible across operating
- *   mode changes. For example, a completion barrier is required on some
- *   implementations on entry to and exit from Debug Mode to guarantee that
- *   memory effects are handled correctly.
- */
-
-/*
- * stype 0 - A completion barrier that affects preceding loads and stores and
- * subsequent loads and stores.
- * Older instructions which must reach the load/store ordering point before the
- * SYNC instruction completes: Loads, Stores
- * Younger instructions which must reach the load/store ordering point only
- * after the SYNC instruction completes: Loads, Stores
- * Older instructions which must be globally performed when the SYNC instruction
- * completes: Loads, Stores
- */
-#define STYPE_SYNC 0x0
-
-/*
- * Ordering barriers:
- * - Every synchronizable specified memory instruction (loads or stores or both)
- *   that occurs in the instruction stream before the SYNC instruction must
- *   reach a stage in the load/store datapath after which no instruction
- *   re-ordering is possible before any synchronizable specified memory
- *   instruction which occurs after the SYNC instruction in the instruction
- *   stream reaches the same stage in the load/store datapath.
- *
- * - If any memory instruction before the SYNC instruction in program order,
- *   generates a memory request to the external memory and any memory
- *   instruction after the SYNC instruction in program order also generates a
- *   memory request to external memory, the memory request belonging to the
- *   older instruction must be globally performed before the time the memory
- *   request belonging to the younger instruction is globally performed.
- *
- * - The barrier does not guarantee the order in which instruction fetches are
- *   performed.
- */
+static inline void __sync(void)
+{
+	asm volatile(__SYNC(full, always) ::: "memory");
+}
 
-/*
- * stype 0x10 - An ordering barrier that affects preceding loads and stores and
- * subsequent loads and stores.
- * Older instructions which must reach the load/store ordering point before the
- * SYNC instruction completes: Loads, Stores
- * Younger instructions which must reach the load/store ordering point only
- * after the SYNC instruction completes: Loads, Stores
- * Older instructions which must be globally performed when the SYNC instruction
- * completes: N/A
- */
-#define STYPE_SYNC_MB 0x10
+static inline void rmb(void)
+{
+	asm volatile(__SYNC(rmb, always) ::: "memory");
+}
+#define rmb rmb
 
-/*
- * stype 0x14 - A completion barrier specific to global invalidations
- *
- * When a sync instruction of this type completes any preceding GINVI or GINVT
- * operation has been globalized & completed on all coherent CPUs. Anything
- * that the GINV* instruction should invalidate will have been invalidated on
- * all coherent CPUs when this instruction completes. It is implementation
- * specific whether the GINV* instructions themselves will ensure completion,
- * or this sync type will.
- *
- * In systems implementing global invalidates (ie. with Config5.GI == 2 or 3)
- * this sync type also requires that previous SYNCI operations have completed.
- */
-#define STYPE_GINV	0x14
+static inline void wmb(void)
+{
+	asm volatile(__SYNC(wmb, always) ::: "memory");
+}
+#define wmb wmb
 
-#ifdef CONFIG_CPU_HAS_SYNC
-#define __sync()				\
-	__asm__ __volatile__(			\
-		".set	push\n\t"		\
-		".set	noreorder\n\t"		\
-		".set	mips2\n\t"		\
-		"sync\n\t"			\
-		".set	pop"			\
-		: /* no output */		\
-		: /* no input */		\
-		: "memory")
-#else
-#define __sync()	do { } while(0)
-#endif
+#define fast_mb()	__sync()
 
 #define __fast_iob()				\
 	__asm__ __volatile__(			\
@@ -146,17 +41,8 @@
 		: "m" (*(int *)CKSEG1)		\
 		: "memory")
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
-# define OCTEON_SYNCW_STR	".set push\n.set arch=octeon\nsyncw\nsyncw\n.set pop\n"
-# define __syncw()	__asm__ __volatile__(OCTEON_SYNCW_STR : : : "memory")
-
-# define fast_wmb()	__syncw()
-# define fast_rmb()	barrier()
-# define fast_mb()	__sync()
 # define fast_iob()	do { } while (0)
 #else /* ! CONFIG_CPU_CAVIUM_OCTEON */
-# define fast_wmb()	__sync()
-# define fast_rmb()	__sync()
-# define fast_mb()	__sync()
 # ifdef CONFIG_SGI_IP28
 #  define fast_iob()				\
 	__asm__ __volatile__(			\
@@ -192,23 +78,14 @@
 
 #endif /* !CONFIG_CPU_HAS_WB */
 
-#define wmb()		fast_wmb()
-#define rmb()		fast_rmb()
-
 #if defined(CONFIG_WEAK_ORDERING)
-# ifdef CONFIG_CPU_CAVIUM_OCTEON
-#  define __smp_mb()	__sync()
-#  define __smp_rmb()	barrier()
-#  define __smp_wmb()	__syncw()
-# else
-#  define __smp_mb()	__asm__ __volatile__("sync" : : :"memory")
-#  define __smp_rmb()	__asm__ __volatile__("sync" : : :"memory")
-#  define __smp_wmb()	__asm__ __volatile__("sync" : : :"memory")
-# endif
+# define __smp_mb()	__sync()
+# define __smp_rmb()	rmb()
+# define __smp_wmb()	wmb()
 #else
-#define __smp_mb()	barrier()
-#define __smp_rmb()	barrier()
-#define __smp_wmb()	barrier()
+# define __smp_mb()	barrier()
+# define __smp_rmb()	barrier()
+# define __smp_wmb()	barrier()
 #endif
 
 /*
@@ -218,13 +95,14 @@
  * ordering will be done by smp_llsc_mb() and friends.
  */
 #if defined(CONFIG_WEAK_REORDERING_BEYOND_LLSC) && defined(CONFIG_SMP)
-#define __WEAK_LLSC_MB		"	sync	\n"
-#define smp_llsc_mb()		__asm__ __volatile__(__WEAK_LLSC_MB : : :"memory")
-#define __LLSC_CLOBBER
+# define __WEAK_LLSC_MB		sync
+# define smp_llsc_mb() \
+	__asm__ __volatile__(__stringify(__WEAK_LLSC_MB) : : :"memory")
+# define __LLSC_CLOBBER
 #else
-#define __WEAK_LLSC_MB		"		\n"
-#define smp_llsc_mb()		do { } while (0)
-#define __LLSC_CLOBBER		"memory"
+# define __WEAK_LLSC_MB
+# define smp_llsc_mb()		do { } while (0)
+# define __LLSC_CLOBBER		"memory"
 #endif
 
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
@@ -241,52 +119,22 @@
 #define nudge_writes() mb()
 #endif
 
-#define __smp_mb__before_atomic()	__smp_mb__before_llsc()
-#define __smp_mb__after_atomic()	smp_llsc_mb()
-
 /*
- * Some Loongson 3 CPUs have a bug wherein execution of a memory access (load,
- * store or prefetch) in between an LL & SC can cause the SC instruction to
- * erroneously succeed, breaking atomicity. Whilst it's unusual to write code
- * containing such sequences, this bug bites harder than we might otherwise
- * expect due to reordering & speculation:
- *
- * 1) A memory access appearing prior to the LL in program order may actually
- *    be executed after the LL - this is the reordering case.
- *
- *    In order to avoid this we need to place a memory barrier (ie. a SYNC
- *    instruction) prior to every LL instruction, in between it and any earlier
- *    memory access instructions.
- *
- *    This reordering case is fixed by 3A R2 CPUs, ie. 3A2000 models and later.
- *
- * 2) If a conditional branch exists between an LL & SC with a target outside
- *    of the LL-SC loop, for example an exit upon value mismatch in cmpxchg()
- *    or similar, then misprediction of the branch may allow speculative
- *    execution of memory accesses from outside of the LL-SC loop.
- *
- *    In order to avoid this we need a memory barrier (ie. a SYNC instruction)
- *    at each affected branch target, for which we also use loongson_llsc_mb()
- *    defined below.
- *
- *    This case affects all current Loongson 3 CPUs.
- *
- * The above described cases cause an error in the cache coherence protocol;
- * such that the Invalidate of a competing LL-SC goes 'missing' and SC
- * erroneously observes its core still has Exclusive state and lets the SC
- * proceed.
- *
- * Therefore the error only occurs on SMP systems.
+ * In the Loongson3 LL/SC workaround case, all of our LL/SC loops already have
+ * a completion barrier immediately preceding the LL instruction. Therefore we
+ * can skip emitting a barrier from __smp_mb__before_atomic().
  */
-#ifdef CONFIG_CPU_LOONGSON3_WORKAROUNDS /* Loongson-3's LLSC workaround */
-#define loongson_llsc_mb()	__asm__ __volatile__("sync" : : :"memory")
+#ifdef CONFIG_CPU_LOONGSON3_WORKAROUNDS
+# define __smp_mb__before_atomic()
 #else
-#define loongson_llsc_mb()	do { } while (0)
+# define __smp_mb__before_atomic()	__smp_mb__before_llsc()
 #endif
 
+#define __smp_mb__after_atomic()	smp_llsc_mb()
+
 static inline void sync_ginv(void)
 {
-	asm volatile("sync\t%0" :: "i"(STYPE_GINV));
+	asm volatile(__SYNC(ginv, always));
 }
 
 #include <asm-generic/barrier.h>
diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h
index 985d6a02f9ea..a74769940fbd 100644
--- a/arch/mips/include/asm/bitops.h
+++ b/arch/mips/include/asm/bitops.h
@@ -13,16 +13,55 @@
 #error only <linux/bitops.h> can be included directly
 #endif
 
+#include <linux/bits.h>
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <asm/barrier.h>
 #include <asm/byteorder.h>		/* sigh ... */
 #include <asm/compiler.h>
 #include <asm/cpu-features.h>
+#include <asm/isa-rev.h>
 #include <asm/llsc.h>
 #include <asm/sgidefs.h>
 #include <asm/war.h>
 
+#define __bit_op(mem, insn, inputs...) do {			\
+	unsigned long temp;					\
+								\
+	asm volatile(						\
+	"	.set		push			\n"	\
+	"	.set		" MIPS_ISA_LEVEL "	\n"	\
+	"	" __SYNC(full, loongson3_war) "		\n"	\
+	"1:	" __LL		"%0, %1			\n"	\
+	"	" insn		"			\n"	\
+	"	" __SC		"%0, %1			\n"	\
+	"	" __SC_BEQZ	"%0, 1b			\n"	\
+	"	.set		pop			\n"	\
+	: "=&r"(temp), "+" GCC_OFF_SMALL_ASM()(mem)		\
+	: inputs						\
+	: __LLSC_CLOBBER);					\
+} while (0)
+
+#define __test_bit_op(mem, ll_dst, insn, inputs...) ({		\
+	unsigned long orig, temp;				\
+								\
+	asm volatile(						\
+	"	.set		push			\n"	\
+	"	.set		" MIPS_ISA_LEVEL "	\n"	\
+	"	" __SYNC(full, loongson3_war) "		\n"	\
+	"1:	" __LL		ll_dst ", %2		\n"	\
+	"	" insn		"			\n"	\
+	"	" __SC		"%1, %2			\n"	\
+	"	" __SC_BEQZ	"%1, 1b			\n"	\
+	"	.set		pop			\n"	\
+	: "=&r"(orig), "=&r"(temp),				\
+	  "+" GCC_OFF_SMALL_ASM()(mem)				\
+	: inputs						\
+	: __LLSC_CLOBBER);					\
+								\
+	orig;							\
+})
+
 /*
  * These are the "slower" versions of the functions and are in bitops.c.
  * These functions call raw_local_irq_{save,restore}().
@@ -30,8 +69,6 @@
 void __mips_set_bit(unsigned long nr, volatile unsigned long *addr);
 void __mips_clear_bit(unsigned long nr, volatile unsigned long *addr);
 void __mips_change_bit(unsigned long nr, volatile unsigned long *addr);
-int __mips_test_and_set_bit(unsigned long nr,
-			    volatile unsigned long *addr);
 int __mips_test_and_set_bit_lock(unsigned long nr,
 				 volatile unsigned long *addr);
 int __mips_test_and_clear_bit(unsigned long nr,
@@ -52,51 +89,20 @@ int __mips_test_and_change_bit(unsigned long nr,
  */
 static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
-	int bit = nr & SZLONG_MASK;
-	unsigned long temp;
+	volatile unsigned long *m = &addr[BIT_WORD(nr)];
+	int bit = nr % BITS_PER_LONG;
 
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	arch=r4000				\n"
-		"1:	" __LL "%0, %1			# set_bit	\n"
-		"	or	%0, %2					\n"
-		"	" __SC	"%0, %1					\n"
-		"	beqzl	%0, 1b					\n"
-		"	.set	pop					\n"
-		: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*m)
-		: "ir" (1UL << bit), GCC_OFF_SMALL_ASM() (*m)
-		: __LLSC_CLOBBER);
-#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
-	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
-		loongson_llsc_mb();
-		do {
-			__asm__ __volatile__(
-			"	" __LL "%0, %1		# set_bit	\n"
-			"	" __INS "%0, %3, %2, 1			\n"
-			"	" __SC "%0, %1				\n"
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
-			: "ir" (bit), "r" (~0)
-			: __LLSC_CLOBBER);
-		} while (unlikely(!temp));
-#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
-	} else if (kernel_uses_llsc) {
-		loongson_llsc_mb();
-		do {
-			__asm__ __volatile__(
-			"	.set	push				\n"
-			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
-			"	" __LL "%0, %1		# set_bit	\n"
-			"	or	%0, %2				\n"
-			"	" __SC	"%0, %1				\n"
-			"	.set	pop				\n"
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
-			: "ir" (1UL << bit)
-			: __LLSC_CLOBBER);
-		} while (unlikely(!temp));
-	} else
+	if (!kernel_uses_llsc) {
 		__mips_set_bit(nr, addr);
+		return;
+	}
+
+	if ((MIPS_ISA_REV >= 2) && __builtin_constant_p(bit) && (bit >= 16)) {
+		__bit_op(*m, __INS "%0, %3, %2, 1", "i"(bit), "r"(~0));
+		return;
+	}
+
+	__bit_op(*m, "or\t%0, %2", "ir"(BIT(bit)));
 }
 
 /*
@@ -111,51 +117,20 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
  */
 static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
-	int bit = nr & SZLONG_MASK;
-	unsigned long temp;
+	volatile unsigned long *m = &addr[BIT_WORD(nr)];
+	int bit = nr % BITS_PER_LONG;
 
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	arch=r4000				\n"
-		"1:	" __LL "%0, %1			# clear_bit	\n"
-		"	and	%0, %2					\n"
-		"	" __SC "%0, %1					\n"
-		"	beqzl	%0, 1b					\n"
-		"	.set	pop					\n"
-		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
-		: "ir" (~(1UL << bit))
-		: __LLSC_CLOBBER);
-#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
-	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
-		loongson_llsc_mb();
-		do {
-			__asm__ __volatile__(
-			"	" __LL "%0, %1		# clear_bit	\n"
-			"	" __INS "%0, $0, %2, 1			\n"
-			"	" __SC "%0, %1				\n"
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
-			: "ir" (bit)
-			: __LLSC_CLOBBER);
-		} while (unlikely(!temp));
-#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
-	} else if (kernel_uses_llsc) {
-		loongson_llsc_mb();
-		do {
-			__asm__ __volatile__(
-			"	.set	push				\n"
-			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
-			"	" __LL "%0, %1		# clear_bit	\n"
-			"	and	%0, %2				\n"
-			"	" __SC "%0, %1				\n"
-			"	.set	pop				\n"
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
-			: "ir" (~(1UL << bit))
-			: __LLSC_CLOBBER);
-		} while (unlikely(!temp));
-	} else
+	if (!kernel_uses_llsc) {
 		__mips_clear_bit(nr, addr);
+		return;
+	}
+
+	if ((MIPS_ISA_REV >= 2) && __builtin_constant_p(bit)) {
+		__bit_op(*m, __INS "%0, $0, %2, 1", "i"(bit));
+		return;
+	}
+
+	__bit_op(*m, "and\t%0, %2", "ir"(~BIT(bit)));
 }
 
 /*
@@ -183,159 +158,61 @@ static inline void clear_bit_unlock(unsigned long nr, volatile unsigned long *ad
  */
 static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	int bit = nr & SZLONG_MASK;
-
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
-		unsigned long temp;
-
-		__asm__ __volatile__(
-		"	.set	push				\n"
-		"	.set	arch=r4000			\n"
-		"1:	" __LL "%0, %1		# change_bit	\n"
-		"	xor	%0, %2				\n"
-		"	" __SC	"%0, %1				\n"
-		"	beqzl	%0, 1b				\n"
-		"	.set	pop				\n"
-		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
-		: "ir" (1UL << bit)
-		: __LLSC_CLOBBER);
-	} else if (kernel_uses_llsc) {
-		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
-		unsigned long temp;
-
-		loongson_llsc_mb();
-		do {
-			__asm__ __volatile__(
-			"	.set	push				\n"
-			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
-			"	" __LL "%0, %1		# change_bit	\n"
-			"	xor	%0, %2				\n"
-			"	" __SC	"%0, %1				\n"
-			"	.set	pop				\n"
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
-			: "ir" (1UL << bit)
-			: __LLSC_CLOBBER);
-		} while (unlikely(!temp));
-	} else
+	volatile unsigned long *m = &addr[BIT_WORD(nr)];
+	int bit = nr % BITS_PER_LONG;
+
+	if (!kernel_uses_llsc) {
 		__mips_change_bit(nr, addr);
+		return;
+	}
+
+	__bit_op(*m, "xor\t%0, %2", "ir"(BIT(bit)));
 }
 
 /*
- * test_and_set_bit - Set a bit and return its old value
+ * test_and_set_bit_lock - Set a bit and return its old value
  * @nr: Bit to set
  * @addr: Address to count from
  *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
+ * This operation is atomic and implies acquire ordering semantics
+ * after the memory operation.
  */
-static inline int test_and_set_bit(unsigned long nr,
+static inline int test_and_set_bit_lock(unsigned long nr,
 	volatile unsigned long *addr)
 {
-	int bit = nr & SZLONG_MASK;
-	unsigned long res;
+	volatile unsigned long *m = &addr[BIT_WORD(nr)];
+	int bit = nr % BITS_PER_LONG;
+	unsigned long res, orig;
 
-	smp_mb__before_llsc();
-
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
-		unsigned long temp;
-
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	arch=r4000				\n"
-		"1:	" __LL "%0, %1		# test_and_set_bit	\n"
-		"	or	%2, %0, %3				\n"
-		"	" __SC	"%2, %1					\n"
-		"	beqzl	%2, 1b					\n"
-		"	and	%2, %0, %3				\n"
-		"	.set	pop					\n"
-		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
-		: "r" (1UL << bit)
-		: __LLSC_CLOBBER);
-	} else if (kernel_uses_llsc) {
-		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
-		unsigned long temp;
-
-		loongson_llsc_mb();
-		do {
-			__asm__ __volatile__(
-			"	.set	push				\n"
-			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
-			"	" __LL "%0, %1	# test_and_set_bit	\n"
-			"	or	%2, %0, %3			\n"
-			"	" __SC	"%2, %1				\n"
-			"	.set	pop				\n"
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
-			: "r" (1UL << bit)
-			: __LLSC_CLOBBER);
-		} while (unlikely(!res));
-
-		res = temp & (1UL << bit);
-	} else
-		res = __mips_test_and_set_bit(nr, addr);
+	if (!kernel_uses_llsc) {
+		res = __mips_test_and_set_bit_lock(nr, addr);
+	} else {
+		orig = __test_bit_op(*m, "%0",
+				     "or\t%1, %0, %3",
+				     "ir"(BIT(bit)));
+		res = (orig & BIT(bit)) != 0;
+	}
 
 	smp_llsc_mb();
 
-	return res != 0;
+	return res;
 }
 
 /*
- * test_and_set_bit_lock - Set a bit and return its old value
+ * test_and_set_bit - Set a bit and return its old value
  * @nr: Bit to set
  * @addr: Address to count from
  *
- * This operation is atomic and implies acquire ordering semantics
- * after the memory operation.
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
  */
-static inline int test_and_set_bit_lock(unsigned long nr,
+static inline int test_and_set_bit(unsigned long nr,
 	volatile unsigned long *addr)
 {
-	int bit = nr & SZLONG_MASK;
-	unsigned long res;
-
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
-		unsigned long temp;
-
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	arch=r4000				\n"
-		"1:	" __LL "%0, %1		# test_and_set_bit	\n"
-		"	or	%2, %0, %3				\n"
-		"	" __SC	"%2, %1					\n"
-		"	beqzl	%2, 1b					\n"
-		"	and	%2, %0, %3				\n"
-		"	.set	pop					\n"
-		: "=&r" (temp), "+m" (*m), "=&r" (res)
-		: "r" (1UL << bit)
-		: __LLSC_CLOBBER);
-	} else if (kernel_uses_llsc) {
-		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
-		unsigned long temp;
-
-		loongson_llsc_mb();
-		do {
-			__asm__ __volatile__(
-			"	.set	push				\n"
-			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
-			"	" __LL "%0, %1	# test_and_set_bit	\n"
-			"	or	%2, %0, %3			\n"
-			"	" __SC	"%2, %1				\n"
-			"	.set	pop				\n"
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
-			: "r" (1UL << bit)
-			: __LLSC_CLOBBER);
-		} while (unlikely(!res));
-
-		res = temp & (1UL << bit);
-	} else
-		res = __mips_test_and_set_bit_lock(nr, addr);
-
-	smp_llsc_mb();
-
-	return res != 0;
+	smp_mb__before_atomic();
+	return test_and_set_bit_lock(nr, addr);
 }
+
 /*
  * test_and_clear_bit - Clear a bit and return its old value
  * @nr: Bit to clear
@@ -347,71 +224,30 @@ static inline int test_and_set_bit_lock(unsigned long nr,
 static inline int test_and_clear_bit(unsigned long nr,
 	volatile unsigned long *addr)
 {
-	int bit = nr & SZLONG_MASK;
-	unsigned long res;
-
-	smp_mb__before_llsc();
+	volatile unsigned long *m = &addr[BIT_WORD(nr)];
+	int bit = nr % BITS_PER_LONG;
+	unsigned long res, orig;
 
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
-		unsigned long temp;
+	smp_mb__before_atomic();
 
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	arch=r4000				\n"
-		"1:	" __LL	"%0, %1		# test_and_clear_bit	\n"
-		"	or	%2, %0, %3				\n"
-		"	xor	%2, %3					\n"
-		"	" __SC	"%2, %1					\n"
-		"	beqzl	%2, 1b					\n"
-		"	and	%2, %0, %3				\n"
-		"	.set	pop					\n"
-		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
-		: "r" (1UL << bit)
-		: __LLSC_CLOBBER);
-#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
-	} else if (kernel_uses_llsc && __builtin_constant_p(nr)) {
-		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
-		unsigned long temp;
-
-		loongson_llsc_mb();
-		do {
-			__asm__ __volatile__(
-			"	" __LL	"%0, %1 # test_and_clear_bit	\n"
-			"	" __EXT "%2, %0, %3, 1			\n"
-			"	" __INS "%0, $0, %3, 1			\n"
-			"	" __SC	"%0, %1				\n"
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
-			: "ir" (bit)
-			: __LLSC_CLOBBER);
-		} while (unlikely(!temp));
-#endif
-	} else if (kernel_uses_llsc) {
-		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
-		unsigned long temp;
-
-		loongson_llsc_mb();
-		do {
-			__asm__ __volatile__(
-			"	.set	push				\n"
-			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
-			"	" __LL	"%0, %1 # test_and_clear_bit	\n"
-			"	or	%2, %0, %3			\n"
-			"	xor	%2, %3				\n"
-			"	" __SC	"%2, %1				\n"
-			"	.set	pop				\n"
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
-			: "r" (1UL << bit)
-			: __LLSC_CLOBBER);
-		} while (unlikely(!res));
-
-		res = temp & (1UL << bit);
-	} else
+	if (!kernel_uses_llsc) {
 		res = __mips_test_and_clear_bit(nr, addr);
+	} else if ((MIPS_ISA_REV >= 2) && __builtin_constant_p(nr)) {
+		res = __test_bit_op(*m, "%1",
+				    __EXT "%0, %1, %3, 1;"
+				    __INS "%1, $0, %3, 1",
+				    "i"(bit));
+	} else {
+		orig = __test_bit_op(*m, "%0",
+				     "or\t%1, %0, %3;"
+				     "xor\t%1, %1, %3",
+				     "ir"(BIT(bit)));
+		res = (orig & BIT(bit)) != 0;
+	}
 
 	smp_llsc_mb();
 
-	return res != 0;
+	return res;
 }
 
 /*
@@ -425,54 +261,29 @@ static inline int test_and_clear_bit(unsigned long nr,
 static inline int test_and_change_bit(unsigned long nr,
 	volatile unsigned long *addr)
 {
-	int bit = nr & SZLONG_MASK;
-	unsigned long res;
+	volatile unsigned long *m = &addr[BIT_WORD(nr)];
+	int bit = nr % BITS_PER_LONG;
+	unsigned long res, orig;
 
-	smp_mb__before_llsc();
-
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
-		unsigned long temp;
+	smp_mb__before_atomic();
 
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	arch=r4000				\n"
-		"1:	" __LL	"%0, %1		# test_and_change_bit	\n"
-		"	xor	%2, %0, %3				\n"
-		"	" __SC	"%2, %1					\n"
-		"	beqzl	%2, 1b					\n"
-		"	and	%2, %0, %3				\n"
-		"	.set	pop					\n"
-		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
-		: "r" (1UL << bit)
-		: __LLSC_CLOBBER);
-	} else if (kernel_uses_llsc) {
-		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
-		unsigned long temp;
-
-		loongson_llsc_mb();
-		do {
-			__asm__ __volatile__(
-			"	.set	push				\n"
-			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
-			"	" __LL	"%0, %1 # test_and_change_bit	\n"
-			"	xor	%2, %0, %3			\n"
-			"	" __SC	"\t%2, %1			\n"
-			"	.set	pop				\n"
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
-			: "r" (1UL << bit)
-			: __LLSC_CLOBBER);
-		} while (unlikely(!res));
-
-		res = temp & (1UL << bit);
-	} else
+	if (!kernel_uses_llsc) {
 		res = __mips_test_and_change_bit(nr, addr);
+	} else {
+		orig = __test_bit_op(*m, "%0",
+				     "xor\t%1, %0, %3",
+				     "ir"(BIT(bit)));
+		res = (orig & BIT(bit)) != 0;
+	}
 
 	smp_llsc_mb();
 
-	return res != 0;
+	return res;
 }
 
+#undef __bit_op
+#undef __test_bit_op
+
 #include <asm-generic/bitops/non-atomic.h>
 
 /*
diff --git a/arch/mips/include/asm/bootinfo.h b/arch/mips/include/asm/bootinfo.h
index 34d62229dea5..d41a5057bc69 100644
--- a/arch/mips/include/asm/bootinfo.h
+++ b/arch/mips/include/asm/bootinfo.h
@@ -61,7 +61,7 @@
 /*
  * Valid machtype for Loongson family
  */
-enum loongson_machine_type {
+enum loongson2ef_machine_type {
 	MACH_LOONGSON_UNKNOWN,
 	MACH_LEMOTE_FL2E,
 	MACH_LEMOTE_FL2F,
@@ -70,7 +70,6 @@ enum loongson_machine_type {
 	MACH_DEXXON_GDIUM2F10,
 	MACH_LEMOTE_NAS,
 	MACH_LEMOTE_LL2F,
-	MACH_LOONGSON_GENERIC,
 	MACH_LOONGSON_END
 };
 
@@ -99,6 +98,7 @@ extern void detect_memory_region(phys_addr_t start, phys_addr_t sz_min,  phys_ad
 
 extern void prom_init(void);
 extern void prom_free_prom_memory(void);
+extern void prom_cleanup(void);
 
 extern void free_init_pages(const char *what,
 			    unsigned long begin, unsigned long end);
diff --git a/arch/mips/include/asm/bugs.h b/arch/mips/include/asm/bugs.h
index d8ab8b7129b5..d72dc6e1cf3c 100644
--- a/arch/mips/include/asm/bugs.h
+++ b/arch/mips/include/asm/bugs.h
@@ -26,9 +26,8 @@ extern void check_bugs64(void);
 
 static inline void check_bugs_early(void)
 {
-#ifdef CONFIG_64BIT
-	check_bugs64_early();
-#endif
+	if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64))
+		check_bugs64_early();
 }
 
 static inline void check_bugs(void)
@@ -37,19 +36,18 @@ static inline void check_bugs(void)
 
 	cpu_data[cpu].udelay_val = loops_per_jiffy;
 	check_bugs32();
-#ifdef CONFIG_64BIT
-	check_bugs64();
-#endif
+
+	if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64))
+		check_bugs64();
 }
 
 static inline int r4k_daddiu_bug(void)
 {
-#ifdef CONFIG_64BIT
+	if (!IS_ENABLED(CONFIG_CPU_R4X00_BUGS64))
+		return 0;
+
 	WARN_ON(daddiu_bug < 0);
 	return daddiu_bug != 0;
-#else
-	return 0;
-#endif
 }
 
 #endif /* _ASM_BUGS_H */
diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
index f6136871561d..5b0b3a6777ea 100644
--- a/arch/mips/include/asm/cmpxchg.h
+++ b/arch/mips/include/asm/cmpxchg.h
@@ -11,20 +11,11 @@
 #include <linux/bug.h>
 #include <linux/irqflags.h>
 #include <asm/compiler.h>
+#include <asm/llsc.h>
+#include <asm/sync.h>
 #include <asm/war.h>
 
 /*
- * Using a branch-likely instruction to check the result of an sc instruction
- * works around a bug present in R10000 CPUs prior to revision 3.0 that could
- * cause ll-sc sequences to execute non-atomically.
- */
-#if R10000_LLSC_WAR
-# define __scbeqz "beqzl"
-#else
-# define __scbeqz "beqz"
-#endif
-
-/*
  * These functions doesn't exist, so if they are called you'll either:
  *
  * - Get an error at compile-time due to __compiletime_error, if supported by
@@ -46,18 +37,18 @@ extern unsigned long __xchg_called_with_bad_pointer(void)
 	__typeof(*(m)) __ret;						\
 									\
 	if (kernel_uses_llsc) {						\
-		loongson_llsc_mb();					\
 		__asm__ __volatile__(					\
 		"	.set	push				\n"	\
 		"	.set	noat				\n"	\
 		"	.set	push				\n"	\
 		"	.set	" MIPS_ISA_ARCH_LEVEL "		\n"	\
+		"	" __SYNC(full, loongson3_war) "		\n"	\
 		"1:	" ld "	%0, %2		# __xchg_asm	\n"	\
 		"	.set	pop				\n"	\
 		"	move	$1, %z3				\n"	\
 		"	.set	" MIPS_ISA_ARCH_LEVEL "		\n"	\
 		"	" st "	$1, %1				\n"	\
-		"\t" __scbeqz "	$1, 1b				\n"	\
+		"\t" __SC_BEQZ	"$1, 1b				\n"	\
 		"	.set	pop				\n"	\
 		: "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m)		\
 		: GCC_OFF_SMALL_ASM() (*m), "Jr" (val)			\
@@ -103,7 +94,13 @@ unsigned long __xchg(volatile void *ptr, unsigned long x, int size)
 ({									\
 	__typeof__(*(ptr)) __res;					\
 									\
-	smp_mb__before_llsc();						\
+	/*								\
+	 * In the Loongson3 workaround case __xchg_asm() already	\
+	 * contains a completion barrier prior to the LL, so we don't	\
+	 * need to emit an extra one here.				\
+	 */								\
+	if (!__SYNC_loongson3_war)					\
+		smp_mb__before_llsc();					\
 									\
 	__res = (__typeof__(*(ptr)))					\
 		__xchg((ptr), (unsigned long)(x), sizeof(*(ptr)));	\
@@ -118,25 +115,24 @@ unsigned long __xchg(volatile void *ptr, unsigned long x, int size)
 	__typeof(*(m)) __ret;						\
 									\
 	if (kernel_uses_llsc) {						\
-		loongson_llsc_mb();					\
 		__asm__ __volatile__(					\
 		"	.set	push				\n"	\
 		"	.set	noat				\n"	\
 		"	.set	push				\n"	\
 		"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"	\
+		"	" __SYNC(full, loongson3_war) "		\n"	\
 		"1:	" ld "	%0, %2		# __cmpxchg_asm \n"	\
 		"	bne	%0, %z3, 2f			\n"	\
 		"	.set	pop				\n"	\
 		"	move	$1, %z4				\n"	\
 		"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"	\
 		"	" st "	$1, %1				\n"	\
-		"\t" __scbeqz "	$1, 1b				\n"	\
+		"\t" __SC_BEQZ	"$1, 1b				\n"	\
 		"	.set	pop				\n"	\
-		"2:						\n"	\
+		"2:	" __SYNC(full, loongson3_war) "		\n"	\
 		: "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m)		\
 		: GCC_OFF_SMALL_ASM() (*m), "Jr" (old), "Jr" (new)	\
 		: __LLSC_CLOBBER);					\
-		loongson_llsc_mb();					\
 	} else {							\
 		unsigned long __flags;					\
 									\
@@ -190,9 +186,23 @@ unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 ({									\
 	__typeof__(*(ptr)) __res;					\
 									\
-	smp_mb__before_llsc();						\
+	/*								\
+	 * In the Loongson3 workaround case __cmpxchg_asm() already	\
+	 * contains a completion barrier prior to the LL, so we don't	\
+	 * need to emit an extra one here.				\
+	 */								\
+	if (!__SYNC_loongson3_war)					\
+		smp_mb__before_llsc();					\
+									\
 	__res = cmpxchg_local((ptr), (old), (new));			\
-	smp_llsc_mb();							\
+									\
+	/*								\
+	 * In the Loongson3 workaround case __cmpxchg_asm() already	\
+	 * contains a completion barrier after the SC, so we don't	\
+	 * need to emit an extra one here.				\
+	 */								\
+	if (!__SYNC_loongson3_war)					\
+		smp_llsc_mb();						\
 									\
 	__res;								\
 })
@@ -233,11 +243,11 @@ static inline unsigned long __cmpxchg64(volatile void *ptr,
 	 */
 	local_irq_save(flags);
 
-	loongson_llsc_mb();
 	asm volatile(
 	"	.set	push				\n"
 	"	.set	" MIPS_ISA_ARCH_LEVEL "		\n"
 	/* Load 64 bits from ptr */
+	"	" __SYNC(full, loongson3_war) "		\n"
 	"1:	lld	%L0, %3		# __cmpxchg64	\n"
 	/*
 	 * Split the 64 bit value we loaded into the 2 registers that hold the
@@ -269,9 +279,9 @@ static inline unsigned long __cmpxchg64(volatile void *ptr,
 	/* Attempt to store new at ptr */
 	"	scd	%L1, %2				\n"
 	/* If we failed, loop! */
-	"\t" __scbeqz "	%L1, 1b				\n"
+	"\t" __SC_BEQZ "%L1, 1b				\n"
 	"	.set	pop				\n"
-	"2:						\n"
+	"2:	" __SYNC(full, loongson3_war) "		\n"
 	: "=&r"(ret),
 	  "=&r"(tmp),
 	  "=" GCC_OFF_SMALL_ASM() (*(unsigned long long *)ptr)
@@ -279,7 +289,6 @@ static inline unsigned long __cmpxchg64(volatile void *ptr,
 	  "r" (old),
 	  "r" (new)
 	: "memory");
-	loongson_llsc_mb();
 
 	local_irq_restore(flags);
 	return ret;
@@ -312,6 +321,4 @@ static inline unsigned long __cmpxchg64(volatile void *ptr,
 # endif /* !CONFIG_SMP */
 #endif /* !CONFIG_64BIT */
 
-#undef __scbeqz
-
 #endif /* __ASM_CMPXCHG_H */
diff --git a/arch/mips/include/asm/cop2.h b/arch/mips/include/asm/cop2.h
index 63b3468ede4c..6b7396a6a115 100644
--- a/arch/mips/include/asm/cop2.h
+++ b/arch/mips/include/asm/cop2.h
@@ -33,7 +33,7 @@ extern void nlm_cop2_restore(struct nlm_cop2_state *);
 #define cop2_present		1
 #define cop2_lazy_restore	0
 
-#elif defined(CONFIG_CPU_LOONGSON3)
+#elif defined(CONFIG_CPU_LOONGSON64)
 
 #define cop2_present		1
 #define cop2_lazy_restore	1
diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h
index 7bbb66760a07..c46c59b0f1b4 100644
--- a/arch/mips/include/asm/cpu-type.h
+++ b/arch/mips/include/asm/cpu-type.h
@@ -15,18 +15,17 @@
 static inline int __pure __get_cpu_type(const int cpu_type)
 {
 	switch (cpu_type) {
-#if defined(CONFIG_SYS_HAS_CPU_LOONGSON2E) || \
-    defined(CONFIG_SYS_HAS_CPU_LOONGSON2F)
-	case CPU_LOONGSON2:
+#if defined(CONFIG_SYS_HAS_CPU_LOONGSON2EF)
+	case CPU_LOONGSON2EF:
 #endif
 
-#ifdef CONFIG_SYS_HAS_CPU_LOONGSON3
-	case CPU_LOONGSON3:
+#ifdef CONFIG_SYS_HAS_CPU_LOONGSON64
+	case CPU_LOONGSON64:
 #endif
 
 #if defined(CONFIG_SYS_HAS_CPU_LOONGSON1B) || \
     defined(CONFIG_SYS_HAS_CPU_LOONGSON1C)
-	case CPU_LOONGSON1:
+	case CPU_LOONGSON32:
 #endif
 
 #ifdef CONFIG_SYS_HAS_CPU_MIPS32_R1
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index 7fddcb8350c6..ea830783d663 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -91,7 +91,9 @@
 #define PRID_IMP_LOONGSON_32	0x4200  /* Loongson-1 */
 #define PRID_IMP_R5432		0x5400
 #define PRID_IMP_R5500		0x5500
-#define PRID_IMP_LOONGSON_64	0x6300  /* Loongson-2/3 */
+#define PRID_IMP_LOONGSON_64R	0x6100  /* Reduced Loongson-2 */
+#define PRID_IMP_LOONGSON_64C	0x6300  /* Classic Loongson-2 and Loongson-3 */
+#define PRID_IMP_LOONGSON_64G	0xc000  /* Generic Loongson-2 and Loongson-3 */
 
 #define PRID_IMP_UNKNOWN	0xff00
 
@@ -310,15 +312,15 @@ enum cpu_type_enum {
 	 */
 	CPU_4KC, CPU_4KEC, CPU_4KSC, CPU_24K, CPU_34K, CPU_1004K, CPU_74K,
 	CPU_ALCHEMY, CPU_PR4450, CPU_BMIPS32, CPU_BMIPS3300, CPU_BMIPS4350,
-	CPU_BMIPS4380, CPU_BMIPS5000, CPU_XBURST, CPU_LOONGSON1, CPU_M14KC,
+	CPU_BMIPS4380, CPU_BMIPS5000, CPU_XBURST, CPU_LOONGSON32, CPU_M14KC,
 	CPU_M14KEC, CPU_INTERAPTIV, CPU_P5600, CPU_PROAPTIV, CPU_1074K,
 	CPU_M5150, CPU_I6400, CPU_P6600, CPU_M6250,
 
 	/*
 	 * MIPS64 class processors
 	 */
-	CPU_5KC, CPU_5KE, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2,
-	CPU_LOONGSON3, CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS,
+	CPU_5KC, CPU_5KE, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2EF,
+	CPU_LOONGSON64, CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS,
 	CPU_CAVIUM_OCTEON2, CPU_CAVIUM_OCTEON3, CPU_XLR, CPU_XLP, CPU_I6500,
 
 	CPU_QEMU_GENERIC,
diff --git a/arch/mips/include/asm/fixmap.h b/arch/mips/include/asm/fixmap.h
index 6842ffafd1e7..1784d4348c36 100644
--- a/arch/mips/include/asm/fixmap.h
+++ b/arch/mips/include/asm/fixmap.h
@@ -70,7 +70,7 @@ enum fixed_addresses {
 #include <asm-generic/fixmap.h>
 
 #define kmap_get_fixmap_pte(vaddr)					\
-	pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr), (vaddr)), (vaddr)), (vaddr))
+	pte_offset_kernel(pmd_offset(pud_offset(p4d_offset(pgd_offset_k(vaddr), (vaddr)), (vaddr)), (vaddr)), (vaddr))
 
 /*
  * Called from pgtable_init()
diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h
index b83b0397462d..110220705e97 100644
--- a/arch/mips/include/asm/futex.h
+++ b/arch/mips/include/asm/futex.h
@@ -16,6 +16,7 @@
 #include <asm/barrier.h>
 #include <asm/compiler.h>
 #include <asm/errno.h>
+#include <asm/sync.h>
 #include <asm/war.h>
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)		\
@@ -32,7 +33,7 @@
 		"	.set	arch=r4000			\n"	\
 		"2:	sc	$1, %2				\n"	\
 		"	beqzl	$1, 1b				\n"	\
-		__WEAK_LLSC_MB						\
+		__stringify(__WEAK_LLSC_MB) "			\n"	\
 		"3:						\n"	\
 		"	.insn					\n"	\
 		"	.set	pop				\n"	\
@@ -50,19 +51,19 @@
 		  "i" (-EFAULT)						\
 		: "memory");						\
 	} else if (cpu_has_llsc) {					\
-		loongson_llsc_mb();					\
 		__asm__ __volatile__(					\
 		"	.set	push				\n"	\
 		"	.set	noat				\n"	\
 		"	.set	push				\n"	\
 		"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"	\
+		"	" __SYNC(full, loongson3_war) "		\n"	\
 		"1:	"user_ll("%1", "%4")" # __futex_atomic_op\n"	\
 		"	.set	pop				\n"	\
 		"	" insn	"				\n"	\
 		"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"	\
 		"2:	"user_sc("$1", "%2")"			\n"	\
 		"	beqz	$1, 1b				\n"	\
-		__WEAK_LLSC_MB						\
+		__stringify(__WEAK_LLSC_MB) "			\n"	\
 		"3:						\n"	\
 		"	.insn					\n"	\
 		"	.set	pop				\n"	\
@@ -147,7 +148,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		"	.set	arch=r4000				\n"
 		"2:	sc	$1, %2					\n"
 		"	beqzl	$1, 1b					\n"
-		__WEAK_LLSC_MB
+		__stringify(__WEAK_LLSC_MB) "				\n"
 		"3:							\n"
 		"	.insn						\n"
 		"	.set	pop					\n"
@@ -164,13 +165,13 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		  "i" (-EFAULT)
 		: "memory");
 	} else if (cpu_has_llsc) {
-		loongson_llsc_mb();
 		__asm__ __volatile__(
 		"# futex_atomic_cmpxchg_inatomic			\n"
 		"	.set	push					\n"
 		"	.set	noat					\n"
 		"	.set	push					\n"
 		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
+		"	" __SYNC(full, loongson3_war) "			\n"
 		"1:	"user_ll("%1", "%3")"				\n"
 		"	bne	%1, %z4, 3f				\n"
 		"	.set	pop					\n"
@@ -178,8 +179,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
 		"2:	"user_sc("$1", "%2")"				\n"
 		"	beqz	$1, 1b					\n"
-		__WEAK_LLSC_MB
-		"3:							\n"
+		"3:	" __SYNC_ELSE(full, loongson3_war, __WEAK_LLSC_MB) "\n"
 		"	.insn						\n"
 		"	.set	pop					\n"
 		"	.section .fixup,\"ax\"				\n"
@@ -194,7 +194,6 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		: GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval),
 		  "i" (-EFAULT)
 		: "memory");
-		loongson_llsc_mb();
 	} else
 		return -ENOSYS;
 
diff --git a/arch/mips/include/asm/hazards.h b/arch/mips/include/asm/hazards.h
index 0fa27446869a..a4f48b0f5541 100644
--- a/arch/mips/include/asm/hazards.h
+++ b/arch/mips/include/asm/hazards.h
@@ -158,7 +158,7 @@ do {									\
 } while (0)
 
 #elif defined(CONFIG_MIPS_ALCHEMY) || defined(CONFIG_CPU_CAVIUM_OCTEON) || \
-	defined(CONFIG_CPU_LOONGSON2) || defined(CONFIG_LOONGSON3_ENHANCEMENT) || \
+	defined(CONFIG_CPU_LOONGSON2EF) || defined(CONFIG_LOONGSON3_ENHANCEMENT) || \
 	defined(CONFIG_CPU_R10000) || defined(CONFIG_CPU_R5500) || defined(CONFIG_CPU_XLR)
 
 /*
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index 2b7b56736372..3f6ce74335b4 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -306,7 +306,7 @@ static inline void iounmap(const volatile void __iomem *addr)
 #undef __IS_KSEG1
 }
 
-#if defined(CONFIG_CPU_CAVIUM_OCTEON) || defined(CONFIG_CPU_LOONGSON3)
+#if defined(CONFIG_CPU_CAVIUM_OCTEON) || defined(CONFIG_CPU_LOONGSON64)
 #define war_io_reorder_wmb()		wmb()
 #else
 #define war_io_reorder_wmb()		barrier()
diff --git a/arch/mips/include/asm/irqflags.h b/arch/mips/include/asm/irqflags.h
index f0b862a83816..c4728bbdf15b 100644
--- a/arch/mips/include/asm/irqflags.h
+++ b/arch/mips/include/asm/irqflags.h
@@ -41,7 +41,7 @@ static inline unsigned long arch_local_irq_save(void)
 	"	.set	push						\n"
 	"	.set	reorder						\n"
 	"	.set	noat						\n"
-#if defined(CONFIG_CPU_LOONGSON3) || defined (CONFIG_CPU_LOONGSON1)
+#if defined(CONFIG_CPU_LOONGSON64) || defined(CONFIG_CPU_LOONGSON32)
 	"	mfc0	%[flags], $12					\n"
 	"	di							\n"
 #else
diff --git a/arch/mips/include/asm/llsc.h b/arch/mips/include/asm/llsc.h
index c6d17d171147..c49738bc3bda 100644
--- a/arch/mips/include/asm/llsc.h
+++ b/arch/mips/include/asm/llsc.h
@@ -9,20 +9,31 @@
 #ifndef __ASM_LLSC_H
 #define __ASM_LLSC_H
 
+#include <asm/isa-rev.h>
+
 #if _MIPS_SZLONG == 32
-#define SZLONG_LOG 5
-#define SZLONG_MASK 31UL
 #define __LL		"ll	"
 #define __SC		"sc	"
 #define __INS		"ins	"
 #define __EXT		"ext	"
 #elif _MIPS_SZLONG == 64
-#define SZLONG_LOG 6
-#define SZLONG_MASK 63UL
 #define __LL		"lld	"
 #define __SC		"scd	"
 #define __INS		"dins	"
 #define __EXT		"dext	"
 #endif
 
+/*
+ * Using a branch-likely instruction to check the result of an sc instruction
+ * works around a bug present in R10000 CPUs prior to revision 3.0 that could
+ * cause ll-sc sequences to execute non-atomically.
+ */
+#if R10000_LLSC_WAR
+# define __SC_BEQZ "beqzl	"
+#elif MIPS_ISA_REV >= 6
+# define __SC_BEQZ "beqzc	"
+#else
+# define __SC_BEQZ "beqz	"
+#endif
+
 #endif /* __ASM_LLSC_H  */
diff --git a/arch/mips/include/asm/mach-ip22/spaces.h b/arch/mips/include/asm/mach-ip22/spaces.h
index 7f9fa6f66059..24fe92cb5313 100644
--- a/arch/mips/include/asm/mach-ip22/spaces.h
+++ b/arch/mips/include/asm/mach-ip22/spaces.h
@@ -10,17 +10,7 @@
 #ifndef _ASM_MACH_IP22_SPACES_H
 #define _ASM_MACH_IP22_SPACES_H
 
-
-#ifdef CONFIG_64BIT
-
-#define PAGE_OFFSET		0xffffffff80000000UL
-
-#define CAC_BASE		0xffffffff80000000
-#define IO_BASE			0xffffffffa0000000
-#define UNCAC_BASE		0xffffffffa0000000
-#define MAP_BASE		0xc000000000000000
-
-#endif /* CONFIG_64BIT */
+#define PHYS_OFFSET     _AC(0x08000000, UL)
 
 #include <asm/mach-generic/spaces.h>
 
diff --git a/arch/mips/include/asm/mach-ip27/mmzone.h b/arch/mips/include/asm/mach-ip27/mmzone.h
index 1cd6a23a84f2..f463826515df 100644
--- a/arch/mips/include/asm/mach-ip27/mmzone.h
+++ b/arch/mips/include/asm/mach-ip27/mmzone.h
@@ -6,7 +6,7 @@
 #include <asm/sn/arch.h>
 #include <asm/sn/hub.h>
 
-#define pa_to_nid(addr)		NASID_TO_COMPACT_NODEID(NASID_GET(addr))
+#define pa_to_nid(addr)		NASID_GET(addr)
 
 struct hub_data {
 	kern_vars_t	kern_vars;
diff --git a/arch/mips/include/asm/mach-ip27/topology.h b/arch/mips/include/asm/mach-ip27/topology.h
index 965f0793a5f9..be61ddcdacab 100644
--- a/arch/mips/include/asm/mach-ip27/topology.h
+++ b/arch/mips/include/asm/mach-ip27/topology.h
@@ -7,14 +7,13 @@
 #include <asm/mmzone.h>
 
 struct cpuinfo_ip27 {
-	cnodeid_t	p_nodeid;	/* my node ID in compact-id-space */
 	nasid_t		p_nasid;	/* my node ID in numa-as-id-space */
 	unsigned char	p_slice;	/* Physical position on node board */
 };
 
 extern struct cpuinfo_ip27 sn_cpu_info[NR_CPUS];
 
-#define cpu_to_node(cpu)	(sn_cpu_info[(cpu)].p_nodeid)
+#define cpu_to_node(cpu)	(cputonasid(cpu))
 #define cpumask_of_node(node)	((node) == -1 ?				\
 				 cpu_all_mask :				\
 				 &hub_data(node)->h_cpus)
@@ -23,7 +22,7 @@ extern int pcibus_to_node(struct pci_bus *);
 
 #define cpumask_of_pcibus(bus)	(cpumask_of_node(pcibus_to_node(bus)))
 
-extern unsigned char __node_distances[MAX_COMPACT_NODES][MAX_COMPACT_NODES];
+extern unsigned char __node_distances[MAX_NUMNODES][MAX_NUMNODES];
 
 #define node_distance(from, to) (__node_distances[(from)][(to)])
 
diff --git a/arch/mips/include/asm/mach-ip30/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip30/cpu-feature-overrides.h
new file mode 100644
index 000000000000..cfa02f3d25df
--- /dev/null
+++ b/arch/mips/include/asm/mach-ip30/cpu-feature-overrides.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * IP30/Octane cpu-features overrides.
+ *
+ * Copyright (C) 2003 Ralf Baechle <ralf@linux-mips.org>
+ *		 2004-2007 Stanislaw Skowronek <skylark@unaligned.org>
+ *		 2009 Johannes Dickgreber <tanzy@gmx.de>
+ *		 2015 Joshua Kinard <kumba@gentoo.org>
+ *
+ */
+#ifndef __ASM_MACH_IP30_CPU_FEATURE_OVERRIDES_H
+#define __ASM_MACH_IP30_CPU_FEATURE_OVERRIDES_H
+
+#include <asm/cpu.h>
+
+/*
+ * IP30 only supports R1[024]000 processors, all using the same config
+ */
+#define cpu_has_tlb			1
+#define cpu_has_tlbinv			0
+#define cpu_has_segments		0
+#define cpu_has_eva			0
+#define cpu_has_htw			0
+#define cpu_has_rixiex			0
+#define cpu_has_maar			0
+#define cpu_has_rw_llb			0
+#define cpu_has_3kex			0
+#define cpu_has_4kex			1
+#define cpu_has_3k_cache		0
+#define cpu_has_4k_cache		1
+#define cpu_has_6k_cache		0
+#define cpu_has_8k_cache		0
+#define cpu_has_tx39_cache		0
+#define cpu_has_fpu			1
+#define cpu_has_nofpuex			0
+#define cpu_has_32fpr			1
+#define cpu_has_counter			1
+#define cpu_has_watch			1
+#define cpu_has_64bits			1
+#define cpu_has_divec			0
+#define cpu_has_vce			0
+#define cpu_has_cache_cdex_p		0
+#define cpu_has_cache_cdex_s		0
+#define cpu_has_prefetch		1
+#define cpu_has_mcheck			0
+#define cpu_has_ejtag			0
+#define cpu_has_llsc			1
+#define cpu_has_mips16			0
+#define cpu_has_mdmx			0
+#define cpu_has_mips3d			0
+#define cpu_has_smartmips		0
+#define cpu_has_rixi			0
+#define cpu_has_xpa			0
+#define cpu_has_vtag_icache		0
+#define cpu_has_dc_aliases		0
+#define cpu_has_ic_fills_f_dc		0
+
+#define cpu_icache_snoops_remote_store	1
+
+#define cpu_has_mips32r1		0
+#define cpu_has_mips32r2		0
+#define cpu_has_mips64r1		0
+#define cpu_has_mips64r2		0
+#define cpu_has_mips32r6		0
+#define cpu_has_mips64r6		0
+
+#define cpu_has_dsp			0
+#define cpu_has_dsp2			0
+#define cpu_has_mipsmt			0
+#define cpu_has_userlocal		0
+#define cpu_has_inclusive_pcaches	1
+#define cpu_hwrena_impl_bits		0
+#define cpu_has_perf_cntr_intr_bit	0
+#define cpu_has_vz			0
+#define cpu_has_fre			0
+#define cpu_has_cdmm			0
+
+#define cpu_dcache_line_size()		32
+#define cpu_icache_line_size()		64
+#define cpu_scache_line_size()		128
+
+#endif /* __ASM_MACH_IP30_CPU_FEATURE_OVERRIDES_H */
+
diff --git a/arch/mips/include/asm/mach-ip30/irq.h b/arch/mips/include/asm/mach-ip30/irq.h
new file mode 100644
index 000000000000..e5c3dd965266
--- /dev/null
+++ b/arch/mips/include/asm/mach-ip30/irq.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * HEART IRQ defines
+ *
+ * Copyright (C) 2009 Johannes Dickgreber <tanzy@gmx.de>
+ *		 2014-2016 Joshua Kinard <kumba@gentoo.org>
+ *
+ */
+
+#ifndef __ASM_MACH_IP30_IRQ_H
+#define __ASM_MACH_IP30_IRQ_H
+
+/*
+ * HEART has 64 hardware interrupts, but use 128 to leave room for a few
+ * software interrupts as well (such as the CPU timer interrupt.
+ */
+#define NR_IRQS				128
+
+extern void __init ip30_install_ipi(void);
+
+/*
+ * HEART has 64 interrupt vectors available to it, subdivided into five
+ * priority levels.  They are numbered 0 to 63.
+ */
+#define HEART_NUM_IRQS			64
+
+/*
+ * These are the five interrupt priority levels and their corresponding
+ * CPU IPx interrupt pins.
+ *
+ * Level 4 - Error Interrupts.
+ * Level 3 - HEART timer interrupt.
+ * Level 2 - CPU IPI, CPU debug, power putton, general device interrupts.
+ * Level 1 - General device interrupts.
+ * Level 0 - General device GFX flow control interrupts.
+ */
+#define HEART_L4_INT_MASK		0xfff8000000000000ULL	/* IP6 */
+#define HEART_L3_INT_MASK		0x0004000000000000ULL	/* IP5 */
+#define HEART_L2_INT_MASK		0x0003ffff00000000ULL	/* IP4 */
+#define HEART_L1_INT_MASK		0x00000000ffff0000ULL	/* IP3 */
+#define HEART_L0_INT_MASK		0x000000000000ffffULL	/* IP2 */
+
+/* HEART L0 Interrupts (Low Priority) */
+#define HEART_L0_INT_GENERIC		 0
+#define HEART_L0_INT_FLOW_CTRL_HWTR_0	 1
+#define HEART_L0_INT_FLOW_CTRL_HWTR_1	 2
+
+/* HEART L2 Interrupts (High Priority) */
+#define HEART_L2_INT_RESCHED_CPU_0	46
+#define HEART_L2_INT_RESCHED_CPU_1	47
+#define HEART_L2_INT_CALL_CPU_0		48
+#define HEART_L2_INT_CALL_CPU_1		49
+
+/* HEART L3 Interrupts (Compare/Counter Timer) */
+#define HEART_L3_INT_TIMER		50
+
+/* HEART L4 Interrupts (Errors) */
+#define HEART_L4_INT_XWID_ERR_9		51
+#define HEART_L4_INT_XWID_ERR_A		52
+#define HEART_L4_INT_XWID_ERR_B		53
+#define HEART_L4_INT_XWID_ERR_C		54
+#define HEART_L4_INT_XWID_ERR_D		55
+#define HEART_L4_INT_XWID_ERR_E		56
+#define HEART_L4_INT_XWID_ERR_F		57
+#define HEART_L4_INT_XWID_ERR_XBOW	58
+#define HEART_L4_INT_CPU_BUS_ERR_0	59
+#define HEART_L4_INT_CPU_BUS_ERR_1	60
+#define HEART_L4_INT_CPU_BUS_ERR_2	61
+#define HEART_L4_INT_CPU_BUS_ERR_3	62
+#define HEART_L4_INT_HEART_EXCP		63
+
+/*
+ * Power Switch is wired via BaseIO BRIDGE slot #6.
+ *
+ * ACFail is wired via BaseIO BRIDGE slot #7.
+ */
+#define IP30_POWER_IRQ		HEART_L2_INT_POWER_BTN
+
+#include_next <irq.h>
+
+#define IP30_HEART_L0_IRQ	(MIPS_CPU_IRQ_BASE + 2)
+#define IP30_HEART_L1_IRQ	(MIPS_CPU_IRQ_BASE + 3)
+#define IP30_HEART_L2_IRQ	(MIPS_CPU_IRQ_BASE + 4)
+#define IP30_HEART_TIMER_IRQ	(MIPS_CPU_IRQ_BASE + 5)
+#define IP30_HEART_ERR_IRQ	(MIPS_CPU_IRQ_BASE + 6)
+
+#endif /* __ASM_MACH_IP30_IRQ_H */
diff --git a/arch/mips/include/asm/mach-ip30/kernel-entry-init.h b/arch/mips/include/asm/mach-ip30/kernel-entry-init.h
new file mode 100644
index 000000000000..be0472c977d8
--- /dev/null
+++ b/arch/mips/include/asm/mach-ip30/kernel-entry-init.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_MACH_IP30_KERNEL_ENTRY_H
+#define __ASM_MACH_IP30_KERNEL_ENTRY_H
+
+	.macro  kernel_entry_setup
+	.endm
+
+	.macro	smp_slave_setup
+	move	gp, a0
+	.endm
+
+#endif /* __ASM_MACH_IP30_KERNEL_ENTRY_H */
diff --git a/arch/mips/include/asm/mach-ip30/mangle-port.h b/arch/mips/include/asm/mach-ip30/mangle-port.h
new file mode 100644
index 000000000000..f3e1262a2d5e
--- /dev/null
+++ b/arch/mips/include/asm/mach-ip30/mangle-port.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2003, 2004 Ralf Baechle
+ */
+#ifndef __ASM_MACH_IP30_MANGLE_PORT_H
+#define __ASM_MACH_IP30_MANGLE_PORT_H
+
+#define __swizzle_addr_b(port)	((port)^3)
+#define __swizzle_addr_w(port)	((port)^2)
+#define __swizzle_addr_l(port)	(port)
+#define __swizzle_addr_q(port)	(port)
+
+#define ioswabb(a, x)		(x)
+#define __mem_ioswabb(a, x)	(x)
+#define ioswabw(a, x)		(x)
+#define __mem_ioswabw(a, x)	cpu_to_le16(x)
+#define ioswabl(a, x)		(x)
+#define __mem_ioswabl(a, x)	cpu_to_le32(x)
+#define ioswabq(a, x)		(x)
+#define __mem_ioswabq(a, x)	cpu_to_le64(x)
+
+#endif /* __ASM_MACH_IP30_MANGLE_PORT_H */
diff --git a/arch/mips/include/asm/mach-ip30/spaces.h b/arch/mips/include/asm/mach-ip30/spaces.h
new file mode 100644
index 000000000000..c8a302dfbe05
--- /dev/null
+++ b/arch/mips/include/asm/mach-ip30/spaces.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2016 Joshua Kinard <kumba@gentoo.org>
+ *
+ */
+#ifndef _ASM_MACH_IP30_SPACES_H
+#define _ASM_MACH_IP30_SPACES_H
+
+/*
+ * Memory in IP30/Octane is offset 512MB in the physical address space.
+ */
+#define PHYS_OFFSET	_AC(0x20000000, UL)
+
+#ifdef CONFIG_64BIT
+#define CAC_BASE	_AC(0xA800000000000000, UL)
+#endif
+
+#include <asm/mach-generic/spaces.h>
+
+#endif /* _ASM_MACH_IP30_SPACES_H */
diff --git a/arch/mips/include/asm/mach-ip30/war.h b/arch/mips/include/asm/mach-ip30/war.h
new file mode 100644
index 000000000000..a98ba204f183
--- /dev/null
+++ b/arch/mips/include/asm/mach-ip30/war.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2002, 2004, 2007 by Ralf Baechle <ralf@linux-mips.org>
+ */
+#ifndef __ASM_MIPS_MACH_IP30_WAR_H
+#define __ASM_MIPS_MACH_IP30_WAR_H
+
+#define R4600_V1_INDEX_ICACHEOP_WAR	0
+#define R4600_V1_HIT_CACHEOP_WAR	0
+#define R4600_V2_HIT_CACHEOP_WAR	0
+#define MIPS_CACHE_SYNC_WAR		0
+#define BCM1250_M3_WAR			0
+#define SIBYTE_1956_WAR			0
+#define MIPS4K_ICACHE_REFILL_WAR	0
+#define MIPS34K_MISSED_ITLB_WAR		0
+#define R5432_CP0_INTERRUPT_WAR		0
+#define TX49XX_ICACHE_INDEX_INV_WAR	0
+#define ICACHE_REFILLS_WORKAROUND_WAR	0
+
+#ifdef CONFIG_CPU_R10000
+#define R10000_LLSC_WAR			1
+#else
+#define R10000_LLSC_WAR			0
+#endif
+
+#endif /* __ASM_MIPS_MACH_IP30_WAR_H */
diff --git a/arch/mips/include/asm/mach-loongson2ef/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson2ef/cpu-feature-overrides.h
new file mode 100644
index 000000000000..b2ee859ca0b7
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson2ef/cpu-feature-overrides.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2009 Wu Zhangjin <wuzhangjin@gmail.com>
+ * Copyright (C) 2009 Philippe Vachon <philippe@cowpig.ca>
+ * Copyright (C) 2009 Zhang Le <r0bertz@gentoo.org>
+ *
+ * reference: /proc/cpuinfo,
+ *	arch/mips/kernel/cpu-probe.c(cpu_probe_legacy),
+ *	arch/mips/kernel/proc.c(show_cpuinfo),
+ *	loongson2f user manual.
+ */
+
+#ifndef __ASM_MACH_LOONGSON2EF_CPU_FEATURE_OVERRIDES_H
+#define __ASM_MACH_LOONGSON2EF_CPU_FEATURE_OVERRIDES_H
+
+#define cpu_has_32fpr		1
+#define cpu_has_3k_cache	0
+#define cpu_has_4k_cache	1
+#define cpu_has_4kex		1
+#define cpu_has_64bits		1
+#define cpu_has_cache_cdex_p	0
+#define cpu_has_cache_cdex_s	0
+#define cpu_has_counter		1
+#define cpu_has_dc_aliases	(PAGE_SIZE < 0x4000)
+#define cpu_has_divec		0
+#define cpu_has_ejtag		0
+#define cpu_has_inclusive_pcaches	1
+#define cpu_has_llsc		1
+#define cpu_has_mcheck		0
+#define cpu_has_mdmx		0
+#define cpu_has_mips16		0
+#define cpu_has_mips16e2	0
+#define cpu_has_mips3d		0
+#define cpu_has_mipsmt		0
+#define cpu_has_smartmips	0
+#define cpu_has_tlb		1
+#define cpu_has_tx39_cache	0
+#define cpu_has_vce		0
+#define cpu_has_veic		0
+#define cpu_has_vint		0
+#define cpu_has_vtag_icache	0
+#define cpu_has_watch		1
+
+#endif /* __ASM_MACH_LOONGSON64_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536.h b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536.h
index 9795b3361532..9795b3361532 100644
--- a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536.h
+++ b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536.h
diff --git a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_mfgpt.h b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_mfgpt.h
index 52e8bb0fc04d..52e8bb0fc04d 100644
--- a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_mfgpt.h
+++ b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_mfgpt.h
diff --git a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_pci.h b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_pci.h
index a0d4b752899e..a0d4b752899e 100644
--- a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_pci.h
+++ b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_pci.h
diff --git a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_vsm.h b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_vsm.h
index 70d0153cccc3..70d0153cccc3 100644
--- a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_vsm.h
+++ b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_vsm.h
diff --git a/arch/mips/include/asm/mach-loongson2ef/loongson.h b/arch/mips/include/asm/mach-loongson2ef/loongson.h
new file mode 100644
index 000000000000..5008af0a1a19
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson2ef/loongson.h
@@ -0,0 +1,326 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2009 Lemote, Inc.
+ * Author: Wu Zhangjin <wuzhangjin@gmail.com>
+ */
+
+#ifndef __ASM_MACH_LOONGSON2EF_LOONGSON_H
+#define __ASM_MACH_LOONGSON2EF_LOONGSON_H
+
+#include <linux/io.h>
+#include <linux/init.h>
+#include <linux/irq.h>
+
+/* loongson internal northbridge initialization */
+extern void bonito_irq_init(void);
+
+/* machine-specific reboot/halt operation */
+extern void mach_prepare_reboot(void);
+extern void mach_prepare_shutdown(void);
+
+/* environment arguments from bootloader */
+extern u32 cpu_clock_freq;
+extern u32 memsize, highmemsize;
+
+/* loongson-specific command line, env and memory initialization */
+extern void __init prom_init_memory(void);
+extern void __init prom_init_machtype(void);
+extern void __init prom_init_env(void);
+#ifdef CONFIG_LOONGSON_UART_BASE
+extern unsigned long _loongson_uart_base, loongson_uart_base;
+extern void prom_init_loongson_uart_base(void);
+#endif
+
+static inline void prom_init_uart_base(void)
+{
+#ifdef CONFIG_LOONGSON_UART_BASE
+	prom_init_loongson_uart_base();
+#endif
+}
+
+/* irq operation functions */
+extern void bonito_irqdispatch(void);
+extern void __init bonito_irq_init(void);
+extern void __init mach_init_irq(void);
+extern void mach_irq_dispatch(unsigned int pending);
+extern int mach_i8259_irq(void);
+
+/* We need this in some places... */
+#define delay() ({		\
+	int x;				\
+	for (x = 0; x < 100000; x++)	\
+		__asm__ __volatile__(""); \
+})
+
+#define LOONGSON_REG(x) \
+	(*(volatile u32 *)((char *)CKSEG1ADDR(LOONGSON_REG_BASE) + (x)))
+
+#define LOONGSON_IRQ_BASE	32
+#define LOONGSON2_PERFCNT_IRQ	(MIPS_CPU_IRQ_BASE + 6) /* cpu perf counter */
+
+#include <linux/interrupt.h>
+static inline void do_perfcnt_IRQ(void)
+{
+#if IS_ENABLED(CONFIG_OPROFILE)
+	do_IRQ(LOONGSON2_PERFCNT_IRQ);
+#endif
+}
+
+#define LOONGSON_FLASH_BASE	0x1c000000
+#define LOONGSON_FLASH_SIZE	0x02000000	/* 32M */
+#define LOONGSON_FLASH_TOP	(LOONGSON_FLASH_BASE+LOONGSON_FLASH_SIZE-1)
+
+#define LOONGSON_LIO0_BASE	0x1e000000
+#define LOONGSON_LIO0_SIZE	0x01C00000	/* 28M */
+#define LOONGSON_LIO0_TOP	(LOONGSON_LIO0_BASE+LOONGSON_LIO0_SIZE-1)
+
+#define LOONGSON_BOOT_BASE	0x1fc00000
+#define LOONGSON_BOOT_SIZE	0x00100000	/* 1M */
+#define LOONGSON_BOOT_TOP	(LOONGSON_BOOT_BASE+LOONGSON_BOOT_SIZE-1)
+#define LOONGSON_REG_BASE	0x1fe00000
+#define LOONGSON_REG_SIZE	0x00100000	/* 256Bytes + 256Bytes + ??? */
+#define LOONGSON_REG_TOP	(LOONGSON_REG_BASE+LOONGSON_REG_SIZE-1)
+
+#define LOONGSON_LIO1_BASE	0x1ff00000
+#define LOONGSON_LIO1_SIZE	0x00100000	/* 1M */
+#define LOONGSON_LIO1_TOP	(LOONGSON_LIO1_BASE+LOONGSON_LIO1_SIZE-1)
+
+#define LOONGSON_PCILO0_BASE	0x10000000
+#define LOONGSON_PCILO1_BASE	0x14000000
+#define LOONGSON_PCILO2_BASE	0x18000000
+#define LOONGSON_PCILO_BASE	LOONGSON_PCILO0_BASE
+#define LOONGSON_PCILO_SIZE	0x0c000000	/* 64M * 3 */
+#define LOONGSON_PCILO_TOP	(LOONGSON_PCILO0_BASE+LOONGSON_PCILO_SIZE-1)
+
+#define LOONGSON_PCICFG_BASE	0x1fe80000
+#define LOONGSON_PCICFG_SIZE	0x00000800	/* 2K */
+#define LOONGSON_PCICFG_TOP	(LOONGSON_PCICFG_BASE+LOONGSON_PCICFG_SIZE-1)
+#define LOONGSON_PCIIO_BASE	0x1fd00000
+
+#define LOONGSON_PCIIO_SIZE	0x00100000	/* 1M */
+#define LOONGSON_PCIIO_TOP	(LOONGSON_PCIIO_BASE+LOONGSON_PCIIO_SIZE-1)
+
+/* Loongson Register Bases */
+
+#define LOONGSON_PCICONFIGBASE	0x00
+#define LOONGSON_REGBASE	0x100
+
+/* PCI Configuration Registers */
+
+#define LOONGSON_PCI_REG(x)	LOONGSON_REG(LOONGSON_PCICONFIGBASE + (x))
+#define LOONGSON_PCIDID		LOONGSON_PCI_REG(0x00)
+#define LOONGSON_PCICMD		LOONGSON_PCI_REG(0x04)
+#define LOONGSON_PCICLASS	LOONGSON_PCI_REG(0x08)
+#define LOONGSON_PCILTIMER	LOONGSON_PCI_REG(0x0c)
+#define LOONGSON_PCIBASE0	LOONGSON_PCI_REG(0x10)
+#define LOONGSON_PCIBASE1	LOONGSON_PCI_REG(0x14)
+#define LOONGSON_PCIBASE2	LOONGSON_PCI_REG(0x18)
+#define LOONGSON_PCIBASE3	LOONGSON_PCI_REG(0x1c)
+#define LOONGSON_PCIBASE4	LOONGSON_PCI_REG(0x20)
+#define LOONGSON_PCIEXPRBASE	LOONGSON_PCI_REG(0x30)
+#define LOONGSON_PCIINT		LOONGSON_PCI_REG(0x3c)
+
+#define LOONGSON_PCI_ISR4C	LOONGSON_PCI_REG(0x4c)
+
+#define LOONGSON_PCICMD_PERR_CLR	0x80000000
+#define LOONGSON_PCICMD_SERR_CLR	0x40000000
+#define LOONGSON_PCICMD_MABORT_CLR	0x20000000
+#define LOONGSON_PCICMD_MTABORT_CLR	0x10000000
+#define LOONGSON_PCICMD_TABORT_CLR	0x08000000
+#define LOONGSON_PCICMD_MPERR_CLR	0x01000000
+#define LOONGSON_PCICMD_PERRRESPEN	0x00000040
+#define LOONGSON_PCICMD_ASTEPEN		0x00000080
+#define LOONGSON_PCICMD_SERREN		0x00000100
+#define LOONGSON_PCILTIMER_BUSLATENCY	0x0000ff00
+#define LOONGSON_PCILTIMER_BUSLATENCY_SHIFT	8
+
+/* Loongson h/w Configuration */
+
+#define LOONGSON_GENCFG_OFFSET		0x4
+#define LOONGSON_GENCFG LOONGSON_REG(LOONGSON_REGBASE + LOONGSON_GENCFG_OFFSET)
+
+#define LOONGSON_GENCFG_DEBUGMODE	0x00000001
+#define LOONGSON_GENCFG_SNOOPEN		0x00000002
+#define LOONGSON_GENCFG_CPUSELFRESET	0x00000004
+
+#define LOONGSON_GENCFG_FORCE_IRQA	0x00000008
+#define LOONGSON_GENCFG_IRQA_ISOUT	0x00000010
+#define LOONGSON_GENCFG_IRQA_FROM_INT1	0x00000020
+#define LOONGSON_GENCFG_BYTESWAP	0x00000040
+
+#define LOONGSON_GENCFG_UNCACHED	0x00000080
+#define LOONGSON_GENCFG_PREFETCHEN	0x00000100
+#define LOONGSON_GENCFG_WBEHINDEN	0x00000200
+#define LOONGSON_GENCFG_CACHEALG	0x00000c00
+#define LOONGSON_GENCFG_CACHEALG_SHIFT	10
+#define LOONGSON_GENCFG_PCIQUEUE	0x00001000
+#define LOONGSON_GENCFG_CACHESTOP	0x00002000
+#define LOONGSON_GENCFG_MSTRBYTESWAP	0x00004000
+#define LOONGSON_GENCFG_BUSERREN	0x00008000
+#define LOONGSON_GENCFG_NORETRYTIMEOUT	0x00010000
+#define LOONGSON_GENCFG_SHORTCOPYTIMEOUT	0x00020000
+
+/* PCI address map control */
+
+#define LOONGSON_PCIMAP			LOONGSON_REG(LOONGSON_REGBASE + 0x10)
+#define LOONGSON_PCIMEMBASECFG		LOONGSON_REG(LOONGSON_REGBASE + 0x14)
+#define LOONGSON_PCIMAP_CFG		LOONGSON_REG(LOONGSON_REGBASE + 0x18)
+
+/* GPIO Regs - r/w */
+
+#define LOONGSON_GPIODATA		LOONGSON_REG(LOONGSON_REGBASE + 0x1c)
+#define LOONGSON_GPIOIE			LOONGSON_REG(LOONGSON_REGBASE + 0x20)
+
+/* ICU Configuration Regs - r/w */
+
+#define LOONGSON_INTEDGE		LOONGSON_REG(LOONGSON_REGBASE + 0x24)
+#define LOONGSON_INTSTEER		LOONGSON_REG(LOONGSON_REGBASE + 0x28)
+#define LOONGSON_INTPOL			LOONGSON_REG(LOONGSON_REGBASE + 0x2c)
+
+/* ICU Enable Regs - IntEn & IntISR are r/o. */
+
+#define LOONGSON_INTENSET		LOONGSON_REG(LOONGSON_REGBASE + 0x30)
+#define LOONGSON_INTENCLR		LOONGSON_REG(LOONGSON_REGBASE + 0x34)
+#define LOONGSON_INTEN			LOONGSON_REG(LOONGSON_REGBASE + 0x38)
+#define LOONGSON_INTISR			LOONGSON_REG(LOONGSON_REGBASE + 0x3c)
+
+/* ICU */
+#define LOONGSON_ICU_MBOXES		0x0000000f
+#define LOONGSON_ICU_MBOXES_SHIFT	0
+#define LOONGSON_ICU_DMARDY		0x00000010
+#define LOONGSON_ICU_DMAEMPTY		0x00000020
+#define LOONGSON_ICU_COPYRDY		0x00000040
+#define LOONGSON_ICU_COPYEMPTY		0x00000080
+#define LOONGSON_ICU_COPYERR		0x00000100
+#define LOONGSON_ICU_PCIIRQ		0x00000200
+#define LOONGSON_ICU_MASTERERR		0x00000400
+#define LOONGSON_ICU_SYSTEMERR		0x00000800
+#define LOONGSON_ICU_DRAMPERR		0x00001000
+#define LOONGSON_ICU_RETRYERR		0x00002000
+#define LOONGSON_ICU_GPIOS		0x01ff0000
+#define LOONGSON_ICU_GPIOS_SHIFT		16
+#define LOONGSON_ICU_GPINS		0x7e000000
+#define LOONGSON_ICU_GPINS_SHIFT		25
+#define LOONGSON_ICU_MBOX(N)		(1<<(LOONGSON_ICU_MBOXES_SHIFT+(N)))
+#define LOONGSON_ICU_GPIO(N)		(1<<(LOONGSON_ICU_GPIOS_SHIFT+(N)))
+#define LOONGSON_ICU_GPIN(N)		(1<<(LOONGSON_ICU_GPINS_SHIFT+(N)))
+
+/* PCI prefetch window base & mask */
+
+#define LOONGSON_MEM_WIN_BASE_L		LOONGSON_REG(LOONGSON_REGBASE + 0x40)
+#define LOONGSON_MEM_WIN_BASE_H		LOONGSON_REG(LOONGSON_REGBASE + 0x44)
+#define LOONGSON_MEM_WIN_MASK_L		LOONGSON_REG(LOONGSON_REGBASE + 0x48)
+#define LOONGSON_MEM_WIN_MASK_H		LOONGSON_REG(LOONGSON_REGBASE + 0x4c)
+
+/* PCI_Hit*_Sel_* */
+
+#define LOONGSON_PCI_HIT0_SEL_L		LOONGSON_REG(LOONGSON_REGBASE + 0x50)
+#define LOONGSON_PCI_HIT0_SEL_H		LOONGSON_REG(LOONGSON_REGBASE + 0x54)
+#define LOONGSON_PCI_HIT1_SEL_L		LOONGSON_REG(LOONGSON_REGBASE + 0x58)
+#define LOONGSON_PCI_HIT1_SEL_H		LOONGSON_REG(LOONGSON_REGBASE + 0x5c)
+#define LOONGSON_PCI_HIT2_SEL_L		LOONGSON_REG(LOONGSON_REGBASE + 0x60)
+#define LOONGSON_PCI_HIT2_SEL_H		LOONGSON_REG(LOONGSON_REGBASE + 0x64)
+
+/* PXArb Config & Status */
+
+#define LOONGSON_PXARB_CFG		LOONGSON_REG(LOONGSON_REGBASE + 0x68)
+#define LOONGSON_PXARB_STATUS		LOONGSON_REG(LOONGSON_REGBASE + 0x6c)
+
+/* Chip Config registor of each physical cpu package, PRid >= Loongson-2F */
+#define LOONGSON_CHIPCFG	(void __iomem *)TO_UNCAC(0x1fc00180)
+
+/* pcimap */
+
+#define LOONGSON_PCIMAP_PCIMAP_LO0	0x0000003f
+#define LOONGSON_PCIMAP_PCIMAP_LO0_SHIFT	0
+#define LOONGSON_PCIMAP_PCIMAP_LO1	0x00000fc0
+#define LOONGSON_PCIMAP_PCIMAP_LO1_SHIFT	6
+#define LOONGSON_PCIMAP_PCIMAP_LO2	0x0003f000
+#define LOONGSON_PCIMAP_PCIMAP_LO2_SHIFT	12
+#define LOONGSON_PCIMAP_PCIMAP_2	0x00040000
+#define LOONGSON_PCIMAP_WIN(WIN, ADDR)	\
+	((((ADDR)>>26) & LOONGSON_PCIMAP_PCIMAP_LO0) << ((WIN)*6))
+
+#ifdef CONFIG_CPU_SUPPORTS_CPUFREQ
+#include <linux/cpufreq.h>
+extern struct cpufreq_frequency_table loongson2_clockmod_table[];
+#endif
+
+/*
+ * address windows configuration module
+ *
+ * loongson2e do not have this module
+ */
+#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG
+
+/* address window config module base address */
+#define LOONGSON_ADDRWINCFG_BASE		0x3ff00000ul
+#define LOONGSON_ADDRWINCFG_SIZE		0x180
+
+extern unsigned long _loongson_addrwincfg_base;
+#define LOONGSON_ADDRWINCFG(offset) \
+	(*(volatile u64 *)(_loongson_addrwincfg_base + (offset)))
+
+#define CPU_WIN0_BASE	LOONGSON_ADDRWINCFG(0x00)
+#define CPU_WIN1_BASE	LOONGSON_ADDRWINCFG(0x08)
+#define CPU_WIN2_BASE	LOONGSON_ADDRWINCFG(0x10)
+#define CPU_WIN3_BASE	LOONGSON_ADDRWINCFG(0x18)
+
+#define CPU_WIN0_MASK	LOONGSON_ADDRWINCFG(0x20)
+#define CPU_WIN1_MASK	LOONGSON_ADDRWINCFG(0x28)
+#define CPU_WIN2_MASK	LOONGSON_ADDRWINCFG(0x30)
+#define CPU_WIN3_MASK	LOONGSON_ADDRWINCFG(0x38)
+
+#define CPU_WIN0_MMAP	LOONGSON_ADDRWINCFG(0x40)
+#define CPU_WIN1_MMAP	LOONGSON_ADDRWINCFG(0x48)
+#define CPU_WIN2_MMAP	LOONGSON_ADDRWINCFG(0x50)
+#define CPU_WIN3_MMAP	LOONGSON_ADDRWINCFG(0x58)
+
+#define PCIDMA_WIN0_BASE	LOONGSON_ADDRWINCFG(0x60)
+#define PCIDMA_WIN1_BASE	LOONGSON_ADDRWINCFG(0x68)
+#define PCIDMA_WIN2_BASE	LOONGSON_ADDRWINCFG(0x70)
+#define PCIDMA_WIN3_BASE	LOONGSON_ADDRWINCFG(0x78)
+
+#define PCIDMA_WIN0_MASK	LOONGSON_ADDRWINCFG(0x80)
+#define PCIDMA_WIN1_MASK	LOONGSON_ADDRWINCFG(0x88)
+#define PCIDMA_WIN2_MASK	LOONGSON_ADDRWINCFG(0x90)
+#define PCIDMA_WIN3_MASK	LOONGSON_ADDRWINCFG(0x98)
+
+#define PCIDMA_WIN0_MMAP	LOONGSON_ADDRWINCFG(0xa0)
+#define PCIDMA_WIN1_MMAP	LOONGSON_ADDRWINCFG(0xa8)
+#define PCIDMA_WIN2_MMAP	LOONGSON_ADDRWINCFG(0xb0)
+#define PCIDMA_WIN3_MMAP	LOONGSON_ADDRWINCFG(0xb8)
+
+#define ADDRWIN_WIN0	0
+#define ADDRWIN_WIN1	1
+#define ADDRWIN_WIN2	2
+#define ADDRWIN_WIN3	3
+
+#define ADDRWIN_MAP_DST_DDR	0
+#define ADDRWIN_MAP_DST_PCI	1
+#define ADDRWIN_MAP_DST_LIO	1
+
+/*
+ * s: CPU, PCIDMA
+ * d: DDR, PCI, LIO
+ * win: 0, 1, 2, 3
+ * src: map source
+ * dst: map destination
+ * size: ~mask + 1
+ */
+#define LOONGSON_ADDRWIN_CFG(s, d, w, src, dst, size) do {\
+	s##_WIN##w##_BASE = (src); \
+	s##_WIN##w##_MMAP = (dst) | ADDRWIN_MAP_DST_##d; \
+	s##_WIN##w##_MASK = ~(size-1); \
+} while (0)
+
+#define LOONGSON_ADDRWIN_CPUTOPCI(win, src, dst, size) \
+	LOONGSON_ADDRWIN_CFG(CPU, PCI, win, src, dst, size)
+#define LOONGSON_ADDRWIN_CPUTODDR(win, src, dst, size) \
+	LOONGSON_ADDRWIN_CFG(CPU, DDR, win, src, dst, size)
+#define LOONGSON_ADDRWIN_PCITODDR(win, src, dst, size) \
+	LOONGSON_ADDRWIN_CFG(PCIDMA, DDR, win, src, dst, size)
+
+#endif	/* ! CONFIG_CPU_SUPPORTS_ADDRWINCFG */
+
+#endif /* __ASM_MACH_LOONGSON2EF_LOONGSON_H */
diff --git a/arch/mips/include/asm/mach-loongson64/machine.h b/arch/mips/include/asm/mach-loongson2ef/machine.h
index 8ef7ea94a26d..4097267ef186 100644
--- a/arch/mips/include/asm/mach-loongson64/machine.h
+++ b/arch/mips/include/asm/mach-loongson2ef/machine.h
@@ -4,8 +4,8 @@
  * Author: Wu Zhangjin <wuzhangjin@gmail.com>
  */
 
-#ifndef __ASM_MACH_LOONGSON64_MACHINE_H
-#define __ASM_MACH_LOONGSON64_MACHINE_H
+#ifndef __ASM_MACH_LOONGSON2EF_MACHINE_H
+#define __ASM_MACH_LOONGSON2EF_MACHINE_H
 
 #ifdef CONFIG_LEMOTE_FULOONG2E
 
@@ -20,10 +20,4 @@
 
 #endif
 
-#ifdef CONFIG_LOONGSON_MACH3X
-
-#define LOONGSON_MACHTYPE MACH_LOONGSON_GENERIC
-
-#endif /* CONFIG_LOONGSON_MACH3X */
-
-#endif /* __ASM_MACH_LOONGSON64_MACHINE_H */
+#endif /* __ASM_MACH_LOONGSON2EF_MACHINE_H */
diff --git a/arch/mips/include/asm/mach-loongson2ef/mc146818rtc.h b/arch/mips/include/asm/mach-loongson2ef/mc146818rtc.h
new file mode 100644
index 000000000000..00d602629a55
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson2ef/mc146818rtc.h
@@ -0,0 +1,36 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998, 2001, 03, 07 by Ralf Baechle (ralf@linux-mips.org)
+ *
+ * RTC routines for PC style attached Dallas chip.
+ */
+#ifndef __ASM_MACH_LOONGSON2EF_MC146818RTC_H
+#define __ASM_MACH_LOONGSON2EF_MC146818RTC_H
+
+#include <linux/io.h>
+
+#define RTC_PORT(x)	(0x70 + (x))
+#define RTC_IRQ		8
+
+static inline unsigned char CMOS_READ(unsigned long addr)
+{
+	outb_p(addr, RTC_PORT(0));
+	return inb_p(RTC_PORT(1));
+}
+
+static inline void CMOS_WRITE(unsigned char data, unsigned long addr)
+{
+	outb_p(addr, RTC_PORT(0));
+	outb_p(data, RTC_PORT(1));
+}
+
+#define RTC_ALWAYS_BCD	0
+
+#ifndef mc146818_decode_year
+#define mc146818_decode_year(year) ((year) < 70 ? (year) + 2000 : (year) + 1970)
+#endif
+
+#endif /* __ASM_MACH_LOONGSON2EF_MC146818RTC_H */
diff --git a/arch/mips/include/asm/mach-loongson64/mem.h b/arch/mips/include/asm/mach-loongson2ef/mem.h
index ce33c174c04d..d1d759b8974e 100644
--- a/arch/mips/include/asm/mach-loongson64/mem.h
+++ b/arch/mips/include/asm/mach-loongson2ef/mem.h
@@ -4,8 +4,8 @@
  * Author: Wu Zhangjin <wuzhangjin@gmail.com>
  */
 
-#ifndef __ASM_MACH_LOONGSON64_MEM_H
-#define __ASM_MACH_LOONGSON64_MEM_H
+#ifndef __ASM_MACH_LOONGSON2EF_MEM_H
+#define __ASM_MACH_LOONGSON2EF_MEM_H
 
 /*
  * high memory space
@@ -34,4 +34,4 @@
 #define LOONGSON_MMIO_MEM_END	0x80000000
 #endif
 
-#endif /* __ASM_MACH_LOONGSON64_MEM_H */
+#endif /* __ASM_MACH_LOONGSON2EF_MEM_H */
diff --git a/arch/mips/include/asm/mach-loongson2ef/pci.h b/arch/mips/include/asm/mach-loongson2ef/pci.h
new file mode 100644
index 000000000000..5588c5bc5395
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson2ef/pci.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2008 Zhang Le <r0bertz@gentoo.org>
+ * Copyright (c) 2009 Wu Zhangjin <wuzhangjin@gmail.com>
+ */
+
+#ifndef __ASM_MACH_LOONGSON2EF_PCI_H_
+#define __ASM_MACH_LOONGSON2EF_PCI_H_
+
+extern struct pci_ops loongson_pci_ops;
+
+/* this is an offset from mips_io_port_base */
+#define LOONGSON_PCI_IO_START	0x00004000UL
+
+#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG
+
+/*
+ * we use address window2 to map cpu address space to pci space
+ * window2: cpu [1G, 2G] -> pci [1G, 2G]
+ * why not use window 0 & 1? because they are used by cpu when booting.
+ * window0: cpu [0, 256M] -> ddr [0, 256M]
+ * window1: cpu [256M, 512M] -> pci [256M, 512M]
+ */
+
+/* the smallest LOONGSON_CPU_MEM_SRC can be 512M */
+#define LOONGSON_CPU_MEM_SRC	0x40000000ul		/* 1G */
+#define LOONGSON_PCI_MEM_DST	LOONGSON_CPU_MEM_SRC
+
+#define LOONGSON_PCI_MEM_START	LOONGSON_PCI_MEM_DST
+#define LOONGSON_PCI_MEM_END	(0x80000000ul-1)	/* 2G */
+
+#define MMAP_CPUTOPCI_SIZE	(LOONGSON_PCI_MEM_END - \
+					LOONGSON_PCI_MEM_START + 1)
+
+#else	/* loongson2f/32bit & loongson2e */
+
+/* this pci memory space is mapped by pcimap in pci.c */
+#define LOONGSON_PCI_MEM_START	LOONGSON_PCILO1_BASE
+#define LOONGSON_PCI_MEM_END	(LOONGSON_PCILO1_BASE + 0x04000000 * 2)
+
+/* this is an offset from mips_io_port_base */
+#define LOONGSON_PCI_IO_START	0x00004000UL
+
+#endif	/* !CONFIG_CPU_SUPPORTS_ADDRWINCFG */
+
+#endif /* !__ASM_MACH_LOONGSON2EF_PCI_H_ */
diff --git a/arch/mips/include/asm/mach-loongson2ef/spaces.h b/arch/mips/include/asm/mach-loongson2ef/spaces.h
new file mode 100644
index 000000000000..ba4e8e9b618e
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson2ef/spaces.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MACH_LOONGSON2EF_SPACES_H_
+#define __ASM_MACH_LOONGSON2EF_SPACES_H_
+
+#if defined(CONFIG_64BIT)
+#define CAC_BASE        _AC(0x9800000000000000, UL)
+#endif /* CONFIG_64BIT */
+
+#include <asm/mach-generic/spaces.h>
+#endif
diff --git a/arch/mips/include/asm/mach-loongson32/prom.h b/arch/mips/include/asm/mach-loongson32/prom.h
deleted file mode 100644
index cb789f18d790..000000000000
--- a/arch/mips/include/asm/mach-loongson32/prom.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
- */
-
-#ifndef __ASM_MACH_LOONGSON32_PROM_H
-#define __ASM_MACH_LOONGSON32_PROM_H
-
-#include <linux/io.h>
-#include <linux/init.h>
-#include <linux/irq.h>
-
-/* environment arguments from bootloader */
-extern unsigned long memsize, highmemsize;
-
-/* loongson-specific command line, env and memory initialization */
-extern char *prom_getenv(char *name);
-extern void __init prom_init_cmdline(void);
-
-#endif /* __ASM_MACH_LOONGSON32_PROM_H */
diff --git a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h
index 4aca25f2ff06..7dc8d75445a9 100644
--- a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h
@@ -43,11 +43,8 @@
 #define cpu_has_vint		0
 #define cpu_has_vtag_icache	0
 #define cpu_has_watch		1
-
-#ifdef CONFIG_CPU_LOONGSON3
 #define cpu_has_wsbh		1
 #define cpu_has_ic_fills_f_dc	1
 #define cpu_hwrena_impl_bits	0xc0000000
-#endif
 
 #endif /* __ASM_MACH_LOONGSON64_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/mach-loongson64/irq.h b/arch/mips/include/asm/mach-loongson64/irq.h
index be9f727a9328..73a89913dc38 100644
--- a/arch/mips/include/asm/mach-loongson64/irq.h
+++ b/arch/mips/include/asm/mach-loongson64/irq.h
@@ -4,8 +4,6 @@
 
 #include <boot_param.h>
 
-#ifdef CONFIG_CPU_LOONGSON3
-
 /* cpu core interrupt numbers */
 #define MIPS_CPU_IRQ_BASE 56
 
@@ -35,8 +33,6 @@
 
 #define LOONGSON_INT_COREx_INTy(x, y)	(1<<(x) | 1<<(y+4))	/* route to int y of core x */
 
-#endif
-
 extern void fixup_irqs(void);
 extern void loongson3_ipi_interrupt(struct pt_regs *regs);
 
diff --git a/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h b/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h
index b5e288a12dfe..87a5bfbf8cfe 100644
--- a/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h
@@ -17,7 +17,6 @@
  * Override macros used in arch/mips/kernel/head.S.
  */
 	.macro	kernel_entry_setup
-#ifdef CONFIG_CPU_LOONGSON3
 	.set	push
 	.set	mips64
 	/* Set LPA on LOONGSON3 config3 */
@@ -30,23 +29,29 @@
 	mtc0	t0, CP0_PAGEGRAIN
 	/* Enable STFill Buffer */
 	mfc0	t0, CP0_PRID
+	/* Loongson-3A R4+ */
+	andi	t1, t0, PRID_IMP_MASK
+	li	t2, PRID_IMP_LOONGSON_64G
+	beq     t1, t2, 1f
+	nop
+	/* Loongson-3A R2/R3 */
 	andi	t0, (PRID_IMP_MASK | PRID_REV_MASK)
-	slti	t0, (PRID_IMP_LOONGSON_64 | PRID_REV_LOONGSON3A_R2_0)
-	bnez	t0, 1f
+	slti	t0, (PRID_IMP_LOONGSON_64C | PRID_REV_LOONGSON3A_R2_0)
+	bnez	t0, 2f
+	nop
+1:
 	mfc0	t0, CP0_CONFIG6
 	or	t0, 0x100
 	mtc0	t0, CP0_CONFIG6
-1:
+2:
 	_ehb
 	.set	pop
-#endif
 	.endm
 
 /*
  * Do SMP slave processor setup.
  */
 	.macro	smp_slave_setup
-#ifdef CONFIG_CPU_LOONGSON3
 	.set	push
 	.set	mips64
 	/* Set LPA on LOONGSON3 config3 */
@@ -59,16 +64,23 @@
 	mtc0	t0, CP0_PAGEGRAIN
 	/* Enable STFill Buffer */
 	mfc0	t0, CP0_PRID
+	/* Loongson-3A R4+ */
+	andi	t1, t0, PRID_IMP_MASK
+	li	t2, PRID_IMP_LOONGSON_64G
+	beq     t1, t2, 1f
+	nop
+	/* Loongson-3A R2/R3 */
 	andi	t0, (PRID_IMP_MASK | PRID_REV_MASK)
-	slti	t0, (PRID_IMP_LOONGSON_64 | PRID_REV_LOONGSON3A_R2_0)
-	bnez	t0, 1f
+	slti	t0, (PRID_IMP_LOONGSON_64C | PRID_REV_LOONGSON3A_R2_0)
+	bnez	t0, 2f
+	nop
+1:
 	mfc0	t0, CP0_CONFIG6
 	or	t0, 0x100
 	mtc0	t0, CP0_CONFIG6
-1:
+2:
 	_ehb
 	.set	pop
-#endif
 	.endm
 
 #endif /* __ASM_MACH_LOONGSON64_KERNEL_ENTRY_H */
diff --git a/arch/mips/include/asm/mach-loongson64/loongson.h b/arch/mips/include/asm/mach-loongson64/loongson.h
index 694a58574ec0..a8fce112a9b0 100644
--- a/arch/mips/include/asm/mach-loongson64/loongson.h
+++ b/arch/mips/include/asm/mach-loongson64/loongson.h
@@ -12,8 +12,6 @@
 #include <linux/irq.h>
 #include <boot_param.h>
 
-/* loongson internal northbridge initialization */
-extern void bonito_irq_init(void);
 
 /* machine-specific reboot/halt operation */
 extern void mach_prepare_reboot(void);
@@ -26,25 +24,9 @@ extern const struct plat_smp_ops loongson3_smp_ops;
 
 /* loongson-specific command line, env and memory initialization */
 extern void __init prom_init_memory(void);
-extern void __init prom_init_cmdline(void);
-extern void __init prom_init_machtype(void);
 extern void __init prom_init_env(void);
-#ifdef CONFIG_LOONGSON_UART_BASE
-extern unsigned long _loongson_uart_base[], loongson_uart_base[];
-extern void prom_init_loongson_uart_base(void);
-#endif
-
-static inline void prom_init_uart_base(void)
-{
-#ifdef CONFIG_LOONGSON_UART_BASE
-	prom_init_loongson_uart_base();
-#endif
-}
 
 /* irq operation functions */
-extern void bonito_irqdispatch(void);
-extern void __init bonito_irq_init(void);
-extern void __init mach_init_irq(void);
 extern void mach_irq_dispatch(unsigned int pending);
 extern int mach_i8259_irq(void);
 
@@ -64,17 +46,6 @@ extern int mach_i8259_irq(void);
 #define LOONGSON3_REG32(base, x) \
 	(*(volatile u32 *)((char *)TO_UNCAC(base) + (x)))
 
-#define LOONGSON_IRQ_BASE	32
-#define LOONGSON2_PERFCNT_IRQ	(MIPS_CPU_IRQ_BASE + 6) /* cpu perf counter */
-
-#include <linux/interrupt.h>
-static inline void do_perfcnt_IRQ(void)
-{
-#if IS_ENABLED(CONFIG_OPROFILE)
-	do_IRQ(LOONGSON2_PERFCNT_IRQ);
-#endif
-}
-
 #define LOONGSON_FLASH_BASE	0x1c000000
 #define LOONGSON_FLASH_SIZE	0x02000000	/* 32M */
 #define LOONGSON_FLASH_TOP	(LOONGSON_FLASH_BASE+LOONGSON_FLASH_SIZE-1)
@@ -109,11 +80,7 @@ static inline void do_perfcnt_IRQ(void)
 #define LOONGSON_PCICFG_SIZE	0x00000800	/* 2K */
 #define LOONGSON_PCICFG_TOP	(LOONGSON_PCICFG_BASE+LOONGSON_PCICFG_SIZE-1)
 
-#ifdef CONFIG_CPU_LOONGSON3
 #define LOONGSON_PCIIO_BASE	loongson_sysconf.pci_io_base
-#else
-#define LOONGSON_PCIIO_BASE	0x1fd00000
-#endif
 
 #define LOONGSON_PCIIO_SIZE	0x00100000	/* 1M */
 #define LOONGSON_PCIIO_TOP	(LOONGSON_PCIIO_BASE+LOONGSON_PCIIO_SIZE-1)
@@ -270,86 +237,4 @@ extern u64 loongson_freqctrl[MAX_PACKAGES];
 #define LOONGSON_PCIMAP_WIN(WIN, ADDR)	\
 	((((ADDR)>>26) & LOONGSON_PCIMAP_PCIMAP_LO0) << ((WIN)*6))
 
-#ifdef CONFIG_CPU_SUPPORTS_CPUFREQ
-#include <linux/cpufreq.h>
-extern struct cpufreq_frequency_table loongson2_clockmod_table[];
-#endif
-
-/*
- * address windows configuration module
- *
- * loongson2e do not have this module
- */
-#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG
-
-/* address window config module base address */
-#define LOONGSON_ADDRWINCFG_BASE		0x3ff00000ul
-#define LOONGSON_ADDRWINCFG_SIZE		0x180
-
-extern unsigned long _loongson_addrwincfg_base;
-#define LOONGSON_ADDRWINCFG(offset) \
-	(*(volatile u64 *)(_loongson_addrwincfg_base + (offset)))
-
-#define CPU_WIN0_BASE	LOONGSON_ADDRWINCFG(0x00)
-#define CPU_WIN1_BASE	LOONGSON_ADDRWINCFG(0x08)
-#define CPU_WIN2_BASE	LOONGSON_ADDRWINCFG(0x10)
-#define CPU_WIN3_BASE	LOONGSON_ADDRWINCFG(0x18)
-
-#define CPU_WIN0_MASK	LOONGSON_ADDRWINCFG(0x20)
-#define CPU_WIN1_MASK	LOONGSON_ADDRWINCFG(0x28)
-#define CPU_WIN2_MASK	LOONGSON_ADDRWINCFG(0x30)
-#define CPU_WIN3_MASK	LOONGSON_ADDRWINCFG(0x38)
-
-#define CPU_WIN0_MMAP	LOONGSON_ADDRWINCFG(0x40)
-#define CPU_WIN1_MMAP	LOONGSON_ADDRWINCFG(0x48)
-#define CPU_WIN2_MMAP	LOONGSON_ADDRWINCFG(0x50)
-#define CPU_WIN3_MMAP	LOONGSON_ADDRWINCFG(0x58)
-
-#define PCIDMA_WIN0_BASE	LOONGSON_ADDRWINCFG(0x60)
-#define PCIDMA_WIN1_BASE	LOONGSON_ADDRWINCFG(0x68)
-#define PCIDMA_WIN2_BASE	LOONGSON_ADDRWINCFG(0x70)
-#define PCIDMA_WIN3_BASE	LOONGSON_ADDRWINCFG(0x78)
-
-#define PCIDMA_WIN0_MASK	LOONGSON_ADDRWINCFG(0x80)
-#define PCIDMA_WIN1_MASK	LOONGSON_ADDRWINCFG(0x88)
-#define PCIDMA_WIN2_MASK	LOONGSON_ADDRWINCFG(0x90)
-#define PCIDMA_WIN3_MASK	LOONGSON_ADDRWINCFG(0x98)
-
-#define PCIDMA_WIN0_MMAP	LOONGSON_ADDRWINCFG(0xa0)
-#define PCIDMA_WIN1_MMAP	LOONGSON_ADDRWINCFG(0xa8)
-#define PCIDMA_WIN2_MMAP	LOONGSON_ADDRWINCFG(0xb0)
-#define PCIDMA_WIN3_MMAP	LOONGSON_ADDRWINCFG(0xb8)
-
-#define ADDRWIN_WIN0	0
-#define ADDRWIN_WIN1	1
-#define ADDRWIN_WIN2	2
-#define ADDRWIN_WIN3	3
-
-#define ADDRWIN_MAP_DST_DDR	0
-#define ADDRWIN_MAP_DST_PCI	1
-#define ADDRWIN_MAP_DST_LIO	1
-
-/*
- * s: CPU, PCIDMA
- * d: DDR, PCI, LIO
- * win: 0, 1, 2, 3
- * src: map source
- * dst: map destination
- * size: ~mask + 1
- */
-#define LOONGSON_ADDRWIN_CFG(s, d, w, src, dst, size) do {\
-	s##_WIN##w##_BASE = (src); \
-	s##_WIN##w##_MMAP = (dst) | ADDRWIN_MAP_DST_##d; \
-	s##_WIN##w##_MASK = ~(size-1); \
-} while (0)
-
-#define LOONGSON_ADDRWIN_CPUTOPCI(win, src, dst, size) \
-	LOONGSON_ADDRWIN_CFG(CPU, PCI, win, src, dst, size)
-#define LOONGSON_ADDRWIN_CPUTODDR(win, src, dst, size) \
-	LOONGSON_ADDRWIN_CFG(CPU, DDR, win, src, dst, size)
-#define LOONGSON_ADDRWIN_PCITODDR(win, src, dst, size) \
-	LOONGSON_ADDRWIN_CFG(PCIDMA, DDR, win, src, dst, size)
-
-#endif	/* ! CONFIG_CPU_SUPPORTS_ADDRWINCFG */
-
 #endif /* __ASM_MACH_LOONGSON64_LOONGSON_H */
diff --git a/arch/mips/include/asm/mach-loongson64/loongson_regs.h b/arch/mips/include/asm/mach-loongson64/loongson_regs.h
new file mode 100644
index 000000000000..363a47a5d26e
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson64/loongson_regs.h
@@ -0,0 +1,227 @@
+/*
+ * Read/Write Loongson Extension Registers
+ */
+
+#ifndef _LOONGSON_REGS_H_
+#define _LOONGSON_REGS_H_
+
+#include <linux/types.h>
+#include <linux/bits.h>
+
+#include <asm/mipsregs.h>
+#include <asm/cpu.h>
+
+static inline bool cpu_has_cfg(void)
+{
+	return ((read_c0_prid() & PRID_IMP_MASK) == PRID_IMP_LOONGSON_64G);
+}
+
+static inline u32 read_cpucfg(u32 reg)
+{
+	u32 __res;
+
+	__asm__ __volatile__(
+		"parse_r __res,%0\n\t"
+		"parse_r reg,%1\n\t"
+		".insn \n\t"
+		".word (0xc8080118 | (reg << 21) | (__res << 11))\n\t"
+		:"=r"(__res)
+		:"r"(reg)
+		:
+		);
+	return __res;
+}
+
+/* Bit Domains for CFG registers */
+#define LOONGSON_CFG0	0x0
+#define LOONGSON_CFG0_PRID GENMASK(31, 0)
+
+#define LOONGSON_CFG1 0x1
+#define LOONGSON_CFG1_FP	BIT(0)
+#define LOONGSON_CFG1_FPREV	GENMASK(3, 1)
+#define LOONGSON_CFG1_MMI	BIT(4)
+#define LOONGSON_CFG1_MSA1	BIT(5)
+#define LOONGSON_CFG1_MSA2	BIT(6)
+#define LOONGSON_CFG1_CGP	BIT(7)
+#define LOONGSON_CFG1_WRP	BIT(8)
+#define LOONGSON_CFG1_LSX1	BIT(9)
+#define LOONGSON_CFG1_LSX2	BIT(10)
+#define LOONGSON_CFG1_LASX	BIT(11)
+#define LOONGSON_CFG1_R6FXP	BIT(12)
+#define LOONGSON_CFG1_R6CRCP	BIT(13)
+#define LOONGSON_CFG1_R6FPP	BIT(14)
+#define LOONGSON_CFG1_CNT64	BIT(15)
+#define LOONGSON_CFG1_LSLDR0	BIT(16)
+#define LOONGSON_CFG1_LSPREF	BIT(17)
+#define LOONGSON_CFG1_LSPREFX	BIT(18)
+#define LOONGSON_CFG1_LSSYNCI	BIT(19)
+#define LOONGSON_CFG1_LSUCA	BIT(20)
+#define LOONGSON_CFG1_LLSYNC	BIT(21)
+#define LOONGSON_CFG1_TGTSYNC	BIT(22)
+#define LOONGSON_CFG1_LLEXC	BIT(23)
+#define LOONGSON_CFG1_SCRAND	BIT(24)
+#define LOONGSON_CFG1_MUALP	BIT(25)
+#define LOONGSON_CFG1_KMUALEN	BIT(26)
+#define LOONGSON_CFG1_ITLBT	BIT(27)
+#define LOONGSON_CFG1_LSUPERF	BIT(28)
+#define LOONGSON_CFG1_SFBP	BIT(29)
+#define LOONGSON_CFG1_CDMAP	BIT(30)
+
+#define LOONGSON_CFG2 0x2
+#define LOONGSON_CFG2_LEXT1	BIT(0)
+#define LOONGSON_CFG2_LEXT2	BIT(1)
+#define LOONGSON_CFG2_LEXT3	BIT(2)
+#define LOONGSON_CFG2_LSPW	BIT(3)
+#define LOONGSON_CFG2_LBT1	BIT(4)
+#define LOONGSON_CFG2_LBT2	BIT(5)
+#define LOONGSON_CFG2_LBT3	BIT(6)
+#define LOONGSON_CFG2_LBTMMU	BIT(7)
+#define LOONGSON_CFG2_LPMP	BIT(8)
+#define LOONGSON_CFG2_LPMPREV	GENMASK(11, 9)
+#define LOONGSON_CFG2_LAMO	BIT(12)
+#define LOONGSON_CFG2_LPIXU	BIT(13)
+#define LOONGSON_CFG2_LPIXUN	BIT(14)
+#define LOONGSON_CFG2_LZVP	BIT(15)
+#define LOONGSON_CFG2_LZVREV	GENMASK(18, 16)
+#define LOONGSON_CFG2_LGFTP	BIT(19)
+#define LOONGSON_CFG2_LGFTPREV	GENMASK(22, 20)
+#define LOONGSON_CFG2_LLFTP	BIT(23)
+#define LOONGSON_CFG2_LLFTPREV	GENMASK(26, 24)
+#define LOONGSON_CFG2_LCSRP	BIT(27)
+#define LOONGSON_CFG2_LDISBLIKELY	BIT(28)
+
+#define LOONGSON_CFG3 0x3
+#define LOONGSON_CFG3_LCAMP	BIT(0)
+#define LOONGSON_CFG3_LCAMREV	GENMASK(3, 1)
+#define LOONGSON_CFG3_LCAMNUM	GENMASK(11, 4)
+#define LOONGSON_CFG3_LCAMKW	GENMASK(19, 12)
+#define LOONGSON_CFG3_LCAMVW	GENMASK(27, 20)
+
+#define LOONGSON_CFG4 0x4
+#define LOONGSON_CFG4_CCFREQ	GENMASK(31, 0)
+
+#define LOONGSON_CFG5 0x5
+#define LOONGSON_CFG5_CFM	GENMASK(15, 0)
+#define LOONGSON_CFG5_CFD	GENMASK(31, 16)
+
+#define LOONGSON_CFG6 0x6
+
+#define LOONGSON_CFG7 0x7
+#define LOONGSON_CFG7_GCCAEQRP	BIT(0)
+#define LOONGSON_CFG7_UCAWINP	BIT(1)
+
+static inline bool cpu_has_csr(void)
+{
+	if (cpu_has_cfg())
+		return (read_cpucfg(LOONGSON_CFG2) & LOONGSON_CFG2_LCSRP);
+
+	return false;
+}
+
+static inline u32 csr_readl(u32 reg)
+{
+	u32 __res;
+
+	/* RDCSR reg, val */
+	__asm__ __volatile__(
+		"parse_r __res,%0\n\t"
+		"parse_r reg,%1\n\t"
+		".insn \n\t"
+		".word (0xc8000118 | (reg << 21) | (__res << 11))\n\t"
+		:"=r"(__res)
+		:"r"(reg)
+		:
+		);
+	return __res;
+}
+
+static inline u64 csr_readq(u32 reg)
+{
+	u64 __res;
+
+	/* DWRCSR reg, val */
+	__asm__ __volatile__(
+		"parse_r __res,%0\n\t"
+		"parse_r reg,%1\n\t"
+		".insn \n\t"
+		".word (0xc8020118 | (reg << 21) | (__res << 11))\n\t"
+		:"=r"(__res)
+		:"r"(reg)
+		:
+		);
+	return __res;
+}
+
+static inline void csr_writel(u32 val, u32 reg)
+{
+	/* WRCSR reg, val */
+	__asm__ __volatile__(
+		"parse_r reg,%0\n\t"
+		"parse_r val,%1\n\t"
+		".insn \n\t"
+		".word (0xc8010118 | (reg << 21) | (val << 11))\n\t"
+		:
+		:"r"(reg),"r"(val)
+		:
+		);
+}
+
+static inline void csr_writeq(u64 val, u32 reg)
+{
+	/* DWRCSR reg, val */
+	__asm__ __volatile__(
+		"parse_r reg,%0\n\t"
+		"parse_r val,%1\n\t"
+		".insn \n\t"
+		".word (0xc8030118 | (reg << 21) | (val << 11))\n\t"
+		:
+		:"r"(reg),"r"(val)
+		:
+		);
+}
+
+/* Public CSR Register can also be accessed with regular addresses */
+#define CSR_PUBLIC_MMIO_BASE 0x1fe00000
+
+#define MMIO_CSR(x)		(void *)TO_UNCAC(CSR_PUBLIC_MMIO_BASE + x)
+
+#define LOONGSON_CSR_FEATURES	0x8
+#define LOONGSON_CSRF_TEMP	BIT(0)
+#define LOONGSON_CSRF_NODECNT	BIT(1)
+#define LOONGSON_CSRF_MSI	BIT(2)
+#define LOONGSON_CSRF_EXTIOI	BIT(3)
+#define LOONGSON_CSRF_IPI	BIT(4)
+#define LOONGSON_CSRF_FREQ	BIT(5)
+
+#define LOONGSON_CSR_VENDOR	0x10 /* Vendor name string, should be "Loongson" */
+#define LOONGSON_CSR_CPUNAME	0x20 /* Processor name string */
+#define LOONGSON_CSR_NODECNT	0x408
+#define LOONGSON_CSR_CPUTEMP	0x428
+
+/* PerCore CSR, only accessable by local cores */
+#define LOONGSON_CSR_IPI_STATUS	0x1000
+#define LOONGSON_CSR_IPI_EN	0x1004
+#define LOONGSON_CSR_IPI_SET	0x1008
+#define LOONGSON_CSR_IPI_CLEAR	0x100c
+#define LOONGSON_CSR_IPI_SEND	0x1040
+#define CSR_IPI_SEND_IP_SHIFT	0
+#define CSR_IPI_SEND_CPU_SHIFT	16
+#define CSR_IPI_SEND_BLOCK	BIT(31)
+
+static inline u64 drdtime(void)
+{
+	int rID = 0;
+	u64 val = 0;
+
+	__asm__ __volatile__(
+		"parse_r rID,%0\n\t"
+		"parse_r val,%1\n\t"
+		".insn \n\t"
+		".word (0xc8090118 | (rID << 21) | (val << 11))\n\t"
+		:"=r"(rID),"=r"(val)
+		:
+		);
+	return val;
+}
+
+#endif
diff --git a/arch/mips/include/asm/mach-loongson64/mmzone.h b/arch/mips/include/asm/mach-loongson64/mmzone.h
index 62073d60739f..3a25dbd3b3e9 100644
--- a/arch/mips/include/asm/mach-loongson64/mmzone.h
+++ b/arch/mips/include/asm/mach-loongson64/mmzone.h
@@ -6,8 +6,8 @@
  *          Huacai Chen, chenhc@lemote.com
  *          Xiaofu Meng, Shuangshuang Zhang
  */
-#ifndef _ASM_MACH_MMZONE_H
-#define _ASM_MACH_MMZONE_H
+#ifndef _ASM_MACH_LOONGSON64_MMZONE_H
+#define _ASM_MACH_LOONGSON64_MMZONE_H
 
 #include <boot_param.h>
 #define NODE_ADDRSPACE_SHIFT 44
@@ -19,30 +19,9 @@
 #define pa_to_nid(addr)  (((addr) & 0xf00000000000) >> NODE_ADDRSPACE_SHIFT)
 #define nid_to_addrbase(nid) ((nid) << NODE_ADDRSPACE_SHIFT)
 
-#define LEVELS_PER_SLICE 128
+extern struct pglist_data *__node_data[];
 
-struct slice_data {
-	unsigned long irq_enable_mask[2];
-	int level_to_irq[LEVELS_PER_SLICE];
-};
-
-struct hub_data {
-	cpumask_t	h_cpus;
-	unsigned long slice_map;
-	unsigned long irq_alloc_mask[2];
-	struct slice_data slice[2];
-};
-
-struct node_data {
-	struct pglist_data pglist;
-	struct hub_data hub;
-	cpumask_t cpumask;
-};
-
-extern struct node_data *__node_data[];
-
-#define NODE_DATA(n)		(&__node_data[(n)]->pglist)
-#define hub_data(n)		(&__node_data[(n)]->hub)
+#define NODE_DATA(n)		(__node_data[n])
 
 extern void setup_zero_pages(void);
 extern void __init prom_init_numa_memory(void);
diff --git a/arch/mips/include/asm/mach-loongson64/pci.h b/arch/mips/include/asm/mach-loongson64/pci.h
index 97f807fb2117..8b59d64a23e8 100644
--- a/arch/mips/include/asm/mach-loongson64/pci.h
+++ b/arch/mips/include/asm/mach-loongson64/pci.h
@@ -12,39 +12,8 @@ extern struct pci_ops loongson_pci_ops;
 /* this is an offset from mips_io_port_base */
 #define LOONGSON_PCI_IO_START	0x00004000UL
 
-#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG
-
-/*
- * we use address window2 to map cpu address space to pci space
- * window2: cpu [1G, 2G] -> pci [1G, 2G]
- * why not use window 0 & 1? because they are used by cpu when booting.
- * window0: cpu [0, 256M] -> ddr [0, 256M]
- * window1: cpu [256M, 512M] -> pci [256M, 512M]
- */
-
-/* the smallest LOONGSON_CPU_MEM_SRC can be 512M */
-#define LOONGSON_CPU_MEM_SRC	0x40000000ul		/* 1G */
-#define LOONGSON_PCI_MEM_DST	LOONGSON_CPU_MEM_SRC
-
-#define LOONGSON_PCI_MEM_START	LOONGSON_PCI_MEM_DST
-#define LOONGSON_PCI_MEM_END	(0x80000000ul-1)	/* 2G */
-
-#define MMAP_CPUTOPCI_SIZE	(LOONGSON_PCI_MEM_END - \
-					LOONGSON_PCI_MEM_START + 1)
-
-#else	/* loongson2f/32bit & loongson2e */
-
-/* this pci memory space is mapped by pcimap in pci.c */
-#ifdef CONFIG_CPU_LOONGSON3
 #define LOONGSON_PCI_MEM_START	0x40000000UL
 #define LOONGSON_PCI_MEM_END	0x7effffffUL
-#else
-#define LOONGSON_PCI_MEM_START	LOONGSON_PCILO1_BASE
-#define LOONGSON_PCI_MEM_END	(LOONGSON_PCILO1_BASE + 0x04000000 * 2)
-#endif
-/* this is an offset from mips_io_port_base */
-#define LOONGSON_PCI_IO_START	0x00004000UL
 
-#endif	/* !CONFIG_CPU_SUPPORTS_ADDRWINCFG */
 
 #endif /* !__ASM_MACH_LOONGSON64_PCI_H_ */
diff --git a/arch/mips/include/asm/mach-loongson64/topology.h b/arch/mips/include/asm/mach-loongson64/topology.h
index 7ff819ab308a..3414a1fd1783 100644
--- a/arch/mips/include/asm/mach-loongson64/topology.h
+++ b/arch/mips/include/asm/mach-loongson64/topology.h
@@ -5,7 +5,9 @@
 #ifdef CONFIG_NUMA
 
 #define cpu_to_node(cpu)	(cpu_logical_map(cpu) >> 2)
-#define cpumask_of_node(node)	(&__node_data[(node)]->cpumask)
+
+extern cpumask_t __node_cpumask[];
+#define cpumask_of_node(node)	(&__node_cpumask[node])
 
 struct pci_bus;
 extern int pcibus_to_node(struct pci_bus *);
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index bdbdc19a2b8f..0d5a30988697 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -689,6 +689,9 @@
 #define MIPS_CONF7_IAR		(_ULCAST_(1) << 10)
 #define MIPS_CONF7_AR		(_ULCAST_(1) << 16)
 
+/* Ingenic HPTLB off bits */
+#define XBURST_PAGECTRL_HPTLB_DIS 0xa9000000
+
 /* Ingenic Config7 bits */
 #define MIPS_CONF7_BTB_LOOP_EN	(_ULCAST_(1) << 4)
 
@@ -1971,6 +1974,9 @@ do {									\
 #define read_c0_brcm_sleepcount()	__read_32bit_c0_register($22, 7)
 #define write_c0_brcm_sleepcount(val)	__write_32bit_c0_register($22, 7, val)
 
+/* Ingenic page ctrl register */
+#define write_c0_page_ctrl(val)	__write_32bit_c0_register($5, 4, val)
+
 /*
  * Macros to access the guest system control coprocessor
  */
diff --git a/arch/mips/include/asm/module.h b/arch/mips/include/asm/module.h
index ed70994fbbec..9846047b3d3d 100644
--- a/arch/mips/include/asm/module.h
+++ b/arch/mips/include/asm/module.h
@@ -119,12 +119,12 @@ search_module_dbetables(unsigned long addr)
 #define MODULE_PROC_FAMILY "RM7000 "
 #elif defined CONFIG_CPU_SB1
 #define MODULE_PROC_FAMILY "SB1 "
-#elif defined CONFIG_CPU_LOONGSON1
-#define MODULE_PROC_FAMILY "LOONGSON1 "
-#elif defined CONFIG_CPU_LOONGSON2
-#define MODULE_PROC_FAMILY "LOONGSON2 "
-#elif defined CONFIG_CPU_LOONGSON3
-#define MODULE_PROC_FAMILY "LOONGSON3 "
+#elif defined CONFIG_CPU_LOONGSON32
+#define MODULE_PROC_FAMILY "LOONGSON32 "
+#elif defined CONFIG_CPU_LOONGSON2EF
+#define MODULE_PROC_FAMILY "LOONGSON2EF "
+#elif defined CONFIG_CPU_LOONGSON64
+#define MODULE_PROC_FAMILY "LOONGSON64 "
 #elif defined CONFIG_CPU_CAVIUM_OCTEON
 #define MODULE_PROC_FAMILY "OCTEON "
 #elif defined CONFIG_CPU_XLR
diff --git a/arch/mips/include/asm/pci/bridge.h b/arch/mips/include/asm/pci/bridge.h
index a92cd30b48c9..3bc630ff9ad4 100644
--- a/arch/mips/include/asm/pci/bridge.h
+++ b/arch/mips/include/asm/pci/bridge.h
@@ -807,6 +807,7 @@ struct bridge_controller {
 	unsigned long		intr_addr;
 	struct irq_domain	*domain;
 	unsigned int		pci_int[8];
+	u32			ioc3_sid[8];
 	nasid_t			nasid;
 };
 
diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h
index 166842337eb2..fa77cb71f303 100644
--- a/arch/mips/include/asm/pgalloc.h
+++ b/arch/mips/include/asm/pgalloc.h
@@ -96,9 +96,9 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 	free_pages((unsigned long)pud, PUD_ORDER);
 }
 
-static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
+static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud)
 {
-	set_pgd(pgd, __pgd((unsigned long)pud));
+	set_p4d(p4d, __p4d((unsigned long)pud));
 }
 
 #define __pud_free_tlb(tlb, x, addr)	pud_free((tlb)->mm, x)
diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h
index ba967148b016..1945c8970141 100644
--- a/arch/mips/include/asm/pgtable-32.h
+++ b/arch/mips/include/asm/pgtable-32.h
@@ -16,7 +16,6 @@
 #include <asm/cachectl.h>
 #include <asm/fixmap.h>
 
-#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #ifdef CONFIG_HIGHMEM
@@ -196,14 +195,11 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
 
 #define pte_page(x)		pfn_to_page(pte_pfn(x))
 
-#define __pgd_offset(address)	pgd_index(address)
-#define __pud_offset(address)	(((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
-#define __pmd_offset(address)	(((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
-
 /* to find an entry in a kernel page-table-directory */
 #define pgd_offset_k(address) pgd_offset(&init_mm, address)
 
 #define pgd_index(address)	(((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
+#define pud_index(address)	(((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
 #define pmd_index(address)	(((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
 
 /* to find an entry in a page-table-directory */
diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h
index 93a9dce31f25..f92716cfa4f4 100644
--- a/arch/mips/include/asm/pgtable-64.h
+++ b/arch/mips/include/asm/pgtable-64.h
@@ -17,11 +17,12 @@
 #include <asm/cachectl.h>
 #include <asm/fixmap.h>
 
-#define __ARCH_USE_5LEVEL_HACK
-#if defined(CONFIG_PAGE_SIZE_64KB) && !defined(CONFIG_MIPS_VA_BITS_48)
+#if CONFIG_PGTABLE_LEVELS == 2
 #include <asm-generic/pgtable-nopmd.h>
-#elif !(defined(CONFIG_PAGE_SIZE_4KB) && defined(CONFIG_MIPS_VA_BITS_48))
+#elif CONFIG_PGTABLE_LEVELS == 3
 #include <asm-generic/pgtable-nopud.h>
+#else
+#include <asm-generic/pgtable-nop4d.h>
 #endif
 
 /*
@@ -186,44 +187,49 @@ extern pud_t invalid_pud_table[PTRS_PER_PUD];
 /*
  * Empty pgd entries point to the invalid_pud_table.
  */
-static inline int pgd_none(pgd_t pgd)
+static inline int p4d_none(p4d_t p4d)
 {
-	return pgd_val(pgd) == (unsigned long)invalid_pud_table;
+	return p4d_val(p4d) == (unsigned long)invalid_pud_table;
 }
 
-static inline int pgd_bad(pgd_t pgd)
+static inline int p4d_bad(p4d_t p4d)
 {
-	if (unlikely(pgd_val(pgd) & ~PAGE_MASK))
+	if (unlikely(p4d_val(p4d) & ~PAGE_MASK))
 		return 1;
 
 	return 0;
 }
 
-static inline int pgd_present(pgd_t pgd)
+static inline int p4d_present(p4d_t p4d)
 {
-	return pgd_val(pgd) != (unsigned long)invalid_pud_table;
+	return p4d_val(p4d) != (unsigned long)invalid_pud_table;
 }
 
-static inline void pgd_clear(pgd_t *pgdp)
+static inline void p4d_clear(p4d_t *p4dp)
 {
-	pgd_val(*pgdp) = (unsigned long)invalid_pud_table;
+	p4d_val(*p4dp) = (unsigned long)invalid_pud_table;
 }
 
 #define pud_index(address)	(((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
 
-static inline unsigned long pgd_page_vaddr(pgd_t pgd)
+static inline unsigned long p4d_page_vaddr(p4d_t p4d)
 {
-	return pgd_val(pgd);
+	return p4d_val(p4d);
 }
 
-static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
+#define p4d_phys(p4d)		virt_to_phys((void *)p4d_val(p4d))
+#define p4d_page(p4d)		(pfn_to_page(p4d_phys(p4d) >> PAGE_SHIFT))
+
+#define p4d_index(address)	(((address) >> P4D_SHIFT) & (PTRS_PER_P4D - 1))
+
+static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
 {
-	return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(address);
+	return (pud_t *)p4d_page_vaddr(*p4d) + pud_index(address);
 }
 
-static inline void set_pgd(pgd_t *pgd, pgd_t pgdval)
+static inline void set_p4d(p4d_t *p4d, p4d_t p4dval)
 {
-	*pgd = pgdval;
+	*p4d = p4dval;
 }
 
 #endif
@@ -314,10 +320,6 @@ static inline void pud_clear(pud_t *pudp)
 #define pfn_pmd(pfn, prot)	__pmd(((pfn) << _PFN_SHIFT) | pgprot_val(prot))
 #endif
 
-#define __pgd_offset(address)	pgd_index(address)
-#define __pud_offset(address)	(((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
-#define __pmd_offset(address)	pmd_index(address)
-
 /* to find an entry in a kernel page-table-directory */
 #define pgd_offset_k(address) pgd_offset(&init_mm, address)
 
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index f85bd5b15f51..91b89aab1787 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -644,17 +644,6 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 #include <asm-generic/pgtable.h>
 
 /*
- * uncached accelerated TLB map for video memory access
- */
-#ifdef CONFIG_CPU_SUPPORTS_UNCACHED_ACCELERATED
-#define __HAVE_PHYS_MEM_ACCESS_PROT
-
-struct file;
-pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-		unsigned long size, pgprot_t vma_prot);
-#endif
-
-/*
  * We provide our own get_unmapped area to cope with the virtual aliasing
  * constraints placed on us by the cache architecture.
  */
diff --git a/arch/mips/include/asm/pmon.h b/arch/mips/include/asm/pmon.h
deleted file mode 100644
index 6ad519189ce2..000000000000
--- a/arch/mips/include/asm/pmon.h
+++ /dev/null
@@ -1,46 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2004 by Ralf Baechle
- *
- * The cpustart method is a PMC-Sierra's function to start the secondary CPU.
- * Stock PMON 2000 has the smpfork, semlock and semunlock methods instead.
- */
-#ifndef _ASM_PMON_H
-#define _ASM_PMON_H
-
-struct callvectors {
-	int	(*open) (char*, int, int);
-	int	(*close) (int);
-	int	(*read) (int, void*, int);
-	int	(*write) (int, void*, int);
-	off_t	(*lseek) (int, off_t, int);
-	int	(*printf) (const char*, ...);
-	void	(*cacheflush) (void);
-	char*	(*gets) (char*);
-	union {
-		int	(*smpfork) (unsigned long cp, char *sp);
-		int	(*cpustart) (long, void (*)(void), void *, long);
-	} _s;
-	int	(*semlock) (int sem);
-	void	(*semunlock) (int sem);
-};
-
-extern struct callvectors *debug_vectors;
-
-#define pmon_open(name, flags, mode)	debug_vectors->open(name, flage, mode)
-#define pmon_close(fd)			debug_vectors->close(fd)
-#define pmon_read(fd, buf, count)	debug_vectors->read(fd, buf, count)
-#define pmon_write(fd, buf, count)	debug_vectors->write(fd, buf, count)
-#define pmon_lseek(fd, off, whence)	debug_vectors->lseek(fd, off, whence)
-#define pmon_printf(fmt...)		debug_vectors->printf(fmt)
-#define pmon_cacheflush()		debug_vectors->cacheflush()
-#define pmon_gets(s)			debug_vectors->gets(s)
-#define pmon_cpustart(n, f, sp, gp)	debug_vectors->_s.cpustart(n, f, sp, gp)
-#define pmon_smpfork(cp, sp)		debug_vectors->_s.smpfork(cp, sp)
-#define pmon_semlock(sem)		debug_vectors->semlock(sem)
-#define pmon_semunlock(sem)		debug_vectors->semunlock(sem)
-
-#endif /* _ASM_PMON_H */
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index fba18d4a9190..7619ad319400 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -385,7 +385,7 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[29])
 #define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status)
 
-#ifdef CONFIG_CPU_LOONGSON3
+#ifdef CONFIG_CPU_LOONGSON64
 /*
  * Loongson-3's SFB (Store-Fill-Buffer) may buffer writes indefinitely when a
  * tight read loop is executed, because reads take priority over writes & the
diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h
index 7f4a32d3345a..15ab16f99f28 100644
--- a/arch/mips/include/asm/r4kcache.h
+++ b/arch/mips/include/asm/r4kcache.h
@@ -15,12 +15,14 @@
 #include <linux/stringify.h>
 
 #include <asm/asm.h>
+#include <asm/asm-eva.h>
 #include <asm/cacheops.h>
 #include <asm/compiler.h>
 #include <asm/cpu-features.h>
 #include <asm/cpu-type.h>
 #include <asm/mipsmtregs.h>
 #include <asm/mmzone.h>
+#include <asm/unroll.h>
 #include <linux/uaccess.h> /* for uaccess_kernel() */
 
 extern void (*r4k_blast_dcache)(void);
@@ -39,16 +41,19 @@ extern void (*r4k_blast_icache)(void);
  */
 #define INDEX_BASE	CKSEG0
 
-#define cache_op(op,addr)						\
+#define _cache_op(insn, op, addr)					\
 	__asm__ __volatile__(						\
 	"	.set	push					\n"	\
 	"	.set	noreorder				\n"	\
 	"	.set "MIPS_ISA_ARCH_LEVEL"			\n"	\
-	"	cache	%0, %1					\n"	\
+	"	" insn("%0", "%1") "				\n"	\
 	"	.set	pop					\n"	\
 	:								\
 	: "i" (op), "R" (*(unsigned char *)(addr)))
 
+#define cache_op(op, addr)						\
+	_cache_op(kernel_cache, op, addr)
+
 static inline void flush_icache_line_indexed(unsigned long addr)
 {
 	cache_op(Index_Invalidate_I, addr);
@@ -67,7 +72,7 @@ static inline void flush_scache_line_indexed(unsigned long addr)
 static inline void flush_icache_line(unsigned long addr)
 {
 	switch (boot_cpu_type()) {
-	case CPU_LOONGSON2:
+	case CPU_LOONGSON2EF:
 		cache_op(Hit_Invalidate_I_Loongson2, addr);
 		break;
 
@@ -149,7 +154,7 @@ static inline void flush_scache_line(unsigned long addr)
 static inline int protected_flush_icache_line(unsigned long addr)
 {
 	switch (boot_cpu_type()) {
-	case CPU_LOONGSON2:
+	case CPU_LOONGSON2EF:
 		return protected_cache_op(Hit_Invalidate_I_Loongson2, addr);
 
 	default:
@@ -193,338 +198,10 @@ static inline void invalidate_tcache_page(unsigned long addr)
 	cache_op(Page_Invalidate_T, addr);
 }
 
-#ifndef CONFIG_CPU_MIPSR6
-#define cache16_unroll32(base,op)					\
-	__asm__ __volatile__(						\
-	"	.set push					\n"	\
-	"	.set noreorder					\n"	\
-	"	.set mips3					\n"	\
-	"	cache %1, 0x000(%0); cache %1, 0x010(%0)	\n"	\
-	"	cache %1, 0x020(%0); cache %1, 0x030(%0)	\n"	\
-	"	cache %1, 0x040(%0); cache %1, 0x050(%0)	\n"	\
-	"	cache %1, 0x060(%0); cache %1, 0x070(%0)	\n"	\
-	"	cache %1, 0x080(%0); cache %1, 0x090(%0)	\n"	\
-	"	cache %1, 0x0a0(%0); cache %1, 0x0b0(%0)	\n"	\
-	"	cache %1, 0x0c0(%0); cache %1, 0x0d0(%0)	\n"	\
-	"	cache %1, 0x0e0(%0); cache %1, 0x0f0(%0)	\n"	\
-	"	cache %1, 0x100(%0); cache %1, 0x110(%0)	\n"	\
-	"	cache %1, 0x120(%0); cache %1, 0x130(%0)	\n"	\
-	"	cache %1, 0x140(%0); cache %1, 0x150(%0)	\n"	\
-	"	cache %1, 0x160(%0); cache %1, 0x170(%0)	\n"	\
-	"	cache %1, 0x180(%0); cache %1, 0x190(%0)	\n"	\
-	"	cache %1, 0x1a0(%0); cache %1, 0x1b0(%0)	\n"	\
-	"	cache %1, 0x1c0(%0); cache %1, 0x1d0(%0)	\n"	\
-	"	cache %1, 0x1e0(%0); cache %1, 0x1f0(%0)	\n"	\
-	"	.set pop					\n"	\
-		:							\
-		: "r" (base),						\
-		  "i" (op));
-
-#define cache32_unroll32(base,op)					\
-	__asm__ __volatile__(						\
-	"	.set push					\n"	\
-	"	.set noreorder					\n"	\
-	"	.set mips3					\n"	\
-	"	cache %1, 0x000(%0); cache %1, 0x020(%0)	\n"	\
-	"	cache %1, 0x040(%0); cache %1, 0x060(%0)	\n"	\
-	"	cache %1, 0x080(%0); cache %1, 0x0a0(%0)	\n"	\
-	"	cache %1, 0x0c0(%0); cache %1, 0x0e0(%0)	\n"	\
-	"	cache %1, 0x100(%0); cache %1, 0x120(%0)	\n"	\
-	"	cache %1, 0x140(%0); cache %1, 0x160(%0)	\n"	\
-	"	cache %1, 0x180(%0); cache %1, 0x1a0(%0)	\n"	\
-	"	cache %1, 0x1c0(%0); cache %1, 0x1e0(%0)	\n"	\
-	"	cache %1, 0x200(%0); cache %1, 0x220(%0)	\n"	\
-	"	cache %1, 0x240(%0); cache %1, 0x260(%0)	\n"	\
-	"	cache %1, 0x280(%0); cache %1, 0x2a0(%0)	\n"	\
-	"	cache %1, 0x2c0(%0); cache %1, 0x2e0(%0)	\n"	\
-	"	cache %1, 0x300(%0); cache %1, 0x320(%0)	\n"	\
-	"	cache %1, 0x340(%0); cache %1, 0x360(%0)	\n"	\
-	"	cache %1, 0x380(%0); cache %1, 0x3a0(%0)	\n"	\
-	"	cache %1, 0x3c0(%0); cache %1, 0x3e0(%0)	\n"	\
-	"	.set pop					\n"	\
-		:							\
-		: "r" (base),						\
-		  "i" (op));
-
-#define cache64_unroll32(base,op)					\
-	__asm__ __volatile__(						\
-	"	.set push					\n"	\
-	"	.set noreorder					\n"	\
-	"	.set mips3					\n"	\
-	"	cache %1, 0x000(%0); cache %1, 0x040(%0)	\n"	\
-	"	cache %1, 0x080(%0); cache %1, 0x0c0(%0)	\n"	\
-	"	cache %1, 0x100(%0); cache %1, 0x140(%0)	\n"	\
-	"	cache %1, 0x180(%0); cache %1, 0x1c0(%0)	\n"	\
-	"	cache %1, 0x200(%0); cache %1, 0x240(%0)	\n"	\
-	"	cache %1, 0x280(%0); cache %1, 0x2c0(%0)	\n"	\
-	"	cache %1, 0x300(%0); cache %1, 0x340(%0)	\n"	\
-	"	cache %1, 0x380(%0); cache %1, 0x3c0(%0)	\n"	\
-	"	cache %1, 0x400(%0); cache %1, 0x440(%0)	\n"	\
-	"	cache %1, 0x480(%0); cache %1, 0x4c0(%0)	\n"	\
-	"	cache %1, 0x500(%0); cache %1, 0x540(%0)	\n"	\
-	"	cache %1, 0x580(%0); cache %1, 0x5c0(%0)	\n"	\
-	"	cache %1, 0x600(%0); cache %1, 0x640(%0)	\n"	\
-	"	cache %1, 0x680(%0); cache %1, 0x6c0(%0)	\n"	\
-	"	cache %1, 0x700(%0); cache %1, 0x740(%0)	\n"	\
-	"	cache %1, 0x780(%0); cache %1, 0x7c0(%0)	\n"	\
-	"	.set pop					\n"	\
-		:							\
-		: "r" (base),						\
-		  "i" (op));
-
-#define cache128_unroll32(base,op)					\
-	__asm__ __volatile__(						\
-	"	.set push					\n"	\
-	"	.set noreorder					\n"	\
-	"	.set mips3					\n"	\
-	"	cache %1, 0x000(%0); cache %1, 0x080(%0)	\n"	\
-	"	cache %1, 0x100(%0); cache %1, 0x180(%0)	\n"	\
-	"	cache %1, 0x200(%0); cache %1, 0x280(%0)	\n"	\
-	"	cache %1, 0x300(%0); cache %1, 0x380(%0)	\n"	\
-	"	cache %1, 0x400(%0); cache %1, 0x480(%0)	\n"	\
-	"	cache %1, 0x500(%0); cache %1, 0x580(%0)	\n"	\
-	"	cache %1, 0x600(%0); cache %1, 0x680(%0)	\n"	\
-	"	cache %1, 0x700(%0); cache %1, 0x780(%0)	\n"	\
-	"	cache %1, 0x800(%0); cache %1, 0x880(%0)	\n"	\
-	"	cache %1, 0x900(%0); cache %1, 0x980(%0)	\n"	\
-	"	cache %1, 0xa00(%0); cache %1, 0xa80(%0)	\n"	\
-	"	cache %1, 0xb00(%0); cache %1, 0xb80(%0)	\n"	\
-	"	cache %1, 0xc00(%0); cache %1, 0xc80(%0)	\n"	\
-	"	cache %1, 0xd00(%0); cache %1, 0xd80(%0)	\n"	\
-	"	cache %1, 0xe00(%0); cache %1, 0xe80(%0)	\n"	\
-	"	cache %1, 0xf00(%0); cache %1, 0xf80(%0)	\n"	\
-	"	.set pop					\n"	\
-		:							\
-		: "r" (base),						\
-		  "i" (op));
-
-#else
-/*
- * MIPS R6 changed the cache opcode and moved to a 8-bit offset field.
- * This means we now need to increment the base register before we flush
- * more cache lines
- */
-#define cache16_unroll32(base,op)				\
-	__asm__ __volatile__(					\
-	"	.set push\n"					\
-	"	.set noreorder\n"				\
-	"	.set mips64r6\n"				\
-	"	.set noat\n"					\
-	"	cache %1, 0x000(%0); cache %1, 0x010(%0)\n"	\
-	"	cache %1, 0x020(%0); cache %1, 0x030(%0)\n"	\
-	"	cache %1, 0x040(%0); cache %1, 0x050(%0)\n"	\
-	"	cache %1, 0x060(%0); cache %1, 0x070(%0)\n"	\
-	"	cache %1, 0x080(%0); cache %1, 0x090(%0)\n"	\
-	"	cache %1, 0x0a0(%0); cache %1, 0x0b0(%0)\n"	\
-	"	cache %1, 0x0c0(%0); cache %1, 0x0d0(%0)\n"	\
-	"	cache %1, 0x0e0(%0); cache %1, 0x0f0(%0)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, %0, 0x100	\n"	\
-	"	cache %1, 0x000($1); cache %1, 0x010($1)\n"	\
-	"	cache %1, 0x020($1); cache %1, 0x030($1)\n"	\
-	"	cache %1, 0x040($1); cache %1, 0x050($1)\n"	\
-	"	cache %1, 0x060($1); cache %1, 0x070($1)\n"	\
-	"	cache %1, 0x080($1); cache %1, 0x090($1)\n"	\
-	"	cache %1, 0x0a0($1); cache %1, 0x0b0($1)\n"	\
-	"	cache %1, 0x0c0($1); cache %1, 0x0d0($1)\n"	\
-	"	cache %1, 0x0e0($1); cache %1, 0x0f0($1)\n"	\
-	"	.set pop\n"					\
-		:						\
-		: "r" (base),					\
-		  "i" (op));
-
-#define cache32_unroll32(base,op)				\
-	__asm__ __volatile__(					\
-	"	.set push\n"					\
-	"	.set noreorder\n"				\
-	"	.set mips64r6\n"				\
-	"	.set noat\n"					\
-	"	cache %1, 0x000(%0); cache %1, 0x020(%0)\n"	\
-	"	cache %1, 0x040(%0); cache %1, 0x060(%0)\n"	\
-	"	cache %1, 0x080(%0); cache %1, 0x0a0(%0)\n"	\
-	"	cache %1, 0x0c0(%0); cache %1, 0x0e0(%0)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, %0, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x020($1)\n"	\
-	"	cache %1, 0x040($1); cache %1, 0x060($1)\n"	\
-	"	cache %1, 0x080($1); cache %1, 0x0a0($1)\n"	\
-	"	cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x020($1)\n"	\
-	"	cache %1, 0x040($1); cache %1, 0x060($1)\n"	\
-	"	cache %1, 0x080($1); cache %1, 0x0a0($1)\n"	\
-	"	cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100\n"	\
-	"	cache %1, 0x000($1); cache %1, 0x020($1)\n"	\
-	"	cache %1, 0x040($1); cache %1, 0x060($1)\n"	\
-	"	cache %1, 0x080($1); cache %1, 0x0a0($1)\n"	\
-	"	cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n"	\
-	"	.set pop\n"					\
-		:						\
-		: "r" (base),					\
-		  "i" (op));
-
-#define cache64_unroll32(base,op)				\
-	__asm__ __volatile__(					\
-	"	.set push\n"					\
-	"	.set noreorder\n"				\
-	"	.set mips64r6\n"				\
-	"	.set noat\n"					\
-	"	cache %1, 0x000(%0); cache %1, 0x040(%0)\n"	\
-	"	cache %1, 0x080(%0); cache %1, 0x0c0(%0)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, %0, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
-	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
-	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
-	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
-	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
-	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
-	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
-	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
-	"	.set pop\n"					\
-		:						\
-		: "r" (base),					\
-		  "i" (op));
-
-#define cache128_unroll32(base,op)				\
-	__asm__ __volatile__(					\
-	"	.set push\n"					\
-	"	.set noreorder\n"				\
-	"	.set mips64r6\n"				\
-	"	.set noat\n"					\
-	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, %0, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	"__stringify(LONG_ADDIU)" $1, $1, 0x100 \n"	\
-	"	cache %1, 0x000($1); cache %1, 0x080($1)\n"	\
-	"	.set pop\n"					\
-		:						\
-		: "r" (base),					\
-		  "i" (op));
-#endif /* CONFIG_CPU_MIPSR6 */
-
-/*
- * Perform the cache operation specified by op using a user mode virtual
- * address while in kernel mode.
- */
-#define cache16_unroll32_user(base,op)					\
-	__asm__ __volatile__(						\
-	"	.set push					\n"	\
-	"	.set noreorder					\n"	\
-	"	.set mips0					\n"	\
-	"	.set eva					\n"	\
-	"	cachee %1, 0x000(%0); cachee %1, 0x010(%0)	\n"	\
-	"	cachee %1, 0x020(%0); cachee %1, 0x030(%0)	\n"	\
-	"	cachee %1, 0x040(%0); cachee %1, 0x050(%0)	\n"	\
-	"	cachee %1, 0x060(%0); cachee %1, 0x070(%0)	\n"	\
-	"	cachee %1, 0x080(%0); cachee %1, 0x090(%0)	\n"	\
-	"	cachee %1, 0x0a0(%0); cachee %1, 0x0b0(%0)	\n"	\
-	"	cachee %1, 0x0c0(%0); cachee %1, 0x0d0(%0)	\n"	\
-	"	cachee %1, 0x0e0(%0); cachee %1, 0x0f0(%0)	\n"	\
-	"	cachee %1, 0x100(%0); cachee %1, 0x110(%0)	\n"	\
-	"	cachee %1, 0x120(%0); cachee %1, 0x130(%0)	\n"	\
-	"	cachee %1, 0x140(%0); cachee %1, 0x150(%0)	\n"	\
-	"	cachee %1, 0x160(%0); cachee %1, 0x170(%0)	\n"	\
-	"	cachee %1, 0x180(%0); cachee %1, 0x190(%0)	\n"	\
-	"	cachee %1, 0x1a0(%0); cachee %1, 0x1b0(%0)	\n"	\
-	"	cachee %1, 0x1c0(%0); cachee %1, 0x1d0(%0)	\n"	\
-	"	cachee %1, 0x1e0(%0); cachee %1, 0x1f0(%0)	\n"	\
-	"	.set pop					\n"	\
-		:							\
-		: "r" (base),						\
-		  "i" (op));
-
-#define cache32_unroll32_user(base, op)					\
-	__asm__ __volatile__(						\
-	"	.set push					\n"	\
-	"	.set noreorder					\n"	\
-	"	.set mips0					\n"	\
-	"	.set eva					\n"	\
-	"	cachee %1, 0x000(%0); cachee %1, 0x020(%0)	\n"	\
-	"	cachee %1, 0x040(%0); cachee %1, 0x060(%0)	\n"	\
-	"	cachee %1, 0x080(%0); cachee %1, 0x0a0(%0)	\n"	\
-	"	cachee %1, 0x0c0(%0); cachee %1, 0x0e0(%0)	\n"	\
-	"	cachee %1, 0x100(%0); cachee %1, 0x120(%0)	\n"	\
-	"	cachee %1, 0x140(%0); cachee %1, 0x160(%0)	\n"	\
-	"	cachee %1, 0x180(%0); cachee %1, 0x1a0(%0)	\n"	\
-	"	cachee %1, 0x1c0(%0); cachee %1, 0x1e0(%0)	\n"	\
-	"	cachee %1, 0x200(%0); cachee %1, 0x220(%0)	\n"	\
-	"	cachee %1, 0x240(%0); cachee %1, 0x260(%0)	\n"	\
-	"	cachee %1, 0x280(%0); cachee %1, 0x2a0(%0)	\n"	\
-	"	cachee %1, 0x2c0(%0); cachee %1, 0x2e0(%0)	\n"	\
-	"	cachee %1, 0x300(%0); cachee %1, 0x320(%0)	\n"	\
-	"	cachee %1, 0x340(%0); cachee %1, 0x360(%0)	\n"	\
-	"	cachee %1, 0x380(%0); cachee %1, 0x3a0(%0)	\n"	\
-	"	cachee %1, 0x3c0(%0); cachee %1, 0x3e0(%0)	\n"	\
-	"	.set pop					\n"	\
-		:							\
-		: "r" (base),						\
-		  "i" (op));
-
-#define cache64_unroll32_user(base, op)					\
-	__asm__ __volatile__(						\
-	"	.set push					\n"	\
-	"	.set noreorder					\n"	\
-	"	.set mips0					\n"	\
-	"	.set eva					\n"	\
-	"	cachee %1, 0x000(%0); cachee %1, 0x040(%0)	\n"	\
-	"	cachee %1, 0x080(%0); cachee %1, 0x0c0(%0)	\n"	\
-	"	cachee %1, 0x100(%0); cachee %1, 0x140(%0)	\n"	\
-	"	cachee %1, 0x180(%0); cachee %1, 0x1c0(%0)	\n"	\
-	"	cachee %1, 0x200(%0); cachee %1, 0x240(%0)	\n"	\
-	"	cachee %1, 0x280(%0); cachee %1, 0x2c0(%0)	\n"	\
-	"	cachee %1, 0x300(%0); cachee %1, 0x340(%0)	\n"	\
-	"	cachee %1, 0x380(%0); cachee %1, 0x3c0(%0)	\n"	\
-	"	cachee %1, 0x400(%0); cachee %1, 0x440(%0)	\n"	\
-	"	cachee %1, 0x480(%0); cachee %1, 0x4c0(%0)	\n"	\
-	"	cachee %1, 0x500(%0); cachee %1, 0x540(%0)	\n"	\
-	"	cachee %1, 0x580(%0); cachee %1, 0x5c0(%0)	\n"	\
-	"	cachee %1, 0x600(%0); cachee %1, 0x640(%0)	\n"	\
-	"	cachee %1, 0x680(%0); cachee %1, 0x6c0(%0)	\n"	\
-	"	cachee %1, 0x700(%0); cachee %1, 0x740(%0)	\n"	\
-	"	cachee %1, 0x780(%0); cachee %1, 0x7c0(%0)	\n"	\
-	"	.set pop					\n"	\
-		:							\
-		: "r" (base),						\
-		  "i" (op));
+#define cache_unroll(times, insn, op, addr, lsize) do {			\
+	int i = 0;							\
+	unroll(times, _cache_op, insn, op, (addr) + (i++ * (lsize)));	\
+} while (0)
 
 /* build blast_xxx, blast_xxx_page, blast_xxx_page_indexed */
 #define __BUILD_BLAST_CACHE(pfx, desc, indexop, hitop, lsize, extra)	\
@@ -539,7 +216,8 @@ static inline void extra##blast_##pfx##cache##lsize(void)		\
 									\
 	for (ws = 0; ws < ws_end; ws += ws_inc)				\
 		for (addr = start; addr < end; addr += lsize * 32)	\
-			cache##lsize##_unroll32(addr|ws, indexop);	\
+			cache_unroll(32, kernel_cache, indexop,		\
+				     addr | ws, lsize);			\
 }									\
 									\
 static inline void extra##blast_##pfx##cache##lsize##_page(unsigned long page) \
@@ -548,7 +226,7 @@ static inline void extra##blast_##pfx##cache##lsize##_page(unsigned long page) \
 	unsigned long end = page + PAGE_SIZE;				\
 									\
 	do {								\
-		cache##lsize##_unroll32(start, hitop);			\
+		cache_unroll(32, kernel_cache, hitop, start, lsize);	\
 		start += lsize * 32;					\
 	} while (start < end);						\
 }									\
@@ -565,7 +243,8 @@ static inline void extra##blast_##pfx##cache##lsize##_page_indexed(unsigned long
 									\
 	for (ws = 0; ws < ws_end; ws += ws_inc)				\
 		for (addr = start; addr < end; addr += lsize * 32)	\
-			cache##lsize##_unroll32(addr|ws, indexop);	\
+			cache_unroll(32, kernel_cache, indexop,		\
+				     addr | ws, lsize);			\
 }
 
 __BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 16, )
@@ -596,7 +275,7 @@ static inline void blast_##pfx##cache##lsize##_user_page(unsigned long page) \
 	unsigned long end = page + PAGE_SIZE;				\
 									\
 	do {								\
-		cache##lsize##_unroll32_user(start, hitop);             \
+		cache_unroll(32, user_cache, hitop, start, lsize);	\
 		start += lsize * 32;					\
 	} while (start < end);						\
 }
@@ -688,7 +367,8 @@ static inline void blast_##pfx##cache##lsize##_node(long node)		\
 									\
 	for (ws = 0; ws < ws_end; ws += ws_inc)				\
 		for (addr = start; addr < end; addr += lsize * 32)	\
-			cache##lsize##_unroll32(addr|ws, indexop);	\
+			cache_unroll(32, kernel_cache, indexop,		\
+				     addr | ws, lsize);			\
 }
 
 __BUILD_BLAST_CACHE_NODE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 16)
diff --git a/arch/mips/include/asm/sgi/heart.h b/arch/mips/include/asm/sgi/heart.h
new file mode 100644
index 000000000000..c423221b4792
--- /dev/null
+++ b/arch/mips/include/asm/sgi/heart.h
@@ -0,0 +1,272 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * HEART chip definitions
+ *
+ * Copyright (C) 2004-2007 Stanislaw Skowronek <skylark@unaligned.org>
+ *		 2009 Johannes Dickgreber <tanzy@gmx.de>
+ *		 2007-2015 Joshua Kinard <kumba@gentoo.org>
+ */
+#ifndef __ASM_SGI_HEART_H
+#define __ASM_SGI_HEART_H
+
+#include <linux/types.h>
+#include <linux/time.h>
+
+/*
+ * There are 8 DIMM slots on an IP30 system
+ * board, which are grouped into four banks
+ */
+#define HEART_MEMORY_BANKS	4
+
+/* HEART can support up to four CPUs */
+#define HEART_MAX_CPUS		4
+
+#define HEART_XKPHYS_BASE	((void *)(IO_BASE | 0x000000000ff00000ULL))
+
+/**
+ * struct ip30_heart_regs - struct that maps IP30 HEART registers.
+ * @mode: HEART_MODE - Purpose Unknown, machine reset called from here.
+ * @sdram_mode: HEART_SDRAM_MODE - purpose unknown.
+ * @mem_refresh: HEART_MEM_REF - purpose unknown.
+ * @mem_req_arb: HEART_MEM_REQ_ARB - purpose unknown.
+ * @mem_cfg.q: union for 64bit access to HEART_MEMCFG - 4x 64bit registers.
+ * @mem_cfg.l: union for 32bit access to HEART_MEMCFG - 8x 32bit registers.
+ * @fc_mode: HEART_FC_MODE - Purpose Unknown, possibly for GFX flow control.
+ * @fc_timer_limit: HEART_FC_TIMER_LIMIT - purpose unknown.
+ * @fc_addr: HEART_FC0_ADDR, HEART_FC1_ADDR - purpose unknown.
+ * @fc_credit_cnt: HEART_FC0_CR_CNT, HEART_FC1_CR_CNT - purpose unknown.
+ * @fc_timer: HEART_FC0_TIMER, HEART_FC1_TIMER - purpose unknown.
+ * @status: HEART_STATUS - HEART status information.
+ * @bus_err_addr: HEART_BERR_ADDR - likely contains addr of recent SIGBUS.
+ * @bus_err_misc: HEART_BERR_MISC - purpose unknown.
+ * @mem_err_addr: HEART_MEMERR_ADDR - likely contains addr of recent mem err.
+ * @mem_err_data: HEART_MEMERR_DATA - purpose unknown.
+ * @piur_acc_err: HEART_PIUR_ACC_ERR - likely for access err to HEART regs.
+ * @mlan_clock_div: HEART_MLAN_CLK_DIV - MicroLAN clock divider.
+ * @mlan_ctrl: HEART_MLAN_CTL - MicroLAN control.
+ * @__pad0: 0x0f40 bytes of padding -> next HEART register 0x01000.
+ * @undefined: Undefined/diag register, write to it triggers PIUR_ACC_ERR.
+ * @__pad1: 0xeff8 bytes of padding -> next HEART register 0x10000.
+ * @imr: HEART_IMR0 to HEART_IMR3 - per-cpu interrupt mask register.
+ * @set_isr: HEART_SET_ISR - set interrupt status register.
+ * @clear_isr: HEART_CLR_ISR - clear interrupt status register.
+ * @isr: HEART_ISR - interrupt status register (read-only).
+ * @imsr: HEART_IMSR - purpose unknown.
+ * @cause: HEART_CAUSE - HEART cause information.
+ * @__pad2: 0xffb8 bytes of padding -> next HEART register 0x20000.
+ * @count: HEART_COUNT - 52-bit counter.
+ * @__pad3: 0xfff8 bytes of padding -> next HEART register 0x30000.
+ * @compare: HEART_COMPARE - 24-bit compare.
+ * @__pad4: 0xfff8 bytes of padding -> next HEART register 0x40000.
+ * @trigger: HEART_TRIGGER - purpose unknown.
+ * @__pad5: 0xfff8 bytes of padding -> next HEART register 0x50000.
+ * @cpuid: HEART_PRID - contains CPU ID of CPU currently accessing HEART.
+ * @__pad6: 0xfff8 bytes of padding -> next HEART register 0x60000.
+ * @sync: HEART_SYNC - purpose unknown.
+ *
+ * HEART is the main system controller ASIC for IP30 system.  It incorporates
+ * a memory controller, interrupt status/cause/set/clear management, basic
+ * timer with count/compare, and other functionality.  For Linux, not all of
+ * HEART's functions are fully understood.
+ *
+ * Implementation note: All HEART registers are 64bits-wide, but the mem_cfg
+ * register only reports correct values if queried in 32bits.  Hence the need
+ * for a union.  Even though mem_cfg.l has 8 array slots, we only ever query
+ * up to 4 of those.  IP30 has 8 DIMM slots arranged into 4 banks, w/ 2 DIMMs
+ * per bank.  Each 32bit read accesses one of these banks.  Perhaps HEART was
+ * designed to address up to 8 banks (16 DIMMs)?  We may never know.
+ */
+struct ip30_heart_regs {		/* 0x0ff00000 */
+	u64 mode;			/* +  0x00000 */
+	/* Memory */
+	u64 sdram_mode;			/* +  0x00008 */
+	u64 mem_refresh;		/* +  0x00010 */
+	u64 mem_req_arb;		/* +  0x00018 */
+	union {
+		u64 q[HEART_MEMORY_BANKS];	/* readq() */
+		u32 l[HEART_MEMORY_BANKS * 2];	/* readl() */
+	} mem_cfg;			/* +  0x00020 */
+	/* Flow control (gfx?) */
+	u64 fc_mode;			/* +  0x00040 */
+	u64 fc_timer_limit;		/* +  0x00048 */
+	u64 fc_addr[2];			/* +  0x00050 */
+	u64 fc_credit_cnt[2];		/* +  0x00060 */
+	u64 fc_timer[2];		/* +  0x00070 */
+	/* Status */
+	u64 status;			/* +  0x00080 */
+	/* Bus error */
+	u64 bus_err_addr;		/* +  0x00088 */
+	u64 bus_err_misc;		/* +  0x00090 */
+	/* Memory error */
+	u64 mem_err_addr;		/* +  0x00098 */
+	u64 mem_err_data;		/* +  0x000a0 */
+	/* Misc */
+	u64 piur_acc_err;		/* +  0x000a8 */
+	u64 mlan_clock_div;		/* +  0x000b0 */
+	u64 mlan_ctrl;			/* +  0x000b8 */
+	u64 __pad0[0x01e8];		/* +  0x000c0 + 0x0f40 */
+	/* Undefined */
+	u64 undefined;			/* +  0x01000 */
+	u64 __pad1[0x1dff];		/* +  0x01008 + 0xeff8 */
+	/* Interrupts */
+	u64 imr[HEART_MAX_CPUS];	/* +  0x10000 */
+	u64 set_isr;			/* +  0x10020 */
+	u64 clear_isr;			/* +  0x10028 */
+	u64 isr;			/* +  0x10030 */
+	u64 imsr;			/* +  0x10038 */
+	u64 cause;			/* +  0x10040 */
+	u64 __pad2[0x1ff7];		/* +  0x10048 + 0xffb8 */
+	/* Timer */
+	u64 count;			/* +  0x20000 */
+	u64 __pad3[0x1fff];		/* +  0x20008 + 0xfff8 */
+	u64 compare;			/* +  0x30000 */
+	u64 __pad4[0x1fff];		/* +  0x30008 + 0xfff8 */
+	u64 trigger;			/* +  0x40000 */
+	u64 __pad5[0x1fff];		/* +  0x40008 + 0xfff8 */
+	/* Misc */
+	u64 cpuid;			/* +  0x50000 */
+	u64 __pad6[0x1fff];		/* +  0x50008 + 0xfff8 */
+	u64 sync;			/* +  0x60000 */
+};
+
+
+/* For timer-related bits. */
+#define HEART_NS_PER_CYCLE	80
+#define HEART_CYCLES_PER_SEC	(NSEC_PER_SEC / HEART_NS_PER_CYCLE)
+
+
+/*
+ * XXX: Everything below this comment will either go away or be cleaned
+ *      up to fit in better with Linux.  A lot of the bit definitions for
+ *      HEART were derived from IRIX's sys/RACER/heart.h header file.
+ */
+
+/* HEART Masks */
+#define HEART_ATK_MASK		0x0007ffffffffffff	/* HEART attack mask */
+#define HEART_ACK_ALL_MASK	0xffffffffffffffff	/* Ack everything */
+#define HEART_CLR_ALL_MASK	0x0000000000000000	/* Clear all */
+#define HEART_BR_ERR_MASK	0x7ff8000000000000	/* BRIDGE error mask */
+#define HEART_CPU0_ERR_MASK	0x8ff8000000000000	/* CPU0 error mask */
+#define HEART_CPU1_ERR_MASK	0x97f8000000000000	/* CPU1 error mask */
+#define HEART_CPU2_ERR_MASK	0xa7f8000000000000	/* CPU2 error mask */
+#define HEART_CPU3_ERR_MASK	0xc7f8000000000000	/* CPU3 error mask */
+#define HEART_ERR_MASK		0x1ff			/* HEART error mask */
+#define HEART_ERR_MASK_START	51			/* HEART error start */
+#define HEART_ERR_MASK_END	63			/* HEART error end */
+
+/* Bits in the HEART_MODE register. */
+#define HM_PROC_DISABLE_SHFT		60
+#define HM_PROC_DISABLE_MSK		(0xfUL << HM_PROC_DISABLE_SHFT)
+#define HM_PROC_DISABLE(x)		(0x1UL << (x) + HM_PROC_DISABLE_SHFT)
+#define HM_MAX_PSR			(0x7UL << 57)
+#define HM_MAX_IOSR			(0x7UL << 54)
+#define HM_MAX_PEND_IOSR		(0x7UL << 51)
+#define HM_TRIG_SRC_SEL_MSK		(0x7UL << 48)
+#define HM_TRIG_HEART_EXC		(0x0UL << 48)
+#define HM_TRIG_REG_BIT			(0x1UL << 48)
+#define HM_TRIG_SYSCLK			(0x2UL << 48)
+#define HM_TRIG_MEMCLK_2X		(0x3UL << 48)
+#define HM_TRIG_MEMCLK			(0x4UL << 48)
+#define HM_TRIG_IOCLK			(0x5UL << 48)
+#define HM_PIU_TEST_MODE		(0xfUL << 40)
+#define HM_GP_FLAG_MSK			(0xfUL << 36)
+#define HM_GP_FLAG(x)			BIT((x) + 36)
+#define HM_MAX_PROC_HYST		(0xfUL << 32)
+#define HM_LLP_WRST_AFTER_RST		BIT(28)
+#define HM_LLP_LINK_RST			BIT(27)
+#define HM_LLP_WARM_RST			BIT(26)
+#define HM_COR_ECC_LCK			BIT(25)
+#define HM_REDUCED_PWR			BIT(24)
+#define HM_COLD_RST			BIT(23)
+#define HM_SW_RST			BIT(22)
+#define HM_MEM_FORCE_WR			BIT(21)
+#define HM_DB_ERR_GEN			BIT(20)
+#define HM_SB_ERR_GEN			BIT(19)
+#define HM_CACHED_PIO_EN		BIT(18)
+#define HM_CACHED_PROM_EN		BIT(17)
+#define HM_PE_SYS_COR_ERE		BIT(16)
+#define HM_GLOBAL_ECC_EN		BIT(15)
+#define HM_IO_COH_EN			BIT(14)
+#define HM_INT_EN			BIT(13)
+#define HM_DATA_CHK_EN			BIT(12)
+#define HM_REF_EN			BIT(11)
+#define HM_BAD_SYSWR_ERE		BIT(10)
+#define HM_BAD_SYSRD_ERE		BIT(9)
+#define HM_SYSSTATE_ERE			BIT(8)
+#define HM_SYSCMD_ERE			BIT(7)
+#define HM_NCOR_SYS_ERE			BIT(6)
+#define HM_COR_SYS_ERE			BIT(5)
+#define HM_DATA_ELMNT_ERE		BIT(4)
+#define HM_MEM_ADDR_PROC_ERE		BIT(3)
+#define HM_MEM_ADDR_IO_ERE		BIT(2)
+#define HM_NCOR_MEM_ERE			BIT(1)
+#define HM_COR_MEM_ERE			BIT(0)
+
+/* Bits in the HEART_MEM_REF register. */
+#define HEART_MEMREF_REFS(x)		((0xfUL & (x)) << 16)
+#define HEART_MEMREF_PERIOD(x)		((0xffffUL & (x)))
+#define HEART_MEMREF_REFS_VAL		HEART_MEMREF_REFS(8)
+#define HEART_MEMREF_PERIOD_VAL		HEART_MEMREF_PERIOD(0x4000)
+#define HEART_MEMREF_VAL		(HEART_MEMREF_REFS_VAL | \
+					 HEART_MEMREF_PERIOD_VAL)
+
+/* Bits in the HEART_MEM_REQ_ARB register. */
+#define HEART_MEMARB_IODIS		(1  << 20)
+#define HEART_MEMARB_MAXPMWRQS		(15 << 16)
+#define HEART_MEMARB_MAXPMRRQS		(15 << 12)
+#define HEART_MEMARB_MAXPMRQS		(15 << 8)
+#define HEART_MEMARB_MAXRRRQS		(15 << 4)
+#define HEART_MEMARB_MAXGBRRQS		(15)
+
+/* Bits in the HEART_MEMCFG<x> registers. */
+#define HEART_MEMCFG_VALID		0x80000000	/* Bank is valid */
+#define HEART_MEMCFG_DENSITY		0x01c00000	/* Mem density */
+#define HEART_MEMCFG_SIZE_MASK		0x003f0000	/* Mem size mask */
+#define HEART_MEMCFG_ADDR_MASK		0x000001ff	/* Base addr mask */
+#define HEART_MEMCFG_SIZE_SHIFT		16		/* Mem size shift */
+#define HEART_MEMCFG_DENSITY_SHIFT	22		/* Density Shift */
+#define HEART_MEMCFG_UNIT_SHIFT		25		/* Unit Shift, 32MB */
+
+/* Bits in the HEART_STATUS register */
+#define HEART_STAT_HSTL_SDRV		BIT(14)
+#define HEART_STAT_FC_CR_OUT(x)		BIT((x) + 12)
+#define HEART_STAT_DIR_CNNCT		BIT(11)
+#define HEART_STAT_TRITON		BIT(10)
+#define HEART_STAT_R4K			BIT(9)
+#define HEART_STAT_BIG_ENDIAN		BIT(8)
+#define HEART_STAT_PROC_SHFT		4
+#define HEART_STAT_PROC_MSK		(0xfUL << HEART_STAT_PROC_SHFT)
+#define HEART_STAT_PROC_ACTIVE(x)	(0x1UL << ((x) + HEART_STAT_PROC_SHFT))
+#define HEART_STAT_WIDGET_ID		0xf
+
+/* Bits in the HEART_CAUSE register */
+#define HC_PE_SYS_COR_ERR_MSK		(0xfUL << 60)
+#define HC_PE_SYS_COR_ERR(x)		BIT((x) + 60)
+#define HC_PIOWDB_OFLOW			BIT(44)
+#define HC_PIORWRB_OFLOW		BIT(43)
+#define HC_PIUR_ACC_ERR			BIT(42)
+#define HC_BAD_SYSWR_ERR		BIT(41)
+#define HC_BAD_SYSRD_ERR		BIT(40)
+#define HC_SYSSTATE_ERR_MSK		(0xfUL << 36)
+#define HC_SYSSTATE_ERR(x)		BIT((x) + 36)
+#define HC_SYSCMD_ERR_MSK		(0xfUL << 32)
+#define HC_SYSCMD_ERR(x)		BIT((x) + 32)
+#define HC_NCOR_SYSAD_ERR_MSK		(0xfUL << 28)
+#define HC_NCOR_SYSAD_ERR(x)		BIT((x) + 28)
+#define HC_COR_SYSAD_ERR_MSK		(0xfUL << 24)
+#define HC_COR_SYSAD_ERR(x)		BIT((x) + 24)
+#define HC_DATA_ELMNT_ERR_MSK		(0xfUL << 20)
+#define HC_DATA_ELMNT_ERR(x)		BIT((x) + 20)
+#define HC_WIDGET_ERR			BIT(16)
+#define HC_MEM_ADDR_ERR_PROC_MSK	(0xfUL << 4)
+#define HC_MEM_ADDR_ERR_PROC(x)	BIT((x) + 4)
+#define HC_MEM_ADDR_ERR_IO		BIT(2)
+#define HC_NCOR_MEM_ERR			BIT(1)
+#define HC_COR_MEM_ERR			BIT(0)
+
+extern struct ip30_heart_regs __iomem *heart_regs;
+
+#define heart_read	____raw_readq
+#define heart_write	____raw_writeq
+
+#endif /* __ASM_SGI_HEART_H */
diff --git a/arch/mips/include/asm/sgi/sgi.h b/arch/mips/include/asm/sgi/sgi.h
deleted file mode 100644
index b61557151e3f..000000000000
--- a/arch/mips/include/asm/sgi/sgi.h
+++ /dev/null
@@ -1,48 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * sgi.h: Definitions specific to SGI machines.
- *
- * Copyright (C) 1996 David S. Miller (dm@sgi.com)
- */
-#ifndef _ASM_SGI_SGI_H
-#define _ASM_SGI_SGI_H
-
-/* UP=UniProcessor MP=MultiProcessor(capable) */
-enum sgi_mach {
-	ip4,	/* R2k UP */
-	ip5,	/* R2k MP */
-	ip6,	/* R3k UP */
-	ip7,	/* R3k MP */
-	ip9,	/* R3k UP */
-	ip12,	/* R3kA UP, Indigo */
-	ip15,	/* R3kA MP */
-	ip17,	/* R4K UP */
-	ip19,	/* R4K MP */
-	ip20,	/* R4K UP, Indigo */
-	ip21,	/* R8k/TFP MP */
-	ip22,	/* R4x00 UP, Indy, Indigo2 */
-	ip25,	/* R10k MP */
-	ip26,	/* R8k/TFP UP, Indigo2 */
-	ip27,	/* R10k MP, R12k MP, R14k MP, Origin 200/2k, Onyx2 */
-	ip28,	/* R10k UP, Indigo2 Impact R10k */
-	ip30,	/* R10k MP, R12k MP, R14k MP, Octane */
-	ip32,	/* R5k UP, RM5200 UP, RM7k UP, R10k UP, R12k UP, O2 */
-	ip35,   /* R14k MP, R16k MP, Origin 300/3k, Onyx3, Fuel, Tezro */
-};
-
-extern enum sgi_mach sgimach;
-extern void sgi_sysinit(void);
-
-/* Many I/O space registers are byte sized and are contained within
- * one byte per word, specifically the MSB, this macro helps out.
- */
-#ifdef __MIPSEL__
-#define SGI_MSB(regaddr)   (regaddr)
-#else
-#define SGI_MSB(regaddr)   ((regaddr) | 0x3)
-#endif
-
-#endif /* _ASM_SGI_SGI_H */
diff --git a/arch/mips/include/asm/sgialib.h b/arch/mips/include/asm/sgialib.h
index 0d9fad5915fe..80f900417f7e 100644
--- a/arch/mips/include/asm/sgialib.h
+++ b/arch/mips/include/asm/sgialib.h
@@ -15,14 +15,6 @@
 #include <asm/sgiarcs.h>
 
 extern struct linux_romvec *romvec;
-extern int prom_argc;
-
-extern LONG *_prom_argv, *_prom_envp;
-
-/* A 32-bit ARC PROM pass arguments and environment as 32-bit pointer.
-   These macros take care of sign extension.  */
-#define prom_argv(index) ((char *) (long) _prom_argv[(index)])
-#define prom_argc(index) ((char *) (long) _prom_argc[(index)])
 
 extern int prom_flags;
 
@@ -47,12 +39,6 @@ extern void prom_meminit(void);
 /* PROM device tree library routines. */
 #define PROM_NULL_COMPONENT ((pcomponent *) 0)
 
-/* Get sibling component of THIS. */
-extern pcomponent *ArcGetPeer(pcomponent *this);
-
-/* Get child component of THIS. */
-extern pcomponent *ArcGetChild(pcomponent *this);
-
 /* This is called at prom_init time to identify the
  * ARC architecture we are running on
  */
@@ -60,22 +46,16 @@ extern void prom_identify_arch(void);
 
 /* Environment variable routines. */
 extern PCHAR ArcGetEnvironmentVariable(PCHAR name);
-extern LONG ArcSetEnvironmentVariable(PCHAR name, PCHAR value);
 
 /* ARCS command line parsing. */
-extern void prom_init_cmdline(void);
+extern void prom_init_cmdline(int argc, LONG *argv);
 
 /* File operations. */
 extern LONG ArcRead(ULONG fd, PVOID buf, ULONG num, PULONG cnt);
 extern LONG ArcWrite(ULONG fd, PVOID buf, ULONG num, PULONG cnt);
 
 /* Misc. routines. */
-extern VOID ArcHalt(VOID) __noreturn;
-extern VOID ArcPowerDown(VOID) __noreturn;
-extern VOID ArcRestart(VOID) __noreturn;
-extern VOID ArcReboot(VOID) __noreturn;
 extern VOID ArcEnterInteractiveMode(VOID) __noreturn;
-extern VOID ArcFlushAllCaches(VOID);
 extern DISPLAY_STATUS *ArcGetDisplayStatus(ULONG FileID);
 
 #endif /* _ASM_SGIALIB_H */
diff --git a/arch/mips/include/asm/sgiarcs.h b/arch/mips/include/asm/sgiarcs.h
index 105a9479ac5f..e1512cab180b 100644
--- a/arch/mips/include/asm/sgiarcs.h
+++ b/arch/mips/include/asm/sgiarcs.h
@@ -12,6 +12,8 @@
 #ifndef _ASM_SGIARCS_H
 #define _ASM_SGIARCS_H
 
+#include <linux/kernel.h>
+
 #include <asm/types.h>
 #include <asm/fw/arc/types.h>
 
@@ -368,110 +370,65 @@ struct linux_smonblock {
 
 #if defined(CONFIG_64BIT) && defined(CONFIG_FW_ARC32)
 
-#define __arc_clobbers							\
-	"$2", "$3" /* ... */, "$8", "$9", "$10", "$11",				\
-	"$12", "$13", "$14", "$15", "$16", "$24", "$25", "$31"
+extern long call_o32(long vec, void *stack, ...);
+
+extern u64 o32_stk[4096];
+#define O32_STK	(&o32_stk[ARRAY_SIZE(o32_stk)])
 
 #define ARC_CALL0(dest)							\
 ({	long __res;							\
 	long __vec = (long) romvec->dest;				\
-	__asm__ __volatile__(						\
-	"dsubu\t$29, 32\n\t"						\
-	"jalr\t%1\n\t"							\
-	"daddu\t$29, 32\n\t"						\
-	"move\t%0, $2"							\
-	: "=r" (__res), "=r" (__vec)					\
-	: "1" (__vec)							\
-	: __arc_clobbers, "$4", "$5", "$6", "$7");			\
-	(unsigned long) __res;						\
+	__res = call_o32(__vec, O32_STK);				\
+	__res;								\
 })
 
 #define ARC_CALL1(dest, a1)						\
 ({	long __res;							\
-	register signed int __a1 __asm__("$4") = (int) (long) (a1);	\
+	int  __a1 = (int) (long) (a1);					\
 	long __vec = (long) romvec->dest;				\
-	__asm__ __volatile__(						\
-	"dsubu\t$29, 32\n\t"						\
-	"jalr\t%1\n\t"							\
-	"daddu\t$29, 32\n\t"						\
-	"move\t%0, $2"							\
-	: "=r" (__res), "=r" (__vec)					\
-	: "1" (__vec), "r" (__a1)					\
-	: __arc_clobbers, "$5", "$6", "$7");				\
-	(unsigned long) __res;						\
+	__res = call_o32(__vec, O32_STK, __a1);				\
+	__res;								\
 })
 
 #define ARC_CALL2(dest, a1, a2)						\
 ({	long __res;							\
-	register signed int __a1 __asm__("$4") = (int) (long) (a1);	\
-	register signed int __a2 __asm__("$5") = (int) (long) (a2);	\
+	int  __a1 = (int) (long) (a1);					\
+	int  __a2 = (int) (long) (a2);					\
 	long __vec = (long) romvec->dest;				\
-	__asm__ __volatile__(						\
-	"dsubu\t$29, 32\n\t"						\
-	"jalr\t%1\n\t"							\
-	"daddu\t$29, 32\n\t"						\
-	"move\t%0, $2"							\
-	: "=r" (__res), "=r" (__vec)					\
-	: "1" (__vec), "r" (__a1), "r" (__a2)				\
-	: __arc_clobbers, "$6", "$7");					\
+	__res = call_o32(__vec, O32_STK, __a1, __a2);			\
 	__res;								\
 })
 
 #define ARC_CALL3(dest, a1, a2, a3)					\
 ({	long __res;							\
-	register signed int __a1 __asm__("$4") = (int) (long) (a1);	\
-	register signed int __a2 __asm__("$5") = (int) (long) (a2);	\
-	register signed int __a3 __asm__("$6") = (int) (long) (a3);	\
+	int  __a1 = (int) (long) (a1);					\
+	int  __a2 = (int) (long) (a2);					\
+	int  __a3 = (int) (long) (a3);					\
 	long __vec = (long) romvec->dest;				\
-	__asm__ __volatile__(						\
-	"dsubu\t$29, 32\n\t"						\
-	"jalr\t%1\n\t"							\
-	"daddu\t$29, 32\n\t"						\
-	"move\t%0, $2"							\
-	: "=r" (__res), "=r" (__vec)					\
-	: "1" (__vec), "r" (__a1), "r" (__a2), "r" (__a3)		\
-	: __arc_clobbers, "$7");					\
+	__res = call_o32(__vec, O32_STK, __a1, __a2, __a3);		\
 	__res;								\
 })
 
 #define ARC_CALL4(dest, a1, a2, a3, a4)					\
 ({	long __res;							\
-	register signed int __a1 __asm__("$4") = (int) (long) (a1);	\
-	register signed int __a2 __asm__("$5") = (int) (long) (a2);	\
-	register signed int __a3 __asm__("$6") = (int) (long) (a3);	\
-	register signed int __a4 __asm__("$7") = (int) (long) (a4);	\
+	int  __a1 = (int) (long) (a1);					\
+	int  __a2 = (int) (long) (a2);					\
+	int  __a3 = (int) (long) (a3);					\
+	int  __a4 = (int) (long) (a4);					\
 	long __vec = (long) romvec->dest;				\
-	__asm__ __volatile__(						\
-	"dsubu\t$29, 32\n\t"						\
-	"jalr\t%1\n\t"							\
-	"daddu\t$29, 32\n\t"						\
-	"move\t%0, $2"							\
-	: "=r" (__res), "=r" (__vec)					\
-	: "1" (__vec), "r" (__a1), "r" (__a2), "r" (__a3),		\
-	  "r" (__a4)							\
-	: __arc_clobbers);						\
+	__res = call_o32(__vec, O32_STK, __a1, __a2, __a3, __a4);	\
 	__res;								\
 })
 
-#define ARC_CALL5(dest, a1, a2, a3, a4, a5)					\
+#define ARC_CALL5(dest, a1, a2, a3, a4, a5)				\
 ({	long __res;							\
-	register signed int __a1 __asm__("$4") = (int) (long) (a1);	\
-	register signed int __a2 __asm__("$5") = (int) (long) (a2);	\
-	register signed int __a3 __asm__("$6") = (int) (long) (a3);	\
-	register signed int __a4 __asm__("$7") = (int) (long) (a4);	\
-	register signed int __a5 = (int) (long) (a5);			\
+	int  __a1 = (int) (long) (a1);					\
+	int  __a2 = (int) (long) (a2);					\
+	int  __a3 = (int) (long) (a3);					\
+	int  __a4 = (int) (long) (a4);					\
+	int  __a5 = (int) (long) (a5);					\
 	long __vec = (long) romvec->dest;				\
-	__asm__ __volatile__(						\
-	"dsubu\t$29, 32\n\t"						\
-	"sw\t%7, 16($29)\n\t"						\
-	"jalr\t%1\n\t"							\
-	"daddu\t$29, 32\n\t"						\
-	"move\t%0, $2"							\
-	: "=r" (__res), "=r" (__vec)					\
-	: "1" (__vec),							\
-	  "r" (__a1), "r" (__a2), "r" (__a3), "r" (__a4),		\
-	  "r" (__a5)							\
-	: __arc_clobbers);						\
+	__res = call_o32(__vec, O32_STK, __a1, __a2, __a3, __a4, __a5);	\
 	__res;								\
 })
 
diff --git a/arch/mips/include/asm/sn/agent.h b/arch/mips/include/asm/sn/agent.h
index e33d09293019..7e9b3271737a 100644
--- a/arch/mips/include/asm/sn/agent.h
+++ b/arch/mips/include/asm/sn/agent.h
@@ -26,7 +26,7 @@
 
 #if defined(CONFIG_SGI_IP27)
 #define HUB_NIC_ADDR(_cpuid)						   \
-	REMOTE_HUB_ADDR(COMPACT_TO_NASID_NODEID(cpu_to_node(_cpuid)),	    \
+	REMOTE_HUB_ADDR(cpu_to_node(_cpuid),				   \
 		MD_MLAN_CTL)
 #endif
 
diff --git a/arch/mips/include/asm/sn/arch.h b/arch/mips/include/asm/sn/arch.h
index 3f1fb1454749..f7d3273d9599 100644
--- a/arch/mips/include/asm/sn/arch.h
+++ b/arch/mips/include/asm/sn/arch.h
@@ -19,44 +19,13 @@
 
 #define cputonasid(cpu)		(sn_cpu_info[(cpu)].p_nasid)
 #define cputoslice(cpu)		(sn_cpu_info[(cpu)].p_slice)
-#define makespnum(_nasid, _slice)					\
-		(((_nasid) << CPUS_PER_NODE_SHFT) | (_slice))
 
 #define INVALID_NASID		(nasid_t)-1
-#define INVALID_CNODEID		(cnodeid_t)-1
 #define INVALID_PNODEID		(pnodeid_t)-1
 #define INVALID_MODULE		(moduleid_t)-1
 #define INVALID_PARTID		(partid_t)-1
 
 extern nasid_t get_nasid(void);
-extern cnodeid_t get_cpu_cnode(cpuid_t);
 extern int get_cpu_slice(cpuid_t);
 
-/*
- * NO ONE should access these arrays directly.	The only reason we refer to
- * them here is to avoid the procedure call that would be required in the
- * macros below.  (Really want private data members here :-)
- */
-extern cnodeid_t nasid_to_compact_node[MAX_NASIDS];
-extern nasid_t compact_to_nasid_node[MAX_COMPACT_NODES];
-
-/*
- * These macros are used by various parts of the kernel to convert
- * between the three different kinds of node numbering.	  At least some
- * of them may change to procedure calls in the future, but the macros
- * will continue to work.  Don't use the arrays above directly.
- */
-
-#define NASID_TO_REGION(nnode)		\
-    ((nnode) >> \
-     (is_fine_dirmode() ? NASID_TO_FINEREG_SHFT : NASID_TO_COARSEREG_SHFT))
-
-extern cnodeid_t nasid_to_compact_node[MAX_NASIDS];
-extern nasid_t compact_to_nasid_node[MAX_COMPACT_NODES];
-extern cnodeid_t cpuid_to_compact_node[MAXCPUS];
-
-#define NASID_TO_COMPACT_NODEID(nnode)	(nasid_to_compact_node[nnode])
-#define COMPACT_TO_NASID_NODEID(cnode)	(compact_to_nasid_node[cnode])
-#define CPUID_TO_COMPACT_NODEID(cpu)	(cpuid_to_compact_node[(cpu)])
-
 #endif /* _ASM_SN_ARCH_H */
diff --git a/arch/mips/include/asm/sn/gda.h b/arch/mips/include/asm/sn/gda.h
index 85fa1b5f639d..d52f81620661 100644
--- a/arch/mips/include/asm/sn/gda.h
+++ b/arch/mips/include/asm/sn/gda.h
@@ -60,9 +60,7 @@ typedef struct gda {
 				/* Pointer to a mask of nodes with copies
 				 * of the kernel. */
 	char	g_padding[56];	/* pad out to 128 bytes */
-	nasid_t g_nasidtable[MAX_COMPACT_NODES]; /* NASID of each node,
-						  * indexed by cnodeid.
-						  */
+	nasid_t g_nasidtable[MAX_NUMNODES]; /* NASID of each node */
 } gda_t;
 
 #define GDA ((gda_t*) GDA_ADDR(get_nasid()))
diff --git a/arch/mips/include/asm/sn/hub.h b/arch/mips/include/asm/sn/hub.h
index 338f7eed74f1..45878fbefbae 100644
--- a/arch/mips/include/asm/sn/hub.h
+++ b/arch/mips/include/asm/sn/hub.h
@@ -10,8 +10,8 @@
 #include <asm/xtalk/xtalk.h>
 
 /* ip27-hubio.c */
-extern unsigned long hub_pio_map(cnodeid_t cnode, xwidgetnum_t widget,
+extern unsigned long hub_pio_map(nasid_t nasid, xwidgetnum_t widget,
 			  unsigned long xtalk_addr, size_t size);
-extern void hub_pio_init(cnodeid_t cnode);
+extern void hub_pio_init(nasid_t nasid);
 
 #endif /* __ASM_SN_HUB_H */
diff --git a/arch/mips/include/asm/sn/ioc3.h b/arch/mips/include/asm/sn/ioc3.h
index a947eed48fee..78ef760ddde4 100644
--- a/arch/mips/include/asm/sn/ioc3.h
+++ b/arch/mips/include/asm/sn/ioc3.h
@@ -590,4 +590,13 @@ struct ioc3_etxd {
 
 #define MIDR_DATA_MASK		0x0000ffff
 
+/* subsystem IDs supplied by card detection in pci-xtalk-bridge */
+#define	IOC3_SUBSYS_IP27_BASEIO6G	0xc300
+#define	IOC3_SUBSYS_IP27_MIO		0xc301
+#define	IOC3_SUBSYS_IP27_BASEIO		0xc302
+#define	IOC3_SUBSYS_IP29_SYSBOARD	0xc303
+#define	IOC3_SUBSYS_IP30_SYSBOARD	0xc304
+#define	IOC3_SUBSYS_MENET		0xc305
+#define	IOC3_SUBSYS_MENET4		0xc306
+
 #endif /* MIPS_SN_IOC3_H */
diff --git a/arch/mips/include/asm/sn/mapped_kernel.h b/arch/mips/include/asm/sn/mapped_kernel.h
index 2f3efa91c16e..3f1049807018 100644
--- a/arch/mips/include/asm/sn/mapped_kernel.h
+++ b/arch/mips/include/asm/sn/mapped_kernel.h
@@ -37,10 +37,10 @@
 
 #define MAPPED_KERN_RO_TO_PHYS(x) \
 				((unsigned long)MAPPED_ADDR_RO_TO_PHYS(x) | \
-				MAPPED_KERN_RO_PHYSBASE(get_compact_nodeid()))
+				MAPPED_KERN_RO_PHYSBASE(get_nasid()))
 #define MAPPED_KERN_RW_TO_PHYS(x) \
 				((unsigned long)MAPPED_ADDR_RW_TO_PHYS(x) | \
-				MAPPED_KERN_RW_PHYSBASE(get_compact_nodeid()))
+				MAPPED_KERN_RW_PHYSBASE(get_nasid()))
 
 #else /* CONFIG_MAPPED_KERNEL */
 
diff --git a/arch/mips/include/asm/sn/sn0/arch.h b/arch/mips/include/asm/sn/sn0/arch.h
index 425a67e6a947..12f4c4649ff0 100644
--- a/arch/mips/include/asm/sn/sn0/arch.h
+++ b/arch/mips/include/asm/sn/sn0/arch.h
@@ -12,25 +12,11 @@
 #define _ASM_SN_SN0_ARCH_H
 
 
-#ifndef SN0XXL	/* 128 cpu SMP max */
-/*
- * This is the maximum number of nodes that can be part of a kernel.
- * Effectively, it's the maximum number of compact node ids (cnodeid_t).
- */
-#define MAX_COMPACT_NODES	64
-
 /*
  * MAXCPUS refers to the maximum number of CPUs in a single kernel.
  * This is not necessarily the same as MAXNODES * CPUS_PER_NODE
  */
-#define MAXCPUS			128
-
-#else /* SN0XXL system */
-
-#define MAX_COMPACT_NODES	128
-#define MAXCPUS			256
-
-#endif /* SN0XXL */
+#define MAXCPUS			(MAX_NUMNODES * CPUS_PER_NODE)
 
 /*
  * This is the maximum number of NASIDS that can be present in a system.
@@ -66,7 +52,5 @@
 #define SLOT_MIN_MEM_SIZE	(32*1024*1024)
 
 #define CPUS_PER_NODE		2	/* CPUs on a single hub */
-#define CPUS_PER_NODE_SHFT	1	/* Bits to shift in the node number */
-#define CPUS_PER_SUBNODE	2	/* CPUs on a single hub PI */
 
 #endif /* _ASM_SN_SN0_ARCH_H */
diff --git a/arch/mips/include/asm/sn/sn_private.h b/arch/mips/include/asm/sn/sn_private.h
index f09ba846c644..63a2c30d81c6 100644
--- a/arch/mips/include/asm/sn/sn_private.h
+++ b/arch/mips/include/asm/sn/sn_private.h
@@ -7,14 +7,13 @@
 extern nasid_t master_nasid;
 
 extern void cpu_node_probe(void);
-extern cnodeid_t get_compact_nodeid(void);
-extern void hub_rtc_init(cnodeid_t);
+extern void hub_rtc_init(nasid_t nasid);
 extern void cpu_time_init(void);
 extern void per_cpu_init(void);
 extern void install_cpu_nmi_handler(int slice);
 extern void install_ipi(void);
 extern void setup_replication_mask(void);
 extern void replicate_kernel_text(void);
-extern unsigned long node_getfirstfree(cnodeid_t);
+extern unsigned long node_getfirstfree(nasid_t nasid);
 
 #endif /* __ASM_SN_SN_PRIVATE_H */
diff --git a/arch/mips/include/asm/sn/types.h b/arch/mips/include/asm/sn/types.h
index 6d24d4e8b9ed..203c927e84d1 100644
--- a/arch/mips/include/asm/sn/types.h
+++ b/arch/mips/include/asm/sn/types.h
@@ -12,13 +12,9 @@
 #include <linux/types.h>
 
 typedef unsigned long	cpuid_t;
-typedef unsigned long	cnodemask_t;
 typedef signed short	nasid_t;	/* node id in numa-as-id space */
-typedef signed short	cnodeid_t;	/* node id in compact-id space */
 typedef signed char	partid_t;	/* partition ID type */
 typedef signed short	moduleid_t;	/* user-visible module number type */
-typedef signed short	cmoduleid_t;	/* kernel compact module id type */
-typedef unsigned char	clusterid_t;	/* Clusterid of the cell */
 
 typedef dev_t		vertex_hdl_t;	/* hardware graph vertex handle */
 
diff --git a/arch/mips/include/asm/string.h b/arch/mips/include/asm/string.h
index 29030cb398ee..1de3bbce8e88 100644
--- a/arch/mips/include/asm/string.h
+++ b/arch/mips/include/asm/string.h
@@ -10,127 +10,6 @@
 #ifndef _ASM_STRING_H
 #define _ASM_STRING_H
 
-
-/*
- * Most of the inline functions are rather naive implementations so I just
- * didn't bother updating them for 64-bit ...
- */
-#ifdef CONFIG_32BIT
-
-#ifndef IN_STRING_C
-
-#define __HAVE_ARCH_STRCPY
-static __inline__ char *strcpy(char *__dest, __const__ char *__src)
-{
-  char *__xdest = __dest;
-
-  __asm__ __volatile__(
-	".set\tnoreorder\n\t"
-	".set\tnoat\n"
-	"1:\tlbu\t$1,(%1)\n\t"
-	"addiu\t%1,1\n\t"
-	"sb\t$1,(%0)\n\t"
-	"bnez\t$1,1b\n\t"
-	"addiu\t%0,1\n\t"
-	".set\tat\n\t"
-	".set\treorder"
-	: "=r" (__dest), "=r" (__src)
-	: "0" (__dest), "1" (__src)
-	: "memory");
-
-  return __xdest;
-}
-
-#define __HAVE_ARCH_STRNCPY
-static __inline__ char *strncpy(char *__dest, __const__ char *__src, size_t __n)
-{
-  char *__xdest = __dest;
-
-  if (__n == 0)
-    return __xdest;
-
-  __asm__ __volatile__(
-	".set\tnoreorder\n\t"
-	".set\tnoat\n"
-	"1:\tlbu\t$1,(%1)\n\t"
-	"subu\t%2,1\n\t"
-	"sb\t$1,(%0)\n\t"
-	"beqz\t$1,2f\n\t"
-	"addiu\t%0,1\n\t"
-	"bnez\t%2,1b\n\t"
-	"addiu\t%1,1\n"
-	"2:\n\t"
-	".set\tat\n\t"
-	".set\treorder"
-	: "=r" (__dest), "=r" (__src), "=r" (__n)
-	: "0" (__dest), "1" (__src), "2" (__n)
-	: "memory");
-
-  return __xdest;
-}
-
-#define __HAVE_ARCH_STRCMP
-static __inline__ int strcmp(__const__ char *__cs, __const__ char *__ct)
-{
-  int __res;
-
-  __asm__ __volatile__(
-	".set\tnoreorder\n\t"
-	".set\tnoat\n\t"
-	"lbu\t%2,(%0)\n"
-	"1:\tlbu\t$1,(%1)\n\t"
-	"addiu\t%0,1\n\t"
-	"bne\t$1,%2,2f\n\t"
-	"addiu\t%1,1\n\t"
-	"bnez\t%2,1b\n\t"
-	"lbu\t%2,(%0)\n\t"
-#if defined(CONFIG_CPU_R3000)
-	"nop\n\t"
-#endif
-	"move\t%2,$1\n"
-	"2:\tsubu\t%2,$1\n"
-	"3:\t.set\tat\n\t"
-	".set\treorder"
-	: "=r" (__cs), "=r" (__ct), "=r" (__res)
-	: "0" (__cs), "1" (__ct));
-
-  return __res;
-}
-
-#endif /* !defined(IN_STRING_C) */
-
-#define __HAVE_ARCH_STRNCMP
-static __inline__ int
-strncmp(__const__ char *__cs, __const__ char *__ct, size_t __count)
-{
-	int __res;
-
-	__asm__ __volatile__(
-	".set\tnoreorder\n\t"
-	".set\tnoat\n"
-	"1:\tlbu\t%3,(%0)\n\t"
-	"beqz\t%2,2f\n\t"
-	"lbu\t$1,(%1)\n\t"
-	"subu\t%2,1\n\t"
-	"bne\t$1,%3,3f\n\t"
-	"addiu\t%0,1\n\t"
-	"bnez\t%3,1b\n\t"
-	"addiu\t%1,1\n"
-	"2:\n\t"
-#if defined(CONFIG_CPU_R3000)
-	"nop\n\t"
-#endif
-	"move\t%3,$1\n"
-	"3:\tsubu\t%3,$1\n\t"
-	".set\tat\n\t"
-	".set\treorder"
-	: "=r" (__cs), "=r" (__ct), "=r" (__count), "=r" (__res)
-	: "0" (__cs), "1" (__ct), "2" (__count));
-
-	return __res;
-}
-#endif /* CONFIG_32BIT */
-
 #define __HAVE_ARCH_MEMSET
 extern void *memset(void *__s, int __c, size_t __count);
 
diff --git a/arch/mips/include/asm/sync.h b/arch/mips/include/asm/sync.h
new file mode 100644
index 000000000000..7c6a1095f556
--- /dev/null
+++ b/arch/mips/include/asm/sync.h
@@ -0,0 +1,207 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __MIPS_ASM_SYNC_H__
+#define __MIPS_ASM_SYNC_H__
+
+/*
+ * sync types are defined by the MIPS64 Instruction Set documentation in Volume
+ * II-A of the MIPS Architecture Reference Manual, which can be found here:
+ *
+ *   https://www.mips.com/?do-download=the-mips64-instruction-set-v6-06
+ *
+ * Two types of barrier are provided:
+ *
+ *   1) Completion barriers, which ensure that a memory operation has actually
+ *      completed & often involve stalling the CPU pipeline to do so.
+ *
+ *   2) Ordering barriers, which only ensure that affected memory operations
+ *      won't be reordered in the CPU pipeline in a manner that violates the
+ *      restrictions imposed by the barrier.
+ *
+ * Ordering barriers can be more efficient than completion barriers, since:
+ *
+ *   a) Ordering barriers only require memory access instructions which preceed
+ *      them in program order (older instructions) to reach a point in the
+ *      load/store datapath beyond which reordering is not possible before
+ *      allowing memory access instructions which follow them (younger
+ *      instructions) to be performed.  That is, older instructions don't
+ *      actually need to complete - they just need to get far enough that all
+ *      other coherent CPUs will observe their completion before they observe
+ *      the effects of younger instructions.
+ *
+ *   b) Multiple variants of ordering barrier are provided which allow the
+ *      effects to be restricted to different combinations of older or younger
+ *      loads or stores. By way of example, if we only care that stores older
+ *      than a barrier are observed prior to stores that are younger than a
+ *      barrier & don't care about the ordering of loads then the 'wmb'
+ *      ordering barrier can be used. Limiting the barrier's effects to stores
+ *      allows loads to continue unaffected & potentially allows the CPU to
+ *      make progress faster than if younger loads had to wait for older stores
+ *      to complete.
+ */
+
+/*
+ * No sync instruction at all; used to allow code to nullify the effect of the
+ * __SYNC() macro without needing lots of #ifdefery.
+ */
+#define __SYNC_none	-1
+
+/*
+ * A full completion barrier; all memory accesses appearing prior to this sync
+ * instruction in program order must complete before any memory accesses
+ * appearing after this sync instruction in program order.
+ */
+#define __SYNC_full	0x00
+
+/*
+ * For now we use a full completion barrier to implement all sync types, until
+ * we're satisfied that lightweight ordering barriers defined by MIPSr6 are
+ * sufficient to uphold our desired memory model.
+ */
+#define __SYNC_aq	__SYNC_full
+#define __SYNC_rl	__SYNC_full
+#define __SYNC_mb	__SYNC_full
+
+/*
+ * ...except on Cavium Octeon CPUs, which have been using the 'wmb' ordering
+ * barrier since 2010 & omit 'rmb' barriers because the CPUs don't perform
+ * speculative reads.
+ */
+#ifdef CONFIG_CPU_CAVIUM_OCTEON
+# define __SYNC_rmb	__SYNC_none
+# define __SYNC_wmb	0x04
+#else
+# define __SYNC_rmb	__SYNC_full
+# define __SYNC_wmb	__SYNC_full
+#endif
+
+/*
+ * A GINV sync is a little different; it doesn't relate directly to loads or
+ * stores, but instead causes synchronization of an icache or TLB global
+ * invalidation operation triggered by the ginvi or ginvt instructions
+ * respectively. In cases where we need to know that a ginvi or ginvt operation
+ * has been performed by all coherent CPUs, we must issue a sync instruction of
+ * this type. Once this instruction graduates all coherent CPUs will have
+ * observed the invalidation.
+ */
+#define __SYNC_ginv	0x14
+
+/* Trivial; indicate that we always need this sync instruction. */
+#define __SYNC_always	(1 << 0)
+
+/*
+ * Indicate that we need this sync instruction only on systems with weakly
+ * ordered memory access. In general this is most MIPS systems, but there are
+ * exceptions which provide strongly ordered memory.
+ */
+#ifdef CONFIG_WEAK_ORDERING
+# define __SYNC_weak_ordering	(1 << 1)
+#else
+# define __SYNC_weak_ordering	0
+#endif
+
+/*
+ * Indicate that we need this sync instruction only on systems where LL/SC
+ * don't implicitly provide a memory barrier. In general this is most MIPS
+ * systems.
+ */
+#ifdef CONFIG_WEAK_REORDERING_BEYOND_LLSC
+# define __SYNC_weak_llsc	(1 << 2)
+#else
+# define __SYNC_weak_llsc	0
+#endif
+
+/*
+ * Some Loongson 3 CPUs have a bug wherein execution of a memory access (load,
+ * store or prefetch) in between an LL & SC can cause the SC instruction to
+ * erroneously succeed, breaking atomicity. Whilst it's unusual to write code
+ * containing such sequences, this bug bites harder than we might otherwise
+ * expect due to reordering & speculation:
+ *
+ * 1) A memory access appearing prior to the LL in program order may actually
+ *    be executed after the LL - this is the reordering case.
+ *
+ *    In order to avoid this we need to place a memory barrier (ie. a SYNC
+ *    instruction) prior to every LL instruction, in between it and any earlier
+ *    memory access instructions.
+ *
+ *    This reordering case is fixed by 3A R2 CPUs, ie. 3A2000 models and later.
+ *
+ * 2) If a conditional branch exists between an LL & SC with a target outside
+ *    of the LL-SC loop, for example an exit upon value mismatch in cmpxchg()
+ *    or similar, then misprediction of the branch may allow speculative
+ *    execution of memory accesses from outside of the LL-SC loop.
+ *
+ *    In order to avoid this we need a memory barrier (ie. a SYNC instruction)
+ *    at each affected branch target.
+ *
+ *    This case affects all current Loongson 3 CPUs.
+ *
+ * The above described cases cause an error in the cache coherence protocol;
+ * such that the Invalidate of a competing LL-SC goes 'missing' and SC
+ * erroneously observes its core still has Exclusive state and lets the SC
+ * proceed.
+ *
+ * Therefore the error only occurs on SMP systems.
+ */
+#ifdef CONFIG_CPU_LOONGSON3_WORKAROUNDS
+# define __SYNC_loongson3_war	(1 << 31)
+#else
+# define __SYNC_loongson3_war	0
+#endif
+
+/*
+ * Some Cavium Octeon CPUs suffer from a bug that causes a single wmb ordering
+ * barrier to be ineffective, requiring the use of 2 in sequence to provide an
+ * effective barrier as noted by commit 6b07d38aaa52 ("MIPS: Octeon: Use
+ * optimized memory barrier primitives."). Here we specify that the affected
+ * sync instructions should be emitted twice.
+ */
+#ifdef CONFIG_CPU_CAVIUM_OCTEON
+# define __SYNC_rpt(type)	(1 + (type == __SYNC_wmb))
+#else
+# define __SYNC_rpt(type)	1
+#endif
+
+/*
+ * The main event. Here we actually emit a sync instruction of a given type, if
+ * reason is non-zero.
+ *
+ * In future we have the option of emitting entries in a fixups-style table
+ * here that would allow us to opportunistically remove some sync instructions
+ * when we detect at runtime that we're running on a CPU that doesn't need
+ * them.
+ */
+#ifdef CONFIG_CPU_HAS_SYNC
+# define ____SYNC(_type, _reason, _else)			\
+	.if	(( _type ) != -1) && ( _reason );		\
+	.set	push;						\
+	.set	MIPS_ISA_LEVEL_RAW;				\
+	.rept	__SYNC_rpt(_type);				\
+	sync	_type;						\
+	.endr;							\
+	.set	pop;						\
+	.else;							\
+	_else;							\
+	.endif
+#else
+# define ____SYNC(_type, _reason, _else)
+#endif
+
+/*
+ * Preprocessor magic to expand macros used as arguments before we insert them
+ * into assembly code.
+ */
+#ifdef __ASSEMBLY__
+# define ___SYNC(type, reason, else)				\
+	____SYNC(type, reason, else)
+#else
+# define ___SYNC(type, reason, else)				\
+	__stringify(____SYNC(type, reason, else))
+#endif
+
+#define __SYNC(type, reason)					\
+	___SYNC(__SYNC_##type, __SYNC_##reason, )
+#define __SYNC_ELSE(type, reason, else)				\
+	___SYNC(__SYNC_##type, __SYNC_##reason, else)
+
+#endif /* __MIPS_ASM_SYNC_H__ */
diff --git a/arch/mips/include/asm/unroll.h b/arch/mips/include/asm/unroll.h
new file mode 100644
index 000000000000..c628747d4ecd
--- /dev/null
+++ b/arch/mips/include/asm/unroll.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_UNROLL_H__
+#define __ASM_UNROLL_H__
+
+/*
+ * Explicitly unroll a loop, for use in cases where doing so is performance
+ * critical.
+ *
+ * Ideally we'd rely upon the compiler to provide this but there's no commonly
+ * available means to do so. For example GCC's "#pragma GCC unroll"
+ * functionality would be ideal but is only available from GCC 8 onwards. Using
+ * -funroll-loops is an option but GCC tends to make poor choices when
+ * compiling our string functions. -funroll-all-loops leads to massive code
+ * bloat, even if only applied to the string functions.
+ */
+#define unroll(times, fn, ...) do {				\
+	extern void bad_unroll(void)				\
+		__compiletime_error("Unsupported unroll");	\
+								\
+	/*							\
+	 * We can't unroll if the number of iterations isn't	\
+	 * compile-time constant. Unfortunately GCC versions	\
+	 * up until 4.6 tend to miss obvious constants & cause	\
+	 * this check to fail, even though they go on to	\
+	 * generate reasonable code for the switch statement,	\
+	 * so we skip the sanity check for those compilers.	\
+	 */							\
+	BUILD_BUG_ON((CONFIG_GCC_VERSION >= 40700 ||		\
+		      CONFIG_CLANG_VERSION >= 80000) &&		\
+		     !__builtin_constant_p(times));		\
+								\
+	switch (times) {					\
+	case 32: fn(__VA_ARGS__); /* fall through */		\
+	case 31: fn(__VA_ARGS__); /* fall through */		\
+	case 30: fn(__VA_ARGS__); /* fall through */		\
+	case 29: fn(__VA_ARGS__); /* fall through */		\
+	case 28: fn(__VA_ARGS__); /* fall through */		\
+	case 27: fn(__VA_ARGS__); /* fall through */		\
+	case 26: fn(__VA_ARGS__); /* fall through */		\
+	case 25: fn(__VA_ARGS__); /* fall through */		\
+	case 24: fn(__VA_ARGS__); /* fall through */		\
+	case 23: fn(__VA_ARGS__); /* fall through */		\
+	case 22: fn(__VA_ARGS__); /* fall through */		\
+	case 21: fn(__VA_ARGS__); /* fall through */		\
+	case 20: fn(__VA_ARGS__); /* fall through */		\
+	case 19: fn(__VA_ARGS__); /* fall through */		\
+	case 18: fn(__VA_ARGS__); /* fall through */		\
+	case 17: fn(__VA_ARGS__); /* fall through */		\
+	case 16: fn(__VA_ARGS__); /* fall through */		\
+	case 15: fn(__VA_ARGS__); /* fall through */		\
+	case 14: fn(__VA_ARGS__); /* fall through */		\
+	case 13: fn(__VA_ARGS__); /* fall through */		\
+	case 12: fn(__VA_ARGS__); /* fall through */		\
+	case 11: fn(__VA_ARGS__); /* fall through */		\
+	case 10: fn(__VA_ARGS__); /* fall through */		\
+	case 9: fn(__VA_ARGS__); /* fall through */		\
+	case 8: fn(__VA_ARGS__); /* fall through */		\
+	case 7: fn(__VA_ARGS__); /* fall through */		\
+	case 6: fn(__VA_ARGS__); /* fall through */		\
+	case 5: fn(__VA_ARGS__); /* fall through */		\
+	case 4: fn(__VA_ARGS__); /* fall through */		\
+	case 3: fn(__VA_ARGS__); /* fall through */		\
+	case 2: fn(__VA_ARGS__); /* fall through */		\
+	case 1: fn(__VA_ARGS__); /* fall through */		\
+	case 0: break;						\
+								\
+	default:						\
+		/*						\
+		 * Either the iteration count is unreasonable	\
+		 * or we need to add more cases above.		\
+		 */						\
+		bad_unroll();					\
+		break;						\
+	}							\
+} while (0)
+
+#endif /* __ASM_UNROLL_H__ */
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 89b07ea8d249..d6e97df51cfb 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -80,7 +80,7 @@ obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_PROC_FS)		+= proc.o
 obj-$(CONFIG_MAGIC_SYSRQ)	+= sysrq.o
 
-obj-$(CONFIG_64BIT)		+= cpu-bugs64.o
+obj-$(CONFIG_CPU_R4X00_BUGS64)	+= r4k-bugs64.o
 
 obj-$(CONFIG_I8253)		+= i8253.o
 
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index f521cbf934e7..c54332697673 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -608,7 +608,7 @@ static int set_ftlb_enable(struct cpuinfo_mips *c, enum ftlb_flags flags)
 		if (!(flags & FTLB_EN))
 			return 1;
 		return 0;
-	case CPU_LOONGSON3:
+	case CPU_LOONGSON64:
 		/* Flush ITLB, DTLB, VTLB and FTLB */
 		write_c0_diag(LOONGSON_DIAG_ITLB | LOONGSON_DIAG_DTLB |
 			      LOONGSON_DIAG_VTLB | LOONGSON_DIAG_FTLB);
@@ -1526,24 +1526,24 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 			     MIPS_CPU_LLSC | MIPS_CPU_BP_GHIST;
 		c->tlbsize = 64;
 		break;
-	case PRID_IMP_LOONGSON_64:  /* Loongson-2/3 */
+	case PRID_IMP_LOONGSON_64C:  /* Loongson-2/3 */
 		switch (c->processor_id & PRID_REV_MASK) {
 		case PRID_REV_LOONGSON2E:
-			c->cputype = CPU_LOONGSON2;
+			c->cputype = CPU_LOONGSON2EF;
 			__cpu_name[cpu] = "ICT Loongson-2";
 			set_elf_platform(cpu, "loongson2e");
 			set_isa(c, MIPS_CPU_ISA_III);
 			c->fpu_msk31 |= FPU_CSR_CONDX;
 			break;
 		case PRID_REV_LOONGSON2F:
-			c->cputype = CPU_LOONGSON2;
+			c->cputype = CPU_LOONGSON2EF;
 			__cpu_name[cpu] = "ICT Loongson-2";
 			set_elf_platform(cpu, "loongson2f");
 			set_isa(c, MIPS_CPU_ISA_III);
 			c->fpu_msk31 |= FPU_CSR_CONDX;
 			break;
 		case PRID_REV_LOONGSON3A_R1:
-			c->cputype = CPU_LOONGSON3;
+			c->cputype = CPU_LOONGSON64;
 			__cpu_name[cpu] = "ICT Loongson-3";
 			set_elf_platform(cpu, "loongson3a");
 			set_isa(c, MIPS_CPU_ISA_M64R1);
@@ -1552,7 +1552,7 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 			break;
 		case PRID_REV_LOONGSON3B_R1:
 		case PRID_REV_LOONGSON3B_R2:
-			c->cputype = CPU_LOONGSON3;
+			c->cputype = CPU_LOONGSON64;
 			__cpu_name[cpu] = "ICT Loongson-3";
 			set_elf_platform(cpu, "loongson3b");
 			set_isa(c, MIPS_CPU_ISA_M64R1);
@@ -1565,12 +1565,13 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 			     MIPS_CPU_FPU | MIPS_CPU_LLSC |
 			     MIPS_CPU_32FPR;
 		c->tlbsize = 64;
+		set_cpu_asid_mask(c, MIPS_ENTRYHI_ASID);
 		c->writecombine = _CACHE_UNCACHED_ACCELERATED;
 		break;
 	case PRID_IMP_LOONGSON_32:  /* Loongson-1 */
 		decode_configs(c);
 
-		c->cputype = CPU_LOONGSON1;
+		c->cputype = CPU_LOONGSON32;
 
 		switch (c->processor_id & PRID_REV_MASK) {
 		case PRID_REV_LOONGSON1B:
@@ -1903,18 +1904,18 @@ platform:
 static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 {
 	switch (c->processor_id & PRID_IMP_MASK) {
-	case PRID_IMP_LOONGSON_64:  /* Loongson-2/3 */
+	case PRID_IMP_LOONGSON_64C:  /* Loongson-2/3 */
 		switch (c->processor_id & PRID_REV_MASK) {
 		case PRID_REV_LOONGSON3A_R2_0:
 		case PRID_REV_LOONGSON3A_R2_1:
-			c->cputype = CPU_LOONGSON3;
+			c->cputype = CPU_LOONGSON64;
 			__cpu_name[cpu] = "ICT Loongson-3";
 			set_elf_platform(cpu, "loongson3a");
 			set_isa(c, MIPS_CPU_ISA_M64R2);
 			break;
 		case PRID_REV_LOONGSON3A_R3_0:
 		case PRID_REV_LOONGSON3A_R3_1:
-			c->cputype = CPU_LOONGSON3;
+			c->cputype = CPU_LOONGSON64;
 			__cpu_name[cpu] = "ICT Loongson-3";
 			set_elf_platform(cpu, "loongson3a");
 			set_isa(c, MIPS_CPU_ISA_M64R2);
@@ -1927,6 +1928,17 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 		c->ases |= (MIPS_ASE_LOONGSON_MMI | MIPS_ASE_LOONGSON_CAM |
 			MIPS_ASE_LOONGSON_EXT | MIPS_ASE_LOONGSON_EXT2);
 		break;
+	case PRID_IMP_LOONGSON_64G:
+		c->cputype = CPU_LOONGSON64;
+		__cpu_name[cpu] = "ICT Loongson-3";
+		set_elf_platform(cpu, "loongson3a");
+		set_isa(c, MIPS_CPU_ISA_M64R2);
+		decode_configs(c);
+		c->options |= MIPS_CPU_FTLB | MIPS_CPU_TLBINV | MIPS_CPU_LDPTE;
+		c->writecombine = _CACHE_UNCACHED_ACCELERATED;
+		c->ases |= (MIPS_ASE_LOONGSON_MMI | MIPS_ASE_LOONGSON_CAM |
+			MIPS_ASE_LOONGSON_EXT | MIPS_ASE_LOONGSON_EXT2);
+		break;
 	default:
 		panic("Unknown Loongson Processor ID!");
 		break;
@@ -1965,13 +1977,30 @@ static inline void cpu_probe_ingenic(struct cpuinfo_mips *c, unsigned int cpu)
 		break;
 	}
 
+	switch (c->processor_id & PRID_COMP_MASK) {
 	/*
-	 * The config0 register in the Xburst CPUs with a processor ID of
+	 * The config0 register in the XBurst CPUs with a processor ID of
+	 * PRID_COMP_INGENIC_D1 has an abandoned huge page tlb mode, this
+	 * mode is not compatible with the MIPS standard, it will cause
+	 * tlbmiss and into an infinite loop (line 21 in the tlb-funcs.S)
+	 * when starting the init process. After chip reset, the default
+	 * is HPTLB mode, Write 0xa9000000 to cp0 register 5 sel 4 to
+	 * switch back to VTLB mode to prevent getting stuck.
+	 */
+	case PRID_COMP_INGENIC_D1:
+		write_c0_page_ctrl(XBURST_PAGECTRL_HPTLB_DIS);
+		break;
+	/*
+	 * The config0 register in the XBurst CPUs with a processor ID of
 	 * PRID_COMP_INGENIC_D0 report themselves as MIPS32r2 compatible,
 	 * but they don't actually support this ISA.
 	 */
-	if ((c->processor_id & PRID_COMP_MASK) == PRID_COMP_INGENIC_D0)
+	case PRID_COMP_INGENIC_D0:
 		c->isa_level &= ~MIPS_CPU_ISA_M32R2;
+		break;
+	default:
+		break;
+	}
 }
 
 static inline void cpu_probe_netlogic(struct cpuinfo_mips *c, int cpu)
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index efde27c99414..0a43c9125267 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -18,6 +18,7 @@
 #include <asm/fpregdef.h>
 #include <asm/mipsregs.h>
 #include <asm/stackframe.h>
+#include <asm/sync.h>
 #include <asm/war.h>
 #include <asm/thread_info.h>
 
@@ -353,8 +354,9 @@ NESTED(ejtag_debug_handler, PT_SIZE, sp)
 
 #ifdef CONFIG_SMP
 1:	PTR_LA	k0, ejtag_debug_buffer_spinlock
-	ll	k0, 0(k0)
-	bnez	k0, 1b
+	__SYNC(full, loongson3_war)
+2:	ll	k0, 0(k0)
+	bnez	k0, 2b
 	PTR_LA	k0, ejtag_debug_buffer_spinlock
 	sc	k0, 0(k0)
 	beqz	k0, 1b
@@ -657,7 +659,7 @@ isrdhwr:
 	.set	pop
 	END(handle_ri_rdhwr)
 
-#ifdef CONFIG_64BIT
+#ifdef CONFIG_CPU_R4X00_BUGS64
 /* A temporary overflow handler used by check_daddi(). */
 
 	__INIT
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index eb2afc0b8db1..37f8e78e2869 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -173,13 +173,14 @@ void __init check_wait(void)
 	case CPU_CAVIUM_OCTEON2:
 	case CPU_CAVIUM_OCTEON3:
 	case CPU_XBURST:
-	case CPU_LOONGSON1:
+	case CPU_LOONGSON32:
 	case CPU_XLR:
 	case CPU_XLP:
 		cpu_wait = r4k_wait;
 		break;
-	case CPU_LOONGSON3:
-		if ((c->processor_id & PRID_REV_MASK) >= PRID_REV_LOONGSON3A_R2_0)
+	case CPU_LOONGSON64:
+		if ((c->processor_id & (PRID_IMP_MASK | PRID_REV_MASK)) >=
+				(PRID_IMP_LOONGSON_64C | PRID_REV_LOONGSON3A_R2_0))
 			cpu_wait = r4k_wait;
 		break;
 
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index a3e2da8391ea..128fc9999c56 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -1623,7 +1623,7 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config)
 			raw_event.cntr_mask =
 				raw_id > 127 ? CNTR_ODD : CNTR_EVEN;
 		break;
-	case CPU_LOONGSON3:
+	case CPU_LOONGSON64:
 		raw_event.cntr_mask = raw_id > 127 ? CNTR_ODD : CNTR_EVEN;
 	break;
 	}
@@ -1764,12 +1764,12 @@ init_hw_perf_events(void)
 		mipspmu.general_event_map = &mipsxxcore_event_map;
 		mipspmu.cache_event_map = &mipsxxcore_cache_map;
 		break;
-	case CPU_LOONGSON1:
+	case CPU_LOONGSON32:
 		mipspmu.name = "mips/loongson1";
 		mipspmu.general_event_map = &mipsxxcore_event_map;
 		mipspmu.cache_event_map = &mipsxxcore_cache_map;
 		break;
-	case CPU_LOONGSON3:
+	case CPU_LOONGSON64:
 		mipspmu.name = "mips/loongson3";
 		mipspmu.general_event_map = &loongson3_event_map;
 		mipspmu.cache_event_map = &loongson3_cache_map;
diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c
index a26f40db15d0..9bf60d7d44d3 100644
--- a/arch/mips/kernel/pm-cps.c
+++ b/arch/mips/kernel/pm-cps.c
@@ -307,7 +307,7 @@ static int cps_gen_flush_fsb(u32 **pp, struct uasm_label **pl,
 	}
 
 	/* Barrier ensuring previous cache invalidates are complete */
-	uasm_i_sync(pp, STYPE_SYNC);
+	uasm_i_sync(pp, __SYNC_full);
 	uasm_i_ehb(pp);
 
 	/* Check whether the pipeline stalled due to the FSB being full */
@@ -397,7 +397,7 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
 
 	if (coupled_coherence) {
 		/* Increment ready_count */
-		uasm_i_sync(&p, STYPE_SYNC_MB);
+		uasm_i_sync(&p, __SYNC_mb);
 		uasm_build_label(&l, p, lbl_incready);
 		uasm_i_ll(&p, t1, 0, r_nc_count);
 		uasm_i_addiu(&p, t2, t1, 1);
@@ -406,7 +406,7 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
 		uasm_i_addiu(&p, t1, t1, 1);
 
 		/* Barrier ensuring all CPUs see the updated r_nc_count value */
-		uasm_i_sync(&p, STYPE_SYNC_MB);
+		uasm_i_sync(&p, __SYNC_mb);
 
 		/*
 		 * If this is the last VPE to become ready for non-coherence
@@ -473,7 +473,7 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
 			      Index_Writeback_Inv_D, lbl_flushdcache);
 
 	/* Barrier ensuring previous cache invalidates are complete */
-	uasm_i_sync(&p, STYPE_SYNC);
+	uasm_i_sync(&p, __SYNC_full);
 	uasm_i_ehb(&p);
 
 	if (mips_cm_revision() < CM_REV_CM3) {
@@ -487,7 +487,7 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
 		uasm_i_lw(&p, t0, 0, r_pcohctl);
 
 		/* Barrier to ensure write to coherence control is complete */
-		uasm_i_sync(&p, STYPE_SYNC);
+		uasm_i_sync(&p, __SYNC_full);
 		uasm_i_ehb(&p);
 	}
 
@@ -534,7 +534,7 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
 		}
 
 		/* Barrier to ensure write to CPC command is complete */
-		uasm_i_sync(&p, STYPE_SYNC);
+		uasm_i_sync(&p, __SYNC_full);
 		uasm_i_ehb(&p);
 	}
 
@@ -572,13 +572,13 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
 	uasm_i_lw(&p, t0, 0, r_pcohctl);
 
 	/* Barrier to ensure write to coherence control is complete */
-	uasm_i_sync(&p, STYPE_SYNC);
+	uasm_i_sync(&p, __SYNC_full);
 	uasm_i_ehb(&p);
 
 	if (coupled_coherence && (state == CPS_PM_NC_WAIT)) {
 		/* Decrement ready_count */
 		uasm_build_label(&l, p, lbl_decready);
-		uasm_i_sync(&p, STYPE_SYNC_MB);
+		uasm_i_sync(&p, __SYNC_mb);
 		uasm_i_ll(&p, t1, 0, r_nc_count);
 		uasm_i_addiu(&p, t2, t1, -1);
 		uasm_i_sc(&p, t2, 0, r_nc_count);
@@ -586,7 +586,7 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
 		uasm_i_andi(&p, v0, t1, (1 << fls(smp_num_siblings)) - 1);
 
 		/* Barrier ensuring all CPUs see the updated r_nc_count value */
-		uasm_i_sync(&p, STYPE_SYNC_MB);
+		uasm_i_sync(&p, __SYNC_mb);
 	}
 
 	if (coupled_coherence && (state == CPS_PM_CLOCK_GATED)) {
@@ -608,7 +608,7 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
 		uasm_build_label(&l, p, lbl_secondary_cont);
 
 		/* Barrier ensuring all CPUs see the updated r_nc_count value */
-		uasm_i_sync(&p, STYPE_SYNC_MB);
+		uasm_i_sync(&p, __SYNC_mb);
 	}
 
 	/* The core is coherent, time to return to C code */
diff --git a/arch/mips/kernel/cpu-bugs64.c b/arch/mips/kernel/r4k-bugs64.c
index 6a7afe7ef4d3..1ff19f1ea5ca 100644
--- a/arch/mips/kernel/cpu-bugs64.c
+++ b/arch/mips/kernel/r4k-bugs64.c
@@ -242,7 +242,7 @@ static __init void check_daddi(void)
 	panic(bug64hit, !DADDI_WAR ? daddiwar : nowar);
 }
 
-int daddiu_bug	= IS_ENABLED(CONFIG_CPU_MIPSR6) ? 0 : -1;
+int daddiu_bug	= -1;
 
 static __init void check_daddiu(void)
 {
@@ -312,14 +312,11 @@ static __init void check_daddiu(void)
 
 void __init check_bugs64_early(void)
 {
-	if (!IS_ENABLED(CONFIG_CPU_MIPSR6)) {
-		check_mult_sh();
-		check_daddiu();
-	}
+	check_mult_sh();
+	check_daddiu();
 }
 
 void __init check_bugs64(void)
 {
-	if (!IS_ENABLED(CONFIG_CPU_MIPSR6))
-		check_daddi();
+	check_daddi();
 }
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 5eec13b8d222..c3d4212b5f1d 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -67,7 +67,9 @@ static char __initdata command_line[COMMAND_LINE_SIZE];
 char __initdata arcs_cmdline[COMMAND_LINE_SIZE];
 
 #ifdef CONFIG_CMDLINE_BOOL
-static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
+static const char builtin_cmdline[] __initconst = CONFIG_CMDLINE;
+#else
+static const char builtin_cmdline[] __initconst = "";
 #endif
 
 /*
@@ -285,7 +287,7 @@ static unsigned long __init init_initrd(void)
  * Initialize the bootmem allocator. It also setup initrd related data
  * if needed.
  */
-#if defined(CONFIG_SGI_IP27) || (defined(CONFIG_CPU_LOONGSON3) && defined(CONFIG_NUMA))
+#if defined(CONFIG_SGI_IP27) || (defined(CONFIG_CPU_LOONGSON64) && defined(CONFIG_NUMA))
 
 static void __init bootmem_init(void)
 {
@@ -538,11 +540,94 @@ static void __init check_kernel_sections_mem(void)
 	}
 }
 
-#define USE_PROM_CMDLINE	IS_ENABLED(CONFIG_MIPS_CMDLINE_FROM_BOOTLOADER)
-#define USE_DTB_CMDLINE		IS_ENABLED(CONFIG_MIPS_CMDLINE_FROM_DTB)
-#define EXTEND_WITH_PROM	IS_ENABLED(CONFIG_MIPS_CMDLINE_DTB_EXTEND)
-#define BUILTIN_EXTEND_WITH_PROM	\
-	IS_ENABLED(CONFIG_MIPS_CMDLINE_BUILTIN_EXTEND)
+static void __init bootcmdline_append(const char *s, size_t max)
+{
+	if (!s[0] || !max)
+		return;
+
+	if (boot_command_line[0])
+		strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
+
+	strlcat(boot_command_line, s, max);
+}
+
+#ifdef CONFIG_OF_EARLY_FLATTREE
+
+static int __init bootcmdline_scan_chosen(unsigned long node, const char *uname,
+					  int depth, void *data)
+{
+	bool *dt_bootargs = data;
+	const char *p;
+	int l;
+
+	if (depth != 1 || !data ||
+	    (strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0))
+		return 0;
+
+	p = of_get_flat_dt_prop(node, "bootargs", &l);
+	if (p != NULL && l > 0) {
+		bootcmdline_append(p, min(l, COMMAND_LINE_SIZE));
+		*dt_bootargs = true;
+	}
+
+	return 1;
+}
+
+#endif /* CONFIG_OF_EARLY_FLATTREE */
+
+static void __init bootcmdline_init(char **cmdline_p)
+{
+	bool dt_bootargs = false;
+
+	/*
+	 * If CMDLINE_OVERRIDE is enabled then initializing the command line is
+	 * trivial - we simply use the built-in command line unconditionally &
+	 * unmodified.
+	 */
+	if (IS_ENABLED(CONFIG_CMDLINE_OVERRIDE)) {
+		strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+		return;
+	}
+
+	/*
+	 * If the user specified a built-in command line &
+	 * MIPS_CMDLINE_BUILTIN_EXTEND, then the built-in command line is
+	 * prepended to arguments from the bootloader or DT so we'll copy them
+	 * to the start of boot_command_line here. Otherwise, empty
+	 * boot_command_line to undo anything early_init_dt_scan_chosen() did.
+	 */
+	if (IS_ENABLED(CONFIG_MIPS_CMDLINE_BUILTIN_EXTEND))
+		strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+	else
+		boot_command_line[0] = 0;
+
+#ifdef CONFIG_OF_EARLY_FLATTREE
+	/*
+	 * If we're configured to take boot arguments from DT, look for those
+	 * now.
+	 */
+	if (IS_ENABLED(CONFIG_MIPS_CMDLINE_FROM_DTB))
+		of_scan_flat_dt(bootcmdline_scan_chosen, &dt_bootargs);
+#endif
+
+	/*
+	 * If we didn't get any arguments from DT (regardless of whether that's
+	 * because we weren't configured to look for them, or because we looked
+	 * & found none) then we'll take arguments from the bootloader.
+	 * plat_mem_setup() should have filled arcs_cmdline with arguments from
+	 * the bootloader.
+	 */
+	if (IS_ENABLED(CONFIG_MIPS_CMDLINE_DTB_EXTEND) || !dt_bootargs)
+		bootcmdline_append(arcs_cmdline, COMMAND_LINE_SIZE);
+
+	/*
+	 * If the user specified a built-in command line & we didn't already
+	 * prepend it, we append it to boot_command_line here.
+	 */
+	if (IS_ENABLED(CONFIG_CMDLINE_BOOL) &&
+	    !IS_ENABLED(CONFIG_MIPS_CMDLINE_BUILTIN_EXTEND))
+		bootcmdline_append(builtin_cmdline, COMMAND_LINE_SIZE);
+}
 
 /*
  * arch_mem_init - initialize memory management subsystem
@@ -570,48 +655,12 @@ static void __init arch_mem_init(char **cmdline_p)
 {
 	extern void plat_mem_setup(void);
 
-	/*
-	 * Initialize boot_command_line to an innocuous but non-empty string in
-	 * order to prevent early_init_dt_scan_chosen() from copying
-	 * CONFIG_CMDLINE into it without our knowledge. We handle
-	 * CONFIG_CMDLINE ourselves below & don't want to duplicate its
-	 * content because repeating arguments can be problematic.
-	 */
-	strlcpy(boot_command_line, " ", COMMAND_LINE_SIZE);
-
 	/* call board setup routine */
 	plat_mem_setup();
 	memblock_set_bottom_up(true);
 
-#if defined(CONFIG_CMDLINE_BOOL) && defined(CONFIG_CMDLINE_OVERRIDE)
-	strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
-#else
-	if ((USE_PROM_CMDLINE && arcs_cmdline[0]) ||
-	    (USE_DTB_CMDLINE && !boot_command_line[0]))
-		strlcpy(boot_command_line, arcs_cmdline, COMMAND_LINE_SIZE);
-
-	if (EXTEND_WITH_PROM && arcs_cmdline[0]) {
-		if (boot_command_line[0])
-			strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
-		strlcat(boot_command_line, arcs_cmdline, COMMAND_LINE_SIZE);
-	}
-
-#if defined(CONFIG_CMDLINE_BOOL)
-	if (builtin_cmdline[0]) {
-		if (boot_command_line[0])
-			strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
-		strlcat(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
-	}
-
-	if (BUILTIN_EXTEND_WITH_PROM && arcs_cmdline[0]) {
-		if (boot_command_line[0])
-			strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
-		strlcat(boot_command_line, arcs_cmdline, COMMAND_LINE_SIZE);
-	}
-#endif
-#endif
+	bootcmdline_init(cmdline_p);
 	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
-
 	*cmdline_p = command_line;
 
 	parse_early_param();
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 712c15de6ab9..9058e9dcf080 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -31,7 +31,6 @@
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/bootinfo.h>
-#include <asm/pmon.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm/mipsregs.h>
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index 3f16f3823031..c333e5788664 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -37,6 +37,7 @@
 #include <asm/signal.h>
 #include <asm/sim.h>
 #include <asm/shmparam.h>
+#include <asm/sync.h>
 #include <asm/sysmips.h>
 #include <asm/switch_to.h>
 
@@ -133,12 +134,12 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new)
 		  [efault] "i" (-EFAULT)
 		: "memory");
 	} else if (cpu_has_llsc) {
-		loongson_llsc_mb();
 		__asm__ __volatile__ (
 		"	.set	push					\n"
 		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
 		"	li	%[err], 0				\n"
 		"1:							\n"
+		"	" __SYNC(full, loongson3_war) "			\n"
 		user_ll("%[old]", "(%[addr])")
 		"	move	%[tmp], %[new]				\n"
 		"2:							\n"
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 342e41de9d64..83f2a437d9e2 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1761,7 +1761,7 @@ static inline void parity_protection_init(void)
 
 	case CPU_5KC:
 	case CPU_5KE:
-	case CPU_LOONGSON1:
+	case CPU_LOONGSON32:
 		write_c0_ecc(0x80000000);
 		back_to_back_c0_hazard();
 		/* Set the PE bit (bit 31) in the c0_errctl register. */
@@ -2394,7 +2394,7 @@ void __init trap_init(void)
 	else {
 		if (cpu_has_vtag_icache)
 			set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp);
-		else if (current_cpu_type() == CPU_LOONGSON3)
+		else if (current_cpu_type() == CPU_LOONGSON64)
 			set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp);
 		else
 			set_except_vector(EXCCODE_RI, handle_ri_rdhwr);
diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c
index 97e538a8c1be..7dad7a293eae 100644
--- a/arch/mips/kvm/mmu.c
+++ b/arch/mips/kvm/mmu.c
@@ -136,6 +136,7 @@ pgd_t *kvm_pgd_alloc(void)
 static pte_t *kvm_mips_walk_pgd(pgd_t *pgd, struct kvm_mmu_memory_cache *cache,
 				unsigned long addr)
 {
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -145,7 +146,8 @@ static pte_t *kvm_mips_walk_pgd(pgd_t *pgd, struct kvm_mmu_memory_cache *cache,
 		BUG();
 		return NULL;
 	}
-	pud = pud_offset(pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	if (pud_none(*pud)) {
 		pmd_t *new_pmd;
 
@@ -204,8 +206,8 @@ static bool kvm_mips_flush_gpa_pmd(pmd_t *pmd, unsigned long start_gpa,
 {
 	pte_t *pte;
 	unsigned long end = ~0ul;
-	int i_min = __pmd_offset(start_gpa);
-	int i_max = __pmd_offset(end_gpa);
+	int i_min = pmd_index(start_gpa);
+	int i_max = pmd_index(end_gpa);
 	bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PMD - 1);
 	int i;
 
@@ -232,8 +234,8 @@ static bool kvm_mips_flush_gpa_pud(pud_t *pud, unsigned long start_gpa,
 {
 	pmd_t *pmd;
 	unsigned long end = ~0ul;
-	int i_min = __pud_offset(start_gpa);
-	int i_max = __pud_offset(end_gpa);
+	int i_min = pud_index(start_gpa);
+	int i_max = pud_index(end_gpa);
 	bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PUD - 1);
 	int i;
 
@@ -258,6 +260,7 @@ static bool kvm_mips_flush_gpa_pud(pud_t *pud, unsigned long start_gpa,
 static bool kvm_mips_flush_gpa_pgd(pgd_t *pgd, unsigned long start_gpa,
 				   unsigned long end_gpa)
 {
+	p4d_t *p4d;
 	pud_t *pud;
 	unsigned long end = ~0ul;
 	int i_min = pgd_index(start_gpa);
@@ -269,7 +272,8 @@ static bool kvm_mips_flush_gpa_pgd(pgd_t *pgd, unsigned long start_gpa,
 		if (!pgd_present(pgd[i]))
 			continue;
 
-		pud = pud_offset(pgd + i, 0);
+		p4d = p4d_offset(pgd, 0);
+		pud = pud_offset(p4d + i, 0);
 		if (i == i_max)
 			end = end_gpa;
 
@@ -334,8 +338,8 @@ static int kvm_mips_##name##_pmd(pmd_t *pmd, unsigned long start,	\
 	int ret = 0;							\
 	pte_t *pte;							\
 	unsigned long cur_end = ~0ul;					\
-	int i_min = __pmd_offset(start);				\
-	int i_max = __pmd_offset(end);					\
+	int i_min = pmd_index(start);				\
+	int i_max = pmd_index(end);					\
 	int i;								\
 									\
 	for (i = i_min; i <= i_max; ++i, start = 0) {			\
@@ -357,8 +361,8 @@ static int kvm_mips_##name##_pud(pud_t *pud, unsigned long start,	\
 	int ret = 0;							\
 	pmd_t *pmd;							\
 	unsigned long cur_end = ~0ul;					\
-	int i_min = __pud_offset(start);				\
-	int i_max = __pud_offset(end);					\
+	int i_min = pud_index(start);				\
+	int i_max = pud_index(end);					\
 	int i;								\
 									\
 	for (i = i_min; i <= i_max; ++i, start = 0) {			\
@@ -378,6 +382,7 @@ static int kvm_mips_##name##_pgd(pgd_t *pgd, unsigned long start,	\
 				 unsigned long end)			\
 {									\
 	int ret = 0;							\
+	p4d_t *p4d;							\
 	pud_t *pud;							\
 	unsigned long cur_end = ~0ul;					\
 	int i_min = pgd_index(start);					\
@@ -388,7 +393,8 @@ static int kvm_mips_##name##_pgd(pgd_t *pgd, unsigned long start,	\
 		if (!pgd_present(pgd[i]))				\
 			continue;					\
 									\
-		pud = pud_offset(pgd + i, 0);				\
+		p4d = p4d_offset(pgd, 0);				\
+		pud = pud_offset(p4d + i, 0);				\
 		if (i == i_max)						\
 			cur_end = end;					\
 									\
@@ -862,8 +868,8 @@ static bool kvm_mips_flush_gva_pmd(pmd_t *pmd, unsigned long start_gva,
 {
 	pte_t *pte;
 	unsigned long end = ~0ul;
-	int i_min = __pmd_offset(start_gva);
-	int i_max = __pmd_offset(end_gva);
+	int i_min = pmd_index(start_gva);
+	int i_max = pmd_index(end_gva);
 	bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PMD - 1);
 	int i;
 
@@ -890,8 +896,8 @@ static bool kvm_mips_flush_gva_pud(pud_t *pud, unsigned long start_gva,
 {
 	pmd_t *pmd;
 	unsigned long end = ~0ul;
-	int i_min = __pud_offset(start_gva);
-	int i_max = __pud_offset(end_gva);
+	int i_min = pud_index(start_gva);
+	int i_max = pud_index(end_gva);
 	bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PUD - 1);
 	int i;
 
@@ -916,6 +922,7 @@ static bool kvm_mips_flush_gva_pud(pud_t *pud, unsigned long start_gva,
 static bool kvm_mips_flush_gva_pgd(pgd_t *pgd, unsigned long start_gva,
 				   unsigned long end_gva)
 {
+	p4d_t *p4d;
 	pud_t *pud;
 	unsigned long end = ~0ul;
 	int i_min = pgd_index(start_gva);
@@ -927,7 +934,8 @@ static bool kvm_mips_flush_gva_pgd(pgd_t *pgd, unsigned long start_gva,
 		if (!pgd_present(pgd[i]))
 			continue;
 
-		pud = pud_offset(pgd + i, 0);
+		p4d = p4d_offset(pgd, 0);
+		pud = pud_offset(p4d + i, 0);
 		if (i == i_max)
 			end = end_gva;
 
diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c
index 73daa6ad33af..5a11e83dffe6 100644
--- a/arch/mips/kvm/trap_emul.c
+++ b/arch/mips/kvm/trap_emul.c
@@ -564,6 +564,7 @@ static void kvm_mips_emul_free_gva_pt(pgd_t *pgd)
 	/* Don't free host kernel page tables copied from init_mm.pgd */
 	const unsigned long end = 0x80000000;
 	unsigned long pgd_va, pud_va, pmd_va;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -576,7 +577,8 @@ static void kvm_mips_emul_free_gva_pt(pgd_t *pgd)
 		pgd_va = (unsigned long)i << PGDIR_SHIFT;
 		if (pgd_va >= end)
 			break;
-		pud = pud_offset(pgd + i, 0);
+		p4d = p4d_offset(pgd, 0);
+		pud = pud_offset(p4d + i, 0);
 		for (j = 0; j < PTRS_PER_PUD; j++) {
 			if (pud_none(pud[j]))
 				continue;
diff --git a/arch/mips/lib/bitops.c b/arch/mips/lib/bitops.c
index 3b2a1e78a543..116d0bd8b2ae 100644
--- a/arch/mips/lib/bitops.c
+++ b/arch/mips/lib/bitops.c
@@ -7,6 +7,7 @@
  * Copyright (c) 1999, 2000  Silicon Graphics, Inc.
  */
 #include <linux/bitops.h>
+#include <linux/bits.h>
 #include <linux/irqflags.h>
 #include <linux/export.h>
 
@@ -19,12 +20,11 @@
  */
 void __mips_set_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *a = (unsigned long *)addr;
-	unsigned bit = nr & SZLONG_MASK;
+	volatile unsigned long *a = &addr[BIT_WORD(nr)];
+	unsigned int bit = nr % BITS_PER_LONG;
 	unsigned long mask;
 	unsigned long flags;
 
-	a += nr >> SZLONG_LOG;
 	mask = 1UL << bit;
 	raw_local_irq_save(flags);
 	*a |= mask;
@@ -41,12 +41,11 @@ EXPORT_SYMBOL(__mips_set_bit);
  */
 void __mips_clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *a = (unsigned long *)addr;
-	unsigned bit = nr & SZLONG_MASK;
+	volatile unsigned long *a = &addr[BIT_WORD(nr)];
+	unsigned int bit = nr % BITS_PER_LONG;
 	unsigned long mask;
 	unsigned long flags;
 
-	a += nr >> SZLONG_LOG;
 	mask = 1UL << bit;
 	raw_local_irq_save(flags);
 	*a &= ~mask;
@@ -63,12 +62,11 @@ EXPORT_SYMBOL(__mips_clear_bit);
  */
 void __mips_change_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *a = (unsigned long *)addr;
-	unsigned bit = nr & SZLONG_MASK;
+	volatile unsigned long *a = &addr[BIT_WORD(nr)];
+	unsigned int bit = nr % BITS_PER_LONG;
 	unsigned long mask;
 	unsigned long flags;
 
-	a += nr >> SZLONG_LOG;
 	mask = 1UL << bit;
 	raw_local_irq_save(flags);
 	*a ^= mask;
@@ -78,32 +76,6 @@ EXPORT_SYMBOL(__mips_change_bit);
 
 
 /**
- * __mips_test_and_set_bit - Set a bit and return its old value.  This is
- * called by test_and_set_bit() if it cannot find a faster solution.
- * @nr: Bit to set
- * @addr: Address to count from
- */
-int __mips_test_and_set_bit(unsigned long nr,
-			    volatile unsigned long *addr)
-{
-	unsigned long *a = (unsigned long *)addr;
-	unsigned bit = nr & SZLONG_MASK;
-	unsigned long mask;
-	unsigned long flags;
-	int res;
-
-	a += nr >> SZLONG_LOG;
-	mask = 1UL << bit;
-	raw_local_irq_save(flags);
-	res = (mask & *a) != 0;
-	*a |= mask;
-	raw_local_irq_restore(flags);
-	return res;
-}
-EXPORT_SYMBOL(__mips_test_and_set_bit);
-
-
-/**
  * __mips_test_and_set_bit_lock - Set a bit and return its old value.  This is
  * called by test_and_set_bit_lock() if it cannot find a faster solution.
  * @nr: Bit to set
@@ -112,13 +84,12 @@ EXPORT_SYMBOL(__mips_test_and_set_bit);
 int __mips_test_and_set_bit_lock(unsigned long nr,
 				 volatile unsigned long *addr)
 {
-	unsigned long *a = (unsigned long *)addr;
-	unsigned bit = nr & SZLONG_MASK;
+	volatile unsigned long *a = &addr[BIT_WORD(nr)];
+	unsigned int bit = nr % BITS_PER_LONG;
 	unsigned long mask;
 	unsigned long flags;
 	int res;
 
-	a += nr >> SZLONG_LOG;
 	mask = 1UL << bit;
 	raw_local_irq_save(flags);
 	res = (mask & *a) != 0;
@@ -137,13 +108,12 @@ EXPORT_SYMBOL(__mips_test_and_set_bit_lock);
  */
 int __mips_test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *a = (unsigned long *)addr;
-	unsigned bit = nr & SZLONG_MASK;
+	volatile unsigned long *a = &addr[BIT_WORD(nr)];
+	unsigned int bit = nr % BITS_PER_LONG;
 	unsigned long mask;
 	unsigned long flags;
 	int res;
 
-	a += nr >> SZLONG_LOG;
 	mask = 1UL << bit;
 	raw_local_irq_save(flags);
 	res = (mask & *a) != 0;
@@ -162,13 +132,12 @@ EXPORT_SYMBOL(__mips_test_and_clear_bit);
  */
 int __mips_test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *a = (unsigned long *)addr;
-	unsigned bit = nr & SZLONG_MASK;
+	volatile unsigned long *a = &addr[BIT_WORD(nr)];
+	unsigned int bit = nr % BITS_PER_LONG;
 	unsigned long mask;
 	unsigned long flags;
 	int res;
 
-	a += nr >> SZLONG_LOG;
 	mask = 1UL << bit;
 	raw_local_irq_save(flags);
 	res = (mask & *a) != 0;
diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S
index 2ff84f4b1717..fda7b57b826e 100644
--- a/arch/mips/lib/csum_partial.S
+++ b/arch/mips/lib/csum_partial.S
@@ -279,7 +279,7 @@ EXPORT_SYMBOL(csum_partial)
 #endif
 
 	/* odd buffer alignment? */
-#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_LOONGSON3)
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_LOONGSON64)
 	.set	push
 	.set	arch=mips32r2
 	wsbh	v1, sum
@@ -732,7 +732,7 @@ EXPORT_SYMBOL(csum_partial)
 	addu	sum, v1
 #endif
 
-#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_LOONGSON3)
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_LOONGSON64)
 	.set	push
 	.set	arch=mips32r2
 	wsbh	v1, sum
diff --git a/arch/mips/loongson2ef/Kconfig b/arch/mips/loongson2ef/Kconfig
new file mode 100644
index 000000000000..595dd48e1e4d
--- /dev/null
+++ b/arch/mips/loongson2ef/Kconfig
@@ -0,0 +1,95 @@
+# SPDX-License-Identifier: GPL-2.0
+if MACH_LOONGSON2EF
+
+choice
+	prompt "Machine Type"
+
+config LEMOTE_FULOONG2E
+	bool "Lemote Fuloong(2e) mini-PC"
+	select ARCH_SPARSEMEM_ENABLE
+	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_MIGHT_HAVE_PC_SERIO
+	select CEVT_R4K
+	select CSRC_R4K
+	select SYS_HAS_CPU_LOONGSON2E
+	select DMA_NONCOHERENT
+	select BOOT_ELF32
+	select BOARD_SCACHE
+	select FORCE_PCI
+	select I8259
+	select ISA
+	select IRQ_MIPS_CPU
+	select SYS_SUPPORTS_64BIT_KERNEL
+	select SYS_SUPPORTS_LITTLE_ENDIAN
+	select SYS_SUPPORTS_HIGHMEM
+	select SYS_HAS_EARLY_PRINTK
+	select USE_GENERIC_EARLY_PRINTK_8250
+	select GENERIC_ISA_DMA_SUPPORT_BROKEN
+	select CPU_HAS_WB
+	select LOONGSON_MC146818
+	help
+	  Lemote Fuloong(2e) mini-PC board based on the Chinese Loongson-2E CPU and
+	  an FPGA northbridge
+
+	  Lemote Fuloong(2e) mini PC have a VIA686B south bridge.
+
+config LEMOTE_MACH2F
+	bool "Lemote Loongson 2F family machines"
+	select ARCH_SPARSEMEM_ENABLE
+	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_MIGHT_HAVE_PC_SERIO
+	select BOARD_SCACHE
+	select BOOT_ELF32
+	select CEVT_R4K if ! MIPS_EXTERNAL_TIMER
+	select CPU_HAS_WB
+	select CS5536
+	select CSRC_R4K if ! MIPS_EXTERNAL_TIMER
+	select DMA_NONCOHERENT
+	select GENERIC_ISA_DMA_SUPPORT_BROKEN
+	select HAVE_CLK
+	select FORCE_PCI
+	select I8259
+	select IRQ_MIPS_CPU
+	select ISA
+	select SYS_HAS_CPU_LOONGSON2F
+	select SYS_HAS_EARLY_PRINTK
+	select USE_GENERIC_EARLY_PRINTK_8250
+	select SYS_SUPPORTS_64BIT_KERNEL
+	select SYS_SUPPORTS_HIGHMEM
+	select SYS_SUPPORTS_LITTLE_ENDIAN
+	select LOONGSON_MC146818
+	help
+	  Lemote Loongson 2F family machines utilize the 2F revision of
+	  Loongson processor and the AMD CS5536 south bridge.
+
+	  These family machines include fuloong2f mini PC, yeeloong2f notebook,
+	  LingLoong allinone PC and so forth.
+
+endchoice
+
+config CS5536
+	bool
+
+config CS5536_MFGPT
+	bool "CS5536 MFGPT Timer"
+	depends on CS5536 && !HIGH_RES_TIMERS
+	select MIPS_EXTERNAL_TIMER
+	help
+	  This option enables the mfgpt0 timer of AMD CS5536. With this timer
+	  switched on you can not use high resolution timers.
+
+	  If you want to enable the Loongson2 CPUFreq Driver, Please enable
+	  this option at first, otherwise, You will get wrong system time.
+
+	  If unsure, say Yes.
+
+config LOONGSON_UART_BASE
+	bool
+	default y
+	depends on EARLY_PRINTK || SERIAL_8250
+
+config LOONGSON_MC146818
+	bool
+	default n
+
+endif # MACH_LOONGSON2EF
diff --git a/arch/mips/loongson2ef/Makefile b/arch/mips/loongson2ef/Makefile
new file mode 100644
index 000000000000..d4af1605cc9b
--- /dev/null
+++ b/arch/mips/loongson2ef/Makefile
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Common code for all Loongson based systems
+#
+
+obj-$(CONFIG_MACH_LOONGSON2EF) += common/
+
+#
+# Lemote Fuloong mini-PC (Loongson 2E-based)
+#
+
+obj-$(CONFIG_LEMOTE_FULOONG2E)	+= fuloong-2e/
+
+#
+# Lemote loongson2f family machines
+#
+
+obj-$(CONFIG_LEMOTE_MACH2F)  += lemote-2f/
diff --git a/arch/mips/loongson2ef/Platform b/arch/mips/loongson2ef/Platform
new file mode 100644
index 000000000000..3aca42963f35
--- /dev/null
+++ b/arch/mips/loongson2ef/Platform
@@ -0,0 +1,32 @@
+#
+# Loongson Processors' Support
+#
+
+# Only gcc >= 4.4 have Loongson specific support
+cflags-$(CONFIG_CPU_LOONGSON2EF)	+= -Wa,--trap
+cflags-$(CONFIG_CPU_LOONGSON2E) += \
+	$(call cc-option,-march=loongson2e,-march=r4600)
+cflags-$(CONFIG_CPU_LOONGSON2F) += \
+	$(call cc-option,-march=loongson2f,-march=r4600)
+# Enable the workarounds for Loongson2f
+ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS
+  ifeq ($(call as-option,-Wa$(comma)-mfix-loongson2f-nop,),)
+    $(error only binutils >= 2.20.2 have needed option -mfix-loongson2f-nop)
+  else
+    cflags-$(CONFIG_CPU_NOP_WORKAROUNDS) += -Wa$(comma)-mfix-loongson2f-nop
+  endif
+  ifeq ($(call as-option,-Wa$(comma)-mfix-loongson2f-jump,),)
+    $(error only binutils >= 2.20.2 have needed option -mfix-loongson2f-jump)
+  else
+    cflags-$(CONFIG_CPU_JUMP_WORKAROUNDS) += -Wa$(comma)-mfix-loongson2f-jump
+  endif
+endif
+
+#
+# Loongson Machines' Support
+#
+
+platform-$(CONFIG_MACH_LOONGSON2EF) += loongson2ef/
+cflags-$(CONFIG_MACH_LOONGSON2EF) += -I$(srctree)/arch/mips/include/asm/mach-loongson2ef -mno-branch-likely
+load-$(CONFIG_LEMOTE_FULOONG2E) += 0xffffffff80100000
+load-$(CONFIG_LEMOTE_MACH2F) += 0xffffffff80200000
diff --git a/arch/mips/loongson64/common/Makefile b/arch/mips/loongson2ef/common/Makefile
index 684624f61f5a..d5ab3e543ea3 100644
--- a/arch/mips/loongson64/common/Makefile
+++ b/arch/mips/loongson2ef/common/Makefile
@@ -3,14 +3,13 @@
 # Makefile for loongson based machines.
 #
 
-obj-y += setup.o init.o cmdline.o env.o time.o reset.o irq.o \
+obj-y += setup.o init.o env.o time.o reset.o irq.o \
     bonito-irq.o mem.o machtype.o platform.o serial.o
 obj-$(CONFIG_PCI) += pci.o
 
 #
 # Serial port support
 #
-obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
 obj-$(CONFIG_LOONGSON_UART_BASE) += uart_base.o
 obj-$(CONFIG_LOONGSON_MC146818) += rtc.o
 
diff --git a/arch/mips/loongson64/common/bonito-irq.c b/arch/mips/loongson2ef/common/bonito-irq.c
index 82352cc25e4c..82352cc25e4c 100644
--- a/arch/mips/loongson64/common/bonito-irq.c
+++ b/arch/mips/loongson2ef/common/bonito-irq.c
diff --git a/arch/mips/loongson64/common/cs5536/Makefile b/arch/mips/loongson2ef/common/cs5536/Makefile
index b32b29661245..b32b29661245 100644
--- a/arch/mips/loongson64/common/cs5536/Makefile
+++ b/arch/mips/loongson2ef/common/cs5536/Makefile
diff --git a/arch/mips/loongson64/common/cs5536/cs5536_acc.c b/arch/mips/loongson2ef/common/cs5536/cs5536_acc.c
index ff50aae72916..ff50aae72916 100644
--- a/arch/mips/loongson64/common/cs5536/cs5536_acc.c
+++ b/arch/mips/loongson2ef/common/cs5536/cs5536_acc.c
diff --git a/arch/mips/loongson64/common/cs5536/cs5536_ehci.c b/arch/mips/loongson2ef/common/cs5536/cs5536_ehci.c
index bd4c39fe6109..bd4c39fe6109 100644
--- a/arch/mips/loongson64/common/cs5536/cs5536_ehci.c
+++ b/arch/mips/loongson2ef/common/cs5536/cs5536_ehci.c
diff --git a/arch/mips/loongson64/common/cs5536/cs5536_ide.c b/arch/mips/loongson2ef/common/cs5536/cs5536_ide.c
index bb933294b092..bb933294b092 100644
--- a/arch/mips/loongson64/common/cs5536/cs5536_ide.c
+++ b/arch/mips/loongson2ef/common/cs5536/cs5536_ide.c
diff --git a/arch/mips/loongson64/common/cs5536/cs5536_isa.c b/arch/mips/loongson2ef/common/cs5536/cs5536_isa.c
index 5ad38f86ee62..5ad38f86ee62 100644
--- a/arch/mips/loongson64/common/cs5536/cs5536_isa.c
+++ b/arch/mips/loongson2ef/common/cs5536/cs5536_isa.c
diff --git a/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c b/arch/mips/loongson2ef/common/cs5536/cs5536_mfgpt.c
index 30af1b7c7529..30af1b7c7529 100644
--- a/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
+++ b/arch/mips/loongson2ef/common/cs5536/cs5536_mfgpt.c
diff --git a/arch/mips/loongson64/common/cs5536/cs5536_ohci.c b/arch/mips/loongson2ef/common/cs5536/cs5536_ohci.c
index 71a52b120317..71a52b120317 100644
--- a/arch/mips/loongson64/common/cs5536/cs5536_ohci.c
+++ b/arch/mips/loongson2ef/common/cs5536/cs5536_ohci.c
diff --git a/arch/mips/loongson64/common/cs5536/cs5536_pci.c b/arch/mips/loongson2ef/common/cs5536/cs5536_pci.c
index 202c89b568ba..202c89b568ba 100644
--- a/arch/mips/loongson64/common/cs5536/cs5536_pci.c
+++ b/arch/mips/loongson2ef/common/cs5536/cs5536_pci.c
diff --git a/arch/mips/loongson2ef/common/env.c b/arch/mips/loongson2ef/common/env.c
new file mode 100644
index 000000000000..6f20bdf9b242
--- /dev/null
+++ b/arch/mips/loongson2ef/common/env.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Based on Ocelot Linux port, which is
+ * Copyright 2001 MontaVista Software Inc.
+ * Author: jsun@mvista.com or jsun@junsun.net
+ *
+ * Copyright 2003 ICT CAS
+ * Author: Michael Guo <guoyi@ict.ac.cn>
+ *
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
+ * Author: Fuxin Zhang, zhangfx@lemote.com
+ *
+ * Copyright (C) 2009 Lemote Inc.
+ * Author: Wu Zhangjin, wuzhangjin@gmail.com
+ */
+#include <linux/export.h>
+#include <asm/bootinfo.h>
+#include <asm/fw/fw.h>
+#include <loongson.h>
+
+u32 cpu_clock_freq;
+EXPORT_SYMBOL(cpu_clock_freq);
+
+void __init prom_init_env(void)
+{
+	/* pmon passes arguments in 32bit pointers */
+	unsigned int processor_id;
+
+	cpu_clock_freq = fw_getenvl("cpuclock");
+	memsize = fw_getenvl("memsize");
+	highmemsize = fw_getenvl("highmemsize");
+
+	if (memsize == 0)
+		memsize = 256;
+
+	pr_info("memsize=%u, highmemsize=%u\n", memsize, highmemsize);
+
+	if (cpu_clock_freq == 0) {
+		processor_id = (&current_cpu_data)->processor_id;
+		switch (processor_id & PRID_REV_MASK) {
+		case PRID_REV_LOONGSON2E:
+			cpu_clock_freq = 533080000;
+			break;
+		case PRID_REV_LOONGSON2F:
+			cpu_clock_freq = 797000000;
+			break;
+		default:
+			cpu_clock_freq = 100000000;
+			break;
+		}
+	}
+	pr_info("CpuClock = %u\n", cpu_clock_freq);
+}
diff --git a/arch/mips/loongson64/common/init.c b/arch/mips/loongson2ef/common/init.c
index 912fe61c4fc7..45512178be77 100644
--- a/arch/mips/loongson64/common/init.c
+++ b/arch/mips/loongson2ef/common/init.c
@@ -9,6 +9,7 @@
 #include <asm/traps.h>
 #include <asm/smp-ops.h>
 #include <asm/cacheflush.h>
+#include <asm/fw/fw.h>
 
 #include <loongson.h>
 
@@ -32,22 +33,17 @@ void __init prom_init(void)
 		ioremap(LOONGSON_ADDRWINCFG_BASE, LOONGSON_ADDRWINCFG_SIZE);
 #endif
 
-	prom_init_cmdline();
+	fw_init_cmdline();
+	prom_init_machtype();
 	prom_init_env();
 
 	/* init base address of io space */
 	set_io_port_base((unsigned long)
 		ioremap(LOONGSON_PCIIO_BASE, LOONGSON_PCIIO_SIZE));
-
-#ifdef CONFIG_NUMA
-	prom_init_numa_memory();
-#else
 	prom_init_memory();
-#endif
 
 	/*init the uart base address */
 	prom_init_uart_base();
-	register_smp_ops(&loongson3_smp_ops);
 	board_nmi_handler_setup = mips_nmi_setup;
 }
 
diff --git a/arch/mips/loongson64/common/irq.c b/arch/mips/loongson2ef/common/irq.c
index 0ea93c1c0a97..0ea93c1c0a97 100644
--- a/arch/mips/loongson64/common/irq.c
+++ b/arch/mips/loongson2ef/common/irq.c
diff --git a/arch/mips/loongson64/common/machtype.c b/arch/mips/loongson2ef/common/machtype.c
index 4e42d929f1c7..82f6de49f20f 100644
--- a/arch/mips/loongson64/common/machtype.c
+++ b/arch/mips/loongson2ef/common/machtype.c
@@ -23,7 +23,6 @@ static const char *system_types[] = {
 	[MACH_DEXXON_GDIUM2F10]	= "dexxon-gdium-2f",
 	[MACH_LEMOTE_NAS]	= "lemote-nas-2f",
 	[MACH_LEMOTE_LL2F]	= "lemote-lynloong-2f",
-	[MACH_LOONGSON_GENERIC]	= "generic-loongson-machine",
 	[MACH_LOONGSON_END]	= NULL,
 };
 
diff --git a/arch/mips/loongson2ef/common/mem.c b/arch/mips/loongson2ef/common/mem.c
new file mode 100644
index 000000000000..ae21f1c62baa
--- /dev/null
+++ b/arch/mips/loongson2ef/common/mem.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ */
+#include <linux/fs.h>
+#include <linux/fcntl.h>
+#include <linux/memblock.h>
+#include <linux/mm.h>
+
+#include <asm/bootinfo.h>
+
+#include <loongson.h>
+#include <mem.h>
+#include <pci.h>
+
+
+u32 memsize, highmemsize;
+
+void __init prom_init_memory(void)
+{
+	add_memory_region(0x0, (memsize << 20), BOOT_MEM_RAM);
+
+	add_memory_region(memsize << 20, LOONGSON_PCI_MEM_START - (memsize <<
+				20), BOOT_MEM_RESERVED);
+
+#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG
+	{
+		int bit;
+
+		bit = fls(memsize + highmemsize);
+		if (bit != ffs(memsize + highmemsize))
+			bit += 20;
+		else
+			bit = bit + 20 - 1;
+
+		/* set cpu window3 to map CPU to DDR: 2G -> 2G */
+		LOONGSON_ADDRWIN_CPUTODDR(ADDRWIN_WIN3, 0x80000000ul,
+					  0x80000000ul, (1 << bit));
+		mmiowb();
+	}
+#endif /* !CONFIG_CPU_SUPPORTS_ADDRWINCFG */
+
+#ifdef CONFIG_64BIT
+	if (highmemsize > 0)
+		add_memory_region(LOONGSON_HIGHMEM_START,
+				  highmemsize << 20, BOOT_MEM_RAM);
+
+	add_memory_region(LOONGSON_PCI_MEM_END + 1, LOONGSON_HIGHMEM_START -
+			  LOONGSON_PCI_MEM_END - 1, BOOT_MEM_RESERVED);
+
+#endif /* !CONFIG_64BIT */
+}
+
+/* override of arch/mips/mm/cache.c: __uncached_access */
+int __uncached_access(struct file *file, unsigned long addr)
+{
+	if (file->f_flags & O_DSYNC)
+		return 1;
+
+	return addr >= __pa(high_memory) ||
+		((addr >= LOONGSON_MMIO_MEM_START) &&
+		 (addr < LOONGSON_MMIO_MEM_END));
+}
diff --git a/arch/mips/loongson64/common/pci.c b/arch/mips/loongson2ef/common/pci.c
index c47bb7bf3aa4..200916925e95 100644
--- a/arch/mips/loongson64/common/pci.c
+++ b/arch/mips/loongson2ef/common/pci.c
@@ -7,7 +7,6 @@
 
 #include <pci.h>
 #include <loongson.h>
-#include <boot_param.h>
 
 static struct resource loongson_pci_mem_resource = {
 	.name	= "pci memory space",
@@ -81,15 +80,8 @@ static int __init pcibios_init(void)
 	setup_pcimap();
 
 	loongson_pci_controller.io_map_base = mips_io_port_base;
-#ifdef CONFIG_LEFI_FIRMWARE_INTERFACE
-	loongson_pci_mem_resource.start = loongson_sysconf.pci_mem_start_addr;
-	loongson_pci_mem_resource.end = loongson_sysconf.pci_mem_end_addr;
-#endif
 	register_pci_controller(&loongson_pci_controller);
 
-#ifdef CONFIG_CPU_LOONGSON3
-	sbx00_acpi_init();
-#endif
 
 	return 0;
 }
diff --git a/arch/mips/loongson64/common/platform.c b/arch/mips/loongson2ef/common/platform.c
index 0084820cffaa..0084820cffaa 100644
--- a/arch/mips/loongson64/common/platform.c
+++ b/arch/mips/loongson2ef/common/platform.c
diff --git a/arch/mips/loongson64/common/pm.c b/arch/mips/loongson2ef/common/pm.c
index b8aed878d912..11f4cfd581fb 100644
--- a/arch/mips/loongson64/common/pm.c
+++ b/arch/mips/loongson2ef/common/pm.c
@@ -75,7 +75,7 @@ int __weak wakeup_loongson(void)
 static void wait_for_wakeup_events(void)
 {
 	while (!wakeup_loongson())
-		LOONGSON_CHIPCFG(0) &= ~0x7;
+		writel(readl(LOONGSON_CHIPCFG) & ~0x7, LOONGSON_CHIPCFG);
 }
 
 /*
@@ -98,15 +98,16 @@ static void loongson_suspend_enter(void)
 
 	stop_perf_counters();
 
-	cached_cpu_freq = LOONGSON_CHIPCFG(0);
+	cached_cpu_freq = readl(LOONGSON_CHIPCFG);
 
 	/* Put CPU into wait mode */
-	LOONGSON_CHIPCFG(0) &= ~0x7;
+	writel(readl(LOONGSON_CHIPCFG) & ~0x7, LOONGSON_CHIPCFG);
 
 	/* wait for the given events to wakeup cpu from wait mode */
 	wait_for_wakeup_events();
 
-	LOONGSON_CHIPCFG(0) = cached_cpu_freq;
+	writel(cached_cpu_freq, LOONGSON_CHIPCFG);
+
 	mmiowb();
 }
 
diff --git a/arch/mips/loongson64/common/reset.c b/arch/mips/loongson2ef/common/reset.c
index ce39e918e4d5..e7c87161ce00 100644
--- a/arch/mips/loongson64/common/reset.c
+++ b/arch/mips/loongson2ef/common/reset.c
@@ -13,7 +13,6 @@
 #include <asm/reboot.h>
 
 #include <loongson.h>
-#include <boot_param.h>
 
 static inline void loongson_reboot(void)
 {
@@ -35,26 +34,15 @@ static inline void loongson_reboot(void)
 
 static void loongson_restart(char *command)
 {
-#ifndef CONFIG_LEFI_FIRMWARE_INTERFACE
 	/* do preparation for reboot */
 	mach_prepare_reboot();
 
 	/* reboot via jumping to boot base address */
 	loongson_reboot();
-#else
-	void (*fw_restart)(void) = (void *)loongson_sysconf.restart_addr;
-
-	fw_restart();
-	while (1) {
-		if (cpu_wait)
-			cpu_wait();
-	}
-#endif
 }
 
 static void loongson_poweroff(void)
 {
-#ifndef CONFIG_LEFI_FIRMWARE_INTERFACE
 	mach_prepare_shutdown();
 
 	/*
@@ -62,15 +50,6 @@ static void loongson_poweroff(void)
 	 * a generic delay loop, machine_hang(), so simply return.
 	 */
 	return;
-#else
-	void (*fw_poweroff)(void) = (void *)loongson_sysconf.poweroff_addr;
-
-	fw_poweroff();
-	while (1) {
-		if (cpu_wait)
-			cpu_wait();
-	}
-#endif
 }
 
 static void loongson_halt(void)
diff --git a/arch/mips/loongson64/common/rtc.c b/arch/mips/loongson2ef/common/rtc.c
index 8d7628c0f513..8d7628c0f513 100644
--- a/arch/mips/loongson64/common/rtc.c
+++ b/arch/mips/loongson2ef/common/rtc.c
diff --git a/arch/mips/loongson2ef/common/serial.c b/arch/mips/loongson2ef/common/serial.c
new file mode 100644
index 000000000000..ac4f6e3ebc3e
--- /dev/null
+++ b/arch/mips/loongson2ef/common/serial.c
@@ -0,0 +1,86 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2007 Ralf Baechle (ralf@linux-mips.org)
+ *
+ * Copyright (C) 2009 Lemote, Inc.
+ * Author: Yan hua (yanhua@lemote.com)
+ * Author: Wu Zhangjin (wuzhangjin@gmail.com)
+ */
+
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/serial_8250.h>
+
+#include <asm/bootinfo.h>
+
+#include <loongson.h>
+#include <machine.h>
+
+#define PORT(int, clk)			\
+{								\
+	.irq		= int,					\
+	.uartclk	= clk,					\
+	.iotype		= UPIO_PORT,				\
+	.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST,	\
+	.regshift	= 0,					\
+}
+
+#define PORT_M(int, clk)				\
+{								\
+	.irq		= MIPS_CPU_IRQ_BASE + (int),		\
+	.uartclk	= clk,					\
+	.iotype		= UPIO_MEM,				\
+	.membase	= (void __iomem *)NULL,			\
+	.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST,	\
+	.regshift	= 0,					\
+}
+
+static struct plat_serial8250_port uart8250_data[MACH_LOONGSON_END + 1] = {
+	[MACH_LOONGSON_UNKNOWN]	= {},
+	[MACH_LEMOTE_FL2E]	= PORT(4, 1843200),
+	[MACH_LEMOTE_FL2F]	= PORT(3, 1843200),
+	[MACH_LEMOTE_ML2F7]	= PORT_M(3, 3686400),
+	[MACH_LEMOTE_YL2F89]	= PORT_M(3, 3686400),
+	[MACH_DEXXON_GDIUM2F10]	= PORT_M(3, 3686400),
+	[MACH_LEMOTE_NAS]	= PORT_M(3, 3686400),
+	[MACH_LEMOTE_LL2F]	= PORT(3, 1843200),
+	[MACH_LOONGSON_END]	= {},
+};
+
+static struct platform_device uart8250_device = {
+	.name = "serial8250",
+	.id = PLAT8250_DEV_PLATFORM,
+};
+
+static int __init serial_init(void)
+{
+	unsigned char iotype;
+
+	iotype = uart8250_data[mips_machtype].iotype;
+
+	if (UPIO_MEM == iotype) {
+		uart8250_data[mips_machtype].mapbase =
+			loongson_uart_base;
+		uart8250_data[mips_machtype].membase =
+			(void __iomem *)_loongson_uart_base;
+	}
+	else if (UPIO_PORT == iotype)
+		uart8250_data[mips_machtype].iobase =
+			loongson_uart_base - LOONGSON_PCIIO_BASE;
+
+	memset(&uart8250_data[mips_machtype + 1], 0,
+			sizeof(struct plat_serial8250_port));
+	uart8250_device.dev.platform_data = &uart8250_data[mips_machtype];
+
+	return platform_device_register(&uart8250_device);
+}
+module_init(serial_init);
+
+static void __exit serial_exit(void)
+{
+	platform_device_unregister(&uart8250_device);
+}
+module_exit(serial_exit);
diff --git a/arch/mips/loongson64/common/setup.c b/arch/mips/loongson2ef/common/setup.c
index bc2da4c140c4..4fd27f4f90ed 100644
--- a/arch/mips/loongson64/common/setup.c
+++ b/arch/mips/loongson2ef/common/setup.c
@@ -11,11 +11,6 @@
 
 #include <loongson.h>
 
-#ifdef CONFIG_VT
-#include <linux/console.h>
-#include <linux/screen_info.h>
-#endif
-
 static void wbflush_loongson(void)
 {
 	asm(".set\tpush\n\t"
@@ -32,20 +27,4 @@ EXPORT_SYMBOL(__wbflush);
 
 void __init plat_mem_setup(void)
 {
-#ifdef CONFIG_VT
-#if defined(CONFIG_VGA_CONSOLE)
-	conswitchp = &vga_con;
-
-	screen_info = (struct screen_info) {
-		.orig_x			= 0,
-		.orig_y			= 25,
-		.orig_video_cols	= 80,
-		.orig_video_lines	= 25,
-		.orig_video_isVGA	= VIDEO_TYPE_VGAC,
-		.orig_video_points	= 16,
-	};
-#elif defined(CONFIG_DUMMY_CONSOLE)
-	conswitchp = &dummy_con;
-#endif
-#endif
 }
diff --git a/arch/mips/loongson64/common/time.c b/arch/mips/loongson2ef/common/time.c
index e78760ce475b..585741af42a9 100644
--- a/arch/mips/loongson64/common/time.c
+++ b/arch/mips/loongson2ef/common/time.c
@@ -18,11 +18,7 @@ void __init plat_time_init(void)
 	/* setup mips r4k timer */
 	mips_hpt_frequency = cpu_clock_freq / 2;
 
-#ifdef CONFIG_RS780_HPET
-	setup_hpet_timer();
-#else
 	setup_mfgpt0_timer();
-#endif
 }
 
 void read_persistent_clock64(struct timespec64 *ts)
diff --git a/arch/mips/loongson64/common/uart_base.c b/arch/mips/loongson2ef/common/uart_base.c
index e88d937f10fe..522bea6ad7b0 100644
--- a/arch/mips/loongson64/common/uart_base.c
+++ b/arch/mips/loongson2ef/common/uart_base.c
@@ -6,13 +6,14 @@
 
 #include <linux/export.h>
 #include <asm/bootinfo.h>
+#include <asm/setup.h>
 
 #include <loongson.h>
 
 /* raw */
-unsigned long loongson_uart_base[MAX_UARTS] = {};
+unsigned long loongson_uart_base;
 /* ioremapped */
-unsigned long _loongson_uart_base[MAX_UARTS] = {};
+unsigned long _loongson_uart_base;
 
 EXPORT_SYMBOL(loongson_uart_base);
 EXPORT_SYMBOL(_loongson_uart_base);
@@ -20,16 +21,12 @@ EXPORT_SYMBOL(_loongson_uart_base);
 void prom_init_loongson_uart_base(void)
 {
 	switch (mips_machtype) {
-	case MACH_LOONGSON_GENERIC:
-		/* The CPU provided serial port (CPU) */
-		loongson_uart_base[0] = LOONGSON_REG_BASE + 0x1e0;
-		break;
 	case MACH_LEMOTE_FL2E:
-		loongson_uart_base[0] = LOONGSON_PCIIO_BASE + 0x3f8;
+		loongson_uart_base = LOONGSON_PCIIO_BASE + 0x3f8;
 		break;
 	case MACH_LEMOTE_FL2F:
 	case MACH_LEMOTE_LL2F:
-		loongson_uart_base[0] = LOONGSON_PCIIO_BASE + 0x2f8;
+		loongson_uart_base = LOONGSON_PCIIO_BASE + 0x2f8;
 		break;
 	case MACH_LEMOTE_ML2F7:
 	case MACH_LEMOTE_YL2F89:
@@ -37,10 +34,10 @@ void prom_init_loongson_uart_base(void)
 	case MACH_LEMOTE_NAS:
 	default:
 		/* The CPU provided serial port (LPC) */
-		loongson_uart_base[0] = LOONGSON_LIO1_BASE + 0x3f8;
+		loongson_uart_base = LOONGSON_LIO1_BASE + 0x3f8;
 		break;
 	}
 
-	_loongson_uart_base[0] =
-		(unsigned long)ioremap_nocache(loongson_uart_base[0], 8);
+	_loongson_uart_base = TO_UNCAC(loongson_uart_base);
+	setup_8250_early_printk_port(_loongson_uart_base, 0, 1024);
 }
diff --git a/arch/mips/loongson64/fuloong-2e/Makefile b/arch/mips/loongson2ef/fuloong-2e/Makefile
index bb58edb3bea7..bb58edb3bea7 100644
--- a/arch/mips/loongson64/fuloong-2e/Makefile
+++ b/arch/mips/loongson2ef/fuloong-2e/Makefile
diff --git a/arch/mips/loongson64/fuloong-2e/dma.c b/arch/mips/loongson2ef/fuloong-2e/dma.c
index e122292bf666..e122292bf666 100644
--- a/arch/mips/loongson64/fuloong-2e/dma.c
+++ b/arch/mips/loongson2ef/fuloong-2e/dma.c
diff --git a/arch/mips/loongson64/fuloong-2e/irq.c b/arch/mips/loongson2ef/fuloong-2e/irq.c
index 32278e7bf85c..32278e7bf85c 100644
--- a/arch/mips/loongson64/fuloong-2e/irq.c
+++ b/arch/mips/loongson2ef/fuloong-2e/irq.c
diff --git a/arch/mips/loongson64/fuloong-2e/reset.c b/arch/mips/loongson2ef/fuloong-2e/reset.c
index 8273de1cf4bb..8273de1cf4bb 100644
--- a/arch/mips/loongson64/fuloong-2e/reset.c
+++ b/arch/mips/loongson2ef/fuloong-2e/reset.c
diff --git a/arch/mips/loongson64/lemote-2f/Makefile b/arch/mips/loongson2ef/lemote-2f/Makefile
index 881a0ec06d1f..881a0ec06d1f 100644
--- a/arch/mips/loongson64/lemote-2f/Makefile
+++ b/arch/mips/loongson2ef/lemote-2f/Makefile
diff --git a/arch/mips/loongson64/lemote-2f/clock.c b/arch/mips/loongson2ef/lemote-2f/clock.c
index 8281334df9c8..414f282c8ab5 100644
--- a/arch/mips/loongson64/lemote-2f/clock.c
+++ b/arch/mips/loongson2ef/lemote-2f/clock.c
@@ -15,7 +15,7 @@
 #include <linux/spinlock.h>
 
 #include <asm/clock.h>
-#include <asm/mach-loongson64/loongson.h>
+#include <asm/mach-loongson2ef/loongson.h>
 
 static LIST_HEAD(clock_list);
 static DEFINE_SPINLOCK(clock_lock);
@@ -118,9 +118,9 @@ int clk_set_rate(struct clk *clk, unsigned long rate)
 
 	clk->rate = rate;
 
-	regval = LOONGSON_CHIPCFG(0);
+	regval = readl(LOONGSON_CHIPCFG);
 	regval = (regval & ~0x7) | (pos->driver_data - 1);
-	LOONGSON_CHIPCFG(0) = regval;
+	writel(regval, LOONGSON_CHIPCFG);
 
 	return ret;
 }
diff --git a/arch/mips/loongson64/lemote-2f/dma.c b/arch/mips/loongson2ef/lemote-2f/dma.c
index abf0e39d7e46..abf0e39d7e46 100644
--- a/arch/mips/loongson64/lemote-2f/dma.c
+++ b/arch/mips/loongson2ef/lemote-2f/dma.c
diff --git a/arch/mips/loongson64/lemote-2f/ec_kb3310b.c b/arch/mips/loongson2ef/lemote-2f/ec_kb3310b.c
index d138220e96a2..d138220e96a2 100644
--- a/arch/mips/loongson64/lemote-2f/ec_kb3310b.c
+++ b/arch/mips/loongson2ef/lemote-2f/ec_kb3310b.c
diff --git a/arch/mips/loongson64/lemote-2f/ec_kb3310b.h b/arch/mips/loongson2ef/lemote-2f/ec_kb3310b.h
index aecdbc9c875a..aecdbc9c875a 100644
--- a/arch/mips/loongson64/lemote-2f/ec_kb3310b.h
+++ b/arch/mips/loongson2ef/lemote-2f/ec_kb3310b.h
diff --git a/arch/mips/loongson64/lemote-2f/irq.c b/arch/mips/loongson2ef/lemote-2f/irq.c
index c58a044c6c07..c58a044c6c07 100644
--- a/arch/mips/loongson64/lemote-2f/irq.c
+++ b/arch/mips/loongson2ef/lemote-2f/irq.c
diff --git a/arch/mips/loongson64/lemote-2f/machtype.c b/arch/mips/loongson2ef/lemote-2f/machtype.c
index 9462a3ab57be..9462a3ab57be 100644
--- a/arch/mips/loongson64/lemote-2f/machtype.c
+++ b/arch/mips/loongson2ef/lemote-2f/machtype.c
diff --git a/arch/mips/loongson64/lemote-2f/pm.c b/arch/mips/loongson2ef/lemote-2f/pm.c
index 3d0027229e3c..3d0027229e3c 100644
--- a/arch/mips/loongson64/lemote-2f/pm.c
+++ b/arch/mips/loongson2ef/lemote-2f/pm.c
diff --git a/arch/mips/loongson64/lemote-2f/reset.c b/arch/mips/loongson2ef/lemote-2f/reset.c
index 0db0934302ea..197dae4ffd23 100644
--- a/arch/mips/loongson64/lemote-2f/reset.c
+++ b/arch/mips/loongson2ef/lemote-2f/reset.c
@@ -24,7 +24,7 @@ static void reset_cpu(void)
 	 * reset cpu to full speed, this is needed when enabling cpu frequency
 	 * scalling
 	 */
-	LOONGSON_CHIPCFG(0) |= 0x7;
+	writel(readl(LOONGSON_CHIPCFG) | 0x7, LOONGSON_CHIPCFG);
 }
 
 /* reset support for fuloong2f */
diff --git a/arch/mips/loongson32/Kconfig b/arch/mips/loongson32/Kconfig
index 6dacc1438906..e27879b4813b 100644
--- a/arch/mips/loongson32/Kconfig
+++ b/arch/mips/loongson32/Kconfig
@@ -38,7 +38,7 @@ endchoice
 menuconfig CEVT_CSRC_LS1X
 	bool "Use PWM Timer for clockevent/clocksource"
 	select MIPS_EXTERNAL_TIMER
-	depends on CPU_LOONGSON1
+	depends on CPU_LOONGSON32
 	help
 	  This option changes the default clockevent/clocksource to PWM Timer,
 	  and is required by Loongson1 CPUFreq support.
diff --git a/arch/mips/loongson32/Platform b/arch/mips/loongson32/Platform
index 333215593092..7f8e342f1ef5 100644
--- a/arch/mips/loongson32/Platform
+++ b/arch/mips/loongson32/Platform
@@ -1,4 +1,4 @@
-cflags-$(CONFIG_CPU_LOONGSON1)		+= -march=mips32r2 -Wa,--trap
+cflags-$(CONFIG_CPU_LOONGSON32)		+= -march=mips32r2 -Wa,--trap
 platform-$(CONFIG_MACH_LOONGSON32)	+= loongson32/
 cflags-$(CONFIG_MACH_LOONGSON32)	+= -I$(srctree)/arch/mips/include/asm/mach-loongson32
-load-$(CONFIG_CPU_LOONGSON1)		+= 0xffffffff80200000
+load-$(CONFIG_CPU_LOONGSON32)		+= 0xffffffff80200000
diff --git a/arch/mips/loongson32/common/prom.c b/arch/mips/loongson32/common/prom.c
index c4e043ee53ff..73dd25142484 100644
--- a/arch/mips/loongson32/common/prom.c
+++ b/arch/mips/loongson32/common/prom.c
@@ -5,63 +5,25 @@
  * Modified from arch/mips/pnx833x/common/prom.c.
  */
 
+#include <linux/io.h>
+#include <linux/init.h>
 #include <linux/serial_reg.h>
 #include <asm/bootinfo.h>
+#include <asm/fw/fw.h>
 
 #include <loongson1.h>
-#include <prom.h>
 
-int prom_argc;
-char **prom_argv, **prom_envp;
-unsigned long memsize, highmemsize;
-
-char *prom_getenv(char *envname)
-{
-	char **env = prom_envp;
-	int i;
-
-	i = strlen(envname);
-
-	while (*env) {
-		if (strncmp(envname, *env, i) == 0 && *(*env + i) == '=')
-			return *env + i + 1;
-		env++;
-	}
-
-	return 0;
-}
-
-static inline unsigned long env_or_default(char *env, unsigned long dfl)
-{
-	char *str = prom_getenv(env);
-	return str ? simple_strtol(str, 0, 0) : dfl;
-}
-
-void __init prom_init_cmdline(void)
-{
-	char *c = &(arcs_cmdline[0]);
-	int i;
-
-	for (i = 1; i < prom_argc; i++) {
-		strcpy(c, prom_argv[i]);
-		c += strlen(prom_argv[i]);
-		if (i < prom_argc - 1)
-			*c++ = ' ';
-	}
-	*c = 0;
-}
+unsigned long memsize;
 
 void __init prom_init(void)
 {
 	void __iomem *uart_base;
-	prom_argc = fw_arg0;
-	prom_argv = (char **)fw_arg1;
-	prom_envp = (char **)fw_arg2;
 
-	prom_init_cmdline();
+	fw_init_cmdline();
 
-	memsize = env_or_default("memsize", DEFAULT_MEMSIZE);
-	highmemsize = env_or_default("highmemsize", 0x0);
+	memsize = fw_getenvl("memsize");
+	if(!memsize)
+		memsize = DEFAULT_MEMSIZE;
 
 	if (strstr(arcs_cmdline, "console=ttyS3"))
 		uart_base = ioremap_nocache(LS1X_UART3_BASE, 0x0f);
@@ -77,3 +39,8 @@ void __init prom_init(void)
 void __init prom_free_prom_memory(void)
 {
 }
+
+void __init plat_mem_setup(void)
+{
+	add_memory_region(0x0, (memsize << 20), BOOT_MEM_RAM);
+}
diff --git a/arch/mips/loongson32/common/setup.c b/arch/mips/loongson32/common/setup.c
index 8b03e18fc4d8..4733fe037176 100644
--- a/arch/mips/loongson32/common/setup.c
+++ b/arch/mips/loongson32/common/setup.c
@@ -3,15 +3,12 @@
  * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
  */
 
+#include <linux/io.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <asm/cpu-info.h>
 #include <asm/bootinfo.h>
 
-#include <prom.h>
-
-void __init plat_mem_setup(void)
-{
-	add_memory_region(0x0, (memsize << 20), BOOT_MEM_RAM);
-}
-
 const char *get_system_type(void)
 {
 	unsigned int processor_id = (&current_cpu_data)->processor_id;
diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig
index 4c14a11525f4..48b29c198acf 100644
--- a/arch/mips/loongson64/Kconfig
+++ b/arch/mips/loongson64/Kconfig
@@ -1,119 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 if MACH_LOONGSON64
 
-choice
-	prompt "Machine Type"
-
-config LEMOTE_FULOONG2E
-	bool "Lemote Fuloong(2e) mini-PC"
-	select ARCH_SPARSEMEM_ENABLE
-	select ARCH_MIGHT_HAVE_PC_PARPORT
-	select ARCH_MIGHT_HAVE_PC_SERIO
-	select CEVT_R4K
-	select CSRC_R4K
-	select SYS_HAS_CPU_LOONGSON2E
-	select DMA_NONCOHERENT
-	select BOOT_ELF32
-	select BOARD_SCACHE
-	select HAVE_PCI
-	select I8259
-	select ISA
-	select IRQ_MIPS_CPU
-	select SYS_SUPPORTS_64BIT_KERNEL
-	select SYS_SUPPORTS_LITTLE_ENDIAN
-	select SYS_SUPPORTS_HIGHMEM
-	select SYS_HAS_EARLY_PRINTK
-	select GENERIC_ISA_DMA_SUPPORT_BROKEN
-	select CPU_HAS_WB
-	select LOONGSON_MC146818
-	help
-	  Lemote Fuloong(2e) mini-PC board based on the Chinese Loongson-2E CPU and
-	  an FPGA northbridge
-
-	  Lemote Fuloong(2e) mini PC have a VIA686B south bridge.
-
-config LEMOTE_MACH2F
-	bool "Lemote Loongson 2F family machines"
-	select ARCH_SPARSEMEM_ENABLE
-	select ARCH_MIGHT_HAVE_PC_PARPORT
-	select ARCH_MIGHT_HAVE_PC_SERIO
-	select BOARD_SCACHE
-	select BOOT_ELF32
-	select CEVT_R4K if ! MIPS_EXTERNAL_TIMER
-	select CPU_HAS_WB
-	select CS5536
-	select CSRC_R4K if ! MIPS_EXTERNAL_TIMER
-	select DMA_NONCOHERENT
-	select GENERIC_ISA_DMA_SUPPORT_BROKEN
-	select HAVE_CLK
-	select HAVE_PCI
-	select I8259
-	select IRQ_MIPS_CPU
-	select ISA
-	select SYS_HAS_CPU_LOONGSON2F
-	select SYS_HAS_EARLY_PRINTK
-	select SYS_SUPPORTS_64BIT_KERNEL
-	select SYS_SUPPORTS_HIGHMEM
-	select SYS_SUPPORTS_LITTLE_ENDIAN
-	select LOONGSON_MC146818
-	help
-	  Lemote Loongson 2F family machines utilize the 2F revision of
-	  Loongson processor and the AMD CS5536 south bridge.
-
-	  These family machines include fuloong2f mini PC, yeeloong2f notebook,
-	  LingLoong allinone PC and so forth.
-
-config LOONGSON_MACH3X
-	bool "Generic Loongson 3 family machines"
-	select ARCH_SPARSEMEM_ENABLE
-	select ARCH_MIGHT_HAVE_PC_PARPORT
-	select ARCH_MIGHT_HAVE_PC_SERIO
-	select GENERIC_ISA_DMA_SUPPORT_BROKEN
-	select BOOT_ELF32
-	select BOARD_SCACHE
-	select CSRC_R4K
-	select CEVT_R4K
-	select CPU_HAS_WB
-	select FORCE_PCI
-	select ISA
-	select I8259
-	select IRQ_MIPS_CPU
-	select NR_CPUS_DEFAULT_4
-	select SYS_HAS_CPU_LOONGSON3
-	select SYS_HAS_EARLY_PRINTK
-	select SYS_SUPPORTS_SMP
-	select SYS_SUPPORTS_HOTPLUG_CPU
-	select SYS_SUPPORTS_NUMA
-	select SYS_SUPPORTS_64BIT_KERNEL
-	select SYS_SUPPORTS_HIGHMEM
-	select SYS_SUPPORTS_LITTLE_ENDIAN
-	select LOONGSON_MC146818
-	select ZONE_DMA32
-	select LEFI_FIRMWARE_INTERFACE
-	help
-		Generic Loongson 3 family machines utilize the 3A/3B revision
-		of Loongson processor and RS780/SBX00 chipset.
-endchoice
-
-config CS5536
-	bool
-
-config CS5536_MFGPT
-	bool "CS5536 MFGPT Timer"
-	depends on CS5536 && !HIGH_RES_TIMERS
-	select MIPS_EXTERNAL_TIMER
-	help
-	  This option enables the mfgpt0 timer of AMD CS5536. With this timer
-	  switched on you can not use high resolution timers.
-
-	  If you want to enable the Loongson2 CPUFreq Driver, Please enable
-	  this option at first, otherwise, You will get wrong system time.
-
-	  If unsure, say Yes.
-
 config RS780_HPET
 	bool "RS780/SBX00 HPET Timer"
-	depends on LOONGSON_MACH3X
+	depends on MACH_LOONGSON64
 	select MIPS_EXTERNAL_TIMER
 	help
 	  This option enables the hpet timer of AMD RS780/SBX00.
@@ -123,16 +13,9 @@ config RS780_HPET
 
 	  If unsure, say Yes.
 
-config LOONGSON_UART_BASE
-	bool
-	default y
-	depends on EARLY_PRINTK || SERIAL_8250
 
 config LOONGSON_MC146818
 	bool
 	default n
 
-config LEFI_FIRMWARE_INTERFACE
-	bool
-
 endif # MACH_LOONGSON64
diff --git a/arch/mips/loongson64/Makefile b/arch/mips/loongson64/Makefile
index 1a5df773707d..7821891bc5d0 100644
--- a/arch/mips/loongson64/Makefile
+++ b/arch/mips/loongson64/Makefile
@@ -1,24 +1,13 @@
 # SPDX-License-Identifier: GPL-2.0-only
 #
-# Common code for all Loongson based systems
+# Makefile for Loongson-3 family machines
 #
+obj-$(CONFIG_MACH_LOONGSON64) += irq.o cop2-ex.o platform.o acpi_init.o dma.o \
+				setup.o init.o env.o time.o reset.o \
 
-obj-$(CONFIG_MACH_LOONGSON64) += common/
-
-#
-# Lemote Fuloong mini-PC (Loongson 2E-based)
-#
-
-obj-$(CONFIG_LEMOTE_FULOONG2E)	+= fuloong-2e/
-
-#
-# Lemote loongson2f family machines
-#
-
-obj-$(CONFIG_LEMOTE_MACH2F)  += lemote-2f/
-
-#
-# All Loongson-3 family machines
-#
-
-obj-$(CONFIG_CPU_LOONGSON3)  += loongson-3/
+obj-$(CONFIG_SMP)	+= smp.o
+obj-$(CONFIG_NUMA)	+= numa.o
+obj-$(CONFIG_RS780_HPET) += hpet.o
+obj-$(CONFIG_PCI) += pci.o
+obj-$(CONFIG_LOONGSON_MC146818) += rtc.o
+obj-$(CONFIG_SUSPEND) += pm.o
diff --git a/arch/mips/loongson64/Platform b/arch/mips/loongson64/Platform
index 9f79908f5063..d5eb94c9edb4 100644
--- a/arch/mips/loongson64/Platform
+++ b/arch/mips/loongson64/Platform
@@ -2,32 +2,13 @@
 # Loongson Processors' Support
 #
 
-# Only gcc >= 4.4 have Loongson specific support
-cflags-$(CONFIG_CPU_LOONGSON2)	+= -Wa,--trap
-cflags-$(CONFIG_CPU_LOONGSON2E) += \
-	$(call cc-option,-march=loongson2e,-march=r4600)
-cflags-$(CONFIG_CPU_LOONGSON2F) += \
-	$(call cc-option,-march=loongson2f,-march=r4600)
-# Enable the workarounds for Loongson2f
-ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS
-  ifeq ($(call as-option,-Wa$(comma)-mfix-loongson2f-nop,),)
-    $(error only binutils >= 2.20.2 have needed option -mfix-loongson2f-nop)
-  else
-    cflags-$(CONFIG_CPU_NOP_WORKAROUNDS) += -Wa$(comma)-mfix-loongson2f-nop
-  endif
-  ifeq ($(call as-option,-Wa$(comma)-mfix-loongson2f-jump,),)
-    $(error only binutils >= 2.20.2 have needed option -mfix-loongson2f-jump)
-  else
-    cflags-$(CONFIG_CPU_JUMP_WORKAROUNDS) += -Wa$(comma)-mfix-loongson2f-jump
-  endif
-endif
 
-cflags-$(CONFIG_CPU_LOONGSON3)	+= -Wa,--trap
+cflags-$(CONFIG_CPU_LOONGSON64)	+= -Wa,--trap
 
 #
 # Some versions of binutils, not currently mainline as of 2019/02/04, support
 # an -mfix-loongson3-llsc flag which emits a sync prior to each ll instruction
-# to work around a CPU bug (see loongson_llsc_mb() in asm/barrier.h for a
+# to work around a CPU bug (see __SYNC_loongson3_war in asm/sync.h for a
 # description).
 #
 # We disable this in order to prevent the assembler meddling with the
@@ -44,7 +25,7 @@ cflags-$(CONFIG_CPU_LOONGSON3)	+= -Wa,--trap
 # binutils does not merge support for the flag then we can revisit & remove
 # this later - for now it ensures vendor toolchains don't cause problems.
 #
-cflags-$(CONFIG_CPU_LOONGSON3)	+= $(call as-option,-Wa$(comma)-mno-fix-loongson3-llsc,)
+cflags-$(CONFIG_CPU_LOONGSON64)	+= $(call as-option,-Wa$(comma)-mno-fix-loongson3-llsc,)
 
 #
 # binutils from v2.25 on and gcc starting from v4.9.0 treat -march=loongson3a
@@ -55,14 +36,14 @@ cflags-$(CONFIG_CPU_LOONGSON3)	+= $(call as-option,-Wa$(comma)-mno-fix-loongson3
 #
 ifeq ($(call cc-ifversion, -ge, 0409, y), y)
   ifeq ($(call ld-ifversion, -ge, 225000000, y), y)
-    cflags-$(CONFIG_CPU_LOONGSON3)  += \
+    cflags-$(CONFIG_CPU_LOONGSON64)  += \
       $(call cc-option,-march=loongson3a -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64)
   else
-    cflags-$(CONFIG_CPU_LOONGSON3)  += \
+    cflags-$(CONFIG_CPU_LOONGSON64)  += \
       $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64)
   endif
 else
-    cflags-$(CONFIG_CPU_LOONGSON3)  += \
+    cflags-$(CONFIG_CPU_LOONGSON64)  += \
       $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64)
 endif
 
@@ -76,6 +57,4 @@ cflags-y += $(call cc-option,-mno-loongson-mmi)
 
 platform-$(CONFIG_MACH_LOONGSON64) += loongson64/
 cflags-$(CONFIG_MACH_LOONGSON64) += -I$(srctree)/arch/mips/include/asm/mach-loongson64 -mno-branch-likely
-load-$(CONFIG_LEMOTE_FULOONG2E) += 0xffffffff80100000
-load-$(CONFIG_LEMOTE_MACH2F) += 0xffffffff80200000
-load-$(CONFIG_LOONGSON_MACH3X) += 0xffffffff80200000
+load-$(CONFIG_CPU_LOONGSON64) += 0xffffffff80200000
diff --git a/arch/mips/loongson64/loongson-3/acpi_init.c b/arch/mips/loongson64/acpi_init.c
index 8d7c119ddf91..8d7c119ddf91 100644
--- a/arch/mips/loongson64/loongson-3/acpi_init.c
+++ b/arch/mips/loongson64/acpi_init.c
diff --git a/arch/mips/loongson64/common/cmdline.c b/arch/mips/loongson64/common/cmdline.c
deleted file mode 100644
index a735460682cf..000000000000
--- a/arch/mips/loongson64/common/cmdline.c
+++ /dev/null
@@ -1,44 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Based on Ocelot Linux port, which is
- * Copyright 2001 MontaVista Software Inc.
- * Author: jsun@mvista.com or jsun@junsun.net
- *
- * Copyright 2003 ICT CAS
- * Author: Michael Guo <guoyi@ict.ac.cn>
- *
- * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
- * Author: Fuxin Zhang, zhangfx@lemote.com
- *
- * Copyright (C) 2009 Lemote Inc.
- * Author: Wu Zhangjin, wuzhangjin@gmail.com
- */
-#include <asm/bootinfo.h>
-
-#include <loongson.h>
-
-void __init prom_init_cmdline(void)
-{
-	int prom_argc;
-	/* pmon passes arguments in 32bit pointers */
-	int *_prom_argv;
-	int i;
-	long l;
-
-	/* firmware arguments are initialized in head.S */
-	prom_argc = fw_arg0;
-	_prom_argv = (int *)fw_arg1;
-
-	/* arg[0] is "g", the rest is boot parameters */
-	arcs_cmdline[0] = '\0';
-	for (i = 1; i < prom_argc; i++) {
-		l = (long)_prom_argv[i];
-		if (strlen(arcs_cmdline) + strlen(((char *)l) + 1)
-		    >= sizeof(arcs_cmdline))
-			break;
-		strcat(arcs_cmdline, ((char *)l));
-		strcat(arcs_cmdline, " ");
-	}
-
-	prom_init_machtype();
-}
diff --git a/arch/mips/loongson64/common/early_printk.c b/arch/mips/loongson64/common/early_printk.c
deleted file mode 100644
index 5e2a151aa30c..000000000000
--- a/arch/mips/loongson64/common/early_printk.c
+++ /dev/null
@@ -1,38 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*  early printk support
- *
- *  Copyright (c) 2009 Philippe Vachon <philippe@cowpig.ca>
- *  Copyright (c) 2009 Lemote Inc.
- *  Author: Wu Zhangjin, wuzhangjin@gmail.com
- */
-#include <linux/serial_reg.h>
-#include <asm/setup.h>
-
-#include <loongson.h>
-
-#define PORT(base, offset) (u8 *)(base + offset)
-
-static inline unsigned int serial_in(unsigned char *base, int offset)
-{
-	return readb(PORT(base, offset));
-}
-
-static inline void serial_out(unsigned char *base, int offset, int value)
-{
-	writeb(value, PORT(base, offset));
-}
-
-void prom_putchar(char c)
-{
-	int timeout;
-	unsigned char *uart_base;
-
-	uart_base = (unsigned char *)_loongson_uart_base[0];
-	timeout = 1024;
-
-	while (((serial_in(uart_base, UART_LSR) & UART_LSR_THRE) == 0) &&
-			(timeout-- > 0))
-		;
-
-	serial_out(uart_base, UART_TX, c);
-}
diff --git a/arch/mips/loongson64/common/mem.c b/arch/mips/loongson64/common/mem.c
deleted file mode 100644
index 4254ac4ec616..000000000000
--- a/arch/mips/loongson64/common/mem.c
+++ /dev/null
@@ -1,157 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- */
-#include <linux/fs.h>
-#include <linux/fcntl.h>
-#include <linux/memblock.h>
-#include <linux/mm.h>
-
-#include <asm/bootinfo.h>
-
-#include <loongson.h>
-#include <boot_param.h>
-#include <mem.h>
-#include <pci.h>
-
-#ifndef CONFIG_LEFI_FIRMWARE_INTERFACE
-
-u32 memsize, highmemsize;
-
-void __init prom_init_memory(void)
-{
-	add_memory_region(0x0, (memsize << 20), BOOT_MEM_RAM);
-
-	add_memory_region(memsize << 20, LOONGSON_PCI_MEM_START - (memsize <<
-				20), BOOT_MEM_RESERVED);
-
-#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG
-	{
-		int bit;
-
-		bit = fls(memsize + highmemsize);
-		if (bit != ffs(memsize + highmemsize))
-			bit += 20;
-		else
-			bit = bit + 20 - 1;
-
-		/* set cpu window3 to map CPU to DDR: 2G -> 2G */
-		LOONGSON_ADDRWIN_CPUTODDR(ADDRWIN_WIN3, 0x80000000ul,
-					  0x80000000ul, (1 << bit));
-		mmiowb();
-	}
-#endif /* !CONFIG_CPU_SUPPORTS_ADDRWINCFG */
-
-#ifdef CONFIG_64BIT
-	if (highmemsize > 0)
-		add_memory_region(LOONGSON_HIGHMEM_START,
-				  highmemsize << 20, BOOT_MEM_RAM);
-
-	add_memory_region(LOONGSON_PCI_MEM_END + 1, LOONGSON_HIGHMEM_START -
-			  LOONGSON_PCI_MEM_END - 1, BOOT_MEM_RESERVED);
-
-#endif /* !CONFIG_64BIT */
-}
-
-#else /* CONFIG_LEFI_FIRMWARE_INTERFACE */
-
-void __init prom_init_memory(void)
-{
-	int i;
-	u32 node_id;
-	u32 mem_type;
-
-	/* parse memory information */
-	for (i = 0; i < loongson_memmap->nr_map; i++) {
-		node_id = loongson_memmap->map[i].node_id;
-		mem_type = loongson_memmap->map[i].mem_type;
-
-		if (node_id != 0)
-			continue;
-
-		switch (mem_type) {
-		case SYSTEM_RAM_LOW:
-			memblock_add(loongson_memmap->map[i].mem_start,
-				(u64)loongson_memmap->map[i].mem_size << 20);
-			break;
-		case SYSTEM_RAM_HIGH:
-			memblock_add(loongson_memmap->map[i].mem_start,
-				(u64)loongson_memmap->map[i].mem_size << 20);
-			break;
-		case SYSTEM_RAM_RESERVED:
-			memblock_reserve(loongson_memmap->map[i].mem_start,
-				(u64)loongson_memmap->map[i].mem_size << 20);
-			break;
-		}
-	}
-}
-
-#endif /* CONFIG_LEFI_FIRMWARE_INTERFACE */
-
-/* override of arch/mips/mm/cache.c: __uncached_access */
-int __uncached_access(struct file *file, unsigned long addr)
-{
-	if (file->f_flags & O_DSYNC)
-		return 1;
-
-	return addr >= __pa(high_memory) ||
-		((addr >= LOONGSON_MMIO_MEM_START) &&
-		 (addr < LOONGSON_MMIO_MEM_END));
-}
-
-#ifdef CONFIG_CPU_SUPPORTS_UNCACHED_ACCELERATED
-
-#include <linux/pci.h>
-#include <linux/sched.h>
-#include <asm/current.h>
-
-static unsigned long uca_start, uca_end;
-
-pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-			      unsigned long size, pgprot_t vma_prot)
-{
-	unsigned long offset = pfn << PAGE_SHIFT;
-	unsigned long end = offset + size;
-
-	if (__uncached_access(file, offset)) {
-		if (uca_start && (offset >= uca_start) &&
-		    (end <= uca_end))
-			return __pgprot((pgprot_val(vma_prot) &
-					 ~_CACHE_MASK) |
-					_CACHE_UNCACHED_ACCELERATED);
-		else
-			return pgprot_noncached(vma_prot);
-	}
-	return vma_prot;
-}
-
-static int __init find_vga_mem_init(void)
-{
-	struct pci_dev *dev = 0;
-	struct resource *r;
-	int idx;
-
-	if (uca_start)
-		return 0;
-
-	for_each_pci_dev(dev) {
-		if ((dev->class >> 16) == PCI_BASE_CLASS_DISPLAY) {
-			for (idx = 0; idx < PCI_NUM_RESOURCES; idx++) {
-				r = &dev->resource[idx];
-				if (!r->start && r->end)
-					continue;
-				if (r->flags & IORESOURCE_IO)
-					continue;
-				if (r->flags & IORESOURCE_MEM) {
-					uca_start = r->start;
-					uca_end = r->end;
-					return 0;
-				}
-			}
-		}
-	}
-
-	return 0;
-}
-
-late_initcall(find_vga_mem_init);
-#endif /* !CONFIG_CPU_SUPPORTS_UNCACHED_ACCELERATED */
diff --git a/arch/mips/loongson64/common/serial.c b/arch/mips/loongson64/common/serial.c
deleted file mode 100644
index 98c3a7feb10f..000000000000
--- a/arch/mips/loongson64/common/serial.c
+++ /dev/null
@@ -1,117 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2007 Ralf Baechle (ralf@linux-mips.org)
- *
- * Copyright (C) 2009 Lemote, Inc.
- * Author: Yan hua (yanhua@lemote.com)
- * Author: Wu Zhangjin (wuzhangjin@gmail.com)
- */
-
-#include <linux/io.h>
-#include <linux/module.h>
-#include <linux/serial_8250.h>
-
-#include <asm/bootinfo.h>
-
-#include <loongson.h>
-#include <machine.h>
-
-#define PORT(int, clk)			\
-{								\
-	.irq		= int,					\
-	.uartclk	= clk,					\
-	.iotype		= UPIO_PORT,				\
-	.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST,	\
-	.regshift	= 0,					\
-}
-
-#define PORT_M(int, clk)				\
-{								\
-	.irq		= MIPS_CPU_IRQ_BASE + (int),		\
-	.uartclk	= clk,					\
-	.iotype		= UPIO_MEM,				\
-	.membase	= (void __iomem *)NULL,			\
-	.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST,	\
-	.regshift	= 0,					\
-}
-
-static struct plat_serial8250_port uart8250_data[][MAX_UARTS + 1] = {
-	[MACH_LOONGSON_UNKNOWN]	= {},
-	[MACH_LEMOTE_FL2E]	= {PORT(4, 1843200), {} },
-	[MACH_LEMOTE_FL2F]	= {PORT(3, 1843200), {} },
-	[MACH_LEMOTE_ML2F7]	= {PORT_M(3, 3686400), {} },
-	[MACH_LEMOTE_YL2F89]	= {PORT_M(3, 3686400), {} },
-	[MACH_DEXXON_GDIUM2F10]	= {PORT_M(3, 3686400), {} },
-	[MACH_LEMOTE_NAS]	= {PORT_M(3, 3686400), {} },
-	[MACH_LEMOTE_LL2F]	= {PORT(3, 1843200), {} },
-	[MACH_LOONGSON_GENERIC]	= {PORT_M(2, 25000000), {} },
-	[MACH_LOONGSON_END]	= {},
-};
-
-static struct platform_device uart8250_device = {
-	.name = "serial8250",
-	.id = PLAT8250_DEV_PLATFORM,
-};
-
-static int __init serial_init(void)
-{
-	int i;
-	unsigned char iotype;
-
-	iotype = uart8250_data[mips_machtype][0].iotype;
-
-	if (UPIO_MEM == iotype) {
-		uart8250_data[mips_machtype][0].mapbase =
-			loongson_uart_base[0];
-		uart8250_data[mips_machtype][0].membase =
-			(void __iomem *)_loongson_uart_base[0];
-	}
-	else if (UPIO_PORT == iotype)
-		uart8250_data[mips_machtype][0].iobase =
-			loongson_uart_base[0] - LOONGSON_PCIIO_BASE;
-
-	if (loongson_sysconf.uarts[0].uartclk)
-		uart8250_data[mips_machtype][0].uartclk =
-			loongson_sysconf.uarts[0].uartclk;
-
-	for (i = 1; i < loongson_sysconf.nr_uarts; i++) {
-		iotype = loongson_sysconf.uarts[i].iotype;
-		uart8250_data[mips_machtype][i].iotype = iotype;
-		loongson_uart_base[i] = loongson_sysconf.uarts[i].uart_base;
-
-		if (UPIO_MEM == iotype) {
-			uart8250_data[mips_machtype][i].irq =
-				MIPS_CPU_IRQ_BASE + loongson_sysconf.uarts[i].int_offset;
-			uart8250_data[mips_machtype][i].mapbase =
-				loongson_uart_base[i];
-			uart8250_data[mips_machtype][i].membase =
-				ioremap_nocache(loongson_uart_base[i], 8);
-		} else if (UPIO_PORT == iotype) {
-			uart8250_data[mips_machtype][i].irq =
-				loongson_sysconf.uarts[i].int_offset;
-			uart8250_data[mips_machtype][i].iobase =
-				loongson_uart_base[i] - LOONGSON_PCIIO_BASE;
-		}
-
-		uart8250_data[mips_machtype][i].uartclk =
-			loongson_sysconf.uarts[i].uartclk;
-		uart8250_data[mips_machtype][i].flags =
-			UPF_BOOT_AUTOCONF | UPF_SKIP_TEST;
-	}
-
-	memset(&uart8250_data[mips_machtype][loongson_sysconf.nr_uarts],
-			0, sizeof(struct plat_serial8250_port));
-	uart8250_device.dev.platform_data = uart8250_data[mips_machtype];
-
-	return platform_device_register(&uart8250_device);
-}
-module_init(serial_init);
-
-static void __exit serial_exit(void)
-{
-	platform_device_unregister(&uart8250_device);
-}
-module_exit(serial_exit);
diff --git a/arch/mips/loongson64/loongson-3/cop2-ex.c b/arch/mips/loongson64/cop2-ex.c
index 9efdfe430ff0..9efdfe430ff0 100644
--- a/arch/mips/loongson64/loongson-3/cop2-ex.c
+++ b/arch/mips/loongson64/cop2-ex.c
diff --git a/arch/mips/loongson64/loongson-3/dma.c b/arch/mips/loongson64/dma.c
index 5e86635f71db..5e86635f71db 100644
--- a/arch/mips/loongson64/loongson-3/dma.c
+++ b/arch/mips/loongson64/dma.c
diff --git a/arch/mips/loongson64/common/env.c b/arch/mips/loongson64/env.c
index 09d5cf4676ca..0daeb7bcf023 100644
--- a/arch/mips/loongson64/common/env.c
+++ b/arch/mips/loongson64/env.c
@@ -30,41 +30,13 @@ u64 loongson_freqctrl[MAX_PACKAGES];
 
 unsigned long long smp_group[4];
 
-#define parse_even_earlier(res, option, p)				\
-do {									\
-	unsigned int tmp __maybe_unused;				\
-									\
-	if (strncmp(option, (char *)p, strlen(option)) == 0)		\
-		tmp = kstrtou32((char *)p + strlen(option"="), 10, &res); \
-} while (0)
+const char *get_system_type(void)
+{
+	return "Generic Loongson64 System";
+}
 
 void __init prom_init_env(void)
 {
-	/* pmon passes arguments in 32bit pointers */
-	unsigned int processor_id;
-
-#ifndef CONFIG_LEFI_FIRMWARE_INTERFACE
-	int *_prom_envp;
-	long l;
-
-	/* firmware arguments are initialized in head.S */
-	_prom_envp = (int *)fw_arg2;
-
-	l = (long)*_prom_envp;
-	while (l != 0) {
-		parse_even_earlier(cpu_clock_freq, "cpuclock", l);
-		parse_even_earlier(memsize, "memsize", l);
-		parse_even_earlier(highmemsize, "highmemsize", l);
-		_prom_envp++;
-		l = (long)*_prom_envp;
-	}
-	if (memsize == 0)
-		memsize = 256;
-
-	loongson_sysconf.nr_uarts = 1;
-
-	pr_info("memsize=%u, highmemsize=%u\n", memsize, highmemsize);
-#else
 	struct boot_params *boot_p;
 	struct loongson_params *loongson_p;
 	struct system_loongson *esys;
@@ -182,31 +154,5 @@ void __init prom_init_env(void)
 	if (loongson_sysconf.nr_sensors)
 		memcpy(loongson_sysconf.sensors, esys->sensors,
 			sizeof(struct sensor_device) * loongson_sysconf.nr_sensors);
-#endif
-	if (cpu_clock_freq == 0) {
-		processor_id = (&current_cpu_data)->processor_id;
-		switch (processor_id & PRID_REV_MASK) {
-		case PRID_REV_LOONGSON2E:
-			cpu_clock_freq = 533080000;
-			break;
-		case PRID_REV_LOONGSON2F:
-			cpu_clock_freq = 797000000;
-			break;
-		case PRID_REV_LOONGSON3A_R1:
-		case PRID_REV_LOONGSON3A_R2_0:
-		case PRID_REV_LOONGSON3A_R2_1:
-		case PRID_REV_LOONGSON3A_R3_0:
-		case PRID_REV_LOONGSON3A_R3_1:
-			cpu_clock_freq = 900000000;
-			break;
-		case PRID_REV_LOONGSON3B_R1:
-		case PRID_REV_LOONGSON3B_R2:
-			cpu_clock_freq = 1000000000;
-			break;
-		default:
-			cpu_clock_freq = 100000000;
-			break;
-		}
-	}
 	pr_info("CpuClock = %u\n", cpu_clock_freq);
 }
diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/hpet.c
index ed15430ad64f..ed15430ad64f 100644
--- a/arch/mips/loongson64/loongson-3/hpet.c
+++ b/arch/mips/loongson64/hpet.c
diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c
new file mode 100644
index 000000000000..5ac1a0f35ca4
--- /dev/null
+++ b/arch/mips/loongson64/init.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2009 Lemote Inc.
+ * Author: Wu Zhangjin, wuzhangjin@gmail.com
+ */
+
+#include <linux/memblock.h>
+#include <asm/bootinfo.h>
+#include <asm/traps.h>
+#include <asm/smp-ops.h>
+#include <asm/cacheflush.h>
+#include <asm/fw/fw.h>
+
+#include <loongson.h>
+
+static void __init mips_nmi_setup(void)
+{
+	void *base;
+	extern char except_vec_nmi;
+
+	base = (void *)(CAC_BASE + 0x380);
+	memcpy(base, &except_vec_nmi, 0x80);
+	flush_icache_range((unsigned long)base, (unsigned long)base + 0x80);
+}
+
+void __init prom_init(void)
+{
+	fw_init_cmdline();
+	prom_init_env();
+
+	/* init base address of io space */
+	set_io_port_base((unsigned long)
+		ioremap(LOONGSON_PCIIO_BASE, LOONGSON_PCIIO_SIZE));
+
+	prom_init_numa_memory();
+
+	/* Hardcode to CPU UART 0 */
+	setup_8250_early_printk_port(TO_UNCAC(LOONGSON_REG_BASE + 0x1e0), 0, 1024);
+
+	register_smp_ops(&loongson3_smp_ops);
+	board_nmi_handler_setup = mips_nmi_setup;
+}
+
+void __init prom_free_prom_memory(void)
+{
+}
diff --git a/arch/mips/loongson64/loongson-3/irq.c b/arch/mips/loongson64/irq.c
index 5605061f5f98..79ad797497e4 100644
--- a/arch/mips/loongson64/loongson-3/irq.c
+++ b/arch/mips/loongson64/irq.c
@@ -78,8 +78,12 @@ static void ht_irqdispatch(void)
 
 #define UNUSED_IPS (CAUSEF_IP5 | CAUSEF_IP4 | CAUSEF_IP1 | CAUSEF_IP0)
 
-void mach_irq_dispatch(unsigned int pending)
+asmlinkage void plat_irq_dispatch(void)
 {
+	unsigned int pending;
+
+	pending = read_c0_cause() & read_c0_status() & ST0_IM;
+
 	if (pending & CAUSEF_IP7)
 		do_IRQ(LOONGSON_TIMER_IRQ);
 #if defined(CONFIG_SMP)
@@ -127,7 +131,7 @@ void irq_router_init(void)
 		LOONGSON_INT_ROUTER_INTEN | (0xffff << 16) | 0x1 << 10;
 }
 
-void __init mach_init_irq(void)
+void __init arch_init_irq(void)
 {
 	struct irq_chip *chip;
 
diff --git a/arch/mips/loongson64/loongson-3/Makefile b/arch/mips/loongson64/loongson-3/Makefile
deleted file mode 100644
index df39598742b2..000000000000
--- a/arch/mips/loongson64/loongson-3/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile for Loongson-3 family machines
-#
-obj-y			+= irq.o cop2-ex.o platform.o acpi_init.o dma.o
-
-obj-$(CONFIG_SMP)	+= smp.o
-
-obj-$(CONFIG_NUMA)	+= numa.o
-
-obj-$(CONFIG_RS780_HPET) += hpet.o
diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/numa.c
index 8f20d2cb3767..ef94a2278561 100644
--- a/arch/mips/loongson64/loongson-3/numa.c
+++ b/arch/mips/loongson64/numa.c
@@ -26,12 +26,15 @@
 #include <asm/wbflush.h>
 #include <boot_param.h>
 
-static struct node_data prealloc__node_data[MAX_NUMNODES];
+static struct pglist_data prealloc__node_data[MAX_NUMNODES];
 unsigned char __node_distances[MAX_NUMNODES][MAX_NUMNODES];
 EXPORT_SYMBOL(__node_distances);
-struct node_data *__node_data[MAX_NUMNODES];
+struct pglist_data *__node_data[MAX_NUMNODES];
 EXPORT_SYMBOL(__node_data);
 
+cpumask_t __node_cpumask[MAX_NUMNODES];
+EXPORT_SYMBOL(__node_cpumask);
+
 static void enable_lpa(void)
 {
 	unsigned long value;
@@ -214,7 +217,7 @@ static __init void prom_meminit(void)
 		if (node_online(node)) {
 			szmem(node);
 			node_mem_init(node);
-			cpumask_clear(&__node_data[(node)]->cpumask);
+			cpumask_clear(&__node_cpumask[node]);
 		}
 	}
 	memblocks_present();
@@ -228,7 +231,7 @@ static __init void prom_meminit(void)
 		if (loongson_sysconf.reserved_cpus_mask & (1<<cpu))
 			continue;
 
-		cpumask_set_cpu(active_cpu, &__node_data[(node)]->cpumask);
+		cpumask_set_cpu(active_cpu, &__node_cpumask[node]);
 		pr_info("NUMA: set cpumask cpu %d on node %d\n", active_cpu, node);
 
 		active_cpu++;
diff --git a/arch/mips/loongson64/pci.c b/arch/mips/loongson64/pci.c
new file mode 100644
index 000000000000..e84ae20c3290
--- /dev/null
+++ b/arch/mips/loongson64/pci.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2007 Lemote, Inc. & Institute of Computing Technology
+ * Author: Fuxin Zhang, zhangfx@lemote.com
+ */
+#include <linux/pci.h>
+
+#include <pci.h>
+#include <loongson.h>
+#include <boot_param.h>
+
+static struct resource loongson_pci_mem_resource = {
+	.name	= "pci memory space",
+	.start	= LOONGSON_PCI_MEM_START,
+	.end	= LOONGSON_PCI_MEM_END,
+	.flags	= IORESOURCE_MEM,
+};
+
+static struct resource loongson_pci_io_resource = {
+	.name	= "pci io space",
+	.start	= LOONGSON_PCI_IO_START,
+	.end	= IO_SPACE_LIMIT,
+	.flags	= IORESOURCE_IO,
+};
+
+static struct pci_controller  loongson_pci_controller = {
+	.pci_ops	= &loongson_pci_ops,
+	.io_resource	= &loongson_pci_io_resource,
+	.mem_resource	= &loongson_pci_mem_resource,
+	.mem_offset	= 0x00000000UL,
+	.io_offset	= 0x00000000UL,
+};
+
+
+extern int sbx00_acpi_init(void);
+
+static int __init pcibios_init(void)
+{
+
+	loongson_pci_controller.io_map_base = mips_io_port_base;
+	loongson_pci_mem_resource.start = loongson_sysconf.pci_mem_start_addr;
+	loongson_pci_mem_resource.end = loongson_sysconf.pci_mem_end_addr;
+
+	register_pci_controller(&loongson_pci_controller);
+
+	sbx00_acpi_init();
+
+	return 0;
+}
+
+arch_initcall(pcibios_init);
diff --git a/arch/mips/loongson64/loongson-3/platform.c b/arch/mips/loongson64/platform.c
index 13f3404f0030..13f3404f0030 100644
--- a/arch/mips/loongson64/loongson-3/platform.c
+++ b/arch/mips/loongson64/platform.c
diff --git a/arch/mips/loongson64/pm.c b/arch/mips/loongson64/pm.c
new file mode 100644
index 000000000000..7c8556f09781
--- /dev/null
+++ b/arch/mips/loongson64/pm.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * loongson-specific suspend support
+ *
+ *  Copyright (C) 2009 Lemote Inc.
+ *  Author: Wu Zhangjin <wuzhangjin@gmail.com>
+ */
+#include <linux/suspend.h>
+#include <linux/interrupt.h>
+#include <linux/pm.h>
+
+#include <asm/i8259.h>
+#include <asm/mipsregs.h>
+
+#include <loongson.h>
+
+static unsigned int __maybe_unused cached_master_mask;	/* i8259A */
+static unsigned int __maybe_unused cached_slave_mask;
+static unsigned int __maybe_unused cached_bonito_irq_mask; /* bonito */
+
+void arch_suspend_disable_irqs(void)
+{
+	/* disable all mips events */
+	local_irq_disable();
+
+#ifdef CONFIG_I8259
+	/* disable all events of i8259A */
+	cached_slave_mask = inb(PIC_SLAVE_IMR);
+	cached_master_mask = inb(PIC_MASTER_IMR);
+
+	outb(0xff, PIC_SLAVE_IMR);
+	inb(PIC_SLAVE_IMR);
+	outb(0xff, PIC_MASTER_IMR);
+	inb(PIC_MASTER_IMR);
+#endif
+	/* disable all events of bonito */
+	cached_bonito_irq_mask = LOONGSON_INTEN;
+	LOONGSON_INTENCLR = 0xffff;
+	(void)LOONGSON_INTENCLR;
+}
+
+void arch_suspend_enable_irqs(void)
+{
+	/* enable all mips events */
+	local_irq_enable();
+#ifdef CONFIG_I8259
+	/* only enable the cached events of i8259A */
+	outb(cached_slave_mask, PIC_SLAVE_IMR);
+	outb(cached_master_mask, PIC_MASTER_IMR);
+#endif
+	/* enable all cached events of bonito */
+	LOONGSON_INTENSET = cached_bonito_irq_mask;
+	(void)LOONGSON_INTENSET;
+}
+
+/*
+ * Setup the board-specific events for waking up loongson from wait mode
+ */
+void __weak setup_wakeup_events(void)
+{
+}
+
+void __weak mach_suspend(void)
+{
+}
+
+void __weak mach_resume(void)
+{
+}
+
+static int loongson_pm_enter(suspend_state_t state)
+{
+	mach_suspend();
+
+	mach_resume();
+
+	return 0;
+}
+
+static int loongson_pm_valid_state(suspend_state_t state)
+{
+	switch (state) {
+	case PM_SUSPEND_ON:
+	case PM_SUSPEND_STANDBY:
+	case PM_SUSPEND_MEM:
+		return 1;
+
+	default:
+		return 0;
+	}
+}
+
+static const struct platform_suspend_ops loongson_pm_ops = {
+	.valid	= loongson_pm_valid_state,
+	.enter	= loongson_pm_enter,
+};
+
+static int __init loongson_pm_init(void)
+{
+	suspend_set_ops(&loongson_pm_ops);
+
+	return 0;
+}
+arch_initcall(loongson_pm_init);
diff --git a/arch/mips/loongson64/reset.c b/arch/mips/loongson64/reset.c
new file mode 100644
index 000000000000..88b3bd5fed25
--- /dev/null
+++ b/arch/mips/loongson64/reset.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *
+ * Copyright (C) 2007 Lemote, Inc. & Institute of Computing Technology
+ * Author: Fuxin Zhang, zhangfx@lemote.com
+ * Copyright (C) 2009 Lemote, Inc.
+ * Author: Zhangjin Wu, wuzhangjin@gmail.com
+ */
+#include <linux/init.h>
+#include <linux/pm.h>
+
+#include <asm/idle.h>
+#include <asm/reboot.h>
+
+#include <loongson.h>
+#include <boot_param.h>
+
+static inline void loongson_reboot(void)
+{
+	((void (*)(void))ioremap_nocache(LOONGSON_BOOT_BASE, 4)) ();
+}
+
+static void loongson_restart(char *command)
+{
+
+	void (*fw_restart)(void) = (void *)loongson_sysconf.restart_addr;
+
+	fw_restart();
+	while (1) {
+		if (cpu_wait)
+			cpu_wait();
+	}
+}
+
+static void loongson_poweroff(void)
+{
+	void (*fw_poweroff)(void) = (void *)loongson_sysconf.poweroff_addr;
+
+	fw_poweroff();
+	while (1) {
+		if (cpu_wait)
+			cpu_wait();
+	}
+}
+
+static void loongson_halt(void)
+{
+	pr_notice("\n\n** You can safely turn off the power now **\n\n");
+	while (1) {
+		if (cpu_wait)
+			cpu_wait();
+	}
+}
+
+static int __init mips_reboot_setup(void)
+{
+	_machine_restart = loongson_restart;
+	_machine_halt = loongson_halt;
+	pm_power_off = loongson_poweroff;
+
+	return 0;
+}
+
+arch_initcall(mips_reboot_setup);
diff --git a/arch/mips/loongson64/rtc.c b/arch/mips/loongson64/rtc.c
new file mode 100644
index 000000000000..8d7628c0f513
--- /dev/null
+++ b/arch/mips/loongson64/rtc.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  Lemote Fuloong platform support
+ *
+ *  Copyright(c) 2010 Arnaud Patard <apatard@mandriva.com>
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/mc146818rtc.h>
+
+static struct resource loongson_rtc_resources[] = {
+	{
+		.start	= RTC_PORT(0),
+		.end	= RTC_PORT(1),
+		.flags	= IORESOURCE_IO,
+	}, {
+		.start	= RTC_IRQ,
+		.end	= RTC_IRQ,
+		.flags	= IORESOURCE_IRQ,
+	}
+};
+
+static struct platform_device loongson_rtc_device = {
+	.name		= "rtc_cmos",
+	.id		= -1,
+	.resource	= loongson_rtc_resources,
+	.num_resources	= ARRAY_SIZE(loongson_rtc_resources),
+};
+
+
+static int __init loongson_rtc_platform_init(void)
+{
+	platform_device_register(&loongson_rtc_device);
+	return 0;
+}
+
+device_initcall(loongson_rtc_platform_init);
diff --git a/arch/mips/loongson64/setup.c b/arch/mips/loongson64/setup.c
new file mode 100644
index 000000000000..4fd27f4f90ed
--- /dev/null
+++ b/arch/mips/loongson64/setup.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
+ * Author: Fuxin Zhang, zhangfx@lemote.com
+ */
+#include <linux/export.h>
+#include <linux/init.h>
+
+#include <asm/wbflush.h>
+#include <asm/bootinfo.h>
+
+#include <loongson.h>
+
+static void wbflush_loongson(void)
+{
+	asm(".set\tpush\n\t"
+	    ".set\tnoreorder\n\t"
+	    ".set mips3\n\t"
+	    "sync\n\t"
+	    "nop\n\t"
+	    ".set\tpop\n\t"
+	    ".set mips0\n\t");
+}
+
+void (*__wbflush)(void) = wbflush_loongson;
+EXPORT_SYMBOL(__wbflush);
+
+void __init plat_mem_setup(void)
+{
+}
diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/smp.c
index ce68cdaaf33c..de8e0741ce2d 100644
--- a/arch/mips/loongson64/loongson-3/smp.c
+++ b/arch/mips/loongson64/smp.c
@@ -18,6 +18,7 @@
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 #include <loongson.h>
+#include <loongson_regs.h>
 #include <workarounds.h>
 
 #include "smp.h"
@@ -48,6 +49,62 @@ static uint32_t core0_c0count[NR_CPUS];
 		__wbflush();			\
 	} while (0)
 
+u32 (*ipi_read_clear)(int cpu);
+void (*ipi_write_action)(int cpu, u32 action);
+
+static u32 csr_ipi_read_clear(int cpu)
+{
+	u32 action;
+
+	/* Load the ipi register to figure out what we're supposed to do */
+	action = csr_readl(LOONGSON_CSR_IPI_STATUS);
+	/* Clear the ipi register to clear the interrupt */
+	csr_writel(action, LOONGSON_CSR_IPI_CLEAR);
+
+	return action;
+}
+
+static void csr_ipi_write_action(int cpu, u32 action)
+{
+	unsigned int irq = 0;
+
+	while ((irq = ffs(action))) {
+		uint32_t val = CSR_IPI_SEND_BLOCK;
+		val |= (irq - 1);
+		val |= (cpu << CSR_IPI_SEND_CPU_SHIFT);
+		csr_writel(val, LOONGSON_CSR_IPI_SEND);
+		action &= ~BIT(irq - 1);
+	}
+}
+
+static u32 legacy_ipi_read_clear(int cpu)
+{
+	u32 action;
+
+	/* Load the ipi register to figure out what we're supposed to do */
+	action = loongson3_ipi_read32(ipi_status0_regs[cpu_logical_map(cpu)]);
+	/* Clear the ipi register to clear the interrupt */
+	loongson3_ipi_write32(action, ipi_clear0_regs[cpu_logical_map(cpu)]);
+
+	return action;
+}
+
+static void legacy_ipi_write_action(int cpu, u32 action)
+{
+	loongson3_ipi_write32((u32)action, ipi_set0_regs[cpu]);
+}
+
+static void csr_ipi_probe(void)
+{
+	if (cpu_has_csr() && csr_readl(LOONGSON_CSR_FEATURES) & LOONGSON_CSRF_IPI) {
+		ipi_read_clear = csr_ipi_read_clear;
+		ipi_write_action = csr_ipi_write_action;
+	} else {
+		ipi_read_clear = legacy_ipi_read_clear;
+		ipi_write_action = legacy_ipi_write_action;
+	}
+}
+
 static void ipi_set0_regs_init(void)
 {
 	ipi_set0_regs[0] = (void *)
@@ -233,7 +290,7 @@ static void ipi_mailbox_buf_init(void)
  */
 static void loongson3_send_ipi_single(int cpu, unsigned int action)
 {
-	loongson3_ipi_write32((u32)action, ipi_set0_regs[cpu_logical_map(cpu)]);
+	ipi_write_action(cpu_logical_map(cpu), (u32)action);
 }
 
 static void
@@ -242,14 +299,14 @@ loongson3_send_ipi_mask(const struct cpumask *mask, unsigned int action)
 	unsigned int i;
 
 	for_each_cpu(i, mask)
-		loongson3_ipi_write32((u32)action, ipi_set0_regs[cpu_logical_map(i)]);
+		ipi_write_action(cpu_logical_map(i), (u32)action);
 }
 
 #define IPI_IRQ_OFFSET 6
 
 void loongson3_send_irq_by_ipi(int cpu, int irqs)
 {
-	loongson3_ipi_write32(irqs << IPI_IRQ_OFFSET, ipi_set0_regs[cpu_logical_map(cpu)]);
+	ipi_write_action(cpu_logical_map(cpu), irqs << IPI_IRQ_OFFSET);
 }
 
 void loongson3_ipi_interrupt(struct pt_regs *regs)
@@ -257,13 +314,9 @@ void loongson3_ipi_interrupt(struct pt_regs *regs)
 	int i, cpu = smp_processor_id();
 	unsigned int action, c0count, irqs;
 
-	/* Load the ipi register to figure out what we're supposed to do */
-	action = loongson3_ipi_read32(ipi_status0_regs[cpu_logical_map(cpu)]);
+	action = ipi_read_clear(cpu);
 	irqs = action >> IPI_IRQ_OFFSET;
 
-	/* Clear the ipi register to clear the interrupt */
-	loongson3_ipi_write32((u32)action, ipi_clear0_regs[cpu_logical_map(cpu)]);
-
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
@@ -372,6 +425,7 @@ static void __init loongson3_smp_setup(void)
 		num++;
 	}
 
+	csr_ipi_probe();
 	ipi_set0_regs_init();
 	ipi_clear0_regs_init();
 	ipi_status0_regs_init();
@@ -450,7 +504,7 @@ static void loongson3_cpu_die(unsigned int cpu)
  * flush all L1 entries at first. Then, another core (usually Core 0) can
  * safely disable the clock of the target core. loongson3_play_dead() is
  * called via CKSEG1 (uncached and unmmaped) */
-static void loongson3a_r1_play_dead(int *state_addr)
+static void loongson3_type1_play_dead(int *state_addr)
 {
 	register int val;
 	register long cpuid, core, node, count;
@@ -512,7 +566,7 @@ static void loongson3a_r1_play_dead(int *state_addr)
 		: "a1");
 }
 
-static void loongson3a_r2r3_play_dead(int *state_addr)
+static void loongson3_type2_play_dead(int *state_addr)
 {
 	register int val;
 	register long cpuid, core, node, count;
@@ -532,27 +586,7 @@ static void loongson3a_r2r3_play_dead(int *state_addr)
 		"   cache 1, 3(%[addr])           \n"
 		"   addiu %[sets], %[sets], -1    \n"
 		"   bnez  %[sets], 1b             \n"
-		"   addiu %[addr], %[addr], 0x40  \n"
-		"   li %[addr], 0x80000000        \n" /* KSEG0 */
-		"2: cache 2, 0(%[addr])           \n" /* flush L1 VCache */
-		"   cache 2, 1(%[addr])           \n"
-		"   cache 2, 2(%[addr])           \n"
-		"   cache 2, 3(%[addr])           \n"
-		"   cache 2, 4(%[addr])           \n"
-		"   cache 2, 5(%[addr])           \n"
-		"   cache 2, 6(%[addr])           \n"
-		"   cache 2, 7(%[addr])           \n"
-		"   cache 2, 8(%[addr])           \n"
-		"   cache 2, 9(%[addr])           \n"
-		"   cache 2, 10(%[addr])          \n"
-		"   cache 2, 11(%[addr])          \n"
-		"   cache 2, 12(%[addr])          \n"
-		"   cache 2, 13(%[addr])          \n"
-		"   cache 2, 14(%[addr])          \n"
-		"   cache 2, 15(%[addr])          \n"
-		"   addiu %[vsets], %[vsets], -1  \n"
-		"   bnez  %[vsets], 2b            \n"
-		"   addiu %[addr], %[addr], 0x40  \n"
+		"   addiu %[addr], %[addr], 0x20  \n"
 		"   li    %[val], 0x7             \n" /* *state_addr = CPU_DEAD; */
 		"   sw    %[val], (%[state_addr]) \n"
 		"   sync                          \n"
@@ -560,8 +594,7 @@ static void loongson3a_r2r3_play_dead(int *state_addr)
 		"   .set pop                      \n"
 		: [addr] "=&r" (addr), [val] "=&r" (val)
 		: [state_addr] "r" (state_addr),
-		  [sets] "r" (cpu_data[smp_processor_id()].dcache.sets),
-		  [vsets] "r" (cpu_data[smp_processor_id()].vcache.sets));
+		  [sets] "r" (cpu_data[smp_processor_id()].dcache.sets));
 
 	__asm__ __volatile__(
 		"   .set push                         \n"
@@ -576,6 +609,8 @@ static void loongson3a_r2r3_play_dead(int *state_addr)
 		"   andi  %[node], %[cpuid], 0xc      \n"
 		"   dsll  %[node], 42                 \n" /* get node id */
 		"   or    %[base], %[base], %[node]   \n"
+		"   dsrl  %[node], 30                 \n" /* 15:14 */
+		"   or    %[base], %[base], %[node]   \n"
 		"1: li    %[count], 0x100             \n" /* wait for init loop */
 		"2: bnez  %[count], 2b                \n" /* limit mailbox access */
 		"   addiu %[count], -1                \n"
@@ -595,7 +630,7 @@ static void loongson3a_r2r3_play_dead(int *state_addr)
 		: "a1");
 }
 
-static void loongson3b_play_dead(int *state_addr)
+static void loongson3_type3_play_dead(int *state_addr)
 {
 	register int val;
 	register long cpuid, core, node, count;
@@ -615,7 +650,27 @@ static void loongson3b_play_dead(int *state_addr)
 		"   cache 1, 3(%[addr])           \n"
 		"   addiu %[sets], %[sets], -1    \n"
 		"   bnez  %[sets], 1b             \n"
-		"   addiu %[addr], %[addr], 0x20  \n"
+		"   addiu %[addr], %[addr], 0x40  \n"
+		"   li %[addr], 0x80000000        \n" /* KSEG0 */
+		"2: cache 2, 0(%[addr])           \n" /* flush L1 VCache */
+		"   cache 2, 1(%[addr])           \n"
+		"   cache 2, 2(%[addr])           \n"
+		"   cache 2, 3(%[addr])           \n"
+		"   cache 2, 4(%[addr])           \n"
+		"   cache 2, 5(%[addr])           \n"
+		"   cache 2, 6(%[addr])           \n"
+		"   cache 2, 7(%[addr])           \n"
+		"   cache 2, 8(%[addr])           \n"
+		"   cache 2, 9(%[addr])           \n"
+		"   cache 2, 10(%[addr])          \n"
+		"   cache 2, 11(%[addr])          \n"
+		"   cache 2, 12(%[addr])          \n"
+		"   cache 2, 13(%[addr])          \n"
+		"   cache 2, 14(%[addr])          \n"
+		"   cache 2, 15(%[addr])          \n"
+		"   addiu %[vsets], %[vsets], -1  \n"
+		"   bnez  %[vsets], 2b            \n"
+		"   addiu %[addr], %[addr], 0x40  \n"
 		"   li    %[val], 0x7             \n" /* *state_addr = CPU_DEAD; */
 		"   sw    %[val], (%[state_addr]) \n"
 		"   sync                          \n"
@@ -623,7 +678,8 @@ static void loongson3b_play_dead(int *state_addr)
 		"   .set pop                      \n"
 		: [addr] "=&r" (addr), [val] "=&r" (val)
 		: [state_addr] "r" (state_addr),
-		  [sets] "r" (cpu_data[smp_processor_id()].dcache.sets));
+		  [sets] "r" (cpu_data[smp_processor_id()].dcache.sets),
+		  [vsets] "r" (cpu_data[smp_processor_id()].vcache.sets));
 
 	__asm__ __volatile__(
 		"   .set push                         \n"
@@ -638,8 +694,6 @@ static void loongson3b_play_dead(int *state_addr)
 		"   andi  %[node], %[cpuid], 0xc      \n"
 		"   dsll  %[node], 42                 \n" /* get node id */
 		"   or    %[base], %[base], %[node]   \n"
-		"   dsrl  %[node], 30                 \n" /* 15:14 */
-		"   or    %[base], %[base], %[node]   \n"
 		"1: li    %[count], 0x100             \n" /* wait for init loop */
 		"2: bnez  %[count], 2b                \n" /* limit mailbox access */
 		"   addiu %[count], -1                \n"
@@ -661,30 +715,42 @@ static void loongson3b_play_dead(int *state_addr)
 
 void play_dead(void)
 {
-	int *state_addr;
+	int prid_imp, prid_rev, *state_addr;
 	unsigned int cpu = smp_processor_id();
 	void (*play_dead_at_ckseg1)(int *);
 
 	idle_task_exit();
-	switch (read_c0_prid() & PRID_REV_MASK) {
+
+	prid_imp = read_c0_prid() & PRID_IMP_MASK;
+	prid_rev = read_c0_prid() & PRID_REV_MASK;
+
+	if (prid_imp == PRID_IMP_LOONGSON_64G) {
+		play_dead_at_ckseg1 =
+			(void *)CKSEG1ADDR((unsigned long)loongson3_type3_play_dead);
+		goto out;
+	}
+
+	switch (prid_rev) {
 	case PRID_REV_LOONGSON3A_R1:
 	default:
 		play_dead_at_ckseg1 =
-			(void *)CKSEG1ADDR((unsigned long)loongson3a_r1_play_dead);
+			(void *)CKSEG1ADDR((unsigned long)loongson3_type1_play_dead);
+		break;
+	case PRID_REV_LOONGSON3B_R1:
+	case PRID_REV_LOONGSON3B_R2:
+		play_dead_at_ckseg1 =
+			(void *)CKSEG1ADDR((unsigned long)loongson3_type2_play_dead);
 		break;
 	case PRID_REV_LOONGSON3A_R2_0:
 	case PRID_REV_LOONGSON3A_R2_1:
 	case PRID_REV_LOONGSON3A_R3_0:
 	case PRID_REV_LOONGSON3A_R3_1:
 		play_dead_at_ckseg1 =
-			(void *)CKSEG1ADDR((unsigned long)loongson3a_r2r3_play_dead);
-		break;
-	case PRID_REV_LOONGSON3B_R1:
-	case PRID_REV_LOONGSON3B_R2:
-		play_dead_at_ckseg1 =
-			(void *)CKSEG1ADDR((unsigned long)loongson3b_play_dead);
+			(void *)CKSEG1ADDR((unsigned long)loongson3_type3_play_dead);
 		break;
 	}
+
+out:
 	state_addr = &per_cpu(cpu_state, cpu);
 	mb();
 	play_dead_at_ckseg1(state_addr);
diff --git a/arch/mips/loongson64/loongson-3/smp.h b/arch/mips/loongson64/smp.h
index 957bde81e0e4..957bde81e0e4 100644
--- a/arch/mips/loongson64/loongson-3/smp.h
+++ b/arch/mips/loongson64/smp.h
diff --git a/arch/mips/loongson64/time.c b/arch/mips/loongson64/time.c
new file mode 100644
index 000000000000..1245f22cec84
--- /dev/null
+++ b/arch/mips/loongson64/time.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2007 Lemote, Inc. & Institute of Computing Technology
+ * Author: Fuxin Zhang, zhangfx@lemote.com
+ *
+ * Copyright (C) 2009 Lemote Inc.
+ * Author: Wu Zhangjin, wuzhangjin@gmail.com
+ */
+#include <asm/mc146818-time.h>
+#include <asm/time.h>
+#include <asm/hpet.h>
+
+#include <loongson.h>
+
+void __init plat_time_init(void)
+{
+	/* setup mips r4k timer */
+	mips_hpt_frequency = cpu_clock_freq / 2;
+
+#ifdef CONFIG_RS780_HPET
+	setup_hpet_timer();
+#endif
+}
+
+void read_persistent_clock64(struct timespec64 *ts)
+{
+	ts->tv_sec = mc146818_get_cmos_time();
+	ts->tv_nsec = 0;
+}
diff --git a/arch/mips/math-emu/me-debugfs.c b/arch/mips/math-emu/me-debugfs.c
index 387724860fa6..d5ad76b2bb67 100644
--- a/arch/mips/math-emu/me-debugfs.c
+++ b/arch/mips/math-emu/me-debugfs.c
@@ -189,6 +189,7 @@ static int __init debugfs_fpuemu(void)
 {
 	struct dentry *fpuemu_debugfs_base_dir;
 	struct dentry *fpuemu_debugfs_inst_dir;
+	char name[32];
 
 	fpuemu_debugfs_base_dir = debugfs_create_dir("fpuemustats",
 						     mips_debugfs_dir);
@@ -225,8 +226,6 @@ do {									\
 
 #define FPU_STAT_CREATE_EX(m)						\
 do {									\
-	char name[32];							\
-									\
 	adjust_instruction_counter_name(name, #m);			\
 									\
 	debugfs_create_file(name, 0444, fpuemu_debugfs_inst_dir,	\
diff --git a/arch/mips/mm/c-r3k.c b/arch/mips/mm/c-r3k.c
index 0ca401ddf3b7..15bb8cf59828 100644
--- a/arch/mips/mm/c-r3k.c
+++ b/arch/mips/mm/c-r3k.c
@@ -241,6 +241,7 @@ static void r3k_flush_cache_page(struct vm_area_struct *vma,
 	int exec = vma->vm_flags & VM_EXEC;
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgdp;
+	p4d_t *p4dp;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
@@ -253,7 +254,8 @@ static void r3k_flush_cache_page(struct vm_area_struct *vma,
 		return;
 
 	pgdp = pgd_offset(mm, addr);
-	pudp = pud_offset(pgdp, addr);
+	p4dp = p4d_offset(pgdp, addr);
+	pudp = pud_offset(p4dp, addr);
 	pmdp = pmd_offset(pudp, addr);
 	ptep = pte_offset(pmdp, addr);
 
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 89b9c851d822..5f3d0103b95d 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -271,12 +271,14 @@ static inline void tx49_blast_icache32(void)
 	/* I'm in even chunk.  blast odd chunks */
 	for (ws = 0; ws < ws_end; ws += ws_inc)
 		for (addr = start + 0x400; addr < end; addr += 0x400 * 2)
-			cache32_unroll32(addr|ws, Index_Invalidate_I);
+			cache_unroll(32, kernel_cache, Index_Invalidate_I,
+				     addr | ws, 32);
 	CACHE32_UNROLL32_ALIGN;
 	/* I'm in odd chunk.  blast even chunks */
 	for (ws = 0; ws < ws_end; ws += ws_inc)
 		for (addr = start; addr < end; addr += 0x400 * 2)
-			cache32_unroll32(addr|ws, Index_Invalidate_I);
+			cache_unroll(32, kernel_cache, Index_Invalidate_I,
+				     addr | ws, 32);
 }
 
 static inline void blast_icache32_r4600_v1_page_indexed(unsigned long page)
@@ -302,12 +304,14 @@ static inline void tx49_blast_icache32_page_indexed(unsigned long page)
 	/* I'm in even chunk.  blast odd chunks */
 	for (ws = 0; ws < ws_end; ws += ws_inc)
 		for (addr = start + 0x400; addr < end; addr += 0x400 * 2)
-			cache32_unroll32(addr|ws, Index_Invalidate_I);
+			cache_unroll(32, kernel_cache, Index_Invalidate_I,
+				     addr | ws, 32);
 	CACHE32_UNROLL32_ALIGN;
 	/* I'm in odd chunk.  blast even chunks */
 	for (ws = 0; ws < ws_end; ws += ws_inc)
 		for (addr = start; addr < end; addr += 0x400 * 2)
-			cache32_unroll32(addr|ws, Index_Invalidate_I);
+			cache_unroll(32, kernel_cache, Index_Invalidate_I,
+				     addr | ws, 32);
 }
 
 static void (* r4k_blast_icache_page)(unsigned long addr);
@@ -320,7 +324,7 @@ static void r4k_blast_icache_page_setup(void)
 		r4k_blast_icache_page = (void *)cache_noop;
 	else if (ic_lsize == 16)
 		r4k_blast_icache_page = blast_icache16_page;
-	else if (ic_lsize == 32 && current_cpu_type() == CPU_LOONGSON2)
+	else if (ic_lsize == 32 && current_cpu_type() == CPU_LOONGSON2EF)
 		r4k_blast_icache_page = loongson2_blast_icache32_page;
 	else if (ic_lsize == 32)
 		r4k_blast_icache_page = blast_icache32_page;
@@ -369,7 +373,7 @@ static void r4k_blast_icache_page_indexed_setup(void)
 		else if (TX49XX_ICACHE_INDEX_INV_WAR)
 			r4k_blast_icache_page_indexed =
 				tx49_blast_icache32_page_indexed;
-		else if (current_cpu_type() == CPU_LOONGSON2)
+		else if (current_cpu_type() == CPU_LOONGSON2EF)
 			r4k_blast_icache_page_indexed =
 				loongson2_blast_icache32_page_indexed;
 		else
@@ -395,7 +399,7 @@ static void r4k_blast_icache_setup(void)
 			r4k_blast_icache = blast_r4600_v1_icache32;
 		else if (TX49XX_ICACHE_INDEX_INV_WAR)
 			r4k_blast_icache = tx49_blast_icache32;
-		else if (current_cpu_type() == CPU_LOONGSON2)
+		else if (current_cpu_type() == CPU_LOONGSON2EF)
 			r4k_blast_icache = loongson2_blast_icache32;
 		else
 			r4k_blast_icache = blast_icache32;
@@ -465,7 +469,7 @@ static void r4k_blast_scache_node_setup(void)
 {
 	unsigned long sc_lsize = cpu_scache_line_size();
 
-	if (current_cpu_type() != CPU_LOONGSON3)
+	if (current_cpu_type() != CPU_LOONGSON64)
 		r4k_blast_scache_node = (void *)cache_noop;
 	else if (sc_lsize == 16)
 		r4k_blast_scache_node = blast_scache16_node;
@@ -480,7 +484,7 @@ static void r4k_blast_scache_node_setup(void)
 static inline void local_r4k___flush_cache_all(void * args)
 {
 	switch (current_cpu_type()) {
-	case CPU_LOONGSON2:
+	case CPU_LOONGSON2EF:
 	case CPU_R4000SC:
 	case CPU_R4000MC:
 	case CPU_R4400SC:
@@ -497,7 +501,7 @@ static inline void local_r4k___flush_cache_all(void * args)
 		r4k_blast_scache();
 		break;
 
-	case CPU_LOONGSON3:
+	case CPU_LOONGSON64:
 		/* Use get_ebase_cpunum() for both NUMA=y/n */
 		r4k_blast_scache_node(get_ebase_cpunum() >> 2);
 		break;
@@ -650,6 +654,7 @@ static inline void local_r4k_flush_cache_page(void *args)
 	struct mm_struct *mm = vma->vm_mm;
 	int map_coherent = 0;
 	pgd_t *pgdp;
+	p4d_t *p4dp;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
@@ -664,7 +669,8 @@ static inline void local_r4k_flush_cache_page(void *args)
 
 	addr &= PAGE_MASK;
 	pgdp = pgd_offset(mm, addr);
-	pudp = pud_offset(pgdp, addr);
+	p4dp = p4d_offset(pgdp, addr);
+	pudp = pud_offset(p4dp, addr);
 	pmdp = pmd_offset(pudp, addr);
 	ptep = pte_offset(pmdp, addr);
 
@@ -770,7 +776,7 @@ static inline void __local_r4k_flush_icache_range(unsigned long start,
 		r4k_blast_icache();
 	else {
 		switch (boot_cpu_type()) {
-		case CPU_LOONGSON2:
+		case CPU_LOONGSON2EF:
 			protected_loongson2_blast_icache_range(start, end);
 			break;
 
@@ -863,7 +869,7 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
 		if (size >= scache_size) {
-			if (current_cpu_type() != CPU_LOONGSON3)
+			if (current_cpu_type() != CPU_LOONGSON64)
 				r4k_blast_scache();
 			else
 				r4k_blast_scache_node(pa_to_nid(addr));
@@ -904,7 +910,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
 		if (size >= scache_size) {
-			if (current_cpu_type() != CPU_LOONGSON3)
+			if (current_cpu_type() != CPU_LOONGSON64)
 				r4k_blast_scache();
 			else
 				r4k_blast_scache_node(pa_to_nid(addr));
@@ -1224,7 +1230,7 @@ static void probe_pcache(void)
 		c->options |= MIPS_CPU_PREFETCH;
 		break;
 
-	case CPU_LOONGSON2:
+	case CPU_LOONGSON2EF:
 		icache_size = 1 << (12 + ((config & CONF_IC) >> 9));
 		c->icache.linesz = 16 << ((config & CONF_IB) >> 5);
 		if (prid & 0x3)
@@ -1242,7 +1248,7 @@ static void probe_pcache(void)
 		c->dcache.waybit = 0;
 		break;
 
-	case CPU_LOONGSON3:
+	case CPU_LOONGSON64:
 		config1 = read_c0_config1();
 		lsize = (config1 >> 19) & 7;
 		if (lsize)
@@ -1267,7 +1273,8 @@ static void probe_pcache(void)
 					  c->dcache.ways *
 					  c->dcache.linesz;
 		c->dcache.waybit = 0;
-		if ((prid & PRID_REV_MASK) >= PRID_REV_LOONGSON3A_R2_0)
+		if ((c->processor_id & (PRID_IMP_MASK | PRID_REV_MASK)) >=
+				(PRID_IMP_LOONGSON_64C | PRID_REV_LOONGSON3A_R2_0))
 			c->options |= MIPS_CPU_PREFETCH;
 		break;
 
@@ -1452,7 +1459,7 @@ static void probe_pcache(void)
 		c->dcache.flags &= ~MIPS_CACHE_ALIASES;
 		break;
 
-	case CPU_LOONGSON2:
+	case CPU_LOONGSON2EF:
 		/*
 		 * LOONGSON2 has 4 way icache, but when using indexed cache op,
 		 * one op will act on all 4 ways
@@ -1478,7 +1485,7 @@ static void probe_vcache(void)
 	struct cpuinfo_mips *c = &current_cpu_data;
 	unsigned int config2, lsize;
 
-	if (current_cpu_type() != CPU_LOONGSON3)
+	if (current_cpu_type() != CPU_LOONGSON64)
 		return;
 
 	config2 = read_c0_config2();
@@ -1653,11 +1660,11 @@ static void setup_scache(void)
 #endif
 		return;
 
-	case CPU_LOONGSON2:
+	case CPU_LOONGSON2EF:
 		loongson2_sc_init();
 		return;
 
-	case CPU_LOONGSON3:
+	case CPU_LOONGSON64:
 		loongson3_sc_init();
 		return;
 
@@ -1926,7 +1933,7 @@ void r4k_cache_init(void)
 		/* Optimization: an L2 flush implicitly flushes the L1 */
 		current_cpu_data.options |= MIPS_CPU_INCLUSIVE_CACHES;
 		break;
-	case CPU_LOONGSON3:
+	case CPU_LOONGSON64:
 		/* Loongson-3 maintains cache coherency by hardware */
 		__flush_cache_all	= cache_noop;
 		__flush_cache_vmap	= cache_noop;
diff --git a/arch/mips/mm/c-tx39.c b/arch/mips/mm/c-tx39.c
index b7c8a9d79c35..686867270627 100644
--- a/arch/mips/mm/c-tx39.c
+++ b/arch/mips/mm/c-tx39.c
@@ -170,6 +170,7 @@ static void tx39_flush_cache_page(struct vm_area_struct *vma, unsigned long page
 	int exec = vma->vm_flags & VM_EXEC;
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgdp;
+	p4d_t *p4dp;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
@@ -183,7 +184,8 @@ static void tx39_flush_cache_page(struct vm_area_struct *vma, unsigned long page
 
 	page &= PAGE_MASK;
 	pgdp = pgd_offset(mm, page);
-	pudp = pud_offset(pgdp, page);
+	p4dp = p4d_offset(pgdp, page);
+	pudp = pud_offset(p4dp, page);
 	pmdp = pmd_offset(pudp, page);
 	ptep = pte_offset(pmdp, page);
 
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index f589aa8f47d9..1e8d00793784 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -292,8 +292,9 @@ vmalloc_fault:
 		 * Do _not_ use "tsk" here. We might be inside
 		 * an interrupt in the middle of a task switch..
 		 */
-		int offset = __pgd_offset(address);
+		int offset = pgd_index(address);
 		pgd_t *pgd, *pgd_k;
+		p4d_t *p4d, *p4d_k;
 		pud_t *pud, *pud_k;
 		pmd_t *pmd, *pmd_k;
 		pte_t *pte_k;
@@ -305,8 +306,13 @@ vmalloc_fault:
 			goto no_context;
 		set_pgd(pgd, *pgd_k);
 
-		pud = pud_offset(pgd, address);
-		pud_k = pud_offset(pgd_k, address);
+		p4d = p4d_offset(pgd, address);
+		p4d_k = p4d_offset(pgd_k, address);
+		if (!p4d_present(*p4d_k))
+			goto no_context;
+
+		pud = pud_offset(p4d, address);
+		pud_k = pud_offset(p4d_k, address);
 		if (!pud_present(*pud_k))
 			goto no_context;
 
diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c
index cef152234312..77ffece9c270 100644
--- a/arch/mips/mm/hugetlbpage.c
+++ b/arch/mips/mm/hugetlbpage.c
@@ -25,11 +25,13 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr,
 		      unsigned long sz)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pte_t *pte = NULL;
 
 	pgd = pgd_offset(mm, addr);
-	pud = pud_alloc(mm, pgd, addr);
+	p4d = p4d_alloc(mm, pgd, addr);
+	pud = pud_alloc(mm, p4d, addr);
 	if (pud)
 		pte = (pte_t *)pmd_alloc(mm, pud, addr);
 
@@ -40,14 +42,18 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
 		       unsigned long sz)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd = NULL;
 
 	pgd = pgd_offset(mm, addr);
 	if (pgd_present(*pgd)) {
-		pud = pud_offset(pgd, addr);
-		if (pud_present(*pud))
-			pmd = pmd_offset(pud, addr);
+		p4d = p4d_offset(pgd, addr);
+		if (p4d_present(*p4d)) {
+			pud = pud_offset(p4d, addr);
+			if (pud_present(*pud))
+				pmd = pmd_offset(pud, addr);
+		}
 	}
 	return (pte_t *) pmd;
 }
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 090fa653dfa9..50f9ed8c6c1b 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -239,9 +239,9 @@ void __init fixrange_init(unsigned long start, unsigned long end,
 	unsigned long vaddr;
 
 	vaddr = start;
-	i = __pgd_offset(vaddr);
-	j = __pud_offset(vaddr);
-	k = __pmd_offset(vaddr);
+	i = pgd_index(vaddr);
+	j = pud_index(vaddr);
+	k = pmd_index(vaddr);
 	pgd = pgd_base + i;
 
 	for ( ; (i < PTRS_PER_PGD) && (vaddr < end); pgd++, i++) {
diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c
index 1601d90b087b..8317f337a86e 100644
--- a/arch/mips/mm/ioremap.c
+++ b/arch/mips/mm/ioremap.c
@@ -78,11 +78,15 @@ static int remap_area_pages(unsigned long address, phys_addr_t phys_addr,
 	flush_cache_all();
 	BUG_ON(address >= end);
 	do {
+		p4d_t *p4d;
 		pud_t *pud;
 		pmd_t *pmd;
 
 		error = -ENOMEM;
-		pud = pud_alloc(&init_mm, dir, address);
+		p4d = p4d_alloc(&init_mm, dir, address);
+		if (!p4d)
+			break;
+		pud = pud_alloc(&init_mm, p4d, address);
 		if (!pud)
 			break;
 		pmd = pmd_alloc(&init_mm, pud, address);
diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c
index 56e4f8bffd4c..c5578897a4fa 100644
--- a/arch/mips/mm/page.c
+++ b/arch/mips/mm/page.c
@@ -187,7 +187,7 @@ static void set_prefetch_parameters(void)
 			}
 			break;
 
-		case CPU_LOONGSON3:
+		case CPU_LOONGSON64:
 			/* Loongson-3 only support the Pref_Load/Pref_Store. */
 			pref_bias_clear_store = 128;
 			pref_bias_copy_load = 128;
diff --git a/arch/mips/mm/pgtable-32.c b/arch/mips/mm/pgtable-32.c
index 6416a531a4c3..37c7a01427d2 100644
--- a/arch/mips/mm/pgtable-32.c
+++ b/arch/mips/mm/pgtable-32.c
@@ -56,6 +56,7 @@ void __init pagetable_init(void)
 	pgd_t *pgd_base;
 #ifdef CONFIG_HIGHMEM
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -81,8 +82,9 @@ void __init pagetable_init(void)
 	vaddr = PKMAP_BASE;
 	fixrange_init(vaddr & PMD_MASK, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base);
 
-	pgd = swapper_pg_dir + __pgd_offset(vaddr);
-	pud = pud_offset(pgd, vaddr);
+	pgd = swapper_pg_dir + pgd_index(vaddr);
+	p4d = p4d_offset(pgd, vaddr);
+	pud = pud_offset(p4d, vaddr);
 	pmd = pmd_offset(pud, vaddr);
 	pte = pte_offset_kernel(pmd, vaddr);
 	pkmap_page_table = pte;
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index c13e46ced425..d7a9d5f211f0 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -35,10 +35,10 @@ extern void build_tlb_refill_handler(void);
 static inline void flush_micro_tlb(void)
 {
 	switch (current_cpu_type()) {
-	case CPU_LOONGSON2:
+	case CPU_LOONGSON2EF:
 		write_c0_diag(LOONGSON_DIAG_ITLB);
 		break;
-	case CPU_LOONGSON3:
+	case CPU_LOONGSON64:
 		write_c0_diag(LOONGSON_DIAG_ITLB | LOONGSON_DIAG_DTLB);
 		break;
 	default:
@@ -295,6 +295,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte)
 {
 	unsigned long flags;
 	pgd_t *pgdp;
+	p4d_t *p4dp;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
@@ -320,7 +321,8 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte)
 	mtc0_tlbw_hazard();
 	tlb_probe();
 	tlb_probe_hazard();
-	pudp = pud_offset(pgdp, address);
+	p4dp = p4d_offset(pgdp, address);
+	pudp = pud_offset(p4dp, address);
 	pmdp = pmd_offset(pudp, address);
 	idx = read_c0_index();
 #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 41bb91f05688..344e6e9ea43b 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -571,8 +571,8 @@ void build_tlb_write_entry(u32 **p, struct uasm_label **l,
 	case CPU_BMIPS4350:
 	case CPU_BMIPS4380:
 	case CPU_BMIPS5000:
-	case CPU_LOONGSON2:
-	case CPU_LOONGSON3:
+	case CPU_LOONGSON2EF:
+	case CPU_LOONGSON64:
 	case CPU_R5500:
 		if (m4kc_tlbp_war())
 			uasm_i_nop(p);
@@ -1377,7 +1377,7 @@ static void build_r4000_tlb_refill_handler(void)
 	switch (boot_cpu_type()) {
 	default:
 		if (sizeof(long) == 4) {
-	case CPU_LOONGSON2:
+	case CPU_LOONGSON2EF:
 		/* Loongson2 ebase is different than r4k, we have more space */
 			if ((p - tlb_handler) > 64)
 				panic("TLB refill handler space exceeded");
diff --git a/arch/mips/oprofile/Makefile b/arch/mips/oprofile/Makefile
index 011cf9f891e7..e10f216d0422 100644
--- a/arch/mips/oprofile/Makefile
+++ b/arch/mips/oprofile/Makefile
@@ -14,5 +14,5 @@ oprofile-$(CONFIG_CPU_MIPS64)		+= op_model_mipsxx.o
 oprofile-$(CONFIG_CPU_R10000)		+= op_model_mipsxx.o
 oprofile-$(CONFIG_CPU_SB1)		+= op_model_mipsxx.o
 oprofile-$(CONFIG_CPU_XLR)		+= op_model_mipsxx.o
-oprofile-$(CONFIG_CPU_LOONGSON2)	+= op_model_loongson2.o
-oprofile-$(CONFIG_CPU_LOONGSON3)	+= op_model_loongson3.o
+oprofile-$(CONFIG_CPU_LOONGSON2EF)	+= op_model_loongson2.o
+oprofile-$(CONFIG_CPU_LOONGSON64)	+= op_model_loongson3.o
diff --git a/arch/mips/oprofile/common.c b/arch/mips/oprofile/common.c
index 2f33992f6dff..03db268cba5c 100644
--- a/arch/mips/oprofile/common.c
+++ b/arch/mips/oprofile/common.c
@@ -93,7 +93,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	case CPU_P5600:
 	case CPU_I6400:
 	case CPU_M5150:
-	case CPU_LOONGSON1:
+	case CPU_LOONGSON32:
 	case CPU_SB1:
 	case CPU_SB1A:
 	case CPU_R10000:
@@ -104,10 +104,10 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 		lmodel = &op_model_mipsxx_ops;
 		break;
 
-	case CPU_LOONGSON2:
+	case CPU_LOONGSON2EF:
 		lmodel = &op_model_loongson2_ops;
 		break;
-	case CPU_LOONGSON3:
+	case CPU_LOONGSON64:
 		lmodel = &op_model_loongson3_ops;
 		break;
 	};
diff --git a/arch/mips/oprofile/op_model_mipsxx.c b/arch/mips/oprofile/op_model_mipsxx.c
index 96c13a0ab078..a537bf98912c 100644
--- a/arch/mips/oprofile/op_model_mipsxx.c
+++ b/arch/mips/oprofile/op_model_mipsxx.c
@@ -420,7 +420,7 @@ static int __init mipsxx_init(void)
 		op_model_mipsxx_ops.cpu_type = "mips/sb1";
 		break;
 
-	case CPU_LOONGSON1:
+	case CPU_LOONGSON32:
 		op_model_mipsxx_ops.cpu_type = "mips/loongson1";
 		break;
 
diff --git a/arch/mips/pci/Makefile b/arch/mips/pci/Makefile
index d6de4cb2e31c..342ce10ef593 100644
--- a/arch/mips/pci/Makefile
+++ b/arch/mips/pci/Makefile
@@ -35,7 +35,7 @@ obj-$(CONFIG_LASAT)		+= pci-lasat.o
 obj-$(CONFIG_MIPS_COBALT)	+= fixup-cobalt.o
 obj-$(CONFIG_LEMOTE_FULOONG2E)	+= fixup-fuloong2e.o ops-loongson2.o
 obj-$(CONFIG_LEMOTE_MACH2F)	+= fixup-lemote2f.o ops-loongson2.o
-obj-$(CONFIG_LOONGSON_MACH3X)	+= fixup-loongson3.o ops-loongson3.o
+obj-$(CONFIG_MACH_LOONGSON64)	+= fixup-loongson3.o ops-loongson3.o
 obj-$(CONFIG_MIPS_MALTA)	+= fixup-malta.o pci-malta.o
 obj-$(CONFIG_PMC_MSP7120_GW)	+= fixup-pmcmsp.o ops-pmcmsp.o
 obj-$(CONFIG_PMC_MSP7120_EVAL)	+= fixup-pmcmsp.o ops-pmcmsp.o
diff --git a/arch/mips/pci/pci-ip27.c b/arch/mips/pci/pci-ip27.c
index 441eb9383b20..8e26b120f994 100644
--- a/arch/mips/pci/pci-ip27.c
+++ b/arch/mips/pci/pci-ip27.c
@@ -7,21 +7,13 @@
  * Copyright (C) 1999, 2000, 04 Ralf Baechle (ralf@linux-mips.org)
  * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
  */
+#include <asm/sn/addrs.h>
+#include <asm/sn/types.h>
+#include <asm/sn/klconfig.h>
+#include <asm/sn/hub.h>
+#include <asm/sn/ioc3.h>
 #include <asm/pci/bridge.h>
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct bridge_controller *bc = BRIDGE_CONTROLLER(pdev->bus);
-
-	return bc->baddr + paddr;
-}
-
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr & ~(0xffUL << 56);
-}
-
 #ifdef CONFIG_NUMA
 int pcibus_to_node(struct pci_bus *bus)
 {
@@ -31,3 +23,20 @@ int pcibus_to_node(struct pci_bus *bus)
 }
 EXPORT_SYMBOL(pcibus_to_node);
 #endif /* CONFIG_NUMA */
+
+static void ip29_fixup_phy(struct pci_dev *dev)
+{
+	int nasid = pcibus_to_node(dev->bus);
+	u32 sid;
+
+	if (nasid != 1)
+		return; /* only needed on second module */
+
+	/* enable ethernet PHY on IP29 systemboard */
+	pci_read_config_dword(dev, PCI_SUBSYSTEM_VENDOR_ID, &sid);
+	if (sid == (PCI_VENDOR_ID_SGI | (IOC3_SUBSYS_IP29_SYSBOARD) << 16))
+		REMOTE_HUB_S(nasid, MD_LED0, 0x09);
+}
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SGI, PCI_DEVICE_ID_SGI_IOC3,
+			ip29_fixup_phy);
diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c
index 7b4d40354ee7..5c1a196be0c5 100644
--- a/arch/mips/pci/pci-xtalk-bridge.c
+++ b/arch/mips/pci/pci-xtalk-bridge.c
@@ -11,16 +11,38 @@
 #include <linux/dma-direct.h>
 #include <linux/platform_device.h>
 #include <linux/platform_data/xtalk-bridge.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/crc16.h>
 
 #include <asm/pci/bridge.h>
 #include <asm/paccess.h>
 #include <asm/sn/irq_alloc.h>
+#include <asm/sn/ioc3.h>
+
+#define CRC16_INIT	0
+#define CRC16_VALID	0xb001
+
+/*
+ * Common phys<->dma mapping for platforms using pci xtalk bridge
+ */
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct bridge_controller *bc = BRIDGE_CONTROLLER(pdev->bus);
+
+	return bc->baddr + paddr;
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr & ~(0xffUL << 56);
+}
 
 /*
  * Most of the IOC3 PCI config register aren't present
  * we emulate what is needed for a normal PCI enumeration
  */
-static int ioc3_cfg_rd(void *addr, int where, int size, u32 *value)
+static int ioc3_cfg_rd(void *addr, int where, int size, u32 *value, u32 sid)
 {
 	u32 cf, shift, mask;
 
@@ -30,6 +52,9 @@ static int ioc3_cfg_rd(void *addr, int where, int size, u32 *value)
 		if (get_dbe(cf, (u32 *)addr))
 			return PCIBIOS_DEVICE_NOT_FOUND;
 		break;
+	case 0x2c:
+		cf = sid;
+		break;
 	case 0x3c:
 		/* emulate sane interrupt pin value */
 		cf = 0x00000100;
@@ -111,7 +136,8 @@ static int pci_conf0_read_config(struct pci_bus *bus, unsigned int devfn,
 	 */
 	if (cf == (PCI_VENDOR_ID_SGI | (PCI_DEVICE_ID_SGI_IOC3 << 16))) {
 		addr = &bridge->b_type0_cfg_dev[slot].f[fn].l[where >> 2];
-		return ioc3_cfg_rd(addr, where, size, value);
+		return ioc3_cfg_rd(addr, where, size, value,
+				   bc->ioc3_sid[slot]);
 	}
 
 	addr = &bridge->b_type0_cfg_dev[slot].f[fn].c[where ^ (4 - size)];
@@ -149,7 +175,8 @@ static int pci_conf1_read_config(struct pci_bus *bus, unsigned int devfn,
 	 */
 	if (cf == (PCI_VENDOR_ID_SGI | (PCI_DEVICE_ID_SGI_IOC3 << 16))) {
 		addr = &bridge->b_type1_cfg.c[(fn << 8) | (where & ~3)];
-		return ioc3_cfg_rd(addr, where, size, value);
+		return ioc3_cfg_rd(addr, where, size, value,
+				   bc->ioc3_sid[slot]);
 	}
 
 	addr = &bridge->b_type1_cfg.c[(fn << 8) | (where ^ (4 - size))];
@@ -279,16 +306,15 @@ static int bridge_set_affinity(struct irq_data *d, const struct cpumask *mask,
 	struct bridge_irq_chip_data *data = d->chip_data;
 	int bit = d->parent_data->hwirq;
 	int pin = d->hwirq;
-	nasid_t nasid;
 	int ret, cpu;
 
 	ret = irq_chip_set_affinity_parent(d, mask, force);
 	if (ret >= 0) {
 		cpu = cpumask_first_and(mask, cpu_online_mask);
-		nasid = COMPACT_TO_NASID_NODEID(cpu_to_node(cpu));
+		data->nasid = cpu_to_node(cpu);
 		bridge_write(data->bc, b_int_addr[pin].addr,
 			     (((data->bc->intr_addr >> 30) & 0x30000) |
-			      bit | (nasid << 8)));
+			      bit | (data->nasid << 8)));
 		bridge_read(data->bc, b_wid_tflush);
 	}
 	return ret;
@@ -426,6 +452,117 @@ static int bridge_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return irq;
 }
 
+#define IOC3_SID(sid)	(PCI_VENDOR_ID_SGI | ((sid) << 16))
+
+static void bridge_setup_ip27_baseio6g(struct bridge_controller *bc)
+{
+	bc->ioc3_sid[2] = IOC3_SID(IOC3_SUBSYS_IP27_BASEIO6G);
+	bc->ioc3_sid[6] = IOC3_SID(IOC3_SUBSYS_IP27_MIO);
+}
+
+static void bridge_setup_ip27_baseio(struct bridge_controller *bc)
+{
+	bc->ioc3_sid[2] = IOC3_SID(IOC3_SUBSYS_IP27_BASEIO);
+}
+
+static void bridge_setup_ip29_baseio(struct bridge_controller *bc)
+{
+	bc->ioc3_sid[2] = IOC3_SID(IOC3_SUBSYS_IP29_SYSBOARD);
+}
+
+static void bridge_setup_ip30_sysboard(struct bridge_controller *bc)
+{
+	bc->ioc3_sid[2] = IOC3_SID(IOC3_SUBSYS_IP30_SYSBOARD);
+}
+
+static void bridge_setup_menet(struct bridge_controller *bc)
+{
+	bc->ioc3_sid[0] = IOC3_SID(IOC3_SUBSYS_MENET);
+	bc->ioc3_sid[1] = IOC3_SID(IOC3_SUBSYS_MENET);
+	bc->ioc3_sid[2] = IOC3_SID(IOC3_SUBSYS_MENET);
+	bc->ioc3_sid[3] = IOC3_SID(IOC3_SUBSYS_MENET4);
+}
+
+#define BRIDGE_BOARD_SETUP(_partno, _setup)	\
+	{ .match = _partno, .setup = _setup }
+
+static const struct {
+	char *match;
+	void (*setup)(struct bridge_controller *bc);
+} bridge_ioc3_devid[] = {
+	BRIDGE_BOARD_SETUP("030-0734-", bridge_setup_ip27_baseio6g),
+	BRIDGE_BOARD_SETUP("030-0880-", bridge_setup_ip27_baseio6g),
+	BRIDGE_BOARD_SETUP("030-1023-", bridge_setup_ip27_baseio),
+	BRIDGE_BOARD_SETUP("030-1124-", bridge_setup_ip27_baseio),
+	BRIDGE_BOARD_SETUP("030-1025-", bridge_setup_ip29_baseio),
+	BRIDGE_BOARD_SETUP("030-1244-", bridge_setup_ip29_baseio),
+	BRIDGE_BOARD_SETUP("030-1389-", bridge_setup_ip29_baseio),
+	BRIDGE_BOARD_SETUP("030-0887-", bridge_setup_ip30_sysboard),
+	BRIDGE_BOARD_SETUP("030-1467-", bridge_setup_ip30_sysboard),
+	BRIDGE_BOARD_SETUP("030-0873-", bridge_setup_menet),
+};
+
+static void bridge_setup_board(struct bridge_controller *bc, char *partnum)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(bridge_ioc3_devid); i++)
+		if (!strncmp(partnum, bridge_ioc3_devid[i].match,
+			     strlen(bridge_ioc3_devid[i].match))) {
+			bridge_ioc3_devid[i].setup(bc);
+		}
+}
+
+static int bridge_nvmem_match(struct device *dev, const void *data)
+{
+	const char *name = dev_name(dev);
+	const char *prefix = data;
+
+	if (strlen(name) < strlen(prefix))
+		return 0;
+
+	return memcmp(prefix, dev_name(dev), strlen(prefix)) == 0;
+}
+
+static int bridge_get_partnum(u64 baddr, char *partnum)
+{
+	struct nvmem_device *nvmem;
+	char prefix[24];
+	u8 prom[64];
+	int i, j;
+	int ret;
+
+	snprintf(prefix, sizeof(prefix), "bridge-%012llx-0b-", baddr);
+
+	nvmem = nvmem_device_find(prefix, bridge_nvmem_match);
+	if (IS_ERR(nvmem))
+		return PTR_ERR(nvmem);
+
+	ret = nvmem_device_read(nvmem, 0, 64, prom);
+	nvmem_device_put(nvmem);
+
+	if (ret != 64)
+		return ret;
+
+	if (crc16(CRC16_INIT, prom, 32) != CRC16_VALID ||
+	    crc16(CRC16_INIT, prom + 32, 32) != CRC16_VALID)
+		return -EINVAL;
+
+	/* Assemble part number */
+	j = 0;
+	for (i = 0; i < 19; i++)
+		if (prom[i + 11] != ' ')
+			partnum[j++] = prom[i + 11];
+
+	for (i = 0; i < 6; i++)
+		if (prom[i + 32] != ' ')
+			partnum[j++] = prom[i + 32];
+
+	partnum[j] = 0;
+
+	return 0;
+}
+
 static int bridge_probe(struct platform_device *pdev)
 {
 	struct xtalk_bridge_platform_data *bd = dev_get_platdata(&pdev->dev);
@@ -434,9 +571,14 @@ static int bridge_probe(struct platform_device *pdev)
 	struct pci_host_bridge *host;
 	struct irq_domain *domain, *parent;
 	struct fwnode_handle *fn;
+	char partnum[26];
 	int slot;
 	int err;
 
+	/* get part number from one wire prom */
+	if (bridge_get_partnum(virt_to_phys((void *)bd->bridge_addr), partnum))
+		return -EPROBE_DEFER; /* not available yet */
+
 	parent = irq_get_default_host();
 	if (!parent)
 		return -ENODEV;
@@ -517,6 +659,8 @@ static int bridge_probe(struct platform_device *pdev)
 	}
 	bridge_read(bc, b_wid_tflush);	  /* wait until Bridge PIO complete */
 
+	bridge_setup_board(bc, partnum);
+
 	host->dev.parent = dev;
 	host->sysdata = bc;
 	host->busnr = 0;
diff --git a/arch/mips/power/cpu.c b/arch/mips/power/cpu.c
index 3340a5530de3..a15e29dfc7b3 100644
--- a/arch/mips/power/cpu.c
+++ b/arch/mips/power/cpu.c
@@ -19,8 +19,8 @@ void save_processor_state(void)
 
 	if (is_fpu_owner())
 		save_fp(current);
-	if (cpu_has_dsp)
-		save_dsp(current);
+
+	save_dsp(current);
 }
 
 void restore_processor_state(void)
@@ -29,8 +29,8 @@ void restore_processor_state(void)
 
 	if (is_fpu_owner())
 		restore_fp(current);
-	if (cpu_has_dsp)
-		restore_dsp(current);
+
+	restore_dsp(current);
 }
 
 int pfn_is_nosave(unsigned long pfn)
diff --git a/arch/mips/sgi-ip22/ip22-mc.c b/arch/mips/sgi-ip22/ip22-mc.c
index 1944d41507ef..74e5b9e27d6c 100644
--- a/arch/mips/sgi-ip22/ip22-mc.c
+++ b/arch/mips/sgi-ip22/ip22-mc.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
+#include <linux/memblock.h>
 #include <linux/spinlock.h>
 
 #include <asm/io.h>
@@ -40,70 +41,36 @@ static inline unsigned int get_bank_config(int bank)
 	return bank % 2 ? res & 0xffff : res >> 16;
 }
 
-struct mem {
-	unsigned long addr;
-	unsigned long size;
-};
-
+#if defined(CONFIG_SGI_IP28) || defined(CONFIG_32BIT)
+static void __init probe_memory(void)
+{
+	/* prom detects all usable memory */
+}
+#else
 /*
- * Detect installed memory, do some sanity checks and notify kernel about it
+ * Detect installed memory, which PROM misses
  */
 static void __init probe_memory(void)
 {
-	int i, j, found, cnt = 0;
-	struct mem bank[4];
-	struct mem space[2] = {{SGIMC_SEG0_BADDR, 0}, {SGIMC_SEG1_BADDR, 0}};
+	unsigned long addr, size;
+	int i;
 
 	printk(KERN_INFO "MC: Probing memory configuration:\n");
-	for (i = 0; i < ARRAY_SIZE(bank); i++) {
+	for (i = 0; i < 4; i++) {
 		unsigned int tmp = get_bank_config(i);
 		if (!(tmp & SGIMC_MCONFIG_BVALID))
 			continue;
 
-		bank[cnt].size = get_bank_size(tmp);
-		bank[cnt].addr = get_bank_addr(tmp);
+		size = get_bank_size(tmp);
+		addr = get_bank_addr(tmp);
 		printk(KERN_INFO " bank%d: %3ldM @ %08lx\n",
-			i, bank[cnt].size / 1024 / 1024, bank[cnt].addr);
-		cnt++;
-	}
+			i, size / 1024 / 1024, addr);
 
-	/* And you thought bubble sort is dead algorithm... */
-	do {
-		unsigned long addr, size;
-
-		found = 0;
-		for (i = 1; i < cnt; i++)
-			if (bank[i-1].addr > bank[i].addr) {
-				addr = bank[i].addr;
-				size = bank[i].size;
-				bank[i].addr = bank[i-1].addr;
-				bank[i].size = bank[i-1].size;
-				bank[i-1].addr = addr;
-				bank[i-1].size = size;
-				found = 1;
-			}
-	} while (found);
-
-	/* Figure out how are memory banks mapped into spaces */
-	for (i = 0; i < cnt; i++) {
-		found = 0;
-		for (j = 0; j < ARRAY_SIZE(space) && !found; j++)
-			if (space[j].addr + space[j].size == bank[i].addr) {
-				space[j].size += bank[i].size;
-				found = 1;
-			}
-		/* There is either hole or overlapping memory */
-		if (!found)
-			printk(KERN_CRIT "MC: Memory configuration mismatch "
-					 "(%08lx), expect Bus Error soon\n",
-					 bank[i].addr);
+		if (addr >= SGIMC_SEG1_BADDR)
+			memblock_add(addr, size);
 	}
-
-	for (i = 0; i < ARRAY_SIZE(space); i++)
-		if (space[i].size)
-			add_memory_region(space[i].addr, space[i].size,
-					  BOOT_MEM_RAM);
 }
+#endif
 
 void __init sgimc_init(void)
 {
@@ -205,10 +172,9 @@ void __init sgimc_init(void)
 	probe_memory();
 }
 
-void __init prom_meminit(void) {}
-void __init prom_free_prom_memory(void)
-{
 #ifdef CONFIG_SGI_IP28
+void __init prom_cleanup(void)
+{
 	u32 mconfig1;
 	unsigned long flags;
 	spinlock_t lock;
@@ -233,5 +199,5 @@ void __init prom_free_prom_memory(void)
 	sgimc->mconfig1 = mconfig1;
 	iob();
 	spin_unlock_irqrestore(&lock, flags);
-#endif
 }
+#endif
diff --git a/arch/mips/sgi-ip27/ip27-common.h b/arch/mips/sgi-ip27/ip27-common.h
new file mode 100644
index 000000000000..3ffbcf9bfd41
--- /dev/null
+++ b/arch/mips/sgi-ip27/ip27-common.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __IP27_COMMON_H
+#define __IP27_COMMON_H
+
+extern void ip27_reboot_setup(void);
+extern void hub_rt_clock_event_init(void);
+extern const struct plat_smp_ops ip27_smp_ops;
+
+#endif /* __IP27_COMMON_H */
diff --git a/arch/mips/sgi-ip27/ip27-hubio.c b/arch/mips/sgi-ip27/ip27-hubio.c
index 6ebb8845a77c..a538d0ceb61d 100644
--- a/arch/mips/sgi-ip27/ip27-hubio.c
+++ b/arch/mips/sgi-ip27/ip27-hubio.c
@@ -25,10 +25,9 @@ static int force_fire_and_forget = 1;
  * @size:	size of the PIO mapping
  *
  **/
-unsigned long hub_pio_map(cnodeid_t cnode, xwidgetnum_t widget,
+unsigned long hub_pio_map(nasid_t nasid, xwidgetnum_t widget,
 			  unsigned long xtalk_addr, size_t size)
 {
-	nasid_t nasid = COMPACT_TO_NASID_NODEID(cnode);
 	unsigned i;
 
 	/* use small-window mapping if possible */
@@ -44,7 +43,7 @@ unsigned long hub_pio_map(cnodeid_t cnode, xwidgetnum_t widget,
 
 	xtalk_addr &= ~(BWIN_SIZE-1);
 	for (i = 0; i < HUB_NUM_BIG_WINDOW; i++) {
-		if (test_and_set_bit(i, hub_data(cnode)->h_bigwin_used))
+		if (test_and_set_bit(i, hub_data(nasid)->h_bigwin_used))
 			continue;
 
 		/*
@@ -171,13 +170,12 @@ static void hub_set_piomode(nasid_t nasid)
  *
  * @hub:	hubinfo structure for our hub
  */
-void hub_pio_init(cnodeid_t cnode)
+void hub_pio_init(nasid_t nasid)
 {
-	nasid_t nasid = COMPACT_TO_NASID_NODEID(cnode);
 	unsigned i;
 
 	/* initialize big window piomaps for this hub */
-	bitmap_zero(hub_data(cnode)->h_bigwin_used, HUB_NUM_BIG_WINDOW);
+	bitmap_zero(hub_data(nasid)->h_bigwin_used, HUB_NUM_BIG_WINDOW);
 	for (i = 0; i < HUB_NUM_BIG_WINDOW; i++)
 		IIO_ITTE_DISABLE(nasid, i);
 
diff --git a/arch/mips/sgi-ip27/ip27-init.c b/arch/mips/sgi-ip27/ip27-init.c
index 79a52c472782..f597e1ee2df7 100644
--- a/arch/mips/sgi-ip27/ip27-init.c
+++ b/arch/mips/sgi-ip27/ip27-init.c
@@ -13,9 +13,11 @@
 #include <linux/mm.h>
 #include <linux/export.h>
 #include <linux/cpumask.h>
+#include <asm/bootinfo.h>
 #include <asm/cpu.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
+#include <asm/sgialib.h>
 #include <asm/time.h>
 #include <asm/sn/types.h>
 #include <asm/sn/sn0/addrs.h>
@@ -36,30 +38,23 @@
 #include <asm/sn/sn0/ip27.h>
 #include <asm/sn/mapped_kernel.h>
 
+#include "ip27-common.h"
+
 #define CPU_NONE		(cpuid_t)-1
 
-static DECLARE_BITMAP(hub_init_mask, MAX_COMPACT_NODES);
+static DECLARE_BITMAP(hub_init_mask, MAX_NUMNODES);
 nasid_t master_nasid = INVALID_NASID;
 
-cnodeid_t	nasid_to_compact_node[MAX_NASIDS];
-nasid_t		compact_to_nasid_node[MAX_COMPACT_NODES];
-cnodeid_t	cpuid_to_compact_node[MAXCPUS];
-
-EXPORT_SYMBOL(nasid_to_compact_node);
-
 struct cpuinfo_ip27 sn_cpu_info[NR_CPUS];
 EXPORT_SYMBOL_GPL(sn_cpu_info);
 
-extern void pcibr_setup(cnodeid_t);
-
-static void per_hub_init(cnodeid_t cnode)
+static void per_hub_init(nasid_t nasid)
 {
-	struct hub_data *hub = hub_data(cnode);
-	nasid_t nasid = COMPACT_TO_NASID_NODEID(cnode);
+	struct hub_data *hub = hub_data(nasid);
 
 	cpumask_set_cpu(smp_processor_id(), &hub->h_cpus);
 
-	if (test_and_set_bit(cnode, hub_init_mask))
+	if (test_and_set_bit(nasid, hub_init_mask))
 		return;
 	/*
 	 * Set CRB timeout at 5ms, (< PI timeout of 10ms)
@@ -67,7 +62,7 @@ static void per_hub_init(cnodeid_t cnode)
 	REMOTE_HUB_S(nasid, IIO_ICTP, 0x800);
 	REMOTE_HUB_S(nasid, IIO_ICTO, 0xff);
 
-	hub_rtc_init(cnode);
+	hub_rtc_init(nasid);
 
 	if (nasid) {
 		/* copy exception handlers from first node to current node */
@@ -83,15 +78,15 @@ void per_cpu_init(void)
 {
 	int cpu = smp_processor_id();
 	int slice = LOCAL_HUB_L(PI_CPU_NUM);
-	cnodeid_t cnode = get_compact_nodeid();
-	struct hub_data *hub = hub_data(cnode);
+	nasid_t nasid = get_nasid();
+	struct hub_data *hub = hub_data(nasid);
 
 	if (test_and_set_bit(slice, &hub->slice_map))
 		return;
 
 	clear_c0_status(ST0_IM);
 
-	per_hub_init(cnode);
+	per_hub_init(nasid);
 
 	cpu_time_init();
 	install_ipi();
@@ -113,21 +108,13 @@ get_nasid(void)
 			 >> NSRI_NODEID_SHFT);
 }
 
-/*
- * Map the physical node id to a virtual node id (virtual node ids are contiguous).
- */
-cnodeid_t get_compact_nodeid(void)
-{
-	return NASID_TO_COMPACT_NODEID(get_nasid());
-}
-
-extern void ip27_reboot_setup(void);
-
 void __init plat_mem_setup(void)
 {
 	u64 p, e, n_mode;
 	nasid_t nid;
 
+	register_smp_ops(&ip27_smp_ops);
+
 	ip27_reboot_setup();
 
 	/*
@@ -166,3 +153,15 @@ void __init plat_mem_setup(void)
 	ioport_resource.end = ~0UL;
 	set_io_port_base(IO_BASE);
 }
+
+const char *get_system_type(void)
+{
+	return "SGI Origin";
+}
+
+void __init prom_init(void)
+{
+	prom_init_cmdline(fw_arg0, (LONG *)fw_arg1);
+	prom_meminit();
+}
+
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index 37be04975831..c72ae330ea93 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -73,7 +73,10 @@ static void setup_hub_mask(struct hub_irq_data *hd, const struct cpumask *mask)
 	int cpu;
 
 	cpu = cpumask_first_and(mask, cpu_online_mask);
-	nasid = COMPACT_TO_NASID_NODEID(cpu_to_node(cpu));
+	if (cpu >= nr_cpu_ids)
+		cpu = cpumask_any(cpu_online_mask);
+
+	nasid = cpu_to_node(cpu);
 	hd->cpu = cpu;
 	if (!cputoslice(cpu)) {
 		hd->irq_mask[0] = REMOTE_HUB_PTR(nasid, PI_INT_MASK0_A);
@@ -137,8 +140,9 @@ static int hub_domain_alloc(struct irq_domain *domain, unsigned int virq,
 			    handle_level_irq, NULL, NULL);
 
 	/* use CPU connected to nearest hub */
-	hub = hub_data(NASID_TO_COMPACT_NODEID(info->nasid));
+	hub = hub_data(info->nasid);
 	setup_hub_mask(hd, &hub->h_cpus);
+	info->nasid = cpu_to_node(hd->cpu);
 
 	/* Make sure it's not already pending when we connect it. */
 	REMOTE_HUB_CLR_INTR(info->nasid, swlevel);
diff --git a/arch/mips/sgi-ip27/ip27-klconfig.c b/arch/mips/sgi-ip27/ip27-klconfig.c
index 41171ff0c75e..6cb2160e7689 100644
--- a/arch/mips/sgi-ip27/ip27-klconfig.c
+++ b/arch/mips/sgi-ip27/ip27-klconfig.c
@@ -73,11 +73,6 @@ lboard_t *find_lboard_class(lboard_t *start, unsigned char brd_type)
 	return (lboard_t *)NULL;
 }
 
-cnodeid_t get_cpu_cnode(cpuid_t cpu)
-{
-	return CPUID_TO_COMPACT_NODEID(cpu);
-}
-
 klcpu_t *nasid_slice_to_cpuinfo(nasid_t nasid, int slice)
 {
 	lboard_t *brd;
@@ -102,19 +97,14 @@ klcpu_t *sn_get_cpuinfo(cpuid_t cpu)
 	nasid_t nasid;
 	int slice;
 	klcpu_t *acpu;
-	gda_t *gdap = GDA;
-	cnodeid_t cnode;
 
 	if (!(cpu < MAXCPUS)) {
 		printk("sn_get_cpuinfo: illegal cpuid 0x%lx\n", cpu);
 		return NULL;
 	}
 
-	cnode = get_cpu_cnode(cpu);
-	if (cnode == INVALID_CNODEID)
-		return NULL;
-
-	if ((nasid = gdap->g_nasidtable[cnode]) == INVALID_NASID)
+	nasid = cputonasid(cpu);
+	if (nasid  == INVALID_NASID)
 		return NULL;
 
 	for (slice = 0; slice < CPUS_PER_NODE; slice++) {
diff --git a/arch/mips/sgi-ip27/ip27-klnuma.c b/arch/mips/sgi-ip27/ip27-klnuma.c
index a4f01328de62..ee1c6ff4aa00 100644
--- a/arch/mips/sgi-ip27/ip27-klnuma.c
+++ b/arch/mips/sgi-ip27/ip27-klnuma.c
@@ -38,13 +38,13 @@ void __init setup_replication_mask(void)
 #error Kernel replication works with mapped kernel support. No calias support.
 #endif
 	{
-		cnodeid_t	cnode;
+		nasid_t nasid;
 
-		for_each_online_node(cnode) {
-			if (cnode == 0)
+		for_each_online_node(nasid) {
+			if (nasid == 0)
 				continue;
 			/* Advertise that we have a copy of the kernel */
-			cpumask_set_cpu(cnode, &ktext_repmask);
+			cpumask_set_cpu(nasid, &ktext_repmask);
 		}
 	}
 #endif
@@ -85,7 +85,6 @@ static __init void copy_kernel(nasid_t dest_nasid)
 
 void __init replicate_kernel_text(void)
 {
-	cnodeid_t cnode;
 	nasid_t client_nasid;
 	nasid_t server_nasid;
 
@@ -94,13 +93,12 @@ void __init replicate_kernel_text(void)
 	/* Record where the master node should get its kernel text */
 	set_ktext_source(master_nasid, master_nasid);
 
-	for_each_online_node(cnode) {
-		if (cnode == 0)
+	for_each_online_node(client_nasid) {
+		if (client_nasid == 0)
 			continue;
-		client_nasid = COMPACT_TO_NASID_NODEID(cnode);
 
 		/* Check if this node should get a copy of the kernel */
-		if (cpumask_test_cpu(cnode, &ktext_repmask)) {
+		if (cpumask_test_cpu(client_nasid, &ktext_repmask)) {
 			server_nasid = client_nasid;
 			copy_kernel(server_nasid);
 		}
@@ -115,17 +113,16 @@ void __init replicate_kernel_text(void)
  * data structures on the first couple of pages of the first slot of each
  * node. If this is the case, getfirstfree(node) > getslotstart(node, 0).
  */
-unsigned long node_getfirstfree(cnodeid_t cnode)
+unsigned long node_getfirstfree(nasid_t nasid)
 {
 	unsigned long loadbase = REP_BASE;
-	nasid_t nasid = COMPACT_TO_NASID_NODEID(cnode);
 	unsigned long offset;
 
 #ifdef CONFIG_MAPPED_KERNEL
 	loadbase += 16777216;
 #endif
 	offset = PAGE_ALIGN((unsigned long)(&_end)) - loadbase;
-	if ((cnode == 0) || (cpumask_test_cpu(cnode, &ktext_repmask)))
+	if ((nasid == 0) || (cpumask_test_cpu(nasid, &ktext_repmask)))
 		return TO_NODE(nasid, offset) >> PAGE_SHIFT;
 	else
 		return KDM_TO_PHYS(PAGE_ALIGN(SYMMON_STK_ADDR(nasid, 0))) >> PAGE_SHIFT;
diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c
index 8624a885d95b..563aad5e6398 100644
--- a/arch/mips/sgi-ip27/ip27-memory.c
+++ b/arch/mips/sgi-ip27/ip27-memory.c
@@ -33,7 +33,7 @@
 #define SLOT_PFNSHIFT		(SLOT_SHIFT - PAGE_SHIFT)
 #define PFN_NASIDSHFT		(NASID_SHFT - PAGE_SHIFT)
 
-struct node_data *__node_data[MAX_COMPACT_NODES];
+struct node_data *__node_data[MAX_NUMNODES];
 
 EXPORT_SYMBOL(__node_data);
 
@@ -44,23 +44,23 @@ static int is_fine_dirmode(void)
 	return ((LOCAL_HUB_L(NI_STATUS_REV_ID) & NSRI_REGIONSIZE_MASK) >> NSRI_REGIONSIZE_SHFT) & REGIONSIZE_FINE;
 }
 
-static u64 get_region(cnodeid_t cnode)
+static u64 get_region(nasid_t nasid)
 {
 	if (fine_mode)
-		return COMPACT_TO_NASID_NODEID(cnode) >> NASID_TO_FINEREG_SHFT;
+		return nasid >> NASID_TO_FINEREG_SHFT;
 	else
-		return COMPACT_TO_NASID_NODEID(cnode) >> NASID_TO_COARSEREG_SHFT;
+		return nasid >> NASID_TO_COARSEREG_SHFT;
 }
 
 static u64 region_mask;
 
 static void gen_region_mask(u64 *region_mask)
 {
-	cnodeid_t cnode;
+	nasid_t nasid;
 
 	(*region_mask) = 0;
-	for_each_online_node(cnode) {
-		(*region_mask) |= 1ULL << get_region(cnode);
+	for_each_online_node(nasid) {
+		(*region_mask) |= 1ULL << get_region(nasid);
 	}
 }
 
@@ -104,23 +104,18 @@ static void router_recurse(klrou_t *router_a, klrou_t *router_b, int depth)
 	router_a->rou_rflag = 0;
 }
 
-unsigned char __node_distances[MAX_COMPACT_NODES][MAX_COMPACT_NODES];
+unsigned char __node_distances[MAX_NUMNODES][MAX_NUMNODES];
 EXPORT_SYMBOL(__node_distances);
 
 static int __init compute_node_distance(nasid_t nasid_a, nasid_t nasid_b)
 {
 	klrou_t *router, *router_a = NULL, *router_b = NULL;
 	lboard_t *brd, *dest_brd;
-	cnodeid_t cnode;
 	nasid_t nasid;
 	int port;
 
 	/* Figure out which routers nodes in question are connected to */
-	for_each_online_node(cnode) {
-		nasid = COMPACT_TO_NASID_NODEID(cnode);
-
-		if (nasid == -1) continue;
-
+	for_each_online_node(nasid) {
 		brd = find_lboard_class((lboard_t *)KL_CONFIG_INFO(nasid),
 					KLTYPE_ROUTER);
 
@@ -176,19 +171,16 @@ static int __init compute_node_distance(nasid_t nasid_a, nasid_t nasid_b)
 
 static void __init init_topology_matrix(void)
 {
-	nasid_t nasid, nasid2;
-	cnodeid_t row, col;
+	nasid_t row, col;
 
-	for (row = 0; row < MAX_COMPACT_NODES; row++)
-		for (col = 0; col < MAX_COMPACT_NODES; col++)
+	for (row = 0; row < MAX_NUMNODES; row++)
+		for (col = 0; col < MAX_NUMNODES; col++)
 			__node_distances[row][col] = -1;
 
 	for_each_online_node(row) {
-		nasid = COMPACT_TO_NASID_NODEID(row);
 		for_each_online_node(col) {
-			nasid2 = COMPACT_TO_NASID_NODEID(col);
 			__node_distances[row][col] =
-				compute_node_distance(nasid, nasid2);
+				compute_node_distance(row, col);
 		}
 	}
 }
@@ -196,12 +188,11 @@ static void __init init_topology_matrix(void)
 static void __init dump_topology(void)
 {
 	nasid_t nasid;
-	cnodeid_t cnode;
 	lboard_t *brd, *dest_brd;
 	int port;
 	int router_num = 0;
 	klrou_t *router;
-	cnodeid_t row, col;
+	nasid_t row, col;
 
 	pr_info("************** Topology ********************\n");
 
@@ -216,11 +207,7 @@ static void __init dump_topology(void)
 		pr_cont("\n");
 	}
 
-	for_each_online_node(cnode) {
-		nasid = COMPACT_TO_NASID_NODEID(cnode);
-
-		if (nasid == -1) continue;
-
+	for_each_online_node(nasid) {
 		brd = find_lboard_class((lboard_t *)KL_CONFIG_INFO(nasid),
 					KLTYPE_ROUTER);
 
@@ -254,21 +241,17 @@ static void __init dump_topology(void)
 	}
 }
 
-static unsigned long __init slot_getbasepfn(cnodeid_t cnode, int slot)
+static unsigned long __init slot_getbasepfn(nasid_t nasid, int slot)
 {
-	nasid_t nasid = COMPACT_TO_NASID_NODEID(cnode);
-
 	return ((unsigned long)nasid << PFN_NASIDSHFT) | (slot << SLOT_PFNSHIFT);
 }
 
-static unsigned long __init slot_psize_compute(cnodeid_t node, int slot)
+static unsigned long __init slot_psize_compute(nasid_t nasid, int slot)
 {
-	nasid_t nasid;
 	lboard_t *brd;
 	klmembnk_t *banks;
 	unsigned long size;
 
-	nasid = COMPACT_TO_NASID_NODEID(node);
 	/* Find the node board */
 	brd = find_lboard((lboard_t *)KL_CONFIG_INFO(nasid), KLTYPE_IP27);
 	if (!brd)
@@ -298,7 +281,7 @@ static unsigned long __init slot_psize_compute(cnodeid_t node, int slot)
 
 static void __init mlreset(void)
 {
-	int i;
+	nasid_t nasid;
 
 	master_nasid = get_nasid();
 	fine_mode = is_fine_dirmode();
@@ -321,11 +304,7 @@ static void __init mlreset(void)
 	/*
 	 * Set all nodes' calias sizes to 8k
 	 */
-	for_each_online_node(i) {
-		nasid_t nasid;
-
-		nasid = COMPACT_TO_NASID_NODEID(i);
-
+	for_each_online_node(nasid) {
 		/*
 		 * Always have node 0 in the region mask, otherwise
 		 * CALIAS accesses get exceptions since the hub
@@ -350,7 +329,7 @@ static void __init szmem(void)
 {
 	unsigned long slot_psize, slot0sz = 0, nodebytes;	/* Hack to detect problem configs */
 	int slot;
-	cnodeid_t node;
+	nasid_t node;
 
 	for_each_online_node(node) {
 		nodebytes = 0;
@@ -380,7 +359,7 @@ static void __init szmem(void)
 	}
 }
 
-static void __init node_mem_init(cnodeid_t node)
+static void __init node_mem_init(nasid_t node)
 {
 	unsigned long slot_firstpfn = slot_getbasepfn(node, 0);
 	unsigned long slot_freepfn = node_getfirstfree(node);
@@ -402,12 +381,8 @@ static void __init node_mem_init(cnodeid_t node)
 	slot_freepfn += PFN_UP(sizeof(struct pglist_data) +
 			       sizeof(struct hub_data));
 
-	free_bootmem_with_active_regions(node, end_pfn);
-
 	memblock_reserve(slot_firstpfn << PAGE_SHIFT,
 			 ((slot_freepfn - slot_firstpfn) << PAGE_SHIFT));
-
-	sparse_memory_present_with_active_regions(node);
 }
 
 /*
@@ -427,19 +402,21 @@ static struct node_data null_node = {
  */
 void __init prom_meminit(void)
 {
-	cnodeid_t node;
+	nasid_t node;
 
 	mlreset();
 	szmem();
 	max_low_pfn = PHYS_PFN(memblock_end_of_DRAM());
 
-	for (node = 0; node < MAX_COMPACT_NODES; node++) {
+	for (node = 0; node < MAX_NUMNODES; node++) {
 		if (node_online(node)) {
 			node_mem_init(node);
 			continue;
 		}
 		__node_data[node] = &null_node;
 	}
+
+	memblocks_present();
 }
 
 void __init prom_free_prom_memory(void)
diff --git a/arch/mips/sgi-ip27/ip27-nmi.c b/arch/mips/sgi-ip27/ip27-nmi.c
index 3aae388561d9..daf3670d94e7 100644
--- a/arch/mips/sgi-ip27/ip27-nmi.c
+++ b/arch/mips/sgi-ip27/ip27-nmi.c
@@ -17,8 +17,6 @@
 #define NODE_NUM_CPUS(n)	CPUS_PER_NODE
 #endif
 
-#define CNODEID_NONE (cnodeid_t)-1
-
 typedef unsigned long machreg_t;
 
 static arch_spinlock_t nmi_lock = __ARCH_SPIN_LOCK_UNLOCKED;
@@ -152,16 +150,10 @@ void nmi_dump_hub_irq(nasid_t nasid, int slice)
  * Copy the cpu registers which have been saved in the IP27prom format
  * into the eframe format for the node under consideration.
  */
-void nmi_node_eframe_save(cnodeid_t  cnode)
+void nmi_node_eframe_save(nasid_t nasid)
 {
-	nasid_t nasid;
 	int slice;
 
-	/* Make sure that we have a valid node */
-	if (cnode == CNODEID_NONE)
-		return;
-
-	nasid = COMPACT_TO_NASID_NODEID(cnode);
 	if (nasid == INVALID_NASID)
 		return;
 
@@ -178,10 +170,10 @@ void nmi_node_eframe_save(cnodeid_t  cnode)
 void
 nmi_eframes_save(void)
 {
-	cnodeid_t	cnode;
+	nasid_t nasid;
 
-	for_each_online_node(cnode)
-		nmi_node_eframe_save(cnode);
+	for_each_online_node(nasid)
+		nmi_node_eframe_save(nasid);
 }
 
 void
diff --git a/arch/mips/sgi-ip27/ip27-reset.c b/arch/mips/sgi-ip27/ip27-reset.c
index e44a15d4f573..74d078247e49 100644
--- a/arch/mips/sgi-ip27/ip27-reset.c
+++ b/arch/mips/sgi-ip27/ip27-reset.c
@@ -26,6 +26,8 @@
 #include <asm/sn/gda.h>
 #include <asm/sn/sn0/hub.h>
 
+#include "ip27-common.h"
+
 void machine_restart(char *command) __noreturn;
 void machine_halt(void) __noreturn;
 void machine_power_off(void) __noreturn;
@@ -45,8 +47,7 @@ static void ip27_machine_restart(char *command)
 #endif
 #if 0
 	for_each_online_node(i)
-		REMOTE_HUB_S(COMPACT_TO_NASID_NODEID(i), PROMOP_REG,
-							PROMOP_REBOOT);
+		REMOTE_HUB_S(i, PROMOP_REG, PROMOP_REBOOT);
 #else
 	LOCAL_HUB_S(NI_PORT_RESET, NPR_PORTRESET | NPR_LOCALRESET);
 #endif
@@ -61,8 +62,7 @@ static void ip27_machine_halt(void)
 	smp_send_stop();
 #endif
 	for_each_online_node(i)
-		REMOTE_HUB_S(COMPACT_TO_NASID_NODEID(i), PROMOP_REG,
-							PROMOP_RESTART);
+		REMOTE_HUB_S(i, PROMOP_REG, PROMOP_RESTART);
 	LOCAL_HUB_S(NI_PORT_RESET, NPR_PORTRESET | NPR_LOCALRESET);
 	noreturn;
 }
diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c
index 20b81209c6b8..faa0244c8b0c 100644
--- a/arch/mips/sgi-ip27/ip27-smp.c
+++ b/arch/mips/sgi-ip27/ip27-smp.c
@@ -27,38 +27,19 @@
 #include <asm/sn/sn0/hubio.h>
 #include <asm/sn/sn0/ip27.h>
 
+#include "ip27-common.h"
+
 /*
  * Takes as first input the PROM assigned cpu id, and the kernel
  * assigned cpu id as the second.
  */
-static void alloc_cpupda(cpuid_t cpu, int cpunum)
+static void alloc_cpupda(nasid_t nasid, cpuid_t cpu, int cpunum)
 {
-	cnodeid_t node = get_cpu_cnode(cpu);
-	nasid_t nasid = COMPACT_TO_NASID_NODEID(node);
-
 	cputonasid(cpunum) = nasid;
-	sn_cpu_info[cpunum].p_nodeid = node;
 	cputoslice(cpunum) = get_cpu_slice(cpu);
 }
 
-static nasid_t get_actual_nasid(lboard_t *brd)
-{
-	klhub_t *hub;
-
-	if (!brd)
-		return INVALID_NASID;
-
-	/* find out if we are a completely disabled brd. */
-	hub  = (klhub_t *)find_first_component(brd, KLSTRUCT_HUB);
-	if (!hub)
-		return INVALID_NASID;
-	if (!(hub->hub_info.flags & KLINFO_ENABLE))	/* disabled node brd */
-		return hub->hub_info.physid;
-	else
-		return brd->brd_nasid;
-}
-
-static int do_cpumask(cnodeid_t cnode, nasid_t nasid, int highest)
+static int do_cpumask(nasid_t nasid, int highest)
 {
 	static int tot_cpus_found = 0;
 	lboard_t *brd;
@@ -72,16 +53,13 @@ static int do_cpumask(cnodeid_t cnode, nasid_t nasid, int highest)
 		acpu = (klcpu_t *)find_first_component(brd, KLSTRUCT_CPU);
 		while (acpu) {
 			cpuid = acpu->cpu_info.virtid;
-			/* cnode is not valid for completely disabled brds */
-			if (get_actual_nasid(brd) == brd->brd_nasid)
-				cpuid_to_compact_node[cpuid] = cnode;
-			if (cpuid > highest)
-				highest = cpuid;
 			/* Only let it join in if it's marked enabled */
 			if ((acpu->cpu_info.flags & KLINFO_ENABLE) &&
 			    (tot_cpus_found != NR_CPUS)) {
+				if (cpuid > highest)
+					highest = cpuid;
 				set_cpu_possible(cpuid, true);
-				alloc_cpupda(cpuid, tot_cpus_found);
+				alloc_cpupda(nasid, cpuid, tot_cpus_found);
 				cpus_found++;
 				tot_cpus_found++;
 			}
@@ -103,29 +81,13 @@ void cpu_node_probe(void)
 	int i, highest = 0;
 	gda_t *gdap = GDA;
 
-	/*
-	 * Initialize the arrays to invalid nodeid (-1)
-	 */
-	for (i = 0; i < MAX_COMPACT_NODES; i++)
-		compact_to_nasid_node[i] = INVALID_NASID;
-	for (i = 0; i < MAX_NASIDS; i++)
-		nasid_to_compact_node[i] = INVALID_CNODEID;
-	for (i = 0; i < MAXCPUS; i++)
-		cpuid_to_compact_node[i] = INVALID_CNODEID;
-
-	/*
-	 * MCD - this whole "compact node" stuff can probably be dropped,
-	 * as we can handle sparse numbering now
-	 */
 	nodes_clear(node_online_map);
-	for (i = 0; i < MAX_COMPACT_NODES; i++) {
+	for (i = 0; i < MAX_NUMNODES; i++) {
 		nasid_t nasid = gdap->g_nasidtable[i];
 		if (nasid == INVALID_NASID)
 			break;
-		compact_to_nasid_node[i] = nasid;
-		nasid_to_compact_node[nasid] = i;
-		node_set_online(num_online_nodes());
-		highest = do_cpumask(i, nasid, highest);
+		node_set_online(nasid);
+		highest = do_cpumask(nasid, highest);
 	}
 
 	printk("Discovered %d cpus on %d nodes\n", highest + 1, num_online_nodes());
@@ -162,11 +124,10 @@ static void ip27_send_ipi_single(int destid, unsigned int action)
 	irq += cputoslice(destid);
 
 	/*
-	 * Convert the compact hub number to the NASID to get the correct
-	 * part of the address space.  Then set the interrupt bit associated
-	 * with the CPU we want to send the interrupt to.
+	 * Set the interrupt bit associated with the CPU we want to
+	 * send the interrupt to.
 	 */
-	REMOTE_HUB_SEND_INTR(COMPACT_TO_NASID_NODEID(cpu_to_node(destid)), irq);
+	REMOTE_HUB_SEND_INTR(cpu_to_node(destid), irq);
 }
 
 static void ip27_send_ipi_mask(const struct cpumask *mask, unsigned int action)
@@ -184,8 +145,6 @@ static void ip27_init_cpu(void)
 
 static void ip27_smp_finish(void)
 {
-	extern void hub_rt_clock_event_init(void);
-
 	hub_rt_clock_event_init();
 	local_irq_enable();
 }
@@ -208,23 +167,20 @@ static int ip27_boot_secondary(int cpu, struct task_struct *idle)
 
 static void __init ip27_smp_setup(void)
 {
-	cnodeid_t	cnode;
+	nasid_t nasid;
 
-	for_each_online_node(cnode) {
-		if (cnode == 0)
+	for_each_online_node(nasid) {
+		if (nasid == 0)
 			continue;
-		intr_clear_all(COMPACT_TO_NASID_NODEID(cnode));
+		intr_clear_all(nasid);
 	}
 
 	replicate_kernel_text();
 
 	/*
-	 * Assumption to be fixed: we're always booted on logical / physical
-	 * processor 0.	 While we're always running on logical processor 0
-	 * this still means this is physical processor zero; it might for
-	 * example be disabled in the firmware.
+	 * PROM sets up system, that boot cpu is always first CPU on nasid 0
 	 */
-	alloc_cpupda(0, 0);
+	alloc_cpupda(0, 0, 0);
 }
 
 static void __init ip27_prepare_cpus(unsigned int max_cpus)
diff --git a/arch/mips/sgi-ip27/ip27-timer.c b/arch/mips/sgi-ip27/ip27-timer.c
index 9b4b9ac621a3..17302bbfa7a6 100644
--- a/arch/mips/sgi-ip27/ip27-timer.c
+++ b/arch/mips/sgi-ip27/ip27-timer.c
@@ -38,6 +38,8 @@
 #include <asm/sn/sn0/hubio.h>
 #include <asm/pci/bridge.h>
 
+#include "ip27-common.h"
+
 static int rt_next_event(unsigned long delta, struct clock_event_device *evt)
 {
 	unsigned int cpu = smp_processor_id();
@@ -170,7 +172,7 @@ void cpu_time_init(void)
 	printk("CPU %d clock is %dMHz.\n", smp_processor_id(), cpu->cpu_speed);
 }
 
-void hub_rtc_init(cnodeid_t cnode)
+void hub_rtc_init(nasid_t nasid)
 {
 
 	/*
@@ -178,7 +180,7 @@ void hub_rtc_init(cnodeid_t cnode)
 	 * If this is not the current node then it is a cpuless
 	 * node and timeouts will not happen there.
 	 */
-	if (get_compact_nodeid() == cnode) {
+	if (get_nasid() == nasid) {
 		LOCAL_HUB_S(PI_RT_EN_A, 1);
 		LOCAL_HUB_S(PI_RT_EN_B, 1);
 		LOCAL_HUB_S(PI_PROF_EN_A, 0);
diff --git a/arch/mips/sgi-ip27/ip27-xtalk.c b/arch/mips/sgi-ip27/ip27-xtalk.c
index 4a1f0b0c29e2..5218b900f855 100644
--- a/arch/mips/sgi-ip27/ip27-xtalk.c
+++ b/arch/mips/sgi-ip27/ip27-xtalk.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/smp.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/sgi-w1.h>
 #include <linux/platform_data/xtalk-bridge.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/types.h>
@@ -26,9 +27,35 @@
 static void bridge_platform_create(nasid_t nasid, int widget, int masterwid)
 {
 	struct xtalk_bridge_platform_data *bd;
+	struct sgi_w1_platform_data *wd;
 	struct platform_device *pdev;
+	struct resource w1_res;
 	unsigned long offset;
 
+	offset = NODE_OFFSET(nasid);
+
+	wd = kzalloc(sizeof(*wd), GFP_KERNEL);
+	if (!wd)
+		goto no_mem;
+
+	snprintf(wd->dev_id, sizeof(wd->dev_id), "bridge-%012lx",
+		 offset + (widget << SWIN_SIZE_BITS));
+
+	memset(&w1_res, 0, sizeof(w1_res));
+	w1_res.start = offset + (widget << SWIN_SIZE_BITS) +
+				offsetof(struct bridge_regs, b_nic);
+	w1_res.end = w1_res.start + 3;
+	w1_res.flags = IORESOURCE_MEM;
+
+	pdev = platform_device_alloc("sgi_w1", PLATFORM_DEVID_AUTO);
+	if (!pdev) {
+		kfree(wd);
+		goto no_mem;
+	}
+	platform_device_add_resources(pdev, &w1_res, 1);
+	platform_device_add_data(pdev, wd, sizeof(*wd));
+	platform_device_add(pdev);
+
 	bd = kzalloc(sizeof(*bd), GFP_KERNEL);
 	if (!bd)
 		goto no_mem;
@@ -38,7 +65,6 @@ static void bridge_platform_create(nasid_t nasid, int widget, int masterwid)
 		goto no_mem;
 	}
 
-	offset = NODE_OFFSET(nasid);
 
 	bd->bridge_addr = RAW_NODE_SWIN_BASE(nasid, widget);
 	bd->intr_addr	= BIT_ULL(47) + 0x01800000 + PI_INT_PEND_MOD;
@@ -46,14 +72,14 @@ static void bridge_platform_create(nasid_t nasid, int widget, int masterwid)
 	bd->masterwid	= masterwid;
 
 	bd->mem.name	= "Bridge PCI MEM";
-	bd->mem.start	= offset + (widget << SWIN_SIZE_BITS);
-	bd->mem.end	= bd->mem.start + SWIN_SIZE - 1;
+	bd->mem.start	= offset + (widget << SWIN_SIZE_BITS) + BRIDGE_DEVIO0;
+	bd->mem.end	= offset + (widget << SWIN_SIZE_BITS) + SWIN_SIZE - 1;
 	bd->mem.flags	= IORESOURCE_MEM;
 	bd->mem_offset	= offset;
 
 	bd->io.name	= "Bridge PCI IO";
-	bd->io.start	= offset + (widget << SWIN_SIZE_BITS);
-	bd->io.end	= bd->io.start + SWIN_SIZE - 1;
+	bd->io.start	= offset + (widget << SWIN_SIZE_BITS) + BRIDGE_DEVIO0;
+	bd->io.end	= offset + (widget << SWIN_SIZE_BITS) + SWIN_SIZE - 1;
 	bd->io.flags	= IORESOURCE_IO;
 	bd->io_offset	= offset;
 
@@ -81,6 +107,8 @@ static int probe_one_port(nasid_t nasid, int widget, int masterwid)
 		bridge_platform_create(nasid, widget, masterwid);
 		break;
 	default:
+		pr_info("xtalk:n%d/%d unknown widget (0x%x)\n",
+			nasid, widget, partnum);
 		break;
 	}
 
@@ -138,14 +166,12 @@ static int xbow_probe(nasid_t nasid)
 	return 0;
 }
 
-static void xtalk_probe_node(cnodeid_t nid)
+static void xtalk_probe_node(nasid_t nasid)
 {
 	volatile u64		hubreg;
-	nasid_t			nasid;
 	xwidget_part_num_t	partnum;
 	widgetreg_t		widget_id;
 
-	nasid = COMPACT_TO_NASID_NODEID(nid);
 	hubreg = REMOTE_HUB_L(nasid, IIO_LLP_CSR);
 
 	/* check whether the link is up */
@@ -173,10 +199,10 @@ static void xtalk_probe_node(cnodeid_t nid)
 
 static int __init xtalk_init(void)
 {
-	cnodeid_t cnode;
+	nasid_t nasid;
 
-	for_each_online_node(cnode)
-		xtalk_probe_node(cnode);
+	for_each_online_node(nasid)
+		xtalk_probe_node(nasid);
 
 	return 0;
 }
diff --git a/arch/mips/sgi-ip30/Makefile b/arch/mips/sgi-ip30/Makefile
new file mode 100644
index 000000000000..18cf561b3d61
--- /dev/null
+++ b/arch/mips/sgi-ip30/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the IP30 specific kernel interface routines under Linux.
+#
+
+obj-y	:= ip30-irq.o ip30-power.o ip30-setup.o ip30-timer.o ip30-xtalk.o
+
+obj-$(CONFIG_EARLY_PRINTK)	+= ip30-console.o
+obj-$(CONFIG_SMP)		+= ip30-smp.o
diff --git a/arch/mips/sgi-ip30/Platform b/arch/mips/sgi-ip30/Platform
new file mode 100644
index 000000000000..2b5695c2049a
--- /dev/null
+++ b/arch/mips/sgi-ip30/Platform
@@ -0,0 +1,8 @@
+#
+# SGI-IP30 (Octane/Octane2)
+#
+ifdef CONFIG_SGI_IP30
+platform-$(CONFIG_SGI_IP30)		+= sgi-ip30/
+cflags-$(CONFIG_SGI_IP30)		+= -I$(srctree)/arch/mips/include/asm/mach-ip30
+load-$(CONFIG_SGI_IP30)			+= 0xa800000020004000
+endif
diff --git a/arch/mips/sgi-ip30/ip30-common.h b/arch/mips/sgi-ip30/ip30-common.h
new file mode 100644
index 000000000000..d2bcaee712f3
--- /dev/null
+++ b/arch/mips/sgi-ip30/ip30-common.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __IP30_COMMON_H
+#define __IP30_COMMON_H
+
+extern struct plat_smp_ops ip30_smp_ops;
+extern void __init ip30_per_cpu_init(void);
+
+#endif /* __IP30_COMMON_H */
diff --git a/arch/mips/sgi-ip30/ip30-console.c b/arch/mips/sgi-ip30/ip30-console.c
new file mode 100644
index 000000000000..b91f8c4fdc78
--- /dev/null
+++ b/arch/mips/sgi-ip30/ip30-console.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/io.h>
+
+#include <asm/sn/ioc3.h>
+
+static inline struct ioc3_uartregs *console_uart(void)
+{
+	struct ioc3 *ioc3;
+
+	ioc3 = (struct ioc3 *)((void *)(0x900000001f600000));
+	return &ioc3->sregs.uarta;
+}
+
+void prom_putchar(char c)
+{
+	struct ioc3_uartregs *uart = console_uart();
+
+	while ((readb(&uart->iu_lsr) & 0x20) == 0)
+		cpu_relax();
+
+	writeb(c, &uart->iu_thr);
+}
diff --git a/arch/mips/sgi-ip30/ip30-irq.c b/arch/mips/sgi-ip30/ip30-irq.c
new file mode 100644
index 000000000000..d46655b914f1
--- /dev/null
+++ b/arch/mips/sgi-ip30/ip30-irq.c
@@ -0,0 +1,328 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ip30-irq.c: Highlevel interrupt handling for IP30 architecture.
+ */
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/percpu.h>
+#include <linux/spinlock.h>
+#include <linux/tick.h>
+#include <linux/types.h>
+
+#include <asm/irq_cpu.h>
+#include <asm/sgi/heart.h>
+
+struct heart_irq_data {
+	u64	*irq_mask;
+	int	cpu;
+};
+
+static DECLARE_BITMAP(heart_irq_map, HEART_NUM_IRQS);
+
+static DEFINE_PER_CPU(unsigned long, irq_enable_mask);
+
+static inline int heart_alloc_int(void)
+{
+	int bit;
+
+again:
+	bit = find_first_zero_bit(heart_irq_map, HEART_NUM_IRQS);
+	if (bit >= HEART_NUM_IRQS)
+		return -ENOSPC;
+
+	if (test_and_set_bit(bit, heart_irq_map))
+		goto again;
+
+	return bit;
+}
+
+static void ip30_error_irq(struct irq_desc *desc)
+{
+	u64 pending, mask, cause, error_irqs, err_reg;
+	int cpu = smp_processor_id();
+	int i;
+
+	pending = heart_read(&heart_regs->isr);
+	mask = heart_read(&heart_regs->imr[cpu]);
+	cause = heart_read(&heart_regs->cause);
+	error_irqs = (pending & HEART_L4_INT_MASK & mask);
+
+	/* Bail if there's nothing to process (how did we get here, then?) */
+	if (unlikely(!error_irqs))
+		return;
+
+	/* Prevent any of the error IRQs from firing again. */
+	heart_write(mask & ~(pending), &heart_regs->imr[cpu]);
+
+	/* Ack all error IRQs. */
+	heart_write(HEART_L4_INT_MASK, &heart_regs->clear_isr);
+
+	/*
+	 * If we also have a cause value, then something happened, so loop
+	 * through the error IRQs and report a "heart attack" for each one
+	 * and print the value of the HEART cause register.  This is really
+	 * primitive right now, but it should hopefully work until a more
+	 * robust error handling routine can be put together.
+	 *
+	 * Refer to heart.h for the HC_* macros to work out the cause
+	 * that got us here.
+	 */
+	if (cause) {
+		pr_alert("IP30: CPU%d: HEART ATTACK! ISR = 0x%.16llx, IMR = 0x%.16llx, CAUSE = 0x%.16llx\n",
+			 cpu, pending, mask, cause);
+
+		if (cause & HC_COR_MEM_ERR) {
+			err_reg = heart_read(&heart_regs->mem_err_addr);
+			pr_alert("  HEART_MEMERR_ADDR = 0x%.16llx\n", err_reg);
+		}
+
+		/* i = 63; i >= 51; i-- */
+		for (i = HEART_ERR_MASK_END; i >= HEART_ERR_MASK_START; i--)
+			if ((pending >> i) & 1)
+				pr_alert("  HEART Error IRQ #%d\n", i);
+
+		/* XXX: Seems possible to loop forever here, so panic(). */
+		panic("IP30: Fatal Error !\n");
+	}
+
+	/* Unmask the error IRQs. */
+	heart_write(mask, &heart_regs->imr[cpu]);
+}
+
+static void ip30_normal_irq(struct irq_desc *desc)
+{
+	int cpu = smp_processor_id();
+	struct irq_domain *domain;
+	u64 pend, mask;
+	int irq;
+
+	pend = heart_read(&heart_regs->isr);
+	mask = (heart_read(&heart_regs->imr[cpu]) &
+		(HEART_L0_INT_MASK | HEART_L1_INT_MASK | HEART_L2_INT_MASK));
+
+	pend &= mask;
+	if (unlikely(!pend))
+		return;
+
+#ifdef CONFIG_SMP
+	if (pend & BIT_ULL(HEART_L2_INT_RESCHED_CPU_0)) {
+		heart_write(BIT_ULL(HEART_L2_INT_RESCHED_CPU_0),
+			    &heart_regs->clear_isr);
+		scheduler_ipi();
+	} else if (pend & BIT_ULL(HEART_L2_INT_RESCHED_CPU_1)) {
+		heart_write(BIT_ULL(HEART_L2_INT_RESCHED_CPU_1),
+			    &heart_regs->clear_isr);
+		scheduler_ipi();
+	} else if (pend & BIT_ULL(HEART_L2_INT_CALL_CPU_0)) {
+		heart_write(BIT_ULL(HEART_L2_INT_CALL_CPU_0),
+			    &heart_regs->clear_isr);
+		generic_smp_call_function_interrupt();
+	} else if (pend & BIT_ULL(HEART_L2_INT_CALL_CPU_1)) {
+		heart_write(BIT_ULL(HEART_L2_INT_CALL_CPU_1),
+			    &heart_regs->clear_isr);
+		generic_smp_call_function_interrupt();
+	} else
+#endif
+	{
+		domain = irq_desc_get_handler_data(desc);
+		irq = irq_linear_revmap(domain, __ffs(pend));
+		if (irq)
+			generic_handle_irq(irq);
+		else
+			spurious_interrupt();
+	}
+}
+
+static void ip30_ack_heart_irq(struct irq_data *d)
+{
+	heart_write(BIT_ULL(d->hwirq), &heart_regs->clear_isr);
+}
+
+static void ip30_mask_heart_irq(struct irq_data *d)
+{
+	struct heart_irq_data *hd = irq_data_get_irq_chip_data(d);
+	unsigned long *mask = &per_cpu(irq_enable_mask, hd->cpu);
+
+	clear_bit(d->hwirq, mask);
+	heart_write(*mask, &heart_regs->imr[hd->cpu]);
+}
+
+static void ip30_mask_and_ack_heart_irq(struct irq_data *d)
+{
+	struct heart_irq_data *hd = irq_data_get_irq_chip_data(d);
+	unsigned long *mask = &per_cpu(irq_enable_mask, hd->cpu);
+
+	clear_bit(d->hwirq, mask);
+	heart_write(*mask, &heart_regs->imr[hd->cpu]);
+	heart_write(BIT_ULL(d->hwirq), &heart_regs->clear_isr);
+}
+
+static void ip30_unmask_heart_irq(struct irq_data *d)
+{
+	struct heart_irq_data *hd = irq_data_get_irq_chip_data(d);
+	unsigned long *mask = &per_cpu(irq_enable_mask, hd->cpu);
+
+	set_bit(d->hwirq, mask);
+	heart_write(*mask, &heart_regs->imr[hd->cpu]);
+}
+
+static int ip30_set_heart_irq_affinity(struct irq_data *d,
+				       const struct cpumask *mask, bool force)
+{
+	struct heart_irq_data *hd = irq_data_get_irq_chip_data(d);
+
+	if (!hd)
+		return -EINVAL;
+
+	if (irqd_is_started(d))
+		ip30_mask_and_ack_heart_irq(d);
+
+	hd->cpu = cpumask_first_and(mask, cpu_online_mask);
+
+	if (irqd_is_started(d))
+		ip30_unmask_heart_irq(d);
+
+	irq_data_update_effective_affinity(d, cpumask_of(hd->cpu));
+
+	return 0;
+}
+
+static struct irq_chip heart_irq_chip = {
+	.name			= "HEART",
+	.irq_ack		= ip30_ack_heart_irq,
+	.irq_mask		= ip30_mask_heart_irq,
+	.irq_mask_ack		= ip30_mask_and_ack_heart_irq,
+	.irq_unmask		= ip30_unmask_heart_irq,
+	.irq_set_affinity	= ip30_set_heart_irq_affinity,
+};
+
+static int heart_domain_alloc(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs, void *arg)
+{
+	struct irq_alloc_info *info = arg;
+	struct heart_irq_data *hd;
+	int hwirq;
+
+	if (nr_irqs > 1 || !info)
+		return -EINVAL;
+
+	hd = kzalloc(sizeof(*hd), GFP_KERNEL);
+	if (!hd)
+		return -ENOMEM;
+
+	hwirq = heart_alloc_int();
+	if (hwirq < 0) {
+		kfree(hd);
+		return -EAGAIN;
+	}
+	irq_domain_set_info(domain, virq, hwirq, &heart_irq_chip, hd,
+			    handle_level_irq, NULL, NULL);
+
+	return 0;
+}
+
+static void heart_domain_free(struct irq_domain *domain,
+			      unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *irqd;
+
+	if (nr_irqs > 1)
+		return;
+
+	irqd = irq_domain_get_irq_data(domain, virq);
+	clear_bit(irqd->hwirq, heart_irq_map);
+	if (irqd && irqd->chip_data)
+		kfree(irqd->chip_data);
+}
+
+static const struct irq_domain_ops heart_domain_ops = {
+	.alloc = heart_domain_alloc,
+	.free  = heart_domain_free,
+};
+
+void __init ip30_install_ipi(void)
+{
+	int cpu = smp_processor_id();
+	unsigned long *mask = &per_cpu(irq_enable_mask, cpu);
+
+	set_bit(HEART_L2_INT_RESCHED_CPU_0 + cpu, mask);
+	heart_write(BIT_ULL(HEART_L2_INT_RESCHED_CPU_0 + cpu),
+		    &heart_regs->clear_isr);
+	set_bit(HEART_L2_INT_CALL_CPU_0 + cpu, mask);
+	heart_write(BIT_ULL(HEART_L2_INT_CALL_CPU_0 + cpu),
+		    &heart_regs->clear_isr);
+
+	heart_write(*mask, &heart_regs->imr[cpu]);
+}
+
+void __init arch_init_irq(void)
+{
+	struct irq_domain *domain;
+	struct fwnode_handle *fn;
+	unsigned long *mask;
+	int i;
+
+	mips_cpu_irq_init();
+
+	/* Mask all IRQs. */
+	heart_write(HEART_CLR_ALL_MASK, &heart_regs->imr[0]);
+	heart_write(HEART_CLR_ALL_MASK, &heart_regs->imr[1]);
+	heart_write(HEART_CLR_ALL_MASK, &heart_regs->imr[2]);
+	heart_write(HEART_CLR_ALL_MASK, &heart_regs->imr[3]);
+
+	/* Ack everything. */
+	heart_write(HEART_ACK_ALL_MASK, &heart_regs->clear_isr);
+
+	/* Enable specific HEART error IRQs for each CPU. */
+	mask = &per_cpu(irq_enable_mask, 0);
+	*mask |= HEART_CPU0_ERR_MASK;
+	heart_write(*mask, &heart_regs->imr[0]);
+	mask = &per_cpu(irq_enable_mask, 1);
+	*mask |= HEART_CPU1_ERR_MASK;
+	heart_write(*mask, &heart_regs->imr[1]);
+
+	/*
+	 * Some HEART bits are reserved by hardware or by software convention.
+	 * Mark these as reserved right away so they won't be accidentally
+	 * used later.
+	 */
+	set_bit(HEART_L0_INT_GENERIC, heart_irq_map);
+	set_bit(HEART_L0_INT_FLOW_CTRL_HWTR_0, heart_irq_map);
+	set_bit(HEART_L0_INT_FLOW_CTRL_HWTR_1, heart_irq_map);
+	set_bit(HEART_L2_INT_RESCHED_CPU_0, heart_irq_map);
+	set_bit(HEART_L2_INT_RESCHED_CPU_1, heart_irq_map);
+	set_bit(HEART_L2_INT_CALL_CPU_0, heart_irq_map);
+	set_bit(HEART_L2_INT_CALL_CPU_1, heart_irq_map);
+	set_bit(HEART_L3_INT_TIMER, heart_irq_map);
+
+	/* Reserve the error interrupts (#51 to #63). */
+	for (i = HEART_L4_INT_XWID_ERR_9; i <= HEART_L4_INT_HEART_EXCP; i++)
+		set_bit(i, heart_irq_map);
+
+	fn = irq_domain_alloc_named_fwnode("HEART");
+	WARN_ON(fn == NULL);
+	if (!fn)
+		return;
+	domain = irq_domain_create_linear(fn, HEART_NUM_IRQS,
+					  &heart_domain_ops, NULL);
+	WARN_ON(domain == NULL);
+	if (!domain)
+		return;
+
+	irq_set_default_host(domain);
+
+	irq_set_percpu_devid(IP30_HEART_L0_IRQ);
+	irq_set_chained_handler_and_data(IP30_HEART_L0_IRQ, ip30_normal_irq,
+					 domain);
+	irq_set_percpu_devid(IP30_HEART_L1_IRQ);
+	irq_set_chained_handler_and_data(IP30_HEART_L1_IRQ, ip30_normal_irq,
+					 domain);
+	irq_set_percpu_devid(IP30_HEART_L2_IRQ);
+	irq_set_chained_handler_and_data(IP30_HEART_L2_IRQ, ip30_normal_irq,
+					 domain);
+	irq_set_percpu_devid(IP30_HEART_ERR_IRQ);
+	irq_set_chained_handler_and_data(IP30_HEART_ERR_IRQ, ip30_error_irq,
+					 domain);
+}
diff --git a/arch/mips/sgi-ip30/ip30-power.c b/arch/mips/sgi-ip30/ip30-power.c
new file mode 100644
index 000000000000..120b3f3d5108
--- /dev/null
+++ b/arch/mips/sgi-ip30/ip30-power.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ip30-power.c: Software powerdown and reset handling for IP30 architecture.
+ *
+ * Copyright (C) 2004-2007 Stanislaw Skowronek <skylark@unaligned.org>
+ *               2014 Joshua Kinard <kumba@gentoo.org>
+ *               2009 Johannes Dickgreber <tanzy@gmx.de>
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/notifier.h>
+#include <linux/delay.h>
+#include <linux/rtc/ds1685.h>
+#include <linux/interrupt.h>
+#include <linux/pm.h>
+
+#include <asm/reboot.h>
+#include <asm/sgi/heart.h>
+
+static void __noreturn ip30_machine_restart(char *cmd)
+{
+	/*
+	 * Execute HEART cold reset
+	 *   Yes, it's cold-HEARTed!
+	 */
+	heart_write((heart_read(&heart_regs->mode) | HM_COLD_RST),
+		    &heart_regs->mode);
+	unreachable();
+}
+
+static int __init ip30_reboot_setup(void)
+{
+	_machine_restart = ip30_machine_restart;
+
+	return 0;
+}
+
+subsys_initcall(ip30_reboot_setup);
diff --git a/arch/mips/sgi-ip30/ip30-setup.c b/arch/mips/sgi-ip30/ip30-setup.c
new file mode 100644
index 000000000000..44b1607e964d
--- /dev/null
+++ b/arch/mips/sgi-ip30/ip30-setup.c
@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * SGI IP30 miscellaneous setup bits.
+ *
+ * Copyright (C) 2004-2007 Stanislaw Skowronek <skylark@unaligned.org>
+ *               2007 Joshua Kinard <kumba@gentoo.org>
+ *               2009 Johannes Dickgreber <tanzy@gmx.de>
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/percpu.h>
+#include <linux/memblock.h>
+
+#include <asm/smp-ops.h>
+#include <asm/sgialib.h>
+#include <asm/time.h>
+#include <asm/sgi/heart.h>
+
+#include "ip30-common.h"
+
+/* Structure of accessible HEART registers located in XKPHYS space. */
+struct ip30_heart_regs __iomem *heart_regs = HEART_XKPHYS_BASE;
+
+/*
+ * ARCS will report up to the first 1GB of
+ * memory if queried.  Anything beyond that
+ * is marked as reserved.
+ */
+#define IP30_MAX_PROM_MEMORY	_AC(0x40000000, UL)
+
+/*
+ * Memory in the Octane starts at 512MB
+ */
+#define IP30_MEMORY_BASE	_AC(0x20000000, UL)
+
+/*
+ * If using ARCS to probe for memory, then
+ * remaining memory will start at this offset.
+ */
+#define IP30_REAL_MEMORY_START  (IP30_MEMORY_BASE + IP30_MAX_PROM_MEMORY)
+
+#define MEM_SHIFT(x) ((x) >> 20)
+
+static void __init ip30_mem_init(void)
+{
+	unsigned long total_mem;
+	phys_addr_t addr;
+	phys_addr_t size;
+	u32 memcfg;
+	int i;
+
+	total_mem = 0;
+	for (i = 0; i < HEART_MEMORY_BANKS; i++) {
+		memcfg = __raw_readl(&heart_regs->mem_cfg.l[i]);
+		if (!(memcfg & HEART_MEMCFG_VALID))
+			continue;
+
+		addr = memcfg & HEART_MEMCFG_ADDR_MASK;
+		addr <<= HEART_MEMCFG_UNIT_SHIFT;
+		addr += IP30_MEMORY_BASE;
+		size = memcfg & HEART_MEMCFG_SIZE_MASK;
+		size >>= HEART_MEMCFG_SIZE_SHIFT;
+		size += 1;
+		size <<= HEART_MEMCFG_UNIT_SHIFT;
+
+		total_mem += size;
+
+		if (addr >= IP30_REAL_MEMORY_START)
+			memblock_free(addr, size);
+		else if ((addr + size) > IP30_REAL_MEMORY_START)
+			memblock_free(IP30_REAL_MEMORY_START,
+				     size - IP30_MAX_PROM_MEMORY);
+	}
+	pr_info("Detected %luMB of physical memory.\n", MEM_SHIFT(total_mem));
+}
+
+/**
+ * ip30_cpu_time_init - platform time initialization.
+ */
+static void __init ip30_cpu_time_init(void)
+{
+	int cpu = smp_processor_id();
+	u64 heart_compare;
+	unsigned int start, end;
+	int time_diff;
+
+	heart_compare = (heart_read(&heart_regs->count) +
+			 (HEART_CYCLES_PER_SEC / 10));
+	start = read_c0_count();
+	while ((heart_read(&heart_regs->count) - heart_compare) & 0x800000)
+		cpu_relax();
+
+	end = read_c0_count();
+	time_diff = (int)end - (int)start;
+	mips_hpt_frequency = time_diff * 10;
+	pr_info("IP30: CPU%d: %d MHz CPU detected.\n", cpu,
+		(mips_hpt_frequency * 2) / 1000000);
+}
+
+void __init ip30_per_cpu_init(void)
+{
+	/* Disable all interrupts. */
+	clear_c0_status(ST0_IM);
+
+	ip30_cpu_time_init();
+#ifdef CONFIG_SMP
+	ip30_install_ipi();
+#endif
+
+	enable_percpu_irq(IP30_HEART_L0_IRQ, IRQ_TYPE_NONE);
+	enable_percpu_irq(IP30_HEART_L1_IRQ, IRQ_TYPE_NONE);
+	enable_percpu_irq(IP30_HEART_L2_IRQ, IRQ_TYPE_NONE);
+	enable_percpu_irq(IP30_HEART_ERR_IRQ, IRQ_TYPE_NONE);
+}
+
+/**
+ * plat_mem_setup - despite the name, misc setup happens here.
+ */
+void __init plat_mem_setup(void)
+{
+	ip30_mem_init();
+
+	/* XXX: Hard lock on /sbin/init if this flag isn't specified. */
+	prom_flags |= PROM_FLAG_DONT_FREE_TEMP;
+
+#ifdef CONFIG_SMP
+	register_smp_ops(&ip30_smp_ops);
+#else
+	ip30_per_cpu_init();
+#endif
+
+	ioport_resource.start = 0;
+	ioport_resource.end = ~0UL;
+	set_io_port_base(IO_BASE);
+}
diff --git a/arch/mips/sgi-ip30/ip30-smp.c b/arch/mips/sgi-ip30/ip30-smp.c
new file mode 100644
index 000000000000..4bfe654602b1
--- /dev/null
+++ b/arch/mips/sgi-ip30/ip30-smp.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ip30-smp.c: SMP on IP30 architecture.
+ * Based off of the original IP30 SMP code, with inspiration from ip27-smp.c
+ * and smp-bmips.c.
+ *
+ * Copyright (C) 2005-2007 Stanislaw Skowronek <skylark@unaligned.org>
+ *               2006-2007, 2014-2015 Joshua Kinard <kumba@gentoo.org>
+ *               2009 Johannes Dickgreber <tanzy@gmx.de>
+ */
+
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/time.h>
+#include <asm/sgi/heart.h>
+
+#include "ip30-common.h"
+
+#define MPCONF_MAGIC	0xbaddeed2
+#define	MPCONF_ADDR	0xa800000000000600L
+#define MPCONF_SIZE	0x80
+#define MPCONF(x)	(MPCONF_ADDR + (x) * MPCONF_SIZE)
+
+/* HEART can theoretically do 4 CPUs, but only 2 are physically possible */
+#define MP_NCPU		2
+
+struct mpconf {
+	u32 magic;
+	u32 prid;
+	u32 physid;
+	u32 virtid;
+	u32 scachesz;
+	u16 fanloads;
+	u16 res;
+	void *launch;
+	void *rendezvous;
+	u64 res2[3];
+	void *stackaddr;
+	void *lnch_parm;
+	void *rndv_parm;
+	u32 idleflag;
+};
+
+static void ip30_smp_send_ipi_single(int cpu, u32 action)
+{
+	int irq;
+
+	switch (action) {
+	case SMP_RESCHEDULE_YOURSELF:
+		irq = HEART_L2_INT_RESCHED_CPU_0;
+		break;
+	case SMP_CALL_FUNCTION:
+		irq = HEART_L2_INT_CALL_CPU_0;
+		break;
+	default:
+		panic("IP30: Unknown action value in %s!\n", __func__);
+	}
+
+	irq += cpu;
+
+	/* Poke the other CPU -- it's got mail! */
+	heart_write(BIT_ULL(irq), &heart_regs->set_isr);
+}
+
+static void ip30_smp_send_ipi_mask(const struct cpumask *mask, u32 action)
+{
+	u32 i;
+
+	for_each_cpu(i, mask)
+		ip30_smp_send_ipi_single(i, action);
+}
+
+static void __init ip30_smp_setup(void)
+{
+	int i;
+	int ncpu = 0;
+	struct mpconf *mpc;
+
+	init_cpu_possible(cpumask_of(0));
+
+	/* Scan the MPCONF structure and enumerate available CPUs. */
+	for (i = 0; i < MP_NCPU; i++) {
+		mpc = (struct mpconf *)MPCONF(i);
+		if (mpc->magic == MPCONF_MAGIC) {
+			set_cpu_possible(i, true);
+			__cpu_number_map[i] = ++ncpu;
+			__cpu_logical_map[ncpu] = i;
+			pr_info("IP30: Slot: %d, PrID: %.8x, PhyID: %d, VirtID: %d\n",
+				i, mpc->prid, mpc->physid, mpc->virtid);
+		}
+	}
+	pr_info("IP30: Detected %d CPU(s) present.\n", ncpu);
+
+	/*
+	 * Set the coherency algorithm to '5' (cacheable coherent
+	 * exclusive on write).  This is needed on IP30 SMP, especially
+	 * for R14000 CPUs, otherwise, instruction bus errors will
+	 * occur upon reaching userland.
+	 */
+	change_c0_config(CONF_CM_CMASK, CONF_CM_CACHABLE_COW);
+}
+
+static void __init ip30_smp_prepare_cpus(unsigned int max_cpus)
+{
+	/* nothing to do here */
+}
+
+static int __init ip30_smp_boot_secondary(int cpu, struct task_struct *idle)
+{
+	struct mpconf *mpc = (struct mpconf *)MPCONF(cpu);
+
+	/* Stack pointer (sp). */
+	mpc->stackaddr = (void *)__KSTK_TOS(idle);
+
+	/* Global pointer (gp). */
+	mpc->lnch_parm = task_thread_info(idle);
+
+	mb(); /* make sure stack and lparm are written */
+
+	/* Boot CPUx. */
+	mpc->launch = smp_bootstrap;
+
+	/* CPUx now executes smp_bootstrap, then ip30_smp_finish */
+	return 0;
+}
+
+static void __init ip30_smp_init_cpu(void)
+{
+	ip30_per_cpu_init();
+}
+
+static void __init ip30_smp_finish(void)
+{
+	enable_percpu_irq(get_c0_compare_int(), IRQ_TYPE_NONE);
+	local_irq_enable();
+}
+
+struct plat_smp_ops __read_mostly ip30_smp_ops = {
+	.send_ipi_single	= ip30_smp_send_ipi_single,
+	.send_ipi_mask		= ip30_smp_send_ipi_mask,
+	.smp_setup		= ip30_smp_setup,
+	.prepare_cpus		= ip30_smp_prepare_cpus,
+	.boot_secondary		= ip30_smp_boot_secondary,
+	.init_secondary		= ip30_smp_init_cpu,
+	.smp_finish		= ip30_smp_finish,
+	.prepare_boot_cpu	= ip30_smp_init_cpu,
+};
diff --git a/arch/mips/sgi-ip30/ip30-timer.c b/arch/mips/sgi-ip30/ip30-timer.c
new file mode 100644
index 000000000000..d13e105478ae
--- /dev/null
+++ b/arch/mips/sgi-ip30/ip30-timer.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ip30-timer.c: Clocksource/clockevent support for the
+ *               HEART chip in SGI Octane (IP30) systems.
+ *
+ * Copyright (C) 2004-2007 Stanislaw Skowronek <skylark@unaligned.org>
+ * Copyright (C) 2009 Johannes Dickgreber <tanzy@gmx.de>
+ * Copyright (C) 2011 Joshua Kinard <kumba@gentoo.org>
+ */
+
+#include <linux/clocksource.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/sched_clock.h>
+
+#include <asm/time.h>
+#include <asm/cevt-r4k.h>
+#include <asm/sgi/heart.h>
+
+static u64 ip30_heart_counter_read(struct clocksource *cs)
+{
+	return heart_read(&heart_regs->count);
+}
+
+struct clocksource ip30_heart_clocksource = {
+	.name	= "HEART",
+	.rating	= 400,
+	.read	= ip30_heart_counter_read,
+	.mask	= CLOCKSOURCE_MASK(52),
+	.flags	= (CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_VALID_FOR_HRES),
+};
+
+static u64 notrace ip30_heart_read_sched_clock(void)
+{
+	return heart_read(&heart_regs->count);
+}
+
+static void __init ip30_heart_clocksource_init(void)
+{
+	struct clocksource *cs = &ip30_heart_clocksource;
+
+	clocksource_register_hz(cs, HEART_CYCLES_PER_SEC);
+
+	sched_clock_register(ip30_heart_read_sched_clock, 52,
+			     HEART_CYCLES_PER_SEC);
+}
+
+void __init plat_time_init(void)
+{
+	int irq = get_c0_compare_int();
+
+	cp0_timer_irq_installed = 1;
+	c0_compare_irqaction.percpu_dev_id = &mips_clockevent_device;
+	c0_compare_irqaction.flags &= ~IRQF_SHARED;
+	irq_set_handler(irq, handle_percpu_devid_irq);
+	irq_set_percpu_devid(irq);
+	setup_percpu_irq(irq, &c0_compare_irqaction);
+	enable_percpu_irq(irq, IRQ_TYPE_NONE);
+
+	ip30_heart_clocksource_init();
+}
diff --git a/arch/mips/sgi-ip30/ip30-xtalk.c b/arch/mips/sgi-ip30/ip30-xtalk.c
new file mode 100644
index 000000000000..8a2894645529
--- /dev/null
+++ b/arch/mips/sgi-ip30/ip30-xtalk.c
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ip30-xtalk.c - Very basic Crosstalk (XIO) detection support.
+ *   Copyright (C) 2004-2007 Stanislaw Skowronek <skylark@unaligned.org>
+ *   Copyright (C) 2009 Johannes Dickgreber <tanzy@gmx.de>
+ *   Copyright (C) 2007, 2014-2016 Joshua Kinard <kumba@gentoo.org>
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/sgi-w1.h>
+#include <linux/platform_data/xtalk-bridge.h>
+
+#include <asm/xtalk/xwidget.h>
+#include <asm/pci/bridge.h>
+
+#define IP30_SWIN_BASE(widget) \
+		(0x0000000010000000 | (((unsigned long)(widget)) << 24))
+
+#define IP30_RAW_SWIN_BASE(widget)	(IO_BASE + IP30_SWIN_BASE(widget))
+
+#define IP30_SWIN_SIZE		(1 << 24)
+
+#define IP30_WIDGET_XBOW        _AC(0x0, UL)    /* XBow is always 0 */
+#define IP30_WIDGET_HEART       _AC(0x8, UL)    /* HEART is always 8 */
+#define IP30_WIDGET_PCI_BASE    _AC(0xf, UL)    /* BaseIO PCI is always 15 */
+
+#define XTALK_NODEV             0xffffffff
+
+#define XBOW_REG_LINK_STAT_0    0x114
+#define XBOW_REG_LINK_BLK_SIZE  0x40
+#define XBOW_REG_LINK_ALIVE     0x80000000
+
+#define HEART_INTR_ADDR		0x00000080
+
+#define xtalk_read	__raw_readl
+
+static void bridge_platform_create(int widget, int masterwid)
+{
+	struct xtalk_bridge_platform_data *bd;
+	struct sgi_w1_platform_data *wd;
+	struct platform_device *pdev;
+	struct resource w1_res;
+
+	wd = kzalloc(sizeof(*wd), GFP_KERNEL);
+	if (!wd)
+		goto no_mem;
+
+	snprintf(wd->dev_id, sizeof(wd->dev_id), "bridge-%012lx",
+		 IP30_SWIN_BASE(widget));
+
+	memset(&w1_res, 0, sizeof(w1_res));
+	w1_res.start = IP30_SWIN_BASE(widget) +
+				offsetof(struct bridge_regs, b_nic);
+	w1_res.end = w1_res.start + 3;
+	w1_res.flags = IORESOURCE_MEM;
+
+	pdev = platform_device_alloc("sgi_w1", PLATFORM_DEVID_AUTO);
+	if (!pdev) {
+		kfree(wd);
+		goto no_mem;
+	}
+	platform_device_add_resources(pdev, &w1_res, 1);
+	platform_device_add_data(pdev, wd, sizeof(*wd));
+	platform_device_add(pdev);
+
+	bd = kzalloc(sizeof(*bd), GFP_KERNEL);
+	if (!bd)
+		goto no_mem;
+	pdev = platform_device_alloc("xtalk-bridge", PLATFORM_DEVID_AUTO);
+	if (!pdev) {
+		kfree(bd);
+		goto no_mem;
+	}
+
+	bd->bridge_addr	= IP30_RAW_SWIN_BASE(widget);
+	bd->intr_addr	= HEART_INTR_ADDR;
+	bd->nasid	= 0;
+	bd->masterwid	= masterwid;
+
+	bd->mem.name	= "Bridge PCI MEM";
+	bd->mem.start	= IP30_SWIN_BASE(widget) + BRIDGE_DEVIO0;
+	bd->mem.end	= IP30_SWIN_BASE(widget) + IP30_SWIN_SIZE - 1;
+	bd->mem.flags	= IORESOURCE_MEM;
+	bd->mem_offset	= IP30_SWIN_BASE(widget);
+
+	bd->io.name	= "Bridge PCI IO";
+	bd->io.start	= IP30_SWIN_BASE(widget) + BRIDGE_DEVIO0;
+	bd->io.end	= IP30_SWIN_BASE(widget) + IP30_SWIN_SIZE - 1;
+	bd->io.flags	= IORESOURCE_IO;
+	bd->io_offset	= IP30_SWIN_BASE(widget);
+
+	platform_device_add_data(pdev, bd, sizeof(*bd));
+	platform_device_add(pdev);
+	pr_info("xtalk:%x bridge widget\n", widget);
+	return;
+
+no_mem:
+	pr_warn("xtalk:%x bridge create out of memory\n", widget);
+}
+
+static unsigned int __init xbow_widget_active(s8 wid)
+{
+	unsigned int link_stat;
+
+	link_stat = xtalk_read((void *)(IP30_RAW_SWIN_BASE(IP30_WIDGET_XBOW) +
+					XBOW_REG_LINK_STAT_0 +
+					XBOW_REG_LINK_BLK_SIZE *
+					(wid - 8)));
+
+	return (link_stat & XBOW_REG_LINK_ALIVE) ? 1 : 0;
+}
+
+static void __init xtalk_init_widget(s8 wid, s8 masterwid)
+{
+	xwidget_part_num_t partnum;
+	widgetreg_t widget_id;
+
+	if (!xbow_widget_active(wid))
+		return;
+
+	widget_id = xtalk_read((void *)(IP30_RAW_SWIN_BASE(wid) + WIDGET_ID));
+
+	partnum = XWIDGET_PART_NUM(widget_id);
+
+	switch (partnum) {
+	case BRIDGE_WIDGET_PART_NUM:
+	case XBRIDGE_WIDGET_PART_NUM:
+		bridge_platform_create(wid, masterwid);
+		break;
+	default:
+		pr_info("xtalk:%x unknown widget (0x%x)\n", wid, partnum);
+		break;
+	}
+}
+
+static int __init ip30_xtalk_init(void)
+{
+	int i;
+
+	/*
+	 * Walk widget IDs backwards so that BaseIO is probed first.  This
+	 * ensures that the BaseIO IOC3 is always detected as eth0.
+	 */
+	for (i = IP30_WIDGET_PCI_BASE; i > IP30_WIDGET_HEART; i--)
+		xtalk_init_widget(i, IP30_WIDGET_HEART);
+
+	return 0;
+}
+
+arch_initcall(ip30_xtalk_init);
diff --git a/arch/mips/tools/.gitignore b/arch/mips/tools/.gitignore
index 56d34ccccce4..b0209450d9ff 100644
--- a/arch/mips/tools/.gitignore
+++ b/arch/mips/tools/.gitignore
@@ -1 +1,2 @@
 elf-entry
+loongson3-llsc-check
diff --git a/arch/mips/tools/Makefile b/arch/mips/tools/Makefile
index 3baee4bc6775..aaef688749f5 100644
--- a/arch/mips/tools/Makefile
+++ b/arch/mips/tools/Makefile
@@ -3,3 +3,8 @@ hostprogs-y := elf-entry
 PHONY += elf-entry
 elf-entry: $(obj)/elf-entry
 	@:
+
+hostprogs-$(CONFIG_CPU_LOONGSON3_WORKAROUNDS) += loongson3-llsc-check
+PHONY += loongson3-llsc-check
+loongson3-llsc-check: $(obj)/loongson3-llsc-check
+	@:
diff --git a/arch/mips/tools/loongson3-llsc-check.c b/arch/mips/tools/loongson3-llsc-check.c
new file mode 100644
index 000000000000..0ebddd0ae46f
--- /dev/null
+++ b/arch/mips/tools/loongson3-llsc-check.c
@@ -0,0 +1,307 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <byteswap.h>
+#include <elf.h>
+#include <endian.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#ifdef be32toh
+/* If libc provides le{16,32,64}toh() then we'll use them */
+#elif BYTE_ORDER == LITTLE_ENDIAN
+# define le16toh(x)	(x)
+# define le32toh(x)	(x)
+# define le64toh(x)	(x)
+#elif BYTE_ORDER == BIG_ENDIAN
+# define le16toh(x)	bswap_16(x)
+# define le32toh(x)	bswap_32(x)
+# define le64toh(x)	bswap_64(x)
+#endif
+
+/* MIPS opcodes, in bits 31:26 of an instruction */
+#define OP_SPECIAL	0x00
+#define OP_REGIMM	0x01
+#define OP_BEQ		0x04
+#define OP_BNE		0x05
+#define OP_BLEZ		0x06
+#define OP_BGTZ		0x07
+#define OP_BEQL		0x14
+#define OP_BNEL		0x15
+#define OP_BLEZL	0x16
+#define OP_BGTZL	0x17
+#define OP_LL		0x30
+#define OP_LLD		0x34
+#define OP_SC		0x38
+#define OP_SCD		0x3c
+
+/* Bits 20:16 of OP_REGIMM instructions */
+#define REGIMM_BLTZ	0x00
+#define REGIMM_BGEZ	0x01
+#define REGIMM_BLTZL	0x02
+#define REGIMM_BGEZL	0x03
+#define REGIMM_BLTZAL	0x10
+#define REGIMM_BGEZAL	0x11
+#define REGIMM_BLTZALL	0x12
+#define REGIMM_BGEZALL	0x13
+
+/* Bits 5:0 of OP_SPECIAL instructions */
+#define SPECIAL_SYNC	0x0f
+
+static void usage(FILE *f)
+{
+	fprintf(f, "Usage: loongson3-llsc-check /path/to/vmlinux\n");
+}
+
+static int se16(uint16_t x)
+{
+	return (int16_t)x;
+}
+
+static bool is_ll(uint32_t insn)
+{
+	switch (insn >> 26) {
+	case OP_LL:
+	case OP_LLD:
+		return true;
+
+	default:
+		return false;
+	}
+}
+
+static bool is_sc(uint32_t insn)
+{
+	switch (insn >> 26) {
+	case OP_SC:
+	case OP_SCD:
+		return true;
+
+	default:
+		return false;
+	}
+}
+
+static bool is_sync(uint32_t insn)
+{
+	/* Bits 31:11 should all be zeroes */
+	if (insn >> 11)
+		return false;
+
+	/* Bits 5:0 specify the SYNC special encoding */
+	if ((insn & 0x3f) != SPECIAL_SYNC)
+		return false;
+
+	return true;
+}
+
+static bool is_branch(uint32_t insn, int *off)
+{
+	switch (insn >> 26) {
+	case OP_BEQ:
+	case OP_BEQL:
+	case OP_BNE:
+	case OP_BNEL:
+	case OP_BGTZ:
+	case OP_BGTZL:
+	case OP_BLEZ:
+	case OP_BLEZL:
+		*off = se16(insn) + 1;
+		return true;
+
+	case OP_REGIMM:
+		switch ((insn >> 16) & 0x1f) {
+		case REGIMM_BGEZ:
+		case REGIMM_BGEZL:
+		case REGIMM_BGEZAL:
+		case REGIMM_BGEZALL:
+		case REGIMM_BLTZ:
+		case REGIMM_BLTZL:
+		case REGIMM_BLTZAL:
+		case REGIMM_BLTZALL:
+			*off = se16(insn) + 1;
+			return true;
+
+		default:
+			return false;
+		}
+
+	default:
+		return false;
+	}
+}
+
+static int check_ll(uint64_t pc, uint32_t *code, size_t sz)
+{
+	ssize_t i, max, sc_pos;
+	int off;
+
+	/*
+	 * Every LL must be preceded by a sync instruction in order to ensure
+	 * that instruction reordering doesn't allow a prior memory access to
+	 * execute after the LL & cause erroneous results.
+	 */
+	if (!is_sync(le32toh(code[-1]))) {
+		fprintf(stderr, "%" PRIx64 ": LL not preceded by sync\n", pc);
+		return -EINVAL;
+	}
+
+	/* Find the matching SC instruction */
+	max = sz / 4;
+	for (sc_pos = 0; sc_pos < max; sc_pos++) {
+		if (is_sc(le32toh(code[sc_pos])))
+			break;
+	}
+	if (sc_pos >= max) {
+		fprintf(stderr, "%" PRIx64 ": LL has no matching SC\n", pc);
+		return -EINVAL;
+	}
+
+	/*
+	 * Check branches within the LL/SC loop target sync instructions,
+	 * ensuring that speculative execution can't generate memory accesses
+	 * due to instructions outside of the loop.
+	 */
+	for (i = 0; i < sc_pos; i++) {
+		if (!is_branch(le32toh(code[i]), &off))
+			continue;
+
+		/*
+		 * If the branch target is within the LL/SC loop then we don't
+		 * need to worry about it.
+		 */
+		if ((off >= -i) && (off <= sc_pos))
+			continue;
+
+		/* If the branch targets a sync instruction we're all good... */
+		if (is_sync(le32toh(code[i + off])))
+			continue;
+
+		/* ...but if not, we have a problem */
+		fprintf(stderr, "%" PRIx64 ": Branch target not a sync\n",
+			pc + (i * 4));
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int check_code(uint64_t pc, uint32_t *code, size_t sz)
+{
+	int err = 0;
+
+	if (sz % 4) {
+		fprintf(stderr, "%" PRIx64 ": Section size not a multiple of 4\n",
+			pc);
+		err = -EINVAL;
+		sz -= (sz % 4);
+	}
+
+	if (is_ll(le32toh(code[0]))) {
+		fprintf(stderr, "%" PRIx64 ": First instruction in section is an LL\n",
+			pc);
+		err = -EINVAL;
+	}
+
+#define advance() (	\
+	code++,		\
+	pc += 4,	\
+	sz -= 4		\
+)
+
+	/*
+	 * Skip the first instructionm allowing check_ll to look backwards
+	 * unconditionally.
+	 */
+	advance();
+
+	/* Now scan through the code looking for LL instructions */
+	for (; sz; advance()) {
+		if (is_ll(le32toh(code[0])))
+			err |= check_ll(pc, code, sz);
+	}
+
+	return err;
+}
+
+int main(int argc, char *argv[])
+{
+	int vmlinux_fd, status, err, i;
+	const char *vmlinux_path;
+	struct stat st;
+	Elf64_Ehdr *eh;
+	Elf64_Shdr *sh;
+	void *vmlinux;
+
+	status = EXIT_FAILURE;
+
+	if (argc < 2) {
+		usage(stderr);
+		goto out_ret;
+	}
+
+	vmlinux_path = argv[1];
+	vmlinux_fd = open(vmlinux_path, O_RDONLY);
+	if (vmlinux_fd == -1) {
+		perror("Unable to open vmlinux");
+		goto out_ret;
+	}
+
+	err = fstat(vmlinux_fd, &st);
+	if (err) {
+		perror("Unable to stat vmlinux");
+		goto out_close;
+	}
+
+	vmlinux = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, vmlinux_fd, 0);
+	if (vmlinux == MAP_FAILED) {
+		perror("Unable to mmap vmlinux");
+		goto out_close;
+	}
+
+	eh = vmlinux;
+	if (memcmp(eh->e_ident, ELFMAG, SELFMAG)) {
+		fprintf(stderr, "vmlinux is not an ELF?\n");
+		goto out_munmap;
+	}
+
+	if (eh->e_ident[EI_CLASS] != ELFCLASS64) {
+		fprintf(stderr, "vmlinux is not 64b?\n");
+		goto out_munmap;
+	}
+
+	if (eh->e_ident[EI_DATA] != ELFDATA2LSB) {
+		fprintf(stderr, "vmlinux is not little endian?\n");
+		goto out_munmap;
+	}
+
+	for (i = 0; i < le16toh(eh->e_shnum); i++) {
+		sh = vmlinux + le64toh(eh->e_shoff) + (i * le16toh(eh->e_shentsize));
+
+		if (sh->sh_type != SHT_PROGBITS)
+			continue;
+		if (!(sh->sh_flags & SHF_EXECINSTR))
+			continue;
+
+		err = check_code(le64toh(sh->sh_addr),
+				 vmlinux + le64toh(sh->sh_offset),
+				 le64toh(sh->sh_size));
+		if (err)
+			goto out_munmap;
+	}
+
+	status = EXIT_SUCCESS;
+out_munmap:
+	munmap(vmlinux, st.st_size);
+out_close:
+	close(vmlinux_fd);
+out_ret:
+	return status;
+}
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index 996a934ece7d..e05938997e69 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -75,6 +75,7 @@ CFLAGS_REMOVE_vdso.o = -pg
 
 GCOV_PROFILE := n
 UBSAN_SANITIZE := n
+KCOV_INSTRUMENT := n
 
 #
 # Shared build commands.
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 36b834f1c933..dca8f2de8cf5 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -60,7 +60,6 @@ KBUILD_CFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY=1 \
 		 -DFTRACE_PATCHABLE_FUNCTION_SIZE=$(NOP_COUNT)
 
 CC_FLAGS_FTRACE := -fpatchable-function-entry=$(NOP_COUNT),$(shell echo $$(($(NOP_COUNT)-1)))
-KBUILD_LDS_MODULE += $(srctree)/arch/parisc/kernel/module.lds
 endif
 
 OBJCOPY_FLAGS =-O binary -R .note -R .comment -S
diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c
index ac5f34993b53..1c50093e2ebe 100644
--- a/arch/parisc/kernel/module.c
+++ b/arch/parisc/kernel/module.c
@@ -43,6 +43,7 @@
 #include <linux/elf.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
+#include <linux/ftrace.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/bug.h>
@@ -862,7 +863,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 	const char *strtab = NULL;
 	const Elf_Shdr *s;
 	char *secstrings;
-	int err, symindex = -1;
+	int symindex = -1;
 	Elf_Sym *newptr, *oldptr;
 	Elf_Shdr *symhdr = NULL;
 #ifdef DEBUG
@@ -946,11 +947,13 @@ int module_finalize(const Elf_Ehdr *hdr,
 			/* patch .altinstructions */
 			apply_alternatives(aseg, aseg + s->sh_size, me->name);
 
+#ifdef CONFIG_DYNAMIC_FTRACE
 		/* For 32 bit kernels we're compiling modules with
 		 * -ffunction-sections so we must relocate the addresses in the
-		 *__mcount_loc section.
+		 *  ftrace callsite section.
 		 */
-		if (symindex != -1 && !strcmp(secname, "__mcount_loc")) {
+		if (symindex != -1 && !strcmp(secname, FTRACE_CALLSITE_SECTION)) {
+			int err;
 			if (s->sh_type == SHT_REL)
 				err = apply_relocate((Elf_Shdr *)sechdrs,
 							strtab, symindex,
@@ -962,6 +965,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 			if (err)
 				return err;
 		}
+#endif
 	}
 	return 0;
 }
diff --git a/arch/parisc/kernel/module.lds b/arch/parisc/kernel/module.lds
deleted file mode 100644
index 1a9a92aca5c8..000000000000
--- a/arch/parisc/kernel/module.lds
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-SECTIONS {
-	__mcount_loc : {
-		*(__patchable_function_entries)
-	}
-}
diff --git a/arch/powerpc/crypto/aes-spe-glue.c b/arch/powerpc/crypto/aes-spe-glue.c
index 3a4ca7d32477..1fad5d4c658d 100644
--- a/arch/powerpc/crypto/aes-spe-glue.c
+++ b/arch/powerpc/crypto/aes-spe-glue.c
@@ -17,7 +17,10 @@
 #include <asm/byteorder.h>
 #include <asm/switch_to.h>
 #include <crypto/algapi.h>
+#include <crypto/internal/skcipher.h>
 #include <crypto/xts.h>
+#include <crypto/gf128mul.h>
+#include <crypto/scatterwalk.h>
 
 /*
  * MAX_BYTES defines the number of bytes that are allowed to be processed
@@ -118,13 +121,19 @@ static int ppc_aes_setkey(struct crypto_tfm *tfm, const u8 *in_key,
 	return 0;
 }
 
-static int ppc_xts_setkey(struct crypto_tfm *tfm, const u8 *in_key,
+static int ppc_aes_setkey_skcipher(struct crypto_skcipher *tfm,
+				   const u8 *in_key, unsigned int key_len)
+{
+	return ppc_aes_setkey(crypto_skcipher_tfm(tfm), in_key, key_len);
+}
+
+static int ppc_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 		   unsigned int key_len)
 {
-	struct ppc_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct ppc_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 	int err;
 
-	err = xts_check_key(tfm, in_key, key_len);
+	err = xts_verify_key(tfm, in_key, key_len);
 	if (err)
 		return err;
 
@@ -133,7 +142,7 @@ static int ppc_xts_setkey(struct crypto_tfm *tfm, const u8 *in_key,
 	if (key_len != AES_KEYSIZE_128 &&
 	    key_len != AES_KEYSIZE_192 &&
 	    key_len != AES_KEYSIZE_256) {
-		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
@@ -178,208 +187,229 @@ static void ppc_aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 	spe_end();
 }
 
-static int ppc_ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-			   struct scatterlist *src, unsigned int nbytes)
+static int ppc_ecb_crypt(struct skcipher_request *req, bool enc)
 {
-	struct ppc_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	unsigned int ubytes;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct ppc_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	while ((nbytes = walk.nbytes)) {
-		ubytes = nbytes > MAX_BYTES ?
-			 nbytes - MAX_BYTES : nbytes & (AES_BLOCK_SIZE - 1);
-		nbytes -= ubytes;
+	while ((nbytes = walk.nbytes) != 0) {
+		nbytes = min_t(unsigned int, nbytes, MAX_BYTES);
+		nbytes = round_down(nbytes, AES_BLOCK_SIZE);
 
 		spe_begin();
-		ppc_encrypt_ecb(walk.dst.virt.addr, walk.src.virt.addr,
-				ctx->key_enc, ctx->rounds, nbytes);
+		if (enc)
+			ppc_encrypt_ecb(walk.dst.virt.addr, walk.src.virt.addr,
+					ctx->key_enc, ctx->rounds, nbytes);
+		else
+			ppc_decrypt_ecb(walk.dst.virt.addr, walk.src.virt.addr,
+					ctx->key_dec, ctx->rounds, nbytes);
 		spe_end();
 
-		err = blkcipher_walk_done(desc, &walk, ubytes);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
 	return err;
 }
 
-static int ppc_ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-			   struct scatterlist *src, unsigned int nbytes)
+static int ppc_ecb_encrypt(struct skcipher_request *req)
 {
-	struct ppc_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	unsigned int ubytes;
-	int err;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-
-	while ((nbytes = walk.nbytes)) {
-		ubytes = nbytes > MAX_BYTES ?
-			 nbytes - MAX_BYTES : nbytes & (AES_BLOCK_SIZE - 1);
-		nbytes -= ubytes;
-
-		spe_begin();
-		ppc_decrypt_ecb(walk.dst.virt.addr, walk.src.virt.addr,
-				ctx->key_dec, ctx->rounds, nbytes);
-		spe_end();
-
-		err = blkcipher_walk_done(desc, &walk, ubytes);
-	}
+	return ppc_ecb_crypt(req, true);
+}
 
-	return err;
+static int ppc_ecb_decrypt(struct skcipher_request *req)
+{
+	return ppc_ecb_crypt(req, false);
 }
 
-static int ppc_cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-			   struct scatterlist *src, unsigned int nbytes)
+static int ppc_cbc_crypt(struct skcipher_request *req, bool enc)
 {
-	struct ppc_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	unsigned int ubytes;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct ppc_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	while ((nbytes = walk.nbytes)) {
-		ubytes = nbytes > MAX_BYTES ?
-			 nbytes - MAX_BYTES : nbytes & (AES_BLOCK_SIZE - 1);
-		nbytes -= ubytes;
+	while ((nbytes = walk.nbytes) != 0) {
+		nbytes = min_t(unsigned int, nbytes, MAX_BYTES);
+		nbytes = round_down(nbytes, AES_BLOCK_SIZE);
 
 		spe_begin();
-		ppc_encrypt_cbc(walk.dst.virt.addr, walk.src.virt.addr,
-				ctx->key_enc, ctx->rounds, nbytes, walk.iv);
+		if (enc)
+			ppc_encrypt_cbc(walk.dst.virt.addr, walk.src.virt.addr,
+					ctx->key_enc, ctx->rounds, nbytes,
+					walk.iv);
+		else
+			ppc_decrypt_cbc(walk.dst.virt.addr, walk.src.virt.addr,
+					ctx->key_dec, ctx->rounds, nbytes,
+					walk.iv);
 		spe_end();
 
-		err = blkcipher_walk_done(desc, &walk, ubytes);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
 	return err;
 }
 
-static int ppc_cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-			   struct scatterlist *src, unsigned int nbytes)
+static int ppc_cbc_encrypt(struct skcipher_request *req)
 {
-	struct ppc_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	unsigned int ubytes;
-	int err;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-
-	while ((nbytes = walk.nbytes)) {
-		ubytes = nbytes > MAX_BYTES ?
-			 nbytes - MAX_BYTES : nbytes & (AES_BLOCK_SIZE - 1);
-		nbytes -= ubytes;
-
-		spe_begin();
-		ppc_decrypt_cbc(walk.dst.virt.addr, walk.src.virt.addr,
-				ctx->key_dec, ctx->rounds, nbytes, walk.iv);
-		spe_end();
-
-		err = blkcipher_walk_done(desc, &walk, ubytes);
-	}
+	return ppc_cbc_crypt(req, true);
+}
 
-	return err;
+static int ppc_cbc_decrypt(struct skcipher_request *req)
+{
+	return ppc_cbc_crypt(req, false);
 }
 
-static int ppc_ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-			 struct scatterlist *src, unsigned int nbytes)
+static int ppc_ctr_crypt(struct skcipher_request *req)
 {
-	struct ppc_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	unsigned int pbytes, ubytes;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct ppc_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	while ((pbytes = walk.nbytes)) {
-		pbytes = pbytes > MAX_BYTES ? MAX_BYTES : pbytes;
-		pbytes = pbytes == nbytes ?
-			 nbytes : pbytes & ~(AES_BLOCK_SIZE - 1);
-		ubytes = walk.nbytes - pbytes;
+	while ((nbytes = walk.nbytes) != 0) {
+		nbytes = min_t(unsigned int, nbytes, MAX_BYTES);
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, AES_BLOCK_SIZE);
 
 		spe_begin();
 		ppc_crypt_ctr(walk.dst.virt.addr, walk.src.virt.addr,
-			      ctx->key_enc, ctx->rounds, pbytes , walk.iv);
+			      ctx->key_enc, ctx->rounds, nbytes, walk.iv);
 		spe_end();
 
-		nbytes -= pbytes;
-		err = blkcipher_walk_done(desc, &walk, ubytes);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
 	return err;
 }
 
-static int ppc_xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-			   struct scatterlist *src, unsigned int nbytes)
+static int ppc_xts_crypt(struct skcipher_request *req, bool enc)
 {
-	struct ppc_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	unsigned int ubytes;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct ppc_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 	u32 *twk;
 
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	err = skcipher_walk_virt(&walk, req, false);
 	twk = ctx->key_twk;
 
-	while ((nbytes = walk.nbytes)) {
-		ubytes = nbytes > MAX_BYTES ?
-			 nbytes - MAX_BYTES : nbytes & (AES_BLOCK_SIZE - 1);
-		nbytes -= ubytes;
+	while ((nbytes = walk.nbytes) != 0) {
+		nbytes = min_t(unsigned int, nbytes, MAX_BYTES);
+		nbytes = round_down(nbytes, AES_BLOCK_SIZE);
 
 		spe_begin();
-		ppc_encrypt_xts(walk.dst.virt.addr, walk.src.virt.addr,
-				ctx->key_enc, ctx->rounds, nbytes, walk.iv, twk);
+		if (enc)
+			ppc_encrypt_xts(walk.dst.virt.addr, walk.src.virt.addr,
+					ctx->key_enc, ctx->rounds, nbytes,
+					walk.iv, twk);
+		else
+			ppc_decrypt_xts(walk.dst.virt.addr, walk.src.virt.addr,
+					ctx->key_dec, ctx->rounds, nbytes,
+					walk.iv, twk);
 		spe_end();
 
 		twk = NULL;
-		err = blkcipher_walk_done(desc, &walk, ubytes);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
 	return err;
 }
 
-static int ppc_xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-			   struct scatterlist *src, unsigned int nbytes)
+static int ppc_xts_encrypt(struct skcipher_request *req)
 {
-	struct ppc_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	unsigned int ubytes;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct ppc_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int tail = req->cryptlen % AES_BLOCK_SIZE;
+	int offset = req->cryptlen - tail - AES_BLOCK_SIZE;
+	struct skcipher_request subreq;
+	u8 b[2][AES_BLOCK_SIZE];
 	int err;
-	u32 *twk;
 
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	twk = ctx->key_twk;
+	if (req->cryptlen < AES_BLOCK_SIZE)
+		return -EINVAL;
+
+	if (tail) {
+		subreq = *req;
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   req->cryptlen - tail, req->iv);
+		req = &subreq;
+	}
 
-	while ((nbytes = walk.nbytes)) {
-		ubytes = nbytes > MAX_BYTES ?
-			 nbytes - MAX_BYTES : nbytes & (AES_BLOCK_SIZE - 1);
-		nbytes -= ubytes;
+	err = ppc_xts_crypt(req, true);
+	if (err || !tail)
+		return err;
 
-		spe_begin();
-		ppc_decrypt_xts(walk.dst.virt.addr, walk.src.virt.addr,
-				ctx->key_dec, ctx->rounds, nbytes, walk.iv, twk);
-		spe_end();
+	scatterwalk_map_and_copy(b[0], req->dst, offset, AES_BLOCK_SIZE, 0);
+	memcpy(b[1], b[0], tail);
+	scatterwalk_map_and_copy(b[0], req->src, offset + AES_BLOCK_SIZE, tail, 0);
 
-		twk = NULL;
-		err = blkcipher_walk_done(desc, &walk, ubytes);
+	spe_begin();
+	ppc_encrypt_xts(b[0], b[0], ctx->key_enc, ctx->rounds, AES_BLOCK_SIZE,
+			req->iv, NULL);
+	spe_end();
+
+	scatterwalk_map_and_copy(b[0], req->dst, offset, AES_BLOCK_SIZE + tail, 1);
+
+	return 0;
+}
+
+static int ppc_xts_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct ppc_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int tail = req->cryptlen % AES_BLOCK_SIZE;
+	int offset = req->cryptlen - tail - AES_BLOCK_SIZE;
+	struct skcipher_request subreq;
+	u8 b[3][AES_BLOCK_SIZE];
+	le128 twk;
+	int err;
+
+	if (req->cryptlen < AES_BLOCK_SIZE)
+		return -EINVAL;
+
+	if (tail) {
+		subreq = *req;
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   offset, req->iv);
+		req = &subreq;
 	}
 
-	return err;
+	err = ppc_xts_crypt(req, false);
+	if (err || !tail)
+		return err;
+
+	scatterwalk_map_and_copy(b[1], req->src, offset, AES_BLOCK_SIZE + tail, 0);
+
+	spe_begin();
+	if (!offset)
+		ppc_encrypt_ecb(req->iv, req->iv, ctx->key_twk, ctx->rounds,
+				AES_BLOCK_SIZE);
+
+	gf128mul_x_ble(&twk, (le128 *)req->iv);
+
+	ppc_decrypt_xts(b[1], b[1], ctx->key_dec, ctx->rounds, AES_BLOCK_SIZE,
+			(u8 *)&twk, NULL);
+	memcpy(b[0], b[2], tail);
+	memcpy(b[0] + tail, b[1] + tail, AES_BLOCK_SIZE - tail);
+	ppc_decrypt_xts(b[0], b[0], ctx->key_dec, ctx->rounds, AES_BLOCK_SIZE,
+			req->iv, NULL);
+	spe_end();
+
+	scatterwalk_map_and_copy(b[0], req->dst, offset, AES_BLOCK_SIZE + tail, 1);
+
+	return 0;
 }
 
 /*
@@ -388,9 +418,9 @@ static int ppc_xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
  * This improves IPsec thoughput by another few percent. Additionally we assume
  * that AES context is always aligned to at least 8 bytes because it is created
  * with kmalloc() in the crypto infrastructure
- *
  */
-static struct crypto_alg aes_algs[] = { {
+
+static struct crypto_alg aes_cipher_alg = {
 	.cra_name		=	"aes",
 	.cra_driver_name	=	"aes-ppc-spe",
 	.cra_priority		=	300,
@@ -408,96 +438,84 @@ static struct crypto_alg aes_algs[] = { {
 			.cia_decrypt		=	ppc_aes_decrypt
 		}
 	}
-}, {
-	.cra_name		=	"ecb(aes)",
-	.cra_driver_name	=	"ecb-ppc-spe",
-	.cra_priority		=	300,
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct ppc_aes_ctx),
-	.cra_alignmask		=	0,
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize		=	AES_MIN_KEY_SIZE,
-			.max_keysize		=	AES_MAX_KEY_SIZE,
-			.ivsize			=	AES_BLOCK_SIZE,
-			.setkey			=	ppc_aes_setkey,
-			.encrypt		=	ppc_ecb_encrypt,
-			.decrypt		=	ppc_ecb_decrypt,
-		}
-	}
-}, {
-	.cra_name		=	"cbc(aes)",
-	.cra_driver_name	=	"cbc-ppc-spe",
-	.cra_priority		=	300,
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct ppc_aes_ctx),
-	.cra_alignmask		=	0,
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize		=	AES_MIN_KEY_SIZE,
-			.max_keysize		=	AES_MAX_KEY_SIZE,
-			.ivsize			=	AES_BLOCK_SIZE,
-			.setkey			=	ppc_aes_setkey,
-			.encrypt		=	ppc_cbc_encrypt,
-			.decrypt		=	ppc_cbc_decrypt,
-		}
-	}
-}, {
-	.cra_name		=	"ctr(aes)",
-	.cra_driver_name	=	"ctr-ppc-spe",
-	.cra_priority		=	300,
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	1,
-	.cra_ctxsize		=	sizeof(struct ppc_aes_ctx),
-	.cra_alignmask		=	0,
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize		=	AES_MIN_KEY_SIZE,
-			.max_keysize		=	AES_MAX_KEY_SIZE,
-			.ivsize			=	AES_BLOCK_SIZE,
-			.setkey			=	ppc_aes_setkey,
-			.encrypt		=	ppc_ctr_crypt,
-			.decrypt		=	ppc_ctr_crypt,
-		}
-	}
-}, {
-	.cra_name		=	"xts(aes)",
-	.cra_driver_name	=	"xts-ppc-spe",
-	.cra_priority		=	300,
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct ppc_xts_ctx),
-	.cra_alignmask		=	0,
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize		=	AES_MIN_KEY_SIZE * 2,
-			.max_keysize		=	AES_MAX_KEY_SIZE * 2,
-			.ivsize			=	AES_BLOCK_SIZE,
-			.setkey			=	ppc_xts_setkey,
-			.encrypt		=	ppc_xts_encrypt,
-			.decrypt		=	ppc_xts_decrypt,
-		}
+};
+
+static struct skcipher_alg aes_skcipher_algs[] = {
+	{
+		.base.cra_name		=	"ecb(aes)",
+		.base.cra_driver_name	=	"ecb-ppc-spe",
+		.base.cra_priority	=	300,
+		.base.cra_blocksize	=	AES_BLOCK_SIZE,
+		.base.cra_ctxsize	=	sizeof(struct ppc_aes_ctx),
+		.base.cra_module	=	THIS_MODULE,
+		.min_keysize		=	AES_MIN_KEY_SIZE,
+		.max_keysize		=	AES_MAX_KEY_SIZE,
+		.setkey			=	ppc_aes_setkey_skcipher,
+		.encrypt		=	ppc_ecb_encrypt,
+		.decrypt		=	ppc_ecb_decrypt,
+	}, {
+		.base.cra_name		=	"cbc(aes)",
+		.base.cra_driver_name	=	"cbc-ppc-spe",
+		.base.cra_priority	=	300,
+		.base.cra_blocksize	=	AES_BLOCK_SIZE,
+		.base.cra_ctxsize	=	sizeof(struct ppc_aes_ctx),
+		.base.cra_module	=	THIS_MODULE,
+		.min_keysize		=	AES_MIN_KEY_SIZE,
+		.max_keysize		=	AES_MAX_KEY_SIZE,
+		.ivsize			=	AES_BLOCK_SIZE,
+		.setkey			=	ppc_aes_setkey_skcipher,
+		.encrypt		=	ppc_cbc_encrypt,
+		.decrypt		=	ppc_cbc_decrypt,
+	}, {
+		.base.cra_name		=	"ctr(aes)",
+		.base.cra_driver_name	=	"ctr-ppc-spe",
+		.base.cra_priority	=	300,
+		.base.cra_blocksize	=	1,
+		.base.cra_ctxsize	=	sizeof(struct ppc_aes_ctx),
+		.base.cra_module	=	THIS_MODULE,
+		.min_keysize		=	AES_MIN_KEY_SIZE,
+		.max_keysize		=	AES_MAX_KEY_SIZE,
+		.ivsize			=	AES_BLOCK_SIZE,
+		.setkey			=	ppc_aes_setkey_skcipher,
+		.encrypt		=	ppc_ctr_crypt,
+		.decrypt		=	ppc_ctr_crypt,
+		.chunksize		=	AES_BLOCK_SIZE,
+	}, {
+		.base.cra_name		=	"xts(aes)",
+		.base.cra_driver_name	=	"xts-ppc-spe",
+		.base.cra_priority	=	300,
+		.base.cra_blocksize	=	AES_BLOCK_SIZE,
+		.base.cra_ctxsize	=	sizeof(struct ppc_xts_ctx),
+		.base.cra_module	=	THIS_MODULE,
+		.min_keysize		=	AES_MIN_KEY_SIZE * 2,
+		.max_keysize		=	AES_MAX_KEY_SIZE * 2,
+		.ivsize			=	AES_BLOCK_SIZE,
+		.setkey			=	ppc_xts_setkey,
+		.encrypt		=	ppc_xts_encrypt,
+		.decrypt		=	ppc_xts_decrypt,
 	}
-} };
+};
 
 static int __init ppc_aes_mod_init(void)
 {
-	return crypto_register_algs(aes_algs, ARRAY_SIZE(aes_algs));
+	int err;
+
+	err = crypto_register_alg(&aes_cipher_alg);
+	if (err)
+		return err;
+
+	err = crypto_register_skciphers(aes_skcipher_algs,
+					ARRAY_SIZE(aes_skcipher_algs));
+	if (err)
+		crypto_unregister_alg(&aes_cipher_alg);
+	return err;
 }
 
 static void __exit ppc_aes_mod_fini(void)
 {
-	crypto_unregister_algs(aes_algs, ARRAY_SIZE(aes_algs));
+	crypto_unregister_alg(&aes_cipher_alg);
+	crypto_unregister_skciphers(aes_skcipher_algs,
+				    ARRAY_SIZE(aes_skcipher_algs));
 }
 
 module_init(ppc_aes_mod_init);
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 6fe6ad64cba5..4273e799203d 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -401,7 +401,6 @@ struct kvmppc_mmu {
 	u32  (*mfsrin)(struct kvm_vcpu *vcpu, u32 srnum);
 	int  (*xlate)(struct kvm_vcpu *vcpu, gva_t eaddr,
 		      struct kvmppc_pte *pte, bool data, bool iswrite);
-	void (*reset_msr)(struct kvm_vcpu *vcpu);
 	void (*tlbie)(struct kvm_vcpu *vcpu, ulong addr, bool large);
 	int  (*esid_to_vsid)(struct kvm_vcpu *vcpu, ulong esid, u64 *vsid);
 	u64  (*ea_to_vp)(struct kvm_vcpu *vcpu, gva_t eaddr, bool data);
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index ee62776e5433..d63f649fe713 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -271,6 +271,7 @@ struct kvmppc_ops {
 			   union kvmppc_one_reg *val);
 	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
+	void (*inject_interrupt)(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags);
 	void (*set_msr)(struct kvm_vcpu *vcpu, u64 msr);
 	int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
 	struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned int id);
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index c8bb14ff4713..f6c562acc3f8 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -329,13 +329,4 @@ struct vm_area_struct;
 #endif /* __ASSEMBLY__ */
 #include <asm/slice.h>
 
-/*
- * Allow 30-bit DMA for very limited Broadcom wifi chips on many powerbooks.
- */
-#ifdef CONFIG_PPC32
-#define ARCH_ZONE_DMA_BITS 30
-#else
-#define ARCH_ZONE_DMA_BITS 31
-#endif
-
 #endif /* _ASM_POWERPC_PAGE_H */
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index b3cbb1136bce..75c7e95a321b 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -748,6 +748,18 @@
 #define SPRN_USPRG7	0x107	/* SPRG7 userspace read */
 #define SPRN_SRR0	0x01A	/* Save/Restore Register 0 */
 #define SPRN_SRR1	0x01B	/* Save/Restore Register 1 */
+
+#ifdef CONFIG_PPC_BOOK3S
+/*
+ * Bits loaded from MSR upon interrupt.
+ * PPC (64-bit) bits 33-36,42-47 are interrupt dependent, the others are
+ * loaded from MSR. The exception is that SRESET and MCE do not always load
+ * bit 62 (RI) from MSR. Don't use PPC_BITMASK for this because 32-bit uses
+ * it.
+ */
+#define   SRR1_MSR_BITS		(~0x783f0000UL)
+#endif
+
 #define   SRR1_ISI_NOPT		0x40000000 /* ISI: Not found in hash */
 #define   SRR1_ISI_N_OR_G	0x10000000 /* ISI: Access is no-exec or G */
 #define   SRR1_ISI_PROT		0x08000000 /* ISI: Other protection fault */
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index b0f72dea8b11..264e266a85bf 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -667,6 +667,8 @@ struct kvm_ppc_cpu_char {
 
 /* PPC64 eXternal Interrupt Controller Specification */
 #define KVM_DEV_XICS_GRP_SOURCES	1	/* 64-bit source attributes */
+#define KVM_DEV_XICS_GRP_CTRL		2
+#define   KVM_DEV_XICS_NR_SERVERS	1
 
 /* Layout of 64-bit source attribute values */
 #define  KVM_XICS_DESTINATION_SHIFT	0
@@ -683,6 +685,7 @@ struct kvm_ppc_cpu_char {
 #define KVM_DEV_XIVE_GRP_CTRL		1
 #define   KVM_DEV_XIVE_RESET		1
 #define   KVM_DEV_XIVE_EQ_SYNC		2
+#define   KVM_DEV_XIVE_NR_SERVERS	3
 #define KVM_DEV_XIVE_GRP_SOURCE		2	/* 64-bit source identifier */
 #define KVM_DEV_XIVE_GRP_SOURCE_CONFIG	3	/* 64-bit source identifier */
 #define KVM_DEV_XIVE_GRP_EQ_CONFIG	4	/* 64-bit EQ identifier */
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index ec2547cc5ecb..58a59ee998e2 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -74,27 +74,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ NULL }
 };
 
-void kvmppc_unfixup_split_real(struct kvm_vcpu *vcpu)
-{
-	if (vcpu->arch.hflags & BOOK3S_HFLAG_SPLIT_HACK) {
-		ulong pc = kvmppc_get_pc(vcpu);
-		ulong lr = kvmppc_get_lr(vcpu);
-		if ((pc & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS)
-			kvmppc_set_pc(vcpu, pc & ~SPLIT_HACK_MASK);
-		if ((lr & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS)
-			kvmppc_set_lr(vcpu, lr & ~SPLIT_HACK_MASK);
-		vcpu->arch.hflags &= ~BOOK3S_HFLAG_SPLIT_HACK;
-	}
-}
-EXPORT_SYMBOL_GPL(kvmppc_unfixup_split_real);
-
-static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
-{
-	if (!is_kvmppc_hv_enabled(vcpu->kvm))
-		return to_book3s(vcpu)->hior;
-	return 0;
-}
-
 static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
 			unsigned long pending_now, unsigned long old_pending)
 {
@@ -134,11 +113,7 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
 
 void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
 {
-	kvmppc_unfixup_split_real(vcpu);
-	kvmppc_set_srr0(vcpu, kvmppc_get_pc(vcpu));
-	kvmppc_set_srr1(vcpu, (kvmppc_get_msr(vcpu) & ~0x783f0000ul) | flags);
-	kvmppc_set_pc(vcpu, kvmppc_interrupt_offset(vcpu) + vec);
-	vcpu->arch.mmu.reset_msr(vcpu);
+	vcpu->kvm->arch.kvm_ops->inject_interrupt(vcpu, vec, flags);
 }
 
 static int kvmppc_book3s_vec2irqprio(unsigned int vec)
diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h
index 2ef1311a2a13..3a4613985949 100644
--- a/arch/powerpc/kvm/book3s.h
+++ b/arch/powerpc/kvm/book3s.h
@@ -32,4 +32,7 @@ extern void kvmppc_emulate_tabort(struct kvm_vcpu *vcpu, int ra_val);
 static inline void kvmppc_emulate_tabort(struct kvm_vcpu *vcpu, int ra_val) {}
 #endif
 
+extern void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr);
+extern void kvmppc_inject_interrupt_hv(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags);
+
 #endif
diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index 18f244aad7aa..f21e73492ce3 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -90,11 +90,6 @@ static u64 kvmppc_mmu_book3s_32_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
 	return (((u64)eaddr >> 12) & 0xffff) | (vsid << 16);
 }
 
-static void kvmppc_mmu_book3s_32_reset_msr(struct kvm_vcpu *vcpu)
-{
-	kvmppc_set_msr(vcpu, 0);
-}
-
 static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvm_vcpu *vcpu,
 				      u32 sre, gva_t eaddr,
 				      bool primary)
@@ -406,7 +401,6 @@ void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu)
 	mmu->mtsrin = kvmppc_mmu_book3s_32_mtsrin;
 	mmu->mfsrin = kvmppc_mmu_book3s_32_mfsrin;
 	mmu->xlate = kvmppc_mmu_book3s_32_xlate;
-	mmu->reset_msr = kvmppc_mmu_book3s_32_reset_msr;
 	mmu->tlbie = kvmppc_mmu_book3s_32_tlbie;
 	mmu->esid_to_vsid = kvmppc_mmu_book3s_32_esid_to_vsid;
 	mmu->ea_to_vp = kvmppc_mmu_book3s_32_ea_to_vp;
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 5f63a5f7f24f..599133256a95 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -24,20 +24,6 @@
 #define dprintk(X...) do { } while(0)
 #endif
 
-static void kvmppc_mmu_book3s_64_reset_msr(struct kvm_vcpu *vcpu)
-{
-	unsigned long msr = vcpu->arch.intr_msr;
-	unsigned long cur_msr = kvmppc_get_msr(vcpu);
-
-	/* If transactional, change to suspend mode on IRQ delivery */
-	if (MSR_TM_TRANSACTIONAL(cur_msr))
-		msr |= MSR_TS_S;
-	else
-		msr |= cur_msr & MSR_TS_MASK;
-
-	kvmppc_set_msr(vcpu, msr);
-}
-
 static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe(
 				struct kvm_vcpu *vcpu,
 				gva_t eaddr)
@@ -676,7 +662,6 @@ void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu)
 	mmu->slbie = kvmppc_mmu_book3s_64_slbie;
 	mmu->slbia = kvmppc_mmu_book3s_64_slbia;
 	mmu->xlate = kvmppc_mmu_book3s_64_xlate;
-	mmu->reset_msr = kvmppc_mmu_book3s_64_reset_msr;
 	mmu->tlbie = kvmppc_mmu_book3s_64_tlbie;
 	mmu->esid_to_vsid = kvmppc_mmu_book3s_64_esid_to_vsid;
 	mmu->ea_to_vp = kvmppc_mmu_book3s_64_ea_to_vp;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 9a75f0e1933b..d381526c5c9b 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -275,18 +275,6 @@ int kvmppc_mmu_hv_init(void)
 	return 0;
 }
 
-static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
-{
-	unsigned long msr = vcpu->arch.intr_msr;
-
-	/* If transactional, change to suspend mode on IRQ delivery */
-	if (MSR_TM_TRANSACTIONAL(vcpu->arch.shregs.msr))
-		msr |= MSR_TS_S;
-	else
-		msr |= vcpu->arch.shregs.msr & MSR_TS_MASK;
-	kvmppc_set_msr(vcpu, msr);
-}
-
 static long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags,
 				long pte_index, unsigned long pteh,
 				unsigned long ptel, unsigned long *pte_idx_ret)
@@ -508,6 +496,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	struct vm_area_struct *vma;
 	unsigned long rcbits;
 	long mmio_update;
+	struct mm_struct *mm;
 
 	if (kvm_is_radix(kvm))
 		return kvmppc_book3s_radix_page_fault(run, vcpu, ea, dsisr);
@@ -584,6 +573,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	is_ci = false;
 	pfn = 0;
 	page = NULL;
+	mm = current->mm;
 	pte_size = PAGE_SIZE;
 	writing = (dsisr & DSISR_ISSTORE) != 0;
 	/* If writing != 0, then the HPTE must allow writing, if we get here */
@@ -592,8 +582,8 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	npages = get_user_pages_fast(hva, 1, writing ? FOLL_WRITE : 0, pages);
 	if (npages < 1) {
 		/* Check if it's an I/O mapping */
-		down_read(&current->mm->mmap_sem);
-		vma = find_vma(current->mm, hva);
+		down_read(&mm->mmap_sem);
+		vma = find_vma(mm, hva);
 		if (vma && vma->vm_start <= hva && hva + psize <= vma->vm_end &&
 		    (vma->vm_flags & VM_PFNMAP)) {
 			pfn = vma->vm_pgoff +
@@ -602,7 +592,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			is_ci = pte_ci(__pte((pgprot_val(vma->vm_page_prot))));
 			write_ok = vma->vm_flags & VM_WRITE;
 		}
-		up_read(&current->mm->mmap_sem);
+		up_read(&mm->mmap_sem);
 		if (!pfn)
 			goto out_put;
 	} else {
@@ -621,8 +611,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			 * hugepage split and collapse.
 			 */
 			local_irq_save(flags);
-			ptep = find_current_mm_pte(current->mm->pgd,
-						   hva, NULL, NULL);
+			ptep = find_current_mm_pte(mm->pgd, hva, NULL, NULL);
 			if (ptep) {
 				pte = kvmppc_read_update_linux_pte(ptep, 1);
 				if (__pte_write(pte))
@@ -2000,7 +1989,7 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf)
 	ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag | O_CLOEXEC);
 	if (ret < 0) {
 		kfree(ctx);
-		kvm_put_kvm(kvm);
+		kvm_put_kvm_no_destroy(kvm);
 		return ret;
 	}
 
@@ -2161,7 +2150,6 @@ void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.slb_nr = 32;		/* POWER7/POWER8 */
 
 	mmu->xlate = kvmppc_mmu_book3s_64_hv_xlate;
-	mmu->reset_msr = kvmppc_mmu_book3s_64_hv_reset_msr;
 
 	vcpu->arch.hflags |= BOOK3S_HFLAG_SLB;
 }
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 5834db0a54c6..883a66e76638 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -317,7 +317,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	if (ret >= 0)
 		list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
 	else
-		kvm_put_kvm(kvm);
+		kvm_put_kvm_no_destroy(kvm);
 
 	mutex_unlock(&kvm->lock);
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 709cf1fd4cf4..ec5c0379296a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -133,7 +133,6 @@ static inline bool nesting_enabled(struct kvm *kvm)
 /* If set, the threads on each CPU core have to be in the same MMU mode */
 static bool no_mixing_hpt_and_radix;
 
-static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
 /*
@@ -338,18 +337,6 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu)
 	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
 }
 
-static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
-{
-	/*
-	 * Check for illegal transactional state bit combination
-	 * and if we find it, force the TS field to a safe state.
-	 */
-	if ((msr & MSR_TS_MASK) == MSR_TS_MASK)
-		msr &= ~MSR_TS_MASK;
-	vcpu->arch.shregs.msr = msr;
-	kvmppc_end_cede(vcpu);
-}
-
 static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
 {
 	vcpu->arch.pvr = pvr;
@@ -792,6 +779,11 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
 		vcpu->arch.dawr  = value1;
 		vcpu->arch.dawrx = value2;
 		return H_SUCCESS;
+	case H_SET_MODE_RESOURCE_ADDR_TRANS_MODE:
+		/* KVM does not support mflags=2 (AIL=2) */
+		if (mflags != 0 && mflags != 3)
+			return H_UNSUPPORTED_FLAG_START;
+		return H_TOO_HARD;
 	default:
 		return H_TOO_HARD;
 	}
@@ -2454,15 +2446,6 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu)
 	vcpu->arch.timer_running = 1;
 }
 
-static void kvmppc_end_cede(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.ceded = 0;
-	if (vcpu->arch.timer_running) {
-		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
-		vcpu->arch.timer_running = 0;
-	}
-}
-
 extern int __kvmppc_vcore_entry(void);
 
 static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
@@ -5401,6 +5384,7 @@ static struct kvmppc_ops kvm_ops_hv = {
 	.set_one_reg = kvmppc_set_one_reg_hv,
 	.vcpu_load   = kvmppc_core_vcpu_load_hv,
 	.vcpu_put    = kvmppc_core_vcpu_put_hv,
+	.inject_interrupt = kvmppc_inject_interrupt_hv,
 	.set_msr     = kvmppc_set_msr_hv,
 	.vcpu_run    = kvmppc_vcpu_run_hv,
 	.vcpu_create = kvmppc_core_vcpu_create_hv,
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 7c1909657b55..7cd3cf3d366b 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -755,6 +755,71 @@ void kvmhv_p9_restore_lpcr(struct kvm_split_mode *sip)
 	local_paca->kvm_hstate.kvm_split_mode = NULL;
 }
 
+static void kvmppc_end_cede(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.ceded = 0;
+	if (vcpu->arch.timer_running) {
+		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
+		vcpu->arch.timer_running = 0;
+	}
+}
+
+void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
+{
+	/*
+	 * Check for illegal transactional state bit combination
+	 * and if we find it, force the TS field to a safe state.
+	 */
+	if ((msr & MSR_TS_MASK) == MSR_TS_MASK)
+		msr &= ~MSR_TS_MASK;
+	vcpu->arch.shregs.msr = msr;
+	kvmppc_end_cede(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvmppc_set_msr_hv);
+
+static void inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags)
+{
+	unsigned long msr, pc, new_msr, new_pc;
+
+	msr = kvmppc_get_msr(vcpu);
+	pc = kvmppc_get_pc(vcpu);
+	new_msr = vcpu->arch.intr_msr;
+	new_pc = vec;
+
+	/* If transactional, change to suspend mode on IRQ delivery */
+	if (MSR_TM_TRANSACTIONAL(msr))
+		new_msr |= MSR_TS_S;
+	else
+		new_msr |= msr & MSR_TS_MASK;
+
+	/*
+	 * Perform MSR and PC adjustment for LPCR[AIL]=3 if it is set and
+	 * applicable. AIL=2 is not supported.
+	 *
+	 * AIL does not apply to SRESET, MCE, or HMI (which is never
+	 * delivered to the guest), and does not apply if IR=0 or DR=0.
+	 */
+	if (vec != BOOK3S_INTERRUPT_SYSTEM_RESET &&
+	    vec != BOOK3S_INTERRUPT_MACHINE_CHECK &&
+	    (vcpu->arch.vcore->lpcr & LPCR_AIL) == LPCR_AIL_3 &&
+	    (msr & (MSR_IR|MSR_DR)) == (MSR_IR|MSR_DR) ) {
+		new_msr |= MSR_IR | MSR_DR;
+		new_pc += 0xC000000000004000ULL;
+	}
+
+	kvmppc_set_srr0(vcpu, pc);
+	kvmppc_set_srr1(vcpu, (msr & SRR1_MSR_BITS) | srr1_flags);
+	kvmppc_set_pc(vcpu, new_pc);
+	vcpu->arch.shregs.msr = new_msr;
+}
+
+void kvmppc_inject_interrupt_hv(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags)
+{
+	inject_interrupt(vcpu, vec, srr1_flags);
+	kvmppc_end_cede(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvmppc_inject_interrupt_hv);
+
 /*
  * Is there a PRIV_DOORBELL pending for the guest (on POWER9)?
  * Can we inject a Decrementer or a External interrupt?
@@ -762,7 +827,6 @@ void kvmhv_p9_restore_lpcr(struct kvm_split_mode *sip)
 void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu)
 {
 	int ext;
-	unsigned long vec = 0;
 	unsigned long lpcr;
 
 	/* Insert EXTERNAL bit into LPCR at the MER bit position */
@@ -774,26 +838,16 @@ void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu)
 
 	if (vcpu->arch.shregs.msr & MSR_EE) {
 		if (ext) {
-			vec = BOOK3S_INTERRUPT_EXTERNAL;
+			inject_interrupt(vcpu, BOOK3S_INTERRUPT_EXTERNAL, 0);
 		} else {
 			long int dec = mfspr(SPRN_DEC);
 			if (!(lpcr & LPCR_LD))
 				dec = (int) dec;
 			if (dec < 0)
-				vec = BOOK3S_INTERRUPT_DECREMENTER;
+				inject_interrupt(vcpu,
+					BOOK3S_INTERRUPT_DECREMENTER, 0);
 		}
 	}
-	if (vec) {
-		unsigned long msr, old_msr = vcpu->arch.shregs.msr;
-
-		kvmppc_set_srr0(vcpu, kvmppc_get_pc(vcpu));
-		kvmppc_set_srr1(vcpu, old_msr);
-		kvmppc_set_pc(vcpu, vec);
-		msr = vcpu->arch.intr_msr;
-		if (MSR_TM_ACTIVE(old_msr))
-			msr |= MSR_TS_S;
-		vcpu->arch.shregs.msr = msr;
-	}
 
 	if (vcpu->arch.doorbell_request) {
 		mtspr(SPRN_DPDES, 1);
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index cdf30c6eaf54..dc97e5be76f6 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -1186,7 +1186,7 @@ static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu,
 forward_to_l1:
 	vcpu->arch.fault_dsisr = flags;
 	if (vcpu->arch.trap == BOOK3S_INTERRUPT_H_INST_STORAGE) {
-		vcpu->arch.shregs.msr &= ~0x783f0000ul;
+		vcpu->arch.shregs.msr &= SRR1_MSR_BITS;
 		vcpu->arch.shregs.msr |= flags;
 	}
 	return RESUME_HOST;
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index cc65af8fe6f7..ce4fcf76e53e 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -90,7 +90,43 @@ static void kvmppc_fixup_split_real(struct kvm_vcpu *vcpu)
 	kvmppc_set_pc(vcpu, pc | SPLIT_HACK_OFFS);
 }
 
-void kvmppc_unfixup_split_real(struct kvm_vcpu *vcpu);
+static void kvmppc_unfixup_split_real(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.hflags & BOOK3S_HFLAG_SPLIT_HACK) {
+		ulong pc = kvmppc_get_pc(vcpu);
+		ulong lr = kvmppc_get_lr(vcpu);
+		if ((pc & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS)
+			kvmppc_set_pc(vcpu, pc & ~SPLIT_HACK_MASK);
+		if ((lr & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS)
+			kvmppc_set_lr(vcpu, lr & ~SPLIT_HACK_MASK);
+		vcpu->arch.hflags &= ~BOOK3S_HFLAG_SPLIT_HACK;
+	}
+}
+
+static void kvmppc_inject_interrupt_pr(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags)
+{
+	unsigned long msr, pc, new_msr, new_pc;
+
+	kvmppc_unfixup_split_real(vcpu);
+
+	msr = kvmppc_get_msr(vcpu);
+	pc = kvmppc_get_pc(vcpu);
+	new_msr = vcpu->arch.intr_msr;
+	new_pc = to_book3s(vcpu)->hior + vec;
+
+#ifdef CONFIG_PPC_BOOK3S_64
+	/* If transactional, change to suspend mode on IRQ delivery */
+	if (MSR_TM_TRANSACTIONAL(msr))
+		new_msr |= MSR_TS_S;
+	else
+		new_msr |= msr & MSR_TS_MASK;
+#endif
+
+	kvmppc_set_srr0(vcpu, pc);
+	kvmppc_set_srr1(vcpu, (msr & SRR1_MSR_BITS) | srr1_flags);
+	kvmppc_set_pc(vcpu, new_pc);
+	kvmppc_set_msr(vcpu, new_msr);
+}
 
 static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu)
 {
@@ -1761,6 +1797,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
 #else
 	/* default to book3s_32 (750) */
 	vcpu->arch.pvr = 0x84202;
+	vcpu->arch.intr_msr = 0;
 #endif
 	kvmppc_set_pvr_pr(vcpu, vcpu->arch.pvr);
 	vcpu->arch.slb_nr = 64;
@@ -2058,6 +2095,7 @@ static struct kvmppc_ops kvm_ops_pr = {
 	.set_one_reg = kvmppc_set_one_reg_pr,
 	.vcpu_load   = kvmppc_core_vcpu_load_pr,
 	.vcpu_put    = kvmppc_core_vcpu_put_pr,
+	.inject_interrupt = kvmppc_inject_interrupt_pr,
 	.set_msr     = kvmppc_set_msr_pr,
 	.vcpu_run    = kvmppc_vcpu_run_pr,
 	.vcpu_create = kvmppc_core_vcpu_create_pr,
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index a3f9c665bb5b..66858b7d3c6b 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -1211,6 +1211,45 @@ void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu)
 	vcpu->arch.xive_vcpu = NULL;
 }
 
+static bool kvmppc_xive_vcpu_id_valid(struct kvmppc_xive *xive, u32 cpu)
+{
+	/* We have a block of xive->nr_servers VPs. We just need to check
+	 * raw vCPU ids are below the expected limit for this guest's
+	 * core stride ; kvmppc_pack_vcpu_id() will pack them down to an
+	 * index that can be safely used to compute a VP id that belongs
+	 * to the VP block.
+	 */
+	return cpu < xive->nr_servers * xive->kvm->arch.emul_smt_mode;
+}
+
+int kvmppc_xive_compute_vp_id(struct kvmppc_xive *xive, u32 cpu, u32 *vp)
+{
+	u32 vp_id;
+
+	if (!kvmppc_xive_vcpu_id_valid(xive, cpu)) {
+		pr_devel("Out of bounds !\n");
+		return -EINVAL;
+	}
+
+	if (xive->vp_base == XIVE_INVALID_VP) {
+		xive->vp_base = xive_native_alloc_vp_block(xive->nr_servers);
+		pr_devel("VP_Base=%x nr_servers=%d\n", xive->vp_base, xive->nr_servers);
+
+		if (xive->vp_base == XIVE_INVALID_VP)
+			return -ENOSPC;
+	}
+
+	vp_id = kvmppc_xive_vp(xive, cpu);
+	if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) {
+		pr_devel("Duplicate !\n");
+		return -EEXIST;
+	}
+
+	*vp = vp_id;
+
+	return 0;
+}
+
 int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 			     struct kvm_vcpu *vcpu, u32 cpu)
 {
@@ -1229,20 +1268,13 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 		return -EPERM;
 	if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
 		return -EBUSY;
-	if (cpu >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) {
-		pr_devel("Out of bounds !\n");
-		return -EINVAL;
-	}
 
 	/* We need to synchronize with queue provisioning */
 	mutex_lock(&xive->lock);
 
-	vp_id = kvmppc_xive_vp(xive, cpu);
-	if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) {
-		pr_devel("Duplicate !\n");
-		r = -EEXIST;
+	r = kvmppc_xive_compute_vp_id(xive, cpu, &vp_id);
+	if (r)
 		goto bail;
-	}
 
 	xc = kzalloc(sizeof(*xc), GFP_KERNEL);
 	if (!xc) {
@@ -1834,6 +1866,43 @@ int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
 	return 0;
 }
 
+int kvmppc_xive_set_nr_servers(struct kvmppc_xive *xive, u64 addr)
+{
+	u32 __user *ubufp = (u32 __user *) addr;
+	u32 nr_servers;
+	int rc = 0;
+
+	if (get_user(nr_servers, ubufp))
+		return -EFAULT;
+
+	pr_devel("%s nr_servers=%u\n", __func__, nr_servers);
+
+	if (!nr_servers || nr_servers > KVM_MAX_VCPU_ID)
+		return -EINVAL;
+
+	mutex_lock(&xive->lock);
+	if (xive->vp_base != XIVE_INVALID_VP)
+		/* The VP block is allocated once and freed when the device
+		 * is released. Better not allow to change its size since its
+		 * used by connect_vcpu to validate vCPU ids are valid (eg,
+		 * setting it back to a higher value could allow connect_vcpu
+		 * to come up with a VP id that goes beyond the VP block, which
+		 * is likely to cause a crash in OPAL).
+		 */
+		rc = -EBUSY;
+	else if (nr_servers > KVM_MAX_VCPUS)
+		/* We don't need more servers. Higher vCPU ids get packed
+		 * down below KVM_MAX_VCPUS by kvmppc_pack_vcpu_id().
+		 */
+		xive->nr_servers = KVM_MAX_VCPUS;
+	else
+		xive->nr_servers = nr_servers;
+
+	mutex_unlock(&xive->lock);
+
+	return rc;
+}
+
 static int xive_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 {
 	struct kvmppc_xive *xive = dev->private;
@@ -1842,6 +1911,11 @@ static int xive_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 	switch (attr->group) {
 	case KVM_DEV_XICS_GRP_SOURCES:
 		return xive_set_source(xive, attr->attr, attr->addr);
+	case KVM_DEV_XICS_GRP_CTRL:
+		switch (attr->attr) {
+		case KVM_DEV_XICS_NR_SERVERS:
+			return kvmppc_xive_set_nr_servers(xive, attr->addr);
+		}
 	}
 	return -ENXIO;
 }
@@ -1867,6 +1941,11 @@ static int xive_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 		    attr->attr < KVMPPC_XICS_NR_IRQS)
 			return 0;
 		break;
+	case KVM_DEV_XICS_GRP_CTRL:
+		switch (attr->attr) {
+		case KVM_DEV_XICS_NR_SERVERS:
+			return 0;
+		}
 	}
 	return -ENXIO;
 }
@@ -2001,10 +2080,13 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 {
 	struct kvmppc_xive *xive;
 	struct kvm *kvm = dev->kvm;
-	int ret = 0;
 
 	pr_devel("Creating xive for partition\n");
 
+	/* Already there ? */
+	if (kvm->arch.xive)
+		return -EEXIST;
+
 	xive = kvmppc_xive_get_device(kvm, type);
 	if (!xive)
 		return -ENOMEM;
@@ -2014,12 +2096,6 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 	xive->kvm = kvm;
 	mutex_init(&xive->lock);
 
-	/* Already there ? */
-	if (kvm->arch.xive)
-		ret = -EEXIST;
-	else
-		kvm->arch.xive = xive;
-
 	/* We use the default queue size set by the host */
 	xive->q_order = xive_native_default_eq_shift();
 	if (xive->q_order < PAGE_SHIFT)
@@ -2027,18 +2103,16 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 	else
 		xive->q_page_order = xive->q_order - PAGE_SHIFT;
 
-	/* Allocate a bunch of VPs */
-	xive->vp_base = xive_native_alloc_vp_block(KVM_MAX_VCPUS);
-	pr_devel("VP_Base=%x\n", xive->vp_base);
-
-	if (xive->vp_base == XIVE_INVALID_VP)
-		ret = -ENOMEM;
+	/* VP allocation is delayed to the first call to connect_vcpu */
+	xive->vp_base = XIVE_INVALID_VP;
+	/* KVM_MAX_VCPUS limits the number of VMs to roughly 64 per sockets
+	 * on a POWER9 system.
+	 */
+	xive->nr_servers = KVM_MAX_VCPUS;
 
 	xive->single_escalation = xive_native_has_single_escalation();
 
-	if (ret)
-		return ret;
-
+	kvm->arch.xive = xive;
 	return 0;
 }
 
@@ -2108,9 +2182,9 @@ static int xive_debug_show(struct seq_file *m, void *private)
 		if (!xc)
 			continue;
 
-		seq_printf(m, "cpu server %#x CPPR:%#x HWCPPR:%#x"
+		seq_printf(m, "cpu server %#x VP:%#x CPPR:%#x HWCPPR:%#x"
 			   " MFRR:%#x PEND:%#x h_xirr: R=%lld V=%lld\n",
-			   xc->server_num, xc->cppr, xc->hw_cppr,
+			   xc->server_num, xc->vp_id, xc->cppr, xc->hw_cppr,
 			   xc->mfrr, xc->pending,
 			   xc->stat_rm_h_xirr, xc->stat_vm_h_xirr);
 
diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
index fe3ed50e0818..382e3a56e789 100644
--- a/arch/powerpc/kvm/book3s_xive.h
+++ b/arch/powerpc/kvm/book3s_xive.h
@@ -135,6 +135,9 @@ struct kvmppc_xive {
 	/* Flags */
 	u8	single_escalation;
 
+	/* Number of entries in the VP block */
+	u32	nr_servers;
+
 	struct kvmppc_xive_ops *ops;
 	struct address_space   *mapping;
 	struct mutex mapping_lock;
@@ -296,6 +299,8 @@ int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio,
 struct kvmppc_xive *kvmppc_xive_get_device(struct kvm *kvm, u32 type);
 void xive_cleanup_single_escalation(struct kvm_vcpu *vcpu,
 				    struct kvmppc_xive_vcpu *xc, int irq);
+int kvmppc_xive_compute_vp_id(struct kvmppc_xive *xive, u32 cpu, u32 *vp);
+int kvmppc_xive_set_nr_servers(struct kvmppc_xive *xive, u64 addr);
 
 #endif /* CONFIG_KVM_XICS */
 #endif /* _KVM_PPC_BOOK3S_XICS_H */
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
index 78b906ffa0d2..d83adb1e1490 100644
--- a/arch/powerpc/kvm/book3s_xive_native.c
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -50,6 +50,24 @@ static void kvmppc_xive_native_cleanup_queue(struct kvm_vcpu *vcpu, int prio)
 	}
 }
 
+static int kvmppc_xive_native_configure_queue(u32 vp_id, struct xive_q *q,
+					      u8 prio, __be32 *qpage,
+					      u32 order, bool can_escalate)
+{
+	int rc;
+	__be32 *qpage_prev = q->qpage;
+
+	rc = xive_native_configure_queue(vp_id, q, prio, qpage, order,
+					 can_escalate);
+	if (rc)
+		return rc;
+
+	if (qpage_prev)
+		put_page(virt_to_page(qpage_prev));
+
+	return rc;
+}
+
 void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
@@ -118,19 +136,12 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
 		return -EPERM;
 	if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
 		return -EBUSY;
-	if (server_num >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) {
-		pr_devel("Out of bounds !\n");
-		return -EINVAL;
-	}
 
 	mutex_lock(&xive->lock);
 
-	vp_id = kvmppc_xive_vp(xive, server_num);
-	if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) {
-		pr_devel("Duplicate !\n");
-		rc = -EEXIST;
+	rc = kvmppc_xive_compute_vp_id(xive, server_num, &vp_id);
+	if (rc)
 		goto bail;
-	}
 
 	xc = kzalloc(sizeof(*xc), GFP_KERNEL);
 	if (!xc) {
@@ -582,19 +593,14 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 		q->guest_qaddr  = 0;
 		q->guest_qshift = 0;
 
-		rc = xive_native_configure_queue(xc->vp_id, q, priority,
-						 NULL, 0, true);
+		rc = kvmppc_xive_native_configure_queue(xc->vp_id, q, priority,
+							NULL, 0, true);
 		if (rc) {
 			pr_err("Failed to reset queue %d for VCPU %d: %d\n",
 			       priority, xc->server_num, rc);
 			return rc;
 		}
 
-		if (q->qpage) {
-			put_page(virt_to_page(q->qpage));
-			q->qpage = NULL;
-		}
-
 		return 0;
 	}
 
@@ -624,12 +630,6 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 	gfn = gpa_to_gfn(kvm_eq.qaddr);
-	page = gfn_to_page(kvm, gfn);
-	if (is_error_page(page)) {
-		srcu_read_unlock(&kvm->srcu, srcu_idx);
-		pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr);
-		return -EINVAL;
-	}
 
 	page_size = kvm_host_page_size(kvm, gfn);
 	if (1ull << kvm_eq.qshift > page_size) {
@@ -638,6 +638,13 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 		return -EINVAL;
 	}
 
+	page = gfn_to_page(kvm, gfn);
+	if (is_error_page(page)) {
+		srcu_read_unlock(&kvm->srcu, srcu_idx);
+		pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr);
+		return -EINVAL;
+	}
+
 	qaddr = page_to_virt(page) + (kvm_eq.qaddr & ~PAGE_MASK);
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 
@@ -653,8 +660,8 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 	  * OPAL level because the use of END ESBs is not supported by
 	  * Linux.
 	  */
-	rc = xive_native_configure_queue(xc->vp_id, q, priority,
-					 (__be32 *) qaddr, kvm_eq.qshift, true);
+	rc = kvmppc_xive_native_configure_queue(xc->vp_id, q, priority,
+					(__be32 *) qaddr, kvm_eq.qshift, true);
 	if (rc) {
 		pr_err("Failed to configure queue %d for VCPU %d: %d\n",
 		       priority, xc->server_num, rc);
@@ -928,6 +935,8 @@ static int kvmppc_xive_native_set_attr(struct kvm_device *dev,
 			return kvmppc_xive_reset(xive);
 		case KVM_DEV_XIVE_EQ_SYNC:
 			return kvmppc_xive_native_eq_sync(xive);
+		case KVM_DEV_XIVE_NR_SERVERS:
+			return kvmppc_xive_set_nr_servers(xive, attr->addr);
 		}
 		break;
 	case KVM_DEV_XIVE_GRP_SOURCE:
@@ -967,6 +976,7 @@ static int kvmppc_xive_native_has_attr(struct kvm_device *dev,
 		switch (attr->attr) {
 		case KVM_DEV_XIVE_RESET:
 		case KVM_DEV_XIVE_EQ_SYNC:
+		case KVM_DEV_XIVE_NR_SERVERS:
 			return 0;
 		}
 		break;
@@ -1067,7 +1077,6 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type)
 {
 	struct kvmppc_xive *xive;
 	struct kvm *kvm = dev->kvm;
-	int ret = 0;
 
 	pr_devel("Creating xive native device\n");
 
@@ -1081,27 +1090,20 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type)
 	dev->private = xive;
 	xive->dev = dev;
 	xive->kvm = kvm;
-	kvm->arch.xive = xive;
 	mutex_init(&xive->mapping_lock);
 	mutex_init(&xive->lock);
 
-	/*
-	 * Allocate a bunch of VPs. KVM_MAX_VCPUS is a large value for
-	 * a default. Getting the max number of CPUs the VM was
-	 * configured with would improve our usage of the XIVE VP space.
+	/* VP allocation is delayed to the first call to connect_vcpu */
+	xive->vp_base = XIVE_INVALID_VP;
+	/* KVM_MAX_VCPUS limits the number of VMs to roughly 64 per sockets
+	 * on a POWER9 system.
 	 */
-	xive->vp_base = xive_native_alloc_vp_block(KVM_MAX_VCPUS);
-	pr_devel("VP_Base=%x\n", xive->vp_base);
-
-	if (xive->vp_base == XIVE_INVALID_VP)
-		ret = -ENXIO;
+	xive->nr_servers = KVM_MAX_VCPUS;
 
 	xive->single_escalation = xive_native_has_single_escalation();
 	xive->ops = &kvmppc_xive_native_ops;
 
-	if (ret)
-		return ret;
-
+	kvm->arch.xive = xive;
 	return 0;
 }
 
@@ -1204,8 +1206,8 @@ static int xive_native_debug_show(struct seq_file *m, void *private)
 		if (!xc)
 			continue;
 
-		seq_printf(m, "cpu server %#x NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x\n",
-			   xc->server_num,
+		seq_printf(m, "cpu server %#x VP=%#x NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x\n",
+			   xc->server_num, xc->vp_id,
 			   vcpu->arch.xive_saved_state.nsr,
 			   vcpu->arch.xive_saved_state.cppr,
 			   vcpu->arch.xive_saved_state.ipb,
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 321db0fdb9db..425d13806645 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -355,9 +355,9 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 
 	if (tlbsel == 1) {
 		struct vm_area_struct *vma;
-		down_read(&current->mm->mmap_sem);
+		down_read(&kvm->mm->mmap_sem);
 
-		vma = find_vma(current->mm, hva);
+		vma = find_vma(kvm->mm, hva);
 		if (vma && hva >= vma->vm_start &&
 		    (vma->vm_flags & VM_PFNMAP)) {
 			/*
@@ -441,7 +441,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
 		}
 
-		up_read(&current->mm->mmap_sem);
+		up_read(&kvm->mm->mmap_sem);
 	}
 
 	if (likely(!pfnmap)) {
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 3a77bb643452..9e085e931d74 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -522,6 +522,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_IMMEDIATE_EXIT:
 		r = 1;
 		break;
+	case KVM_CAP_PPC_GUEST_DEBUG_SSTEP:
+		/* fall through */
 	case KVM_CAP_PPC_PAIRED_SINGLES:
 	case KVM_CAP_PPC_OSI:
 	case KVM_CAP_PPC_GET_PVINFO:
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index be941d382c8d..c95b7fe9f298 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -31,6 +31,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/memremap.h>
+#include <linux/dma-direct.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -201,10 +202,10 @@ static int __init mark_nonram_nosave(void)
  * everything else. GFP_DMA32 page allocations automatically fall back to
  * ZONE_DMA.
  *
- * By using 31-bit unconditionally, we can exploit ARCH_ZONE_DMA_BITS to
- * inform the generic DMA mapping code.  32-bit only devices (if not handled
- * by an IOMMU anyway) will take a first dip into ZONE_NORMAL and get
- * otherwise served by ZONE_DMA.
+ * By using 31-bit unconditionally, we can exploit zone_dma_bits to inform the
+ * generic DMA mapping code.  32-bit only devices (if not handled by an IOMMU
+ * anyway) will take a first dip into ZONE_NORMAL and get otherwise served by
+ * ZONE_DMA.
  */
 static unsigned long max_zone_pfns[MAX_NR_ZONES];
 
@@ -237,9 +238,18 @@ void __init paging_init(void)
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (long int)((top_of_ram - total_ram) >> 20));
 
+	/*
+	 * Allow 30-bit DMA for very limited Broadcom wifi chips on many
+	 * powerbooks.
+	 */
+	if (IS_ENABLED(CONFIG_PPC32))
+		zone_dma_bits = 30;
+	else
+		zone_dma_bits = 31;
+
 #ifdef CONFIG_ZONE_DMA
 	max_zone_pfns[ZONE_DMA]	= min(max_low_pfn,
-				      1UL << (ARCH_ZONE_DMA_BITS - PAGE_SHIFT));
+				      1UL << (zone_dma_bits - PAGE_SHIFT));
 #endif
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 #ifdef CONFIG_HIGHMEM
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 8eebbc8860bb..75a6c9117622 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -164,7 +164,7 @@ config ARCH_RV32I
 config ARCH_RV64I
 	bool "RV64I"
 	select 64BIT
-	select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000
+	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && GCC_VERSION >= 50000
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FTRACE_MCOUNT_RECORD
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 70bb94ae61c5..b7401858d872 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -315,8 +315,8 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 			/* Ignore unresolved weak symbol */
 			if (ELF_ST_BIND(sym->st_info) == STB_WEAK)
 				continue;
-			pr_warning("%s: Unknown symbol %s\n",
-				   me->name, strtab + sym->st_name);
+			pr_warn("%s: Unknown symbol %s\n",
+				me->name, strtab + sym->st_name);
 			return -ENOENT;
 		}
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 43a81d0ad507..f0df9e48e651 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -246,8 +246,8 @@ choice
 
 config MARCH_Z900
 	bool "IBM zSeries model z800 and z900"
-	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z900_FEATURES
+	depends on $(cc-option,-march=z900)
 	help
 	  Select this to enable optimizations for model z800/z900 (2064 and
 	  2066 series). This will enable some optimizations that are not
@@ -255,8 +255,8 @@ config MARCH_Z900
 
 config MARCH_Z990
 	bool "IBM zSeries model z890 and z990"
-	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z990_FEATURES
+	depends on $(cc-option,-march=z990)
 	help
 	  Select this to enable optimizations for model z890/z990 (2084 and
 	  2086 series). The kernel will be slightly faster but will not work
@@ -264,8 +264,8 @@ config MARCH_Z990
 
 config MARCH_Z9_109
 	bool "IBM System z9"
-	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z9_109_FEATURES
+	depends on $(cc-option,-march=z9-109)
 	help
 	  Select this to enable optimizations for IBM System z9 (2094 and
 	  2096 series). The kernel will be slightly faster but will not work
@@ -274,6 +274,7 @@ config MARCH_Z9_109
 config MARCH_Z10
 	bool "IBM System z10"
 	select HAVE_MARCH_Z10_FEATURES
+	depends on $(cc-option,-march=z10)
 	help
 	  Select this to enable optimizations for IBM System z10 (2097 and
 	  2098 series). The kernel will be slightly faster but will not work
@@ -282,6 +283,7 @@ config MARCH_Z10
 config MARCH_Z196
 	bool "IBM zEnterprise 114 and 196"
 	select HAVE_MARCH_Z196_FEATURES
+	depends on $(cc-option,-march=z196)
 	help
 	  Select this to enable optimizations for IBM zEnterprise 114 and 196
 	  (2818 and 2817 series). The kernel will be slightly faster but will
@@ -290,6 +292,7 @@ config MARCH_Z196
 config MARCH_ZEC12
 	bool "IBM zBC12 and zEC12"
 	select HAVE_MARCH_ZEC12_FEATURES
+	depends on $(cc-option,-march=zEC12)
 	help
 	  Select this to enable optimizations for IBM zBC12 and zEC12 (2828 and
 	  2827 series). The kernel will be slightly faster but will not work on
@@ -298,6 +301,7 @@ config MARCH_ZEC12
 config MARCH_Z13
 	bool "IBM z13s and z13"
 	select HAVE_MARCH_Z13_FEATURES
+	depends on $(cc-option,-march=z13)
 	help
 	  Select this to enable optimizations for IBM z13s and z13 (2965 and
 	  2964 series). The kernel will be slightly faster but will not work on
@@ -306,6 +310,7 @@ config MARCH_Z13
 config MARCH_Z14
 	bool "IBM z14 ZR1 and z14"
 	select HAVE_MARCH_Z14_FEATURES
+	depends on $(cc-option,-march=z14)
 	help
 	  Select this to enable optimizations for IBM z14 ZR1 and z14 (3907
 	  and 3906 series). The kernel will be slightly faster but will not
@@ -314,6 +319,7 @@ config MARCH_Z14
 config MARCH_Z15
 	bool "IBM z15"
 	select HAVE_MARCH_Z15_FEATURES
+	depends on $(cc-option,-march=z15)
 	help
 	  Select this to enable optimizations for IBM z15 (8562
 	  and 8561 series). The kernel will be slightly faster but will not
@@ -367,33 +373,39 @@ config TUNE_DEFAULT
 
 config TUNE_Z900
 	bool "IBM zSeries model z800 and z900"
-	depends on !CC_IS_CLANG
+	depends on $(cc-option,-mtune=z900)
 
 config TUNE_Z990
 	bool "IBM zSeries model z890 and z990"
-	depends on !CC_IS_CLANG
+	depends on $(cc-option,-mtune=z990)
 
 config TUNE_Z9_109
 	bool "IBM System z9"
-	depends on !CC_IS_CLANG
+	depends on $(cc-option,-mtune=z9-109)
 
 config TUNE_Z10
 	bool "IBM System z10"
+	depends on $(cc-option,-mtune=z10)
 
 config TUNE_Z196
 	bool "IBM zEnterprise 114 and 196"
+	depends on $(cc-option,-mtune=z196)
 
 config TUNE_ZEC12
 	bool "IBM zBC12 and zEC12"
+	depends on $(cc-option,-mtune=zEC12)
 
 config TUNE_Z13
-	bool "IBM z13"
+	bool "IBM z13s and z13"
+	depends on $(cc-option,-mtune=z13)
 
 config TUNE_Z14
-	bool "IBM z14"
+	bool "IBM z14 ZR1 and z14"
+	depends on $(cc-option,-mtune=z14)
 
 config TUNE_Z15
 	bool "IBM z15"
+	depends on $(cc-option,-mtune=z15)
 
 endchoice
 
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 5367950510f6..fbd341ea03b8 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -46,7 +46,7 @@ struct diag_ops __bootdata_preserved(diag_dma_ops) = {
 	.diag0c = _diag0c_dma,
 	.diag308_reset = _diag308_reset_dma
 };
-static struct diag210 _diag210_tmp_dma __section(".dma.data");
+static struct diag210 _diag210_tmp_dma __section(.dma.data);
 struct diag210 *__bootdata_preserved(__diag210_tmp_dma) = &_diag210_tmp_dma;
 void _swsusp_reset_dma(void);
 unsigned long __bootdata_preserved(__swsusp_reset_dma) = __pa(_swsusp_reset_dma);
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index 9803e96d2924..ead0b2c9881d 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -44,7 +44,7 @@ struct s390_aes_ctx {
 	int key_len;
 	unsigned long fc;
 	union {
-		struct crypto_sync_skcipher *blk;
+		struct crypto_skcipher *skcipher;
 		struct crypto_cipher *cip;
 	} fallback;
 };
@@ -54,7 +54,7 @@ struct s390_xts_ctx {
 	u8 pcc_key[32];
 	int key_len;
 	unsigned long fc;
-	struct crypto_sync_skcipher *fallback;
+	struct crypto_skcipher *fallback;
 };
 
 struct gcm_sg_walk {
@@ -178,66 +178,41 @@ static struct crypto_alg aes_alg = {
 	}
 };
 
-static int setkey_fallback_blk(struct crypto_tfm *tfm, const u8 *key,
-		unsigned int len)
+static int setkey_fallback_skcipher(struct crypto_skcipher *tfm, const u8 *key,
+				    unsigned int len)
 {
-	struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
-	unsigned int ret;
-
-	crypto_sync_skcipher_clear_flags(sctx->fallback.blk,
-					 CRYPTO_TFM_REQ_MASK);
-	crypto_sync_skcipher_set_flags(sctx->fallback.blk, tfm->crt_flags &
-						      CRYPTO_TFM_REQ_MASK);
-
-	ret = crypto_sync_skcipher_setkey(sctx->fallback.blk, key, len);
-
-	tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-	tfm->crt_flags |= crypto_sync_skcipher_get_flags(sctx->fallback.blk) &
-			  CRYPTO_TFM_RES_MASK;
-
-	return ret;
-}
-
-static int fallback_blk_dec(struct blkcipher_desc *desc,
-		struct scatterlist *dst, struct scatterlist *src,
-		unsigned int nbytes)
-{
-	unsigned int ret;
-	struct crypto_blkcipher *tfm = desc->tfm;
-	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(tfm);
-	SYNC_SKCIPHER_REQUEST_ON_STACK(req, sctx->fallback.blk);
-
-	skcipher_request_set_sync_tfm(req, sctx->fallback.blk);
-	skcipher_request_set_callback(req, desc->flags, NULL, NULL);
-	skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
-
-	ret = crypto_skcipher_decrypt(req);
+	struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm);
+	int ret;
 
-	skcipher_request_zero(req);
+	crypto_skcipher_clear_flags(sctx->fallback.skcipher,
+				    CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(sctx->fallback.skcipher,
+				  crypto_skcipher_get_flags(tfm) &
+				  CRYPTO_TFM_REQ_MASK);
+	ret = crypto_skcipher_setkey(sctx->fallback.skcipher, key, len);
+	crypto_skcipher_set_flags(tfm,
+				  crypto_skcipher_get_flags(sctx->fallback.skcipher) &
+				  CRYPTO_TFM_RES_MASK);
 	return ret;
 }
 
-static int fallback_blk_enc(struct blkcipher_desc *desc,
-		struct scatterlist *dst, struct scatterlist *src,
-		unsigned int nbytes)
+static int fallback_skcipher_crypt(struct s390_aes_ctx *sctx,
+				   struct skcipher_request *req,
+				   unsigned long modifier)
 {
-	unsigned int ret;
-	struct crypto_blkcipher *tfm = desc->tfm;
-	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(tfm);
-	SYNC_SKCIPHER_REQUEST_ON_STACK(req, sctx->fallback.blk);
-
-	skcipher_request_set_sync_tfm(req, sctx->fallback.blk);
-	skcipher_request_set_callback(req, desc->flags, NULL, NULL);
-	skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
+	struct skcipher_request *subreq = skcipher_request_ctx(req);
 
-	ret = crypto_skcipher_encrypt(req);
-	return ret;
+	*subreq = *req;
+	skcipher_request_set_tfm(subreq, sctx->fallback.skcipher);
+	return (modifier & CPACF_DECRYPT) ?
+		crypto_skcipher_decrypt(subreq) :
+		crypto_skcipher_encrypt(subreq);
 }
 
-static int ecb_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+static int ecb_aes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
 			   unsigned int key_len)
 {
-	struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
+	struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm);
 	unsigned long fc;
 
 	/* Pick the correct function code based on the key length */
@@ -248,111 +223,92 @@ static int ecb_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 	/* Check if the function code is available */
 	sctx->fc = (fc && cpacf_test_func(&km_functions, fc)) ? fc : 0;
 	if (!sctx->fc)
-		return setkey_fallback_blk(tfm, in_key, key_len);
+		return setkey_fallback_skcipher(tfm, in_key, key_len);
 
 	sctx->key_len = key_len;
 	memcpy(sctx->key, in_key, key_len);
 	return 0;
 }
 
-static int ecb_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
-			 struct blkcipher_walk *walk)
+static int ecb_aes_crypt(struct skcipher_request *req, unsigned long modifier)
 {
-	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
 	unsigned int nbytes, n;
 	int ret;
 
-	ret = blkcipher_walk_virt(desc, walk);
-	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
+	if (unlikely(!sctx->fc))
+		return fallback_skcipher_crypt(sctx, req, modifier);
+
+	ret = skcipher_walk_virt(&walk, req, false);
+	while ((nbytes = walk.nbytes) != 0) {
 		/* only use complete blocks */
 		n = nbytes & ~(AES_BLOCK_SIZE - 1);
 		cpacf_km(sctx->fc | modifier, sctx->key,
-			 walk->dst.virt.addr, walk->src.virt.addr, n);
-		ret = blkcipher_walk_done(desc, walk, nbytes - n);
+			 walk.dst.virt.addr, walk.src.virt.addr, n);
+		ret = skcipher_walk_done(&walk, nbytes - n);
 	}
-
 	return ret;
 }
 
-static int ecb_aes_encrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
+static int ecb_aes_encrypt(struct skcipher_request *req)
 {
-	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-
-	if (unlikely(!sctx->fc))
-		return fallback_blk_enc(desc, dst, src, nbytes);
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_aes_crypt(desc, 0, &walk);
+	return ecb_aes_crypt(req, 0);
 }
 
-static int ecb_aes_decrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
+static int ecb_aes_decrypt(struct skcipher_request *req)
 {
-	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-
-	if (unlikely(!sctx->fc))
-		return fallback_blk_dec(desc, dst, src, nbytes);
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_aes_crypt(desc, CPACF_DECRYPT, &walk);
+	return ecb_aes_crypt(req, CPACF_DECRYPT);
 }
 
-static int fallback_init_blk(struct crypto_tfm *tfm)
+static int fallback_init_skcipher(struct crypto_skcipher *tfm)
 {
-	const char *name = tfm->__crt_alg->cra_name;
-	struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
+	const char *name = crypto_tfm_alg_name(&tfm->base);
+	struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm);
 
-	sctx->fallback.blk = crypto_alloc_sync_skcipher(name, 0,
-						   CRYPTO_ALG_NEED_FALLBACK);
+	sctx->fallback.skcipher = crypto_alloc_skcipher(name, 0,
+				CRYPTO_ALG_NEED_FALLBACK | CRYPTO_ALG_ASYNC);
 
-	if (IS_ERR(sctx->fallback.blk)) {
+	if (IS_ERR(sctx->fallback.skcipher)) {
 		pr_err("Allocating AES fallback algorithm %s failed\n",
 		       name);
-		return PTR_ERR(sctx->fallback.blk);
+		return PTR_ERR(sctx->fallback.skcipher);
 	}
 
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct skcipher_request) +
+				    crypto_skcipher_reqsize(sctx->fallback.skcipher));
 	return 0;
 }
 
-static void fallback_exit_blk(struct crypto_tfm *tfm)
+static void fallback_exit_skcipher(struct crypto_skcipher *tfm)
 {
-	struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
+	struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm);
 
-	crypto_free_sync_skcipher(sctx->fallback.blk);
+	crypto_free_skcipher(sctx->fallback.skcipher);
 }
 
-static struct crypto_alg ecb_aes_alg = {
-	.cra_name		=	"ecb(aes)",
-	.cra_driver_name	=	"ecb-aes-s390",
-	.cra_priority		=	401,	/* combo: aes + ecb + 1 */
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER |
-					CRYPTO_ALG_NEED_FALLBACK,
-	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct s390_aes_ctx),
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_init		=	fallback_init_blk,
-	.cra_exit		=	fallback_exit_blk,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	AES_MIN_KEY_SIZE,
-			.max_keysize		=	AES_MAX_KEY_SIZE,
-			.setkey			=	ecb_aes_set_key,
-			.encrypt		=	ecb_aes_encrypt,
-			.decrypt		=	ecb_aes_decrypt,
-		}
-	}
+static struct skcipher_alg ecb_aes_alg = {
+	.base.cra_name		=	"ecb(aes)",
+	.base.cra_driver_name	=	"ecb-aes-s390",
+	.base.cra_priority	=	401,	/* combo: aes + ecb + 1 */
+	.base.cra_flags		=	CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize	=	AES_BLOCK_SIZE,
+	.base.cra_ctxsize	=	sizeof(struct s390_aes_ctx),
+	.base.cra_module	=	THIS_MODULE,
+	.init			=	fallback_init_skcipher,
+	.exit			=	fallback_exit_skcipher,
+	.min_keysize		=	AES_MIN_KEY_SIZE,
+	.max_keysize		=	AES_MAX_KEY_SIZE,
+	.setkey			=	ecb_aes_set_key,
+	.encrypt		=	ecb_aes_encrypt,
+	.decrypt		=	ecb_aes_decrypt,
 };
 
-static int cbc_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+static int cbc_aes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
 			   unsigned int key_len)
 {
-	struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
+	struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm);
 	unsigned long fc;
 
 	/* Pick the correct function code based on the key length */
@@ -363,17 +319,18 @@ static int cbc_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 	/* Check if the function code is available */
 	sctx->fc = (fc && cpacf_test_func(&kmc_functions, fc)) ? fc : 0;
 	if (!sctx->fc)
-		return setkey_fallback_blk(tfm, in_key, key_len);
+		return setkey_fallback_skcipher(tfm, in_key, key_len);
 
 	sctx->key_len = key_len;
 	memcpy(sctx->key, in_key, key_len);
 	return 0;
 }
 
-static int cbc_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
-			 struct blkcipher_walk *walk)
+static int cbc_aes_crypt(struct skcipher_request *req, unsigned long modifier)
 {
-	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
 	unsigned int nbytes, n;
 	int ret;
 	struct {
@@ -381,134 +338,74 @@ static int cbc_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
 		u8 key[AES_MAX_KEY_SIZE];
 	} param;
 
-	ret = blkcipher_walk_virt(desc, walk);
-	memcpy(param.iv, walk->iv, AES_BLOCK_SIZE);
+	if (unlikely(!sctx->fc))
+		return fallback_skcipher_crypt(sctx, req, modifier);
+
+	ret = skcipher_walk_virt(&walk, req, false);
+	if (ret)
+		return ret;
+	memcpy(param.iv, walk.iv, AES_BLOCK_SIZE);
 	memcpy(param.key, sctx->key, sctx->key_len);
-	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
+	while ((nbytes = walk.nbytes) != 0) {
 		/* only use complete blocks */
 		n = nbytes & ~(AES_BLOCK_SIZE - 1);
 		cpacf_kmc(sctx->fc | modifier, &param,
-			  walk->dst.virt.addr, walk->src.virt.addr, n);
-		ret = blkcipher_walk_done(desc, walk, nbytes - n);
+			  walk.dst.virt.addr, walk.src.virt.addr, n);
+		memcpy(walk.iv, param.iv, AES_BLOCK_SIZE);
+		ret = skcipher_walk_done(&walk, nbytes - n);
 	}
-	memcpy(walk->iv, param.iv, AES_BLOCK_SIZE);
 	return ret;
 }
 
-static int cbc_aes_encrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
+static int cbc_aes_encrypt(struct skcipher_request *req)
 {
-	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-
-	if (unlikely(!sctx->fc))
-		return fallback_blk_enc(desc, dst, src, nbytes);
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_aes_crypt(desc, 0, &walk);
+	return cbc_aes_crypt(req, 0);
 }
 
-static int cbc_aes_decrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
+static int cbc_aes_decrypt(struct skcipher_request *req)
 {
-	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-
-	if (unlikely(!sctx->fc))
-		return fallback_blk_dec(desc, dst, src, nbytes);
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_aes_crypt(desc, CPACF_DECRYPT, &walk);
+	return cbc_aes_crypt(req, CPACF_DECRYPT);
 }
 
-static struct crypto_alg cbc_aes_alg = {
-	.cra_name		=	"cbc(aes)",
-	.cra_driver_name	=	"cbc-aes-s390",
-	.cra_priority		=	402,	/* ecb-aes-s390 + 1 */
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER |
-					CRYPTO_ALG_NEED_FALLBACK,
-	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct s390_aes_ctx),
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_init		=	fallback_init_blk,
-	.cra_exit		=	fallback_exit_blk,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	AES_MIN_KEY_SIZE,
-			.max_keysize		=	AES_MAX_KEY_SIZE,
-			.ivsize			=	AES_BLOCK_SIZE,
-			.setkey			=	cbc_aes_set_key,
-			.encrypt		=	cbc_aes_encrypt,
-			.decrypt		=	cbc_aes_decrypt,
-		}
-	}
+static struct skcipher_alg cbc_aes_alg = {
+	.base.cra_name		=	"cbc(aes)",
+	.base.cra_driver_name	=	"cbc-aes-s390",
+	.base.cra_priority	=	402,	/* ecb-aes-s390 + 1 */
+	.base.cra_flags		=	CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize	=	AES_BLOCK_SIZE,
+	.base.cra_ctxsize	=	sizeof(struct s390_aes_ctx),
+	.base.cra_module	=	THIS_MODULE,
+	.init			=	fallback_init_skcipher,
+	.exit			=	fallback_exit_skcipher,
+	.min_keysize		=	AES_MIN_KEY_SIZE,
+	.max_keysize		=	AES_MAX_KEY_SIZE,
+	.ivsize			=	AES_BLOCK_SIZE,
+	.setkey			=	cbc_aes_set_key,
+	.encrypt		=	cbc_aes_encrypt,
+	.decrypt		=	cbc_aes_decrypt,
 };
 
-static int xts_fallback_setkey(struct crypto_tfm *tfm, const u8 *key,
-				   unsigned int len)
-{
-	struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm);
-	unsigned int ret;
-
-	crypto_sync_skcipher_clear_flags(xts_ctx->fallback,
-					 CRYPTO_TFM_REQ_MASK);
-	crypto_sync_skcipher_set_flags(xts_ctx->fallback, tfm->crt_flags &
-						     CRYPTO_TFM_REQ_MASK);
-
-	ret = crypto_sync_skcipher_setkey(xts_ctx->fallback, key, len);
-
-	tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-	tfm->crt_flags |= crypto_sync_skcipher_get_flags(xts_ctx->fallback) &
-			  CRYPTO_TFM_RES_MASK;
-
-	return ret;
-}
-
-static int xts_fallback_decrypt(struct blkcipher_desc *desc,
-		struct scatterlist *dst, struct scatterlist *src,
-		unsigned int nbytes)
-{
-	struct crypto_blkcipher *tfm = desc->tfm;
-	struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(tfm);
-	SYNC_SKCIPHER_REQUEST_ON_STACK(req, xts_ctx->fallback);
-	unsigned int ret;
-
-	skcipher_request_set_sync_tfm(req, xts_ctx->fallback);
-	skcipher_request_set_callback(req, desc->flags, NULL, NULL);
-	skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
-
-	ret = crypto_skcipher_decrypt(req);
-
-	skcipher_request_zero(req);
-	return ret;
-}
-
-static int xts_fallback_encrypt(struct blkcipher_desc *desc,
-		struct scatterlist *dst, struct scatterlist *src,
-		unsigned int nbytes)
+static int xts_fallback_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			       unsigned int len)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
-	struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(tfm);
-	SYNC_SKCIPHER_REQUEST_ON_STACK(req, xts_ctx->fallback);
-	unsigned int ret;
-
-	skcipher_request_set_sync_tfm(req, xts_ctx->fallback);
-	skcipher_request_set_callback(req, desc->flags, NULL, NULL);
-	skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
-
-	ret = crypto_skcipher_encrypt(req);
+	struct s390_xts_ctx *xts_ctx = crypto_skcipher_ctx(tfm);
+	int ret;
 
-	skcipher_request_zero(req);
+	crypto_skcipher_clear_flags(xts_ctx->fallback, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(xts_ctx->fallback,
+				  crypto_skcipher_get_flags(tfm) &
+				  CRYPTO_TFM_REQ_MASK);
+	ret = crypto_skcipher_setkey(xts_ctx->fallback, key, len);
+	crypto_skcipher_set_flags(tfm,
+				  crypto_skcipher_get_flags(xts_ctx->fallback) &
+				  CRYPTO_TFM_RES_MASK);
 	return ret;
 }
 
-static int xts_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+static int xts_aes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
 			   unsigned int key_len)
 {
-	struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm);
+	struct s390_xts_ctx *xts_ctx = crypto_skcipher_ctx(tfm);
 	unsigned long fc;
 	int err;
 
@@ -518,7 +415,7 @@ static int xts_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 
 	/* In fips mode only 128 bit or 256 bit keys are valid */
 	if (fips_enabled && key_len != 32 && key_len != 64) {
-		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
@@ -539,10 +436,11 @@ static int xts_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 	return 0;
 }
 
-static int xts_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
-			 struct blkcipher_walk *walk)
+static int xts_aes_crypt(struct skcipher_request *req, unsigned long modifier)
 {
-	struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_xts_ctx *xts_ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
 	unsigned int offset, nbytes, n;
 	int ret;
 	struct {
@@ -557,113 +455,100 @@ static int xts_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
 		u8 init[16];
 	} xts_param;
 
-	ret = blkcipher_walk_virt(desc, walk);
+	if (req->cryptlen < AES_BLOCK_SIZE)
+		return -EINVAL;
+
+	if (unlikely(!xts_ctx->fc || (req->cryptlen % AES_BLOCK_SIZE) != 0)) {
+		struct skcipher_request *subreq = skcipher_request_ctx(req);
+
+		*subreq = *req;
+		skcipher_request_set_tfm(subreq, xts_ctx->fallback);
+		return (modifier & CPACF_DECRYPT) ?
+			crypto_skcipher_decrypt(subreq) :
+			crypto_skcipher_encrypt(subreq);
+	}
+
+	ret = skcipher_walk_virt(&walk, req, false);
+	if (ret)
+		return ret;
 	offset = xts_ctx->key_len & 0x10;
 	memset(pcc_param.block, 0, sizeof(pcc_param.block));
 	memset(pcc_param.bit, 0, sizeof(pcc_param.bit));
 	memset(pcc_param.xts, 0, sizeof(pcc_param.xts));
-	memcpy(pcc_param.tweak, walk->iv, sizeof(pcc_param.tweak));
+	memcpy(pcc_param.tweak, walk.iv, sizeof(pcc_param.tweak));
 	memcpy(pcc_param.key + offset, xts_ctx->pcc_key, xts_ctx->key_len);
 	cpacf_pcc(xts_ctx->fc, pcc_param.key + offset);
 
 	memcpy(xts_param.key + offset, xts_ctx->key, xts_ctx->key_len);
 	memcpy(xts_param.init, pcc_param.xts, 16);
 
-	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
+	while ((nbytes = walk.nbytes) != 0) {
 		/* only use complete blocks */
 		n = nbytes & ~(AES_BLOCK_SIZE - 1);
 		cpacf_km(xts_ctx->fc | modifier, xts_param.key + offset,
-			 walk->dst.virt.addr, walk->src.virt.addr, n);
-		ret = blkcipher_walk_done(desc, walk, nbytes - n);
+			 walk.dst.virt.addr, walk.src.virt.addr, n);
+		ret = skcipher_walk_done(&walk, nbytes - n);
 	}
 	return ret;
 }
 
-static int xts_aes_encrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
+static int xts_aes_encrypt(struct skcipher_request *req)
 {
-	struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-
-	if (!nbytes)
-		return -EINVAL;
-
-	if (unlikely(!xts_ctx->fc || (nbytes % XTS_BLOCK_SIZE) != 0))
-		return xts_fallback_encrypt(desc, dst, src, nbytes);
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return xts_aes_crypt(desc, 0, &walk);
+	return xts_aes_crypt(req, 0);
 }
 
-static int xts_aes_decrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
+static int xts_aes_decrypt(struct skcipher_request *req)
 {
-	struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-
-	if (!nbytes)
-		return -EINVAL;
-
-	if (unlikely(!xts_ctx->fc || (nbytes % XTS_BLOCK_SIZE) != 0))
-		return xts_fallback_decrypt(desc, dst, src, nbytes);
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return xts_aes_crypt(desc, CPACF_DECRYPT, &walk);
+	return xts_aes_crypt(req, CPACF_DECRYPT);
 }
 
-static int xts_fallback_init(struct crypto_tfm *tfm)
+static int xts_fallback_init(struct crypto_skcipher *tfm)
 {
-	const char *name = tfm->__crt_alg->cra_name;
-	struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm);
+	const char *name = crypto_tfm_alg_name(&tfm->base);
+	struct s390_xts_ctx *xts_ctx = crypto_skcipher_ctx(tfm);
 
-	xts_ctx->fallback = crypto_alloc_sync_skcipher(name, 0,
-						  CRYPTO_ALG_NEED_FALLBACK);
+	xts_ctx->fallback = crypto_alloc_skcipher(name, 0,
+				CRYPTO_ALG_NEED_FALLBACK | CRYPTO_ALG_ASYNC);
 
 	if (IS_ERR(xts_ctx->fallback)) {
 		pr_err("Allocating XTS fallback algorithm %s failed\n",
 		       name);
 		return PTR_ERR(xts_ctx->fallback);
 	}
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct skcipher_request) +
+				    crypto_skcipher_reqsize(xts_ctx->fallback));
 	return 0;
 }
 
-static void xts_fallback_exit(struct crypto_tfm *tfm)
+static void xts_fallback_exit(struct crypto_skcipher *tfm)
 {
-	struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm);
+	struct s390_xts_ctx *xts_ctx = crypto_skcipher_ctx(tfm);
 
-	crypto_free_sync_skcipher(xts_ctx->fallback);
+	crypto_free_skcipher(xts_ctx->fallback);
 }
 
-static struct crypto_alg xts_aes_alg = {
-	.cra_name		=	"xts(aes)",
-	.cra_driver_name	=	"xts-aes-s390",
-	.cra_priority		=	402,	/* ecb-aes-s390 + 1 */
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER |
-					CRYPTO_ALG_NEED_FALLBACK,
-	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct s390_xts_ctx),
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_init		=	xts_fallback_init,
-	.cra_exit		=	xts_fallback_exit,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	2 * AES_MIN_KEY_SIZE,
-			.max_keysize		=	2 * AES_MAX_KEY_SIZE,
-			.ivsize			=	AES_BLOCK_SIZE,
-			.setkey			=	xts_aes_set_key,
-			.encrypt		=	xts_aes_encrypt,
-			.decrypt		=	xts_aes_decrypt,
-		}
-	}
+static struct skcipher_alg xts_aes_alg = {
+	.base.cra_name		=	"xts(aes)",
+	.base.cra_driver_name	=	"xts-aes-s390",
+	.base.cra_priority	=	402,	/* ecb-aes-s390 + 1 */
+	.base.cra_flags		=	CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize	=	AES_BLOCK_SIZE,
+	.base.cra_ctxsize	=	sizeof(struct s390_xts_ctx),
+	.base.cra_module	=	THIS_MODULE,
+	.init			=	xts_fallback_init,
+	.exit			=	xts_fallback_exit,
+	.min_keysize		=	2 * AES_MIN_KEY_SIZE,
+	.max_keysize		=	2 * AES_MAX_KEY_SIZE,
+	.ivsize			=	AES_BLOCK_SIZE,
+	.setkey			=	xts_aes_set_key,
+	.encrypt		=	xts_aes_encrypt,
+	.decrypt		=	xts_aes_decrypt,
 };
 
-static int ctr_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+static int ctr_aes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
 			   unsigned int key_len)
 {
-	struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
+	struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm);
 	unsigned long fc;
 
 	/* Pick the correct function code based on the key length */
@@ -674,7 +559,7 @@ static int ctr_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 	/* Check if the function code is available */
 	sctx->fc = (fc && cpacf_test_func(&kmctr_functions, fc)) ? fc : 0;
 	if (!sctx->fc)
-		return setkey_fallback_blk(tfm, in_key, key_len);
+		return setkey_fallback_skcipher(tfm, in_key, key_len);
 
 	sctx->key_len = key_len;
 	memcpy(sctx->key, in_key, key_len);
@@ -696,30 +581,34 @@ static unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes)
 	return n;
 }
 
-static int ctr_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
-			 struct blkcipher_walk *walk)
+static int ctr_aes_crypt(struct skcipher_request *req)
 {
-	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm);
 	u8 buf[AES_BLOCK_SIZE], *ctrptr;
+	struct skcipher_walk walk;
 	unsigned int n, nbytes;
 	int ret, locked;
 
+	if (unlikely(!sctx->fc))
+		return fallback_skcipher_crypt(sctx, req, 0);
+
 	locked = mutex_trylock(&ctrblk_lock);
 
-	ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE);
-	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
+	ret = skcipher_walk_virt(&walk, req, false);
+	while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
 		n = AES_BLOCK_SIZE;
+
 		if (nbytes >= 2*AES_BLOCK_SIZE && locked)
-			n = __ctrblk_init(ctrblk, walk->iv, nbytes);
-		ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk->iv;
-		cpacf_kmctr(sctx->fc | modifier, sctx->key,
-			    walk->dst.virt.addr, walk->src.virt.addr,
-			    n, ctrptr);
+			n = __ctrblk_init(ctrblk, walk.iv, nbytes);
+		ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk.iv;
+		cpacf_kmctr(sctx->fc, sctx->key, walk.dst.virt.addr,
+			    walk.src.virt.addr, n, ctrptr);
 		if (ctrptr == ctrblk)
-			memcpy(walk->iv, ctrptr + n - AES_BLOCK_SIZE,
+			memcpy(walk.iv, ctrptr + n - AES_BLOCK_SIZE,
 			       AES_BLOCK_SIZE);
-		crypto_inc(walk->iv, AES_BLOCK_SIZE);
-		ret = blkcipher_walk_done(desc, walk, nbytes - n);
+		crypto_inc(walk.iv, AES_BLOCK_SIZE);
+		ret = skcipher_walk_done(&walk, nbytes - n);
 	}
 	if (locked)
 		mutex_unlock(&ctrblk_lock);
@@ -727,67 +616,33 @@ static int ctr_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
 	 * final block may be < AES_BLOCK_SIZE, copy only nbytes
 	 */
 	if (nbytes) {
-		cpacf_kmctr(sctx->fc | modifier, sctx->key,
-			    buf, walk->src.virt.addr,
-			    AES_BLOCK_SIZE, walk->iv);
-		memcpy(walk->dst.virt.addr, buf, nbytes);
-		crypto_inc(walk->iv, AES_BLOCK_SIZE);
-		ret = blkcipher_walk_done(desc, walk, 0);
+		cpacf_kmctr(sctx->fc, sctx->key, buf, walk.src.virt.addr,
+			    AES_BLOCK_SIZE, walk.iv);
+		memcpy(walk.dst.virt.addr, buf, nbytes);
+		crypto_inc(walk.iv, AES_BLOCK_SIZE);
+		ret = skcipher_walk_done(&walk, 0);
 	}
 
 	return ret;
 }
 
-static int ctr_aes_encrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
-{
-	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-
-	if (unlikely(!sctx->fc))
-		return fallback_blk_enc(desc, dst, src, nbytes);
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ctr_aes_crypt(desc, 0, &walk);
-}
-
-static int ctr_aes_decrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
-{
-	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-
-	if (unlikely(!sctx->fc))
-		return fallback_blk_dec(desc, dst, src, nbytes);
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ctr_aes_crypt(desc, CPACF_DECRYPT, &walk);
-}
-
-static struct crypto_alg ctr_aes_alg = {
-	.cra_name		=	"ctr(aes)",
-	.cra_driver_name	=	"ctr-aes-s390",
-	.cra_priority		=	402,	/* ecb-aes-s390 + 1 */
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER |
-					CRYPTO_ALG_NEED_FALLBACK,
-	.cra_blocksize		=	1,
-	.cra_ctxsize		=	sizeof(struct s390_aes_ctx),
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_init		=	fallback_init_blk,
-	.cra_exit		=	fallback_exit_blk,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	AES_MIN_KEY_SIZE,
-			.max_keysize		=	AES_MAX_KEY_SIZE,
-			.ivsize			=	AES_BLOCK_SIZE,
-			.setkey			=	ctr_aes_set_key,
-			.encrypt		=	ctr_aes_encrypt,
-			.decrypt		=	ctr_aes_decrypt,
-		}
-	}
+static struct skcipher_alg ctr_aes_alg = {
+	.base.cra_name		=	"ctr(aes)",
+	.base.cra_driver_name	=	"ctr-aes-s390",
+	.base.cra_priority	=	402,	/* ecb-aes-s390 + 1 */
+	.base.cra_flags		=	CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize	=	1,
+	.base.cra_ctxsize	=	sizeof(struct s390_aes_ctx),
+	.base.cra_module	=	THIS_MODULE,
+	.init			=	fallback_init_skcipher,
+	.exit			=	fallback_exit_skcipher,
+	.min_keysize		=	AES_MIN_KEY_SIZE,
+	.max_keysize		=	AES_MAX_KEY_SIZE,
+	.ivsize			=	AES_BLOCK_SIZE,
+	.setkey			=	ctr_aes_set_key,
+	.encrypt		=	ctr_aes_crypt,
+	.decrypt		=	ctr_aes_crypt,
+	.chunksize		=	AES_BLOCK_SIZE,
 };
 
 static int gcm_aes_setkey(struct crypto_aead *tfm, const u8 *key,
@@ -1116,24 +971,27 @@ static struct aead_alg gcm_aes_aead = {
 	},
 };
 
-static struct crypto_alg *aes_s390_algs_ptr[5];
-static int aes_s390_algs_num;
+static struct crypto_alg *aes_s390_alg;
+static struct skcipher_alg *aes_s390_skcipher_algs[4];
+static int aes_s390_skciphers_num;
 static struct aead_alg *aes_s390_aead_alg;
 
-static int aes_s390_register_alg(struct crypto_alg *alg)
+static int aes_s390_register_skcipher(struct skcipher_alg *alg)
 {
 	int ret;
 
-	ret = crypto_register_alg(alg);
+	ret = crypto_register_skcipher(alg);
 	if (!ret)
-		aes_s390_algs_ptr[aes_s390_algs_num++] = alg;
+		aes_s390_skcipher_algs[aes_s390_skciphers_num++] = alg;
 	return ret;
 }
 
 static void aes_s390_fini(void)
 {
-	while (aes_s390_algs_num--)
-		crypto_unregister_alg(aes_s390_algs_ptr[aes_s390_algs_num]);
+	if (aes_s390_alg)
+		crypto_unregister_alg(aes_s390_alg);
+	while (aes_s390_skciphers_num--)
+		crypto_unregister_skcipher(aes_s390_skcipher_algs[aes_s390_skciphers_num]);
 	if (ctrblk)
 		free_page((unsigned long) ctrblk);
 
@@ -1154,10 +1012,11 @@ static int __init aes_s390_init(void)
 	if (cpacf_test_func(&km_functions, CPACF_KM_AES_128) ||
 	    cpacf_test_func(&km_functions, CPACF_KM_AES_192) ||
 	    cpacf_test_func(&km_functions, CPACF_KM_AES_256)) {
-		ret = aes_s390_register_alg(&aes_alg);
+		ret = crypto_register_alg(&aes_alg);
 		if (ret)
 			goto out_err;
-		ret = aes_s390_register_alg(&ecb_aes_alg);
+		aes_s390_alg = &aes_alg;
+		ret = aes_s390_register_skcipher(&ecb_aes_alg);
 		if (ret)
 			goto out_err;
 	}
@@ -1165,14 +1024,14 @@ static int __init aes_s390_init(void)
 	if (cpacf_test_func(&kmc_functions, CPACF_KMC_AES_128) ||
 	    cpacf_test_func(&kmc_functions, CPACF_KMC_AES_192) ||
 	    cpacf_test_func(&kmc_functions, CPACF_KMC_AES_256)) {
-		ret = aes_s390_register_alg(&cbc_aes_alg);
+		ret = aes_s390_register_skcipher(&cbc_aes_alg);
 		if (ret)
 			goto out_err;
 	}
 
 	if (cpacf_test_func(&km_functions, CPACF_KM_XTS_128) ||
 	    cpacf_test_func(&km_functions, CPACF_KM_XTS_256)) {
-		ret = aes_s390_register_alg(&xts_aes_alg);
+		ret = aes_s390_register_skcipher(&xts_aes_alg);
 		if (ret)
 			goto out_err;
 	}
@@ -1185,7 +1044,7 @@ static int __init aes_s390_init(void)
 			ret = -ENOMEM;
 			goto out_err;
 		}
-		ret = aes_s390_register_alg(&ctr_aes_alg);
+		ret = aes_s390_register_skcipher(&ctr_aes_alg);
 		if (ret)
 			goto out_err;
 	}
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index 439b100c6f2e..bfbafd35bcbd 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -17,6 +17,7 @@
 #include <linux/mutex.h>
 #include <crypto/algapi.h>
 #include <crypto/internal/des.h>
+#include <crypto/internal/skcipher.h>
 #include <asm/cpacf.h>
 
 #define DES3_KEY_SIZE	(3 * DES_KEY_SIZE)
@@ -45,6 +46,12 @@ static int des_setkey(struct crypto_tfm *tfm, const u8 *key,
 	return 0;
 }
 
+static int des_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key,
+			       unsigned int key_len)
+{
+	return des_setkey(crypto_skcipher_tfm(tfm), key, key_len);
+}
+
 static void s390_des_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
 	struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm);
@@ -79,28 +86,30 @@ static struct crypto_alg des_alg = {
 	}
 };
 
-static int ecb_desall_crypt(struct blkcipher_desc *desc, unsigned long fc,
-			    struct blkcipher_walk *walk)
+static int ecb_desall_crypt(struct skcipher_request *req, unsigned long fc)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_des_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
 	unsigned int nbytes, n;
 	int ret;
 
-	ret = blkcipher_walk_virt(desc, walk);
-	while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) {
+	ret = skcipher_walk_virt(&walk, req, false);
+	while ((nbytes = walk.nbytes) != 0) {
 		/* only use complete blocks */
 		n = nbytes & ~(DES_BLOCK_SIZE - 1);
-		cpacf_km(fc, ctx->key, walk->dst.virt.addr,
-			 walk->src.virt.addr, n);
-		ret = blkcipher_walk_done(desc, walk, nbytes - n);
+		cpacf_km(fc, ctx->key, walk.dst.virt.addr,
+			 walk.src.virt.addr, n);
+		ret = skcipher_walk_done(&walk, nbytes - n);
 	}
 	return ret;
 }
 
-static int cbc_desall_crypt(struct blkcipher_desc *desc, unsigned long fc,
-			    struct blkcipher_walk *walk)
+static int cbc_desall_crypt(struct skcipher_request *req, unsigned long fc)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_des_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
 	unsigned int nbytes, n;
 	int ret;
 	struct {
@@ -108,99 +117,69 @@ static int cbc_desall_crypt(struct blkcipher_desc *desc, unsigned long fc,
 		u8 key[DES3_KEY_SIZE];
 	} param;
 
-	ret = blkcipher_walk_virt(desc, walk);
-	memcpy(param.iv, walk->iv, DES_BLOCK_SIZE);
+	ret = skcipher_walk_virt(&walk, req, false);
+	if (ret)
+		return ret;
+	memcpy(param.iv, walk.iv, DES_BLOCK_SIZE);
 	memcpy(param.key, ctx->key, DES3_KEY_SIZE);
-	while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) {
+	while ((nbytes = walk.nbytes) != 0) {
 		/* only use complete blocks */
 		n = nbytes & ~(DES_BLOCK_SIZE - 1);
-		cpacf_kmc(fc, &param, walk->dst.virt.addr,
-			  walk->src.virt.addr, n);
-		ret = blkcipher_walk_done(desc, walk, nbytes - n);
+		cpacf_kmc(fc, &param, walk.dst.virt.addr,
+			  walk.src.virt.addr, n);
+		memcpy(walk.iv, param.iv, DES_BLOCK_SIZE);
+		ret = skcipher_walk_done(&walk, nbytes - n);
 	}
-	memcpy(walk->iv, param.iv, DES_BLOCK_SIZE);
 	return ret;
 }
 
-static int ecb_des_encrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
+static int ecb_des_encrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_desall_crypt(desc, CPACF_KM_DEA, &walk);
+	return ecb_desall_crypt(req, CPACF_KM_DEA);
 }
 
-static int ecb_des_decrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
+static int ecb_des_decrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_desall_crypt(desc, CPACF_KM_DEA | CPACF_DECRYPT, &walk);
+	return ecb_desall_crypt(req, CPACF_KM_DEA | CPACF_DECRYPT);
 }
 
-static struct crypto_alg ecb_des_alg = {
-	.cra_name		=	"ecb(des)",
-	.cra_driver_name	=	"ecb-des-s390",
-	.cra_priority		=	400,	/* combo: des + ecb */
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	DES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct s390_des_ctx),
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	DES_KEY_SIZE,
-			.max_keysize		=	DES_KEY_SIZE,
-			.setkey			=	des_setkey,
-			.encrypt		=	ecb_des_encrypt,
-			.decrypt		=	ecb_des_decrypt,
-		}
-	}
+static struct skcipher_alg ecb_des_alg = {
+	.base.cra_name		=	"ecb(des)",
+	.base.cra_driver_name	=	"ecb-des-s390",
+	.base.cra_priority	=	400,	/* combo: des + ecb */
+	.base.cra_blocksize	=	DES_BLOCK_SIZE,
+	.base.cra_ctxsize	=	sizeof(struct s390_des_ctx),
+	.base.cra_module	=	THIS_MODULE,
+	.min_keysize		=	DES_KEY_SIZE,
+	.max_keysize		=	DES_KEY_SIZE,
+	.setkey			=	des_setkey_skcipher,
+	.encrypt		=	ecb_des_encrypt,
+	.decrypt		=	ecb_des_decrypt,
 };
 
-static int cbc_des_encrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
+static int cbc_des_encrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, CPACF_KMC_DEA, &walk);
+	return cbc_desall_crypt(req, CPACF_KMC_DEA);
 }
 
-static int cbc_des_decrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
+static int cbc_des_decrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, CPACF_KMC_DEA | CPACF_DECRYPT, &walk);
+	return cbc_desall_crypt(req, CPACF_KMC_DEA | CPACF_DECRYPT);
 }
 
-static struct crypto_alg cbc_des_alg = {
-	.cra_name		=	"cbc(des)",
-	.cra_driver_name	=	"cbc-des-s390",
-	.cra_priority		=	400,	/* combo: des + cbc */
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	DES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct s390_des_ctx),
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	DES_KEY_SIZE,
-			.max_keysize		=	DES_KEY_SIZE,
-			.ivsize			=	DES_BLOCK_SIZE,
-			.setkey			=	des_setkey,
-			.encrypt		=	cbc_des_encrypt,
-			.decrypt		=	cbc_des_decrypt,
-		}
-	}
+static struct skcipher_alg cbc_des_alg = {
+	.base.cra_name		=	"cbc(des)",
+	.base.cra_driver_name	=	"cbc-des-s390",
+	.base.cra_priority	=	400,	/* combo: des + cbc */
+	.base.cra_blocksize	=	DES_BLOCK_SIZE,
+	.base.cra_ctxsize	=	sizeof(struct s390_des_ctx),
+	.base.cra_module	=	THIS_MODULE,
+	.min_keysize		=	DES_KEY_SIZE,
+	.max_keysize		=	DES_KEY_SIZE,
+	.ivsize			=	DES_BLOCK_SIZE,
+	.setkey			=	des_setkey_skcipher,
+	.encrypt		=	cbc_des_encrypt,
+	.decrypt		=	cbc_des_decrypt,
 };
 
 /*
@@ -232,6 +211,12 @@ static int des3_setkey(struct crypto_tfm *tfm, const u8 *key,
 	return 0;
 }
 
+static int des3_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key,
+				unsigned int key_len)
+{
+	return des3_setkey(crypto_skcipher_tfm(tfm), key, key_len);
+}
+
 static void des3_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm);
@@ -266,87 +251,53 @@ static struct crypto_alg des3_alg = {
 	}
 };
 
-static int ecb_des3_encrypt(struct blkcipher_desc *desc,
-			    struct scatterlist *dst, struct scatterlist *src,
-			    unsigned int nbytes)
+static int ecb_des3_encrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_desall_crypt(desc, CPACF_KM_TDEA_192, &walk);
+	return ecb_desall_crypt(req, CPACF_KM_TDEA_192);
 }
 
-static int ecb_des3_decrypt(struct blkcipher_desc *desc,
-			    struct scatterlist *dst, struct scatterlist *src,
-			    unsigned int nbytes)
+static int ecb_des3_decrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_desall_crypt(desc, CPACF_KM_TDEA_192 | CPACF_DECRYPT,
-				&walk);
+	return ecb_desall_crypt(req, CPACF_KM_TDEA_192 | CPACF_DECRYPT);
 }
 
-static struct crypto_alg ecb_des3_alg = {
-	.cra_name		=	"ecb(des3_ede)",
-	.cra_driver_name	=	"ecb-des3_ede-s390",
-	.cra_priority		=	400,	/* combo: des3 + ecb */
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	DES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct s390_des_ctx),
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	DES3_KEY_SIZE,
-			.max_keysize		=	DES3_KEY_SIZE,
-			.setkey			=	des3_setkey,
-			.encrypt		=	ecb_des3_encrypt,
-			.decrypt		=	ecb_des3_decrypt,
-		}
-	}
+static struct skcipher_alg ecb_des3_alg = {
+	.base.cra_name		=	"ecb(des3_ede)",
+	.base.cra_driver_name	=	"ecb-des3_ede-s390",
+	.base.cra_priority	=	400,	/* combo: des3 + ecb */
+	.base.cra_blocksize	=	DES_BLOCK_SIZE,
+	.base.cra_ctxsize	=	sizeof(struct s390_des_ctx),
+	.base.cra_module	=	THIS_MODULE,
+	.min_keysize		=	DES3_KEY_SIZE,
+	.max_keysize		=	DES3_KEY_SIZE,
+	.setkey			=	des3_setkey_skcipher,
+	.encrypt		=	ecb_des3_encrypt,
+	.decrypt		=	ecb_des3_decrypt,
 };
 
-static int cbc_des3_encrypt(struct blkcipher_desc *desc,
-			    struct scatterlist *dst, struct scatterlist *src,
-			    unsigned int nbytes)
+static int cbc_des3_encrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, CPACF_KMC_TDEA_192, &walk);
+	return cbc_desall_crypt(req, CPACF_KMC_TDEA_192);
 }
 
-static int cbc_des3_decrypt(struct blkcipher_desc *desc,
-			    struct scatterlist *dst, struct scatterlist *src,
-			    unsigned int nbytes)
+static int cbc_des3_decrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, CPACF_KMC_TDEA_192 | CPACF_DECRYPT,
-				&walk);
+	return cbc_desall_crypt(req, CPACF_KMC_TDEA_192 | CPACF_DECRYPT);
 }
 
-static struct crypto_alg cbc_des3_alg = {
-	.cra_name		=	"cbc(des3_ede)",
-	.cra_driver_name	=	"cbc-des3_ede-s390",
-	.cra_priority		=	400,	/* combo: des3 + cbc */
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	DES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct s390_des_ctx),
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	DES3_KEY_SIZE,
-			.max_keysize		=	DES3_KEY_SIZE,
-			.ivsize			=	DES_BLOCK_SIZE,
-			.setkey			=	des3_setkey,
-			.encrypt		=	cbc_des3_encrypt,
-			.decrypt		=	cbc_des3_decrypt,
-		}
-	}
+static struct skcipher_alg cbc_des3_alg = {
+	.base.cra_name		=	"cbc(des3_ede)",
+	.base.cra_driver_name	=	"cbc-des3_ede-s390",
+	.base.cra_priority	=	400,	/* combo: des3 + cbc */
+	.base.cra_blocksize	=	DES_BLOCK_SIZE,
+	.base.cra_ctxsize	=	sizeof(struct s390_des_ctx),
+	.base.cra_module	=	THIS_MODULE,
+	.min_keysize		=	DES3_KEY_SIZE,
+	.max_keysize		=	DES3_KEY_SIZE,
+	.ivsize			=	DES_BLOCK_SIZE,
+	.setkey			=	des3_setkey_skcipher,
+	.encrypt		=	cbc_des3_encrypt,
+	.decrypt		=	cbc_des3_decrypt,
 };
 
 static unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes)
@@ -364,128 +315,90 @@ static unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes)
 	return n;
 }
 
-static int ctr_desall_crypt(struct blkcipher_desc *desc, unsigned long fc,
-			    struct blkcipher_walk *walk)
+static int ctr_desall_crypt(struct skcipher_request *req, unsigned long fc)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_des_ctx *ctx = crypto_skcipher_ctx(tfm);
 	u8 buf[DES_BLOCK_SIZE], *ctrptr;
+	struct skcipher_walk walk;
 	unsigned int n, nbytes;
 	int ret, locked;
 
 	locked = mutex_trylock(&ctrblk_lock);
 
-	ret = blkcipher_walk_virt_block(desc, walk, DES_BLOCK_SIZE);
-	while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) {
+	ret = skcipher_walk_virt(&walk, req, false);
+	while ((nbytes = walk.nbytes) >= DES_BLOCK_SIZE) {
 		n = DES_BLOCK_SIZE;
 		if (nbytes >= 2*DES_BLOCK_SIZE && locked)
-			n = __ctrblk_init(ctrblk, walk->iv, nbytes);
-		ctrptr = (n > DES_BLOCK_SIZE) ? ctrblk : walk->iv;
-		cpacf_kmctr(fc, ctx->key, walk->dst.virt.addr,
-			    walk->src.virt.addr, n, ctrptr);
+			n = __ctrblk_init(ctrblk, walk.iv, nbytes);
+		ctrptr = (n > DES_BLOCK_SIZE) ? ctrblk : walk.iv;
+		cpacf_kmctr(fc, ctx->key, walk.dst.virt.addr,
+			    walk.src.virt.addr, n, ctrptr);
 		if (ctrptr == ctrblk)
-			memcpy(walk->iv, ctrptr + n - DES_BLOCK_SIZE,
+			memcpy(walk.iv, ctrptr + n - DES_BLOCK_SIZE,
 				DES_BLOCK_SIZE);
-		crypto_inc(walk->iv, DES_BLOCK_SIZE);
-		ret = blkcipher_walk_done(desc, walk, nbytes - n);
+		crypto_inc(walk.iv, DES_BLOCK_SIZE);
+		ret = skcipher_walk_done(&walk, nbytes - n);
 	}
 	if (locked)
 		mutex_unlock(&ctrblk_lock);
 	/* final block may be < DES_BLOCK_SIZE, copy only nbytes */
 	if (nbytes) {
-		cpacf_kmctr(fc, ctx->key, buf, walk->src.virt.addr,
-			    DES_BLOCK_SIZE, walk->iv);
-		memcpy(walk->dst.virt.addr, buf, nbytes);
-		crypto_inc(walk->iv, DES_BLOCK_SIZE);
-		ret = blkcipher_walk_done(desc, walk, 0);
+		cpacf_kmctr(fc, ctx->key, buf, walk.src.virt.addr,
+			    DES_BLOCK_SIZE, walk.iv);
+		memcpy(walk.dst.virt.addr, buf, nbytes);
+		crypto_inc(walk.iv, DES_BLOCK_SIZE);
+		ret = skcipher_walk_done(&walk, 0);
 	}
 	return ret;
 }
 
-static int ctr_des_encrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
-{
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ctr_desall_crypt(desc, CPACF_KMCTR_DEA, &walk);
-}
-
-static int ctr_des_decrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
+static int ctr_des_crypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ctr_desall_crypt(desc, CPACF_KMCTR_DEA | CPACF_DECRYPT, &walk);
+	return ctr_desall_crypt(req, CPACF_KMCTR_DEA);
 }
 
-static struct crypto_alg ctr_des_alg = {
-	.cra_name		=	"ctr(des)",
-	.cra_driver_name	=	"ctr-des-s390",
-	.cra_priority		=	400,	/* combo: des + ctr */
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	1,
-	.cra_ctxsize		=	sizeof(struct s390_des_ctx),
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	DES_KEY_SIZE,
-			.max_keysize		=	DES_KEY_SIZE,
-			.ivsize			=	DES_BLOCK_SIZE,
-			.setkey			=	des_setkey,
-			.encrypt		=	ctr_des_encrypt,
-			.decrypt		=	ctr_des_decrypt,
-		}
-	}
+static struct skcipher_alg ctr_des_alg = {
+	.base.cra_name		=	"ctr(des)",
+	.base.cra_driver_name	=	"ctr-des-s390",
+	.base.cra_priority	=	400,	/* combo: des + ctr */
+	.base.cra_blocksize	=	1,
+	.base.cra_ctxsize	=	sizeof(struct s390_des_ctx),
+	.base.cra_module	=	THIS_MODULE,
+	.min_keysize		=	DES_KEY_SIZE,
+	.max_keysize		=	DES_KEY_SIZE,
+	.ivsize			=	DES_BLOCK_SIZE,
+	.setkey			=	des_setkey_skcipher,
+	.encrypt		=	ctr_des_crypt,
+	.decrypt		=	ctr_des_crypt,
+	.chunksize		=	DES_BLOCK_SIZE,
 };
 
-static int ctr_des3_encrypt(struct blkcipher_desc *desc,
-			    struct scatterlist *dst, struct scatterlist *src,
-			    unsigned int nbytes)
-{
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ctr_desall_crypt(desc, CPACF_KMCTR_TDEA_192, &walk);
-}
-
-static int ctr_des3_decrypt(struct blkcipher_desc *desc,
-			    struct scatterlist *dst, struct scatterlist *src,
-			    unsigned int nbytes)
+static int ctr_des3_crypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ctr_desall_crypt(desc, CPACF_KMCTR_TDEA_192 | CPACF_DECRYPT,
-				&walk);
+	return ctr_desall_crypt(req, CPACF_KMCTR_TDEA_192);
 }
 
-static struct crypto_alg ctr_des3_alg = {
-	.cra_name		=	"ctr(des3_ede)",
-	.cra_driver_name	=	"ctr-des3_ede-s390",
-	.cra_priority		=	400,	/* combo: des3 + ede */
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	1,
-	.cra_ctxsize		=	sizeof(struct s390_des_ctx),
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	DES3_KEY_SIZE,
-			.max_keysize		=	DES3_KEY_SIZE,
-			.ivsize			=	DES_BLOCK_SIZE,
-			.setkey			=	des3_setkey,
-			.encrypt		=	ctr_des3_encrypt,
-			.decrypt		=	ctr_des3_decrypt,
-		}
-	}
+static struct skcipher_alg ctr_des3_alg = {
+	.base.cra_name		=	"ctr(des3_ede)",
+	.base.cra_driver_name	=	"ctr-des3_ede-s390",
+	.base.cra_priority	=	400,	/* combo: des3 + ede */
+	.base.cra_blocksize	=	1,
+	.base.cra_ctxsize	=	sizeof(struct s390_des_ctx),
+	.base.cra_module	=	THIS_MODULE,
+	.min_keysize		=	DES3_KEY_SIZE,
+	.max_keysize		=	DES3_KEY_SIZE,
+	.ivsize			=	DES_BLOCK_SIZE,
+	.setkey			=	des3_setkey_skcipher,
+	.encrypt		=	ctr_des3_crypt,
+	.decrypt		=	ctr_des3_crypt,
+	.chunksize		=	DES_BLOCK_SIZE,
 };
 
-static struct crypto_alg *des_s390_algs_ptr[8];
+static struct crypto_alg *des_s390_algs_ptr[2];
 static int des_s390_algs_num;
+static struct skcipher_alg *des_s390_skciphers_ptr[6];
+static int des_s390_skciphers_num;
 
 static int des_s390_register_alg(struct crypto_alg *alg)
 {
@@ -497,10 +410,22 @@ static int des_s390_register_alg(struct crypto_alg *alg)
 	return ret;
 }
 
+static int des_s390_register_skcipher(struct skcipher_alg *alg)
+{
+	int ret;
+
+	ret = crypto_register_skcipher(alg);
+	if (!ret)
+		des_s390_skciphers_ptr[des_s390_skciphers_num++] = alg;
+	return ret;
+}
+
 static void des_s390_exit(void)
 {
 	while (des_s390_algs_num--)
 		crypto_unregister_alg(des_s390_algs_ptr[des_s390_algs_num]);
+	while (des_s390_skciphers_num--)
+		crypto_unregister_skcipher(des_s390_skciphers_ptr[des_s390_skciphers_num]);
 	if (ctrblk)
 		free_page((unsigned long) ctrblk);
 }
@@ -518,12 +443,12 @@ static int __init des_s390_init(void)
 		ret = des_s390_register_alg(&des_alg);
 		if (ret)
 			goto out_err;
-		ret = des_s390_register_alg(&ecb_des_alg);
+		ret = des_s390_register_skcipher(&ecb_des_alg);
 		if (ret)
 			goto out_err;
 	}
 	if (cpacf_test_func(&kmc_functions, CPACF_KMC_DEA)) {
-		ret = des_s390_register_alg(&cbc_des_alg);
+		ret = des_s390_register_skcipher(&cbc_des_alg);
 		if (ret)
 			goto out_err;
 	}
@@ -531,12 +456,12 @@ static int __init des_s390_init(void)
 		ret = des_s390_register_alg(&des3_alg);
 		if (ret)
 			goto out_err;
-		ret = des_s390_register_alg(&ecb_des3_alg);
+		ret = des_s390_register_skcipher(&ecb_des3_alg);
 		if (ret)
 			goto out_err;
 	}
 	if (cpacf_test_func(&kmc_functions, CPACF_KMC_TDEA_192)) {
-		ret = des_s390_register_alg(&cbc_des3_alg);
+		ret = des_s390_register_skcipher(&cbc_des3_alg);
 		if (ret)
 			goto out_err;
 	}
@@ -551,12 +476,12 @@ static int __init des_s390_init(void)
 	}
 
 	if (cpacf_test_func(&kmctr_functions, CPACF_KMCTR_DEA)) {
-		ret = des_s390_register_alg(&ctr_des_alg);
+		ret = des_s390_register_skcipher(&ctr_des_alg);
 		if (ret)
 			goto out_err;
 	}
 	if (cpacf_test_func(&kmctr_functions, CPACF_KMCTR_TDEA_192)) {
-		ret = des_s390_register_alg(&ctr_des3_alg);
+		ret = des_s390_register_skcipher(&ctr_des3_alg);
 		if (ret)
 			goto out_err;
 	}
diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c
index 6184dceed340..c7119c617b6e 100644
--- a/arch/s390/crypto/paes_s390.c
+++ b/arch/s390/crypto/paes_s390.c
@@ -21,6 +21,7 @@
 #include <linux/cpufeature.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
+#include <crypto/internal/skcipher.h>
 #include <crypto/xts.h>
 #include <asm/cpacf.h>
 #include <asm/pkey.h>
@@ -123,27 +124,27 @@ static int __paes_set_key(struct s390_paes_ctx *ctx)
 	return ctx->fc ? 0 : -EINVAL;
 }
 
-static int ecb_paes_init(struct crypto_tfm *tfm)
+static int ecb_paes_init(struct crypto_skcipher *tfm)
 {
-	struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	ctx->kb.key = NULL;
 
 	return 0;
 }
 
-static void ecb_paes_exit(struct crypto_tfm *tfm)
+static void ecb_paes_exit(struct crypto_skcipher *tfm)
 {
-	struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	_free_kb_keybuf(&ctx->kb);
 }
 
-static int ecb_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+static int ecb_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
 			    unsigned int key_len)
 {
 	int rc;
-	struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	_free_kb_keybuf(&ctx->kb);
 	rc = _copy_key_to_kb(&ctx->kb, in_key, key_len);
@@ -151,91 +152,75 @@ static int ecb_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 		return rc;
 
 	if (__paes_set_key(ctx)) {
-		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 	return 0;
 }
 
-static int ecb_paes_crypt(struct blkcipher_desc *desc,
-			  unsigned long modifier,
-			  struct blkcipher_walk *walk)
+static int ecb_paes_crypt(struct skcipher_request *req, unsigned long modifier)
 {
-	struct s390_paes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
 	unsigned int nbytes, n, k;
 	int ret;
 
-	ret = blkcipher_walk_virt(desc, walk);
-	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
+	ret = skcipher_walk_virt(&walk, req, false);
+	while ((nbytes = walk.nbytes) != 0) {
 		/* only use complete blocks */
 		n = nbytes & ~(AES_BLOCK_SIZE - 1);
 		k = cpacf_km(ctx->fc | modifier, ctx->pk.protkey,
-			     walk->dst.virt.addr, walk->src.virt.addr, n);
+			     walk.dst.virt.addr, walk.src.virt.addr, n);
 		if (k)
-			ret = blkcipher_walk_done(desc, walk, nbytes - k);
+			ret = skcipher_walk_done(&walk, nbytes - k);
 		if (k < n) {
 			if (__paes_set_key(ctx) != 0)
-				return blkcipher_walk_done(desc, walk, -EIO);
+				return skcipher_walk_done(&walk, -EIO);
 		}
 	}
 	return ret;
 }
 
-static int ecb_paes_encrypt(struct blkcipher_desc *desc,
-			    struct scatterlist *dst, struct scatterlist *src,
-			    unsigned int nbytes)
+static int ecb_paes_encrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_paes_crypt(desc, CPACF_ENCRYPT, &walk);
+	return ecb_paes_crypt(req, 0);
 }
 
-static int ecb_paes_decrypt(struct blkcipher_desc *desc,
-			    struct scatterlist *dst, struct scatterlist *src,
-			    unsigned int nbytes)
+static int ecb_paes_decrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_paes_crypt(desc, CPACF_DECRYPT, &walk);
+	return ecb_paes_crypt(req, CPACF_DECRYPT);
 }
 
-static struct crypto_alg ecb_paes_alg = {
-	.cra_name		=	"ecb(paes)",
-	.cra_driver_name	=	"ecb-paes-s390",
-	.cra_priority		=	401,	/* combo: aes + ecb + 1 */
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct s390_paes_ctx),
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_list		=	LIST_HEAD_INIT(ecb_paes_alg.cra_list),
-	.cra_init		=	ecb_paes_init,
-	.cra_exit		=	ecb_paes_exit,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	PAES_MIN_KEYSIZE,
-			.max_keysize		=	PAES_MAX_KEYSIZE,
-			.setkey			=	ecb_paes_set_key,
-			.encrypt		=	ecb_paes_encrypt,
-			.decrypt		=	ecb_paes_decrypt,
-		}
-	}
+static struct skcipher_alg ecb_paes_alg = {
+	.base.cra_name		=	"ecb(paes)",
+	.base.cra_driver_name	=	"ecb-paes-s390",
+	.base.cra_priority	=	401,	/* combo: aes + ecb + 1 */
+	.base.cra_blocksize	=	AES_BLOCK_SIZE,
+	.base.cra_ctxsize	=	sizeof(struct s390_paes_ctx),
+	.base.cra_module	=	THIS_MODULE,
+	.base.cra_list		=	LIST_HEAD_INIT(ecb_paes_alg.base.cra_list),
+	.init			=	ecb_paes_init,
+	.exit			=	ecb_paes_exit,
+	.min_keysize		=	PAES_MIN_KEYSIZE,
+	.max_keysize		=	PAES_MAX_KEYSIZE,
+	.setkey			=	ecb_paes_set_key,
+	.encrypt		=	ecb_paes_encrypt,
+	.decrypt		=	ecb_paes_decrypt,
 };
 
-static int cbc_paes_init(struct crypto_tfm *tfm)
+static int cbc_paes_init(struct crypto_skcipher *tfm)
 {
-	struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	ctx->kb.key = NULL;
 
 	return 0;
 }
 
-static void cbc_paes_exit(struct crypto_tfm *tfm)
+static void cbc_paes_exit(struct crypto_skcipher *tfm)
 {
-	struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	_free_kb_keybuf(&ctx->kb);
 }
@@ -258,11 +243,11 @@ static int __cbc_paes_set_key(struct s390_paes_ctx *ctx)
 	return ctx->fc ? 0 : -EINVAL;
 }
 
-static int cbc_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+static int cbc_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
 			    unsigned int key_len)
 {
 	int rc;
-	struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	_free_kb_keybuf(&ctx->kb);
 	rc = _copy_key_to_kb(&ctx->kb, in_key, key_len);
@@ -270,16 +255,17 @@ static int cbc_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 		return rc;
 
 	if (__cbc_paes_set_key(ctx)) {
-		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 	return 0;
 }
 
-static int cbc_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
-			  struct blkcipher_walk *walk)
+static int cbc_paes_crypt(struct skcipher_request *req, unsigned long modifier)
 {
-	struct s390_paes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
 	unsigned int nbytes, n, k;
 	int ret;
 	struct {
@@ -287,73 +273,60 @@ static int cbc_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
 		u8 key[MAXPROTKEYSIZE];
 	} param;
 
-	ret = blkcipher_walk_virt(desc, walk);
-	memcpy(param.iv, walk->iv, AES_BLOCK_SIZE);
+	ret = skcipher_walk_virt(&walk, req, false);
+	if (ret)
+		return ret;
+	memcpy(param.iv, walk.iv, AES_BLOCK_SIZE);
 	memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE);
-	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
+	while ((nbytes = walk.nbytes) != 0) {
 		/* only use complete blocks */
 		n = nbytes & ~(AES_BLOCK_SIZE - 1);
 		k = cpacf_kmc(ctx->fc | modifier, &param,
-			      walk->dst.virt.addr, walk->src.virt.addr, n);
-		if (k)
-			ret = blkcipher_walk_done(desc, walk, nbytes - k);
+			      walk.dst.virt.addr, walk.src.virt.addr, n);
+		if (k) {
+			memcpy(walk.iv, param.iv, AES_BLOCK_SIZE);
+			ret = skcipher_walk_done(&walk, nbytes - k);
+		}
 		if (k < n) {
 			if (__cbc_paes_set_key(ctx) != 0)
-				return blkcipher_walk_done(desc, walk, -EIO);
+				return skcipher_walk_done(&walk, -EIO);
 			memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE);
 		}
 	}
-	memcpy(walk->iv, param.iv, AES_BLOCK_SIZE);
 	return ret;
 }
 
-static int cbc_paes_encrypt(struct blkcipher_desc *desc,
-			    struct scatterlist *dst, struct scatterlist *src,
-			    unsigned int nbytes)
+static int cbc_paes_encrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_paes_crypt(desc, 0, &walk);
+	return cbc_paes_crypt(req, 0);
 }
 
-static int cbc_paes_decrypt(struct blkcipher_desc *desc,
-			    struct scatterlist *dst, struct scatterlist *src,
-			    unsigned int nbytes)
+static int cbc_paes_decrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_paes_crypt(desc, CPACF_DECRYPT, &walk);
+	return cbc_paes_crypt(req, CPACF_DECRYPT);
 }
 
-static struct crypto_alg cbc_paes_alg = {
-	.cra_name		=	"cbc(paes)",
-	.cra_driver_name	=	"cbc-paes-s390",
-	.cra_priority		=	402,	/* ecb-paes-s390 + 1 */
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct s390_paes_ctx),
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_list		=	LIST_HEAD_INIT(cbc_paes_alg.cra_list),
-	.cra_init		=	cbc_paes_init,
-	.cra_exit		=	cbc_paes_exit,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	PAES_MIN_KEYSIZE,
-			.max_keysize		=	PAES_MAX_KEYSIZE,
-			.ivsize			=	AES_BLOCK_SIZE,
-			.setkey			=	cbc_paes_set_key,
-			.encrypt		=	cbc_paes_encrypt,
-			.decrypt		=	cbc_paes_decrypt,
-		}
-	}
+static struct skcipher_alg cbc_paes_alg = {
+	.base.cra_name		=	"cbc(paes)",
+	.base.cra_driver_name	=	"cbc-paes-s390",
+	.base.cra_priority	=	402,	/* ecb-paes-s390 + 1 */
+	.base.cra_blocksize	=	AES_BLOCK_SIZE,
+	.base.cra_ctxsize	=	sizeof(struct s390_paes_ctx),
+	.base.cra_module	=	THIS_MODULE,
+	.base.cra_list		=	LIST_HEAD_INIT(cbc_paes_alg.base.cra_list),
+	.init			=	cbc_paes_init,
+	.exit			=	cbc_paes_exit,
+	.min_keysize		=	PAES_MIN_KEYSIZE,
+	.max_keysize		=	PAES_MAX_KEYSIZE,
+	.ivsize			=	AES_BLOCK_SIZE,
+	.setkey			=	cbc_paes_set_key,
+	.encrypt		=	cbc_paes_encrypt,
+	.decrypt		=	cbc_paes_decrypt,
 };
 
-static int xts_paes_init(struct crypto_tfm *tfm)
+static int xts_paes_init(struct crypto_skcipher *tfm)
 {
-	struct s390_pxts_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	ctx->kb[0].key = NULL;
 	ctx->kb[1].key = NULL;
@@ -361,9 +334,9 @@ static int xts_paes_init(struct crypto_tfm *tfm)
 	return 0;
 }
 
-static void xts_paes_exit(struct crypto_tfm *tfm)
+static void xts_paes_exit(struct crypto_skcipher *tfm)
 {
-	struct s390_pxts_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	_free_kb_keybuf(&ctx->kb[0]);
 	_free_kb_keybuf(&ctx->kb[1]);
@@ -391,11 +364,11 @@ static int __xts_paes_set_key(struct s390_pxts_ctx *ctx)
 	return ctx->fc ? 0 : -EINVAL;
 }
 
-static int xts_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+static int xts_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
 			    unsigned int xts_key_len)
 {
 	int rc;
-	struct s390_pxts_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm);
 	u8 ckey[2 * AES_MAX_KEY_SIZE];
 	unsigned int ckey_len, key_len;
 
@@ -414,7 +387,7 @@ static int xts_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 		return rc;
 
 	if (__xts_paes_set_key(ctx)) {
-		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
@@ -427,13 +400,14 @@ static int xts_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 		AES_KEYSIZE_128 : AES_KEYSIZE_256;
 	memcpy(ckey, ctx->pk[0].protkey, ckey_len);
 	memcpy(ckey + ckey_len, ctx->pk[1].protkey, ckey_len);
-	return xts_check_key(tfm, ckey, 2*ckey_len);
+	return xts_verify_key(tfm, ckey, 2*ckey_len);
 }
 
-static int xts_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
-			  struct blkcipher_walk *walk)
+static int xts_paes_crypt(struct skcipher_request *req, unsigned long modifier)
 {
-	struct s390_pxts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
 	unsigned int keylen, offset, nbytes, n, k;
 	int ret;
 	struct {
@@ -448,90 +422,76 @@ static int xts_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
 		u8 init[16];
 	} xts_param;
 
-	ret = blkcipher_walk_virt(desc, walk);
+	ret = skcipher_walk_virt(&walk, req, false);
+	if (ret)
+		return ret;
 	keylen = (ctx->pk[0].type == PKEY_KEYTYPE_AES_128) ? 48 : 64;
 	offset = (ctx->pk[0].type == PKEY_KEYTYPE_AES_128) ? 16 : 0;
 retry:
 	memset(&pcc_param, 0, sizeof(pcc_param));
-	memcpy(pcc_param.tweak, walk->iv, sizeof(pcc_param.tweak));
+	memcpy(pcc_param.tweak, walk.iv, sizeof(pcc_param.tweak));
 	memcpy(pcc_param.key + offset, ctx->pk[1].protkey, keylen);
 	cpacf_pcc(ctx->fc, pcc_param.key + offset);
 
 	memcpy(xts_param.key + offset, ctx->pk[0].protkey, keylen);
 	memcpy(xts_param.init, pcc_param.xts, 16);
 
-	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
+	while ((nbytes = walk.nbytes) != 0) {
 		/* only use complete blocks */
 		n = nbytes & ~(AES_BLOCK_SIZE - 1);
 		k = cpacf_km(ctx->fc | modifier, xts_param.key + offset,
-			     walk->dst.virt.addr, walk->src.virt.addr, n);
+			     walk.dst.virt.addr, walk.src.virt.addr, n);
 		if (k)
-			ret = blkcipher_walk_done(desc, walk, nbytes - k);
+			ret = skcipher_walk_done(&walk, nbytes - k);
 		if (k < n) {
 			if (__xts_paes_set_key(ctx) != 0)
-				return blkcipher_walk_done(desc, walk, -EIO);
+				return skcipher_walk_done(&walk, -EIO);
 			goto retry;
 		}
 	}
 	return ret;
 }
 
-static int xts_paes_encrypt(struct blkcipher_desc *desc,
-			    struct scatterlist *dst, struct scatterlist *src,
-			    unsigned int nbytes)
+static int xts_paes_encrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return xts_paes_crypt(desc, 0, &walk);
+	return xts_paes_crypt(req, 0);
 }
 
-static int xts_paes_decrypt(struct blkcipher_desc *desc,
-			    struct scatterlist *dst, struct scatterlist *src,
-			    unsigned int nbytes)
+static int xts_paes_decrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return xts_paes_crypt(desc, CPACF_DECRYPT, &walk);
+	return xts_paes_crypt(req, CPACF_DECRYPT);
 }
 
-static struct crypto_alg xts_paes_alg = {
-	.cra_name		=	"xts(paes)",
-	.cra_driver_name	=	"xts-paes-s390",
-	.cra_priority		=	402,	/* ecb-paes-s390 + 1 */
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct s390_pxts_ctx),
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_list		=	LIST_HEAD_INIT(xts_paes_alg.cra_list),
-	.cra_init		=	xts_paes_init,
-	.cra_exit		=	xts_paes_exit,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	2 * PAES_MIN_KEYSIZE,
-			.max_keysize		=	2 * PAES_MAX_KEYSIZE,
-			.ivsize			=	AES_BLOCK_SIZE,
-			.setkey			=	xts_paes_set_key,
-			.encrypt		=	xts_paes_encrypt,
-			.decrypt		=	xts_paes_decrypt,
-		}
-	}
+static struct skcipher_alg xts_paes_alg = {
+	.base.cra_name		=	"xts(paes)",
+	.base.cra_driver_name	=	"xts-paes-s390",
+	.base.cra_priority	=	402,	/* ecb-paes-s390 + 1 */
+	.base.cra_blocksize	=	AES_BLOCK_SIZE,
+	.base.cra_ctxsize	=	sizeof(struct s390_pxts_ctx),
+	.base.cra_module	=	THIS_MODULE,
+	.base.cra_list		=	LIST_HEAD_INIT(xts_paes_alg.base.cra_list),
+	.init			=	xts_paes_init,
+	.exit			=	xts_paes_exit,
+	.min_keysize		=	2 * PAES_MIN_KEYSIZE,
+	.max_keysize		=	2 * PAES_MAX_KEYSIZE,
+	.ivsize			=	AES_BLOCK_SIZE,
+	.setkey			=	xts_paes_set_key,
+	.encrypt		=	xts_paes_encrypt,
+	.decrypt		=	xts_paes_decrypt,
 };
 
-static int ctr_paes_init(struct crypto_tfm *tfm)
+static int ctr_paes_init(struct crypto_skcipher *tfm)
 {
-	struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	ctx->kb.key = NULL;
 
 	return 0;
 }
 
-static void ctr_paes_exit(struct crypto_tfm *tfm)
+static void ctr_paes_exit(struct crypto_skcipher *tfm)
 {
-	struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	_free_kb_keybuf(&ctx->kb);
 }
@@ -555,11 +515,11 @@ static int __ctr_paes_set_key(struct s390_paes_ctx *ctx)
 	return ctx->fc ? 0 : -EINVAL;
 }
 
-static int ctr_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+static int ctr_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
 			    unsigned int key_len)
 {
 	int rc;
-	struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	_free_kb_keybuf(&ctx->kb);
 	rc = _copy_key_to_kb(&ctx->kb, in_key, key_len);
@@ -567,7 +527,7 @@ static int ctr_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 		return rc;
 
 	if (__ctr_paes_set_key(ctx)) {
-		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 	return 0;
@@ -588,37 +548,37 @@ static unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes)
 	return n;
 }
 
-static int ctr_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
-			  struct blkcipher_walk *walk)
+static int ctr_paes_crypt(struct skcipher_request *req)
 {
-	struct s390_paes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 	u8 buf[AES_BLOCK_SIZE], *ctrptr;
+	struct skcipher_walk walk;
 	unsigned int nbytes, n, k;
 	int ret, locked;
 
 	locked = spin_trylock(&ctrblk_lock);
 
-	ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE);
-	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
+	ret = skcipher_walk_virt(&walk, req, false);
+	while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
 		n = AES_BLOCK_SIZE;
 		if (nbytes >= 2*AES_BLOCK_SIZE && locked)
-			n = __ctrblk_init(ctrblk, walk->iv, nbytes);
-		ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk->iv;
-		k = cpacf_kmctr(ctx->fc | modifier, ctx->pk.protkey,
-				walk->dst.virt.addr, walk->src.virt.addr,
-				n, ctrptr);
+			n = __ctrblk_init(ctrblk, walk.iv, nbytes);
+		ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk.iv;
+		k = cpacf_kmctr(ctx->fc, ctx->pk.protkey, walk.dst.virt.addr,
+				walk.src.virt.addr, n, ctrptr);
 		if (k) {
 			if (ctrptr == ctrblk)
-				memcpy(walk->iv, ctrptr + k - AES_BLOCK_SIZE,
+				memcpy(walk.iv, ctrptr + k - AES_BLOCK_SIZE,
 				       AES_BLOCK_SIZE);
-			crypto_inc(walk->iv, AES_BLOCK_SIZE);
-			ret = blkcipher_walk_done(desc, walk, nbytes - n);
+			crypto_inc(walk.iv, AES_BLOCK_SIZE);
+			ret = skcipher_walk_done(&walk, nbytes - n);
 		}
 		if (k < n) {
 			if (__ctr_paes_set_key(ctx) != 0) {
 				if (locked)
 					spin_unlock(&ctrblk_lock);
-				return blkcipher_walk_done(desc, walk, -EIO);
+				return skcipher_walk_done(&walk, -EIO);
 			}
 		}
 	}
@@ -629,80 +589,54 @@ static int ctr_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
 	 */
 	if (nbytes) {
 		while (1) {
-			if (cpacf_kmctr(ctx->fc | modifier,
-					ctx->pk.protkey, buf,
-					walk->src.virt.addr, AES_BLOCK_SIZE,
-					walk->iv) == AES_BLOCK_SIZE)
+			if (cpacf_kmctr(ctx->fc, ctx->pk.protkey, buf,
+					walk.src.virt.addr, AES_BLOCK_SIZE,
+					walk.iv) == AES_BLOCK_SIZE)
 				break;
 			if (__ctr_paes_set_key(ctx) != 0)
-				return blkcipher_walk_done(desc, walk, -EIO);
+				return skcipher_walk_done(&walk, -EIO);
 		}
-		memcpy(walk->dst.virt.addr, buf, nbytes);
-		crypto_inc(walk->iv, AES_BLOCK_SIZE);
-		ret = blkcipher_walk_done(desc, walk, 0);
+		memcpy(walk.dst.virt.addr, buf, nbytes);
+		crypto_inc(walk.iv, AES_BLOCK_SIZE);
+		ret = skcipher_walk_done(&walk, 0);
 	}
 
 	return ret;
 }
 
-static int ctr_paes_encrypt(struct blkcipher_desc *desc,
-			    struct scatterlist *dst, struct scatterlist *src,
-			    unsigned int nbytes)
-{
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ctr_paes_crypt(desc, 0, &walk);
-}
-
-static int ctr_paes_decrypt(struct blkcipher_desc *desc,
-			    struct scatterlist *dst, struct scatterlist *src,
-			    unsigned int nbytes)
-{
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ctr_paes_crypt(desc, CPACF_DECRYPT, &walk);
-}
-
-static struct crypto_alg ctr_paes_alg = {
-	.cra_name		=	"ctr(paes)",
-	.cra_driver_name	=	"ctr-paes-s390",
-	.cra_priority		=	402,	/* ecb-paes-s390 + 1 */
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	1,
-	.cra_ctxsize		=	sizeof(struct s390_paes_ctx),
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_list		=	LIST_HEAD_INIT(ctr_paes_alg.cra_list),
-	.cra_init		=	ctr_paes_init,
-	.cra_exit		=	ctr_paes_exit,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	PAES_MIN_KEYSIZE,
-			.max_keysize		=	PAES_MAX_KEYSIZE,
-			.ivsize			=	AES_BLOCK_SIZE,
-			.setkey			=	ctr_paes_set_key,
-			.encrypt		=	ctr_paes_encrypt,
-			.decrypt		=	ctr_paes_decrypt,
-		}
-	}
+static struct skcipher_alg ctr_paes_alg = {
+	.base.cra_name		=	"ctr(paes)",
+	.base.cra_driver_name	=	"ctr-paes-s390",
+	.base.cra_priority	=	402,	/* ecb-paes-s390 + 1 */
+	.base.cra_blocksize	=	1,
+	.base.cra_ctxsize	=	sizeof(struct s390_paes_ctx),
+	.base.cra_module	=	THIS_MODULE,
+	.base.cra_list		=	LIST_HEAD_INIT(ctr_paes_alg.base.cra_list),
+	.init			=	ctr_paes_init,
+	.exit			=	ctr_paes_exit,
+	.min_keysize		=	PAES_MIN_KEYSIZE,
+	.max_keysize		=	PAES_MAX_KEYSIZE,
+	.ivsize			=	AES_BLOCK_SIZE,
+	.setkey			=	ctr_paes_set_key,
+	.encrypt		=	ctr_paes_crypt,
+	.decrypt		=	ctr_paes_crypt,
+	.chunksize		=	AES_BLOCK_SIZE,
 };
 
-static inline void __crypto_unregister_alg(struct crypto_alg *alg)
+static inline void __crypto_unregister_skcipher(struct skcipher_alg *alg)
 {
-	if (!list_empty(&alg->cra_list))
-		crypto_unregister_alg(alg);
+	if (!list_empty(&alg->base.cra_list))
+		crypto_unregister_skcipher(alg);
 }
 
 static void paes_s390_fini(void)
 {
 	if (ctrblk)
 		free_page((unsigned long) ctrblk);
-	__crypto_unregister_alg(&ctr_paes_alg);
-	__crypto_unregister_alg(&xts_paes_alg);
-	__crypto_unregister_alg(&cbc_paes_alg);
-	__crypto_unregister_alg(&ecb_paes_alg);
+	__crypto_unregister_skcipher(&ctr_paes_alg);
+	__crypto_unregister_skcipher(&xts_paes_alg);
+	__crypto_unregister_skcipher(&cbc_paes_alg);
+	__crypto_unregister_skcipher(&ecb_paes_alg);
 }
 
 static int __init paes_s390_init(void)
@@ -717,7 +651,7 @@ static int __init paes_s390_init(void)
 	if (cpacf_test_func(&km_functions, CPACF_KM_PAES_128) ||
 	    cpacf_test_func(&km_functions, CPACF_KM_PAES_192) ||
 	    cpacf_test_func(&km_functions, CPACF_KM_PAES_256)) {
-		ret = crypto_register_alg(&ecb_paes_alg);
+		ret = crypto_register_skcipher(&ecb_paes_alg);
 		if (ret)
 			goto out_err;
 	}
@@ -725,14 +659,14 @@ static int __init paes_s390_init(void)
 	if (cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_128) ||
 	    cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_192) ||
 	    cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_256)) {
-		ret = crypto_register_alg(&cbc_paes_alg);
+		ret = crypto_register_skcipher(&cbc_paes_alg);
 		if (ret)
 			goto out_err;
 	}
 
 	if (cpacf_test_func(&km_functions, CPACF_KM_PXTS_128) ||
 	    cpacf_test_func(&km_functions, CPACF_KM_PXTS_256)) {
-		ret = crypto_register_alg(&xts_paes_alg);
+		ret = crypto_register_skcipher(&xts_paes_alg);
 		if (ret)
 			goto out_err;
 	}
@@ -740,7 +674,7 @@ static int __init paes_s390_init(void)
 	if (cpacf_test_func(&kmctr_functions, CPACF_KMCTR_PAES_128) ||
 	    cpacf_test_func(&kmctr_functions, CPACF_KMCTR_PAES_192) ||
 	    cpacf_test_func(&kmctr_functions, CPACF_KMCTR_PAES_256)) {
-		ret = crypto_register_alg(&ctr_paes_alg);
+		ret = crypto_register_skcipher(&ctr_paes_alg);
 		if (ret)
 			goto out_err;
 		ctrblk = (u8 *) __get_free_page(GFP_KERNEL);
diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c
index d39e0f079217..686fe7aa192f 100644
--- a/arch/s390/crypto/sha_common.c
+++ b/arch/s390/crypto/sha_common.c
@@ -74,14 +74,17 @@ int s390_sha_final(struct shash_desc *desc, u8 *out)
 	struct s390_sha_ctx *ctx = shash_desc_ctx(desc);
 	unsigned int bsize = crypto_shash_blocksize(desc->tfm);
 	u64 bits;
-	unsigned int n, mbl_offset;
+	unsigned int n;
+	int mbl_offset;
 
 	n = ctx->count % bsize;
 	bits = ctx->count * 8;
-	mbl_offset = s390_crypto_shash_parmsize(ctx->func) / sizeof(u32);
+	mbl_offset = s390_crypto_shash_parmsize(ctx->func);
 	if (mbl_offset < 0)
 		return -EINVAL;
 
+	mbl_offset = mbl_offset / sizeof(u32);
+
 	/* set total msg bit length (mbl) in CPACF parmblock */
 	switch (ctx->func) {
 	case CPACF_KLMD_SHA_1:
diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h
index c2cf7bcdef9b..1c8a38f762a3 100644
--- a/arch/s390/include/asm/alternative.h
+++ b/arch/s390/include/asm/alternative.h
@@ -139,10 +139,10 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
  * without volatile and memory clobber.
  */
 #define alternative(oldinstr, altinstr, facility)			\
-	asm volatile(ALTERNATIVE(oldinstr, altinstr, facility) : : : "memory")
+	asm_inline volatile(ALTERNATIVE(oldinstr, altinstr, facility) : : : "memory")
 
 #define alternative_2(oldinstr, altinstr1, facility1, altinstr2, facility2) \
-	asm volatile(ALTERNATIVE_2(oldinstr, altinstr1, facility1,	    \
+	asm_inline volatile(ALTERNATIVE_2(oldinstr, altinstr1, facility1,   \
 				   altinstr2, facility2) ::: "memory")
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h
index 713fc9735ffb..a2b11ac00f60 100644
--- a/arch/s390/include/asm/bug.h
+++ b/arch/s390/include/asm/bug.h
@@ -9,7 +9,7 @@
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 
 #define __EMIT_BUG(x) do {					\
-	asm volatile(						\
+	asm_inline volatile(					\
 		"0:	j	0b+2\n"				\
 		"1:\n"						\
 		".section .rodata.str,\"aMS\",@progbits,1\n"	\
@@ -28,7 +28,7 @@
 #else /* CONFIG_DEBUG_BUGVERBOSE */
 
 #define __EMIT_BUG(x) do {					\
-	asm volatile(						\
+	asm_inline volatile(					\
 		"0:	j	0b+2\n"				\
 		"1:\n"						\
 		".section __bug_table,\"awM\",@progbits,%1\n"	\
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index 60f907516335..ed5efbb531c4 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -11,6 +11,7 @@
 #include <linux/bits.h>
 
 #define CR0_CLOCK_COMPARATOR_SIGN	BIT(63 - 10)
+#define CR0_LOW_ADDRESS_PROTECTION	BIT(63 - 35)
 #define CR0_EMERGENCY_SIGNAL_SUBMASK	BIT(63 - 49)
 #define CR0_EXTERNAL_CALL_SUBMASK	BIT(63 - 50)
 #define CR0_CLOCK_COMPARATOR_SUBMASK	BIT(63 - 52)
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index abe60268335d..02f4c21c57f6 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -392,6 +392,7 @@ struct kvm_vcpu_stat {
 	u64 diagnose_10;
 	u64 diagnose_44;
 	u64 diagnose_9c;
+	u64 diagnose_9c_ignored;
 	u64 diagnose_258;
 	u64 diagnose_308;
 	u64 diagnose_500;
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 823578c6b9e2..a4d38092530a 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -177,8 +177,6 @@ static inline int devmem_is_allowed(unsigned long pfn)
 #define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | \
 				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
-#define ARCH_ZONE_DMA_BITS	31
-
 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>
 
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index bccb8f4a63e2..77606c4acd58 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -56,7 +56,12 @@ static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address)
 		crst_table_init(table, _REGION2_ENTRY_EMPTY);
 	return (p4d_t *) table;
 }
-#define p4d_free(mm, p4d) crst_table_free(mm, (unsigned long *) p4d)
+
+static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+	if (!mm_p4d_folded(mm))
+		crst_table_free(mm, (unsigned long *) p4d);
+}
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 {
@@ -65,7 +70,12 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 		crst_table_init(table, _REGION3_ENTRY_EMPTY);
 	return (pud_t *) table;
 }
-#define pud_free(mm, pud) crst_table_free(mm, (unsigned long *) pud)
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	if (!mm_pud_folded(mm))
+		crst_table_free(mm, (unsigned long *) pud);
+}
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 {
@@ -83,6 +93,8 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
+	if (mm_pmd_folded(mm))
+		return;
 	pgtable_pmd_page_dtor(virt_to_page(pmd));
 	crst_table_free(mm, (unsigned long *) pmd);
 }
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 5ff98d76a66c..7b03037a8475 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -266,11 +266,9 @@ static inline int is_module_addr(void *addr)
 #endif
 
 #define _REGION_ENTRY_BITS	 0xfffffffffffff22fUL
-#define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe2fUL
 
 /* Bits in the segment table entry */
 #define _SEGMENT_ENTRY_BITS			0xfffffffffffffe33UL
-#define _SEGMENT_ENTRY_BITS_LARGE		0xfffffffffff0ff33UL
 #define _SEGMENT_ENTRY_HARDWARE_BITS		0xfffffffffffffe30UL
 #define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE	0xfffffffffff00730UL
 #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address	    */
@@ -699,10 +697,8 @@ static inline int pmd_large(pmd_t pmd)
 
 static inline int pmd_bad(pmd_t pmd)
 {
-	if ((pmd_val(pmd) & _SEGMENT_ENTRY_TYPE_MASK) > 0)
+	if ((pmd_val(pmd) & _SEGMENT_ENTRY_TYPE_MASK) > 0 || pmd_large(pmd))
 		return 1;
-	if (pmd_large(pmd))
-		return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0;
 	return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0;
 }
 
@@ -710,12 +706,10 @@ static inline int pud_bad(pud_t pud)
 {
 	unsigned long type = pud_val(pud) & _REGION_ENTRY_TYPE_MASK;
 
-	if (type > _REGION_ENTRY_TYPE_R3)
+	if (type > _REGION_ENTRY_TYPE_R3 || pud_large(pud))
 		return 1;
 	if (type < _REGION_ENTRY_TYPE_R3)
 		return 0;
-	if (pud_large(pud))
-		return (pud_val(pud) & ~_REGION_ENTRY_BITS_LARGE) != 0;
 	return (pud_val(pud) & ~_REGION_ENTRY_BITS) != 0;
 }
 
@@ -758,18 +752,12 @@ static inline int pmd_write(pmd_t pmd)
 
 static inline int pmd_dirty(pmd_t pmd)
 {
-	int dirty = 1;
-	if (pmd_large(pmd))
-		dirty = (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0;
-	return dirty;
+	return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0;
 }
 
 static inline int pmd_young(pmd_t pmd)
 {
-	int young = 1;
-	if (pmd_large(pmd))
-		young = (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0;
-	return young;
+	return (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0;
 }
 
 static inline int pte_present(pte_t pte)
@@ -1173,8 +1161,6 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr);
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t entry)
 {
-	if (!MACHINE_HAS_NX)
-		pte_val(entry) &= ~_PAGE_NOEXEC;
 	if (pte_present(entry))
 		pte_val(entry) &= ~_PAGE_UNUSED;
 	if (mm_has_pgste(mm))
@@ -1191,6 +1177,8 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot)
 {
 	pte_t __pte;
 	pte_val(__pte) = physpage + pgprot_val(pgprot);
+	if (!MACHINE_HAS_NX)
+		pte_val(__pte) &= ~_PAGE_NOEXEC;
 	return pte_mkyoung(__pte);
 }
 
@@ -1297,29 +1285,23 @@ static inline pmd_t pmd_wrprotect(pmd_t pmd)
 static inline pmd_t pmd_mkwrite(pmd_t pmd)
 {
 	pmd_val(pmd) |= _SEGMENT_ENTRY_WRITE;
-	if (pmd_large(pmd) && !(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY))
-		return pmd;
-	pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
+	if (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
 	return pmd;
 }
 
 static inline pmd_t pmd_mkclean(pmd_t pmd)
 {
-	if (pmd_large(pmd)) {
-		pmd_val(pmd) &= ~_SEGMENT_ENTRY_DIRTY;
-		pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
-	}
+	pmd_val(pmd) &= ~_SEGMENT_ENTRY_DIRTY;
+	pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
 	return pmd;
 }
 
 static inline pmd_t pmd_mkdirty(pmd_t pmd)
 {
-	if (pmd_large(pmd)) {
-		pmd_val(pmd) |= _SEGMENT_ENTRY_DIRTY |
-				_SEGMENT_ENTRY_SOFT_DIRTY;
-		if (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE)
-			pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
-	}
+	pmd_val(pmd) |= _SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_SOFT_DIRTY;
+	if (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE)
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
 	return pmd;
 }
 
@@ -1333,29 +1315,23 @@ static inline pud_t pud_wrprotect(pud_t pud)
 static inline pud_t pud_mkwrite(pud_t pud)
 {
 	pud_val(pud) |= _REGION3_ENTRY_WRITE;
-	if (pud_large(pud) && !(pud_val(pud) & _REGION3_ENTRY_DIRTY))
-		return pud;
-	pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
+	if (pud_val(pud) & _REGION3_ENTRY_DIRTY)
+		pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
 	return pud;
 }
 
 static inline pud_t pud_mkclean(pud_t pud)
 {
-	if (pud_large(pud)) {
-		pud_val(pud) &= ~_REGION3_ENTRY_DIRTY;
-		pud_val(pud) |= _REGION_ENTRY_PROTECT;
-	}
+	pud_val(pud) &= ~_REGION3_ENTRY_DIRTY;
+	pud_val(pud) |= _REGION_ENTRY_PROTECT;
 	return pud;
 }
 
 static inline pud_t pud_mkdirty(pud_t pud)
 {
-	if (pud_large(pud)) {
-		pud_val(pud) |= _REGION3_ENTRY_DIRTY |
-				_REGION3_ENTRY_SOFT_DIRTY;
-		if (pud_val(pud) & _REGION3_ENTRY_WRITE)
-			pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
-	}
+	pud_val(pud) |= _REGION3_ENTRY_DIRTY | _REGION3_ENTRY_SOFT_DIRTY;
+	if (pud_val(pud) & _REGION3_ENTRY_WRITE)
+		pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
 	return pud;
 }
 
@@ -1379,38 +1355,29 @@ static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot)
 
 static inline pmd_t pmd_mkyoung(pmd_t pmd)
 {
-	if (pmd_large(pmd)) {
-		pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG;
-		if (pmd_val(pmd) & _SEGMENT_ENTRY_READ)
-			pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID;
-	}
+	pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG;
+	if (pmd_val(pmd) & _SEGMENT_ENTRY_READ)
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID;
 	return pmd;
 }
 
 static inline pmd_t pmd_mkold(pmd_t pmd)
 {
-	if (pmd_large(pmd)) {
-		pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG;
-		pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
-	}
+	pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG;
+	pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
 	return pmd;
 }
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
-	if (pmd_large(pmd)) {
-		pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE |
-			_SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG |
-			_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SOFT_DIRTY;
-		pmd_val(pmd) |= massage_pgprot_pmd(newprot);
-		if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY))
-			pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
-		if (!(pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG))
-			pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
-		return pmd;
-	}
-	pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN;
+	pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE |
+		_SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG |
+		_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SOFT_DIRTY;
 	pmd_val(pmd) |= massage_pgprot_pmd(newprot);
+	if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY))
+		pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
+	if (!(pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG))
+		pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
 	return pmd;
 }
 
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 51a0e4a2dc96..881fc37c11c6 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -206,7 +206,7 @@ unsigned long get_wchan(struct task_struct *p);
 /* Has task runtime instrumentation enabled ? */
 #define is_ri_task(tsk) (!!(tsk)->thread.ri_cb)
 
-static inline unsigned long current_stack_pointer(void)
+static __always_inline unsigned long current_stack_pointer(void)
 {
 	unsigned long sp;
 
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index e3f238e8c611..71e3f0146cda 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -276,6 +276,7 @@ struct qdio_outbuf_state {
 #define CHSC_AC2_MULTI_BUFFER_AVAILABLE	0x0080
 #define CHSC_AC2_MULTI_BUFFER_ENABLED	0x0040
 #define CHSC_AC2_DATA_DIV_AVAILABLE	0x0010
+#define CHSC_AC2_SNIFFER_AVAILABLE	0x0008
 #define CHSC_AC2_DATA_DIV_ENABLED	0x0002
 
 #define CHSC_AC3_FORMAT2_CQ_AVAILABLE	0x8000
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index c02bff33f6c7..3a37172d5398 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -85,7 +85,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lp)
 static inline void arch_spin_unlock(arch_spinlock_t *lp)
 {
 	typecheck(int, lp->lock);
-	asm volatile(
+	asm_inline volatile(
 		ALTERNATIVE("", ".long 0xb2fa0070", 49)	/* NIAI 7 */
 		"	sth	%1,%0\n"
 		: "=Q" (((unsigned short *) &lp->lock)[1])
diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h
index 0ae4bbf7779c..fee40212af11 100644
--- a/arch/s390/include/asm/stacktrace.h
+++ b/arch/s390/include/asm/stacktrace.h
@@ -38,7 +38,7 @@ static inline unsigned long get_stack_pointer(struct task_struct *task,
 {
 	if (regs)
 		return (unsigned long) kernel_stack_pointer(regs);
-	if (task == current)
+	if (!task || task == current)
 		return current_stack_pointer();
 	return (unsigned long) task->thread.ksp;
 }
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 64539c221672..6da8885251d6 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -10,8 +10,9 @@
 #ifndef _ASM_S390_TIMEX_H
 #define _ASM_S390_TIMEX_H
 
-#include <asm/lowcore.h>
+#include <linux/preempt.h>
 #include <linux/time64.h>
+#include <asm/lowcore.h>
 
 /* The value of the TOD clock for 1.1.1970. */
 #define TOD_UNIX_EPOCH 0x7d91048bca000000ULL
@@ -179,22 +180,24 @@ static inline cycles_t get_cycles(void)
 
 int get_phys_clock(unsigned long *clock);
 void init_cpu_timer(void);
-unsigned long long monotonic_clock(void);
 
 extern unsigned char tod_clock_base[16] __aligned(8);
 
 /**
  * get_clock_monotonic - returns current time in clock rate units
  *
- * The caller must ensure that preemption is disabled.
  * The clock and tod_clock_base get changed via stop_machine.
- * Therefore preemption must be disabled when calling this
- * function, otherwise the returned value is not guaranteed to
- * be monotonic.
+ * Therefore preemption must be disabled, otherwise the returned
+ * value is not guaranteed to be monotonic.
  */
 static inline unsigned long long get_tod_clock_monotonic(void)
 {
-	return get_tod_clock() - *(unsigned long long *) &tod_clock_base[1];
+	unsigned long long tod;
+
+	preempt_disable();
+	tod = get_tod_clock() - *(unsigned long long *) &tod_clock_base[1];
+	preempt_enable();
+	return tod;
 }
 
 /**
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 7abe6ae261b4..f304802ecf7b 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -461,10 +461,11 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 				ptr += sprintf(ptr, "%%c%i", value);
 			else if (operand->flags & OPERAND_VR)
 				ptr += sprintf(ptr, "%%v%i", value);
-			else if (operand->flags & OPERAND_PCREL)
-				ptr += sprintf(ptr, "%lx", (signed int) value
-								      + addr);
-			else if (operand->flags & OPERAND_SIGNED)
+			else if (operand->flags & OPERAND_PCREL) {
+				void *pcrel = (void *)((int)value + addr);
+
+				ptr += sprintf(ptr, "%px", pcrel);
+			} else if (operand->flags & OPERAND_SIGNED)
 				ptr += sprintf(ptr, "%i", value);
 			else
 				ptr += sprintf(ptr, "%u", value);
@@ -536,7 +537,7 @@ void show_code(struct pt_regs *regs)
 		else
 			*ptr++ = ' ';
 		addr = regs->psw.addr + start - 32;
-		ptr += sprintf(ptr, "%016lx: ", addr);
+		ptr += sprintf(ptr, "%px: ", (void *)addr);
 		if (start + opsize >= end)
 			break;
 		for (i = 0; i < opsize; i++)
@@ -564,7 +565,7 @@ void print_fn_code(unsigned char *code, unsigned long len)
 		opsize = insn_length(*code);
 		if (opsize > len)
 			break;
-		ptr += sprintf(ptr, "%p: ", code);
+		ptr += sprintf(ptr, "%px: ", code);
 		for (i = 0; i < opsize; i++)
 			ptr += sprintf(ptr, "%02x", code[i]);
 		*ptr++ = '\t';
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index b432d63d0b37..db32a55daaec 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -30,6 +30,7 @@
 #include <asm/sclp.h>
 #include <asm/facility.h>
 #include <asm/boot_data.h>
+#include <asm/switch_to.h>
 #include "entry.h"
 
 static void __init reset_tod_clock(void)
@@ -238,7 +239,7 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_VX;
 		__ctl_set_bit(0, 17);
 	}
-	if (test_facility(130)) {
+	if (test_facility(130) && !noexec_disabled) {
 		S390_lowcore.machine_flags |= MACHINE_FLAG_NX;
 		__ctl_set_bit(0, 20);
 	}
@@ -260,6 +261,24 @@ static inline void save_vector_registers(void)
 #endif
 }
 
+static inline void setup_control_registers(void)
+{
+	unsigned long reg;
+
+	__ctl_store(reg, 0, 0);
+	reg |= CR0_LOW_ADDRESS_PROTECTION;
+	reg |= CR0_EMERGENCY_SIGNAL_SUBMASK;
+	reg |= CR0_EXTERNAL_CALL_SUBMASK;
+	__ctl_load(reg, 0, 0);
+}
+
+static inline void setup_access_registers(void)
+{
+	unsigned int acrs[NUM_ACRS] = { 0 };
+
+	restore_access_regs(acrs);
+}
+
 static int __init disable_vector_extension(char *str)
 {
 	S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX;
@@ -268,21 +287,6 @@ static int __init disable_vector_extension(char *str)
 }
 early_param("novx", disable_vector_extension);
 
-static int __init noexec_setup(char *str)
-{
-	bool enabled;
-	int rc;
-
-	rc = kstrtobool(str, &enabled);
-	if (!rc && !enabled) {
-		/* Disable no-execute support */
-		S390_lowcore.machine_flags &= ~MACHINE_FLAG_NX;
-		__ctl_clear_bit(0, 20);
-	}
-	return rc;
-}
-early_param("noexec", noexec_setup);
-
 static int __init cad_setup(char *str)
 {
 	bool enabled;
@@ -332,5 +336,7 @@ void __init startup_init(void)
 	save_vector_registers();
 	setup_topology();
 	sclp_early_detect();
+	setup_control_registers();
+	setup_access_registers();
 	lockdep_on();
 }
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 0d9ee198f4eb..b9e585f528a6 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -26,8 +26,6 @@ ENTRY(startup_continue)
 0:	larl	%r1,tod_clock_base
 	mvc	0(16,%r1),__LC_BOOT_CLOCK
 	larl	%r13,.LPG1		# get base
-	larl	%r0,boot_vdso_data
-	stg	%r0,__LC_VDSO_PER_CPU
 #
 # Setup stack
 #
@@ -37,19 +35,8 @@ ENTRY(startup_continue)
 #ifdef CONFIG_KASAN
 	brasl	%r14,kasan_early_init
 #endif
-#
-# Early machine initialization and detection functions.
-#
-	brasl	%r14,startup_init
-
-# check control registers
-	stctg	%c0,%c15,0(%r15)
-	oi	6(%r15),0x60		# enable sigp emergency & external call
-	oi	4(%r15),0x10		# switch on low address proctection
-	lctlg	%c0,%c15,0(%r15)
-
-	lam	0,15,.Laregs-.LPG1(%r13)	# load acrs needed by uaccess
-	brasl	%r14,start_kernel		# go to C code
+	brasl	%r14,startup_init		# s390 specific early init
+	brasl	%r14,start_kernel		# common init code
 #
 # We returned from start_kernel ?!? PANIK
 #
@@ -59,4 +46,3 @@ ENTRY(startup_continue)
 	.align	16
 .LPG1:
 .Ldw:	.quad	0x0002000180000000,0x0000000000000000
-.Laregs:.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 48d48b6187c0..0eb1d1cc53a8 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -199,7 +199,7 @@ static const int cpumf_generic_events_user[] = {
 	[PERF_COUNT_HW_BUS_CYCLES]	    = -1,
 };
 
-static int __hw_perf_event_init(struct perf_event *event)
+static int __hw_perf_event_init(struct perf_event *event, unsigned int type)
 {
 	struct perf_event_attr *attr = &event->attr;
 	struct hw_perf_event *hwc = &event->hw;
@@ -207,7 +207,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 	int err = 0;
 	u64 ev;
 
-	switch (attr->type) {
+	switch (type) {
 	case PERF_TYPE_RAW:
 		/* Raw events are used to access counters directly,
 		 * hence do not permit excludes */
@@ -294,17 +294,16 @@ static int __hw_perf_event_init(struct perf_event *event)
 
 static int cpumf_pmu_event_init(struct perf_event *event)
 {
+	unsigned int type = event->attr.type;
 	int err;
 
-	switch (event->attr.type) {
-	case PERF_TYPE_HARDWARE:
-	case PERF_TYPE_HW_CACHE:
-	case PERF_TYPE_RAW:
-		err = __hw_perf_event_init(event);
-		break;
-	default:
+	if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW)
+		err = __hw_perf_event_init(event, type);
+	else if (event->pmu->type == type)
+		/* Registered as unknown PMU */
+		err = __hw_perf_event_init(event, PERF_TYPE_RAW);
+	else
 		return -ENOENT;
-	}
 
 	if (unlikely(err) && event->destroy)
 		event->destroy(event);
@@ -553,7 +552,7 @@ static int __init cpumf_pmu_init(void)
 		return -ENODEV;
 
 	cpumf_pmu.attr_groups = cpumf_cf_event_group();
-	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
+	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", -1);
 	if (rc)
 		pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc);
 	return rc;
diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
index 2654e348801a..e949ab832ed7 100644
--- a/arch/s390/kernel/perf_cpum_cf_diag.c
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -243,13 +243,13 @@ static int cf_diag_event_init(struct perf_event *event)
 	int err = -ENOENT;
 
 	debug_sprintf_event(cf_diag_dbg, 5,
-			    "%s event %p cpu %d config %#llx "
+			    "%s event %p cpu %d config %#llx type:%u "
 			    "sample_type %#llx cf_diag_events %d\n", __func__,
-			    event, event->cpu, attr->config, attr->sample_type,
-			    atomic_read(&cf_diag_events));
+			    event, event->cpu, attr->config, event->pmu->type,
+			    attr->sample_type, atomic_read(&cf_diag_events));
 
 	if (event->attr.config != PERF_EVENT_CPUM_CF_DIAG ||
-	    event->attr.type != PERF_TYPE_RAW)
+	    event->attr.type != event->pmu->type)
 		goto out;
 
 	/* Raw events are used to access counters directly,
@@ -693,7 +693,7 @@ static int __init cf_diag_init(void)
 	}
 	debug_register_view(cf_diag_dbg, &debug_sprintf_view);
 
-	rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", PERF_TYPE_RAW);
+	rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", -1);
 	if (rc) {
 		debug_unregister_view(cf_diag_dbg, &debug_sprintf_view);
 		debug_unregister(cf_diag_dbg);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 3d8b12a9a6ff..69506fdbd9a1 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -156,8 +156,8 @@ static void free_sampling_buffer(struct sf_buffer *sfb)
 		}
 	}
 
-	debug_sprintf_event(sfdbg, 5,
-			    "free_sampling_buffer: freed sdbt=%p\n", sfb->sdbt);
+	debug_sprintf_event(sfdbg, 5, "%s freed sdbt %p\n", __func__,
+			    sfb->sdbt);
 	memset(sfb, 0, sizeof(*sfb));
 }
 
@@ -212,10 +212,10 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb,
 	 * the sampling buffer origin.
 	 */
 	if (sfb->sdbt != get_next_sdbt(tail)) {
-		debug_sprintf_event(sfdbg, 3, "realloc_sampling_buffer: "
-				    "sampling buffer is not linked: origin=%p"
-				    "tail=%p\n",
-				    (void *) sfb->sdbt, (void *) tail);
+		debug_sprintf_event(sfdbg, 3, "%s: "
+				    "sampling buffer is not linked: origin %p"
+				    " tail %p\n", __func__,
+				    (void *)sfb->sdbt, (void *)tail);
 		return -EINVAL;
 	}
 
@@ -252,7 +252,7 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb,
 	sfb->tail = tail;
 
 	debug_sprintf_event(sfdbg, 4, "realloc_sampling_buffer: new buffer"
-			    " settings: sdbt=%lu sdb=%lu\n",
+			    " settings: sdbt %lu sdb %lu\n",
 			    sfb->num_sdbt, sfb->num_sdb);
 	return rc;
 }
@@ -293,11 +293,11 @@ static int alloc_sampling_buffer(struct sf_buffer *sfb, unsigned long num_sdb)
 	if (rc) {
 		free_sampling_buffer(sfb);
 		debug_sprintf_event(sfdbg, 4, "alloc_sampling_buffer: "
-			"realloc_sampling_buffer failed with rc=%i\n", rc);
+			"realloc_sampling_buffer failed with rc %i\n", rc);
 	} else
 		debug_sprintf_event(sfdbg, 4,
-			"alloc_sampling_buffer: tear=%p dear=%p\n",
-			sfb->sdbt, (void *) *sfb->sdbt);
+			"alloc_sampling_buffer: tear %p dear %p\n",
+			sfb->sdbt, (void *)*sfb->sdbt);
 	return rc;
 }
 
@@ -404,8 +404,8 @@ static int allocate_buffers(struct cpu_hw_sf *cpuhw, struct hw_perf_event *hwc)
 		return 0;
 
 	debug_sprintf_event(sfdbg, 3,
-			    "allocate_buffers: rate=%lu f=%lu sdb=%lu/%lu"
-			    " sample_size=%lu cpuhw=%p\n",
+			    "%s: rate %lu f %lu sdb %lu/%lu"
+			    " sample_size %lu cpuhw %p\n", __func__,
 			    SAMPL_RATE(hwc), freq, n_sdb, sfb_max_limit(hwc),
 			    sample_size, cpuhw);
 
@@ -465,8 +465,8 @@ static void sfb_account_overflows(struct cpu_hw_sf *cpuhw,
 	if (num)
 		sfb_account_allocs(num, hwc);
 
-	debug_sprintf_event(sfdbg, 5, "sfb: overflow: overflow=%llu ratio=%lu"
-			    " num=%lu\n", OVERFLOW_REG(hwc), ratio, num);
+	debug_sprintf_event(sfdbg, 5, "sfb: overflow: overflow %llu ratio %lu"
+			    " num %lu\n", OVERFLOW_REG(hwc), ratio, num);
 	OVERFLOW_REG(hwc) = 0;
 }
 
@@ -505,11 +505,11 @@ static void extend_sampling_buffer(struct sf_buffer *sfb,
 	rc = realloc_sampling_buffer(sfb, num, GFP_ATOMIC);
 	if (rc)
 		debug_sprintf_event(sfdbg, 5, "sfb: extend: realloc "
-				    "failed with rc=%i\n", rc);
+				    "failed with rc %i\n", rc);
 
 	if (sfb_has_pending_allocs(sfb, hwc))
 		debug_sprintf_event(sfdbg, 5, "sfb: extend: "
-				    "req=%lu alloc=%lu remaining=%lu\n",
+				    "req %lu alloc %lu remaining %lu\n",
 				    num, sfb->num_sdb - num_old,
 				    sfb_pending_allocs(sfb, hwc));
 }
@@ -538,20 +538,22 @@ static void setup_pmc_cpu(void *flags)
 		err = sf_disable();
 		if (err)
 			pr_err("Switching off the sampling facility failed "
-			       "with rc=%i\n", err);
+			       "with rc %i\n", err);
 		debug_sprintf_event(sfdbg, 5,
-				    "setup_pmc_cpu: initialized: cpuhw=%p\n", cpusf);
+				    "%s: initialized: cpuhw %p\n", __func__,
+				    cpusf);
 		break;
 	case PMC_RELEASE:
 		cpusf->flags &= ~PMU_F_RESERVED;
 		err = sf_disable();
 		if (err) {
 			pr_err("Switching off the sampling facility failed "
-			       "with rc=%i\n", err);
+			       "with rc %i\n", err);
 		} else
 			deallocate_buffers(cpusf);
 		debug_sprintf_event(sfdbg, 5,
-				    "setup_pmc_cpu: released: cpuhw=%p\n", cpusf);
+				    "%s: released: cpuhw %p\n", __func__,
+				    cpusf);
 		break;
 	}
 	if (err)
@@ -744,7 +746,7 @@ static int __hw_perf_event_init_rate(struct perf_event *event,
 	SAMPL_RATE(hwc) = rate;
 	hw_init_period(hwc, SAMPL_RATE(hwc));
 	debug_sprintf_event(sfdbg, 4, "__hw_perf_event_init_rate:"
-			    "cpu:%d period:%llx freq:%d,%#lx\n", event->cpu,
+			    "cpu:%d period:%#llx freq:%d,%#lx\n", event->cpu,
 			    event->attr.sample_period, event->attr.freq,
 			    SAMPLE_FREQ_MODE(hwc));
 	return 0;
@@ -963,7 +965,7 @@ static void cpumsf_pmu_enable(struct pmu *pmu)
 	err = lsctl(&cpuhw->lsctl);
 	if (err) {
 		cpuhw->flags &= ~PMU_F_ENABLED;
-		pr_err("Loading sampling controls failed: op=%i err=%i\n",
+		pr_err("Loading sampling controls failed: op %i err %i\n",
 			1, err);
 		return;
 	}
@@ -971,8 +973,8 @@ static void cpumsf_pmu_enable(struct pmu *pmu)
 	/* Load current program parameter */
 	lpp(&S390_lowcore.lpp);
 
-	debug_sprintf_event(sfdbg, 6, "pmu_enable: es=%i cs=%i ed=%i cd=%i "
-			    "interval:%lx tear=%p dear=%p\n",
+	debug_sprintf_event(sfdbg, 6, "pmu_enable: es %i cs %i ed %i cd %i "
+			    "interval %#lx tear %p dear %p\n",
 			    cpuhw->lsctl.es, cpuhw->lsctl.cs, cpuhw->lsctl.ed,
 			    cpuhw->lsctl.cd, cpuhw->lsctl.interval,
 			    (void *) cpuhw->lsctl.tear,
@@ -999,13 +1001,14 @@ static void cpumsf_pmu_disable(struct pmu *pmu)
 
 	err = lsctl(&inactive);
 	if (err) {
-		pr_err("Loading sampling controls failed: op=%i err=%i\n",
+		pr_err("Loading sampling controls failed: op %i err %i\n",
 			2, err);
 		return;
 	}
 
 	/* Save state of TEAR and DEAR register contents */
-	if (!qsi(&si)) {
+	err = qsi(&si);
+	if (!err) {
 		/* TEAR/DEAR values are valid only if the sampling facility is
 		 * enabled.  Note that cpumsf_pmu_disable() might be called even
 		 * for a disabled sampling facility because cpumsf_pmu_enable()
@@ -1017,7 +1020,7 @@ static void cpumsf_pmu_disable(struct pmu *pmu)
 		}
 	} else
 		debug_sprintf_event(sfdbg, 3, "cpumsf_pmu_disable: "
-				    "qsi() failed with err=%i\n", err);
+				    "qsi() failed with err %i\n", err);
 
 	cpuhw->flags &= ~PMU_F_ENABLED;
 }
@@ -1130,15 +1133,6 @@ static void perf_event_count_update(struct perf_event *event, u64 count)
 	local64_add(count, &event->count);
 }
 
-static void debug_sample_entry(struct hws_basic_entry *sample,
-			       struct hws_trailer_entry *te)
-{
-	debug_sprintf_event(sfdbg, 4, "hw_collect_samples: Found unknown "
-			    "sampling data entry: te->f=%i basic.def=%04x "
-			    "(%p)\n",
-			    te->f, sample->def, sample);
-}
-
 /* hw_collect_samples() - Walk through a sample-data-block and collect samples
  * @event:	The perf event
  * @sdbt:	Sample-data-block table
@@ -1192,7 +1186,11 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
 				/* Count discarded samples */
 				*overflow += 1;
 		} else {
-			debug_sample_entry(sample, te);
+			debug_sprintf_event(sfdbg, 4,
+					    "%s: Found unknown"
+					    " sampling data entry: te->f %i"
+					    " basic.def %#4x (%p)\n", __func__,
+					    te->f, sample->def, sample);
 			/* Sample slot is not yet written or other record.
 			 *
 			 * This condition can occur if the buffer was reused
@@ -1267,9 +1265,9 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 			sampl_overflow += te->overflow;
 
 		/* Timestamps are valid for full sample-data-blocks only */
-		debug_sprintf_event(sfdbg, 6, "hw_perf_event_update: sdbt=%p "
-				    "overflow=%llu timestamp=%#llx\n",
-				    sdbt, te->overflow,
+		debug_sprintf_event(sfdbg, 6, "%s: sdbt %p "
+				    "overflow %llu timestamp %#llx\n",
+				    __func__, sdbt, te->overflow,
 				    (te->f) ? trailer_timestamp(te) : 0ULL);
 
 		/* Collect all samples from a single sample-data-block and
@@ -1313,9 +1311,9 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 		OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) +
 						 sampl_overflow, 1 + num_sdb);
 	if (sampl_overflow || event_overflow)
-		debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: "
-				    "overflow stats: sample=%llu event=%llu\n",
-				    sampl_overflow, event_overflow);
+		debug_sprintf_event(sfdbg, 4, "%s: "
+				    "overflow stats: sample %llu event %llu\n",
+				    __func__, sampl_overflow, event_overflow);
 }
 
 #define AUX_SDB_INDEX(aux, i) ((i) % aux->sfb.num_sdb)
@@ -1368,7 +1366,7 @@ static void aux_output_end(struct perf_output_handle *handle)
 	te = aux_sdb_trailer(aux, aux->alert_mark);
 	te->flags &= ~SDB_TE_ALERT_REQ_MASK;
 
-	debug_sprintf_event(sfdbg, 6, "aux_output_end: collect %lx SDBs\n", i);
+	debug_sprintf_event(sfdbg, 6, "%s: collect %#lx SDBs\n", __func__, i);
 }
 
 /*
@@ -1428,8 +1426,8 @@ static int aux_output_begin(struct perf_output_handle *handle,
 
 	debug_sprintf_event(sfdbg, 6, "aux_output_begin: "
 			    "head->alert_mark->empty_mark (num_alert, range)"
-			    "[%lx -> %lx -> %lx] (%lx, %lx) "
-			    "tear index %lx, tear %lx dear %lx\n",
+			    "[%#lx -> %#lx -> %#lx] (%#lx, %#lx) "
+			    "tear index %#lx, tear %#lx dear %#lx\n",
 			    aux->head, aux->alert_mark, aux->empty_mark,
 			    AUX_SDB_NUM_ALERT(aux), range,
 			    head / CPUM_SF_SDB_PER_TABLE,
@@ -1596,13 +1594,13 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw)
 			perf_aux_output_end(&cpuhw->handle, size);
 			pr_err("Sample data caused the AUX buffer with %lu "
 			       "pages to overflow\n", num_sdb);
-			debug_sprintf_event(sfdbg, 1, "head %lx range %lx "
-					    "overflow %llx\n",
+			debug_sprintf_event(sfdbg, 1, "head %#lx range %#lx "
+					    "overflow %#llx\n",
 					    aux->head, range, overflow);
 		} else {
 			size = AUX_SDB_NUM_ALERT(aux) << PAGE_SHIFT;
 			perf_aux_output_end(&cpuhw->handle, size);
-			debug_sprintf_event(sfdbg, 6, "head %lx alert %lx "
+			debug_sprintf_event(sfdbg, 6, "head %#lx alert %#lx "
 					    "already full, try another\n",
 					    aux->head, aux->alert_mark);
 		}
@@ -1610,7 +1608,7 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw)
 
 	if (done)
 		debug_sprintf_event(sfdbg, 6, "aux_reset_buffer: "
-				    "[%lx -> %lx -> %lx] (%lx, %lx)\n",
+				    "[%#lx -> %#lx -> %#lx] (%#lx, %#lx)\n",
 				    aux->head, aux->alert_mark, aux->empty_mark,
 				    AUX_SDB_NUM_ALERT(aux), range);
 }
@@ -1800,7 +1798,7 @@ static int cpumsf_pmu_check_period(struct perf_event *event, u64 value)
 	SAMPL_RATE(&event->hw) = rate;
 	hw_init_period(&event->hw, SAMPL_RATE(&event->hw));
 	debug_sprintf_event(sfdbg, 4, "cpumsf_pmu_check_period:"
-			    "cpu:%d value:%llx period:%llx freq:%d\n",
+			    "cpu:%d value:%#llx period:%#llx freq:%d\n",
 			    event->cpu, value,
 			    event->attr.sample_period, do_freq);
 	return 0;
@@ -2111,7 +2109,7 @@ static int param_set_sfb_size(const char *val, const struct kernel_param *kp)
 
 	sfb_set_limits(min, max);
 	pr_info("The sampling buffer limits have changed to: "
-		"min=%lu max=%lu (diag=x%lu)\n",
+		"min %lu max %lu (diag %lu)\n",
 		CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB, CPUM_SF_SDB_DIAG_FACTOR);
 	return 0;
 }
@@ -2129,7 +2127,7 @@ static const struct kernel_param_ops param_ops_sfb_size = {
 static void __init pr_cpumsf_err(unsigned int reason)
 {
 	pr_err("Sampling facility support for perf is not available: "
-	       "reason=%04x\n", reason);
+	       "reason %#x\n", reason);
 }
 
 static int __init init_cpum_sampling_pmu(void)
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index fcb6c2e92b07..1e75cc983546 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -224,9 +224,13 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 			   struct pt_regs *regs)
 {
 	struct unwind_state state;
+	unsigned long addr;
 
-	unwind_for_each_frame(&state, current, regs, 0)
-		perf_callchain_store(entry, state.ip);
+	unwind_for_each_frame(&state, current, regs, 0) {
+		addr = unwind_get_return_address(&state);
+		if (!addr || perf_callchain_store(entry, addr))
+			return;
+	}
 }
 
 /* Perf definitions for PMU event attributes in sysfs */
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index b0afec673f77..6ccef5f29761 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -40,6 +40,7 @@
 #include <asm/stacktrace.h>
 #include <asm/switch_to.h>
 #include <asm/runtime_instr.h>
+#include <asm/unwind.h>
 #include "entry.h"
 
 asmlinkage void ret_from_fork(void) asm ("ret_from_fork");
@@ -178,9 +179,8 @@ EXPORT_SYMBOL(dump_fpu);
 
 unsigned long get_wchan(struct task_struct *p)
 {
-	struct stack_frame *sf, *low, *high;
-	unsigned long return_address;
-	int count;
+	struct unwind_state state;
+	unsigned long ip = 0;
 
 	if (!p || p == current || p->state == TASK_RUNNING || !task_stack_page(p))
 		return 0;
@@ -188,26 +188,22 @@ unsigned long get_wchan(struct task_struct *p)
 	if (!try_get_task_stack(p))
 		return 0;
 
-	low = task_stack_page(p);
-	high = (struct stack_frame *) task_pt_regs(p);
-	sf = (struct stack_frame *) p->thread.ksp;
-	if (sf <= low || sf > high) {
-		return_address = 0;
-		goto out;
-	}
-	for (count = 0; count < 16; count++) {
-		sf = (struct stack_frame *)READ_ONCE_NOCHECK(sf->back_chain);
-		if (sf <= low || sf > high) {
-			return_address = 0;
-			goto out;
+	unwind_for_each_frame(&state, p, NULL, 0) {
+		if (state.stack_info.type != STACK_TYPE_TASK) {
+			ip = 0;
+			break;
 		}
-		return_address = READ_ONCE_NOCHECK(sf->gprs[8]);
-		if (!in_sched_functions(return_address))
-			goto out;
+
+		ip = unwind_get_return_address(&state);
+		if (!ip)
+			break;
+
+		if (!in_sched_functions(ip))
+			break;
 	}
-out:
+
 	put_task_stack(p);
-	return return_address;
+	return ip;
 }
 
 unsigned long arch_align_stack(unsigned long sp)
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 44974654cbd0..6acdcf1d4074 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -724,39 +724,67 @@ static void __ref smp_get_core_info(struct sclp_core_info *info, int early)
 
 static int smp_add_present_cpu(int cpu);
 
-static int __smp_rescan_cpus(struct sclp_core_info *info, int sysfs_add)
+static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail,
+			bool configured, bool early)
 {
 	struct pcpu *pcpu;
-	cpumask_t avail;
-	int cpu, nr, i, j;
+	int cpu, nr, i;
 	u16 address;
 
 	nr = 0;
-	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
-	cpu = cpumask_first(&avail);
-	for (i = 0; (i < info->combined) && (cpu < nr_cpu_ids); i++) {
-		if (sclp.has_core_type && info->core[i].type != boot_core_type)
+	if (sclp.has_core_type && core->type != boot_core_type)
+		return nr;
+	cpu = cpumask_first(avail);
+	address = core->core_id << smp_cpu_mt_shift;
+	for (i = 0; (i <= smp_cpu_mtid) && (cpu < nr_cpu_ids); i++) {
+		if (pcpu_find_address(cpu_present_mask, address + i))
 			continue;
-		address = info->core[i].core_id << smp_cpu_mt_shift;
-		for (j = 0; j <= smp_cpu_mtid; j++) {
-			if (pcpu_find_address(cpu_present_mask, address + j))
-				continue;
-			pcpu = pcpu_devices + cpu;
-			pcpu->address = address + j;
-			pcpu->state =
-				(cpu >= info->configured*(smp_cpu_mtid + 1)) ?
-				CPU_STATE_STANDBY : CPU_STATE_CONFIGURED;
-			smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
-			set_cpu_present(cpu, true);
-			if (sysfs_add && smp_add_present_cpu(cpu) != 0)
-				set_cpu_present(cpu, false);
-			else
-				nr++;
-			cpu = cpumask_next(cpu, &avail);
-			if (cpu >= nr_cpu_ids)
+		pcpu = pcpu_devices + cpu;
+		pcpu->address = address + i;
+		if (configured)
+			pcpu->state = CPU_STATE_CONFIGURED;
+		else
+			pcpu->state = CPU_STATE_STANDBY;
+		smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
+		set_cpu_present(cpu, true);
+		if (!early && smp_add_present_cpu(cpu) != 0)
+			set_cpu_present(cpu, false);
+		else
+			nr++;
+		cpumask_clear_cpu(cpu, avail);
+		cpu = cpumask_next(cpu, avail);
+	}
+	return nr;
+}
+
+static int __smp_rescan_cpus(struct sclp_core_info *info, bool early)
+{
+	struct sclp_core_entry *core;
+	cpumask_t avail;
+	bool configured;
+	u16 core_id;
+	int nr, i;
+
+	nr = 0;
+	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
+	/*
+	 * Add IPL core first (which got logical CPU number 0) to make sure
+	 * that all SMT threads get subsequent logical CPU numbers.
+	 */
+	if (early) {
+		core_id = pcpu_devices[0].address >> smp_cpu_mt_shift;
+		for (i = 0; i < info->configured; i++) {
+			core = &info->core[i];
+			if (core->core_id == core_id) {
+				nr += smp_add_core(core, &avail, true, early);
 				break;
+			}
 		}
 	}
+	for (i = 0; i < info->combined; i++) {
+		configured = i < info->configured;
+		nr += smp_add_core(&info->core[i], &avail, configured, early);
+	}
 	return nr;
 }
 
@@ -805,7 +833,7 @@ void __init smp_detect_cpus(void)
 
 	/* Add CPUs present at boot */
 	get_online_cpus();
-	__smp_rescan_cpus(info, 0);
+	__smp_rescan_cpus(info, true);
 	put_online_cpus();
 	memblock_free_early((unsigned long)info, sizeof(*info));
 }
@@ -1148,7 +1176,7 @@ int __ref smp_rescan_cpus(void)
 	smp_get_core_info(info, 0);
 	get_online_cpus();
 	mutex_lock(&smp_cpu_state_mutex);
-	nr = __smp_rescan_cpus(info, 1);
+	nr = __smp_rescan_cpus(info, false);
 	mutex_unlock(&smp_cpu_state_mutex);
 	put_online_cpus();
 	kfree(info);
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index e8766beee5ad..f9d070d016e3 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -110,15 +110,6 @@ unsigned long long notrace sched_clock(void)
 }
 NOKPROBE_SYMBOL(sched_clock);
 
-/*
- * Monotonic_clock - returns # of nanoseconds passed since time_init()
- */
-unsigned long long monotonic_clock(void)
-{
-	return sched_clock();
-}
-EXPORT_SYMBOL(monotonic_clock);
-
 static void ext_to_timespec64(unsigned char *clk, struct timespec64 *xt)
 {
 	unsigned long long high, low, rem, sec, nsec;
diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c
index a8204f952315..fa111d3d378f 100644
--- a/arch/s390/kernel/unwind_bc.c
+++ b/arch/s390/kernel/unwind_bc.c
@@ -85,12 +85,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		}
 	}
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	/* Decode any ftrace redirection */
-	if (ip == (unsigned long) return_to_handler)
-		ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
-					   ip, (void *) sp);
-#endif
+	ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, (void *) sp);
 
 	/* Update unwind state */
 	state->sp = sp;
@@ -147,12 +142,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 		reuse_sp = false;
 	}
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	/* Decode any ftrace redirection */
-	if (ip == (unsigned long) return_to_handler)
-		ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
-					   ip, NULL);
-#endif
+	ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, NULL);
 
 	/* Update unwind state */
 	state->sp = sp;
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 45634b3d2e0a..3fb54ec2cf3e 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -158,14 +158,28 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
 
 	tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
 	vcpu->stat.diagnose_9c++;
-	VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d", tid);
 
+	/* yield to self */
 	if (tid == vcpu->vcpu_id)
-		return 0;
+		goto no_yield;
 
+	/* yield to invalid */
 	tcpu = kvm_get_vcpu_by_id(vcpu->kvm, tid);
-	if (tcpu)
-		kvm_vcpu_yield_to(tcpu);
+	if (!tcpu)
+		goto no_yield;
+
+	/* target already running */
+	if (READ_ONCE(tcpu->cpu) >= 0)
+		goto no_yield;
+
+	if (kvm_vcpu_yield_to(tcpu) <= 0)
+		goto no_yield;
+
+	VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d: done", tid);
+	return 0;
+no_yield:
+	VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d: ignored", tid);
+	vcpu->stat.diagnose_9c_ignored++;
 	return 0;
 }
 
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index d1ccc168c071..165dea4c7f19 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1477,8 +1477,7 @@ static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	return 0;
 }
 
-static int __inject_sigp_restart(struct kvm_vcpu *vcpu,
-				 struct kvm_s390_irq *irq)
+static int __inject_sigp_restart(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
@@ -2007,7 +2006,7 @@ static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 		rc = __inject_sigp_stop(vcpu, irq);
 		break;
 	case KVM_S390_RESTART:
-		rc = __inject_sigp_restart(vcpu, irq);
+		rc = __inject_sigp_restart(vcpu);
 		break;
 	case KVM_S390_INT_CLOCK_COMP:
 		rc = __inject_ckc(vcpu);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index d047e846e1b9..d9e6bf3d54f0 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -155,6 +155,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "instruction_diag_10", VCPU_STAT(diagnose_10) },
 	{ "instruction_diag_44", VCPU_STAT(diagnose_44) },
 	{ "instruction_diag_9c", VCPU_STAT(diagnose_9c) },
+	{ "diag_9c_ignored", VCPU_STAT(diagnose_9c_ignored) },
 	{ "instruction_diag_258", VCPU_STAT(diagnose_258) },
 	{ "instruction_diag_308", VCPU_STAT(diagnose_308) },
 	{ "instruction_diag_500", VCPU_STAT(diagnose_500) },
@@ -453,16 +454,14 @@ static void kvm_s390_cpu_feat_init(void)
 
 int kvm_arch_init(void *opaque)
 {
-	int rc;
+	int rc = -ENOMEM;
 
 	kvm_s390_dbf = debug_register("kvm-trace", 32, 1, 7 * sizeof(long));
 	if (!kvm_s390_dbf)
 		return -ENOMEM;
 
-	if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) {
-		rc = -ENOMEM;
-		goto out_debug_unreg;
-	}
+	if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view))
+		goto out;
 
 	kvm_s390_cpu_feat_init();
 
@@ -470,19 +469,17 @@ int kvm_arch_init(void *opaque)
 	rc = kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
 	if (rc) {
 		pr_err("A FLIC registration call failed with rc=%d\n", rc);
-		goto out_debug_unreg;
+		goto out;
 	}
 
 	rc = kvm_s390_gib_init(GAL_ISC);
 	if (rc)
-		goto out_gib_destroy;
+		goto out;
 
 	return 0;
 
-out_gib_destroy:
-	kvm_s390_gib_destroy();
-out_debug_unreg:
-	debug_unregister(kvm_s390_dbf);
+out:
+	kvm_arch_exit();
 	return rc;
 }
 
diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c
index 30a7c8c29964..ce1e4bbe53aa 100644
--- a/arch/s390/lib/spinlock.c
+++ b/arch/s390/lib/spinlock.c
@@ -74,7 +74,7 @@ static inline int arch_load_niai4(int *lock)
 {
 	int owner;
 
-	asm volatile(
+	asm_inline volatile(
 		ALTERNATIVE("", ".long 0xb2fa0040", 49)	/* NIAI 4 */
 		"	l	%0,%1\n"
 		: "=d" (owner) : "Q" (*lock) : "memory");
@@ -85,7 +85,7 @@ static inline int arch_cmpxchg_niai8(int *lock, int old, int new)
 {
 	int expected = old;
 
-	asm volatile(
+	asm_inline volatile(
 		ALTERNATIVE("", ".long 0xb2fa0080", 49)	/* NIAI 8 */
 		"	cs	%0,%3,%1\n"
 		: "=d" (old), "=Q" (*lock)
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index a124f19f7b3c..f0ce22220565 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -118,6 +118,7 @@ void __init paging_init(void)
 
 	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
+	zone_dma_bits = 31;
 	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
 	max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS);
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 1864a8bb9622..59ad7997fed1 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -70,7 +70,7 @@ void notrace s390_kernel_write(void *dst, const void *src, size_t size)
 	spin_unlock_irqrestore(&s390_kernel_write_lock, flags);
 }
 
-static int __memcpy_real(void *dest, void *src, size_t count)
+static int __no_sanitize_address __memcpy_real(void *dest, void *src, size_t count)
 {
 	register unsigned long _dest asm("2") = (unsigned long) dest;
 	register unsigned long _len1 asm("3") = (unsigned long) count;
@@ -91,19 +91,23 @@ static int __memcpy_real(void *dest, void *src, size_t count)
 	return rc;
 }
 
-static unsigned long _memcpy_real(unsigned long dest, unsigned long src,
-				  unsigned long count)
+static unsigned long __no_sanitize_address _memcpy_real(unsigned long dest,
+							unsigned long src,
+							unsigned long count)
 {
 	int irqs_disabled, rc;
 	unsigned long flags;
 
 	if (!count)
 		return 0;
-	flags = __arch_local_irq_stnsm(0xf8UL);
+	flags = arch_local_irq_save();
 	irqs_disabled = arch_irqs_disabled_flags(flags);
 	if (!irqs_disabled)
 		trace_hardirqs_off();
+	__arch_local_irq_stnsm(0xf8); // disable DAT
 	rc = __memcpy_real((void *) dest, (void *) src, (size_t) count);
+	if (flags & PSW_MASK_DAT)
+		__arch_local_irq_stosm(0x04); // enable DAT
 	if (!irqs_disabled)
 		trace_hardirqs_on();
 	__arch_local_irq_ssm(flags);
diff --git a/arch/sh/boards/mach-sdk7786/nmi.c b/arch/sh/boards/mach-sdk7786/nmi.c
index c2e09d798537..afba49679a12 100644
--- a/arch/sh/boards/mach-sdk7786/nmi.c
+++ b/arch/sh/boards/mach-sdk7786/nmi.c
@@ -37,7 +37,7 @@ static int __init nmi_mode_setup(char *str)
 		nmi_mode = NMI_MODE_ANY;
 	else {
 		nmi_mode = NMI_MODE_UNKNOWN;
-		pr_warning("Unknown NMI mode %s\n", str);
+		pr_warn("Unknown NMI mode %s\n", str);
 	}
 
 	printk("Set NMI mode to %d\n", nmi_mode);
diff --git a/arch/sh/drivers/pci/fixups-sdk7786.c b/arch/sh/drivers/pci/fixups-sdk7786.c
index 8cbfa5310a4b..6972af7b4e93 100644
--- a/arch/sh/drivers/pci/fixups-sdk7786.c
+++ b/arch/sh/drivers/pci/fixups-sdk7786.c
@@ -53,7 +53,7 @@ static int __init sdk7786_pci_init(void)
 
 		/* Warn about forced rerouting if slot#3 is occupied */
 		if ((data & PCIECR_PRST3) == 0) {
-			pr_warning("Unreachable card detected in slot#3\n");
+			pr_warn("Unreachable card detected in slot#3\n");
 			return -EBUSY;
 		}
 	} else
diff --git a/arch/sh/kernel/io_trapped.c b/arch/sh/kernel/io_trapped.c
index bacad6da4fe4..60c828a2b8a2 100644
--- a/arch/sh/kernel/io_trapped.c
+++ b/arch/sh/kernel/io_trapped.c
@@ -99,7 +99,7 @@ int register_trapped_io(struct trapped_io *tiop)
 
 	return 0;
  bad:
-	pr_warning("unable to install trapped io filter\n");
+	pr_warn("unable to install trapped io filter\n");
 	return -1;
 }
 EXPORT_SYMBOL_GPL(register_trapped_io);
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index 2c0e0f37a318..6ef341f6cfee 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -354,7 +354,7 @@ void __init setup_arch(char **cmdline_p)
 /* processor boot mode configuration */
 int generic_mode_pins(void)
 {
-	pr_warning("generic_mode_pins(): missing mode pin configuration\n");
+	pr_warn("generic_mode_pins(): missing mode pin configuration\n");
 	return 0;
 }
 
diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index 792f36129062..3169a343a5ab 100644
--- a/arch/sh/mm/consistent.c
+++ b/arch/sh/mm/consistent.c
@@ -43,8 +43,7 @@ int __init platform_resource_setup_memory(struct platform_device *pdev,
 
 	r = pdev->resource + pdev->num_resources - 1;
 	if (r->flags) {
-		pr_warning("%s: unable to find empty space for resource\n",
-			name);
+		pr_warn("%s: unable to find empty space for resource\n", name);
 		return -EINVAL;
 	}
 
@@ -54,7 +53,7 @@ int __init platform_resource_setup_memory(struct platform_device *pdev,
 
 	buf = dma_alloc_coherent(&pdev->dev, memsize, &dma_handle, GFP_KERNEL);
 	if (!buf) {
-		pr_warning("%s: unable to allocate memory\n", name);
+		pr_warn("%s: unable to allocate memory\n", name);
 		return -ENOMEM;
 	}
 
diff --git a/arch/sparc/crypto/aes_glue.c b/arch/sparc/crypto/aes_glue.c
index 7b946b3dee9d..0f5a501c95a9 100644
--- a/arch/sparc/crypto/aes_glue.c
+++ b/arch/sparc/crypto/aes_glue.c
@@ -24,6 +24,7 @@
 #include <linux/types.h>
 #include <crypto/algapi.h>
 #include <crypto/aes.h>
+#include <crypto/internal/skcipher.h>
 
 #include <asm/fpumacro.h>
 #include <asm/pstate.h>
@@ -197,6 +198,12 @@ static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 	return 0;
 }
 
+static int aes_set_key_skcipher(struct crypto_skcipher *tfm, const u8 *in_key,
+				unsigned int key_len)
+{
+	return aes_set_key(crypto_skcipher_tfm(tfm), in_key, key_len);
+}
+
 static void crypto_aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct crypto_sparc64_aes_ctx *ctx = crypto_tfm_ctx(tfm);
@@ -211,131 +218,108 @@ static void crypto_aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 	ctx->ops->decrypt(&ctx->key[0], (const u32 *) src, (u32 *) dst);
 }
 
-#define AES_BLOCK_MASK	(~(AES_BLOCK_SIZE-1))
-
-static int ecb_encrypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes)
+static int ecb_encrypt(struct skcipher_request *req)
 {
-	struct crypto_sparc64_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct crypto_sparc64_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
 	ctx->ops->load_encrypt_keys(&ctx->key[0]);
-	while ((nbytes = walk.nbytes)) {
-		unsigned int block_len = nbytes & AES_BLOCK_MASK;
-
-		if (likely(block_len)) {
-			ctx->ops->ecb_encrypt(&ctx->key[0],
-					      (const u64 *)walk.src.virt.addr,
-					      (u64 *) walk.dst.virt.addr,
-					      block_len);
-		}
-		nbytes &= AES_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+	while ((nbytes = walk.nbytes) != 0) {
+		ctx->ops->ecb_encrypt(&ctx->key[0], walk.src.virt.addr,
+				      walk.dst.virt.addr,
+				      round_down(nbytes, AES_BLOCK_SIZE));
+		err = skcipher_walk_done(&walk, nbytes % AES_BLOCK_SIZE);
 	}
 	fprs_write(0);
 	return err;
 }
 
-static int ecb_decrypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes)
+static int ecb_decrypt(struct skcipher_request *req)
 {
-	struct crypto_sparc64_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	u64 *key_end;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct crypto_sparc64_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	const u64 *key_end;
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
 	ctx->ops->load_decrypt_keys(&ctx->key[0]);
 	key_end = &ctx->key[ctx->expanded_key_length / sizeof(u64)];
-	while ((nbytes = walk.nbytes)) {
-		unsigned int block_len = nbytes & AES_BLOCK_MASK;
-
-		if (likely(block_len)) {
-			ctx->ops->ecb_decrypt(key_end,
-					      (const u64 *) walk.src.virt.addr,
-					      (u64 *) walk.dst.virt.addr, block_len);
-		}
-		nbytes &= AES_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+	while ((nbytes = walk.nbytes) != 0) {
+		ctx->ops->ecb_decrypt(key_end, walk.src.virt.addr,
+				      walk.dst.virt.addr,
+				      round_down(nbytes, AES_BLOCK_SIZE));
+		err = skcipher_walk_done(&walk, nbytes % AES_BLOCK_SIZE);
 	}
 	fprs_write(0);
 
 	return err;
 }
 
-static int cbc_encrypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes)
+static int cbc_encrypt(struct skcipher_request *req)
 {
-	struct crypto_sparc64_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct crypto_sparc64_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
 	ctx->ops->load_encrypt_keys(&ctx->key[0]);
-	while ((nbytes = walk.nbytes)) {
-		unsigned int block_len = nbytes & AES_BLOCK_MASK;
-
-		if (likely(block_len)) {
-			ctx->ops->cbc_encrypt(&ctx->key[0],
-					      (const u64 *)walk.src.virt.addr,
-					      (u64 *) walk.dst.virt.addr,
-					      block_len, (u64 *) walk.iv);
-		}
-		nbytes &= AES_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+	while ((nbytes = walk.nbytes) != 0) {
+		ctx->ops->cbc_encrypt(&ctx->key[0], walk.src.virt.addr,
+				      walk.dst.virt.addr,
+				      round_down(nbytes, AES_BLOCK_SIZE),
+				      walk.iv);
+		err = skcipher_walk_done(&walk, nbytes % AES_BLOCK_SIZE);
 	}
 	fprs_write(0);
 	return err;
 }
 
-static int cbc_decrypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes)
+static int cbc_decrypt(struct skcipher_request *req)
 {
-	struct crypto_sparc64_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	u64 *key_end;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct crypto_sparc64_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	const u64 *key_end;
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
 	ctx->ops->load_decrypt_keys(&ctx->key[0]);
 	key_end = &ctx->key[ctx->expanded_key_length / sizeof(u64)];
-	while ((nbytes = walk.nbytes)) {
-		unsigned int block_len = nbytes & AES_BLOCK_MASK;
-
-		if (likely(block_len)) {
-			ctx->ops->cbc_decrypt(key_end,
-					      (const u64 *) walk.src.virt.addr,
-					      (u64 *) walk.dst.virt.addr,
-					      block_len, (u64 *) walk.iv);
-		}
-		nbytes &= AES_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+	while ((nbytes = walk.nbytes) != 0) {
+		ctx->ops->cbc_decrypt(key_end, walk.src.virt.addr,
+				      walk.dst.virt.addr,
+				      round_down(nbytes, AES_BLOCK_SIZE),
+				      walk.iv);
+		err = skcipher_walk_done(&walk, nbytes % AES_BLOCK_SIZE);
 	}
 	fprs_write(0);
 
 	return err;
 }
 
-static void ctr_crypt_final(struct crypto_sparc64_aes_ctx *ctx,
-			    struct blkcipher_walk *walk)
+static void ctr_crypt_final(const struct crypto_sparc64_aes_ctx *ctx,
+			    struct skcipher_walk *walk)
 {
 	u8 *ctrblk = walk->iv;
 	u64 keystream[AES_BLOCK_SIZE / sizeof(u64)];
@@ -349,40 +333,35 @@ static void ctr_crypt_final(struct crypto_sparc64_aes_ctx *ctx,
 	crypto_inc(ctrblk, AES_BLOCK_SIZE);
 }
 
-static int ctr_crypt(struct blkcipher_desc *desc,
-		     struct scatterlist *dst, struct scatterlist *src,
-		     unsigned int nbytes)
+static int ctr_crypt(struct skcipher_request *req)
 {
-	struct crypto_sparc64_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct crypto_sparc64_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
 	ctx->ops->load_encrypt_keys(&ctx->key[0]);
 	while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
-		unsigned int block_len = nbytes & AES_BLOCK_MASK;
-
-		if (likely(block_len)) {
-			ctx->ops->ctr_crypt(&ctx->key[0],
-					    (const u64 *)walk.src.virt.addr,
-					    (u64 *) walk.dst.virt.addr,
-					    block_len, (u64 *) walk.iv);
-		}
-		nbytes &= AES_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		ctx->ops->ctr_crypt(&ctx->key[0], walk.src.virt.addr,
+				    walk.dst.virt.addr,
+				    round_down(nbytes, AES_BLOCK_SIZE),
+				    walk.iv);
+		err = skcipher_walk_done(&walk, nbytes % AES_BLOCK_SIZE);
 	}
 	if (walk.nbytes) {
 		ctr_crypt_final(ctx, &walk);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = skcipher_walk_done(&walk, 0);
 	}
 	fprs_write(0);
 	return err;
 }
 
-static struct crypto_alg algs[] = { {
+static struct crypto_alg cipher_alg = {
 	.cra_name		= "aes",
 	.cra_driver_name	= "aes-sparc64",
 	.cra_priority		= SPARC_CR_OPCODE_PRIORITY,
@@ -400,66 +379,53 @@ static struct crypto_alg algs[] = { {
 			.cia_decrypt		= crypto_aes_decrypt
 		}
 	}
-}, {
-	.cra_name		= "ecb(aes)",
-	.cra_driver_name	= "ecb-aes-sparc64",
-	.cra_priority		= SPARC_CR_OPCODE_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct crypto_sparc64_aes_ctx),
-	.cra_alignmask		= 7,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= AES_MIN_KEY_SIZE,
-			.max_keysize	= AES_MAX_KEY_SIZE,
-			.setkey		= aes_set_key,
-			.encrypt	= ecb_encrypt,
-			.decrypt	= ecb_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "cbc(aes)",
-	.cra_driver_name	= "cbc-aes-sparc64",
-	.cra_priority		= SPARC_CR_OPCODE_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct crypto_sparc64_aes_ctx),
-	.cra_alignmask		= 7,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= AES_MIN_KEY_SIZE,
-			.max_keysize	= AES_MAX_KEY_SIZE,
-			.ivsize		= AES_BLOCK_SIZE,
-			.setkey		= aes_set_key,
-			.encrypt	= cbc_encrypt,
-			.decrypt	= cbc_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ctr(aes)",
-	.cra_driver_name	= "ctr-aes-sparc64",
-	.cra_priority		= SPARC_CR_OPCODE_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct crypto_sparc64_aes_ctx),
-	.cra_alignmask		= 7,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= AES_MIN_KEY_SIZE,
-			.max_keysize	= AES_MAX_KEY_SIZE,
-			.ivsize		= AES_BLOCK_SIZE,
-			.setkey		= aes_set_key,
-			.encrypt	= ctr_crypt,
-			.decrypt	= ctr_crypt,
-		},
-	},
-} };
+};
+
+static struct skcipher_alg skcipher_algs[] = {
+	{
+		.base.cra_name		= "ecb(aes)",
+		.base.cra_driver_name	= "ecb-aes-sparc64",
+		.base.cra_priority	= SPARC_CR_OPCODE_PRIORITY,
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct crypto_sparc64_aes_ctx),
+		.base.cra_alignmask	= 7,
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.setkey			= aes_set_key_skcipher,
+		.encrypt		= ecb_encrypt,
+		.decrypt		= ecb_decrypt,
+	}, {
+		.base.cra_name		= "cbc(aes)",
+		.base.cra_driver_name	= "cbc-aes-sparc64",
+		.base.cra_priority	= SPARC_CR_OPCODE_PRIORITY,
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct crypto_sparc64_aes_ctx),
+		.base.cra_alignmask	= 7,
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.ivsize			= AES_BLOCK_SIZE,
+		.setkey			= aes_set_key_skcipher,
+		.encrypt		= cbc_encrypt,
+		.decrypt		= cbc_decrypt,
+	}, {
+		.base.cra_name		= "ctr(aes)",
+		.base.cra_driver_name	= "ctr-aes-sparc64",
+		.base.cra_priority	= SPARC_CR_OPCODE_PRIORITY,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct crypto_sparc64_aes_ctx),
+		.base.cra_alignmask	= 7,
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.ivsize			= AES_BLOCK_SIZE,
+		.setkey			= aes_set_key_skcipher,
+		.encrypt		= ctr_crypt,
+		.decrypt		= ctr_crypt,
+		.chunksize		= AES_BLOCK_SIZE,
+	}
+};
 
 static bool __init sparc64_has_aes_opcode(void)
 {
@@ -477,17 +443,27 @@ static bool __init sparc64_has_aes_opcode(void)
 
 static int __init aes_sparc64_mod_init(void)
 {
-	if (sparc64_has_aes_opcode()) {
-		pr_info("Using sparc64 aes opcodes optimized AES implementation\n");
-		return crypto_register_algs(algs, ARRAY_SIZE(algs));
+	int err;
+
+	if (!sparc64_has_aes_opcode()) {
+		pr_info("sparc64 aes opcodes not available.\n");
+		return -ENODEV;
 	}
-	pr_info("sparc64 aes opcodes not available.\n");
-	return -ENODEV;
+	pr_info("Using sparc64 aes opcodes optimized AES implementation\n");
+	err = crypto_register_alg(&cipher_alg);
+	if (err)
+		return err;
+	err = crypto_register_skciphers(skcipher_algs,
+					ARRAY_SIZE(skcipher_algs));
+	if (err)
+		crypto_unregister_alg(&cipher_alg);
+	return err;
 }
 
 static void __exit aes_sparc64_mod_fini(void)
 {
-	crypto_unregister_algs(algs, ARRAY_SIZE(algs));
+	crypto_unregister_alg(&cipher_alg);
+	crypto_unregister_skciphers(skcipher_algs, ARRAY_SIZE(skcipher_algs));
 }
 
 module_init(aes_sparc64_mod_init);
diff --git a/arch/sparc/crypto/camellia_glue.c b/arch/sparc/crypto/camellia_glue.c
index 3823f9491a72..1700f863748c 100644
--- a/arch/sparc/crypto/camellia_glue.c
+++ b/arch/sparc/crypto/camellia_glue.c
@@ -12,6 +12,7 @@
 #include <linux/mm.h>
 #include <linux/types.h>
 #include <crypto/algapi.h>
+#include <crypto/internal/skcipher.h>
 
 #include <asm/fpumacro.h>
 #include <asm/pstate.h>
@@ -52,6 +53,12 @@ static int camellia_set_key(struct crypto_tfm *tfm, const u8 *_in_key,
 	return 0;
 }
 
+static int camellia_set_key_skcipher(struct crypto_skcipher *tfm,
+				     const u8 *in_key, unsigned int key_len)
+{
+	return camellia_set_key(crypto_skcipher_tfm(tfm), in_key, key_len);
+}
+
 extern void camellia_sparc64_crypt(const u64 *key, const u32 *input,
 				   u32 *output, unsigned int key_len);
 
@@ -81,61 +88,46 @@ typedef void ecb_crypt_op(const u64 *input, u64 *output, unsigned int len,
 extern ecb_crypt_op camellia_sparc64_ecb_crypt_3_grand_rounds;
 extern ecb_crypt_op camellia_sparc64_ecb_crypt_4_grand_rounds;
 
-#define CAMELLIA_BLOCK_MASK	(~(CAMELLIA_BLOCK_SIZE - 1))
-
-static int __ecb_crypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes, bool encrypt)
+static int __ecb_crypt(struct skcipher_request *req, bool encrypt)
 {
-	struct camellia_sparc64_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct camellia_sparc64_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
 	ecb_crypt_op *op;
 	const u64 *key;
+	unsigned int nbytes;
 	int err;
 
 	op = camellia_sparc64_ecb_crypt_3_grand_rounds;
 	if (ctx->key_len != 16)
 		op = camellia_sparc64_ecb_crypt_4_grand_rounds;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
 	if (encrypt)
 		key = &ctx->encrypt_key[0];
 	else
 		key = &ctx->decrypt_key[0];
 	camellia_sparc64_load_keys(key, ctx->key_len);
-	while ((nbytes = walk.nbytes)) {
-		unsigned int block_len = nbytes & CAMELLIA_BLOCK_MASK;
-
-		if (likely(block_len)) {
-			const u64 *src64;
-			u64 *dst64;
-
-			src64 = (const u64 *)walk.src.virt.addr;
-			dst64 = (u64 *) walk.dst.virt.addr;
-			op(src64, dst64, block_len, key);
-		}
-		nbytes &= CAMELLIA_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+	while ((nbytes = walk.nbytes) != 0) {
+		op(walk.src.virt.addr, walk.dst.virt.addr,
+		   round_down(nbytes, CAMELLIA_BLOCK_SIZE), key);
+		err = skcipher_walk_done(&walk, nbytes % CAMELLIA_BLOCK_SIZE);
 	}
 	fprs_write(0);
 	return err;
 }
 
-static int ecb_encrypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes)
+static int ecb_encrypt(struct skcipher_request *req)
 {
-	return __ecb_crypt(desc, dst, src, nbytes, true);
+	return __ecb_crypt(req, true);
 }
 
-static int ecb_decrypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes)
+static int ecb_decrypt(struct skcipher_request *req)
 {
-	return __ecb_crypt(desc, dst, src, nbytes, false);
+	return __ecb_crypt(req, false);
 }
 
 typedef void cbc_crypt_op(const u64 *input, u64 *output, unsigned int len,
@@ -146,85 +138,65 @@ extern cbc_crypt_op camellia_sparc64_cbc_encrypt_4_grand_rounds;
 extern cbc_crypt_op camellia_sparc64_cbc_decrypt_3_grand_rounds;
 extern cbc_crypt_op camellia_sparc64_cbc_decrypt_4_grand_rounds;
 
-static int cbc_encrypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes)
+static int cbc_encrypt(struct skcipher_request *req)
 {
-	struct camellia_sparc64_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct camellia_sparc64_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
 	cbc_crypt_op *op;
 	const u64 *key;
+	unsigned int nbytes;
 	int err;
 
 	op = camellia_sparc64_cbc_encrypt_3_grand_rounds;
 	if (ctx->key_len != 16)
 		op = camellia_sparc64_cbc_encrypt_4_grand_rounds;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
 	key = &ctx->encrypt_key[0];
 	camellia_sparc64_load_keys(key, ctx->key_len);
-	while ((nbytes = walk.nbytes)) {
-		unsigned int block_len = nbytes & CAMELLIA_BLOCK_MASK;
-
-		if (likely(block_len)) {
-			const u64 *src64;
-			u64 *dst64;
-
-			src64 = (const u64 *)walk.src.virt.addr;
-			dst64 = (u64 *) walk.dst.virt.addr;
-			op(src64, dst64, block_len, key,
-			   (u64 *) walk.iv);
-		}
-		nbytes &= CAMELLIA_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+	while ((nbytes = walk.nbytes) != 0) {
+		op(walk.src.virt.addr, walk.dst.virt.addr,
+		   round_down(nbytes, CAMELLIA_BLOCK_SIZE), key, walk.iv);
+		err = skcipher_walk_done(&walk, nbytes % CAMELLIA_BLOCK_SIZE);
 	}
 	fprs_write(0);
 	return err;
 }
 
-static int cbc_decrypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes)
+static int cbc_decrypt(struct skcipher_request *req)
 {
-	struct camellia_sparc64_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct camellia_sparc64_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
 	cbc_crypt_op *op;
 	const u64 *key;
+	unsigned int nbytes;
 	int err;
 
 	op = camellia_sparc64_cbc_decrypt_3_grand_rounds;
 	if (ctx->key_len != 16)
 		op = camellia_sparc64_cbc_decrypt_4_grand_rounds;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
 	key = &ctx->decrypt_key[0];
 	camellia_sparc64_load_keys(key, ctx->key_len);
-	while ((nbytes = walk.nbytes)) {
-		unsigned int block_len = nbytes & CAMELLIA_BLOCK_MASK;
-
-		if (likely(block_len)) {
-			const u64 *src64;
-			u64 *dst64;
-
-			src64 = (const u64 *)walk.src.virt.addr;
-			dst64 = (u64 *) walk.dst.virt.addr;
-			op(src64, dst64, block_len, key,
-			   (u64 *) walk.iv);
-		}
-		nbytes &= CAMELLIA_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+	while ((nbytes = walk.nbytes) != 0) {
+		op(walk.src.virt.addr, walk.dst.virt.addr,
+		   round_down(nbytes, CAMELLIA_BLOCK_SIZE), key, walk.iv);
+		err = skcipher_walk_done(&walk, nbytes % CAMELLIA_BLOCK_SIZE);
 	}
 	fprs_write(0);
 	return err;
 }
 
-static struct crypto_alg algs[] = { {
+static struct crypto_alg cipher_alg = {
 	.cra_name		= "camellia",
 	.cra_driver_name	= "camellia-sparc64",
 	.cra_priority		= SPARC_CR_OPCODE_PRIORITY,
@@ -242,46 +214,37 @@ static struct crypto_alg algs[] = { {
 			.cia_decrypt		= camellia_decrypt
 		}
 	}
-}, {
-	.cra_name		= "ecb(camellia)",
-	.cra_driver_name	= "ecb-camellia-sparc64",
-	.cra_priority		= SPARC_CR_OPCODE_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct camellia_sparc64_ctx),
-	.cra_alignmask		= 7,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.setkey		= camellia_set_key,
-			.encrypt	= ecb_encrypt,
-			.decrypt	= ecb_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "cbc(camellia)",
-	.cra_driver_name	= "cbc-camellia-sparc64",
-	.cra_priority		= SPARC_CR_OPCODE_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct camellia_sparc64_ctx),
-	.cra_alignmask		= 7,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= camellia_set_key,
-			.encrypt	= cbc_encrypt,
-			.decrypt	= cbc_decrypt,
-		},
-	},
-}
+};
+
+static struct skcipher_alg skcipher_algs[] = {
+	{
+		.base.cra_name		= "ecb(camellia)",
+		.base.cra_driver_name	= "ecb-camellia-sparc64",
+		.base.cra_priority	= SPARC_CR_OPCODE_PRIORITY,
+		.base.cra_blocksize	= CAMELLIA_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct camellia_sparc64_ctx),
+		.base.cra_alignmask	= 7,
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAMELLIA_MIN_KEY_SIZE,
+		.max_keysize		= CAMELLIA_MAX_KEY_SIZE,
+		.setkey			= camellia_set_key_skcipher,
+		.encrypt		= ecb_encrypt,
+		.decrypt		= ecb_decrypt,
+	}, {
+		.base.cra_name		= "cbc(camellia)",
+		.base.cra_driver_name	= "cbc-camellia-sparc64",
+		.base.cra_priority	= SPARC_CR_OPCODE_PRIORITY,
+		.base.cra_blocksize	= CAMELLIA_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct camellia_sparc64_ctx),
+		.base.cra_alignmask	= 7,
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAMELLIA_MIN_KEY_SIZE,
+		.max_keysize		= CAMELLIA_MAX_KEY_SIZE,
+		.ivsize			= CAMELLIA_BLOCK_SIZE,
+		.setkey			= camellia_set_key_skcipher,
+		.encrypt		= cbc_encrypt,
+		.decrypt		= cbc_decrypt,
+	}
 };
 
 static bool __init sparc64_has_camellia_opcode(void)
@@ -300,17 +263,27 @@ static bool __init sparc64_has_camellia_opcode(void)
 
 static int __init camellia_sparc64_mod_init(void)
 {
-	if (sparc64_has_camellia_opcode()) {
-		pr_info("Using sparc64 camellia opcodes optimized CAMELLIA implementation\n");
-		return crypto_register_algs(algs, ARRAY_SIZE(algs));
+	int err;
+
+	if (!sparc64_has_camellia_opcode()) {
+		pr_info("sparc64 camellia opcodes not available.\n");
+		return -ENODEV;
 	}
-	pr_info("sparc64 camellia opcodes not available.\n");
-	return -ENODEV;
+	pr_info("Using sparc64 camellia opcodes optimized CAMELLIA implementation\n");
+	err = crypto_register_alg(&cipher_alg);
+	if (err)
+		return err;
+	err = crypto_register_skciphers(skcipher_algs,
+					ARRAY_SIZE(skcipher_algs));
+	if (err)
+		crypto_unregister_alg(&cipher_alg);
+	return err;
 }
 
 static void __exit camellia_sparc64_mod_fini(void)
 {
-	crypto_unregister_algs(algs, ARRAY_SIZE(algs));
+	crypto_unregister_alg(&cipher_alg);
+	crypto_unregister_skciphers(skcipher_algs, ARRAY_SIZE(skcipher_algs));
 }
 
 module_init(camellia_sparc64_mod_init);
diff --git a/arch/sparc/crypto/des_glue.c b/arch/sparc/crypto/des_glue.c
index db6010b4e52e..a499102bf706 100644
--- a/arch/sparc/crypto/des_glue.c
+++ b/arch/sparc/crypto/des_glue.c
@@ -13,6 +13,7 @@
 #include <linux/types.h>
 #include <crypto/algapi.h>
 #include <crypto/internal/des.h>
+#include <crypto/internal/skcipher.h>
 
 #include <asm/fpumacro.h>
 #include <asm/pstate.h>
@@ -61,6 +62,12 @@ static int des_set_key(struct crypto_tfm *tfm, const u8 *key,
 	return 0;
 }
 
+static int des_set_key_skcipher(struct crypto_skcipher *tfm, const u8 *key,
+				unsigned int keylen)
+{
+	return des_set_key(crypto_skcipher_tfm(tfm), key, keylen);
+}
+
 extern void des_sparc64_crypt(const u64 *key, const u64 *input,
 			      u64 *output);
 
@@ -85,113 +92,90 @@ extern void des_sparc64_load_keys(const u64 *key);
 extern void des_sparc64_ecb_crypt(const u64 *input, u64 *output,
 				  unsigned int len);
 
-#define DES_BLOCK_MASK	(~(DES_BLOCK_SIZE - 1))
-
-static int __ecb_crypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes, bool encrypt)
+static int __ecb_crypt(struct skcipher_request *req, bool encrypt)
 {
-	struct des_sparc64_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct des_sparc64_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
 	if (encrypt)
 		des_sparc64_load_keys(&ctx->encrypt_expkey[0]);
 	else
 		des_sparc64_load_keys(&ctx->decrypt_expkey[0]);
-	while ((nbytes = walk.nbytes)) {
-		unsigned int block_len = nbytes & DES_BLOCK_MASK;
-
-		if (likely(block_len)) {
-			des_sparc64_ecb_crypt((const u64 *)walk.src.virt.addr,
-					      (u64 *) walk.dst.virt.addr,
-					      block_len);
-		}
-		nbytes &= DES_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+	while ((nbytes = walk.nbytes) != 0) {
+		des_sparc64_ecb_crypt(walk.src.virt.addr, walk.dst.virt.addr,
+				      round_down(nbytes, DES_BLOCK_SIZE));
+		err = skcipher_walk_done(&walk, nbytes % DES_BLOCK_SIZE);
 	}
 	fprs_write(0);
 	return err;
 }
 
-static int ecb_encrypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes)
+static int ecb_encrypt(struct skcipher_request *req)
 {
-	return __ecb_crypt(desc, dst, src, nbytes, true);
+	return __ecb_crypt(req, true);
 }
 
-static int ecb_decrypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes)
+static int ecb_decrypt(struct skcipher_request *req)
 {
-	return __ecb_crypt(desc, dst, src, nbytes, false);
+	return __ecb_crypt(req, false);
 }
 
 extern void des_sparc64_cbc_encrypt(const u64 *input, u64 *output,
 				    unsigned int len, u64 *iv);
 
-static int cbc_encrypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes)
+extern void des_sparc64_cbc_decrypt(const u64 *input, u64 *output,
+				    unsigned int len, u64 *iv);
+
+static int __cbc_crypt(struct skcipher_request *req, bool encrypt)
 {
-	struct des_sparc64_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct des_sparc64_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-
-	des_sparc64_load_keys(&ctx->encrypt_expkey[0]);
-	while ((nbytes = walk.nbytes)) {
-		unsigned int block_len = nbytes & DES_BLOCK_MASK;
+	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
-		if (likely(block_len)) {
-			des_sparc64_cbc_encrypt((const u64 *)walk.src.virt.addr,
-						(u64 *) walk.dst.virt.addr,
-						block_len, (u64 *) walk.iv);
-		}
-		nbytes &= DES_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+	if (encrypt)
+		des_sparc64_load_keys(&ctx->encrypt_expkey[0]);
+	else
+		des_sparc64_load_keys(&ctx->decrypt_expkey[0]);
+	while ((nbytes = walk.nbytes) != 0) {
+		if (encrypt)
+			des_sparc64_cbc_encrypt(walk.src.virt.addr,
+						walk.dst.virt.addr,
+						round_down(nbytes,
+							   DES_BLOCK_SIZE),
+						walk.iv);
+		else
+			des_sparc64_cbc_decrypt(walk.src.virt.addr,
+						walk.dst.virt.addr,
+						round_down(nbytes,
+							   DES_BLOCK_SIZE),
+						walk.iv);
+		err = skcipher_walk_done(&walk, nbytes % DES_BLOCK_SIZE);
 	}
 	fprs_write(0);
 	return err;
 }
 
-extern void des_sparc64_cbc_decrypt(const u64 *input, u64 *output,
-				    unsigned int len, u64 *iv);
-
-static int cbc_decrypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes)
+static int cbc_encrypt(struct skcipher_request *req)
 {
-	struct des_sparc64_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	int err;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-
-	des_sparc64_load_keys(&ctx->decrypt_expkey[0]);
-	while ((nbytes = walk.nbytes)) {
-		unsigned int block_len = nbytes & DES_BLOCK_MASK;
+	return __cbc_crypt(req, true);
+}
 
-		if (likely(block_len)) {
-			des_sparc64_cbc_decrypt((const u64 *)walk.src.virt.addr,
-						(u64 *) walk.dst.virt.addr,
-						block_len, (u64 *) walk.iv);
-		}
-		nbytes &= DES_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
-	fprs_write(0);
-	return err;
+static int cbc_decrypt(struct skcipher_request *req)
+{
+	return __cbc_crypt(req, false);
 }
 
 static int des3_ede_set_key(struct crypto_tfm *tfm, const u8 *key,
@@ -227,6 +211,12 @@ static int des3_ede_set_key(struct crypto_tfm *tfm, const u8 *key,
 	return 0;
 }
 
+static int des3_ede_set_key_skcipher(struct crypto_skcipher *tfm, const u8 *key,
+				     unsigned int keylen)
+{
+	return des3_ede_set_key(crypto_skcipher_tfm(tfm), key, keylen);
+}
+
 extern void des3_ede_sparc64_crypt(const u64 *key, const u64 *input,
 				   u64 *output);
 
@@ -251,241 +241,196 @@ extern void des3_ede_sparc64_load_keys(const u64 *key);
 extern void des3_ede_sparc64_ecb_crypt(const u64 *expkey, const u64 *input,
 				       u64 *output, unsigned int len);
 
-static int __ecb3_crypt(struct blkcipher_desc *desc,
-			struct scatterlist *dst, struct scatterlist *src,
-			unsigned int nbytes, bool encrypt)
+static int __ecb3_crypt(struct skcipher_request *req, bool encrypt)
 {
-	struct des3_ede_sparc64_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct des3_ede_sparc64_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
 	const u64 *K;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
 	if (encrypt)
 		K = &ctx->encrypt_expkey[0];
 	else
 		K = &ctx->decrypt_expkey[0];
 	des3_ede_sparc64_load_keys(K);
-	while ((nbytes = walk.nbytes)) {
-		unsigned int block_len = nbytes & DES_BLOCK_MASK;
-
-		if (likely(block_len)) {
-			const u64 *src64 = (const u64 *)walk.src.virt.addr;
-			des3_ede_sparc64_ecb_crypt(K, src64,
-						   (u64 *) walk.dst.virt.addr,
-						   block_len);
-		}
-		nbytes &= DES_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+	while ((nbytes = walk.nbytes) != 0) {
+		des3_ede_sparc64_ecb_crypt(K, walk.src.virt.addr,
+					   walk.dst.virt.addr,
+					   round_down(nbytes, DES_BLOCK_SIZE));
+		err = skcipher_walk_done(&walk, nbytes % DES_BLOCK_SIZE);
 	}
 	fprs_write(0);
 	return err;
 }
 
-static int ecb3_encrypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes)
+static int ecb3_encrypt(struct skcipher_request *req)
 {
-	return __ecb3_crypt(desc, dst, src, nbytes, true);
+	return __ecb3_crypt(req, true);
 }
 
-static int ecb3_decrypt(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes)
+static int ecb3_decrypt(struct skcipher_request *req)
 {
-	return __ecb3_crypt(desc, dst, src, nbytes, false);
+	return __ecb3_crypt(req, false);
 }
 
 extern void des3_ede_sparc64_cbc_encrypt(const u64 *expkey, const u64 *input,
 					 u64 *output, unsigned int len,
 					 u64 *iv);
 
-static int cbc3_encrypt(struct blkcipher_desc *desc,
-			struct scatterlist *dst, struct scatterlist *src,
-			unsigned int nbytes)
-{
-	struct des3_ede_sparc64_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	const u64 *K;
-	int err;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-
-	K = &ctx->encrypt_expkey[0];
-	des3_ede_sparc64_load_keys(K);
-	while ((nbytes = walk.nbytes)) {
-		unsigned int block_len = nbytes & DES_BLOCK_MASK;
-
-		if (likely(block_len)) {
-			const u64 *src64 = (const u64 *)walk.src.virt.addr;
-			des3_ede_sparc64_cbc_encrypt(K, src64,
-						     (u64 *) walk.dst.virt.addr,
-						     block_len,
-						     (u64 *) walk.iv);
-		}
-		nbytes &= DES_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
-	fprs_write(0);
-	return err;
-}
-
 extern void des3_ede_sparc64_cbc_decrypt(const u64 *expkey, const u64 *input,
 					 u64 *output, unsigned int len,
 					 u64 *iv);
 
-static int cbc3_decrypt(struct blkcipher_desc *desc,
-			struct scatterlist *dst, struct scatterlist *src,
-			unsigned int nbytes)
+static int __cbc3_crypt(struct skcipher_request *req, bool encrypt)
 {
-	struct des3_ede_sparc64_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct des3_ede_sparc64_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
 	const u64 *K;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
-	K = &ctx->decrypt_expkey[0];
+	if (encrypt)
+		K = &ctx->encrypt_expkey[0];
+	else
+		K = &ctx->decrypt_expkey[0];
 	des3_ede_sparc64_load_keys(K);
-	while ((nbytes = walk.nbytes)) {
-		unsigned int block_len = nbytes & DES_BLOCK_MASK;
-
-		if (likely(block_len)) {
-			const u64 *src64 = (const u64 *)walk.src.virt.addr;
-			des3_ede_sparc64_cbc_decrypt(K, src64,
-						     (u64 *) walk.dst.virt.addr,
-						     block_len,
-						     (u64 *) walk.iv);
-		}
-		nbytes &= DES_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+	while ((nbytes = walk.nbytes) != 0) {
+		if (encrypt)
+			des3_ede_sparc64_cbc_encrypt(K, walk.src.virt.addr,
+						     walk.dst.virt.addr,
+						     round_down(nbytes,
+								DES_BLOCK_SIZE),
+						     walk.iv);
+		else
+			des3_ede_sparc64_cbc_decrypt(K, walk.src.virt.addr,
+						     walk.dst.virt.addr,
+						     round_down(nbytes,
+								DES_BLOCK_SIZE),
+						     walk.iv);
+		err = skcipher_walk_done(&walk, nbytes % DES_BLOCK_SIZE);
 	}
 	fprs_write(0);
 	return err;
 }
 
-static struct crypto_alg algs[] = { {
-	.cra_name		= "des",
-	.cra_driver_name	= "des-sparc64",
-	.cra_priority		= SPARC_CR_OPCODE_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct des_sparc64_ctx),
-	.cra_alignmask		= 7,
-	.cra_module		= THIS_MODULE,
-	.cra_u	= {
-		.cipher	= {
-			.cia_min_keysize	= DES_KEY_SIZE,
-			.cia_max_keysize	= DES_KEY_SIZE,
-			.cia_setkey		= des_set_key,
-			.cia_encrypt		= sparc_des_encrypt,
-			.cia_decrypt		= sparc_des_decrypt
+static int cbc3_encrypt(struct skcipher_request *req)
+{
+	return __cbc3_crypt(req, true);
+}
+
+static int cbc3_decrypt(struct skcipher_request *req)
+{
+	return __cbc3_crypt(req, false);
+}
+
+static struct crypto_alg cipher_algs[] = {
+	{
+		.cra_name		= "des",
+		.cra_driver_name	= "des-sparc64",
+		.cra_priority		= SPARC_CR_OPCODE_PRIORITY,
+		.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
+		.cra_blocksize		= DES_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct des_sparc64_ctx),
+		.cra_alignmask		= 7,
+		.cra_module		= THIS_MODULE,
+		.cra_u	= {
+			.cipher	= {
+				.cia_min_keysize	= DES_KEY_SIZE,
+				.cia_max_keysize	= DES_KEY_SIZE,
+				.cia_setkey		= des_set_key,
+				.cia_encrypt		= sparc_des_encrypt,
+				.cia_decrypt		= sparc_des_decrypt
+			}
 		}
-	}
-}, {
-	.cra_name		= "ecb(des)",
-	.cra_driver_name	= "ecb-des-sparc64",
-	.cra_priority		= SPARC_CR_OPCODE_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct des_sparc64_ctx),
-	.cra_alignmask		= 7,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= DES_KEY_SIZE,
-			.max_keysize	= DES_KEY_SIZE,
-			.setkey		= des_set_key,
-			.encrypt	= ecb_encrypt,
-			.decrypt	= ecb_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "cbc(des)",
-	.cra_driver_name	= "cbc-des-sparc64",
-	.cra_priority		= SPARC_CR_OPCODE_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct des_sparc64_ctx),
-	.cra_alignmask		= 7,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= DES_KEY_SIZE,
-			.max_keysize	= DES_KEY_SIZE,
-			.ivsize		= DES_BLOCK_SIZE,
-			.setkey		= des_set_key,
-			.encrypt	= cbc_encrypt,
-			.decrypt	= cbc_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "des3_ede",
-	.cra_driver_name	= "des3_ede-sparc64",
-	.cra_priority		= SPARC_CR_OPCODE_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
-	.cra_blocksize		= DES3_EDE_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct des3_ede_sparc64_ctx),
-	.cra_alignmask		= 7,
-	.cra_module		= THIS_MODULE,
-	.cra_u	= {
-		.cipher	= {
-			.cia_min_keysize	= DES3_EDE_KEY_SIZE,
-			.cia_max_keysize	= DES3_EDE_KEY_SIZE,
-			.cia_setkey		= des3_ede_set_key,
-			.cia_encrypt		= sparc_des3_ede_encrypt,
-			.cia_decrypt		= sparc_des3_ede_decrypt
+	}, {
+		.cra_name		= "des3_ede",
+		.cra_driver_name	= "des3_ede-sparc64",
+		.cra_priority		= SPARC_CR_OPCODE_PRIORITY,
+		.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
+		.cra_blocksize		= DES3_EDE_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct des3_ede_sparc64_ctx),
+		.cra_alignmask		= 7,
+		.cra_module		= THIS_MODULE,
+		.cra_u	= {
+			.cipher	= {
+				.cia_min_keysize	= DES3_EDE_KEY_SIZE,
+				.cia_max_keysize	= DES3_EDE_KEY_SIZE,
+				.cia_setkey		= des3_ede_set_key,
+				.cia_encrypt		= sparc_des3_ede_encrypt,
+				.cia_decrypt		= sparc_des3_ede_decrypt
+			}
 		}
 	}
-}, {
-	.cra_name		= "ecb(des3_ede)",
-	.cra_driver_name	= "ecb-des3_ede-sparc64",
-	.cra_priority		= SPARC_CR_OPCODE_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= DES3_EDE_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct des3_ede_sparc64_ctx),
-	.cra_alignmask		= 7,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= DES3_EDE_KEY_SIZE,
-			.max_keysize	= DES3_EDE_KEY_SIZE,
-			.setkey		= des3_ede_set_key,
-			.encrypt	= ecb3_encrypt,
-			.decrypt	= ecb3_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "cbc(des3_ede)",
-	.cra_driver_name	= "cbc-des3_ede-sparc64",
-	.cra_priority		= SPARC_CR_OPCODE_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= DES3_EDE_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct des3_ede_sparc64_ctx),
-	.cra_alignmask		= 7,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= DES3_EDE_KEY_SIZE,
-			.max_keysize	= DES3_EDE_KEY_SIZE,
-			.ivsize		= DES3_EDE_BLOCK_SIZE,
-			.setkey		= des3_ede_set_key,
-			.encrypt	= cbc3_encrypt,
-			.decrypt	= cbc3_decrypt,
-		},
-	},
-} };
+};
+
+static struct skcipher_alg skcipher_algs[] = {
+	{
+		.base.cra_name		= "ecb(des)",
+		.base.cra_driver_name	= "ecb-des-sparc64",
+		.base.cra_priority	= SPARC_CR_OPCODE_PRIORITY,
+		.base.cra_blocksize	= DES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct des_sparc64_ctx),
+		.base.cra_alignmask	= 7,
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= DES_KEY_SIZE,
+		.max_keysize		= DES_KEY_SIZE,
+		.setkey			= des_set_key_skcipher,
+		.encrypt		= ecb_encrypt,
+		.decrypt		= ecb_decrypt,
+	}, {
+		.base.cra_name		= "cbc(des)",
+		.base.cra_driver_name	= "cbc-des-sparc64",
+		.base.cra_priority	= SPARC_CR_OPCODE_PRIORITY,
+		.base.cra_blocksize	= DES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct des_sparc64_ctx),
+		.base.cra_alignmask	= 7,
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= DES_KEY_SIZE,
+		.max_keysize		= DES_KEY_SIZE,
+		.ivsize			= DES_BLOCK_SIZE,
+		.setkey			= des_set_key_skcipher,
+		.encrypt		= cbc_encrypt,
+		.decrypt		= cbc_decrypt,
+	}, {
+		.base.cra_name		= "ecb(des3_ede)",
+		.base.cra_driver_name	= "ecb-des3_ede-sparc64",
+		.base.cra_priority	= SPARC_CR_OPCODE_PRIORITY,
+		.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct des3_ede_sparc64_ctx),
+		.base.cra_alignmask	= 7,
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= DES3_EDE_KEY_SIZE,
+		.max_keysize		= DES3_EDE_KEY_SIZE,
+		.setkey			= des3_ede_set_key_skcipher,
+		.encrypt		= ecb3_encrypt,
+		.decrypt		= ecb3_decrypt,
+	}, {
+		.base.cra_name		= "cbc(des3_ede)",
+		.base.cra_driver_name	= "cbc-des3_ede-sparc64",
+		.base.cra_priority	= SPARC_CR_OPCODE_PRIORITY,
+		.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct des3_ede_sparc64_ctx),
+		.base.cra_alignmask	= 7,
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= DES3_EDE_KEY_SIZE,
+		.max_keysize		= DES3_EDE_KEY_SIZE,
+		.ivsize			= DES3_EDE_BLOCK_SIZE,
+		.setkey			= des3_ede_set_key_skcipher,
+		.encrypt		= cbc3_encrypt,
+		.decrypt		= cbc3_decrypt,
+	}
+};
 
 static bool __init sparc64_has_des_opcode(void)
 {
@@ -503,17 +448,27 @@ static bool __init sparc64_has_des_opcode(void)
 
 static int __init des_sparc64_mod_init(void)
 {
-	if (sparc64_has_des_opcode()) {
-		pr_info("Using sparc64 des opcodes optimized DES implementation\n");
-		return crypto_register_algs(algs, ARRAY_SIZE(algs));
+	int err;
+
+	if (!sparc64_has_des_opcode()) {
+		pr_info("sparc64 des opcodes not available.\n");
+		return -ENODEV;
 	}
-	pr_info("sparc64 des opcodes not available.\n");
-	return -ENODEV;
+	pr_info("Using sparc64 des opcodes optimized DES implementation\n");
+	err = crypto_register_algs(cipher_algs, ARRAY_SIZE(cipher_algs));
+	if (err)
+		return err;
+	err = crypto_register_skciphers(skcipher_algs,
+					ARRAY_SIZE(skcipher_algs));
+	if (err)
+		crypto_unregister_algs(cipher_algs, ARRAY_SIZE(cipher_algs));
+	return err;
 }
 
 static void __exit des_sparc64_mod_fini(void)
 {
-	crypto_unregister_algs(algs, ARRAY_SIZE(algs));
+	crypto_unregister_algs(cipher_algs, ARRAY_SIZE(cipher_algs));
+	crypto_unregister_skciphers(skcipher_algs, ARRAY_SIZE(skcipher_algs));
 }
 
 module_init(des_sparc64_mod_init);
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index a8275fea4b70..9b4506373353 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1673,9 +1673,9 @@ void __init setup_per_cpu_areas(void)
 					    pcpu_alloc_bootmem,
 					    pcpu_free_bootmem);
 		if (rc)
-			pr_warning("PERCPU: %s allocator failed (%d), "
-				   "falling back to page size\n",
-				   pcpu_fc_names[pcpu_chosen_fc], rc);
+			pr_warn("PERCPU: %s allocator failed (%d), "
+				"falling back to page size\n",
+				pcpu_fc_names[pcpu_chosen_fc], rc);
 	}
 	if (rc < 0)
 		rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE,
diff --git a/arch/um/configs/kunit_defconfig b/arch/um/configs/kunit_defconfig
new file mode 100644
index 000000000000..9235b7d42d38
--- /dev/null
+++ b/arch/um/configs/kunit_defconfig
@@ -0,0 +1,3 @@
+CONFIG_KUNIT=y
+CONFIG_KUNIT_TEST=y
+CONFIG_KUNIT_EXAMPLE_TEST=y
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8ef85139553f..f2aed8012e9c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -24,7 +24,7 @@ config X86_64
 	depends on 64BIT
 	# Options that are inherently 64-bit kernel only:
 	select ARCH_HAS_GIGANTIC_PAGE
-	select ARCH_SUPPORTS_INT128
+	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select HAVE_ARCH_SOFT_DIRTY
 	select MODULES_USE_ELF_RELA
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index bf9cd83de777..409c00f74e60 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -316,10 +316,6 @@ config UNWINDER_FRAME_POINTER
 	  unwinder, but the kernel text size will grow by ~3% and the kernel's
 	  overall performance will degrade by roughly 5-10%.
 
-	  This option is recommended if you want to use the livepatch
-	  consistency model, as this is currently the only way to get a
-	  reliable stack trace (CONFIG_HAVE_RELIABLE_STACKTRACE).
-
 config UNWINDER_GUESS
 	bool "Guess unwinder"
 	depends on EXPERT
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 759b1a927826..958440eae27e 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o
 
 obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o
 obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o
+obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o
 
 # These modules require assembler to support AVX.
 ifeq ($(avx_supported),yes)
@@ -48,6 +49,7 @@ ifeq ($(avx_supported),yes)
 	obj-$(CONFIG_CRYPTO_CAST6_AVX_X86_64) += cast6-avx-x86_64.o
 	obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o
 	obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o
+	obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += blake2s-x86_64.o
 endif
 
 # These modules require assembler to support AVX2.
@@ -70,6 +72,7 @@ serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
 aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o
 
 nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o
+blake2s-x86_64-y := blake2s-core.o blake2s-glue.o
 
 ifeq ($(avx_supported),yes)
 	camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \
diff --git a/arch/x86/crypto/blake2s-core.S b/arch/x86/crypto/blake2s-core.S
new file mode 100644
index 000000000000..8591938eee26
--- /dev/null
+++ b/arch/x86/crypto/blake2s-core.S
@@ -0,0 +1,258 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ * Copyright (C) 2017-2019 Samuel Neves <sneves@dei.uc.pt>. All Rights Reserved.
+ */
+
+#include <linux/linkage.h>
+
+.section .rodata.cst32.BLAKE2S_IV, "aM", @progbits, 32
+.align 32
+IV:	.octa 0xA54FF53A3C6EF372BB67AE856A09E667
+	.octa 0x5BE0CD191F83D9AB9B05688C510E527F
+.section .rodata.cst16.ROT16, "aM", @progbits, 16
+.align 16
+ROT16:	.octa 0x0D0C0F0E09080B0A0504070601000302
+.section .rodata.cst16.ROR328, "aM", @progbits, 16
+.align 16
+ROR328:	.octa 0x0C0F0E0D080B0A090407060500030201
+.section .rodata.cst64.BLAKE2S_SIGMA, "aM", @progbits, 160
+.align 64
+SIGMA:
+.byte  0,  2,  4,  6,  1,  3,  5,  7, 14,  8, 10, 12, 15,  9, 11, 13
+.byte 14,  4,  9, 13, 10,  8, 15,  6,  5,  1,  0, 11,  3, 12,  2,  7
+.byte 11, 12,  5, 15,  8,  0,  2, 13,  9, 10,  3,  7,  4, 14,  6,  1
+.byte  7,  3, 13, 11,  9,  1, 12, 14, 15,  2,  5,  4,  8,  6, 10,  0
+.byte  9,  5,  2, 10,  0,  7,  4, 15,  3, 14, 11,  6, 13,  1, 12,  8
+.byte  2,  6,  0,  8, 12, 10, 11,  3,  1,  4,  7, 15,  9, 13,  5, 14
+.byte 12,  1, 14,  4,  5, 15, 13, 10,  8,  0,  6,  9, 11,  7,  3,  2
+.byte 13,  7, 12,  3, 11, 14,  1,  9,  2,  5, 15,  8, 10,  0,  4,  6
+.byte  6, 14, 11,  0, 15,  9,  3,  8, 10, 12, 13,  1,  5,  2,  7,  4
+.byte 10,  8,  7,  1,  2,  4,  6,  5, 13, 15,  9,  3,  0, 11, 14, 12
+#ifdef CONFIG_AS_AVX512
+.section .rodata.cst64.BLAKE2S_SIGMA2, "aM", @progbits, 640
+.align 64
+SIGMA2:
+.long  0,  2,  4,  6,  1,  3,  5,  7, 14,  8, 10, 12, 15,  9, 11, 13
+.long  8,  2, 13, 15, 10,  9, 12,  3,  6,  4,  0, 14,  5, 11,  1,  7
+.long 11, 13,  8,  6,  5, 10, 14,  3,  2,  4, 12, 15,  1,  0,  7,  9
+.long 11, 10,  7,  0,  8, 15,  1, 13,  3,  6,  2, 12,  4, 14,  9,  5
+.long  4, 10,  9, 14, 15,  0, 11,  8,  1,  7,  3, 13,  2,  5,  6, 12
+.long  2, 11,  4, 15, 14,  3, 10,  8, 13,  6,  5,  7,  0, 12,  1,  9
+.long  4,  8, 15,  9, 14, 11, 13,  5,  3,  2,  1, 12,  6, 10,  7,  0
+.long  6, 13,  0, 14, 12,  2,  1, 11, 15,  4,  5,  8,  7,  9,  3, 10
+.long 15,  5,  4, 13, 10,  7,  3, 11, 12,  2,  0,  6,  9,  8,  1, 14
+.long  8,  7, 14, 11, 13, 15,  0, 12, 10,  4,  5,  6,  3,  2,  1,  9
+#endif /* CONFIG_AS_AVX512 */
+
+.text
+#ifdef CONFIG_AS_SSSE3
+ENTRY(blake2s_compress_ssse3)
+	testq		%rdx,%rdx
+	je		.Lendofloop
+	movdqu		(%rdi),%xmm0
+	movdqu		0x10(%rdi),%xmm1
+	movdqa		ROT16(%rip),%xmm12
+	movdqa		ROR328(%rip),%xmm13
+	movdqu		0x20(%rdi),%xmm14
+	movq		%rcx,%xmm15
+	leaq		SIGMA+0xa0(%rip),%r8
+	jmp		.Lbeginofloop
+	.align		32
+.Lbeginofloop:
+	movdqa		%xmm0,%xmm10
+	movdqa		%xmm1,%xmm11
+	paddq		%xmm15,%xmm14
+	movdqa		IV(%rip),%xmm2
+	movdqa		%xmm14,%xmm3
+	pxor		IV+0x10(%rip),%xmm3
+	leaq		SIGMA(%rip),%rcx
+.Lroundloop:
+	movzbl		(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm4
+	movzbl		0x1(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm5
+	movzbl		0x2(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm6
+	movzbl		0x3(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm7
+	punpckldq	%xmm5,%xmm4
+	punpckldq	%xmm7,%xmm6
+	punpcklqdq	%xmm6,%xmm4
+	paddd		%xmm4,%xmm0
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm12,%xmm3
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm8
+	psrld		$0xc,%xmm1
+	pslld		$0x14,%xmm8
+	por		%xmm8,%xmm1
+	movzbl		0x4(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm5
+	movzbl		0x5(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm6
+	movzbl		0x6(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm7
+	movzbl		0x7(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm4
+	punpckldq	%xmm6,%xmm5
+	punpckldq	%xmm4,%xmm7
+	punpcklqdq	%xmm7,%xmm5
+	paddd		%xmm5,%xmm0
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm13,%xmm3
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm8
+	psrld		$0x7,%xmm1
+	pslld		$0x19,%xmm8
+	por		%xmm8,%xmm1
+	pshufd		$0x93,%xmm0,%xmm0
+	pshufd		$0x4e,%xmm3,%xmm3
+	pshufd		$0x39,%xmm2,%xmm2
+	movzbl		0x8(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm6
+	movzbl		0x9(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm7
+	movzbl		0xa(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm4
+	movzbl		0xb(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm5
+	punpckldq	%xmm7,%xmm6
+	punpckldq	%xmm5,%xmm4
+	punpcklqdq	%xmm4,%xmm6
+	paddd		%xmm6,%xmm0
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm12,%xmm3
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm8
+	psrld		$0xc,%xmm1
+	pslld		$0x14,%xmm8
+	por		%xmm8,%xmm1
+	movzbl		0xc(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm7
+	movzbl		0xd(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm4
+	movzbl		0xe(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm5
+	movzbl		0xf(%rcx),%eax
+	movd		(%rsi,%rax,4),%xmm6
+	punpckldq	%xmm4,%xmm7
+	punpckldq	%xmm6,%xmm5
+	punpcklqdq	%xmm5,%xmm7
+	paddd		%xmm7,%xmm0
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm13,%xmm3
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm8
+	psrld		$0x7,%xmm1
+	pslld		$0x19,%xmm8
+	por		%xmm8,%xmm1
+	pshufd		$0x39,%xmm0,%xmm0
+	pshufd		$0x4e,%xmm3,%xmm3
+	pshufd		$0x93,%xmm2,%xmm2
+	addq		$0x10,%rcx
+	cmpq		%r8,%rcx
+	jnz		.Lroundloop
+	pxor		%xmm2,%xmm0
+	pxor		%xmm3,%xmm1
+	pxor		%xmm10,%xmm0
+	pxor		%xmm11,%xmm1
+	addq		$0x40,%rsi
+	decq		%rdx
+	jnz		.Lbeginofloop
+	movdqu		%xmm0,(%rdi)
+	movdqu		%xmm1,0x10(%rdi)
+	movdqu		%xmm14,0x20(%rdi)
+.Lendofloop:
+	ret
+ENDPROC(blake2s_compress_ssse3)
+#endif /* CONFIG_AS_SSSE3 */
+
+#ifdef CONFIG_AS_AVX512
+ENTRY(blake2s_compress_avx512)
+	vmovdqu		(%rdi),%xmm0
+	vmovdqu		0x10(%rdi),%xmm1
+	vmovdqu		0x20(%rdi),%xmm4
+	vmovq		%rcx,%xmm5
+	vmovdqa		IV(%rip),%xmm14
+	vmovdqa		IV+16(%rip),%xmm15
+	jmp		.Lblake2s_compress_avx512_mainloop
+.align 32
+.Lblake2s_compress_avx512_mainloop:
+	vmovdqa		%xmm0,%xmm10
+	vmovdqa		%xmm1,%xmm11
+	vpaddq		%xmm5,%xmm4,%xmm4
+	vmovdqa		%xmm14,%xmm2
+	vpxor		%xmm15,%xmm4,%xmm3
+	vmovdqu		(%rsi),%ymm6
+	vmovdqu		0x20(%rsi),%ymm7
+	addq		$0x40,%rsi
+	leaq		SIGMA2(%rip),%rax
+	movb		$0xa,%cl
+.Lblake2s_compress_avx512_roundloop:
+	addq		$0x40,%rax
+	vmovdqa		-0x40(%rax),%ymm8
+	vmovdqa		-0x20(%rax),%ymm9
+	vpermi2d	%ymm7,%ymm6,%ymm8
+	vpermi2d	%ymm7,%ymm6,%ymm9
+	vmovdqa		%ymm8,%ymm6
+	vmovdqa		%ymm9,%ymm7
+	vpaddd		%xmm8,%xmm0,%xmm0
+	vpaddd		%xmm1,%xmm0,%xmm0
+	vpxor		%xmm0,%xmm3,%xmm3
+	vprord		$0x10,%xmm3,%xmm3
+	vpaddd		%xmm3,%xmm2,%xmm2
+	vpxor		%xmm2,%xmm1,%xmm1
+	vprord		$0xc,%xmm1,%xmm1
+	vextracti128	$0x1,%ymm8,%xmm8
+	vpaddd		%xmm8,%xmm0,%xmm0
+	vpaddd		%xmm1,%xmm0,%xmm0
+	vpxor		%xmm0,%xmm3,%xmm3
+	vprord		$0x8,%xmm3,%xmm3
+	vpaddd		%xmm3,%xmm2,%xmm2
+	vpxor		%xmm2,%xmm1,%xmm1
+	vprord		$0x7,%xmm1,%xmm1
+	vpshufd		$0x93,%xmm0,%xmm0
+	vpshufd		$0x4e,%xmm3,%xmm3
+	vpshufd		$0x39,%xmm2,%xmm2
+	vpaddd		%xmm9,%xmm0,%xmm0
+	vpaddd		%xmm1,%xmm0,%xmm0
+	vpxor		%xmm0,%xmm3,%xmm3
+	vprord		$0x10,%xmm3,%xmm3
+	vpaddd		%xmm3,%xmm2,%xmm2
+	vpxor		%xmm2,%xmm1,%xmm1
+	vprord		$0xc,%xmm1,%xmm1
+	vextracti128	$0x1,%ymm9,%xmm9
+	vpaddd		%xmm9,%xmm0,%xmm0
+	vpaddd		%xmm1,%xmm0,%xmm0
+	vpxor		%xmm0,%xmm3,%xmm3
+	vprord		$0x8,%xmm3,%xmm3
+	vpaddd		%xmm3,%xmm2,%xmm2
+	vpxor		%xmm2,%xmm1,%xmm1
+	vprord		$0x7,%xmm1,%xmm1
+	vpshufd		$0x39,%xmm0,%xmm0
+	vpshufd		$0x4e,%xmm3,%xmm3
+	vpshufd		$0x93,%xmm2,%xmm2
+	decb		%cl
+	jne		.Lblake2s_compress_avx512_roundloop
+	vpxor		%xmm10,%xmm0,%xmm0
+	vpxor		%xmm11,%xmm1,%xmm1
+	vpxor		%xmm2,%xmm0,%xmm0
+	vpxor		%xmm3,%xmm1,%xmm1
+	decq		%rdx
+	jne		.Lblake2s_compress_avx512_mainloop
+	vmovdqu		%xmm0,(%rdi)
+	vmovdqu		%xmm1,0x10(%rdi)
+	vmovdqu		%xmm4,0x20(%rdi)
+	vzeroupper
+	retq
+ENDPROC(blake2s_compress_avx512)
+#endif /* CONFIG_AS_AVX512 */
diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c
new file mode 100644
index 000000000000..4a37ba7cdbe5
--- /dev/null
+++ b/arch/x86/crypto/blake2s-glue.c
@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <crypto/internal/blake2s.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/hash.h>
+
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/cpufeature.h>
+#include <asm/fpu/api.h>
+#include <asm/processor.h>
+#include <asm/simd.h>
+
+asmlinkage void blake2s_compress_ssse3(struct blake2s_state *state,
+				       const u8 *block, const size_t nblocks,
+				       const u32 inc);
+asmlinkage void blake2s_compress_avx512(struct blake2s_state *state,
+					const u8 *block, const size_t nblocks,
+					const u32 inc);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_ssse3);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_avx512);
+
+void blake2s_compress_arch(struct blake2s_state *state,
+			   const u8 *block, size_t nblocks,
+			   const u32 inc)
+{
+	/* SIMD disables preemption, so relax after processing each page. */
+	BUILD_BUG_ON(PAGE_SIZE / BLAKE2S_BLOCK_SIZE < 8);
+
+	if (!static_branch_likely(&blake2s_use_ssse3) || !crypto_simd_usable()) {
+		blake2s_compress_generic(state, block, nblocks, inc);
+		return;
+	}
+
+	for (;;) {
+		const size_t blocks = min_t(size_t, nblocks,
+					    PAGE_SIZE / BLAKE2S_BLOCK_SIZE);
+
+		kernel_fpu_begin();
+		if (IS_ENABLED(CONFIG_AS_AVX512) &&
+		    static_branch_likely(&blake2s_use_avx512))
+			blake2s_compress_avx512(state, block, blocks, inc);
+		else
+			blake2s_compress_ssse3(state, block, blocks, inc);
+		kernel_fpu_end();
+
+		nblocks -= blocks;
+		if (!nblocks)
+			break;
+		block += blocks * BLAKE2S_BLOCK_SIZE;
+	}
+}
+EXPORT_SYMBOL(blake2s_compress_arch);
+
+static int crypto_blake2s_setkey(struct crypto_shash *tfm, const u8 *key,
+				 unsigned int keylen)
+{
+	struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(tfm);
+
+	if (keylen == 0 || keylen > BLAKE2S_KEY_SIZE) {
+		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(tctx->key, key, keylen);
+	tctx->keylen = keylen;
+
+	return 0;
+}
+
+static int crypto_blake2s_init(struct shash_desc *desc)
+{
+	struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	struct blake2s_state *state = shash_desc_ctx(desc);
+	const int outlen = crypto_shash_digestsize(desc->tfm);
+
+	if (tctx->keylen)
+		blake2s_init_key(state, outlen, tctx->key, tctx->keylen);
+	else
+		blake2s_init(state, outlen);
+
+	return 0;
+}
+
+static int crypto_blake2s_update(struct shash_desc *desc, const u8 *in,
+				 unsigned int inlen)
+{
+	struct blake2s_state *state = shash_desc_ctx(desc);
+	const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen;
+
+	if (unlikely(!inlen))
+		return 0;
+	if (inlen > fill) {
+		memcpy(state->buf + state->buflen, in, fill);
+		blake2s_compress_arch(state, state->buf, 1, BLAKE2S_BLOCK_SIZE);
+		state->buflen = 0;
+		in += fill;
+		inlen -= fill;
+	}
+	if (inlen > BLAKE2S_BLOCK_SIZE) {
+		const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE);
+		/* Hash one less (full) block than strictly possible */
+		blake2s_compress_arch(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE);
+		in += BLAKE2S_BLOCK_SIZE * (nblocks - 1);
+		inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1);
+	}
+	memcpy(state->buf + state->buflen, in, inlen);
+	state->buflen += inlen;
+
+	return 0;
+}
+
+static int crypto_blake2s_final(struct shash_desc *desc, u8 *out)
+{
+	struct blake2s_state *state = shash_desc_ctx(desc);
+
+	blake2s_set_lastblock(state);
+	memset(state->buf + state->buflen, 0,
+	       BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */
+	blake2s_compress_arch(state, state->buf, 1, state->buflen);
+	cpu_to_le32_array(state->h, ARRAY_SIZE(state->h));
+	memcpy(out, state->h, state->outlen);
+	memzero_explicit(state, sizeof(*state));
+
+	return 0;
+}
+
+static struct shash_alg blake2s_algs[] = {{
+	.base.cra_name		= "blake2s-128",
+	.base.cra_driver_name	= "blake2s-128-x86",
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
+	.base.cra_priority	= 200,
+	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= BLAKE2S_128_HASH_SIZE,
+	.setkey			= crypto_blake2s_setkey,
+	.init			= crypto_blake2s_init,
+	.update			= crypto_blake2s_update,
+	.final			= crypto_blake2s_final,
+	.descsize		= sizeof(struct blake2s_state),
+}, {
+	.base.cra_name		= "blake2s-160",
+	.base.cra_driver_name	= "blake2s-160-x86",
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
+	.base.cra_priority	= 200,
+	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= BLAKE2S_160_HASH_SIZE,
+	.setkey			= crypto_blake2s_setkey,
+	.init			= crypto_blake2s_init,
+	.update			= crypto_blake2s_update,
+	.final			= crypto_blake2s_final,
+	.descsize		= sizeof(struct blake2s_state),
+}, {
+	.base.cra_name		= "blake2s-224",
+	.base.cra_driver_name	= "blake2s-224-x86",
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
+	.base.cra_priority	= 200,
+	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= BLAKE2S_224_HASH_SIZE,
+	.setkey			= crypto_blake2s_setkey,
+	.init			= crypto_blake2s_init,
+	.update			= crypto_blake2s_update,
+	.final			= crypto_blake2s_final,
+	.descsize		= sizeof(struct blake2s_state),
+}, {
+	.base.cra_name		= "blake2s-256",
+	.base.cra_driver_name	= "blake2s-256-x86",
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
+	.base.cra_priority	= 200,
+	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= BLAKE2S_256_HASH_SIZE,
+	.setkey			= crypto_blake2s_setkey,
+	.init			= crypto_blake2s_init,
+	.update			= crypto_blake2s_update,
+	.final			= crypto_blake2s_final,
+	.descsize		= sizeof(struct blake2s_state),
+}};
+
+static int __init blake2s_mod_init(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_SSSE3))
+		return 0;
+
+	static_branch_enable(&blake2s_use_ssse3);
+
+	if (IS_ENABLED(CONFIG_AS_AVX512) &&
+	    boot_cpu_has(X86_FEATURE_AVX) &&
+	    boot_cpu_has(X86_FEATURE_AVX2) &&
+	    boot_cpu_has(X86_FEATURE_AVX512F) &&
+	    boot_cpu_has(X86_FEATURE_AVX512VL) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM |
+			      XFEATURE_MASK_AVX512, NULL))
+		static_branch_enable(&blake2s_use_avx512);
+
+	return crypto_register_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs));
+}
+
+static void __exit blake2s_mod_exit(void)
+{
+	if (boot_cpu_has(X86_FEATURE_SSSE3))
+		crypto_unregister_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs));
+}
+
+module_init(blake2s_mod_init);
+module_exit(blake2s_mod_exit);
+
+MODULE_ALIAS_CRYPTO("blake2s-128");
+MODULE_ALIAS_CRYPTO("blake2s-128-x86");
+MODULE_ALIAS_CRYPTO("blake2s-160");
+MODULE_ALIAS_CRYPTO("blake2s-160-x86");
+MODULE_ALIAS_CRYPTO("blake2s-224");
+MODULE_ALIAS_CRYPTO("blake2s-224-x86");
+MODULE_ALIAS_CRYPTO("blake2s-256");
+MODULE_ALIAS_CRYPTO("blake2s-256-x86");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index 388f95a4ec24..a94e30b6f941 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -7,7 +7,7 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
@@ -21,24 +21,24 @@ asmlinkage void chacha_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
 asmlinkage void chacha_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
 					unsigned int len, int nrounds);
 asmlinkage void hchacha_block_ssse3(const u32 *state, u32 *out, int nrounds);
-#ifdef CONFIG_AS_AVX2
+
 asmlinkage void chacha_2block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
 				       unsigned int len, int nrounds);
 asmlinkage void chacha_4block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
 				       unsigned int len, int nrounds);
 asmlinkage void chacha_8block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
 				       unsigned int len, int nrounds);
-static bool chacha_use_avx2;
-#ifdef CONFIG_AS_AVX512
+
 asmlinkage void chacha_2block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
 					   unsigned int len, int nrounds);
 asmlinkage void chacha_4block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
 					   unsigned int len, int nrounds);
 asmlinkage void chacha_8block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
 					   unsigned int len, int nrounds);
-static bool chacha_use_avx512vl;
-#endif
-#endif
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_simd);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx2);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx512vl);
 
 static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks)
 {
@@ -49,9 +49,8 @@ static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks)
 static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
 			  unsigned int bytes, int nrounds)
 {
-#ifdef CONFIG_AS_AVX2
-#ifdef CONFIG_AS_AVX512
-	if (chacha_use_avx512vl) {
+	if (IS_ENABLED(CONFIG_AS_AVX512) &&
+	    static_branch_likely(&chacha_use_avx512vl)) {
 		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
 			chacha_8block_xor_avx512vl(state, dst, src, bytes,
 						   nrounds);
@@ -79,8 +78,9 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
 			return;
 		}
 	}
-#endif
-	if (chacha_use_avx2) {
+
+	if (IS_ENABLED(CONFIG_AS_AVX2) &&
+	    static_branch_likely(&chacha_use_avx2)) {
 		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
 			chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
 			bytes -= CHACHA_BLOCK_SIZE * 8;
@@ -104,7 +104,7 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
 			return;
 		}
 	}
-#endif
+
 	while (bytes >= CHACHA_BLOCK_SIZE * 4) {
 		chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
 		bytes -= CHACHA_BLOCK_SIZE * 4;
@@ -123,37 +123,76 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
 	}
 }
 
-static int chacha_simd_stream_xor(struct skcipher_walk *walk,
+void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
+{
+	state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
+
+	if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable()) {
+		hchacha_block_generic(state, stream, nrounds);
+	} else {
+		kernel_fpu_begin();
+		hchacha_block_ssse3(state, stream, nrounds);
+		kernel_fpu_end();
+	}
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
+{
+	state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
+
+	chacha_init_generic(state, key, iv);
+}
+EXPORT_SYMBOL(chacha_init_arch);
+
+void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
+		       int nrounds)
+{
+	state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
+
+	if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable() ||
+	    bytes <= CHACHA_BLOCK_SIZE)
+		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+
+	kernel_fpu_begin();
+	chacha_dosimd(state, dst, src, bytes, nrounds);
+	kernel_fpu_end();
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+static int chacha_simd_stream_xor(struct skcipher_request *req,
 				  const struct chacha_ctx *ctx, const u8 *iv)
 {
 	u32 *state, state_buf[16 + 2] __aligned(8);
-	int next_yield = 4096; /* bytes until next FPU yield */
-	int err = 0;
+	struct skcipher_walk walk;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
 
 	BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
 	state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
 
-	crypto_chacha_init(state, ctx, iv);
-
-	while (walk->nbytes > 0) {
-		unsigned int nbytes = walk->nbytes;
+	chacha_init_generic(state, ctx->key, iv);
 
-		if (nbytes < walk->total) {
-			nbytes = round_down(nbytes, walk->stride);
-			next_yield -= nbytes;
-		}
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
 
-		chacha_dosimd(state, walk->dst.virt.addr, walk->src.virt.addr,
-			      nbytes, ctx->nrounds);
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, walk.stride);
 
-		if (next_yield <= 0) {
-			/* temporarily allow preemption */
-			kernel_fpu_end();
+		if (!static_branch_likely(&chacha_use_simd) ||
+		    !crypto_simd_usable()) {
+			chacha_crypt_generic(state, walk.dst.virt.addr,
+					     walk.src.virt.addr, nbytes,
+					     ctx->nrounds);
+		} else {
 			kernel_fpu_begin();
-			next_yield = 4096;
+			chacha_dosimd(state, walk.dst.virt.addr,
+				      walk.src.virt.addr, nbytes,
+				      ctx->nrounds);
+			kernel_fpu_end();
 		}
-
-		err = skcipher_walk_done(walk, walk->nbytes - nbytes);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
 	return err;
@@ -163,55 +202,34 @@ static int chacha_simd(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
-	int err;
-
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
-		return crypto_chacha_crypt(req);
 
-	err = skcipher_walk_virt(&walk, req, true);
-	if (err)
-		return err;
-
-	kernel_fpu_begin();
-	err = chacha_simd_stream_xor(&walk, ctx, req->iv);
-	kernel_fpu_end();
-	return err;
+	return chacha_simd_stream_xor(req, ctx, req->iv);
 }
 
 static int xchacha_simd(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
-	struct chacha_ctx subctx;
 	u32 *state, state_buf[16 + 2] __aligned(8);
+	struct chacha_ctx subctx;
 	u8 real_iv[16];
-	int err;
-
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
-		return crypto_xchacha_crypt(req);
-
-	err = skcipher_walk_virt(&walk, req, true);
-	if (err)
-		return err;
 
 	BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
 	state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
-	crypto_chacha_init(state, ctx, req->iv);
-
-	kernel_fpu_begin();
-
-	hchacha_block_ssse3(state, subctx.key, ctx->nrounds);
+	chacha_init_generic(state, ctx->key, req->iv);
+
+	if (req->cryptlen > CHACHA_BLOCK_SIZE && crypto_simd_usable()) {
+		kernel_fpu_begin();
+		hchacha_block_ssse3(state, subctx.key, ctx->nrounds);
+		kernel_fpu_end();
+	} else {
+		hchacha_block_generic(state, subctx.key, ctx->nrounds);
+	}
 	subctx.nrounds = ctx->nrounds;
 
 	memcpy(&real_iv[0], req->iv + 24, 8);
 	memcpy(&real_iv[8], req->iv + 16, 8);
-	err = chacha_simd_stream_xor(&walk, &subctx, real_iv);
-
-	kernel_fpu_end();
-
-	return err;
+	return chacha_simd_stream_xor(req, &subctx, real_iv);
 }
 
 static struct skcipher_alg algs[] = {
@@ -227,7 +245,7 @@ static struct skcipher_alg algs[] = {
 		.max_keysize		= CHACHA_KEY_SIZE,
 		.ivsize			= CHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
+		.setkey			= chacha20_setkey,
 		.encrypt		= chacha_simd,
 		.decrypt		= chacha_simd,
 	}, {
@@ -242,7 +260,7 @@ static struct skcipher_alg algs[] = {
 		.max_keysize		= CHACHA_KEY_SIZE,
 		.ivsize			= XCHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
+		.setkey			= chacha20_setkey,
 		.encrypt		= xchacha_simd,
 		.decrypt		= xchacha_simd,
 	}, {
@@ -257,7 +275,7 @@ static struct skcipher_alg algs[] = {
 		.max_keysize		= CHACHA_KEY_SIZE,
 		.ivsize			= XCHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha12_setkey,
+		.setkey			= chacha12_setkey,
 		.encrypt		= xchacha_simd,
 		.decrypt		= xchacha_simd,
 	},
@@ -266,24 +284,28 @@ static struct skcipher_alg algs[] = {
 static int __init chacha_simd_mod_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_SSSE3))
-		return -ENODEV;
-
-#ifdef CONFIG_AS_AVX2
-	chacha_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) &&
-			  boot_cpu_has(X86_FEATURE_AVX2) &&
-			  cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL);
-#ifdef CONFIG_AS_AVX512
-	chacha_use_avx512vl = chacha_use_avx2 &&
-			      boot_cpu_has(X86_FEATURE_AVX512VL) &&
-			      boot_cpu_has(X86_FEATURE_AVX512BW); /* kmovq */
-#endif
-#endif
+		return 0;
+
+	static_branch_enable(&chacha_use_simd);
+
+	if (IS_ENABLED(CONFIG_AS_AVX2) &&
+	    boot_cpu_has(X86_FEATURE_AVX) &&
+	    boot_cpu_has(X86_FEATURE_AVX2) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
+		static_branch_enable(&chacha_use_avx2);
+
+		if (IS_ENABLED(CONFIG_AS_AVX512) &&
+		    boot_cpu_has(X86_FEATURE_AVX512VL) &&
+		    boot_cpu_has(X86_FEATURE_AVX512BW)) /* kmovq */
+			static_branch_enable(&chacha_use_avx512vl);
+	}
 	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
 }
 
 static void __exit chacha_simd_mod_fini(void)
 {
-	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
+	if (boot_cpu_has(X86_FEATURE_SSSE3))
+		crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
 }
 
 module_init(chacha_simd_mod_init);
diff --git a/arch/x86/crypto/curve25519-x86_64.c b/arch/x86/crypto/curve25519-x86_64.c
new file mode 100644
index 000000000000..a52a3fb15727
--- /dev/null
+++ b/arch/x86/crypto/curve25519-x86_64.c
@@ -0,0 +1,2475 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (c) 2017 Armando Faz <armfazh@ic.unicamp.br>. All Rights Reserved.
+ * Copyright (C) 2018-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ * Copyright (C) 2018 Samuel Neves <sneves@dei.uc.pt>. All Rights Reserved.
+ */
+
+#include <crypto/curve25519.h>
+#include <crypto/internal/kpp.h>
+
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/cpufeature.h>
+#include <asm/processor.h>
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_bmi2);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_adx);
+
+enum { NUM_WORDS_ELTFP25519 = 4 };
+typedef __aligned(32) u64 eltfp25519_1w[NUM_WORDS_ELTFP25519];
+typedef __aligned(32) u64 eltfp25519_1w_buffer[2 * NUM_WORDS_ELTFP25519];
+
+#define mul_eltfp25519_1w_adx(c, a, b) do { \
+	mul_256x256_integer_adx(m.buffer, a, b); \
+	red_eltfp25519_1w_adx(c, m.buffer); \
+} while (0)
+
+#define mul_eltfp25519_1w_bmi2(c, a, b) do { \
+	mul_256x256_integer_bmi2(m.buffer, a, b); \
+	red_eltfp25519_1w_bmi2(c, m.buffer); \
+} while (0)
+
+#define sqr_eltfp25519_1w_adx(a) do { \
+	sqr_256x256_integer_adx(m.buffer, a); \
+	red_eltfp25519_1w_adx(a, m.buffer); \
+} while (0)
+
+#define sqr_eltfp25519_1w_bmi2(a) do { \
+	sqr_256x256_integer_bmi2(m.buffer, a); \
+	red_eltfp25519_1w_bmi2(a, m.buffer); \
+} while (0)
+
+#define mul_eltfp25519_2w_adx(c, a, b) do { \
+	mul2_256x256_integer_adx(m.buffer, a, b); \
+	red_eltfp25519_2w_adx(c, m.buffer); \
+} while (0)
+
+#define mul_eltfp25519_2w_bmi2(c, a, b) do { \
+	mul2_256x256_integer_bmi2(m.buffer, a, b); \
+	red_eltfp25519_2w_bmi2(c, m.buffer); \
+} while (0)
+
+#define sqr_eltfp25519_2w_adx(a) do { \
+	sqr2_256x256_integer_adx(m.buffer, a); \
+	red_eltfp25519_2w_adx(a, m.buffer); \
+} while (0)
+
+#define sqr_eltfp25519_2w_bmi2(a) do { \
+	sqr2_256x256_integer_bmi2(m.buffer, a); \
+	red_eltfp25519_2w_bmi2(a, m.buffer); \
+} while (0)
+
+#define sqrn_eltfp25519_1w_adx(a, times) do { \
+	int ____counter = (times); \
+	while (____counter-- > 0) \
+		sqr_eltfp25519_1w_adx(a); \
+} while (0)
+
+#define sqrn_eltfp25519_1w_bmi2(a, times) do { \
+	int ____counter = (times); \
+	while (____counter-- > 0) \
+		sqr_eltfp25519_1w_bmi2(a); \
+} while (0)
+
+#define copy_eltfp25519_1w(C, A) do { \
+	(C)[0] = (A)[0]; \
+	(C)[1] = (A)[1]; \
+	(C)[2] = (A)[2]; \
+	(C)[3] = (A)[3]; \
+} while (0)
+
+#define setzero_eltfp25519_1w(C) do { \
+	(C)[0] = 0; \
+	(C)[1] = 0; \
+	(C)[2] = 0; \
+	(C)[3] = 0; \
+} while (0)
+
+__aligned(32) static const u64 table_ladder_8k[252 * NUM_WORDS_ELTFP25519] = {
+	/*   1 */ 0xfffffffffffffff3UL, 0xffffffffffffffffUL,
+		  0xffffffffffffffffUL, 0x5fffffffffffffffUL,
+	/*   2 */ 0x6b8220f416aafe96UL, 0x82ebeb2b4f566a34UL,
+		  0xd5a9a5b075a5950fUL, 0x5142b2cf4b2488f4UL,
+	/*   3 */ 0x6aaebc750069680cUL, 0x89cf7820a0f99c41UL,
+		  0x2a58d9183b56d0f4UL, 0x4b5aca80e36011a4UL,
+	/*   4 */ 0x329132348c29745dUL, 0xf4a2e616e1642fd7UL,
+		  0x1e45bb03ff67bc34UL, 0x306912d0f42a9b4aUL,
+	/*   5 */ 0xff886507e6af7154UL, 0x04f50e13dfeec82fUL,
+		  0xaa512fe82abab5ceUL, 0x174e251a68d5f222UL,
+	/*   6 */ 0xcf96700d82028898UL, 0x1743e3370a2c02c5UL,
+		  0x379eec98b4e86eaaUL, 0x0c59888a51e0482eUL,
+	/*   7 */ 0xfbcbf1d699b5d189UL, 0xacaef0d58e9fdc84UL,
+		  0xc1c20d06231f7614UL, 0x2938218da274f972UL,
+	/*   8 */ 0xf6af49beff1d7f18UL, 0xcc541c22387ac9c2UL,
+		  0x96fcc9ef4015c56bUL, 0x69c1627c690913a9UL,
+	/*   9 */ 0x7a86fd2f4733db0eUL, 0xfdb8c4f29e087de9UL,
+		  0x095e4b1a8ea2a229UL, 0x1ad7a7c829b37a79UL,
+	/*  10 */ 0x342d89cad17ea0c0UL, 0x67bedda6cced2051UL,
+		  0x19ca31bf2bb42f74UL, 0x3df7b4c84980acbbUL,
+	/*  11 */ 0xa8c6444dc80ad883UL, 0xb91e440366e3ab85UL,
+		  0xc215cda00164f6d8UL, 0x3d867c6ef247e668UL,
+	/*  12 */ 0xc7dd582bcc3e658cUL, 0xfd2c4748ee0e5528UL,
+		  0xa0fd9b95cc9f4f71UL, 0x7529d871b0675ddfUL,
+	/*  13 */ 0xb8f568b42d3cbd78UL, 0x1233011b91f3da82UL,
+		  0x2dce6ccd4a7c3b62UL, 0x75e7fc8e9e498603UL,
+	/*  14 */ 0x2f4f13f1fcd0b6ecUL, 0xf1a8ca1f29ff7a45UL,
+		  0xc249c1a72981e29bUL, 0x6ebe0dbb8c83b56aUL,
+	/*  15 */ 0x7114fa8d170bb222UL, 0x65a2dcd5bf93935fUL,
+		  0xbdc41f68b59c979aUL, 0x2f0eef79a2ce9289UL,
+	/*  16 */ 0x42ecbf0c083c37ceUL, 0x2930bc09ec496322UL,
+		  0xf294b0c19cfeac0dUL, 0x3780aa4bedfabb80UL,
+	/*  17 */ 0x56c17d3e7cead929UL, 0xe7cb4beb2e5722c5UL,
+		  0x0ce931732dbfe15aUL, 0x41b883c7621052f8UL,
+	/*  18 */ 0xdbf75ca0c3d25350UL, 0x2936be086eb1e351UL,
+		  0xc936e03cb4a9b212UL, 0x1d45bf82322225aaUL,
+	/*  19 */ 0xe81ab1036a024cc5UL, 0xe212201c304c9a72UL,
+		  0xc5d73fba6832b1fcUL, 0x20ffdb5a4d839581UL,
+	/*  20 */ 0xa283d367be5d0fadUL, 0x6c2b25ca8b164475UL,
+		  0x9d4935467caaf22eUL, 0x5166408eee85ff49UL,
+	/*  21 */ 0x3c67baa2fab4e361UL, 0xb3e433c67ef35cefUL,
+		  0x5259729241159b1cUL, 0x6a621892d5b0ab33UL,
+	/*  22 */ 0x20b74a387555cdcbUL, 0x532aa10e1208923fUL,
+		  0xeaa17b7762281dd1UL, 0x61ab3443f05c44bfUL,
+	/*  23 */ 0x257a6c422324def8UL, 0x131c6c1017e3cf7fUL,
+		  0x23758739f630a257UL, 0x295a407a01a78580UL,
+	/*  24 */ 0xf8c443246d5da8d9UL, 0x19d775450c52fa5dUL,
+		  0x2afcfc92731bf83dUL, 0x7d10c8e81b2b4700UL,
+	/*  25 */ 0xc8e0271f70baa20bUL, 0x993748867ca63957UL,
+		  0x5412efb3cb7ed4bbUL, 0x3196d36173e62975UL,
+	/*  26 */ 0xde5bcad141c7dffcUL, 0x47cc8cd2b395c848UL,
+		  0xa34cd942e11af3cbUL, 0x0256dbf2d04ecec2UL,
+	/*  27 */ 0x875ab7e94b0e667fUL, 0xcad4dd83c0850d10UL,
+		  0x47f12e8f4e72c79fUL, 0x5f1a87bb8c85b19bUL,
+	/*  28 */ 0x7ae9d0b6437f51b8UL, 0x12c7ce5518879065UL,
+		  0x2ade09fe5cf77aeeUL, 0x23a05a2f7d2c5627UL,
+	/*  29 */ 0x5908e128f17c169aUL, 0xf77498dd8ad0852dUL,
+		  0x74b4c4ceab102f64UL, 0x183abadd10139845UL,
+	/*  30 */ 0xb165ba8daa92aaacUL, 0xd5c5ef9599386705UL,
+		  0xbe2f8f0cf8fc40d1UL, 0x2701e635ee204514UL,
+	/*  31 */ 0x629fa80020156514UL, 0xf223868764a8c1ceUL,
+		  0x5b894fff0b3f060eUL, 0x60d9944cf708a3faUL,
+	/*  32 */ 0xaeea001a1c7a201fUL, 0xebf16a633ee2ce63UL,
+		  0x6f7709594c7a07e1UL, 0x79b958150d0208cbUL,
+	/*  33 */ 0x24b55e5301d410e7UL, 0xe3a34edff3fdc84dUL,
+		  0xd88768e4904032d8UL, 0x131384427b3aaeecUL,
+	/*  34 */ 0x8405e51286234f14UL, 0x14dc4739adb4c529UL,
+		  0xb8a2b5b250634ffdUL, 0x2fe2a94ad8a7ff93UL,
+	/*  35 */ 0xec5c57efe843faddUL, 0x2843ce40f0bb9918UL,
+		  0xa4b561d6cf3d6305UL, 0x743629bde8fb777eUL,
+	/*  36 */ 0x343edd46bbaf738fUL, 0xed981828b101a651UL,
+		  0xa401760b882c797aUL, 0x1fc223e28dc88730UL,
+	/*  37 */ 0x48604e91fc0fba0eUL, 0xb637f78f052c6fa4UL,
+		  0x91ccac3d09e9239cUL, 0x23f7eed4437a687cUL,
+	/*  38 */ 0x5173b1118d9bd800UL, 0x29d641b63189d4a7UL,
+		  0xfdbf177988bbc586UL, 0x2959894fcad81df5UL,
+	/*  39 */ 0xaebc8ef3b4bbc899UL, 0x4148995ab26992b9UL,
+		  0x24e20b0134f92cfbUL, 0x40d158894a05dee8UL,
+	/*  40 */ 0x46b00b1185af76f6UL, 0x26bac77873187a79UL,
+		  0x3dc0bf95ab8fff5fUL, 0x2a608bd8945524d7UL,
+	/*  41 */ 0x26449588bd446302UL, 0x7c4bc21c0388439cUL,
+		  0x8e98a4f383bd11b2UL, 0x26218d7bc9d876b9UL,
+	/*  42 */ 0xe3081542997c178aUL, 0x3c2d29a86fb6606fUL,
+		  0x5c217736fa279374UL, 0x7dde05734afeb1faUL,
+	/*  43 */ 0x3bf10e3906d42babUL, 0xe4f7803e1980649cUL,
+		  0xe6053bf89595bf7aUL, 0x394faf38da245530UL,
+	/*  44 */ 0x7a8efb58896928f4UL, 0xfbc778e9cc6a113cUL,
+		  0x72670ce330af596fUL, 0x48f222a81d3d6cf7UL,
+	/*  45 */ 0xf01fce410d72caa7UL, 0x5a20ecc7213b5595UL,
+		  0x7bc21165c1fa1483UL, 0x07f89ae31da8a741UL,
+	/*  46 */ 0x05d2c2b4c6830ff9UL, 0xd43e330fc6316293UL,
+		  0xa5a5590a96d3a904UL, 0x705edb91a65333b6UL,
+	/*  47 */ 0x048ee15e0bb9a5f7UL, 0x3240cfca9e0aaf5dUL,
+		  0x8f4b71ceedc4a40bUL, 0x621c0da3de544a6dUL,
+	/*  48 */ 0x92872836a08c4091UL, 0xce8375b010c91445UL,
+		  0x8a72eb524f276394UL, 0x2667fcfa7ec83635UL,
+	/*  49 */ 0x7f4c173345e8752aUL, 0x061b47feee7079a5UL,
+		  0x25dd9afa9f86ff34UL, 0x3780cef5425dc89cUL,
+	/*  50 */ 0x1a46035a513bb4e9UL, 0x3e1ef379ac575adaUL,
+		  0xc78c5f1c5fa24b50UL, 0x321a967634fd9f22UL,
+	/*  51 */ 0x946707b8826e27faUL, 0x3dca84d64c506fd0UL,
+		  0xc189218075e91436UL, 0x6d9284169b3b8484UL,
+	/*  52 */ 0x3a67e840383f2ddfUL, 0x33eec9a30c4f9b75UL,
+		  0x3ec7c86fa783ef47UL, 0x26ec449fbac9fbc4UL,
+	/*  53 */ 0x5c0f38cba09b9e7dUL, 0x81168cc762a3478cUL,
+		  0x3e23b0d306fc121cUL, 0x5a238aa0a5efdcddUL,
+	/*  54 */ 0x1ba26121c4ea43ffUL, 0x36f8c77f7c8832b5UL,
+		  0x88fbea0b0adcf99aUL, 0x5ca9938ec25bebf9UL,
+	/*  55 */ 0xd5436a5e51fccda0UL, 0x1dbc4797c2cd893bUL,
+		  0x19346a65d3224a08UL, 0x0f5034e49b9af466UL,
+	/*  56 */ 0xf23c3967a1e0b96eUL, 0xe58b08fa867a4d88UL,
+		  0xfb2fabc6a7341679UL, 0x2a75381eb6026946UL,
+	/*  57 */ 0xc80a3be4c19420acUL, 0x66b1f6c681f2b6dcUL,
+		  0x7cf7036761e93388UL, 0x25abbbd8a660a4c4UL,
+	/*  58 */ 0x91ea12ba14fd5198UL, 0x684950fc4a3cffa9UL,
+		  0xf826842130f5ad28UL, 0x3ea988f75301a441UL,
+	/*  59 */ 0xc978109a695f8c6fUL, 0x1746eb4a0530c3f3UL,
+		  0x444d6d77b4459995UL, 0x75952b8c054e5cc7UL,
+	/*  60 */ 0xa3703f7915f4d6aaUL, 0x66c346202f2647d8UL,
+		  0xd01469df811d644bUL, 0x77fea47d81a5d71fUL,
+	/*  61 */ 0xc5e9529ef57ca381UL, 0x6eeeb4b9ce2f881aUL,
+		  0xb6e91a28e8009bd6UL, 0x4b80be3e9afc3fecUL,
+	/*  62 */ 0x7e3773c526aed2c5UL, 0x1b4afcb453c9a49dUL,
+		  0xa920bdd7baffb24dUL, 0x7c54699f122d400eUL,
+	/*  63 */ 0xef46c8e14fa94bc8UL, 0xe0b074ce2952ed5eUL,
+		  0xbea450e1dbd885d5UL, 0x61b68649320f712cUL,
+	/*  64 */ 0x8a485f7309ccbdd1UL, 0xbd06320d7d4d1a2dUL,
+		  0x25232973322dbef4UL, 0x445dc4758c17f770UL,
+	/*  65 */ 0xdb0434177cc8933cUL, 0xed6fe82175ea059fUL,
+		  0x1efebefdc053db34UL, 0x4adbe867c65daf99UL,
+	/*  66 */ 0x3acd71a2a90609dfUL, 0xe5e991856dd04050UL,
+		  0x1ec69b688157c23cUL, 0x697427f6885cfe4dUL,
+	/*  67 */ 0xd7be7b9b65e1a851UL, 0xa03d28d522c536ddUL,
+		  0x28399d658fd2b645UL, 0x49e5b7e17c2641e1UL,
+	/*  68 */ 0x6f8c3a98700457a4UL, 0x5078f0a25ebb6778UL,
+		  0xd13c3ccbc382960fUL, 0x2e003258a7df84b1UL,
+	/*  69 */ 0x8ad1f39be6296a1cUL, 0xc1eeaa652a5fbfb2UL,
+		  0x33ee0673fd26f3cbUL, 0x59256173a69d2cccUL,
+	/*  70 */ 0x41ea07aa4e18fc41UL, 0xd9fc19527c87a51eUL,
+		  0xbdaacb805831ca6fUL, 0x445b652dc916694fUL,
+	/*  71 */ 0xce92a3a7f2172315UL, 0x1edc282de11b9964UL,
+		  0xa1823aafe04c314aUL, 0x790a2d94437cf586UL,
+	/*  72 */ 0x71c447fb93f6e009UL, 0x8922a56722845276UL,
+		  0xbf70903b204f5169UL, 0x2f7a89891ba319feUL,
+	/*  73 */ 0x02a08eb577e2140cUL, 0xed9a4ed4427bdcf4UL,
+		  0x5253ec44e4323cd1UL, 0x3e88363c14e9355bUL,
+	/*  74 */ 0xaa66c14277110b8cUL, 0x1ae0391610a23390UL,
+		  0x2030bd12c93fc2a2UL, 0x3ee141579555c7abUL,
+	/*  75 */ 0x9214de3a6d6e7d41UL, 0x3ccdd88607f17efeUL,
+		  0x674f1288f8e11217UL, 0x5682250f329f93d0UL,
+	/*  76 */ 0x6cf00b136d2e396eUL, 0x6e4cf86f1014debfUL,
+		  0x5930b1b5bfcc4e83UL, 0x047069b48aba16b6UL,
+	/*  77 */ 0x0d4ce4ab69b20793UL, 0xb24db91a97d0fb9eUL,
+		  0xcdfa50f54e00d01dUL, 0x221b1085368bddb5UL,
+	/*  78 */ 0xe7e59468b1e3d8d2UL, 0x53c56563bd122f93UL,
+		  0xeee8a903e0663f09UL, 0x61efa662cbbe3d42UL,
+	/*  79 */ 0x2cf8ddddde6eab2aUL, 0x9bf80ad51435f231UL,
+		  0x5deadacec9f04973UL, 0x29275b5d41d29b27UL,
+	/*  80 */ 0xcfde0f0895ebf14fUL, 0xb9aab96b054905a7UL,
+		  0xcae80dd9a1c420fdUL, 0x0a63bf2f1673bbc7UL,
+	/*  81 */ 0x092f6e11958fbc8cUL, 0x672a81e804822fadUL,
+		  0xcac8351560d52517UL, 0x6f3f7722c8f192f8UL,
+	/*  82 */ 0xf8ba90ccc2e894b7UL, 0x2c7557a438ff9f0dUL,
+		  0x894d1d855ae52359UL, 0x68e122157b743d69UL,
+	/*  83 */ 0xd87e5570cfb919f3UL, 0x3f2cdecd95798db9UL,
+		  0x2121154710c0a2ceUL, 0x3c66a115246dc5b2UL,
+	/*  84 */ 0xcbedc562294ecb72UL, 0xba7143c36a280b16UL,
+		  0x9610c2efd4078b67UL, 0x6144735d946a4b1eUL,
+	/*  85 */ 0x536f111ed75b3350UL, 0x0211db8c2041d81bUL,
+		  0xf93cb1000e10413cUL, 0x149dfd3c039e8876UL,
+	/*  86 */ 0xd479dde46b63155bUL, 0xb66e15e93c837976UL,
+		  0xdafde43b1f13e038UL, 0x5fafda1a2e4b0b35UL,
+	/*  87 */ 0x3600bbdf17197581UL, 0x3972050bbe3cd2c2UL,
+		  0x5938906dbdd5be86UL, 0x34fce5e43f9b860fUL,
+	/*  88 */ 0x75a8a4cd42d14d02UL, 0x828dabc53441df65UL,
+		  0x33dcabedd2e131d3UL, 0x3ebad76fb814d25fUL,
+	/*  89 */ 0xd4906f566f70e10fUL, 0x5d12f7aa51690f5aUL,
+		  0x45adb16e76cefcf2UL, 0x01f768aead232999UL,
+	/*  90 */ 0x2b6cc77b6248febdUL, 0x3cd30628ec3aaffdUL,
+		  0xce1c0b80d4ef486aUL, 0x4c3bff2ea6f66c23UL,
+	/*  91 */ 0x3f2ec4094aeaeb5fUL, 0x61b19b286e372ca7UL,
+		  0x5eefa966de2a701dUL, 0x23b20565de55e3efUL,
+	/*  92 */ 0xe301ca5279d58557UL, 0x07b2d4ce27c2874fUL,
+		  0xa532cd8a9dcf1d67UL, 0x2a52fee23f2bff56UL,
+	/*  93 */ 0x8624efb37cd8663dUL, 0xbbc7ac20ffbd7594UL,
+		  0x57b85e9c82d37445UL, 0x7b3052cb86a6ec66UL,
+	/*  94 */ 0x3482f0ad2525e91eUL, 0x2cb68043d28edca0UL,
+		  0xaf4f6d052e1b003aUL, 0x185f8c2529781b0aUL,
+	/*  95 */ 0xaa41de5bd80ce0d6UL, 0x9407b2416853e9d6UL,
+		  0x563ec36e357f4c3aUL, 0x4cc4b8dd0e297bceUL,
+	/*  96 */ 0xa2fc1a52ffb8730eUL, 0x1811f16e67058e37UL,
+		  0x10f9a366cddf4ee1UL, 0x72f4a0c4a0b9f099UL,
+	/*  97 */ 0x8c16c06f663f4ea7UL, 0x693b3af74e970fbaUL,
+		  0x2102e7f1d69ec345UL, 0x0ba53cbc968a8089UL,
+	/*  98 */ 0xca3d9dc7fea15537UL, 0x4c6824bb51536493UL,
+		  0xb9886314844006b1UL, 0x40d2a72ab454cc60UL,
+	/*  99 */ 0x5936a1b712570975UL, 0x91b9d648debda657UL,
+		  0x3344094bb64330eaUL, 0x006ba10d12ee51d0UL,
+	/* 100 */ 0x19228468f5de5d58UL, 0x0eb12f4c38cc05b0UL,
+		  0xa1039f9dd5601990UL, 0x4502d4ce4fff0e0bUL,
+	/* 101 */ 0xeb2054106837c189UL, 0xd0f6544c6dd3b93cUL,
+		  0x40727064c416d74fUL, 0x6e15c6114b502ef0UL,
+	/* 102 */ 0x4df2a398cfb1a76bUL, 0x11256c7419f2f6b1UL,
+		  0x4a497962066e6043UL, 0x705b3aab41355b44UL,
+	/* 103 */ 0x365ef536d797b1d8UL, 0x00076bd622ddf0dbUL,
+		  0x3bbf33b0e0575a88UL, 0x3777aa05c8e4ca4dUL,
+	/* 104 */ 0x392745c85578db5fUL, 0x6fda4149dbae5ae2UL,
+		  0xb1f0b00b8adc9867UL, 0x09963437d36f1da3UL,
+	/* 105 */ 0x7e824e90a5dc3853UL, 0xccb5f6641f135cbdUL,
+		  0x6736d86c87ce8fccUL, 0x625f3ce26604249fUL,
+	/* 106 */ 0xaf8ac8059502f63fUL, 0x0c05e70a2e351469UL,
+		  0x35292e9c764b6305UL, 0x1a394360c7e23ac3UL,
+	/* 107 */ 0xd5c6d53251183264UL, 0x62065abd43c2b74fUL,
+		  0xb5fbf5d03b973f9bUL, 0x13a3da3661206e5eUL,
+	/* 108 */ 0xc6bd5837725d94e5UL, 0x18e30912205016c5UL,
+		  0x2088ce1570033c68UL, 0x7fba1f495c837987UL,
+	/* 109 */ 0x5a8c7423f2f9079dUL, 0x1735157b34023fc5UL,
+		  0xe4f9b49ad2fab351UL, 0x6691ff72c878e33cUL,
+	/* 110 */ 0x122c2adedc5eff3eUL, 0xf8dd4bf1d8956cf4UL,
+		  0xeb86205d9e9e5bdaUL, 0x049b92b9d975c743UL,
+	/* 111 */ 0xa5379730b0f6c05aUL, 0x72a0ffacc6f3a553UL,
+		  0xb0032c34b20dcd6dUL, 0x470e9dbc88d5164aUL,
+	/* 112 */ 0xb19cf10ca237c047UL, 0xb65466711f6c81a2UL,
+		  0xb3321bd16dd80b43UL, 0x48c14f600c5fbe8eUL,
+	/* 113 */ 0x66451c264aa6c803UL, 0xb66e3904a4fa7da6UL,
+		  0xd45f19b0b3128395UL, 0x31602627c3c9bc10UL,
+	/* 114 */ 0x3120dc4832e4e10dUL, 0xeb20c46756c717f7UL,
+		  0x00f52e3f67280294UL, 0x566d4fc14730c509UL,
+	/* 115 */ 0x7e3a5d40fd837206UL, 0xc1e926dc7159547aUL,
+		  0x216730fba68d6095UL, 0x22e8c3843f69cea7UL,
+	/* 116 */ 0x33d074e8930e4b2bUL, 0xb6e4350e84d15816UL,
+		  0x5534c26ad6ba2365UL, 0x7773c12f89f1f3f3UL,
+	/* 117 */ 0x8cba404da57962aaUL, 0x5b9897a81999ce56UL,
+		  0x508e862f121692fcUL, 0x3a81907fa093c291UL,
+	/* 118 */ 0x0dded0ff4725a510UL, 0x10d8cc10673fc503UL,
+		  0x5b9d151c9f1f4e89UL, 0x32a5c1d5cb09a44cUL,
+	/* 119 */ 0x1e0aa442b90541fbUL, 0x5f85eb7cc1b485dbUL,
+		  0xbee595ce8a9df2e5UL, 0x25e496c722422236UL,
+	/* 120 */ 0x5edf3c46cd0fe5b9UL, 0x34e75a7ed2a43388UL,
+		  0xe488de11d761e352UL, 0x0e878a01a085545cUL,
+	/* 121 */ 0xba493c77e021bb04UL, 0x2b4d1843c7df899aUL,
+		  0x9ea37a487ae80d67UL, 0x67a9958011e41794UL,
+	/* 122 */ 0x4b58051a6697b065UL, 0x47e33f7d8d6ba6d4UL,
+		  0xbb4da8d483ca46c1UL, 0x68becaa181c2db0dUL,
+	/* 123 */ 0x8d8980e90b989aa5UL, 0xf95eb14a2c93c99bUL,
+		  0x51c6c7c4796e73a2UL, 0x6e228363b5efb569UL,
+	/* 124 */ 0xc6bbc0b02dd624c8UL, 0x777eb47dec8170eeUL,
+		  0x3cde15a004cfafa9UL, 0x1dc6bc087160bf9bUL,
+	/* 125 */ 0x2e07e043eec34002UL, 0x18e9fc677a68dc7fUL,
+		  0xd8da03188bd15b9aUL, 0x48fbc3bb00568253UL,
+	/* 126 */ 0x57547d4cfb654ce1UL, 0xd3565b82a058e2adUL,
+		  0xf63eaf0bbf154478UL, 0x47531ef114dfbb18UL,
+	/* 127 */ 0xe1ec630a4278c587UL, 0x5507d546ca8e83f3UL,
+		  0x85e135c63adc0c2bUL, 0x0aa7efa85682844eUL,
+	/* 128 */ 0x72691ba8b3e1f615UL, 0x32b4e9701fbe3ffaUL,
+		  0x97b6d92e39bb7868UL, 0x2cfe53dea02e39e8UL,
+	/* 129 */ 0x687392cd85cd52b0UL, 0x27ff66c910e29831UL,
+		  0x97134556a9832d06UL, 0x269bb0360a84f8a0UL,
+	/* 130 */ 0x706e55457643f85cUL, 0x3734a48c9b597d1bUL,
+		  0x7aee91e8c6efa472UL, 0x5cd6abc198a9d9e0UL,
+	/* 131 */ 0x0e04de06cb3ce41aUL, 0xd8c6eb893402e138UL,
+		  0x904659bb686e3772UL, 0x7215c371746ba8c8UL,
+	/* 132 */ 0xfd12a97eeae4a2d9UL, 0x9514b7516394f2c5UL,
+		  0x266fd5809208f294UL, 0x5c847085619a26b9UL,
+	/* 133 */ 0x52985410fed694eaUL, 0x3c905b934a2ed254UL,
+		  0x10bb47692d3be467UL, 0x063b3d2d69e5e9e1UL,
+	/* 134 */ 0x472726eedda57debUL, 0xefb6c4ae10f41891UL,
+		  0x2b1641917b307614UL, 0x117c554fc4f45b7cUL,
+	/* 135 */ 0xc07cf3118f9d8812UL, 0x01dbd82050017939UL,
+		  0xd7e803f4171b2827UL, 0x1015e87487d225eaUL,
+	/* 136 */ 0xc58de3fed23acc4dUL, 0x50db91c294a7be2dUL,
+		  0x0b94d43d1c9cf457UL, 0x6b1640fa6e37524aUL,
+	/* 137 */ 0x692f346c5fda0d09UL, 0x200b1c59fa4d3151UL,
+		  0xb8c46f760777a296UL, 0x4b38395f3ffdfbcfUL,
+	/* 138 */ 0x18d25e00be54d671UL, 0x60d50582bec8aba6UL,
+		  0x87ad8f263b78b982UL, 0x50fdf64e9cda0432UL,
+	/* 139 */ 0x90f567aac578dcf0UL, 0xef1e9b0ef2a3133bUL,
+		  0x0eebba9242d9de71UL, 0x15473c9bf03101c7UL,
+	/* 140 */ 0x7c77e8ae56b78095UL, 0xb678e7666e6f078eUL,
+		  0x2da0b9615348ba1fUL, 0x7cf931c1ff733f0bUL,
+	/* 141 */ 0x26b357f50a0a366cUL, 0xe9708cf42b87d732UL,
+		  0xc13aeea5f91cb2c0UL, 0x35d90c991143bb4cUL,
+	/* 142 */ 0x47c1c404a9a0d9dcUL, 0x659e58451972d251UL,
+		  0x3875a8c473b38c31UL, 0x1fbd9ed379561f24UL,
+	/* 143 */ 0x11fabc6fd41ec28dUL, 0x7ef8dfe3cd2a2dcaUL,
+		  0x72e73b5d8c404595UL, 0x6135fa4954b72f27UL,
+	/* 144 */ 0xccfc32a2de24b69cUL, 0x3f55698c1f095d88UL,
+		  0xbe3350ed5ac3f929UL, 0x5e9bf806ca477eebUL,
+	/* 145 */ 0xe9ce8fb63c309f68UL, 0x5376f63565e1f9f4UL,
+		  0xd1afcfb35a6393f1UL, 0x6632a1ede5623506UL,
+	/* 146 */ 0x0b7d6c390c2ded4cUL, 0x56cb3281df04cb1fUL,
+		  0x66305a1249ecc3c7UL, 0x5d588b60a38ca72aUL,
+	/* 147 */ 0xa6ecbf78e8e5f42dUL, 0x86eeb44b3c8a3eecUL,
+		  0xec219c48fbd21604UL, 0x1aaf1af517c36731UL,
+	/* 148 */ 0xc306a2836769bde7UL, 0x208280622b1e2adbUL,
+		  0x8027f51ffbff94a6UL, 0x76cfa1ce1124f26bUL,
+	/* 149 */ 0x18eb00562422abb6UL, 0xf377c4d58f8c29c3UL,
+		  0x4dbbc207f531561aUL, 0x0253b7f082128a27UL,
+	/* 150 */ 0x3d1f091cb62c17e0UL, 0x4860e1abd64628a9UL,
+		  0x52d17436309d4253UL, 0x356f97e13efae576UL,
+	/* 151 */ 0xd351e11aa150535bUL, 0x3e6b45bb1dd878ccUL,
+		  0x0c776128bed92c98UL, 0x1d34ae93032885b8UL,
+	/* 152 */ 0x4ba0488ca85ba4c3UL, 0x985348c33c9ce6ceUL,
+		  0x66124c6f97bda770UL, 0x0f81a0290654124aUL,
+	/* 153 */ 0x9ed09ca6569b86fdUL, 0x811009fd18af9a2dUL,
+		  0xff08d03f93d8c20aUL, 0x52a148199faef26bUL,
+	/* 154 */ 0x3e03f9dc2d8d1b73UL, 0x4205801873961a70UL,
+		  0xc0d987f041a35970UL, 0x07aa1f15a1c0d549UL,
+	/* 155 */ 0xdfd46ce08cd27224UL, 0x6d0a024f934e4239UL,
+		  0x808a7a6399897b59UL, 0x0a4556e9e13d95a2UL,
+	/* 156 */ 0xd21a991fe9c13045UL, 0x9b0e8548fe7751b8UL,
+		  0x5da643cb4bf30035UL, 0x77db28d63940f721UL,
+	/* 157 */ 0xfc5eeb614adc9011UL, 0x5229419ae8c411ebUL,
+		  0x9ec3e7787d1dcf74UL, 0x340d053e216e4cb5UL,
+	/* 158 */ 0xcac7af39b48df2b4UL, 0xc0faec2871a10a94UL,
+		  0x140a69245ca575edUL, 0x0cf1c37134273a4cUL,
+	/* 159 */ 0xc8ee306ac224b8a5UL, 0x57eaee7ccb4930b0UL,
+		  0xa1e806bdaacbe74fUL, 0x7d9a62742eeb657dUL,
+	/* 160 */ 0x9eb6b6ef546c4830UL, 0x885cca1fddb36e2eUL,
+		  0xe6b9f383ef0d7105UL, 0x58654fef9d2e0412UL,
+	/* 161 */ 0xa905c4ffbe0e8e26UL, 0x942de5df9b31816eUL,
+		  0x497d723f802e88e1UL, 0x30684dea602f408dUL,
+	/* 162 */ 0x21e5a278a3e6cb34UL, 0xaefb6e6f5b151dc4UL,
+		  0xb30b8e049d77ca15UL, 0x28c3c9cf53b98981UL,
+	/* 163 */ 0x287fb721556cdd2aUL, 0x0d317ca897022274UL,
+		  0x7468c7423a543258UL, 0x4a7f11464eb5642fUL,
+	/* 164 */ 0xa237a4774d193aa6UL, 0xd865986ea92129a1UL,
+		  0x24c515ecf87c1a88UL, 0x604003575f39f5ebUL,
+	/* 165 */ 0x47b9f189570a9b27UL, 0x2b98cede465e4b78UL,
+		  0x026df551dbb85c20UL, 0x74fcd91047e21901UL,
+	/* 166 */ 0x13e2a90a23c1bfa3UL, 0x0cb0074e478519f6UL,
+		  0x5ff1cbbe3af6cf44UL, 0x67fe5438be812dbeUL,
+	/* 167 */ 0xd13cf64fa40f05b0UL, 0x054dfb2f32283787UL,
+		  0x4173915b7f0d2aeaUL, 0x482f144f1f610d4eUL,
+	/* 168 */ 0xf6210201b47f8234UL, 0x5d0ae1929e70b990UL,
+		  0xdcd7f455b049567cUL, 0x7e93d0f1f0916f01UL,
+	/* 169 */ 0xdd79cbf18a7db4faUL, 0xbe8391bf6f74c62fUL,
+		  0x027145d14b8291bdUL, 0x585a73ea2cbf1705UL,
+	/* 170 */ 0x485ca03e928a0db2UL, 0x10fc01a5742857e7UL,
+		  0x2f482edbd6d551a7UL, 0x0f0433b5048fdb8aUL,
+	/* 171 */ 0x60da2e8dd7dc6247UL, 0x88b4c9d38cd4819aUL,
+		  0x13033ac001f66697UL, 0x273b24fe3b367d75UL,
+	/* 172 */ 0xc6e8f66a31b3b9d4UL, 0x281514a494df49d5UL,
+		  0xd1726fdfc8b23da7UL, 0x4b3ae7d103dee548UL,
+	/* 173 */ 0xc6256e19ce4b9d7eUL, 0xff5c5cf186e3c61cUL,
+		  0xacc63ca34b8ec145UL, 0x74621888fee66574UL,
+	/* 174 */ 0x956f409645290a1eUL, 0xef0bf8e3263a962eUL,
+		  0xed6a50eb5ec2647bUL, 0x0694283a9dca7502UL,
+	/* 175 */ 0x769b963643a2dcd1UL, 0x42b7c8ea09fc5353UL,
+		  0x4f002aee13397eabUL, 0x63005e2c19b7d63aUL,
+	/* 176 */ 0xca6736da63023beaUL, 0x966c7f6db12a99b7UL,
+		  0xace09390c537c5e1UL, 0x0b696063a1aa89eeUL,
+	/* 177 */ 0xebb03e97288c56e5UL, 0x432a9f9f938c8be8UL,
+		  0xa6a5a93d5b717f71UL, 0x1a5fb4c3e18f9d97UL,
+	/* 178 */ 0x1c94e7ad1c60cdceUL, 0xee202a43fc02c4a0UL,
+		  0x8dafe4d867c46a20UL, 0x0a10263c8ac27b58UL,
+	/* 179 */ 0xd0dea9dfe4432a4aUL, 0x856af87bbe9277c5UL,
+		  0xce8472acc212c71aUL, 0x6f151b6d9bbb1e91UL,
+	/* 180 */ 0x26776c527ceed56aUL, 0x7d211cb7fbf8faecUL,
+		  0x37ae66a6fd4609ccUL, 0x1f81b702d2770c42UL,
+	/* 181 */ 0x2fb0b057eac58392UL, 0xe1dd89fe29744e9dUL,
+		  0xc964f8eb17beb4f8UL, 0x29571073c9a2d41eUL,
+	/* 182 */ 0xa948a18981c0e254UL, 0x2df6369b65b22830UL,
+		  0xa33eb2d75fcfd3c6UL, 0x078cd6ec4199a01fUL,
+	/* 183 */ 0x4a584a41ad900d2fUL, 0x32142b78e2c74c52UL,
+		  0x68c4e8338431c978UL, 0x7f69ea9008689fc2UL,
+	/* 184 */ 0x52f2c81e46a38265UL, 0xfd78072d04a832fdUL,
+		  0x8cd7d5fa25359e94UL, 0x4de71b7454cc29d2UL,
+	/* 185 */ 0x42eb60ad1eda6ac9UL, 0x0aad37dfdbc09c3aUL,
+		  0x81004b71e33cc191UL, 0x44e6be345122803cUL,
+	/* 186 */ 0x03fe8388ba1920dbUL, 0xf5d57c32150db008UL,
+		  0x49c8c4281af60c29UL, 0x21edb518de701aeeUL,
+	/* 187 */ 0x7fb63e418f06dc99UL, 0xa4460d99c166d7b8UL,
+		  0x24dd5248ce520a83UL, 0x5ec3ad712b928358UL,
+	/* 188 */ 0x15022a5fbd17930fUL, 0xa4f64a77d82570e3UL,
+		  0x12bc8d6915783712UL, 0x498194c0fc620abbUL,
+	/* 189 */ 0x38a2d9d255686c82UL, 0x785c6bd9193e21f0UL,
+		  0xe4d5c81ab24a5484UL, 0x56307860b2e20989UL,
+	/* 190 */ 0x429d55f78b4d74c4UL, 0x22f1834643350131UL,
+		  0x1e60c24598c71fffUL, 0x59f2f014979983efUL,
+	/* 191 */ 0x46a47d56eb494a44UL, 0x3e22a854d636a18eUL,
+		  0xb346e15274491c3bUL, 0x2ceafd4e5390cde7UL,
+	/* 192 */ 0xba8a8538be0d6675UL, 0x4b9074bb50818e23UL,
+		  0xcbdab89085d304c3UL, 0x61a24fe0e56192c4UL,
+	/* 193 */ 0xcb7615e6db525bcbUL, 0xdd7d8c35a567e4caUL,
+		  0xe6b4153acafcdd69UL, 0x2d668e097f3c9766UL,
+	/* 194 */ 0xa57e7e265ce55ef0UL, 0x5d9f4e527cd4b967UL,
+		  0xfbc83606492fd1e5UL, 0x090d52beb7c3f7aeUL,
+	/* 195 */ 0x09b9515a1e7b4d7cUL, 0x1f266a2599da44c0UL,
+		  0xa1c49548e2c55504UL, 0x7ef04287126f15ccUL,
+	/* 196 */ 0xfed1659dbd30ef15UL, 0x8b4ab9eec4e0277bUL,
+		  0x884d6236a5df3291UL, 0x1fd96ea6bf5cf788UL,
+	/* 197 */ 0x42a161981f190d9aUL, 0x61d849507e6052c1UL,
+		  0x9fe113bf285a2cd5UL, 0x7c22d676dbad85d8UL,
+	/* 198 */ 0x82e770ed2bfbd27dUL, 0x4c05b2ece996f5a5UL,
+		  0xcd40a9c2b0900150UL, 0x5895319213d9bf64UL,
+	/* 199 */ 0xe7cc5d703fea2e08UL, 0xb50c491258e2188cUL,
+		  0xcce30baa48205bf0UL, 0x537c659ccfa32d62UL,
+	/* 200 */ 0x37b6623a98cfc088UL, 0xfe9bed1fa4d6aca4UL,
+		  0x04d29b8e56a8d1b0UL, 0x725f71c40b519575UL,
+	/* 201 */ 0x28c7f89cd0339ce6UL, 0x8367b14469ddc18bUL,
+		  0x883ada83a6a1652cUL, 0x585f1974034d6c17UL,
+	/* 202 */ 0x89cfb266f1b19188UL, 0xe63b4863e7c35217UL,
+		  0xd88c9da6b4c0526aUL, 0x3e035c9df0954635UL,
+	/* 203 */ 0xdd9d5412fb45de9dUL, 0xdd684532e4cff40dUL,
+		  0x4b5c999b151d671cUL, 0x2d8c2cc811e7f690UL,
+	/* 204 */ 0x7f54be1d90055d40UL, 0xa464c5df464aaf40UL,
+		  0x33979624f0e917beUL, 0x2c018dc527356b30UL,
+	/* 205 */ 0xa5415024e330b3d4UL, 0x73ff3d96691652d3UL,
+		  0x94ec42c4ef9b59f1UL, 0x0747201618d08e5aUL,
+	/* 206 */ 0x4d6ca48aca411c53UL, 0x66415f2fcfa66119UL,
+		  0x9c4dd40051e227ffUL, 0x59810bc09a02f7ebUL,
+	/* 207 */ 0x2a7eb171b3dc101dUL, 0x441c5ab99ffef68eUL,
+		  0x32025c9b93b359eaUL, 0x5e8ce0a71e9d112fUL,
+	/* 208 */ 0xbfcccb92429503fdUL, 0xd271ba752f095d55UL,
+		  0x345ead5e972d091eUL, 0x18c8df11a83103baUL,
+	/* 209 */ 0x90cd949a9aed0f4cUL, 0xc5d1f4cb6660e37eUL,
+		  0xb8cac52d56c52e0bUL, 0x6e42e400c5808e0dUL,
+	/* 210 */ 0xa3b46966eeaefd23UL, 0x0c4f1f0be39ecdcaUL,
+		  0x189dc8c9d683a51dUL, 0x51f27f054c09351bUL,
+	/* 211 */ 0x4c487ccd2a320682UL, 0x587ea95bb3df1c96UL,
+		  0xc8ccf79e555cb8e8UL, 0x547dc829a206d73dUL,
+	/* 212 */ 0xb822a6cd80c39b06UL, 0xe96d54732000d4c6UL,
+		  0x28535b6f91463b4dUL, 0x228f4660e2486e1dUL,
+	/* 213 */ 0x98799538de8d3abfUL, 0x8cd8330045ebca6eUL,
+		  0x79952a008221e738UL, 0x4322e1a7535cd2bbUL,
+	/* 214 */ 0xb114c11819d1801cUL, 0x2016e4d84f3f5ec7UL,
+		  0xdd0e2df409260f4cUL, 0x5ec362c0ae5f7266UL,
+	/* 215 */ 0xc0462b18b8b2b4eeUL, 0x7cc8d950274d1afbUL,
+		  0xf25f7105436b02d2UL, 0x43bbf8dcbff9ccd3UL,
+	/* 216 */ 0xb6ad1767a039e9dfUL, 0xb0714da8f69d3583UL,
+		  0x5e55fa18b42931f5UL, 0x4ed5558f33c60961UL,
+	/* 217 */ 0x1fe37901c647a5ddUL, 0x593ddf1f8081d357UL,
+		  0x0249a4fd813fd7a6UL, 0x69acca274e9caf61UL,
+	/* 218 */ 0x047ba3ea330721c9UL, 0x83423fc20e7e1ea0UL,
+		  0x1df4c0af01314a60UL, 0x09a62dab89289527UL,
+	/* 219 */ 0xa5b325a49cc6cb00UL, 0xe94b5dc654b56cb6UL,
+		  0x3be28779adc994a0UL, 0x4296e8f8ba3a4aadUL,
+	/* 220 */ 0x328689761e451eabUL, 0x2e4d598bff59594aUL,
+		  0x49b96853d7a7084aUL, 0x4980a319601420a8UL,
+	/* 221 */ 0x9565b9e12f552c42UL, 0x8a5318db7100fe96UL,
+		  0x05c90b4d43add0d7UL, 0x538b4cd66a5d4edaUL,
+	/* 222 */ 0xf4e94fc3e89f039fUL, 0x592c9af26f618045UL,
+		  0x08a36eb5fd4b9550UL, 0x25fffaf6c2ed1419UL,
+	/* 223 */ 0x34434459cc79d354UL, 0xeeecbfb4b1d5476bUL,
+		  0xddeb34a061615d99UL, 0x5129cecceb64b773UL,
+	/* 224 */ 0xee43215894993520UL, 0x772f9c7cf14c0b3bUL,
+		  0xd2e2fce306bedad5UL, 0x715f42b546f06a97UL,
+	/* 225 */ 0x434ecdceda5b5f1aUL, 0x0da17115a49741a9UL,
+		  0x680bd77c73edad2eUL, 0x487c02354edd9041UL,
+	/* 226 */ 0xb8efeff3a70ed9c4UL, 0x56a32aa3e857e302UL,
+		  0xdf3a68bd48a2a5a0UL, 0x07f650b73176c444UL,
+	/* 227 */ 0xe38b9b1626e0ccb1UL, 0x79e053c18b09fb36UL,
+		  0x56d90319c9f94964UL, 0x1ca941e7ac9ff5c4UL,
+	/* 228 */ 0x49c4df29162fa0bbUL, 0x8488cf3282b33305UL,
+		  0x95dfda14cabb437dUL, 0x3391f78264d5ad86UL,
+	/* 229 */ 0x729ae06ae2b5095dUL, 0xd58a58d73259a946UL,
+		  0xe9834262d13921edUL, 0x27fedafaa54bb592UL,
+	/* 230 */ 0xa99dc5b829ad48bbUL, 0x5f025742499ee260UL,
+		  0x802c8ecd5d7513fdUL, 0x78ceb3ef3f6dd938UL,
+	/* 231 */ 0xc342f44f8a135d94UL, 0x7b9edb44828cdda3UL,
+		  0x9436d11a0537cfe7UL, 0x5064b164ec1ab4c8UL,
+	/* 232 */ 0x7020eccfd37eb2fcUL, 0x1f31ea3ed90d25fcUL,
+		  0x1b930d7bdfa1bb34UL, 0x5344467a48113044UL,
+	/* 233 */ 0x70073170f25e6dfbUL, 0xe385dc1a50114cc8UL,
+		  0x2348698ac8fc4f00UL, 0x2a77a55284dd40d8UL,
+	/* 234 */ 0xfe06afe0c98c6ce4UL, 0xc235df96dddfd6e4UL,
+		  0x1428d01e33bf1ed3UL, 0x785768ec9300bdafUL,
+	/* 235 */ 0x9702e57a91deb63bUL, 0x61bdb8bfe5ce8b80UL,
+		  0x645b426f3d1d58acUL, 0x4804a82227a557bcUL,
+	/* 236 */ 0x8e57048ab44d2601UL, 0x68d6501a4b3a6935UL,
+		  0xc39c9ec3f9e1c293UL, 0x4172f257d4de63e2UL,
+	/* 237 */ 0xd368b450330c6401UL, 0x040d3017418f2391UL,
+		  0x2c34bb6090b7d90dUL, 0x16f649228fdfd51fUL,
+	/* 238 */ 0xbea6818e2b928ef5UL, 0xe28ccf91cdc11e72UL,
+		  0x594aaa68e77a36cdUL, 0x313034806c7ffd0fUL,
+	/* 239 */ 0x8a9d27ac2249bd65UL, 0x19a3b464018e9512UL,
+		  0xc26ccff352b37ec7UL, 0x056f68341d797b21UL,
+	/* 240 */ 0x5e79d6757efd2327UL, 0xfabdbcb6553afe15UL,
+		  0xd3e7222c6eaf5a60UL, 0x7046c76d4dae743bUL,
+	/* 241 */ 0x660be872b18d4a55UL, 0x19992518574e1496UL,
+		  0xc103053a302bdcbbUL, 0x3ed8e9800b218e8eUL,
+	/* 242 */ 0x7b0b9239fa75e03eUL, 0xefe9fb684633c083UL,
+		  0x98a35fbe391a7793UL, 0x6065510fe2d0fe34UL,
+	/* 243 */ 0x55cb668548abad0cUL, 0xb4584548da87e527UL,
+		  0x2c43ecea0107c1ddUL, 0x526028809372de35UL,
+	/* 244 */ 0x3415c56af9213b1fUL, 0x5bee1a4d017e98dbUL,
+		  0x13f6b105b5cf709bUL, 0x5ff20e3482b29ab6UL,
+	/* 245 */ 0x0aa29c75cc2e6c90UL, 0xfc7d73ca3a70e206UL,
+		  0x899fc38fc4b5c515UL, 0x250386b124ffc207UL,
+	/* 246 */ 0x54ea28d5ae3d2b56UL, 0x9913149dd6de60ceUL,
+		  0x16694fc58f06d6c1UL, 0x46b23975eb018fc7UL,
+	/* 247 */ 0x470a6a0fb4b7b4e2UL, 0x5d92475a8f7253deUL,
+		  0xabeee5b52fbd3adbUL, 0x7fa20801a0806968UL,
+	/* 248 */ 0x76f3faf19f7714d2UL, 0xb3e840c12f4660c3UL,
+		  0x0fb4cd8df212744eUL, 0x4b065a251d3a2dd2UL,
+	/* 249 */ 0x5cebde383d77cd4aUL, 0x6adf39df882c9cb1UL,
+		  0xa2dd242eb09af759UL, 0x3147c0e50e5f6422UL,
+	/* 250 */ 0x164ca5101d1350dbUL, 0xf8d13479c33fc962UL,
+		  0xe640ce4d13e5da08UL, 0x4bdee0c45061f8baUL,
+	/* 251 */ 0xd7c46dc1a4edb1c9UL, 0x5514d7b6437fd98aUL,
+		  0x58942f6bb2a1c00bUL, 0x2dffb2ab1d70710eUL,
+	/* 252 */ 0xccdfcf2fc18b6d68UL, 0xa8ebcba8b7806167UL,
+		  0x980697f95e2937e3UL, 0x02fbba1cd0126e8cUL
+};
+
+/* c is two 512-bit products: c0[0:7]=a0[0:3]*b0[0:3] and c1[8:15]=a1[4:7]*b1[4:7]
+ * a is two 256-bit integers: a0[0:3] and a1[4:7]
+ * b is two 256-bit integers: b0[0:3] and b1[4:7]
+ */
+static void mul2_256x256_integer_adx(u64 *const c, const u64 *const a,
+				     const u64 *const b)
+{
+	asm volatile(
+		"xorl %%r14d, %%r14d ;"
+		"movq   (%1), %%rdx; "	/* A[0] */
+		"mulx   (%2),  %%r8, %%r15; " /* A[0]*B[0] */
+		"xorl %%r10d, %%r10d ;"
+		"movq %%r8, (%0) ;"
+		"mulx  8(%2), %%r10, %%rax; " /* A[0]*B[1] */
+		"adox %%r10, %%r15 ;"
+		"mulx 16(%2),  %%r8, %%rbx; " /* A[0]*B[2] */
+		"adox  %%r8, %%rax ;"
+		"mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */
+		"adox %%r10, %%rbx ;"
+		/******************************************/
+		"adox %%r14, %%rcx ;"
+
+		"movq  8(%1), %%rdx; "	/* A[1] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[1]*B[0] */
+		"adox %%r15,  %%r8 ;"
+		"movq  %%r8, 8(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[1]*B[1] */
+		"adox %%r10,  %%r9 ;"
+		"adcx  %%r9, %%rax ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[1]*B[2] */
+		"adox  %%r8, %%r11 ;"
+		"adcx %%r11, %%rbx ;"
+		"mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */
+		"adox %%r10, %%r13 ;"
+		"adcx %%r13, %%rcx ;"
+		/******************************************/
+		"adox %%r14, %%r15 ;"
+		"adcx %%r14, %%r15 ;"
+
+		"movq 16(%1), %%rdx; " /* A[2] */
+		"xorl %%r10d, %%r10d ;"
+		"mulx   (%2),  %%r8,  %%r9; " /* A[2]*B[0] */
+		"adox %%rax,  %%r8 ;"
+		"movq %%r8, 16(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[2]*B[1] */
+		"adox %%r10,  %%r9 ;"
+		"adcx  %%r9, %%rbx ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[2]*B[2] */
+		"adox  %%r8, %%r11 ;"
+		"adcx %%r11, %%rcx ;"
+		"mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */
+		"adox %%r10, %%r13 ;"
+		"adcx %%r13, %%r15 ;"
+		/******************************************/
+		"adox %%r14, %%rax ;"
+		"adcx %%r14, %%rax ;"
+
+		"movq 24(%1), %%rdx; " /* A[3] */
+		"xorl %%r10d, %%r10d ;"
+		"mulx   (%2),  %%r8,  %%r9; " /* A[3]*B[0] */
+		"adox %%rbx,  %%r8 ;"
+		"movq %%r8, 24(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[3]*B[1] */
+		"adox %%r10,  %%r9 ;"
+		"adcx  %%r9, %%rcx ;"
+		"movq %%rcx, 32(%0) ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[3]*B[2] */
+		"adox  %%r8, %%r11 ;"
+		"adcx %%r11, %%r15 ;"
+		"movq %%r15, 40(%0) ;"
+		"mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */
+		"adox %%r10, %%r13 ;"
+		"adcx %%r13, %%rax ;"
+		"movq %%rax, 48(%0) ;"
+		/******************************************/
+		"adox %%r14, %%rbx ;"
+		"adcx %%r14, %%rbx ;"
+		"movq %%rbx, 56(%0) ;"
+
+		"movq 32(%1), %%rdx; "	/* C[0] */
+		"mulx 32(%2),  %%r8, %%r15; " /* C[0]*D[0] */
+		"xorl %%r10d, %%r10d ;"
+		"movq %%r8, 64(%0);"
+		"mulx 40(%2), %%r10, %%rax; " /* C[0]*D[1] */
+		"adox %%r10, %%r15 ;"
+		"mulx 48(%2),  %%r8, %%rbx; " /* C[0]*D[2] */
+		"adox  %%r8, %%rax ;"
+		"mulx 56(%2), %%r10, %%rcx; " /* C[0]*D[3] */
+		"adox %%r10, %%rbx ;"
+		/******************************************/
+		"adox %%r14, %%rcx ;"
+
+		"movq 40(%1), %%rdx; " /* C[1] */
+		"xorl %%r10d, %%r10d ;"
+		"mulx 32(%2),  %%r8,  %%r9; " /* C[1]*D[0] */
+		"adox %%r15,  %%r8 ;"
+		"movq  %%r8, 72(%0);"
+		"mulx 40(%2), %%r10, %%r11; " /* C[1]*D[1] */
+		"adox %%r10,  %%r9 ;"
+		"adcx  %%r9, %%rax ;"
+		"mulx 48(%2),  %%r8, %%r13; " /* C[1]*D[2] */
+		"adox  %%r8, %%r11 ;"
+		"adcx %%r11, %%rbx ;"
+		"mulx 56(%2), %%r10, %%r15; " /* C[1]*D[3] */
+		"adox %%r10, %%r13 ;"
+		"adcx %%r13, %%rcx ;"
+		/******************************************/
+		"adox %%r14, %%r15 ;"
+		"adcx %%r14, %%r15 ;"
+
+		"movq 48(%1), %%rdx; " /* C[2] */
+		"xorl %%r10d, %%r10d ;"
+		"mulx 32(%2),  %%r8,  %%r9; " /* C[2]*D[0] */
+		"adox %%rax,  %%r8 ;"
+		"movq  %%r8, 80(%0);"
+		"mulx 40(%2), %%r10, %%r11; " /* C[2]*D[1] */
+		"adox %%r10,  %%r9 ;"
+		"adcx  %%r9, %%rbx ;"
+		"mulx 48(%2),  %%r8, %%r13; " /* C[2]*D[2] */
+		"adox  %%r8, %%r11 ;"
+		"adcx %%r11, %%rcx ;"
+		"mulx 56(%2), %%r10, %%rax; " /* C[2]*D[3] */
+		"adox %%r10, %%r13 ;"
+		"adcx %%r13, %%r15 ;"
+		/******************************************/
+		"adox %%r14, %%rax ;"
+		"adcx %%r14, %%rax ;"
+
+		"movq 56(%1), %%rdx; " /* C[3] */
+		"xorl %%r10d, %%r10d ;"
+		"mulx 32(%2),  %%r8,  %%r9; " /* C[3]*D[0] */
+		"adox %%rbx,  %%r8 ;"
+		"movq  %%r8, 88(%0);"
+		"mulx 40(%2), %%r10, %%r11; " /* C[3]*D[1] */
+		"adox %%r10,  %%r9 ;"
+		"adcx  %%r9, %%rcx ;"
+		"movq %%rcx,  96(%0) ;"
+		"mulx 48(%2),  %%r8, %%r13; " /* C[3]*D[2] */
+		"adox  %%r8, %%r11 ;"
+		"adcx %%r11, %%r15 ;"
+		"movq %%r15, 104(%0) ;"
+		"mulx 56(%2), %%r10, %%rbx; " /* C[3]*D[3] */
+		"adox %%r10, %%r13 ;"
+		"adcx %%r13, %%rax ;"
+		"movq %%rax, 112(%0) ;"
+		/******************************************/
+		"adox %%r14, %%rbx ;"
+		"adcx %%r14, %%rbx ;"
+		"movq %%rbx, 120(%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(b)
+		: "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9",
+		  "%r10", "%r11", "%r13", "%r14", "%r15");
+}
+
+static void mul2_256x256_integer_bmi2(u64 *const c, const u64 *const a,
+				      const u64 *const b)
+{
+	asm volatile(
+		"movq   (%1), %%rdx; "	/* A[0] */
+		"mulx   (%2),  %%r8, %%r15; " /* A[0]*B[0] */
+		"movq %%r8,  (%0) ;"
+		"mulx  8(%2), %%r10, %%rax; " /* A[0]*B[1] */
+		"addq %%r10, %%r15 ;"
+		"mulx 16(%2),  %%r8, %%rbx; " /* A[0]*B[2] */
+		"adcq  %%r8, %%rax ;"
+		"mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */
+		"adcq %%r10, %%rbx ;"
+		/******************************************/
+		"adcq    $0, %%rcx ;"
+
+		"movq  8(%1), %%rdx; "	/* A[1] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[1]*B[0] */
+		"addq %%r15,  %%r8 ;"
+		"movq %%r8, 8(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[1]*B[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[1]*B[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%r15 ;"
+
+		"addq  %%r9, %%rax ;"
+		"adcq %%r11, %%rbx ;"
+		"adcq %%r13, %%rcx ;"
+		"adcq    $0, %%r15 ;"
+
+		"movq 16(%1), %%rdx; "	/* A[2] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[2]*B[0] */
+		"addq %%rax,  %%r8 ;"
+		"movq %%r8, 16(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[2]*B[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[2]*B[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%rax ;"
+
+		"addq  %%r9, %%rbx ;"
+		"adcq %%r11, %%rcx ;"
+		"adcq %%r13, %%r15 ;"
+		"adcq    $0, %%rax ;"
+
+		"movq 24(%1), %%rdx; "	/* A[3] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[3]*B[0] */
+		"addq %%rbx,  %%r8 ;"
+		"movq %%r8, 24(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[3]*B[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[3]*B[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%rbx ;"
+
+		"addq  %%r9, %%rcx ;"
+		"movq %%rcx, 32(%0) ;"
+		"adcq %%r11, %%r15 ;"
+		"movq %%r15, 40(%0) ;"
+		"adcq %%r13, %%rax ;"
+		"movq %%rax, 48(%0) ;"
+		"adcq    $0, %%rbx ;"
+		"movq %%rbx, 56(%0) ;"
+
+		"movq 32(%1), %%rdx; "	/* C[0] */
+		"mulx 32(%2),  %%r8, %%r15; " /* C[0]*D[0] */
+		"movq %%r8, 64(%0) ;"
+		"mulx 40(%2), %%r10, %%rax; " /* C[0]*D[1] */
+		"addq %%r10, %%r15 ;"
+		"mulx 48(%2),  %%r8, %%rbx; " /* C[0]*D[2] */
+		"adcq  %%r8, %%rax ;"
+		"mulx 56(%2), %%r10, %%rcx; " /* C[0]*D[3] */
+		"adcq %%r10, %%rbx ;"
+		/******************************************/
+		"adcq    $0, %%rcx ;"
+
+		"movq 40(%1), %%rdx; "	/* C[1] */
+		"mulx 32(%2),  %%r8,  %%r9; " /* C[1]*D[0] */
+		"addq %%r15,  %%r8 ;"
+		"movq %%r8, 72(%0) ;"
+		"mulx 40(%2), %%r10, %%r11; " /* C[1]*D[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 48(%2),  %%r8, %%r13; " /* C[1]*D[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 56(%2), %%r10, %%r15; " /* C[1]*D[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%r15 ;"
+
+		"addq  %%r9, %%rax ;"
+		"adcq %%r11, %%rbx ;"
+		"adcq %%r13, %%rcx ;"
+		"adcq    $0, %%r15 ;"
+
+		"movq 48(%1), %%rdx; "	/* C[2] */
+		"mulx 32(%2),  %%r8,  %%r9; " /* C[2]*D[0] */
+		"addq %%rax,  %%r8 ;"
+		"movq %%r8, 80(%0) ;"
+		"mulx 40(%2), %%r10, %%r11; " /* C[2]*D[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 48(%2),  %%r8, %%r13; " /* C[2]*D[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 56(%2), %%r10, %%rax; " /* C[2]*D[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%rax ;"
+
+		"addq  %%r9, %%rbx ;"
+		"adcq %%r11, %%rcx ;"
+		"adcq %%r13, %%r15 ;"
+		"adcq    $0, %%rax ;"
+
+		"movq 56(%1), %%rdx; "	/* C[3] */
+		"mulx 32(%2),  %%r8,  %%r9; " /* C[3]*D[0] */
+		"addq %%rbx,  %%r8 ;"
+		"movq %%r8, 88(%0) ;"
+		"mulx 40(%2), %%r10, %%r11; " /* C[3]*D[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 48(%2),  %%r8, %%r13; " /* C[3]*D[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 56(%2), %%r10, %%rbx; " /* C[3]*D[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%rbx ;"
+
+		"addq  %%r9, %%rcx ;"
+		"movq %%rcx,  96(%0) ;"
+		"adcq %%r11, %%r15 ;"
+		"movq %%r15, 104(%0) ;"
+		"adcq %%r13, %%rax ;"
+		"movq %%rax, 112(%0) ;"
+		"adcq    $0, %%rbx ;"
+		"movq %%rbx, 120(%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(b)
+		: "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9",
+		  "%r10", "%r11", "%r13", "%r15");
+}
+
+static void sqr2_256x256_integer_adx(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movq   (%1), %%rdx        ;" /* A[0]      */
+		"mulx  8(%1),  %%r8, %%r14 ;" /* A[1]*A[0] */
+		"xorl %%r15d, %%r15d;"
+		"mulx 16(%1),  %%r9, %%r10 ;" /* A[2]*A[0] */
+		"adcx %%r14,  %%r9 ;"
+		"mulx 24(%1), %%rax, %%rcx ;" /* A[3]*A[0] */
+		"adcx %%rax, %%r10 ;"
+		"movq 24(%1), %%rdx        ;" /* A[3]      */
+		"mulx  8(%1), %%r11, %%rbx ;" /* A[1]*A[3] */
+		"adcx %%rcx, %%r11 ;"
+		"mulx 16(%1), %%rax, %%r13 ;" /* A[2]*A[3] */
+		"adcx %%rax, %%rbx ;"
+		"movq  8(%1), %%rdx        ;" /* A[1]      */
+		"adcx %%r15, %%r13 ;"
+		"mulx 16(%1), %%rax, %%rcx ;" /* A[2]*A[1] */
+		"movq    $0, %%r14 ;"
+		/******************************************/
+		"adcx %%r15, %%r14 ;"
+
+		"xorl %%r15d, %%r15d;"
+		"adox %%rax, %%r10 ;"
+		"adcx  %%r8,  %%r8 ;"
+		"adox %%rcx, %%r11 ;"
+		"adcx  %%r9,  %%r9 ;"
+		"adox %%r15, %%rbx ;"
+		"adcx %%r10, %%r10 ;"
+		"adox %%r15, %%r13 ;"
+		"adcx %%r11, %%r11 ;"
+		"adox %%r15, %%r14 ;"
+		"adcx %%rbx, %%rbx ;"
+		"adcx %%r13, %%r13 ;"
+		"adcx %%r14, %%r14 ;"
+
+		"movq   (%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */
+		/*******************/
+		"movq %%rax,  0(%0) ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,  8(%0) ;"
+		"movq  8(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */
+		"adcq %%rax,  %%r9 ;"
+		"movq  %%r9, 16(%0) ;"
+		"adcq %%rcx, %%r10 ;"
+		"movq %%r10, 24(%0) ;"
+		"movq 16(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */
+		"adcq %%rax, %%r11 ;"
+		"movq %%r11, 32(%0) ;"
+		"adcq %%rcx, %%rbx ;"
+		"movq %%rbx, 40(%0) ;"
+		"movq 24(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */
+		"adcq %%rax, %%r13 ;"
+		"movq %%r13, 48(%0) ;"
+		"adcq %%rcx, %%r14 ;"
+		"movq %%r14, 56(%0) ;"
+
+
+		"movq 32(%1), %%rdx        ;" /* B[0]      */
+		"mulx 40(%1),  %%r8, %%r14 ;" /* B[1]*B[0] */
+		"xorl %%r15d, %%r15d;"
+		"mulx 48(%1),  %%r9, %%r10 ;" /* B[2]*B[0] */
+		"adcx %%r14,  %%r9 ;"
+		"mulx 56(%1), %%rax, %%rcx ;" /* B[3]*B[0] */
+		"adcx %%rax, %%r10 ;"
+		"movq 56(%1), %%rdx        ;" /* B[3]      */
+		"mulx 40(%1), %%r11, %%rbx ;" /* B[1]*B[3] */
+		"adcx %%rcx, %%r11 ;"
+		"mulx 48(%1), %%rax, %%r13 ;" /* B[2]*B[3] */
+		"adcx %%rax, %%rbx ;"
+		"movq 40(%1), %%rdx        ;" /* B[1]      */
+		"adcx %%r15, %%r13 ;"
+		"mulx 48(%1), %%rax, %%rcx ;" /* B[2]*B[1] */
+		"movq    $0, %%r14 ;"
+		/******************************************/
+		"adcx %%r15, %%r14 ;"
+
+		"xorl %%r15d, %%r15d;"
+		"adox %%rax, %%r10 ;"
+		"adcx  %%r8,  %%r8 ;"
+		"adox %%rcx, %%r11 ;"
+		"adcx  %%r9,  %%r9 ;"
+		"adox %%r15, %%rbx ;"
+		"adcx %%r10, %%r10 ;"
+		"adox %%r15, %%r13 ;"
+		"adcx %%r11, %%r11 ;"
+		"adox %%r15, %%r14 ;"
+		"adcx %%rbx, %%rbx ;"
+		"adcx %%r13, %%r13 ;"
+		"adcx %%r14, %%r14 ;"
+
+		"movq 32(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* B[0]^2 */
+		/*******************/
+		"movq %%rax,  64(%0) ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,  72(%0) ;"
+		"movq 40(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* B[1]^2 */
+		"adcq %%rax,  %%r9 ;"
+		"movq  %%r9,  80(%0) ;"
+		"adcq %%rcx, %%r10 ;"
+		"movq %%r10,  88(%0) ;"
+		"movq 48(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* B[2]^2 */
+		"adcq %%rax, %%r11 ;"
+		"movq %%r11,  96(%0) ;"
+		"adcq %%rcx, %%rbx ;"
+		"movq %%rbx, 104(%0) ;"
+		"movq 56(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* B[3]^2 */
+		"adcq %%rax, %%r13 ;"
+		"movq %%r13, 112(%0) ;"
+		"adcq %%rcx, %%r14 ;"
+		"movq %%r14, 120(%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9",
+		  "%r10", "%r11", "%r13", "%r14", "%r15");
+}
+
+static void sqr2_256x256_integer_bmi2(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movq  8(%1), %%rdx        ;" /* A[1]      */
+		"mulx   (%1),  %%r8,  %%r9 ;" /* A[0]*A[1] */
+		"mulx 16(%1), %%r10, %%r11 ;" /* A[2]*A[1] */
+		"mulx 24(%1), %%rcx, %%r14 ;" /* A[3]*A[1] */
+
+		"movq 16(%1), %%rdx        ;" /* A[2]      */
+		"mulx 24(%1), %%r15, %%r13 ;" /* A[3]*A[2] */
+		"mulx   (%1), %%rax, %%rdx ;" /* A[0]*A[2] */
+
+		"addq %%rax,  %%r9 ;"
+		"adcq %%rdx, %%r10 ;"
+		"adcq %%rcx, %%r11 ;"
+		"adcq %%r14, %%r15 ;"
+		"adcq    $0, %%r13 ;"
+		"movq    $0, %%r14 ;"
+		"adcq    $0, %%r14 ;"
+
+		"movq   (%1), %%rdx        ;" /* A[0]      */
+		"mulx 24(%1), %%rax, %%rcx ;" /* A[0]*A[3] */
+
+		"addq %%rax, %%r10 ;"
+		"adcq %%rcx, %%r11 ;"
+		"adcq    $0, %%r15 ;"
+		"adcq    $0, %%r13 ;"
+		"adcq    $0, %%r14 ;"
+
+		"shldq $1, %%r13, %%r14 ;"
+		"shldq $1, %%r15, %%r13 ;"
+		"shldq $1, %%r11, %%r15 ;"
+		"shldq $1, %%r10, %%r11 ;"
+		"shldq $1,  %%r9, %%r10 ;"
+		"shldq $1,  %%r8,  %%r9 ;"
+		"shlq  $1,  %%r8        ;"
+
+		/*******************/
+		"mulx %%rdx, %%rax, %%rcx ; " /* A[0]^2 */
+		/*******************/
+		"movq %%rax,  0(%0) ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,  8(%0) ;"
+		"movq  8(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ; " /* A[1]^2 */
+		"adcq %%rax,  %%r9 ;"
+		"movq  %%r9, 16(%0) ;"
+		"adcq %%rcx, %%r10 ;"
+		"movq %%r10, 24(%0) ;"
+		"movq 16(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ; " /* A[2]^2 */
+		"adcq %%rax, %%r11 ;"
+		"movq %%r11, 32(%0) ;"
+		"adcq %%rcx, %%r15 ;"
+		"movq %%r15, 40(%0) ;"
+		"movq 24(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ; " /* A[3]^2 */
+		"adcq %%rax, %%r13 ;"
+		"movq %%r13, 48(%0) ;"
+		"adcq %%rcx, %%r14 ;"
+		"movq %%r14, 56(%0) ;"
+
+		"movq 40(%1), %%rdx        ;" /* B[1]      */
+		"mulx 32(%1),  %%r8,  %%r9 ;" /* B[0]*B[1] */
+		"mulx 48(%1), %%r10, %%r11 ;" /* B[2]*B[1] */
+		"mulx 56(%1), %%rcx, %%r14 ;" /* B[3]*B[1] */
+
+		"movq 48(%1), %%rdx        ;" /* B[2]      */
+		"mulx 56(%1), %%r15, %%r13 ;" /* B[3]*B[2] */
+		"mulx 32(%1), %%rax, %%rdx ;" /* B[0]*B[2] */
+
+		"addq %%rax,  %%r9 ;"
+		"adcq %%rdx, %%r10 ;"
+		"adcq %%rcx, %%r11 ;"
+		"adcq %%r14, %%r15 ;"
+		"adcq    $0, %%r13 ;"
+		"movq    $0, %%r14 ;"
+		"adcq    $0, %%r14 ;"
+
+		"movq 32(%1), %%rdx        ;" /* B[0]      */
+		"mulx 56(%1), %%rax, %%rcx ;" /* B[0]*B[3] */
+
+		"addq %%rax, %%r10 ;"
+		"adcq %%rcx, %%r11 ;"
+		"adcq    $0, %%r15 ;"
+		"adcq    $0, %%r13 ;"
+		"adcq    $0, %%r14 ;"
+
+		"shldq $1, %%r13, %%r14 ;"
+		"shldq $1, %%r15, %%r13 ;"
+		"shldq $1, %%r11, %%r15 ;"
+		"shldq $1, %%r10, %%r11 ;"
+		"shldq $1,  %%r9, %%r10 ;"
+		"shldq $1,  %%r8,  %%r9 ;"
+		"shlq  $1,  %%r8        ;"
+
+		/*******************/
+		"mulx %%rdx, %%rax, %%rcx ; " /* B[0]^2 */
+		/*******************/
+		"movq %%rax,  64(%0) ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,  72(%0) ;"
+		"movq 40(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ; " /* B[1]^2 */
+		"adcq %%rax,  %%r9 ;"
+		"movq  %%r9,  80(%0) ;"
+		"adcq %%rcx, %%r10 ;"
+		"movq %%r10,  88(%0) ;"
+		"movq 48(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ; " /* B[2]^2 */
+		"adcq %%rax, %%r11 ;"
+		"movq %%r11,  96(%0) ;"
+		"adcq %%rcx, %%r15 ;"
+		"movq %%r15, 104(%0) ;"
+		"movq 56(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ; " /* B[3]^2 */
+		"adcq %%rax, %%r13 ;"
+		"movq %%r13, 112(%0) ;"
+		"adcq %%rcx, %%r14 ;"
+		"movq %%r14, 120(%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10",
+		  "%r11", "%r13", "%r14", "%r15");
+}
+
+static void red_eltfp25519_2w_adx(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movl    $38, %%edx; "	/* 2*c = 38 = 2^256 */
+		"mulx 32(%1),  %%r8, %%r10; " /* c*C[4] */
+		"xorl %%ebx, %%ebx ;"
+		"adox   (%1),  %%r8 ;"
+		"mulx 40(%1),  %%r9, %%r11; " /* c*C[5] */
+		"adcx %%r10,  %%r9 ;"
+		"adox  8(%1),  %%r9 ;"
+		"mulx 48(%1), %%r10, %%rax; " /* c*C[6] */
+		"adcx %%r11, %%r10 ;"
+		"adox 16(%1), %%r10 ;"
+		"mulx 56(%1), %%r11, %%rcx; " /* c*C[7] */
+		"adcx %%rax, %%r11 ;"
+		"adox 24(%1), %%r11 ;"
+		/***************************************/
+		"adcx %%rbx, %%rcx ;"
+		"adox  %%rbx, %%rcx ;"
+		"imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */
+		"adcx %%rcx,  %%r8 ;"
+		"adcx %%rbx,  %%r9 ;"
+		"movq  %%r9,  8(%0) ;"
+		"adcx %%rbx, %%r10 ;"
+		"movq %%r10, 16(%0) ;"
+		"adcx %%rbx, %%r11 ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $0, %%ecx ;"
+		"cmovc %%edx, %%ecx ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,   (%0) ;"
+
+		"mulx  96(%1),  %%r8, %%r10; " /* c*C[4] */
+		"xorl %%ebx, %%ebx ;"
+		"adox 64(%1),  %%r8 ;"
+		"mulx 104(%1),  %%r9, %%r11; " /* c*C[5] */
+		"adcx %%r10,  %%r9 ;"
+		"adox 72(%1),  %%r9 ;"
+		"mulx 112(%1), %%r10, %%rax; " /* c*C[6] */
+		"adcx %%r11, %%r10 ;"
+		"adox 80(%1), %%r10 ;"
+		"mulx 120(%1), %%r11, %%rcx; " /* c*C[7] */
+		"adcx %%rax, %%r11 ;"
+		"adox 88(%1), %%r11 ;"
+		/****************************************/
+		"adcx %%rbx, %%rcx ;"
+		"adox  %%rbx, %%rcx ;"
+		"imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */
+		"adcx %%rcx,  %%r8 ;"
+		"adcx %%rbx,  %%r9 ;"
+		"movq  %%r9, 40(%0) ;"
+		"adcx %%rbx, %%r10 ;"
+		"movq %%r10, 48(%0) ;"
+		"adcx %%rbx, %%r11 ;"
+		"movq %%r11, 56(%0) ;"
+		"mov     $0, %%ecx ;"
+		"cmovc %%edx, %%ecx ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8, 32(%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9",
+		  "%r10", "%r11");
+}
+
+static void red_eltfp25519_2w_bmi2(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movl    $38, %%edx ; "       /* 2*c = 38 = 2^256 */
+		"mulx 32(%1),  %%r8, %%r10 ;" /* c*C[4] */
+		"mulx 40(%1),  %%r9, %%r11 ;" /* c*C[5] */
+		"addq %%r10,  %%r9 ;"
+		"mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */
+		"adcq %%r11, %%r10 ;"
+		"mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */
+		"adcq %%rax, %%r11 ;"
+		/***************************************/
+		"adcq    $0, %%rcx ;"
+		"addq   (%1),  %%r8 ;"
+		"adcq  8(%1),  %%r9 ;"
+		"adcq 16(%1), %%r10 ;"
+		"adcq 24(%1), %%r11 ;"
+		"adcq     $0, %%rcx ;"
+		"imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */
+		"addq %%rcx,  %%r8 ;"
+		"adcq    $0,  %%r9 ;"
+		"movq  %%r9,  8(%0) ;"
+		"adcq    $0, %%r10 ;"
+		"movq %%r10, 16(%0) ;"
+		"adcq    $0, %%r11 ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $0, %%ecx ;"
+		"cmovc %%edx, %%ecx ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,   (%0) ;"
+
+		"mulx  96(%1),  %%r8, %%r10 ;" /* c*C[4] */
+		"mulx 104(%1),  %%r9, %%r11 ;" /* c*C[5] */
+		"addq %%r10,  %%r9 ;"
+		"mulx 112(%1), %%r10, %%rax ;" /* c*C[6] */
+		"adcq %%r11, %%r10 ;"
+		"mulx 120(%1), %%r11, %%rcx ;" /* c*C[7] */
+		"adcq %%rax, %%r11 ;"
+		/****************************************/
+		"adcq    $0, %%rcx ;"
+		"addq 64(%1),  %%r8 ;"
+		"adcq 72(%1),  %%r9 ;"
+		"adcq 80(%1), %%r10 ;"
+		"adcq 88(%1), %%r11 ;"
+		"adcq     $0, %%rcx ;"
+		"imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */
+		"addq %%rcx,  %%r8 ;"
+		"adcq    $0,  %%r9 ;"
+		"movq  %%r9, 40(%0) ;"
+		"adcq    $0, %%r10 ;"
+		"movq %%r10, 48(%0) ;"
+		"adcq    $0, %%r11 ;"
+		"movq %%r11, 56(%0) ;"
+		"mov     $0, %%ecx ;"
+		"cmovc %%edx, %%ecx ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8, 32(%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10",
+		  "%r11");
+}
+
+static void mul_256x256_integer_adx(u64 *const c, const u64 *const a,
+				    const u64 *const b)
+{
+	asm volatile(
+		"movq   (%1), %%rdx; "	/* A[0] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[0]*B[0] */
+		"xorl %%r10d, %%r10d ;"
+		"movq  %%r8,  (%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[0]*B[1] */
+		"adox  %%r9, %%r10 ;"
+		"movq %%r10, 8(%0) ;"
+		"mulx 16(%2), %%r15, %%r13; " /* A[0]*B[2] */
+		"adox %%r11, %%r15 ;"
+		"mulx 24(%2), %%r14, %%rdx; " /* A[0]*B[3] */
+		"adox %%r13, %%r14 ;"
+		"movq $0, %%rax ;"
+		/******************************************/
+		"adox %%rdx, %%rax ;"
+
+		"movq  8(%1), %%rdx; "	/* A[1] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[1]*B[0] */
+		"xorl %%r10d, %%r10d ;"
+		"adcx 8(%0),  %%r8 ;"
+		"movq  %%r8,  8(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[1]*B[1] */
+		"adox  %%r9, %%r10 ;"
+		"adcx %%r15, %%r10 ;"
+		"movq %%r10, 16(%0) ;"
+		"mulx 16(%2), %%r15, %%r13; " /* A[1]*B[2] */
+		"adox %%r11, %%r15 ;"
+		"adcx %%r14, %%r15 ;"
+		"movq $0, %%r8  ;"
+		"mulx 24(%2), %%r14, %%rdx; " /* A[1]*B[3] */
+		"adox %%r13, %%r14 ;"
+		"adcx %%rax, %%r14 ;"
+		"movq $0, %%rax ;"
+		/******************************************/
+		"adox %%rdx, %%rax ;"
+		"adcx  %%r8, %%rax ;"
+
+		"movq 16(%1), %%rdx; "	/* A[2] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[2]*B[0] */
+		"xorl %%r10d, %%r10d ;"
+		"adcx 16(%0), %%r8 ;"
+		"movq  %%r8, 16(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[2]*B[1] */
+		"adox  %%r9, %%r10 ;"
+		"adcx %%r15, %%r10 ;"
+		"movq %%r10, 24(%0) ;"
+		"mulx 16(%2), %%r15, %%r13; " /* A[2]*B[2] */
+		"adox %%r11, %%r15 ;"
+		"adcx %%r14, %%r15 ;"
+		"movq $0, %%r8  ;"
+		"mulx 24(%2), %%r14, %%rdx; " /* A[2]*B[3] */
+		"adox %%r13, %%r14 ;"
+		"adcx %%rax, %%r14 ;"
+		"movq $0, %%rax ;"
+		/******************************************/
+		"adox %%rdx, %%rax ;"
+		"adcx  %%r8, %%rax ;"
+
+		"movq 24(%1), %%rdx; "	/* A[3] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[3]*B[0] */
+		"xorl %%r10d, %%r10d ;"
+		"adcx 24(%0), %%r8 ;"
+		"movq  %%r8, 24(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[3]*B[1] */
+		"adox  %%r9, %%r10 ;"
+		"adcx %%r15, %%r10 ;"
+		"movq %%r10, 32(%0) ;"
+		"mulx 16(%2), %%r15, %%r13; " /* A[3]*B[2] */
+		"adox %%r11, %%r15 ;"
+		"adcx %%r14, %%r15 ;"
+		"movq %%r15, 40(%0) ;"
+		"movq $0, %%r8  ;"
+		"mulx 24(%2), %%r14, %%rdx; " /* A[3]*B[3] */
+		"adox %%r13, %%r14 ;"
+		"adcx %%rax, %%r14 ;"
+		"movq %%r14, 48(%0) ;"
+		"movq $0, %%rax ;"
+		/******************************************/
+		"adox %%rdx, %%rax ;"
+		"adcx  %%r8, %%rax ;"
+		"movq %%rax, 56(%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(b)
+		: "memory", "cc", "%rax", "%rdx", "%r8", "%r9", "%r10", "%r11",
+		  "%r13", "%r14", "%r15");
+}
+
+static void mul_256x256_integer_bmi2(u64 *const c, const u64 *const a,
+				     const u64 *const b)
+{
+	asm volatile(
+		"movq   (%1), %%rdx; "	/* A[0] */
+		"mulx   (%2),  %%r8, %%r15; " /* A[0]*B[0] */
+		"movq %%r8,  (%0) ;"
+		"mulx  8(%2), %%r10, %%rax; " /* A[0]*B[1] */
+		"addq %%r10, %%r15 ;"
+		"mulx 16(%2),  %%r8, %%rbx; " /* A[0]*B[2] */
+		"adcq  %%r8, %%rax ;"
+		"mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */
+		"adcq %%r10, %%rbx ;"
+		/******************************************/
+		"adcq    $0, %%rcx ;"
+
+		"movq  8(%1), %%rdx; "	/* A[1] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[1]*B[0] */
+		"addq %%r15,  %%r8 ;"
+		"movq %%r8, 8(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[1]*B[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[1]*B[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%r15 ;"
+
+		"addq  %%r9, %%rax ;"
+		"adcq %%r11, %%rbx ;"
+		"adcq %%r13, %%rcx ;"
+		"adcq    $0, %%r15 ;"
+
+		"movq 16(%1), %%rdx; "	/* A[2] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[2]*B[0] */
+		"addq %%rax,  %%r8 ;"
+		"movq %%r8, 16(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[2]*B[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[2]*B[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%rax ;"
+
+		"addq  %%r9, %%rbx ;"
+		"adcq %%r11, %%rcx ;"
+		"adcq %%r13, %%r15 ;"
+		"adcq    $0, %%rax ;"
+
+		"movq 24(%1), %%rdx; "	/* A[3] */
+		"mulx   (%2),  %%r8,  %%r9; " /* A[3]*B[0] */
+		"addq %%rbx,  %%r8 ;"
+		"movq %%r8, 24(%0) ;"
+		"mulx  8(%2), %%r10, %%r11; " /* A[3]*B[1] */
+		"adcq %%r10,  %%r9 ;"
+		"mulx 16(%2),  %%r8, %%r13; " /* A[3]*B[2] */
+		"adcq  %%r8, %%r11 ;"
+		"mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */
+		"adcq %%r10, %%r13 ;"
+		/******************************************/
+		"adcq    $0, %%rbx ;"
+
+		"addq  %%r9, %%rcx ;"
+		"movq %%rcx, 32(%0) ;"
+		"adcq %%r11, %%r15 ;"
+		"movq %%r15, 40(%0) ;"
+		"adcq %%r13, %%rax ;"
+		"movq %%rax, 48(%0) ;"
+		"adcq    $0, %%rbx ;"
+		"movq %%rbx, 56(%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(b)
+		: "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9",
+		  "%r10", "%r11", "%r13", "%r15");
+}
+
+static void sqr_256x256_integer_adx(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movq   (%1), %%rdx        ;" /* A[0]      */
+		"mulx  8(%1),  %%r8, %%r14 ;" /* A[1]*A[0] */
+		"xorl %%r15d, %%r15d;"
+		"mulx 16(%1),  %%r9, %%r10 ;" /* A[2]*A[0] */
+		"adcx %%r14,  %%r9 ;"
+		"mulx 24(%1), %%rax, %%rcx ;" /* A[3]*A[0] */
+		"adcx %%rax, %%r10 ;"
+		"movq 24(%1), %%rdx        ;" /* A[3]      */
+		"mulx  8(%1), %%r11, %%rbx ;" /* A[1]*A[3] */
+		"adcx %%rcx, %%r11 ;"
+		"mulx 16(%1), %%rax, %%r13 ;" /* A[2]*A[3] */
+		"adcx %%rax, %%rbx ;"
+		"movq  8(%1), %%rdx        ;" /* A[1]      */
+		"adcx %%r15, %%r13 ;"
+		"mulx 16(%1), %%rax, %%rcx ;" /* A[2]*A[1] */
+		"movq    $0, %%r14 ;"
+		/******************************************/
+		"adcx %%r15, %%r14 ;"
+
+		"xorl %%r15d, %%r15d;"
+		"adox %%rax, %%r10 ;"
+		"adcx  %%r8,  %%r8 ;"
+		"adox %%rcx, %%r11 ;"
+		"adcx  %%r9,  %%r9 ;"
+		"adox %%r15, %%rbx ;"
+		"adcx %%r10, %%r10 ;"
+		"adox %%r15, %%r13 ;"
+		"adcx %%r11, %%r11 ;"
+		"adox %%r15, %%r14 ;"
+		"adcx %%rbx, %%rbx ;"
+		"adcx %%r13, %%r13 ;"
+		"adcx %%r14, %%r14 ;"
+
+		"movq   (%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */
+		/*******************/
+		"movq %%rax,  0(%0) ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,  8(%0) ;"
+		"movq  8(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */
+		"adcq %%rax,  %%r9 ;"
+		"movq  %%r9, 16(%0) ;"
+		"adcq %%rcx, %%r10 ;"
+		"movq %%r10, 24(%0) ;"
+		"movq 16(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */
+		"adcq %%rax, %%r11 ;"
+		"movq %%r11, 32(%0) ;"
+		"adcq %%rcx, %%rbx ;"
+		"movq %%rbx, 40(%0) ;"
+		"movq 24(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */
+		"adcq %%rax, %%r13 ;"
+		"movq %%r13, 48(%0) ;"
+		"adcq %%rcx, %%r14 ;"
+		"movq %%r14, 56(%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9",
+		  "%r10", "%r11", "%r13", "%r14", "%r15");
+}
+
+static void sqr_256x256_integer_bmi2(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movq  8(%1), %%rdx        ;" /* A[1]      */
+		"mulx   (%1),  %%r8,  %%r9 ;" /* A[0]*A[1] */
+		"mulx 16(%1), %%r10, %%r11 ;" /* A[2]*A[1] */
+		"mulx 24(%1), %%rcx, %%r14 ;" /* A[3]*A[1] */
+
+		"movq 16(%1), %%rdx        ;" /* A[2]      */
+		"mulx 24(%1), %%r15, %%r13 ;" /* A[3]*A[2] */
+		"mulx   (%1), %%rax, %%rdx ;" /* A[0]*A[2] */
+
+		"addq %%rax,  %%r9 ;"
+		"adcq %%rdx, %%r10 ;"
+		"adcq %%rcx, %%r11 ;"
+		"adcq %%r14, %%r15 ;"
+		"adcq    $0, %%r13 ;"
+		"movq    $0, %%r14 ;"
+		"adcq    $0, %%r14 ;"
+
+		"movq   (%1), %%rdx        ;" /* A[0]      */
+		"mulx 24(%1), %%rax, %%rcx ;" /* A[0]*A[3] */
+
+		"addq %%rax, %%r10 ;"
+		"adcq %%rcx, %%r11 ;"
+		"adcq    $0, %%r15 ;"
+		"adcq    $0, %%r13 ;"
+		"adcq    $0, %%r14 ;"
+
+		"shldq $1, %%r13, %%r14 ;"
+		"shldq $1, %%r15, %%r13 ;"
+		"shldq $1, %%r11, %%r15 ;"
+		"shldq $1, %%r10, %%r11 ;"
+		"shldq $1,  %%r9, %%r10 ;"
+		"shldq $1,  %%r8,  %%r9 ;"
+		"shlq  $1,  %%r8        ;"
+
+		/*******************/
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */
+		/*******************/
+		"movq %%rax,  0(%0) ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,  8(%0) ;"
+		"movq  8(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */
+		"adcq %%rax,  %%r9 ;"
+		"movq  %%r9, 16(%0) ;"
+		"adcq %%rcx, %%r10 ;"
+		"movq %%r10, 24(%0) ;"
+		"movq 16(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */
+		"adcq %%rax, %%r11 ;"
+		"movq %%r11, 32(%0) ;"
+		"adcq %%rcx, %%r15 ;"
+		"movq %%r15, 40(%0) ;"
+		"movq 24(%1), %%rdx ;"
+		"mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */
+		"adcq %%rax, %%r13 ;"
+		"movq %%r13, 48(%0) ;"
+		"adcq %%rcx, %%r14 ;"
+		"movq %%r14, 56(%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10",
+		  "%r11", "%r13", "%r14", "%r15");
+}
+
+static void red_eltfp25519_1w_adx(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movl    $38, %%edx ;"	/* 2*c = 38 = 2^256 */
+		"mulx 32(%1),  %%r8, %%r10 ;" /* c*C[4] */
+		"xorl %%ebx, %%ebx ;"
+		"adox   (%1),  %%r8 ;"
+		"mulx 40(%1),  %%r9, %%r11 ;" /* c*C[5] */
+		"adcx %%r10,  %%r9 ;"
+		"adox  8(%1),  %%r9 ;"
+		"mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */
+		"adcx %%r11, %%r10 ;"
+		"adox 16(%1), %%r10 ;"
+		"mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */
+		"adcx %%rax, %%r11 ;"
+		"adox 24(%1), %%r11 ;"
+		/***************************************/
+		"adcx %%rbx, %%rcx ;"
+		"adox  %%rbx, %%rcx ;"
+		"imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */
+		"adcx %%rcx,  %%r8 ;"
+		"adcx %%rbx,  %%r9 ;"
+		"movq  %%r9,  8(%0) ;"
+		"adcx %%rbx, %%r10 ;"
+		"movq %%r10, 16(%0) ;"
+		"adcx %%rbx, %%r11 ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $0, %%ecx ;"
+		"cmovc %%edx, %%ecx ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,   (%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9",
+		  "%r10", "%r11");
+}
+
+static void red_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a)
+{
+	asm volatile(
+		"movl    $38, %%edx ;"	/* 2*c = 38 = 2^256 */
+		"mulx 32(%1),  %%r8, %%r10 ;" /* c*C[4] */
+		"mulx 40(%1),  %%r9, %%r11 ;" /* c*C[5] */
+		"addq %%r10,  %%r9 ;"
+		"mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */
+		"adcq %%r11, %%r10 ;"
+		"mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */
+		"adcq %%rax, %%r11 ;"
+		/***************************************/
+		"adcq    $0, %%rcx ;"
+		"addq   (%1),  %%r8 ;"
+		"adcq  8(%1),  %%r9 ;"
+		"adcq 16(%1), %%r10 ;"
+		"adcq 24(%1), %%r11 ;"
+		"adcq     $0, %%rcx ;"
+		"imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */
+		"addq %%rcx,  %%r8 ;"
+		"adcq    $0,  %%r9 ;"
+		"movq  %%r9,  8(%0) ;"
+		"adcq    $0, %%r10 ;"
+		"movq %%r10, 16(%0) ;"
+		"adcq    $0, %%r11 ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $0, %%ecx ;"
+		"cmovc %%edx, %%ecx ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,   (%0) ;"
+		:
+		: "r"(c), "r"(a)
+		: "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10",
+		  "%r11");
+}
+
+static __always_inline void
+add_eltfp25519_1w_adx(u64 *const c, const u64 *const a, const u64 *const b)
+{
+	asm volatile(
+		"mov     $38, %%eax ;"
+		"xorl  %%ecx, %%ecx ;"
+		"movq   (%2),  %%r8 ;"
+		"adcx   (%1),  %%r8 ;"
+		"movq  8(%2),  %%r9 ;"
+		"adcx  8(%1),  %%r9 ;"
+		"movq 16(%2), %%r10 ;"
+		"adcx 16(%1), %%r10 ;"
+		"movq 24(%2), %%r11 ;"
+		"adcx 24(%1), %%r11 ;"
+		"cmovc %%eax, %%ecx ;"
+		"xorl %%eax, %%eax  ;"
+		"adcx %%rcx,  %%r8  ;"
+		"adcx %%rax,  %%r9  ;"
+		"movq  %%r9,  8(%0) ;"
+		"adcx %%rax, %%r10  ;"
+		"movq %%r10, 16(%0) ;"
+		"adcx %%rax, %%r11  ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $38, %%ecx ;"
+		"cmovc %%ecx, %%eax ;"
+		"addq %%rax,  %%r8  ;"
+		"movq  %%r8,   (%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(b)
+		: "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11");
+}
+
+static __always_inline void
+add_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a, const u64 *const b)
+{
+	asm volatile(
+		"mov     $38, %%eax ;"
+		"movq   (%2),  %%r8 ;"
+		"addq   (%1),  %%r8 ;"
+		"movq  8(%2),  %%r9 ;"
+		"adcq  8(%1),  %%r9 ;"
+		"movq 16(%2), %%r10 ;"
+		"adcq 16(%1), %%r10 ;"
+		"movq 24(%2), %%r11 ;"
+		"adcq 24(%1), %%r11 ;"
+		"mov      $0, %%ecx ;"
+		"cmovc %%eax, %%ecx ;"
+		"addq %%rcx,  %%r8  ;"
+		"adcq    $0,  %%r9  ;"
+		"movq  %%r9,  8(%0) ;"
+		"adcq    $0, %%r10  ;"
+		"movq %%r10, 16(%0) ;"
+		"adcq    $0, %%r11  ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $0, %%ecx  ;"
+		"cmovc %%eax, %%ecx ;"
+		"addq %%rcx,  %%r8  ;"
+		"movq  %%r8,   (%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(b)
+		: "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11");
+}
+
+static __always_inline void
+sub_eltfp25519_1w(u64 *const c, const u64 *const a, const u64 *const b)
+{
+	asm volatile(
+		"mov     $38, %%eax ;"
+		"movq   (%1),  %%r8 ;"
+		"subq   (%2),  %%r8 ;"
+		"movq  8(%1),  %%r9 ;"
+		"sbbq  8(%2),  %%r9 ;"
+		"movq 16(%1), %%r10 ;"
+		"sbbq 16(%2), %%r10 ;"
+		"movq 24(%1), %%r11 ;"
+		"sbbq 24(%2), %%r11 ;"
+		"mov      $0, %%ecx ;"
+		"cmovc %%eax, %%ecx ;"
+		"subq %%rcx,  %%r8  ;"
+		"sbbq    $0,  %%r9  ;"
+		"movq  %%r9,  8(%0) ;"
+		"sbbq    $0, %%r10  ;"
+		"movq %%r10, 16(%0) ;"
+		"sbbq    $0, %%r11  ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $0, %%ecx  ;"
+		"cmovc %%eax, %%ecx ;"
+		"subq %%rcx,  %%r8  ;"
+		"movq  %%r8,   (%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(b)
+		: "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11");
+}
+
+/* Multiplication by a24 = (A+2)/4 = (486662+2)/4 = 121666 */
+static __always_inline void
+mul_a24_eltfp25519_1w(u64 *const c, const u64 *const a)
+{
+	const u64 a24 = 121666;
+	asm volatile(
+		"movq     %2, %%rdx ;"
+		"mulx   (%1),  %%r8, %%r10 ;"
+		"mulx  8(%1),  %%r9, %%r11 ;"
+		"addq %%r10,  %%r9 ;"
+		"mulx 16(%1), %%r10, %%rax ;"
+		"adcq %%r11, %%r10 ;"
+		"mulx 24(%1), %%r11, %%rcx ;"
+		"adcq %%rax, %%r11 ;"
+		/**************************/
+		"adcq    $0, %%rcx ;"
+		"movl   $38, %%edx ;" /* 2*c = 38 = 2^256 mod 2^255-19*/
+		"imul %%rdx, %%rcx ;"
+		"addq %%rcx,  %%r8 ;"
+		"adcq    $0,  %%r9 ;"
+		"movq  %%r9,  8(%0) ;"
+		"adcq    $0, %%r10 ;"
+		"movq %%r10, 16(%0) ;"
+		"adcq    $0, %%r11 ;"
+		"movq %%r11, 24(%0) ;"
+		"mov     $0, %%ecx ;"
+		"cmovc %%edx, %%ecx ;"
+		"addq %%rcx,  %%r8 ;"
+		"movq  %%r8,   (%0) ;"
+		:
+		: "r"(c), "r"(a), "r"(a24)
+		: "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10",
+		  "%r11");
+}
+
+static void inv_eltfp25519_1w_adx(u64 *const c, const u64 *const a)
+{
+	struct {
+		eltfp25519_1w_buffer buffer;
+		eltfp25519_1w x0, x1, x2;
+	} __aligned(32) m;
+	u64 *T[4];
+
+	T[0] = m.x0;
+	T[1] = c; /* x^(-1) */
+	T[2] = m.x1;
+	T[3] = m.x2;
+
+	copy_eltfp25519_1w(T[1], a);
+	sqrn_eltfp25519_1w_adx(T[1], 1);
+	copy_eltfp25519_1w(T[2], T[1]);
+	sqrn_eltfp25519_1w_adx(T[2], 2);
+	mul_eltfp25519_1w_adx(T[0], a, T[2]);
+	mul_eltfp25519_1w_adx(T[1], T[1], T[0]);
+	copy_eltfp25519_1w(T[2], T[1]);
+	sqrn_eltfp25519_1w_adx(T[2], 1);
+	mul_eltfp25519_1w_adx(T[0], T[0], T[2]);
+	copy_eltfp25519_1w(T[2], T[0]);
+	sqrn_eltfp25519_1w_adx(T[2], 5);
+	mul_eltfp25519_1w_adx(T[0], T[0], T[2]);
+	copy_eltfp25519_1w(T[2], T[0]);
+	sqrn_eltfp25519_1w_adx(T[2], 10);
+	mul_eltfp25519_1w_adx(T[2], T[2], T[0]);
+	copy_eltfp25519_1w(T[3], T[2]);
+	sqrn_eltfp25519_1w_adx(T[3], 20);
+	mul_eltfp25519_1w_adx(T[3], T[3], T[2]);
+	sqrn_eltfp25519_1w_adx(T[3], 10);
+	mul_eltfp25519_1w_adx(T[3], T[3], T[0]);
+	copy_eltfp25519_1w(T[0], T[3]);
+	sqrn_eltfp25519_1w_adx(T[0], 50);
+	mul_eltfp25519_1w_adx(T[0], T[0], T[3]);
+	copy_eltfp25519_1w(T[2], T[0]);
+	sqrn_eltfp25519_1w_adx(T[2], 100);
+	mul_eltfp25519_1w_adx(T[2], T[2], T[0]);
+	sqrn_eltfp25519_1w_adx(T[2], 50);
+	mul_eltfp25519_1w_adx(T[2], T[2], T[3]);
+	sqrn_eltfp25519_1w_adx(T[2], 5);
+	mul_eltfp25519_1w_adx(T[1], T[1], T[2]);
+
+	memzero_explicit(&m, sizeof(m));
+}
+
+static void inv_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a)
+{
+	struct {
+		eltfp25519_1w_buffer buffer;
+		eltfp25519_1w x0, x1, x2;
+	} __aligned(32) m;
+	u64 *T[5];
+
+	T[0] = m.x0;
+	T[1] = c; /* x^(-1) */
+	T[2] = m.x1;
+	T[3] = m.x2;
+
+	copy_eltfp25519_1w(T[1], a);
+	sqrn_eltfp25519_1w_bmi2(T[1], 1);
+	copy_eltfp25519_1w(T[2], T[1]);
+	sqrn_eltfp25519_1w_bmi2(T[2], 2);
+	mul_eltfp25519_1w_bmi2(T[0], a, T[2]);
+	mul_eltfp25519_1w_bmi2(T[1], T[1], T[0]);
+	copy_eltfp25519_1w(T[2], T[1]);
+	sqrn_eltfp25519_1w_bmi2(T[2], 1);
+	mul_eltfp25519_1w_bmi2(T[0], T[0], T[2]);
+	copy_eltfp25519_1w(T[2], T[0]);
+	sqrn_eltfp25519_1w_bmi2(T[2], 5);
+	mul_eltfp25519_1w_bmi2(T[0], T[0], T[2]);
+	copy_eltfp25519_1w(T[2], T[0]);
+	sqrn_eltfp25519_1w_bmi2(T[2], 10);
+	mul_eltfp25519_1w_bmi2(T[2], T[2], T[0]);
+	copy_eltfp25519_1w(T[3], T[2]);
+	sqrn_eltfp25519_1w_bmi2(T[3], 20);
+	mul_eltfp25519_1w_bmi2(T[3], T[3], T[2]);
+	sqrn_eltfp25519_1w_bmi2(T[3], 10);
+	mul_eltfp25519_1w_bmi2(T[3], T[3], T[0]);
+	copy_eltfp25519_1w(T[0], T[3]);
+	sqrn_eltfp25519_1w_bmi2(T[0], 50);
+	mul_eltfp25519_1w_bmi2(T[0], T[0], T[3]);
+	copy_eltfp25519_1w(T[2], T[0]);
+	sqrn_eltfp25519_1w_bmi2(T[2], 100);
+	mul_eltfp25519_1w_bmi2(T[2], T[2], T[0]);
+	sqrn_eltfp25519_1w_bmi2(T[2], 50);
+	mul_eltfp25519_1w_bmi2(T[2], T[2], T[3]);
+	sqrn_eltfp25519_1w_bmi2(T[2], 5);
+	mul_eltfp25519_1w_bmi2(T[1], T[1], T[2]);
+
+	memzero_explicit(&m, sizeof(m));
+}
+
+/* Given c, a 256-bit number, fred_eltfp25519_1w updates c
+ * with a number such that 0 <= C < 2**255-19.
+ */
+static __always_inline void fred_eltfp25519_1w(u64 *const c)
+{
+	u64 tmp0 = 38, tmp1 = 19;
+	asm volatile(
+		"btrq   $63,    %3 ;" /* Put bit 255 in carry flag and clear */
+		"cmovncl %k5,   %k4 ;" /* c[255] ? 38 : 19 */
+
+		/* Add either 19 or 38 to c */
+		"addq    %4,   %0 ;"
+		"adcq    $0,   %1 ;"
+		"adcq    $0,   %2 ;"
+		"adcq    $0,   %3 ;"
+
+		/* Test for bit 255 again; only triggered on overflow modulo 2^255-19 */
+		"movl    $0,  %k4 ;"
+		"cmovnsl %k5,  %k4 ;" /* c[255] ? 0 : 19 */
+		"btrq   $63,   %3 ;" /* Clear bit 255 */
+
+		/* Subtract 19 if necessary */
+		"subq    %4,   %0 ;"
+		"sbbq    $0,   %1 ;"
+		"sbbq    $0,   %2 ;"
+		"sbbq    $0,   %3 ;"
+
+		: "+r"(c[0]), "+r"(c[1]), "+r"(c[2]), "+r"(c[3]), "+r"(tmp0),
+		  "+r"(tmp1)
+		:
+		: "memory", "cc");
+}
+
+static __always_inline void cswap(u8 bit, u64 *const px, u64 *const py)
+{
+	u64 temp;
+	asm volatile(
+		"test %9, %9 ;"
+		"movq %0, %8 ;"
+		"cmovnzq %4, %0 ;"
+		"cmovnzq %8, %4 ;"
+		"movq %1, %8 ;"
+		"cmovnzq %5, %1 ;"
+		"cmovnzq %8, %5 ;"
+		"movq %2, %8 ;"
+		"cmovnzq %6, %2 ;"
+		"cmovnzq %8, %6 ;"
+		"movq %3, %8 ;"
+		"cmovnzq %7, %3 ;"
+		"cmovnzq %8, %7 ;"
+		: "+r"(px[0]), "+r"(px[1]), "+r"(px[2]), "+r"(px[3]),
+		  "+r"(py[0]), "+r"(py[1]), "+r"(py[2]), "+r"(py[3]),
+		  "=r"(temp)
+		: "r"(bit)
+		: "cc"
+	);
+}
+
+static __always_inline void cselect(u8 bit, u64 *const px, const u64 *const py)
+{
+	asm volatile(
+		"test %4, %4 ;"
+		"cmovnzq %5, %0 ;"
+		"cmovnzq %6, %1 ;"
+		"cmovnzq %7, %2 ;"
+		"cmovnzq %8, %3 ;"
+		: "+r"(px[0]), "+r"(px[1]), "+r"(px[2]), "+r"(px[3])
+		: "r"(bit), "rm"(py[0]), "rm"(py[1]), "rm"(py[2]), "rm"(py[3])
+		: "cc"
+	);
+}
+
+static void curve25519_adx(u8 shared[CURVE25519_KEY_SIZE],
+			   const u8 private_key[CURVE25519_KEY_SIZE],
+			   const u8 session_key[CURVE25519_KEY_SIZE])
+{
+	struct {
+		u64 buffer[4 * NUM_WORDS_ELTFP25519];
+		u64 coordinates[4 * NUM_WORDS_ELTFP25519];
+		u64 workspace[6 * NUM_WORDS_ELTFP25519];
+		u8 session[CURVE25519_KEY_SIZE];
+		u8 private[CURVE25519_KEY_SIZE];
+	} __aligned(32) m;
+
+	int i = 0, j = 0;
+	u64 prev = 0;
+	u64 *const X1 = (u64 *)m.session;
+	u64 *const key = (u64 *)m.private;
+	u64 *const Px = m.coordinates + 0;
+	u64 *const Pz = m.coordinates + 4;
+	u64 *const Qx = m.coordinates + 8;
+	u64 *const Qz = m.coordinates + 12;
+	u64 *const X2 = Qx;
+	u64 *const Z2 = Qz;
+	u64 *const X3 = Px;
+	u64 *const Z3 = Pz;
+	u64 *const X2Z2 = Qx;
+	u64 *const X3Z3 = Px;
+
+	u64 *const A = m.workspace + 0;
+	u64 *const B = m.workspace + 4;
+	u64 *const D = m.workspace + 8;
+	u64 *const C = m.workspace + 12;
+	u64 *const DA = m.workspace + 16;
+	u64 *const CB = m.workspace + 20;
+	u64 *const AB = A;
+	u64 *const DC = D;
+	u64 *const DACB = DA;
+
+	memcpy(m.private, private_key, sizeof(m.private));
+	memcpy(m.session, session_key, sizeof(m.session));
+
+	curve25519_clamp_secret(m.private);
+
+	/* As in the draft:
+	 * When receiving such an array, implementations of curve25519
+	 * MUST mask the most-significant bit in the final byte. This
+	 * is done to preserve compatibility with point formats which
+	 * reserve the sign bit for use in other protocols and to
+	 * increase resistance to implementation fingerprinting
+	 */
+	m.session[CURVE25519_KEY_SIZE - 1] &= (1 << (255 % 8)) - 1;
+
+	copy_eltfp25519_1w(Px, X1);
+	setzero_eltfp25519_1w(Pz);
+	setzero_eltfp25519_1w(Qx);
+	setzero_eltfp25519_1w(Qz);
+
+	Pz[0] = 1;
+	Qx[0] = 1;
+
+	/* main-loop */
+	prev = 0;
+	j = 62;
+	for (i = 3; i >= 0; --i) {
+		while (j >= 0) {
+			u64 bit = (key[i] >> j) & 0x1;
+			u64 swap = bit ^ prev;
+			prev = bit;
+
+			add_eltfp25519_1w_adx(A, X2, Z2);	/* A = (X2+Z2) */
+			sub_eltfp25519_1w(B, X2, Z2);		/* B = (X2-Z2) */
+			add_eltfp25519_1w_adx(C, X3, Z3);	/* C = (X3+Z3) */
+			sub_eltfp25519_1w(D, X3, Z3);		/* D = (X3-Z3) */
+			mul_eltfp25519_2w_adx(DACB, AB, DC);	/* [DA|CB] = [A|B]*[D|C] */
+
+			cselect(swap, A, C);
+			cselect(swap, B, D);
+
+			sqr_eltfp25519_2w_adx(AB);		/* [AA|BB] = [A^2|B^2] */
+			add_eltfp25519_1w_adx(X3, DA, CB);	/* X3 = (DA+CB) */
+			sub_eltfp25519_1w(Z3, DA, CB);		/* Z3 = (DA-CB) */
+			sqr_eltfp25519_2w_adx(X3Z3);		/* [X3|Z3] = [(DA+CB)|(DA+CB)]^2 */
+
+			copy_eltfp25519_1w(X2, B);		/* X2 = B^2 */
+			sub_eltfp25519_1w(Z2, A, B);		/* Z2 = E = AA-BB */
+
+			mul_a24_eltfp25519_1w(B, Z2);		/* B = a24*E */
+			add_eltfp25519_1w_adx(B, B, X2);	/* B = a24*E+B */
+			mul_eltfp25519_2w_adx(X2Z2, X2Z2, AB);	/* [X2|Z2] = [B|E]*[A|a24*E+B] */
+			mul_eltfp25519_1w_adx(Z3, Z3, X1);	/* Z3 = Z3*X1 */
+			--j;
+		}
+		j = 63;
+	}
+
+	inv_eltfp25519_1w_adx(A, Qz);
+	mul_eltfp25519_1w_adx((u64 *)shared, Qx, A);
+	fred_eltfp25519_1w((u64 *)shared);
+
+	memzero_explicit(&m, sizeof(m));
+}
+
+static void curve25519_adx_base(u8 session_key[CURVE25519_KEY_SIZE],
+				const u8 private_key[CURVE25519_KEY_SIZE])
+{
+	struct {
+		u64 buffer[4 * NUM_WORDS_ELTFP25519];
+		u64 coordinates[4 * NUM_WORDS_ELTFP25519];
+		u64 workspace[4 * NUM_WORDS_ELTFP25519];
+		u8 private[CURVE25519_KEY_SIZE];
+	} __aligned(32) m;
+
+	const int ite[4] = { 64, 64, 64, 63 };
+	const int q = 3;
+	u64 swap = 1;
+
+	int i = 0, j = 0, k = 0;
+	u64 *const key = (u64 *)m.private;
+	u64 *const Ur1 = m.coordinates + 0;
+	u64 *const Zr1 = m.coordinates + 4;
+	u64 *const Ur2 = m.coordinates + 8;
+	u64 *const Zr2 = m.coordinates + 12;
+
+	u64 *const UZr1 = m.coordinates + 0;
+	u64 *const ZUr2 = m.coordinates + 8;
+
+	u64 *const A = m.workspace + 0;
+	u64 *const B = m.workspace + 4;
+	u64 *const C = m.workspace + 8;
+	u64 *const D = m.workspace + 12;
+
+	u64 *const AB = m.workspace + 0;
+	u64 *const CD = m.workspace + 8;
+
+	const u64 *const P = table_ladder_8k;
+
+	memcpy(m.private, private_key, sizeof(m.private));
+
+	curve25519_clamp_secret(m.private);
+
+	setzero_eltfp25519_1w(Ur1);
+	setzero_eltfp25519_1w(Zr1);
+	setzero_eltfp25519_1w(Zr2);
+	Ur1[0] = 1;
+	Zr1[0] = 1;
+	Zr2[0] = 1;
+
+	/* G-S */
+	Ur2[3] = 0x1eaecdeee27cab34UL;
+	Ur2[2] = 0xadc7a0b9235d48e2UL;
+	Ur2[1] = 0xbbf095ae14b2edf8UL;
+	Ur2[0] = 0x7e94e1fec82faabdUL;
+
+	/* main-loop */
+	j = q;
+	for (i = 0; i < NUM_WORDS_ELTFP25519; ++i) {
+		while (j < ite[i]) {
+			u64 bit = (key[i] >> j) & 0x1;
+			k = (64 * i + j - q);
+			swap = swap ^ bit;
+			cswap(swap, Ur1, Ur2);
+			cswap(swap, Zr1, Zr2);
+			swap = bit;
+			/* Addition */
+			sub_eltfp25519_1w(B, Ur1, Zr1);		/* B = Ur1-Zr1 */
+			add_eltfp25519_1w_adx(A, Ur1, Zr1);	/* A = Ur1+Zr1 */
+			mul_eltfp25519_1w_adx(C, &P[4 * k], B);	/* C = M0-B */
+			sub_eltfp25519_1w(B, A, C);		/* B = (Ur1+Zr1) - M*(Ur1-Zr1) */
+			add_eltfp25519_1w_adx(A, A, C);		/* A = (Ur1+Zr1) + M*(Ur1-Zr1) */
+			sqr_eltfp25519_2w_adx(AB);		/* A = A^2      |  B = B^2 */
+			mul_eltfp25519_2w_adx(UZr1, ZUr2, AB);	/* Ur1 = Zr2*A  |  Zr1 = Ur2*B */
+			++j;
+		}
+		j = 0;
+	}
+
+	/* Doubling */
+	for (i = 0; i < q; ++i) {
+		add_eltfp25519_1w_adx(A, Ur1, Zr1);	/*  A = Ur1+Zr1 */
+		sub_eltfp25519_1w(B, Ur1, Zr1);		/*  B = Ur1-Zr1 */
+		sqr_eltfp25519_2w_adx(AB);		/*  A = A**2     B = B**2 */
+		copy_eltfp25519_1w(C, B);		/*  C = B */
+		sub_eltfp25519_1w(B, A, B);		/*  B = A-B */
+		mul_a24_eltfp25519_1w(D, B);		/*  D = my_a24*B */
+		add_eltfp25519_1w_adx(D, D, C);		/*  D = D+C */
+		mul_eltfp25519_2w_adx(UZr1, AB, CD);	/*  Ur1 = A*B   Zr1 = Zr1*A */
+	}
+
+	/* Convert to affine coordinates */
+	inv_eltfp25519_1w_adx(A, Zr1);
+	mul_eltfp25519_1w_adx((u64 *)session_key, Ur1, A);
+	fred_eltfp25519_1w((u64 *)session_key);
+
+	memzero_explicit(&m, sizeof(m));
+}
+
+static void curve25519_bmi2(u8 shared[CURVE25519_KEY_SIZE],
+			    const u8 private_key[CURVE25519_KEY_SIZE],
+			    const u8 session_key[CURVE25519_KEY_SIZE])
+{
+	struct {
+		u64 buffer[4 * NUM_WORDS_ELTFP25519];
+		u64 coordinates[4 * NUM_WORDS_ELTFP25519];
+		u64 workspace[6 * NUM_WORDS_ELTFP25519];
+		u8 session[CURVE25519_KEY_SIZE];
+		u8 private[CURVE25519_KEY_SIZE];
+	} __aligned(32) m;
+
+	int i = 0, j = 0;
+	u64 prev = 0;
+	u64 *const X1 = (u64 *)m.session;
+	u64 *const key = (u64 *)m.private;
+	u64 *const Px = m.coordinates + 0;
+	u64 *const Pz = m.coordinates + 4;
+	u64 *const Qx = m.coordinates + 8;
+	u64 *const Qz = m.coordinates + 12;
+	u64 *const X2 = Qx;
+	u64 *const Z2 = Qz;
+	u64 *const X3 = Px;
+	u64 *const Z3 = Pz;
+	u64 *const X2Z2 = Qx;
+	u64 *const X3Z3 = Px;
+
+	u64 *const A = m.workspace + 0;
+	u64 *const B = m.workspace + 4;
+	u64 *const D = m.workspace + 8;
+	u64 *const C = m.workspace + 12;
+	u64 *const DA = m.workspace + 16;
+	u64 *const CB = m.workspace + 20;
+	u64 *const AB = A;
+	u64 *const DC = D;
+	u64 *const DACB = DA;
+
+	memcpy(m.private, private_key, sizeof(m.private));
+	memcpy(m.session, session_key, sizeof(m.session));
+
+	curve25519_clamp_secret(m.private);
+
+	/* As in the draft:
+	 * When receiving such an array, implementations of curve25519
+	 * MUST mask the most-significant bit in the final byte. This
+	 * is done to preserve compatibility with point formats which
+	 * reserve the sign bit for use in other protocols and to
+	 * increase resistance to implementation fingerprinting
+	 */
+	m.session[CURVE25519_KEY_SIZE - 1] &= (1 << (255 % 8)) - 1;
+
+	copy_eltfp25519_1w(Px, X1);
+	setzero_eltfp25519_1w(Pz);
+	setzero_eltfp25519_1w(Qx);
+	setzero_eltfp25519_1w(Qz);
+
+	Pz[0] = 1;
+	Qx[0] = 1;
+
+	/* main-loop */
+	prev = 0;
+	j = 62;
+	for (i = 3; i >= 0; --i) {
+		while (j >= 0) {
+			u64 bit = (key[i] >> j) & 0x1;
+			u64 swap = bit ^ prev;
+			prev = bit;
+
+			add_eltfp25519_1w_bmi2(A, X2, Z2);	/* A = (X2+Z2) */
+			sub_eltfp25519_1w(B, X2, Z2);		/* B = (X2-Z2) */
+			add_eltfp25519_1w_bmi2(C, X3, Z3);	/* C = (X3+Z3) */
+			sub_eltfp25519_1w(D, X3, Z3);		/* D = (X3-Z3) */
+			mul_eltfp25519_2w_bmi2(DACB, AB, DC);	/* [DA|CB] = [A|B]*[D|C] */
+
+			cselect(swap, A, C);
+			cselect(swap, B, D);
+
+			sqr_eltfp25519_2w_bmi2(AB);		/* [AA|BB] = [A^2|B^2] */
+			add_eltfp25519_1w_bmi2(X3, DA, CB);	/* X3 = (DA+CB) */
+			sub_eltfp25519_1w(Z3, DA, CB);		/* Z3 = (DA-CB) */
+			sqr_eltfp25519_2w_bmi2(X3Z3);		/* [X3|Z3] = [(DA+CB)|(DA+CB)]^2 */
+
+			copy_eltfp25519_1w(X2, B);		/* X2 = B^2 */
+			sub_eltfp25519_1w(Z2, A, B);		/* Z2 = E = AA-BB */
+
+			mul_a24_eltfp25519_1w(B, Z2);		/* B = a24*E */
+			add_eltfp25519_1w_bmi2(B, B, X2);	/* B = a24*E+B */
+			mul_eltfp25519_2w_bmi2(X2Z2, X2Z2, AB);	/* [X2|Z2] = [B|E]*[A|a24*E+B] */
+			mul_eltfp25519_1w_bmi2(Z3, Z3, X1);	/* Z3 = Z3*X1 */
+			--j;
+		}
+		j = 63;
+	}
+
+	inv_eltfp25519_1w_bmi2(A, Qz);
+	mul_eltfp25519_1w_bmi2((u64 *)shared, Qx, A);
+	fred_eltfp25519_1w((u64 *)shared);
+
+	memzero_explicit(&m, sizeof(m));
+}
+
+static void curve25519_bmi2_base(u8 session_key[CURVE25519_KEY_SIZE],
+				 const u8 private_key[CURVE25519_KEY_SIZE])
+{
+	struct {
+		u64 buffer[4 * NUM_WORDS_ELTFP25519];
+		u64 coordinates[4 * NUM_WORDS_ELTFP25519];
+		u64 workspace[4 * NUM_WORDS_ELTFP25519];
+		u8 private[CURVE25519_KEY_SIZE];
+	} __aligned(32) m;
+
+	const int ite[4] = { 64, 64, 64, 63 };
+	const int q = 3;
+	u64 swap = 1;
+
+	int i = 0, j = 0, k = 0;
+	u64 *const key = (u64 *)m.private;
+	u64 *const Ur1 = m.coordinates + 0;
+	u64 *const Zr1 = m.coordinates + 4;
+	u64 *const Ur2 = m.coordinates + 8;
+	u64 *const Zr2 = m.coordinates + 12;
+
+	u64 *const UZr1 = m.coordinates + 0;
+	u64 *const ZUr2 = m.coordinates + 8;
+
+	u64 *const A = m.workspace + 0;
+	u64 *const B = m.workspace + 4;
+	u64 *const C = m.workspace + 8;
+	u64 *const D = m.workspace + 12;
+
+	u64 *const AB = m.workspace + 0;
+	u64 *const CD = m.workspace + 8;
+
+	const u64 *const P = table_ladder_8k;
+
+	memcpy(m.private, private_key, sizeof(m.private));
+
+	curve25519_clamp_secret(m.private);
+
+	setzero_eltfp25519_1w(Ur1);
+	setzero_eltfp25519_1w(Zr1);
+	setzero_eltfp25519_1w(Zr2);
+	Ur1[0] = 1;
+	Zr1[0] = 1;
+	Zr2[0] = 1;
+
+	/* G-S */
+	Ur2[3] = 0x1eaecdeee27cab34UL;
+	Ur2[2] = 0xadc7a0b9235d48e2UL;
+	Ur2[1] = 0xbbf095ae14b2edf8UL;
+	Ur2[0] = 0x7e94e1fec82faabdUL;
+
+	/* main-loop */
+	j = q;
+	for (i = 0; i < NUM_WORDS_ELTFP25519; ++i) {
+		while (j < ite[i]) {
+			u64 bit = (key[i] >> j) & 0x1;
+			k = (64 * i + j - q);
+			swap = swap ^ bit;
+			cswap(swap, Ur1, Ur2);
+			cswap(swap, Zr1, Zr2);
+			swap = bit;
+			/* Addition */
+			sub_eltfp25519_1w(B, Ur1, Zr1);		/* B = Ur1-Zr1 */
+			add_eltfp25519_1w_bmi2(A, Ur1, Zr1);	/* A = Ur1+Zr1 */
+			mul_eltfp25519_1w_bmi2(C, &P[4 * k], B);/* C = M0-B */
+			sub_eltfp25519_1w(B, A, C);		/* B = (Ur1+Zr1) - M*(Ur1-Zr1) */
+			add_eltfp25519_1w_bmi2(A, A, C);	/* A = (Ur1+Zr1) + M*(Ur1-Zr1) */
+			sqr_eltfp25519_2w_bmi2(AB);		/* A = A^2      |  B = B^2 */
+			mul_eltfp25519_2w_bmi2(UZr1, ZUr2, AB);	/* Ur1 = Zr2*A  |  Zr1 = Ur2*B */
+			++j;
+		}
+		j = 0;
+	}
+
+	/* Doubling */
+	for (i = 0; i < q; ++i) {
+		add_eltfp25519_1w_bmi2(A, Ur1, Zr1);	/*  A = Ur1+Zr1 */
+		sub_eltfp25519_1w(B, Ur1, Zr1);		/*  B = Ur1-Zr1 */
+		sqr_eltfp25519_2w_bmi2(AB);		/*  A = A**2     B = B**2 */
+		copy_eltfp25519_1w(C, B);		/*  C = B */
+		sub_eltfp25519_1w(B, A, B);		/*  B = A-B */
+		mul_a24_eltfp25519_1w(D, B);		/*  D = my_a24*B */
+		add_eltfp25519_1w_bmi2(D, D, C);	/*  D = D+C */
+		mul_eltfp25519_2w_bmi2(UZr1, AB, CD);	/*  Ur1 = A*B   Zr1 = Zr1*A */
+	}
+
+	/* Convert to affine coordinates */
+	inv_eltfp25519_1w_bmi2(A, Zr1);
+	mul_eltfp25519_1w_bmi2((u64 *)session_key, Ur1, A);
+	fred_eltfp25519_1w((u64 *)session_key);
+
+	memzero_explicit(&m, sizeof(m));
+}
+
+void curve25519_arch(u8 mypublic[CURVE25519_KEY_SIZE],
+		     const u8 secret[CURVE25519_KEY_SIZE],
+		     const u8 basepoint[CURVE25519_KEY_SIZE])
+{
+	if (static_branch_likely(&curve25519_use_adx))
+		curve25519_adx(mypublic, secret, basepoint);
+	else if (static_branch_likely(&curve25519_use_bmi2))
+		curve25519_bmi2(mypublic, secret, basepoint);
+	else
+		curve25519_generic(mypublic, secret, basepoint);
+}
+EXPORT_SYMBOL(curve25519_arch);
+
+void curve25519_base_arch(u8 pub[CURVE25519_KEY_SIZE],
+			  const u8 secret[CURVE25519_KEY_SIZE])
+{
+	if (static_branch_likely(&curve25519_use_adx))
+		curve25519_adx_base(pub, secret);
+	else if (static_branch_likely(&curve25519_use_bmi2))
+		curve25519_bmi2_base(pub, secret);
+	else
+		curve25519_generic(pub, secret, curve25519_base_point);
+}
+EXPORT_SYMBOL(curve25519_base_arch);
+
+static int curve25519_set_secret(struct crypto_kpp *tfm, const void *buf,
+				 unsigned int len)
+{
+	u8 *secret = kpp_tfm_ctx(tfm);
+
+	if (!len)
+		curve25519_generate_secret(secret);
+	else if (len == CURVE25519_KEY_SIZE &&
+		 crypto_memneq(buf, curve25519_null_point, CURVE25519_KEY_SIZE))
+		memcpy(secret, buf, CURVE25519_KEY_SIZE);
+	else
+		return -EINVAL;
+	return 0;
+}
+
+static int curve25519_generate_public_key(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	const u8 *secret = kpp_tfm_ctx(tfm);
+	u8 buf[CURVE25519_KEY_SIZE];
+	int copied, nbytes;
+
+	if (req->src)
+		return -EINVAL;
+
+	curve25519_base_arch(buf, secret);
+
+	/* might want less than we've got */
+	nbytes = min_t(size_t, CURVE25519_KEY_SIZE, req->dst_len);
+	copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst,
+								nbytes),
+				     buf, nbytes);
+	if (copied != nbytes)
+		return -EINVAL;
+	return 0;
+}
+
+static int curve25519_compute_shared_secret(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	const u8 *secret = kpp_tfm_ctx(tfm);
+	u8 public_key[CURVE25519_KEY_SIZE];
+	u8 buf[CURVE25519_KEY_SIZE];
+	int copied, nbytes;
+
+	if (!req->src)
+		return -EINVAL;
+
+	copied = sg_copy_to_buffer(req->src,
+				   sg_nents_for_len(req->src,
+						    CURVE25519_KEY_SIZE),
+				   public_key, CURVE25519_KEY_SIZE);
+	if (copied != CURVE25519_KEY_SIZE)
+		return -EINVAL;
+
+	curve25519_arch(buf, secret, public_key);
+
+	/* might want less than we've got */
+	nbytes = min_t(size_t, CURVE25519_KEY_SIZE, req->dst_len);
+	copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst,
+								nbytes),
+				     buf, nbytes);
+	if (copied != nbytes)
+		return -EINVAL;
+	return 0;
+}
+
+static unsigned int curve25519_max_size(struct crypto_kpp *tfm)
+{
+	return CURVE25519_KEY_SIZE;
+}
+
+static struct kpp_alg curve25519_alg = {
+	.base.cra_name		= "curve25519",
+	.base.cra_driver_name	= "curve25519-x86",
+	.base.cra_priority	= 200,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_ctxsize	= CURVE25519_KEY_SIZE,
+
+	.set_secret		= curve25519_set_secret,
+	.generate_public_key	= curve25519_generate_public_key,
+	.compute_shared_secret	= curve25519_compute_shared_secret,
+	.max_size		= curve25519_max_size,
+};
+
+static int __init curve25519_mod_init(void)
+{
+	if (boot_cpu_has(X86_FEATURE_BMI2))
+		static_branch_enable(&curve25519_use_bmi2);
+	else if (boot_cpu_has(X86_FEATURE_ADX))
+		static_branch_enable(&curve25519_use_adx);
+	else
+		return 0;
+	return crypto_register_kpp(&curve25519_alg);
+}
+
+static void __exit curve25519_mod_exit(void)
+{
+	if (boot_cpu_has(X86_FEATURE_BMI2) ||
+	    boot_cpu_has(X86_FEATURE_ADX))
+		crypto_unregister_kpp(&curve25519_alg);
+}
+
+module_init(curve25519_mod_init);
+module_exit(curve25519_mod_exit);
+
+MODULE_ALIAS_CRYPTO("curve25519");
+MODULE_ALIAS_CRYPTO("curve25519-x86");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 4a1c05dce950..370cd88068ec 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -7,47 +7,23 @@
 
 #include <crypto/algapi.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/poly1305.h>
 #include <crypto/internal/simd.h>
-#include <crypto/poly1305.h>
 #include <linux/crypto.h>
+#include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <asm/simd.h>
 
-struct poly1305_simd_desc_ctx {
-	struct poly1305_desc_ctx base;
-	/* derived key u set? */
-	bool uset;
-#ifdef CONFIG_AS_AVX2
-	/* derived keys r^3, r^4 set? */
-	bool wset;
-#endif
-	/* derived Poly1305 key r^2 */
-	u32 u[5];
-	/* ... silently appended r^3 and r^4 when using AVX2 */
-};
-
 asmlinkage void poly1305_block_sse2(u32 *h, const u8 *src,
 				    const u32 *r, unsigned int blocks);
 asmlinkage void poly1305_2block_sse2(u32 *h, const u8 *src, const u32 *r,
 				     unsigned int blocks, const u32 *u);
-#ifdef CONFIG_AS_AVX2
 asmlinkage void poly1305_4block_avx2(u32 *h, const u8 *src, const u32 *r,
 				     unsigned int blocks, const u32 *u);
-static bool poly1305_use_avx2;
-#endif
-
-static int poly1305_simd_init(struct shash_desc *desc)
-{
-	struct poly1305_simd_desc_ctx *sctx = shash_desc_ctx(desc);
 
-	sctx->uset = false;
-#ifdef CONFIG_AS_AVX2
-	sctx->wset = false;
-#endif
-
-	return crypto_poly1305_init(desc);
-}
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_simd);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx2);
 
 static void poly1305_simd_mult(u32 *a, const u32 *b)
 {
@@ -60,72 +36,85 @@ static void poly1305_simd_mult(u32 *a, const u32 *b)
 	poly1305_block_sse2(a, m, b, 1);
 }
 
+static unsigned int poly1305_scalar_blocks(struct poly1305_desc_ctx *dctx,
+					   const u8 *src, unsigned int srclen)
+{
+	unsigned int datalen;
+
+	if (unlikely(!dctx->sset)) {
+		datalen = crypto_poly1305_setdesckey(dctx, src, srclen);
+		src += srclen - datalen;
+		srclen = datalen;
+	}
+	if (srclen >= POLY1305_BLOCK_SIZE) {
+		poly1305_core_blocks(&dctx->h, dctx->r, src,
+				     srclen / POLY1305_BLOCK_SIZE, 1);
+		srclen %= POLY1305_BLOCK_SIZE;
+	}
+	return srclen;
+}
+
 static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx,
 					 const u8 *src, unsigned int srclen)
 {
-	struct poly1305_simd_desc_ctx *sctx;
 	unsigned int blocks, datalen;
 
-	BUILD_BUG_ON(offsetof(struct poly1305_simd_desc_ctx, base));
-	sctx = container_of(dctx, struct poly1305_simd_desc_ctx, base);
-
 	if (unlikely(!dctx->sset)) {
 		datalen = crypto_poly1305_setdesckey(dctx, src, srclen);
 		src += srclen - datalen;
 		srclen = datalen;
 	}
 
-#ifdef CONFIG_AS_AVX2
-	if (poly1305_use_avx2 && srclen >= POLY1305_BLOCK_SIZE * 4) {
-		if (unlikely(!sctx->wset)) {
-			if (!sctx->uset) {
-				memcpy(sctx->u, dctx->r.r, sizeof(sctx->u));
-				poly1305_simd_mult(sctx->u, dctx->r.r);
-				sctx->uset = true;
+	if (IS_ENABLED(CONFIG_AS_AVX2) &&
+	    static_branch_likely(&poly1305_use_avx2) &&
+	    srclen >= POLY1305_BLOCK_SIZE * 4) {
+		if (unlikely(dctx->rset < 4)) {
+			if (dctx->rset < 2) {
+				dctx->r[1] = dctx->r[0];
+				poly1305_simd_mult(dctx->r[1].r, dctx->r[0].r);
 			}
-			memcpy(sctx->u + 5, sctx->u, sizeof(sctx->u));
-			poly1305_simd_mult(sctx->u + 5, dctx->r.r);
-			memcpy(sctx->u + 10, sctx->u + 5, sizeof(sctx->u));
-			poly1305_simd_mult(sctx->u + 10, dctx->r.r);
-			sctx->wset = true;
+			dctx->r[2] = dctx->r[1];
+			poly1305_simd_mult(dctx->r[2].r, dctx->r[0].r);
+			dctx->r[3] = dctx->r[2];
+			poly1305_simd_mult(dctx->r[3].r, dctx->r[0].r);
+			dctx->rset = 4;
 		}
 		blocks = srclen / (POLY1305_BLOCK_SIZE * 4);
-		poly1305_4block_avx2(dctx->h.h, src, dctx->r.r, blocks,
-				     sctx->u);
+		poly1305_4block_avx2(dctx->h.h, src, dctx->r[0].r, blocks,
+				     dctx->r[1].r);
 		src += POLY1305_BLOCK_SIZE * 4 * blocks;
 		srclen -= POLY1305_BLOCK_SIZE * 4 * blocks;
 	}
-#endif
+
 	if (likely(srclen >= POLY1305_BLOCK_SIZE * 2)) {
-		if (unlikely(!sctx->uset)) {
-			memcpy(sctx->u, dctx->r.r, sizeof(sctx->u));
-			poly1305_simd_mult(sctx->u, dctx->r.r);
-			sctx->uset = true;
+		if (unlikely(dctx->rset < 2)) {
+			dctx->r[1] = dctx->r[0];
+			poly1305_simd_mult(dctx->r[1].r, dctx->r[0].r);
+			dctx->rset = 2;
 		}
 		blocks = srclen / (POLY1305_BLOCK_SIZE * 2);
-		poly1305_2block_sse2(dctx->h.h, src, dctx->r.r, blocks,
-				     sctx->u);
+		poly1305_2block_sse2(dctx->h.h, src, dctx->r[0].r,
+				     blocks, dctx->r[1].r);
 		src += POLY1305_BLOCK_SIZE * 2 * blocks;
 		srclen -= POLY1305_BLOCK_SIZE * 2 * blocks;
 	}
 	if (srclen >= POLY1305_BLOCK_SIZE) {
-		poly1305_block_sse2(dctx->h.h, src, dctx->r.r, 1);
+		poly1305_block_sse2(dctx->h.h, src, dctx->r[0].r, 1);
 		srclen -= POLY1305_BLOCK_SIZE;
 	}
 	return srclen;
 }
 
-static int poly1305_simd_update(struct shash_desc *desc,
-				const u8 *src, unsigned int srclen)
+void poly1305_init_arch(struct poly1305_desc_ctx *desc, const u8 *key)
 {
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-	unsigned int bytes;
-
-	/* kernel_fpu_begin/end is costly, use fallback for small updates */
-	if (srclen <= 288 || !crypto_simd_usable())
-		return crypto_poly1305_update(desc, src, srclen);
+	poly1305_init_generic(desc, key);
+}
+EXPORT_SYMBOL(poly1305_init_arch);
 
-	kernel_fpu_begin();
+void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
+			  unsigned int srclen)
+{
+	unsigned int bytes;
 
 	if (unlikely(dctx->buflen)) {
 		bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
@@ -135,34 +124,84 @@ static int poly1305_simd_update(struct shash_desc *desc,
 		dctx->buflen += bytes;
 
 		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
-			poly1305_simd_blocks(dctx, dctx->buf,
-					     POLY1305_BLOCK_SIZE);
+			if (static_branch_likely(&poly1305_use_simd) &&
+			    likely(crypto_simd_usable())) {
+				kernel_fpu_begin();
+				poly1305_simd_blocks(dctx, dctx->buf,
+						     POLY1305_BLOCK_SIZE);
+				kernel_fpu_end();
+			} else {
+				poly1305_scalar_blocks(dctx, dctx->buf,
+						       POLY1305_BLOCK_SIZE);
+			}
 			dctx->buflen = 0;
 		}
 	}
 
 	if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
-		bytes = poly1305_simd_blocks(dctx, src, srclen);
+		if (static_branch_likely(&poly1305_use_simd) &&
+		    likely(crypto_simd_usable())) {
+			kernel_fpu_begin();
+			bytes = poly1305_simd_blocks(dctx, src, srclen);
+			kernel_fpu_end();
+		} else {
+			bytes = poly1305_scalar_blocks(dctx, src, srclen);
+		}
 		src += srclen - bytes;
 		srclen = bytes;
 	}
 
-	kernel_fpu_end();
-
 	if (unlikely(srclen)) {
 		dctx->buflen = srclen;
 		memcpy(dctx->buf, src, srclen);
 	}
+}
+EXPORT_SYMBOL(poly1305_update_arch);
+
+void poly1305_final_arch(struct poly1305_desc_ctx *desc, u8 *digest)
+{
+	poly1305_final_generic(desc, digest);
+}
+EXPORT_SYMBOL(poly1305_final_arch);
+
+static int crypto_poly1305_init(struct shash_desc *desc)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	poly1305_core_init(&dctx->h);
+	dctx->buflen = 0;
+	dctx->rset = 0;
+	dctx->sset = false;
+
+	return 0;
+}
+
+static int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (unlikely(!dctx->sset))
+		return -ENOKEY;
+
+	poly1305_final_generic(dctx, dst);
+	return 0;
+}
+
+static int poly1305_simd_update(struct shash_desc *desc,
+				const u8 *src, unsigned int srclen)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
 
+	poly1305_update_arch(dctx, src, srclen);
 	return 0;
 }
 
 static struct shash_alg alg = {
 	.digestsize	= POLY1305_DIGEST_SIZE,
-	.init		= poly1305_simd_init,
+	.init		= crypto_poly1305_init,
 	.update		= poly1305_simd_update,
 	.final		= crypto_poly1305_final,
-	.descsize	= sizeof(struct poly1305_simd_desc_ctx),
+	.descsize	= sizeof(struct poly1305_desc_ctx),
 	.base		= {
 		.cra_name		= "poly1305",
 		.cra_driver_name	= "poly1305-simd",
@@ -175,16 +214,16 @@ static struct shash_alg alg = {
 static int __init poly1305_simd_mod_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_XMM2))
-		return -ENODEV;
-
-#ifdef CONFIG_AS_AVX2
-	poly1305_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) &&
-			    boot_cpu_has(X86_FEATURE_AVX2) &&
-			    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL);
-	alg.descsize = sizeof(struct poly1305_simd_desc_ctx);
-	if (poly1305_use_avx2)
-		alg.descsize += 10 * sizeof(u32);
-#endif
+		return 0;
+
+	static_branch_enable(&poly1305_use_simd);
+
+	if (IS_ENABLED(CONFIG_AS_AVX2) &&
+	    boot_cpu_has(X86_FEATURE_AVX) &&
+	    boot_cpu_has(X86_FEATURE_AVX2) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
+		static_branch_enable(&poly1305_use_avx2);
+
 	return crypto_register_shash(&alg);
 }
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index fcef678c3423..937363b803c1 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3323,8 +3323,19 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	return 0;
 }
 
+#ifdef CONFIG_RETPOLINE
+static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr);
+static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr);
+#endif
+
 struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
 {
+#ifdef CONFIG_RETPOLINE
+	if (x86_pmu.guest_get_msrs == intel_guest_get_msrs)
+		return intel_guest_get_msrs(nr);
+	else if (x86_pmu.guest_get_msrs == core_guest_get_msrs)
+		return core_guest_get_msrs(nr);
+#endif
 	if (x86_pmu.guest_get_msrs)
 		return x86_pmu.guest_get_msrs(nr);
 	*nr = 0;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4fc61483919a..b79cd6aa4075 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -156,10 +156,8 @@ enum kvm_reg {
 	VCPU_REGS_R15 = __VCPU_REGS_R15,
 #endif
 	VCPU_REGS_RIP,
-	NR_VCPU_REGS
-};
+	NR_VCPU_REGS,
 
-enum kvm_reg_ex {
 	VCPU_EXREG_PDPTR = NR_VCPU_REGS,
 	VCPU_EXREG_CR3,
 	VCPU_EXREG_RFLAGS,
@@ -454,6 +452,11 @@ struct kvm_pmc {
 	u64 eventsel;
 	struct perf_event *perf_event;
 	struct kvm_vcpu *vcpu;
+	/*
+	 * eventsel value for general purpose counters,
+	 * ctrl value for fixed counters.
+	 */
+	u64 current_config;
 };
 
 struct kvm_pmu {
@@ -472,7 +475,21 @@ struct kvm_pmu {
 	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
 	struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
 	struct irq_work irq_work;
-	u64 reprogram_pmi;
+	DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX);
+	DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
+	DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX);
+
+	/*
+	 * The gate to release perf_events not marked in
+	 * pmc_in_use only once in a vcpu time slice.
+	 */
+	bool need_cleanup;
+
+	/*
+	 * The total number of programmed perf_events and it helps to avoid
+	 * redundant check before cleanup if guest don't use vPMU at all.
+	 */
+	u8 event_count;
 };
 
 struct kvm_pmu_ops;
@@ -565,6 +582,7 @@ struct kvm_vcpu_arch {
 	u64 smbase;
 	u64 smi_count;
 	bool tpr_access_reporting;
+	bool xsaves_enabled;
 	u64 ia32_xss;
 	u64 microcode_version;
 	u64 arch_capabilities;
@@ -1041,7 +1059,6 @@ struct kvm_x86_ops {
 			    struct kvm_segment *var, int seg);
 	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
 	void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu);
-	void (*decache_cr3)(struct kvm_vcpu *vcpu);
 	void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
 	void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
@@ -1090,7 +1107,7 @@ struct kvm_x86_ops {
 	void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
 	void (*enable_irq_window)(struct kvm_vcpu *vcpu);
 	void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
-	bool (*get_enable_apicv)(struct kvm_vcpu *vcpu);
+	bool (*get_enable_apicv)(struct kvm *kvm);
 	void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
 	void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
 	void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr);
@@ -1357,6 +1374,7 @@ int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
 
 void kvm_enable_efer_bits(u64);
 bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer);
+int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated);
 int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data);
 int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data);
 int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu);
@@ -1577,6 +1595,8 @@ bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
 
 void kvm_make_mclock_inprogress_request(struct kvm *kvm);
 void kvm_make_scan_ioapic_request(struct kvm *kvm);
+void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
+				       unsigned long *vcpu_bitmap);
 
 void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 				     struct kvm_async_pf *work);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 6a3124664289..084e98da04a7 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -409,6 +409,8 @@
 #define MSR_AMD_PSTATE_DEF_BASE		0xc0010064
 #define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
 #define MSR_AMD64_OSVW_STATUS		0xc0010141
+#define MSR_AMD_PPIN_CTL		0xc00102f0
+#define MSR_AMD_PPIN			0xc00102f1
 #define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022
 #define MSR_AMD64_BU_CFG2		0xc001102a
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 0bc530c4eb13..ad97dc155195 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1463,6 +1463,12 @@ static inline bool arch_has_pfn_modify_check(void)
 	return boot_cpu_has_bug(X86_BUG_L1TF);
 }
 
+#define arch_faults_on_old_pte arch_faults_on_old_pte
+static inline bool arch_faults_on_old_pte(void)
+{
+	return false;
+}
+
 #include <asm-generic/pgtable.h>
 #endif	/* __ASSEMBLY__ */
 
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index a6ac3712db8b..4bbccb9d16dc 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -510,10 +510,9 @@ static __init unsigned long check_iommu_size(unsigned long aper, u64 aper_size)
 	iommu_size -= round_up(a, PMD_PAGE_SIZE) - a;
 
 	if (iommu_size < 64*1024*1024) {
-		pr_warning(
-			"PCI-DMA: Warning: Small IOMMU %luMB."
+		pr_warn("PCI-DMA: Warning: Small IOMMU %luMB."
 			" Consider increasing the AGP aperture in BIOS\n",
-				iommu_size >> 20);
+			iommu_size >> 20);
 	}
 
 	return iommu_size;
@@ -665,8 +664,7 @@ static __init int init_amd_gatt(struct agp_kern_info *info)
 
  nommu:
 	/* Should not happen anymore */
-	pr_warning("PCI-DMA: More than 4GB of RAM and no IOMMU\n"
-	       "falling back to iommu=soft.\n");
+	pr_warn("PCI-DMA: More than 4GB of RAM and no IOMMU - falling back to iommu=soft.\n");
 	return -1;
 }
 
@@ -733,8 +731,8 @@ int __init gart_iommu_init(void)
 	    !gart_iommu_aperture ||
 	    (no_agp && init_amd_gatt(&info) < 0)) {
 		if (max_pfn > MAX_DMA32_PFN) {
-			pr_warning("More than 4GB of memory but GART IOMMU not available.\n");
-			pr_warning("falling back to iommu=soft.\n");
+			pr_warn("More than 4GB of memory but GART IOMMU not available.\n");
+			pr_warn("falling back to iommu=soft.\n");
 		}
 		return 0;
 	}
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2b0faf86da1b..05feaec5d3d7 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -780,8 +780,8 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
 
 	res = (((u64)deltapm) *  mult) >> 22;
 	do_div(res, 1000000);
-	pr_warning("APIC calibration not consistent "
-		   "with PM-Timer: %ldms instead of 100ms\n",(long)res);
+	pr_warn("APIC calibration not consistent "
+		"with PM-Timer: %ldms instead of 100ms\n", (long)res);
 
 	/* Correct the lapic counter value */
 	res = (((u64)(*delta)) * pm_100ms);
@@ -977,7 +977,7 @@ static int __init calibrate_APIC_clock(void)
 	 */
 	if (lapic_timer_period < (1000000 / HZ)) {
 		local_irq_enable();
-		pr_warning("APIC frequency too slow, disabling apic timer\n");
+		pr_warn("APIC frequency too slow, disabling apic timer\n");
 		return -1;
 	}
 
@@ -1021,7 +1021,7 @@ static int __init calibrate_APIC_clock(void)
 	local_irq_enable();
 
 	if (levt->features & CLOCK_EVT_FEAT_DUMMY) {
-		pr_warning("APIC timer disabled due to verification failure\n");
+		pr_warn("APIC timer disabled due to verification failure\n");
 		return -1;
 	}
 
@@ -1095,8 +1095,8 @@ static void local_apic_timer_interrupt(void)
 	 * spurious.
 	 */
 	if (!evt->event_handler) {
-		pr_warning("Spurious LAPIC timer interrupt on cpu %d\n",
-			   smp_processor_id());
+		pr_warn("Spurious LAPIC timer interrupt on cpu %d\n",
+			smp_processor_id());
 		/* Switch it off */
 		lapic_timer_shutdown(evt);
 		return;
@@ -1811,11 +1811,11 @@ static int __init setup_nox2apic(char *str)
 		int apicid = native_apic_msr_read(APIC_ID);
 
 		if (apicid >= 255) {
-			pr_warning("Apicid: %08x, cannot enforce nox2apic\n",
-				   apicid);
+			pr_warn("Apicid: %08x, cannot enforce nox2apic\n",
+				apicid);
 			return 0;
 		}
-		pr_warning("x2apic already enabled.\n");
+		pr_warn("x2apic already enabled.\n");
 		__x2apic_disable();
 	}
 	setup_clear_cpu_cap(X86_FEATURE_X2APIC);
@@ -1983,7 +1983,7 @@ static int __init apic_verify(void)
 	 */
 	features = cpuid_edx(1);
 	if (!(features & (1 << X86_FEATURE_APIC))) {
-		pr_warning("Could not enable APIC!\n");
+		pr_warn("Could not enable APIC!\n");
 		return -1;
 	}
 	set_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
@@ -2410,9 +2410,8 @@ int generic_processor_info(int apicid, int version)
 	    disabled_cpu_apicid == apicid) {
 		int thiscpu = num_processors + disabled_cpus;
 
-		pr_warning("APIC: Disabling requested cpu."
-			   " Processor %d/0x%x ignored.\n",
-			   thiscpu, apicid);
+		pr_warn("APIC: Disabling requested cpu."
+			" Processor %d/0x%x ignored.\n", thiscpu, apicid);
 
 		disabled_cpus++;
 		return -ENODEV;
@@ -2426,8 +2425,7 @@ int generic_processor_info(int apicid, int version)
 	    apicid != boot_cpu_physical_apicid) {
 		int thiscpu = max + disabled_cpus - 1;
 
-		pr_warning(
-			"APIC: NR_CPUS/possible_cpus limit of %i almost"
+		pr_warn("APIC: NR_CPUS/possible_cpus limit of %i almost"
 			" reached. Keeping one slot for boot cpu."
 			"  Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
 
@@ -2438,9 +2436,8 @@ int generic_processor_info(int apicid, int version)
 	if (num_processors >= nr_cpu_ids) {
 		int thiscpu = max + disabled_cpus;
 
-		pr_warning("APIC: NR_CPUS/possible_cpus limit of %i "
-			   "reached. Processor %d/0x%x ignored.\n",
-			   max, thiscpu, apicid);
+		pr_warn("APIC: NR_CPUS/possible_cpus limit of %i reached. "
+			"Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
 
 		disabled_cpus++;
 		return -EINVAL;
@@ -2470,13 +2467,13 @@ int generic_processor_info(int apicid, int version)
 	 * Validate version
 	 */
 	if (version == 0x0) {
-		pr_warning("BIOS bug: APIC version is 0 for CPU %d/0x%x, fixing up to 0x10\n",
-			   cpu, apicid);
+		pr_warn("BIOS bug: APIC version is 0 for CPU %d/0x%x, fixing up to 0x10\n",
+			cpu, apicid);
 		version = 0x10;
 	}
 
 	if (version != boot_cpu_apic_version) {
-		pr_warning("BIOS bug: APIC version mismatch, boot CPU: %x, CPU %d: version %x\n",
+		pr_warn("BIOS bug: APIC version mismatch, boot CPU: %x, CPU %d: version %x\n",
 			boot_cpu_apic_version, cpu, version);
 	}
 
@@ -2845,7 +2842,7 @@ static int __init apic_set_verbosity(char *arg)
 		apic_verbosity = APIC_VERBOSE;
 #ifdef CONFIG_X86_64
 	else {
-		pr_warning("APIC Verbosity level %s not recognised"
+		pr_warn("APIC Verbosity level %s not recognised"
 			" use apic=verbose or apic=debug\n", arg);
 		return -EINVAL;
 	}
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 6ea7fdc82f3c..5167bd2bb6b1 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -583,7 +583,7 @@ bool amd_filter_mce(struct mce *m)
  * - Prevent possible spurious interrupts from the IF bank on Family 0x17
  *   Models 0x10-0x2F due to Erratum #1114.
  */
-void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
+static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
 {
 	int i, num_msrs;
 	u64 hwcr;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 743370ee4983..5f42f25bac8f 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -488,8 +488,9 @@ int mce_usable_address(struct mce *m)
 	if (!(m->status & MCI_STATUS_ADDRV))
 		return 0;
 
-	/* Checks after this one are Intel-specific: */
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	/* Checks after this one are Intel/Zhaoxin-specific: */
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
 		return 1;
 
 	if (!(m->status & MCI_STATUS_MISCV))
@@ -507,10 +508,13 @@ EXPORT_SYMBOL_GPL(mce_usable_address);
 
 bool mce_is_memory_error(struct mce *m)
 {
-	if (m->cpuvendor == X86_VENDOR_AMD ||
-	    m->cpuvendor == X86_VENDOR_HYGON) {
+	switch (m->cpuvendor) {
+	case X86_VENDOR_AMD:
+	case X86_VENDOR_HYGON:
 		return amd_mce_is_memory_error(m);
-	} else if (m->cpuvendor == X86_VENDOR_INTEL) {
+
+	case X86_VENDOR_INTEL:
+	case X86_VENDOR_ZHAOXIN:
 		/*
 		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
 		 *
@@ -527,9 +531,10 @@ bool mce_is_memory_error(struct mce *m)
 		return (m->status & 0xef80) == BIT(7) ||
 		       (m->status & 0xef00) == BIT(8) ||
 		       (m->status & 0xeffc) == 0xc;
-	}
 
-	return false;
+	default:
+		return false;
+	}
 }
 EXPORT_SYMBOL_GPL(mce_is_memory_error);
 
@@ -1127,6 +1132,12 @@ static bool __mc_check_crashing_cpu(int cpu)
 		u64 mcgstatus;
 
 		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+
+		if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) {
+			if (mcgstatus & MCG_STATUS_LMCES)
+				return false;
+		}
+
 		if (mcgstatus & MCG_STATUS_RIPV) {
 			mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
 			return true;
@@ -1277,9 +1288,10 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 
 	/*
 	 * Check if this MCE is signaled to only this logical processor,
-	 * on Intel only.
+	 * on Intel, Zhaoxin only.
 	 */
-	if (m.cpuvendor == X86_VENDOR_INTEL)
+	if (m.cpuvendor == X86_VENDOR_INTEL ||
+	    m.cpuvendor == X86_VENDOR_ZHAOXIN)
 		lmce = m.mcgstatus & MCG_STATUS_LMCES;
 
 	/*
@@ -1697,6 +1709,18 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 		if (c->x86 == 6 && c->x86_model == 45)
 			quirk_no_way_out = quirk_sandybridge_ifu;
 	}
+
+	if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
+		/*
+		 * All newer Zhaoxin CPUs support MCE broadcasting. Enable
+		 * synchronization with a one second timeout.
+		 */
+		if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) {
+			if (cfg->monarch_timeout < 0)
+				cfg->monarch_timeout = USEC_PER_SEC;
+		}
+	}
+
 	if (cfg->monarch_timeout < 0)
 		cfg->monarch_timeout = 0;
 	if (cfg->bootlog != 0)
@@ -1760,6 +1784,35 @@ static void mce_centaur_feature_init(struct cpuinfo_x86 *c)
 	}
 }
 
+static void mce_zhaoxin_feature_init(struct cpuinfo_x86 *c)
+{
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+
+	/*
+	 * These CPUs have MCA bank 8 which reports only one error type called
+	 * SVAD (System View Address Decoder). The reporting of that error is
+	 * controlled by IA32_MC8.CTL.0.
+	 *
+	 * If enabled, prefetching on these CPUs will cause SVAD MCE when
+	 * virtual machines start and result in a system  panic. Always disable
+	 * bank 8 SVAD error by default.
+	 */
+	if ((c->x86 == 7 && c->x86_model == 0x1b) ||
+	    (c->x86_model == 0x19 || c->x86_model == 0x1f)) {
+		if (this_cpu_read(mce_num_banks) > 8)
+			mce_banks[8].ctl = 0;
+	}
+
+	intel_init_cmci();
+	intel_init_lmce();
+	mce_adjust_timer = cmci_intel_adjust_timer;
+}
+
+static void mce_zhaoxin_feature_clear(struct cpuinfo_x86 *c)
+{
+	intel_clear_lmce();
+}
+
 static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 {
 	switch (c->x86_vendor) {
@@ -1781,6 +1834,10 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 		mce_centaur_feature_init(c);
 		break;
 
+	case X86_VENDOR_ZHAOXIN:
+		mce_zhaoxin_feature_init(c);
+		break;
+
 	default:
 		break;
 	}
@@ -1792,6 +1849,11 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
 	case X86_VENDOR_INTEL:
 		mce_intel_feature_clear(c);
 		break;
+
+	case X86_VENDOR_ZHAOXIN:
+		mce_zhaoxin_feature_clear(c);
+		break;
+
 	default:
 		break;
 	}
@@ -2014,15 +2076,16 @@ static void mce_disable_error_reporting(void)
 static void vendor_disable_error_reporting(void)
 {
 	/*
-	 * Don't clear on Intel or AMD or Hygon CPUs. Some of these MSRs
-	 * are socket-wide.
-	 * Disabling them for just a single offlined CPU is bad, since it will
-	 * inhibit reporting for all shared resources on the socket like the
-	 * last level cache (LLC), the integrated memory controller (iMC), etc.
+	 * Don't clear on Intel or AMD or Hygon or Zhaoxin CPUs. Some of these
+	 * MSRs are socket-wide. Disabling them for just a single offlined CPU
+	 * is bad, since it will inhibit reporting for all shared resources on
+	 * the socket like the last level cache (LLC), the integrated memory
+	 * controller (iMC), etc.
 	 */
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL ||
 	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ||
-	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+	    boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN)
 		return;
 
 	mce_disable_error_reporting();
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index 88cd9598fa57..e270d0770134 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -85,8 +85,10 @@ static int cmci_supported(int *banks)
 	 * initialization is vendor keyed and this
 	 * makes sure none of the backdoors are entered otherwise.
 	 */
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
 		return 0;
+
 	if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6)
 		return 0;
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
@@ -423,7 +425,7 @@ void cmci_disable_bank(int bank)
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
-static void intel_init_cmci(void)
+void intel_init_cmci(void)
 {
 	int banks;
 
@@ -442,7 +444,7 @@ static void intel_init_cmci(void)
 	cmci_recheck();
 }
 
-static void intel_init_lmce(void)
+void intel_init_lmce(void)
 {
 	u64 val;
 
@@ -455,7 +457,7 @@ static void intel_init_lmce(void)
 		wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
 }
 
-static void intel_clear_lmce(void)
+void intel_clear_lmce(void)
 {
 	u64 val;
 
@@ -482,6 +484,7 @@ static void intel_ppin_init(struct cpuinfo_x86 *c)
 	case INTEL_FAM6_BROADWELL_D:
 	case INTEL_FAM6_BROADWELL_X:
 	case INTEL_FAM6_SKYLAKE_X:
+	case INTEL_FAM6_ICELAKE_X:
 	case INTEL_FAM6_XEON_PHI_KNL:
 	case INTEL_FAM6_XEON_PHI_KNM:
 
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 43031db429d2..842b273bce31 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -45,11 +45,17 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval);
 bool mce_intel_cmci_poll(void);
 void mce_intel_hcpu_update(unsigned long cpu);
 void cmci_disable_bank(int bank);
+void intel_init_cmci(void);
+void intel_init_lmce(void);
+void intel_clear_lmce(void);
 #else
 # define cmci_intel_adjust_timer mce_adjust_timer_default
 static inline bool mce_intel_cmci_poll(void) { return false; }
 static inline void mce_intel_hcpu_update(unsigned long cpu) { }
 static inline void cmci_disable_bank(int bank) { }
+static inline void intel_init_cmci(void) { }
+static inline void intel_init_lmce(void) { }
+static inline void intel_clear_lmce(void) { }
 #endif
 
 void mce_timer_kick(unsigned long interval);
diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c
index 6e2becf547c5..d01e0da0163a 100644
--- a/arch/x86/kernel/cpu/mce/therm_throt.c
+++ b/arch/x86/kernel/cpu/mce/therm_throt.c
@@ -40,15 +40,58 @@
 #define THERMAL_THROTTLING_EVENT	0
 #define POWER_LIMIT_EVENT		1
 
-/*
- * Current thermal event state:
+/**
+ * struct _thermal_state - Represent the current thermal event state
+ * @next_check:			Stores the next timestamp, when it is allowed
+ *				to log the next warning message.
+ * @last_interrupt_time:	Stores the timestamp for the last threshold
+ *				high event.
+ * @therm_work:			Delayed workqueue structure
+ * @count:			Stores the current running count for thermal
+ *				or power threshold interrupts.
+ * @last_count:			Stores the previous running count for thermal
+ *				or power threshold interrupts.
+ * @max_time_ms:		This shows the maximum amount of time CPU was
+ *				in throttled state for a single thermal
+ *				threshold high to low state.
+ * @total_time_ms:		This is a cumulative time during which CPU was
+ *				in the throttled state.
+ * @rate_control_active:	Set when a throttling message is logged.
+ *				This is used for the purpose of rate-control.
+ * @new_event:			Stores the last high/low status of the
+ *				THERM_STATUS_PROCHOT or
+ *				THERM_STATUS_POWER_LIMIT.
+ * @level:			Stores whether this _thermal_state instance is
+ *				for a CORE level or for PACKAGE level.
+ * @sample_index:		Index for storing the next sample in the buffer
+ *				temp_samples[].
+ * @sample_count:		Total number of samples collected in the buffer
+ *				temp_samples[].
+ * @average:			The last moving average of temperature samples
+ * @baseline_temp:		Temperature at which thermal threshold high
+ *				interrupt was generated.
+ * @temp_samples:		Storage for temperature samples to calculate
+ *				moving average.
+ *
+ * This structure is used to represent data related to thermal state for a CPU.
+ * There is a separate storage for core and package level for each CPU.
  */
 struct _thermal_state {
-	bool			new_event;
-	int			event;
 	u64			next_check;
+	u64			last_interrupt_time;
+	struct delayed_work	therm_work;
 	unsigned long		count;
 	unsigned long		last_count;
+	unsigned long		max_time_ms;
+	unsigned long		total_time_ms;
+	bool			rate_control_active;
+	bool			new_event;
+	u8			level;
+	u8			sample_index;
+	u8			sample_count;
+	u8			average;
+	u8			baseline_temp;
+	u8			temp_samples[3];
 };
 
 struct thermal_state {
@@ -121,8 +164,22 @@ define_therm_throt_device_one_ro(package_throttle_count);
 define_therm_throt_device_show_func(package_power_limit, count);
 define_therm_throt_device_one_ro(package_power_limit_count);
 
+define_therm_throt_device_show_func(core_throttle, max_time_ms);
+define_therm_throt_device_one_ro(core_throttle_max_time_ms);
+
+define_therm_throt_device_show_func(package_throttle, max_time_ms);
+define_therm_throt_device_one_ro(package_throttle_max_time_ms);
+
+define_therm_throt_device_show_func(core_throttle, total_time_ms);
+define_therm_throt_device_one_ro(core_throttle_total_time_ms);
+
+define_therm_throt_device_show_func(package_throttle, total_time_ms);
+define_therm_throt_device_one_ro(package_throttle_total_time_ms);
+
 static struct attribute *thermal_throttle_attrs[] = {
 	&dev_attr_core_throttle_count.attr,
+	&dev_attr_core_throttle_max_time_ms.attr,
+	&dev_attr_core_throttle_total_time_ms.attr,
 	NULL
 };
 
@@ -135,6 +192,105 @@ static const struct attribute_group thermal_attr_group = {
 #define CORE_LEVEL	0
 #define PACKAGE_LEVEL	1
 
+#define THERM_THROT_POLL_INTERVAL	HZ
+#define THERM_STATUS_PROCHOT_LOG	BIT(1)
+
+static void clear_therm_status_log(int level)
+{
+	int msr;
+	u64 msr_val;
+
+	if (level == CORE_LEVEL)
+		msr = MSR_IA32_THERM_STATUS;
+	else
+		msr = MSR_IA32_PACKAGE_THERM_STATUS;
+
+	rdmsrl(msr, msr_val);
+	wrmsrl(msr, msr_val & ~THERM_STATUS_PROCHOT_LOG);
+}
+
+static void get_therm_status(int level, bool *proc_hot, u8 *temp)
+{
+	int msr;
+	u64 msr_val;
+
+	if (level == CORE_LEVEL)
+		msr = MSR_IA32_THERM_STATUS;
+	else
+		msr = MSR_IA32_PACKAGE_THERM_STATUS;
+
+	rdmsrl(msr, msr_val);
+	if (msr_val & THERM_STATUS_PROCHOT_LOG)
+		*proc_hot = true;
+	else
+		*proc_hot = false;
+
+	*temp = (msr_val >> 16) & 0x7F;
+}
+
+static void throttle_active_work(struct work_struct *work)
+{
+	struct _thermal_state *state = container_of(to_delayed_work(work),
+						struct _thermal_state, therm_work);
+	unsigned int i, avg, this_cpu = smp_processor_id();
+	u64 now = get_jiffies_64();
+	bool hot;
+	u8 temp;
+
+	get_therm_status(state->level, &hot, &temp);
+	/* temperature value is offset from the max so lesser means hotter */
+	if (!hot && temp > state->baseline_temp) {
+		if (state->rate_control_active)
+			pr_info("CPU%d: %s temperature/speed normal (total events = %lu)\n",
+				this_cpu,
+				state->level == CORE_LEVEL ? "Core" : "Package",
+				state->count);
+
+		state->rate_control_active = false;
+		return;
+	}
+
+	if (time_before64(now, state->next_check) &&
+			  state->rate_control_active)
+		goto re_arm;
+
+	state->next_check = now + CHECK_INTERVAL;
+
+	if (state->count != state->last_count) {
+		/* There was one new thermal interrupt */
+		state->last_count = state->count;
+		state->average = 0;
+		state->sample_count = 0;
+		state->sample_index = 0;
+	}
+
+	state->temp_samples[state->sample_index] = temp;
+	state->sample_count++;
+	state->sample_index = (state->sample_index + 1) % ARRAY_SIZE(state->temp_samples);
+	if (state->sample_count < ARRAY_SIZE(state->temp_samples))
+		goto re_arm;
+
+	avg = 0;
+	for (i = 0; i < ARRAY_SIZE(state->temp_samples); ++i)
+		avg += state->temp_samples[i];
+
+	avg /= ARRAY_SIZE(state->temp_samples);
+
+	if (state->average > avg) {
+		pr_warn("CPU%d: %s temperature is above threshold, cpu clock is throttled (total events = %lu)\n",
+			this_cpu,
+			state->level == CORE_LEVEL ? "Core" : "Package",
+			state->count);
+		state->rate_control_active = true;
+	}
+
+	state->average = avg;
+
+re_arm:
+	clear_therm_status_log(state->level);
+	schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL);
+}
+
 /***
  * therm_throt_process - Process thermal throttling event from interrupt
  * @curr: Whether the condition is current or not (boolean), since the
@@ -178,27 +334,33 @@ static void therm_throt_process(bool new_event, int event, int level)
 	if (new_event)
 		state->count++;
 
-	if (time_before64(now, state->next_check) &&
-			state->count != state->last_count)
+	if (event != THERMAL_THROTTLING_EVENT)
 		return;
 
-	state->next_check = now + CHECK_INTERVAL;
-	state->last_count = state->count;
+	if (new_event && !state->last_interrupt_time) {
+		bool hot;
+		u8 temp;
+
+		get_therm_status(state->level, &hot, &temp);
+		/*
+		 * Ignore short temperature spike as the system is not close
+		 * to PROCHOT. 10C offset is large enough to ignore. It is
+		 * already dropped from the high threshold temperature.
+		 */
+		if (temp > 10)
+			return;
 
-	/* if we just entered the thermal event */
-	if (new_event) {
-		if (event == THERMAL_THROTTLING_EVENT)
-			pr_crit("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n",
-				this_cpu,
-				level == CORE_LEVEL ? "Core" : "Package",
-				state->count);
-		return;
-	}
-	if (old_event) {
-		if (event == THERMAL_THROTTLING_EVENT)
-			pr_info("CPU%d: %s temperature/speed normal\n", this_cpu,
-				level == CORE_LEVEL ? "Core" : "Package");
-		return;
+		state->baseline_temp = temp;
+		state->last_interrupt_time = now;
+		schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL);
+	} else if (old_event && state->last_interrupt_time) {
+		unsigned long throttle_time;
+
+		throttle_time = jiffies_delta_to_msecs(now - state->last_interrupt_time);
+		if (throttle_time > state->max_time_ms)
+			state->max_time_ms = throttle_time;
+		state->total_time_ms += throttle_time;
+		state->last_interrupt_time = 0;
 	}
 }
 
@@ -244,20 +406,47 @@ static int thermal_throttle_add_dev(struct device *dev, unsigned int cpu)
 	if (err)
 		return err;
 
-	if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable)
+	if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) {
 		err = sysfs_add_file_to_group(&dev->kobj,
 					      &dev_attr_core_power_limit_count.attr,
 					      thermal_attr_group.name);
+		if (err)
+			goto del_group;
+	}
+
 	if (cpu_has(c, X86_FEATURE_PTS)) {
 		err = sysfs_add_file_to_group(&dev->kobj,
 					      &dev_attr_package_throttle_count.attr,
 					      thermal_attr_group.name);
-		if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable)
+		if (err)
+			goto del_group;
+
+		err = sysfs_add_file_to_group(&dev->kobj,
+					      &dev_attr_package_throttle_max_time_ms.attr,
+					      thermal_attr_group.name);
+		if (err)
+			goto del_group;
+
+		err = sysfs_add_file_to_group(&dev->kobj,
+					      &dev_attr_package_throttle_total_time_ms.attr,
+					      thermal_attr_group.name);
+		if (err)
+			goto del_group;
+
+		if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) {
 			err = sysfs_add_file_to_group(&dev->kobj,
 					&dev_attr_package_power_limit_count.attr,
 					thermal_attr_group.name);
+			if (err)
+				goto del_group;
+		}
 	}
 
+	return 0;
+
+del_group:
+	sysfs_remove_group(&dev->kobj, &thermal_attr_group);
+
 	return err;
 }
 
@@ -269,15 +458,29 @@ static void thermal_throttle_remove_dev(struct device *dev)
 /* Get notified when a cpu comes on/off. Be hotplug friendly. */
 static int thermal_throttle_online(unsigned int cpu)
 {
+	struct thermal_state *state = &per_cpu(thermal_state, cpu);
 	struct device *dev = get_cpu_device(cpu);
 
+	state->package_throttle.level = PACKAGE_LEVEL;
+	state->core_throttle.level = CORE_LEVEL;
+
+	INIT_DELAYED_WORK(&state->package_throttle.therm_work, throttle_active_work);
+	INIT_DELAYED_WORK(&state->core_throttle.therm_work, throttle_active_work);
+
 	return thermal_throttle_add_dev(dev, cpu);
 }
 
 static int thermal_throttle_offline(unsigned int cpu)
 {
+	struct thermal_state *state = &per_cpu(thermal_state, cpu);
 	struct device *dev = get_cpu_device(cpu);
 
+	cancel_delayed_work(&state->package_throttle.therm_work);
+	cancel_delayed_work(&state->core_throttle.therm_work);
+
+	state->package_throttle.rate_control_active = false;
+	state->core_throttle.rate_control_active = false;
+
 	thermal_throttle_remove_dev(dev);
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index a0e52bd00ecc..3f6b137ef4e6 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -567,7 +567,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 void reload_ucode_amd(void)
 {
 	struct microcode_amd *mc;
-	u32 rev, dummy;
+	u32 rev, dummy __always_unused;
 
 	mc = (struct microcode_amd *)amd_ucode_patch;
 
@@ -673,7 +673,7 @@ static enum ucode_state apply_microcode_amd(int cpu)
 	struct ucode_cpu_info *uci;
 	struct ucode_patch *p;
 	enum ucode_state ret;
-	u32 rev, dummy;
+	u32 rev, dummy __always_unused;
 
 	BUG_ON(raw_smp_processor_id() != cpu);
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index cb0fdcaf1415..7019d4b2df0c 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -63,11 +63,6 @@ LIST_HEAD(microcode_cache);
  */
 static DEFINE_MUTEX(microcode_mutex);
 
-/*
- * Serialize late loading so that CPUs get updated one-by-one.
- */
-static DEFINE_RAW_SPINLOCK(update_lock);
-
 struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 
 struct cpu_info_ctx {
@@ -566,11 +561,18 @@ static int __reload_late(void *info)
 	if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC))
 		return -1;
 
-	raw_spin_lock(&update_lock);
-	apply_microcode_local(&err);
-	raw_spin_unlock(&update_lock);
+	/*
+	 * On an SMT system, it suffices to load the microcode on one sibling of
+	 * the core because the microcode engine is shared between the threads.
+	 * Synchronization still needs to take place so that no concurrent
+	 * loading attempts happen on multiple threads of an SMT core. See
+	 * below.
+	 */
+	if (cpumask_first(topology_sibling_cpumask(cpu)) == cpu)
+		apply_microcode_local(&err);
+	else
+		goto wait_for_siblings;
 
-	/* siblings return UCODE_OK because their engine got updated already */
 	if (err > UCODE_NFOUND) {
 		pr_warn("Error reloading microcode on CPU %d\n", cpu);
 		ret = -1;
@@ -578,14 +580,18 @@ static int __reload_late(void *info)
 		ret = 1;
 	}
 
+wait_for_siblings:
+	if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC))
+		panic("Timeout during microcode update!\n");
+
 	/*
-	 * Increase the wait timeout to a safe value here since we're
-	 * serializing the microcode update and that could take a while on a
-	 * large number of CPUs. And that is fine as the *actual* timeout will
-	 * be determined by the last CPU finished updating and thus cut short.
+	 * At least one thread has completed update on each core.
+	 * For others, simply call the update to make sure the
+	 * per-cpu cpuinfo can be updated with right microcode
+	 * revision.
 	 */
-	if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC * num_online_cpus()))
-		panic("Timeout during microcode update!\n");
+	if (cpumask_first(topology_sibling_cpumask(cpu)) != cpu)
+		apply_microcode_local(&err);
 
 	return ret;
 }
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index ce799cfe9434..6a99535d7f37 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -791,6 +791,7 @@ static enum ucode_state apply_microcode_intel(int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
 	struct microcode_intel *mc;
 	enum ucode_state ret;
 	static int prev_rev;
@@ -836,7 +837,7 @@ static enum ucode_state apply_microcode_intel(int cpu)
 		return UCODE_ERROR;
 	}
 
-	if (rev != prev_rev) {
+	if (bsp && rev != prev_rev) {
 		pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n",
 			rev,
 			mc->hdr.date & 0xffff,
@@ -852,7 +853,7 @@ out:
 	c->microcode	 = rev;
 
 	/* Update boot_cpu_data's revision too, if we're on the BSP: */
-	if (c->cpu_index == boot_cpu_data.cpu_index)
+	if (bsp)
 		boot_cpu_data.microcode = rev;
 
 	return ret;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index e820568ed4d5..32ef1ee733b7 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -33,6 +33,7 @@
 #include <asm/apicdef.h>
 #include <asm/hypervisor.h>
 #include <asm/tlb.h>
+#include <asm/cpuidle_haltpoll.h>
 
 static int kvmapf = 1;
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 86663874ef04..e6d7894ad127 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -207,8 +207,8 @@ void __init setup_per_cpu_areas(void)
 					    pcpu_cpu_distance,
 					    pcpu_fc_alloc, pcpu_fc_free);
 		if (rc < 0)
-			pr_warning("%s allocator failed (%d), falling back to page size\n",
-				   pcpu_fc_names[pcpu_chosen_fc], rc);
+			pr_warn("%s allocator failed (%d), falling back to page size\n",
+				pcpu_fc_names[pcpu_chosen_fc], rc);
 	}
 	if (rc < 0)
 		rc = pcpu_page_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index a49fe1dcb47e..4c61f0713832 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -57,7 +57,7 @@ void __init tboot_probe(void)
 	 */
 	if (!e820__mapped_any(boot_params.tboot_addr,
 			     boot_params.tboot_addr, E820_TYPE_RESERVED)) {
-		pr_warning("non-0 tboot_addr but it is not of type E820_TYPE_RESERVED\n");
+		pr_warn("non-0 tboot_addr but it is not of type E820_TYPE_RESERVED\n");
 		return;
 	}
 
@@ -65,13 +65,12 @@ void __init tboot_probe(void)
 	set_fixmap(FIX_TBOOT_BASE, boot_params.tboot_addr);
 	tboot = (struct tboot *)fix_to_virt(FIX_TBOOT_BASE);
 	if (memcmp(&tboot_uuid, &tboot->uuid, sizeof(tboot->uuid))) {
-		pr_warning("tboot at 0x%llx is invalid\n",
-			   boot_params.tboot_addr);
+		pr_warn("tboot at 0x%llx is invalid\n", boot_params.tboot_addr);
 		tboot = NULL;
 		return;
 	}
 	if (tboot->version < 5) {
-		pr_warning("tboot version is invalid: %u\n", tboot->version);
+		pr_warn("tboot version is invalid: %u\n", tboot->version);
 		tboot = NULL;
 		return;
 	}
@@ -289,7 +288,7 @@ static int tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control)
 
 	if (sleep_state >= ACPI_S_STATE_COUNT ||
 	    acpi_shutdown_map[sleep_state] == -1) {
-		pr_warning("unsupported sleep state 0x%x\n", sleep_state);
+		pr_warn("unsupported sleep state 0x%x\n", sleep_state);
 		return -1;
 	}
 
@@ -302,7 +301,7 @@ static int tboot_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b)
 	if (!tboot_enabled())
 		return 0;
 
-	pr_warning("tboot is not able to suspend on platforms with reduced hardware sleep (ACPIv5)");
+	pr_warn("tboot is not able to suspend on platforms with reduced hardware sleep (ACPIv5)");
 	return -ENODEV;
 }
 
@@ -320,7 +319,7 @@ static int tboot_wait_for_aps(int num_aps)
 	}
 
 	if (timeout)
-		pr_warning("tboot wait for APs timeout\n");
+		pr_warn("tboot wait for APs timeout\n");
 
 	return !(atomic_read((atomic_t *)&tboot->num_in_wfs) == num_aps);
 }
@@ -516,7 +515,7 @@ int tboot_force_iommu(void)
 		return 1;
 
 	if (no_iommu || swiotlb || dmar_disabled)
-		pr_warning("Forcing Intel-IOMMU to enabled\n");
+		pr_warn("Forcing Intel-IOMMU to enabled\n");
 
 	dmar_disabled = 0;
 #ifdef CONFIG_SWIOTLB
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index ec534f978867..b8acf639abd1 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -364,12 +364,12 @@ retry:
 		/* Force it to 0 if random warps brought us here */
 		atomic_set(&test_runs, 0);
 
-		pr_warning("TSC synchronization [CPU#%d -> CPU#%d]:\n",
+		pr_warn("TSC synchronization [CPU#%d -> CPU#%d]:\n",
 			smp_processor_id(), cpu);
-		pr_warning("Measured %Ld cycles TSC warp between CPUs, "
-			   "turning off TSC clock.\n", max_warp);
+		pr_warn("Measured %Ld cycles TSC warp between CPUs, "
+			"turning off TSC clock.\n", max_warp);
 		if (random_warps)
-			pr_warning("TSC warped randomly between CPUs\n");
+			pr_warn("TSC warped randomly between CPUs\n");
 		mark_tsc_unstable("check_tsc_sync_source failed");
 	}
 
diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c
index 548fefed71ee..b4a304893189 100644
--- a/arch/x86/kernel/umip.c
+++ b/arch/x86/kernel/umip.c
@@ -91,7 +91,7 @@ const char * const umip_insns[5] = {
 
 #define umip_pr_err(regs, fmt, ...) \
 	umip_printk(regs, KERN_ERR, fmt, ##__VA_ARGS__)
-#define umip_pr_warning(regs, fmt, ...) \
+#define umip_pr_warn(regs, fmt, ...) \
 	umip_printk(regs, KERN_WARNING, fmt,  ##__VA_ARGS__)
 
 /**
@@ -380,14 +380,14 @@ bool fixup_umip_exception(struct pt_regs *regs)
 	if (umip_inst < 0)
 		return false;
 
-	umip_pr_warning(regs, "%s instruction cannot be used by applications.\n",
+	umip_pr_warn(regs, "%s instruction cannot be used by applications.\n",
 			umip_insns[umip_inst]);
 
 	/* Do not emulate (spoof) SLDT or STR. */
 	if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT)
 		return false;
 
-	umip_pr_warning(regs, "For now, expensive software emulation returns the result.\n");
+	umip_pr_warn(regs, "For now, expensive software emulation returns the result.\n");
 
 	if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size,
 			      user_64bit_mode(regs)))
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 31ecf7a76d5a..b19ef421084d 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -8,9 +8,9 @@ kvm-y			+= $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
 				$(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
-kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
+kvm-y			+= x86.o emulate.o i8259.o irq.o lapic.o \
 			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
-			   hyperv.o page_track.o debugfs.o
+			   hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o
 
 kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o vmx/evmcs.o vmx/nested.o
 kvm-amd-y		+= svm.o pmu_amd.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index f68c0c753c38..c0aa07487eb8 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -816,8 +816,6 @@ static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func,
 	return __do_cpuid_func(entry, func, nent, maxnent);
 }
 
-#undef F
-
 struct kvm_cpuid_param {
 	u32 func;
 	bool (*qualifier)(const struct kvm_cpuid_param *param);
@@ -1015,6 +1013,12 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
 		*ebx = entry->ebx;
 		*ecx = entry->ecx;
 		*edx = entry->edx;
+		if (function == 7 && index == 0) {
+			u64 data;
+		        if (!__kvm_get_msr(vcpu, MSR_IA32_TSX_CTRL, &data, true) &&
+			    (data & TSX_CTRL_CPUID_CLEAR))
+				*ebx &= ~(F(RTM) | F(HLE));
+		}
 	} else {
 		*eax = *ebx = *ecx = *edx = 0;
 		/*
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 698efb8c3897..952d1a4f4d7e 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2770,11 +2770,10 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
 		return emulate_ud(ctxt);
 
 	ops->get_msr(ctxt, MSR_EFER, &efer);
-	setup_syscalls_segments(ctxt, &cs, &ss);
-
 	if (!(efer & EFER_SCE))
 		return emulate_ud(ctxt);
 
+	setup_syscalls_segments(ctxt, &cs, &ss);
 	ops->get_msr(ctxt, MSR_STAR, &msr_data);
 	msr_data >>= 32;
 	cs_sel = (u16)(msr_data & 0xfffc);
@@ -2838,12 +2837,11 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->mode == X86EMUL_MODE_PROT64)
 		return X86EMUL_UNHANDLEABLE;
 
-	setup_syscalls_segments(ctxt, &cs, &ss);
-
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data);
 	if ((msr_data & 0xfffc) == 0x0)
 		return emulate_gp(ctxt, 0);
 
+	setup_syscalls_segments(ctxt, &cs, &ss);
 	ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF);
 	cs_sel = (u16)msr_data & ~SEGMENT_RPL_MASK;
 	ss_sel = cs_sel + 8;
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index d859ae8890d0..9fd2dd89a1c5 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -271,8 +271,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 {
 	unsigned index;
 	bool mask_before, mask_after;
-	int old_remote_irr, old_delivery_status;
 	union kvm_ioapic_redirect_entry *e;
+	unsigned long vcpu_bitmap;
+	int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode;
 
 	switch (ioapic->ioregsel) {
 	case IOAPIC_REG_VERSION:
@@ -296,6 +297,8 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		/* Preserve read-only fields */
 		old_remote_irr = e->fields.remote_irr;
 		old_delivery_status = e->fields.delivery_status;
+		old_dest_id = e->fields.dest_id;
+		old_dest_mode = e->fields.dest_mode;
 		if (ioapic->ioregsel & 1) {
 			e->bits &= 0xffffffff;
 			e->bits |= (u64) val << 32;
@@ -321,7 +324,34 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
 		    && ioapic->irr & (1 << index))
 			ioapic_service(ioapic, index, false);
-		kvm_make_scan_ioapic_request(ioapic->kvm);
+		if (e->fields.delivery_mode == APIC_DM_FIXED) {
+			struct kvm_lapic_irq irq;
+
+			irq.shorthand = 0;
+			irq.vector = e->fields.vector;
+			irq.delivery_mode = e->fields.delivery_mode << 8;
+			irq.dest_id = e->fields.dest_id;
+			irq.dest_mode = e->fields.dest_mode;
+			bitmap_zero(&vcpu_bitmap, 16);
+			kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
+						 &vcpu_bitmap);
+			if (old_dest_mode != e->fields.dest_mode ||
+			    old_dest_id != e->fields.dest_id) {
+				/*
+				 * Update vcpu_bitmap with vcpus specified in
+				 * the previous request as well. This is done to
+				 * keep ioapic_handled_vectors synchronized.
+				 */
+				irq.dest_id = old_dest_id;
+				irq.dest_mode = old_dest_mode;
+				kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
+							 &vcpu_bitmap);
+			}
+			kvm_make_scan_ioapic_request_mask(ioapic->kvm,
+							  &vcpu_bitmap);
+		} else {
+			kvm_make_scan_ioapic_request(ioapic->kvm);
+		}
 		break;
 	}
 }
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 1cc6c47dc77e..58767020de41 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -37,22 +37,50 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14)
 BUILD_KVM_GPR_ACCESSORS(r15, R15)
 #endif
 
-static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu,
-					      enum kvm_reg reg)
+static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu,
+					     enum kvm_reg reg)
 {
-	if (!test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail))
+	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+}
+
+static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu,
+					 enum kvm_reg reg)
+{
+	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
+}
+
+static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu,
+					       enum kvm_reg reg)
+{
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+}
+
+static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu,
+					   enum kvm_reg reg)
+{
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
+}
+
+static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg)
+{
+	if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS))
+		return 0;
+
+	if (!kvm_register_is_available(vcpu, reg))
 		kvm_x86_ops->cache_reg(vcpu, reg);
 
 	return vcpu->arch.regs[reg];
 }
 
-static inline void kvm_register_write(struct kvm_vcpu *vcpu,
-				      enum kvm_reg reg,
+static inline void kvm_register_write(struct kvm_vcpu *vcpu, int reg,
 				      unsigned long val)
 {
+	if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS))
+		return;
+
 	vcpu->arch.regs[reg] = val;
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+	kvm_register_mark_dirty(vcpu, reg);
 }
 
 static inline unsigned long kvm_rip_read(struct kvm_vcpu *vcpu)
@@ -79,9 +107,8 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index)
 {
 	might_sleep();  /* on svm */
 
-	if (!test_bit(VCPU_EXREG_PDPTR,
-		      (unsigned long *)&vcpu->arch.regs_avail))
-		kvm_x86_ops->cache_reg(vcpu, (enum kvm_reg)VCPU_EXREG_PDPTR);
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR))
+		kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_PDPTR);
 
 	return vcpu->arch.walk_mmu->pdptrs[index];
 }
@@ -109,8 +136,8 @@ static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask)
 
 static inline ulong kvm_read_cr3(struct kvm_vcpu *vcpu)
 {
-	if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
-		kvm_x86_ops->decache_cr3(vcpu);
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3))
+		kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_CR3);
 	return vcpu->arch.cr3;
 }
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index b29d00b661ff..cf9177b4a07f 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -557,60 +557,53 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
 			irq->level, irq->trig_mode, dest_map);
 }
 
+static int __pv_send_ipi(unsigned long *ipi_bitmap, struct kvm_apic_map *map,
+			 struct kvm_lapic_irq *irq, u32 min)
+{
+	int i, count = 0;
+	struct kvm_vcpu *vcpu;
+
+	if (min > map->max_apic_id)
+		return 0;
+
+	for_each_set_bit(i, ipi_bitmap,
+		min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) {
+		if (map->phys_map[min + i]) {
+			vcpu = map->phys_map[min + i]->vcpu;
+			count += kvm_apic_set_irq(vcpu, irq, NULL);
+		}
+	}
+
+	return count;
+}
+
 int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
 		    unsigned long ipi_bitmap_high, u32 min,
 		    unsigned long icr, int op_64_bit)
 {
-	int i;
 	struct kvm_apic_map *map;
-	struct kvm_vcpu *vcpu;
 	struct kvm_lapic_irq irq = {0};
 	int cluster_size = op_64_bit ? 64 : 32;
-	int count = 0;
+	int count;
+
+	if (icr & (APIC_DEST_MASK | APIC_SHORT_MASK))
+		return -KVM_EINVAL;
 
 	irq.vector = icr & APIC_VECTOR_MASK;
 	irq.delivery_mode = icr & APIC_MODE_MASK;
 	irq.level = (icr & APIC_INT_ASSERT) != 0;
 	irq.trig_mode = icr & APIC_INT_LEVELTRIG;
 
-	if (icr & APIC_DEST_MASK)
-		return -KVM_EINVAL;
-	if (icr & APIC_SHORT_MASK)
-		return -KVM_EINVAL;
-
 	rcu_read_lock();
 	map = rcu_dereference(kvm->arch.apic_map);
 
-	if (unlikely(!map)) {
-		count = -EOPNOTSUPP;
-		goto out;
-	}
-
-	if (min > map->max_apic_id)
-		goto out;
-	/* Bits above cluster_size are masked in the caller.  */
-	for_each_set_bit(i, &ipi_bitmap_low,
-		min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) {
-		if (map->phys_map[min + i]) {
-			vcpu = map->phys_map[min + i]->vcpu;
-			count += kvm_apic_set_irq(vcpu, &irq, NULL);
-		}
+	count = -EOPNOTSUPP;
+	if (likely(map)) {
+		count = __pv_send_ipi(&ipi_bitmap_low, map, &irq, min);
+		min += cluster_size;
+		count += __pv_send_ipi(&ipi_bitmap_high, map, &irq, min);
 	}
 
-	min += cluster_size;
-
-	if (min > map->max_apic_id)
-		goto out;
-
-	for_each_set_bit(i, &ipi_bitmap_high,
-		min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) {
-		if (map->phys_map[min + i]) {
-			vcpu = map->phys_map[min + i]->vcpu;
-			count += kvm_apic_set_irq(vcpu, &irq, NULL);
-		}
-	}
-
-out:
 	rcu_read_unlock();
 	return count;
 }
@@ -1124,6 +1117,50 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 	return result;
 }
 
+/*
+ * This routine identifies the destination vcpus mask meant to receive the
+ * IOAPIC interrupts. It either uses kvm_apic_map_get_dest_lapic() to find
+ * out the destination vcpus array and set the bitmap or it traverses to
+ * each available vcpu to identify the same.
+ */
+void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq,
+			      unsigned long *vcpu_bitmap)
+{
+	struct kvm_lapic **dest_vcpu = NULL;
+	struct kvm_lapic *src = NULL;
+	struct kvm_apic_map *map;
+	struct kvm_vcpu *vcpu;
+	unsigned long bitmap;
+	int i, vcpu_idx;
+	bool ret;
+
+	rcu_read_lock();
+	map = rcu_dereference(kvm->arch.apic_map);
+
+	ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dest_vcpu,
+					  &bitmap);
+	if (ret) {
+		for_each_set_bit(i, &bitmap, 16) {
+			if (!dest_vcpu[i])
+				continue;
+			vcpu_idx = dest_vcpu[i]->vcpu->vcpu_idx;
+			__set_bit(vcpu_idx, vcpu_bitmap);
+		}
+	} else {
+		kvm_for_each_vcpu(i, vcpu, kvm) {
+			if (!kvm_apic_present(vcpu))
+				continue;
+			if (!kvm_apic_match_dest(vcpu, NULL,
+						 irq->delivery_mode,
+						 irq->dest_id,
+						 irq->dest_mode))
+				continue;
+			__set_bit(i, vcpu_bitmap);
+		}
+	}
+	rcu_read_unlock();
+}
+
 int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
 {
 	return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio;
@@ -2709,7 +2746,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 	 * KVM_MP_STATE_INIT_RECEIVED state), just eat SIPIs
 	 * and leave the INIT pending.
 	 */
-	if (is_smm(vcpu) || kvm_x86_ops->apic_init_signal_blocked(vcpu)) {
+	if (kvm_vcpu_latch_init(vcpu)) {
 		WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED);
 		if (test_bit(KVM_APIC_SIPI, &apic->pending_events))
 			clear_bit(KVM_APIC_SIPI, &apic->pending_events);
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 1f5014852e20..39925afdfcdc 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -226,6 +226,9 @@ bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
 
 void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu);
 
+void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq,
+			      unsigned long *vcpu_bitmap);
+
 bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
 			struct kvm_vcpu **dest_vcpu);
 int kvm_vector_to_index(u32 vector, u32 dest_vcpus,
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 2ce9da58611e..6f92b40d798c 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4395,7 +4395,7 @@ static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3,
 			kvm_make_request(KVM_REQ_LOAD_CR3, vcpu);
 			if (!skip_tlb_flush) {
 				kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
-				kvm_x86_ops->tlb_flush(vcpu, true);
+				kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 			}
 
 			/*
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 3521e2d176f2..3521e2d176f2 100644
--- a/arch/x86/kvm/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 97b21e7fd013..97b21e7fd013 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 46875bbd0419..d5e6d5b3f06f 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -62,8 +62,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event,
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 
-	if (!test_and_set_bit(pmc->idx,
-			      (unsigned long *)&pmu->reprogram_pmi)) {
+	if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
 		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
 		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
 	}
@@ -76,8 +75,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event,
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 
-	if (!test_and_set_bit(pmc->idx,
-			      (unsigned long *)&pmu->reprogram_pmi)) {
+	if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
 		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
 		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
 
@@ -137,7 +135,37 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 	}
 
 	pmc->perf_event = event;
-	clear_bit(pmc->idx, (unsigned long*)&pmc_to_pmu(pmc)->reprogram_pmi);
+	pmc_to_pmu(pmc)->event_count++;
+	clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
+}
+
+static void pmc_pause_counter(struct kvm_pmc *pmc)
+{
+	u64 counter = pmc->counter;
+
+	if (!pmc->perf_event)
+		return;
+
+	/* update counter, reset event value to avoid redundant accumulation */
+	counter += perf_event_pause(pmc->perf_event, true);
+	pmc->counter = counter & pmc_bitmask(pmc);
+}
+
+static bool pmc_resume_counter(struct kvm_pmc *pmc)
+{
+	if (!pmc->perf_event)
+		return false;
+
+	/* recalibrate sample period and check if it's accepted by perf core */
+	if (perf_event_period(pmc->perf_event,
+			(-pmc->counter) & pmc_bitmask(pmc)))
+		return false;
+
+	/* reuse perf_event to serve as pmc_reprogram_counter() does*/
+	perf_event_enable(pmc->perf_event);
+
+	clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
+	return true;
 }
 
 void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
@@ -154,7 +182,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 
 	pmc->eventsel = eventsel;
 
-	pmc_stop_counter(pmc);
+	pmc_pause_counter(pmc);
 
 	if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc))
 		return;
@@ -193,6 +221,12 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	if (type == PERF_TYPE_RAW)
 		config = eventsel & X86_RAW_EVENT_MASK;
 
+	if (pmc->current_config == eventsel && pmc_resume_counter(pmc))
+		return;
+
+	pmc_release_perf_event(pmc);
+
+	pmc->current_config = eventsel;
 	pmc_reprogram_counter(pmc, type, config,
 			      !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
 			      !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
@@ -209,7 +243,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
 	struct kvm_pmu_event_filter *filter;
 	struct kvm *kvm = pmc->vcpu->kvm;
 
-	pmc_stop_counter(pmc);
+	pmc_pause_counter(pmc);
 
 	if (!en_field || !pmc_is_enabled(pmc))
 		return;
@@ -224,6 +258,12 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
 			return;
 	}
 
+	if (pmc->current_config == (u64)ctrl && pmc_resume_counter(pmc))
+		return;
+
+	pmc_release_perf_event(pmc);
+
+	pmc->current_config = (u64)ctrl;
 	pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE,
 			      kvm_x86_ops->pmu_ops->find_fixed_event(idx),
 			      !(en_field & 0x2), /* exclude user */
@@ -253,27 +293,32 @@ EXPORT_SYMBOL_GPL(reprogram_counter);
 void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	u64 bitmask;
 	int bit;
 
-	bitmask = pmu->reprogram_pmi;
-
-	for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) {
+	for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) {
 		struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, bit);
 
 		if (unlikely(!pmc || !pmc->perf_event)) {
-			clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi);
+			clear_bit(bit, pmu->reprogram_pmi);
 			continue;
 		}
 
 		reprogram_counter(pmu, bit);
 	}
+
+	/*
+	 * Unused perf_events are only released if the corresponding MSRs
+	 * weren't accessed during the last vCPU time slice. kvm_arch_sched_in
+	 * triggers KVM_REQ_PMU if cleanup is needed.
+	 */
+	if (unlikely(pmu->need_cleanup))
+		kvm_pmu_cleanup(vcpu);
 }
 
 /* check if idx is a valid index to access PMU */
-int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
+int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 {
-	return kvm_x86_ops->pmu_ops->is_valid_msr_idx(vcpu, idx);
+	return kvm_x86_ops->pmu_ops->is_valid_rdpmc_ecx(vcpu, idx);
 }
 
 bool is_vmware_backdoor_pmc(u32 pmc_idx)
@@ -323,7 +368,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 	if (is_vmware_backdoor_pmc(idx))
 		return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
 
-	pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx, &mask);
+	pmc = kvm_x86_ops->pmu_ops->rdpmc_ecx_to_pmc(vcpu, idx, &mask);
 	if (!pmc)
 		return 1;
 
@@ -339,7 +384,17 @@ void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu)
 
 bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 {
-	return kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr);
+	return kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr) ||
+		kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr);
+}
+
+static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr);
+
+	if (pmc)
+		__set_bit(pmc->idx, pmu->pmc_in_use);
 }
 
 int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
@@ -349,6 +404,7 @@ int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
 
 int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
+	kvm_pmu_mark_pmc_in_use(vcpu, msr_info->index);
 	return kvm_x86_ops->pmu_ops->set_msr(vcpu, msr_info);
 }
 
@@ -376,9 +432,45 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu)
 	memset(pmu, 0, sizeof(*pmu));
 	kvm_x86_ops->pmu_ops->init(vcpu);
 	init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn);
+	pmu->event_count = 0;
+	pmu->need_cleanup = false;
 	kvm_pmu_refresh(vcpu);
 }
 
+static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc)
+{
+	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+
+	if (pmc_is_fixed(pmc))
+		return fixed_ctrl_field(pmu->fixed_ctr_ctrl,
+			pmc->idx - INTEL_PMC_IDX_FIXED) & 0x3;
+
+	return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE;
+}
+
+/* Release perf_events for vPMCs that have been unused for a full time slice.  */
+void kvm_pmu_cleanup(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc = NULL;
+	DECLARE_BITMAP(bitmask, X86_PMC_IDX_MAX);
+	int i;
+
+	pmu->need_cleanup = false;
+
+	bitmap_andnot(bitmask, pmu->all_valid_pmc_idx,
+		      pmu->pmc_in_use, X86_PMC_IDX_MAX);
+
+	for_each_set_bit(i, bitmask, X86_PMC_IDX_MAX) {
+		pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, i);
+
+		if (pmc && pmc->perf_event && !pmc_speculative_in_use(pmc))
+			pmc_stop_counter(pmc);
+	}
+
+	bitmap_zero(pmu->pmc_in_use, X86_PMC_IDX_MAX);
+}
+
 void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
 {
 	kvm_pmu_reset(vcpu);
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 58265f761c3b..7ebb62326c14 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -25,9 +25,10 @@ struct kvm_pmu_ops {
 	unsigned (*find_fixed_event)(int idx);
 	bool (*pmc_is_enabled)(struct kvm_pmc *pmc);
 	struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx);
-	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx,
-					  u64 *mask);
-	int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx);
+	struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu,
+		unsigned int idx, u64 *mask);
+	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr);
+	int (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx);
 	bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr);
 	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 	int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
@@ -55,12 +56,21 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
 	return counter & pmc_bitmask(pmc);
 }
 
-static inline void pmc_stop_counter(struct kvm_pmc *pmc)
+static inline void pmc_release_perf_event(struct kvm_pmc *pmc)
 {
 	if (pmc->perf_event) {
-		pmc->counter = pmc_read_counter(pmc);
 		perf_event_release_kernel(pmc->perf_event);
 		pmc->perf_event = NULL;
+		pmc->current_config = 0;
+		pmc_to_pmu(pmc)->event_count--;
+	}
+}
+
+static inline void pmc_stop_counter(struct kvm_pmc *pmc)
+{
+	if (pmc->perf_event) {
+		pmc->counter = pmc_read_counter(pmc);
+		pmc_release_perf_event(pmc);
 	}
 }
 
@@ -79,6 +89,12 @@ static inline bool pmc_is_enabled(struct kvm_pmc *pmc)
 	return kvm_x86_ops->pmu_ops->pmc_is_enabled(pmc);
 }
 
+static inline bool kvm_valid_perf_global_ctrl(struct kvm_pmu *pmu,
+						 u64 data)
+{
+	return !(pmu->global_ctrl_mask & data);
+}
+
 /* returns general purpose PMC with the specified MSR. Note that it can be
  * used for both PERFCTRn and EVNTSELn; that is why it accepts base as a
  * paramenter to tell them apart.
@@ -110,13 +126,14 @@ void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx);
 void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu);
 void kvm_pmu_handle_event(struct kvm_vcpu *vcpu);
 int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
-int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx);
+int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx);
 bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr);
 int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
 void kvm_pmu_refresh(struct kvm_vcpu *vcpu);
 void kvm_pmu_reset(struct kvm_vcpu *vcpu);
 void kvm_pmu_init(struct kvm_vcpu *vcpu);
+void kvm_pmu_cleanup(struct kvm_vcpu *vcpu);
 void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
 int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp);
 
diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c
index c8388389a3b0..ce0b10fe5e2b 100644
--- a/arch/x86/kvm/pmu_amd.c
+++ b/arch/x86/kvm/pmu_amd.c
@@ -174,7 +174,7 @@ static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
 }
 
 /* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */
-static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
+static int amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 
@@ -184,7 +184,8 @@ static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
 }
 
 /* idx is the ECX register of RDPMC instruction */
-static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *mask)
+static struct kvm_pmc *amd_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
+	unsigned int idx, u64 *mask)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *counters;
@@ -199,13 +200,19 @@ static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u
 
 static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 {
+	/* All MSRs refer to exactly one PMC, so msr_idx_to_pmc is enough.  */
+	return false;
+}
+
+static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr)
+{
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	int ret = false;
+	struct kvm_pmc *pmc;
 
-	ret = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER) ||
-		get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL);
+	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
+	pmc = pmc ? pmc : get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL);
 
-	return ret;
+	return pmc;
 }
 
 static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
@@ -272,6 +279,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
 	pmu->nr_arch_fixed_counters = 0;
 	pmu->global_status = 0;
+	bitmap_set(pmu->all_valid_pmc_idx, 0, pmu->nr_arch_gp_counters);
 }
 
 static void amd_pmu_init(struct kvm_vcpu *vcpu)
@@ -285,6 +293,7 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu)
 		pmu->gp_counters[i].type = KVM_PMC_GP;
 		pmu->gp_counters[i].vcpu = vcpu;
 		pmu->gp_counters[i].idx = i;
+		pmu->gp_counters[i].current_config = 0;
 	}
 }
 
@@ -306,8 +315,9 @@ struct kvm_pmu_ops amd_pmu_ops = {
 	.find_fixed_event = amd_find_fixed_event,
 	.pmc_is_enabled = amd_pmc_is_enabled,
 	.pmc_idx_to_pmc = amd_pmc_idx_to_pmc,
+	.rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc,
 	.msr_idx_to_pmc = amd_msr_idx_to_pmc,
-	.is_valid_msr_idx = amd_is_valid_msr_idx,
+	.is_valid_rdpmc_ecx = amd_is_valid_rdpmc_ecx,
 	.is_valid_msr = amd_is_valid_msr,
 	.get_msr = amd_pmu_get_msr,
 	.set_msr = amd_pmu_set_msr,
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index c5673bda4b66..362e874297e4 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -38,6 +38,7 @@
 #include <linux/file.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
+#include <linux/rwsem.h>
 
 #include <asm/apic.h>
 #include <asm/perf_event.h>
@@ -418,9 +419,13 @@ enum {
 
 #define VMCB_AVIC_APIC_BAR_MASK		0xFFFFFFFFFF000ULL
 
+static int sev_flush_asids(void);
+static DECLARE_RWSEM(sev_deactivate_lock);
+static DEFINE_MUTEX(sev_bitmap_lock);
 static unsigned int max_sev_asid;
 static unsigned int min_sev_asid;
 static unsigned long *sev_asid_bitmap;
+static unsigned long *sev_reclaim_asid_bitmap;
 #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT)
 
 struct enc_region {
@@ -1235,11 +1240,15 @@ static __init int sev_hardware_setup(void)
 	/* Minimum ASID value that should be used for SEV guest */
 	min_sev_asid = cpuid_edx(0x8000001F);
 
-	/* Initialize SEV ASID bitmap */
+	/* Initialize SEV ASID bitmaps */
 	sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
 	if (!sev_asid_bitmap)
 		return 1;
 
+	sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
+	if (!sev_reclaim_asid_bitmap)
+		return 1;
+
 	status = kmalloc(sizeof(*status), GFP_KERNEL);
 	if (!status)
 		return 1;
@@ -1418,8 +1427,12 @@ static __exit void svm_hardware_unsetup(void)
 {
 	int cpu;
 
-	if (svm_sev_enabled())
+	if (svm_sev_enabled()) {
 		bitmap_free(sev_asid_bitmap);
+		bitmap_free(sev_reclaim_asid_bitmap);
+
+		sev_flush_asids();
+	}
 
 	for_each_possible_cpu(cpu)
 		svm_cpu_uninit(cpu);
@@ -1729,25 +1742,22 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static void __sev_asid_free(int asid)
+static void sev_asid_free(int asid)
 {
 	struct svm_cpu_data *sd;
 	int cpu, pos;
 
+	mutex_lock(&sev_bitmap_lock);
+
 	pos = asid - 1;
-	clear_bit(pos, sev_asid_bitmap);
+	__set_bit(pos, sev_reclaim_asid_bitmap);
 
 	for_each_possible_cpu(cpu) {
 		sd = per_cpu(svm_data, cpu);
 		sd->sev_vmcbs[pos] = NULL;
 	}
-}
 
-static void sev_asid_free(struct kvm *kvm)
-{
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
-
-	__sev_asid_free(sev->asid);
+	mutex_unlock(&sev_bitmap_lock);
 }
 
 static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
@@ -1764,10 +1774,12 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
 
 	/* deactivate handle */
 	data->handle = handle;
+
+	/* Guard DEACTIVATE against WBINVD/DF_FLUSH used in ASID recycling */
+	down_read(&sev_deactivate_lock);
 	sev_guest_deactivate(data, NULL);
+	up_read(&sev_deactivate_lock);
 
-	wbinvd_on_all_cpus();
-	sev_guest_df_flush(NULL);
 	kfree(data);
 
 	decommission = kzalloc(sizeof(*decommission), GFP_KERNEL);
@@ -1916,7 +1928,7 @@ static void sev_vm_destroy(struct kvm *kvm)
 	mutex_unlock(&kvm->lock);
 
 	sev_unbind_asid(kvm, sev->handle);
-	sev_asid_free(kvm);
+	sev_asid_free(sev->asid);
 }
 
 static void avic_vm_destroy(struct kvm *kvm)
@@ -2370,7 +2382,7 @@ static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 		load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
 		break;
 	default:
-		BUG();
+		WARN_ON_ONCE(1);
 	}
 }
 
@@ -2523,10 +2535,6 @@ static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
 {
 }
 
-static void svm_decache_cr3(struct kvm_vcpu *vcpu)
-{
-}
-
 static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 {
 }
@@ -4997,6 +5005,18 @@ static int handle_exit(struct kvm_vcpu *vcpu)
 		return 0;
 	}
 
+#ifdef CONFIG_RETPOLINE
+	if (exit_code == SVM_EXIT_MSR)
+		return msr_interception(svm);
+	else if (exit_code == SVM_EXIT_VINTR)
+		return interrupt_window_interception(svm);
+	else if (exit_code == SVM_EXIT_INTR)
+		return intr_interception(svm);
+	else if (exit_code == SVM_EXIT_HLT)
+		return halt_interception(svm);
+	else if (exit_code == SVM_EXIT_NPF)
+		return npf_interception(svm);
+#endif
 	return svm_exit_handlers[exit_code](svm);
 }
 
@@ -5092,8 +5112,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (svm_nested_virtualize_tpr(vcpu) ||
-	    kvm_vcpu_apicv_active(vcpu))
+	if (svm_nested_virtualize_tpr(vcpu))
 		return;
 
 	clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
@@ -5110,9 +5129,9 @@ static void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
 	return;
 }
 
-static bool svm_get_enable_apicv(struct kvm_vcpu *vcpu)
+static bool svm_get_enable_apicv(struct kvm *kvm)
 {
-	return avic && irqchip_split(vcpu->kvm);
+	return avic && irqchip_split(kvm);
 }
 
 static void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
@@ -5634,7 +5653,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	svm->vmcb->save.cr2 = vcpu->arch.cr2;
 
 	clgi();
-	kvm_load_guest_xcr0(vcpu);
+	kvm_load_guest_xsave_state(vcpu);
 
 	if (lapic_in_kernel(vcpu) &&
 		vcpu->arch.apic->lapic_timer.timer_advance_ns)
@@ -5784,7 +5803,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_before_interrupt(&svm->vcpu);
 
-	kvm_put_guest_xcr0(vcpu);
+	kvm_load_host_xsave_state(vcpu);
 	stgi();
 
 	/* Any pending NMI will happen here */
@@ -5893,6 +5912,9 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
+				    boot_cpu_has(X86_FEATURE_XSAVES);
+
 	/* Update nrips enabled cache */
 	svm->nrips_enabled = !!guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS);
 
@@ -5968,7 +5990,7 @@ static bool svm_mpx_supported(void)
 
 static bool svm_xsaves_supported(void)
 {
-	return false;
+	return boot_cpu_has(X86_FEATURE_XSAVES);
 }
 
 static bool svm_umip_emulated(void)
@@ -6270,18 +6292,73 @@ static int enable_smi_window(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int sev_flush_asids(void)
+{
+	int ret, error;
+
+	/*
+	 * DEACTIVATE will clear the WBINVD indicator causing DF_FLUSH to fail,
+	 * so it must be guarded.
+	 */
+	down_write(&sev_deactivate_lock);
+
+	wbinvd_on_all_cpus();
+	ret = sev_guest_df_flush(&error);
+
+	up_write(&sev_deactivate_lock);
+
+	if (ret)
+		pr_err("SEV: DF_FLUSH failed, ret=%d, error=%#x\n", ret, error);
+
+	return ret;
+}
+
+/* Must be called with the sev_bitmap_lock held */
+static bool __sev_recycle_asids(void)
+{
+	int pos;
+
+	/* Check if there are any ASIDs to reclaim before performing a flush */
+	pos = find_next_bit(sev_reclaim_asid_bitmap,
+			    max_sev_asid, min_sev_asid - 1);
+	if (pos >= max_sev_asid)
+		return false;
+
+	if (sev_flush_asids())
+		return false;
+
+	bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap,
+		   max_sev_asid);
+	bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid);
+
+	return true;
+}
+
 static int sev_asid_new(void)
 {
+	bool retry = true;
 	int pos;
 
+	mutex_lock(&sev_bitmap_lock);
+
 	/*
 	 * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid.
 	 */
+again:
 	pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_sev_asid - 1);
-	if (pos >= max_sev_asid)
+	if (pos >= max_sev_asid) {
+		if (retry && __sev_recycle_asids()) {
+			retry = false;
+			goto again;
+		}
+		mutex_unlock(&sev_bitmap_lock);
 		return -EBUSY;
+	}
+
+	__set_bit(pos, sev_asid_bitmap);
+
+	mutex_unlock(&sev_bitmap_lock);
 
-	set_bit(pos, sev_asid_bitmap);
 	return pos + 1;
 }
 
@@ -6309,7 +6386,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	return 0;
 
 e_free:
-	__sev_asid_free(asid);
+	sev_asid_free(asid);
 	return ret;
 }
 
@@ -6319,12 +6396,6 @@ static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
 	int asid = sev_get_asid(kvm);
 	int ret;
 
-	wbinvd_on_all_cpus();
-
-	ret = sev_guest_df_flush(error);
-	if (ret)
-		return ret;
-
 	data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT);
 	if (!data)
 		return -ENOMEM;
@@ -7214,7 +7285,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.get_cpl = svm_get_cpl,
 	.get_cs_db_l_bits = kvm_get_cs_db_l_bits,
 	.decache_cr0_guest_bits = svm_decache_cr0_guest_bits,
-	.decache_cr3 = svm_decache_cr3,
 	.decache_cr4_guest_bits = svm_decache_cr4_guest_bits,
 	.set_cr0 = svm_set_cr0,
 	.set_cr3 = svm_set_cr3,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 0e7c9301fe86..4aea7d304beb 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -10,6 +10,7 @@
 #include "hyperv.h"
 #include "mmu.h"
 #include "nested.h"
+#include "pmu.h"
 #include "trace.h"
 #include "x86.h"
 
@@ -27,6 +28,16 @@ module_param(nested_early_check, bool, S_IRUGO);
 	failed;								\
 })
 
+#define SET_MSR_OR_WARN(vcpu, idx, data)				\
+({									\
+	bool failed = kvm_set_msr(vcpu, idx, data);			\
+	if (failed)							\
+		pr_warn_ratelimited(					\
+				"%s cannot write MSR (0x%x, 0x%llx)\n",	\
+				__func__, idx, data);			\
+	failed;								\
+})
+
 /*
  * Hyper-V requires all of these, so mark them as supported even though
  * they are just treated the same as all-context.
@@ -257,7 +268,7 @@ static void free_nested(struct kvm_vcpu *vcpu)
 	vmx->nested.cached_shadow_vmcs12 = NULL;
 	/* Unpin physical memory we referred to in the vmcs02 */
 	if (vmx->nested.apic_access_page) {
-		kvm_release_page_dirty(vmx->nested.apic_access_page);
+		kvm_release_page_clean(vmx->nested.apic_access_page);
 		vmx->nested.apic_access_page = NULL;
 	}
 	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
@@ -929,6 +940,57 @@ fail:
 	return i + 1;
 }
 
+static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu,
+					    u32 msr_index,
+					    u64 *data)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	/*
+	 * If the L0 hypervisor stored a more accurate value for the TSC that
+	 * does not include the time taken for emulation of the L2->L1
+	 * VM-exit in L0, use the more accurate value.
+	 */
+	if (msr_index == MSR_IA32_TSC) {
+		int index = vmx_find_msr_index(&vmx->msr_autostore.guest,
+					       MSR_IA32_TSC);
+
+		if (index >= 0) {
+			u64 val = vmx->msr_autostore.guest.val[index].value;
+
+			*data = kvm_read_l1_tsc(vcpu, val);
+			return true;
+		}
+	}
+
+	if (kvm_get_msr(vcpu, msr_index, data)) {
+		pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__,
+			msr_index);
+		return false;
+	}
+	return true;
+}
+
+static bool read_and_check_msr_entry(struct kvm_vcpu *vcpu, u64 gpa, int i,
+				     struct vmx_msr_entry *e)
+{
+	if (kvm_vcpu_read_guest(vcpu,
+				gpa + i * sizeof(*e),
+				e, 2 * sizeof(u32))) {
+		pr_debug_ratelimited(
+			"%s cannot read MSR entry (%u, 0x%08llx)\n",
+			__func__, i, gpa + i * sizeof(*e));
+		return false;
+	}
+	if (nested_vmx_store_msr_check(vcpu, e)) {
+		pr_debug_ratelimited(
+			"%s check failed (%u, 0x%x, 0x%x)\n",
+			__func__, i, e->index, e->reserved);
+		return false;
+	}
+	return true;
+}
+
 static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 {
 	u64 data;
@@ -940,26 +1002,12 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 		if (unlikely(i >= max_msr_list_size))
 			return -EINVAL;
 
-		if (kvm_vcpu_read_guest(vcpu,
-					gpa + i * sizeof(e),
-					&e, 2 * sizeof(u32))) {
-			pr_debug_ratelimited(
-				"%s cannot read MSR entry (%u, 0x%08llx)\n",
-				__func__, i, gpa + i * sizeof(e));
+		if (!read_and_check_msr_entry(vcpu, gpa, i, &e))
 			return -EINVAL;
-		}
-		if (nested_vmx_store_msr_check(vcpu, &e)) {
-			pr_debug_ratelimited(
-				"%s check failed (%u, 0x%x, 0x%x)\n",
-				__func__, i, e.index, e.reserved);
-			return -EINVAL;
-		}
-		if (kvm_get_msr(vcpu, e.index, &data)) {
-			pr_debug_ratelimited(
-				"%s cannot read MSR (%u, 0x%x)\n",
-				__func__, i, e.index);
+
+		if (!nested_vmx_get_vmexit_msr_value(vcpu, e.index, &data))
 			return -EINVAL;
-		}
+
 		if (kvm_vcpu_write_guest(vcpu,
 					 gpa + i * sizeof(e) +
 					     offsetof(struct vmx_msr_entry, value),
@@ -973,6 +1021,60 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 	return 0;
 }
 
+static bool nested_msr_store_list_has_msr(struct kvm_vcpu *vcpu, u32 msr_index)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	u32 count = vmcs12->vm_exit_msr_store_count;
+	u64 gpa = vmcs12->vm_exit_msr_store_addr;
+	struct vmx_msr_entry e;
+	u32 i;
+
+	for (i = 0; i < count; i++) {
+		if (!read_and_check_msr_entry(vcpu, gpa, i, &e))
+			return false;
+
+		if (e.index == msr_index)
+			return true;
+	}
+	return false;
+}
+
+static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu,
+					   u32 msr_index)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vmx_msrs *autostore = &vmx->msr_autostore.guest;
+	bool in_vmcs12_store_list;
+	int msr_autostore_index;
+	bool in_autostore_list;
+	int last;
+
+	msr_autostore_index = vmx_find_msr_index(autostore, msr_index);
+	in_autostore_list = msr_autostore_index >= 0;
+	in_vmcs12_store_list = nested_msr_store_list_has_msr(vcpu, msr_index);
+
+	if (in_vmcs12_store_list && !in_autostore_list) {
+		if (autostore->nr == NR_LOADSTORE_MSRS) {
+			/*
+			 * Emulated VMEntry does not fail here.  Instead a less
+			 * accurate value will be returned by
+			 * nested_vmx_get_vmexit_msr_value() using kvm_get_msr()
+			 * instead of reading the value from the vmcs02 VMExit
+			 * MSR-store area.
+			 */
+			pr_warn_ratelimited(
+				"Not enough msr entries in msr_autostore.  Can't add msr %x\n",
+				msr_index);
+			return;
+		}
+		last = autostore->nr++;
+		autostore->val[last].index = msr_index;
+	} else if (!in_vmcs12_store_list && in_autostore_list) {
+		last = --autostore->nr;
+		autostore->val[msr_autostore_index] = autostore->val[last];
+	}
+}
+
 static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	unsigned long invalid_mask;
@@ -1012,7 +1114,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne
 		kvm_mmu_new_cr3(vcpu, cr3, false);
 
 	vcpu->arch.cr3 = cr3;
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
 
 	kvm_init_mmu(vcpu, false);
 
@@ -1024,7 +1126,9 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne
  * populated by L2 differently than TLB entries populated
  * by L1.
  *
- * If L1 uses EPT, then TLB entries are tagged with different EPTP.
+ * If L0 uses EPT, L1 and L2 run with different EPTP because
+ * guest_mode is part of kvm_mmu_page_role. Thus, TLB entries
+ * are tagged with different EPTP.
  *
  * If L1 uses VPID and we allocated a vpid02, TLB entries are tagged
  * with different VPID (L1 entries are tagged with vmx->vpid
@@ -1034,7 +1138,7 @@ static bool nested_has_guest_tlb_tag(struct kvm_vcpu *vcpu)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 
-	return nested_cpu_has_ept(vmcs12) ||
+	return enable_ept ||
 	       (nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02);
 }
 
@@ -2018,7 +2122,7 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx)
 	 * addresses are constant (for vmcs02), the counts can change based
 	 * on L2's behavior, e.g. switching to/from long mode.
 	 */
-	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
+	vmcs_write64(VM_EXIT_MSR_STORE_ADDR, __pa(vmx->msr_autostore.guest.val));
 	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
 	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
 
@@ -2073,6 +2177,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 	exec_control &= ~CPU_BASED_TPR_SHADOW;
 	exec_control |= vmcs12->cpu_based_vm_exec_control;
 
+	vmx->nested.l1_tpr_threshold = -1;
 	if (exec_control & CPU_BASED_TPR_SHADOW)
 		vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
 #ifdef CONFIG_X86_64
@@ -2285,6 +2390,13 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 		vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3);
 	}
 
+	/*
+	 * Make sure the msr_autostore list is up to date before we set the
+	 * count in the vmcs02.
+	 */
+	prepare_vmx_msr_autostore_list(&vmx->vcpu, MSR_IA32_TSC);
+
+	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, vmx->msr_autostore.guest.nr);
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
 
@@ -2381,9 +2493,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	if (nested_cpu_has_ept(vmcs12))
 		nested_ept_init_mmu_context(vcpu);
-	else if (nested_cpu_has2(vmcs12,
-				 SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
-		vmx_flush_tlb(vcpu, true);
 
 	/*
 	 * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those
@@ -2418,6 +2527,16 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 				entry_failure_code))
 		return -EINVAL;
 
+	/*
+	 * Immediately write vmcs02.GUEST_CR3.  It will be propagated to vmcs12
+	 * on nested VM-Exit, which can occur without actually running L2 and
+	 * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with
+	 * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the
+	 * transition to HLT instead of running L2.
+	 */
+	if (enable_ept)
+		vmcs_writel(GUEST_CR3, vmcs12->guest_cr3);
+
 	/* Late preparation of GUEST_PDPTRs now that EFER and CRs are set. */
 	if (load_guest_pdptrs_vmcs12 && nested_cpu_has_ept(vmcs12) &&
 	    is_pae_paging(vcpu)) {
@@ -2430,6 +2549,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	if (!enable_ept)
 		vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
 
+	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
+	    SET_MSR_OR_WARN(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
+			    vmcs12->guest_ia32_perf_global_ctrl))
+		return -EINVAL;
+
 	kvm_rsp_write(vcpu, vmcs12->guest_rsp);
 	kvm_rip_write(vcpu, vmcs12->guest_rip);
 	return 0;
@@ -2664,6 +2788,11 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 	    CC(!kvm_pat_valid(vmcs12->host_ia32_pat)))
 		return -EINVAL;
 
+	if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) &&
+	    CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu),
+					   vmcs12->host_ia32_perf_global_ctrl)))
+		return -EINVAL;
+
 #ifdef CONFIG_X86_64
 	ia32e = !!(vcpu->arch.efer & EFER_LMA);
 #else
@@ -2779,6 +2908,11 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 	}
 
+	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
+	    CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu),
+					   vmcs12->guest_ia32_perf_global_ctrl)))
+		return -EINVAL;
+
 	/*
 	 * If the load IA32_EFER VM-entry control is 1, the following checks
 	 * are performed on the field for the IA32_EFER MSR:
@@ -2933,7 +3067,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 		 * to it so we can release it later.
 		 */
 		if (vmx->nested.apic_access_page) { /* shouldn't happen */
-			kvm_release_page_dirty(vmx->nested.apic_access_page);
+			kvm_release_page_clean(vmx->nested.apic_access_page);
 			vmx->nested.apic_access_page = NULL;
 		}
 		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr);
@@ -3461,6 +3595,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 		test_bit(KVM_APIC_INIT, &apic->pending_events)) {
 		if (block_nested_events)
 			return -EBUSY;
+		clear_bit(KVM_APIC_INIT, &apic->pending_events);
 		nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0);
 		return 0;
 	}
@@ -3864,8 +3999,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 		vcpu->arch.pat = vmcs12->host_ia32_pat;
 	}
 	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
-		vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL,
-			vmcs12->host_ia32_perf_global_ctrl);
+		SET_MSR_OR_WARN(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
+				vmcs12->host_ia32_perf_global_ctrl);
 
 	/* Set L1 segment info according to Intel SDM
 	    27.5.2 Loading Host Segment and Descriptor-Table Registers */
@@ -3984,7 +4119,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
 
 	nested_ept_uninit_mmu_context(vcpu);
 	vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
 
 	/*
 	 * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
@@ -4112,6 +4247,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
 	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+	if (vmx->nested.l1_tpr_threshold != -1)
+		vmcs_write32(TPR_THRESHOLD, vmx->nested.l1_tpr_threshold);
 
 	if (kvm_has_tsc_control)
 		decache_tsc_multiplier(vmx);
@@ -4119,15 +4256,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	if (vmx->nested.change_vmcs01_virtual_apic_mode) {
 		vmx->nested.change_vmcs01_virtual_apic_mode = false;
 		vmx_set_virtual_apic_mode(vcpu);
-	} else if (!nested_cpu_has_ept(vmcs12) &&
-		   nested_cpu_has2(vmcs12,
-				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
-		vmx_flush_tlb(vcpu, true);
 	}
 
 	/* Unpin physical memory we referred to in vmcs02 */
 	if (vmx->nested.apic_access_page) {
-		kvm_release_page_dirty(vmx->nested.apic_access_page);
+		kvm_release_page_clean(vmx->nested.apic_access_page);
 		vmx->nested.apic_access_page = NULL;
 	}
 	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
@@ -4327,6 +4460,27 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 	return 0;
 }
 
+void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx;
+
+	if (!nested_vmx_allowed(vcpu))
+		return;
+
+	vmx = to_vmx(vcpu);
+	if (kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL)) {
+		vmx->nested.msrs.entry_ctls_high |=
+				VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+		vmx->nested.msrs.exit_ctls_high |=
+				VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
+	} else {
+		vmx->nested.msrs.entry_ctls_high &=
+				~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+		vmx->nested.msrs.exit_ctls_high &=
+				~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+	}
+}
+
 static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer)
 {
 	gva_t gva;
@@ -5766,7 +5920,7 @@ error_guest_mode:
 	return ret;
 }
 
-void nested_vmx_vcpu_setup(void)
+void nested_vmx_set_vmcs_shadowing_bitmap(void)
 {
 	if (enable_shadow_vmcs) {
 		vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap));
@@ -6047,23 +6201,23 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
 		init_vmcs_shadow_fields();
 	}
 
-	exit_handlers[EXIT_REASON_VMCLEAR]	= handle_vmclear,
-	exit_handlers[EXIT_REASON_VMLAUNCH]	= handle_vmlaunch,
-	exit_handlers[EXIT_REASON_VMPTRLD]	= handle_vmptrld,
-	exit_handlers[EXIT_REASON_VMPTRST]	= handle_vmptrst,
-	exit_handlers[EXIT_REASON_VMREAD]	= handle_vmread,
-	exit_handlers[EXIT_REASON_VMRESUME]	= handle_vmresume,
-	exit_handlers[EXIT_REASON_VMWRITE]	= handle_vmwrite,
-	exit_handlers[EXIT_REASON_VMOFF]	= handle_vmoff,
-	exit_handlers[EXIT_REASON_VMON]		= handle_vmon,
-	exit_handlers[EXIT_REASON_INVEPT]	= handle_invept,
-	exit_handlers[EXIT_REASON_INVVPID]	= handle_invvpid,
-	exit_handlers[EXIT_REASON_VMFUNC]	= handle_vmfunc,
+	exit_handlers[EXIT_REASON_VMCLEAR]	= handle_vmclear;
+	exit_handlers[EXIT_REASON_VMLAUNCH]	= handle_vmlaunch;
+	exit_handlers[EXIT_REASON_VMPTRLD]	= handle_vmptrld;
+	exit_handlers[EXIT_REASON_VMPTRST]	= handle_vmptrst;
+	exit_handlers[EXIT_REASON_VMREAD]	= handle_vmread;
+	exit_handlers[EXIT_REASON_VMRESUME]	= handle_vmresume;
+	exit_handlers[EXIT_REASON_VMWRITE]	= handle_vmwrite;
+	exit_handlers[EXIT_REASON_VMOFF]	= handle_vmoff;
+	exit_handlers[EXIT_REASON_VMON]		= handle_vmon;
+	exit_handlers[EXIT_REASON_INVEPT]	= handle_invept;
+	exit_handlers[EXIT_REASON_INVVPID]	= handle_invvpid;
+	exit_handlers[EXIT_REASON_VMFUNC]	= handle_vmfunc;
 
 	kvm_x86_ops->check_nested_events = vmx_check_nested_events;
 	kvm_x86_ops->get_nested_state = vmx_get_nested_state;
 	kvm_x86_ops->set_nested_state = vmx_set_nested_state;
-	kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages,
+	kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages;
 	kvm_x86_ops->nested_enable_evmcs = nested_enable_evmcs;
 	kvm_x86_ops->nested_get_evmcs_version = nested_get_evmcs_version;
 
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index 6280f33e5fa6..fc874d4ead0f 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -21,7 +21,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
 				bool apicv);
 void nested_vmx_hardware_unsetup(void);
 __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
-void nested_vmx_vcpu_setup(void);
+void nested_vmx_set_vmcs_shadowing_bitmap(void);
 void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu);
 enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 						     bool from_vmentry);
@@ -33,6 +33,7 @@ int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata);
 int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 			u32 vmx_instruction_info, bool wr, int len, gva_t *ret);
+void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu);
 
 static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
 {
@@ -256,7 +257,7 @@ static inline bool fixed_bits_valid(u64 val, u64 fixed0, u64 fixed1)
 	return ((val & fixed1) | fixed0) == val;
 }
 
-static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
+static inline bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0;
 	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1;
@@ -270,7 +271,7 @@ static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
 	return fixed_bits_valid(val, fixed0, fixed1);
 }
 
-static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
+static inline bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0;
 	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1;
@@ -278,7 +279,7 @@ static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
 	return fixed_bits_valid(val, fixed0, fixed1);
 }
 
-static bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val)
+static inline bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr4_fixed0;
 	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr4_fixed1;
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 3e9c059099e9..7023138b1cb0 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -15,6 +15,7 @@
 #include "x86.h"
 #include "cpuid.h"
 #include "lapic.h"
+#include "nested.h"
 #include "pmu.h"
 
 static struct kvm_event_hw_type_mapping intel_arch_events[] = {
@@ -46,6 +47,7 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
 		if (old_ctrl == new_ctrl)
 			continue;
 
+		__set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use);
 		reprogram_fixed_counter(pmc, new_ctrl, i);
 	}
 
@@ -111,7 +113,7 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
 }
 
 /* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */
-static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
+static int intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	bool fixed = idx & (1u << 30);
@@ -122,8 +124,8 @@ static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
 		(fixed && idx >= pmu->nr_arch_fixed_counters);
 }
 
-static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu,
-					    unsigned idx, u64 *mask)
+static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
+					    unsigned int idx, u64 *mask)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	bool fixed = idx & (1u << 30);
@@ -162,6 +164,18 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 	return ret;
 }
 
+static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc;
+
+	pmc = get_fixed_pmc(pmu, msr);
+	pmc = pmc ? pmc : get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0);
+	pmc = pmc ? pmc : get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0);
+
+	return pmc;
+}
+
 static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -223,7 +237,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_CORE_PERF_GLOBAL_CTRL:
 		if (pmu->global_ctrl == data)
 			return 0;
-		if (!(data & pmu->global_ctrl_mask)) {
+		if (kvm_valid_perf_global_ctrl(pmu, data)) {
 			global_ctrl_changed(pmu, data);
 			return 0;
 		}
@@ -317,6 +331,13 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	    (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
 	    (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
 		pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED;
+
+	bitmap_set(pmu->all_valid_pmc_idx,
+		0, pmu->nr_arch_gp_counters);
+	bitmap_set(pmu->all_valid_pmc_idx,
+		INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters);
+
+	nested_vmx_pmu_entry_exit_ctls_update(vcpu);
 }
 
 static void intel_pmu_init(struct kvm_vcpu *vcpu)
@@ -328,12 +349,14 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
 		pmu->gp_counters[i].type = KVM_PMC_GP;
 		pmu->gp_counters[i].vcpu = vcpu;
 		pmu->gp_counters[i].idx = i;
+		pmu->gp_counters[i].current_config = 0;
 	}
 
 	for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) {
 		pmu->fixed_counters[i].type = KVM_PMC_FIXED;
 		pmu->fixed_counters[i].vcpu = vcpu;
 		pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED;
+		pmu->fixed_counters[i].current_config = 0;
 	}
 }
 
@@ -366,8 +389,9 @@ struct kvm_pmu_ops intel_pmu_ops = {
 	.find_fixed_event = intel_find_fixed_event,
 	.pmc_is_enabled = intel_pmc_is_enabled,
 	.pmc_idx_to_pmc = intel_pmc_idx_to_pmc,
+	.rdpmc_ecx_to_pmc = intel_rdpmc_ecx_to_pmc,
 	.msr_idx_to_pmc = intel_msr_idx_to_pmc,
-	.is_valid_msr_idx = intel_is_valid_msr_idx,
+	.is_valid_rdpmc_ecx = intel_is_valid_rdpmc_ecx,
 	.is_valid_msr = intel_is_valid_msr,
 	.get_msr = intel_pmu_get_msr,
 	.set_msr = intel_pmu_set_msr,
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 04a8212704c1..d175429c91b0 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -106,8 +106,6 @@ module_param(enable_apicv, bool, S_IRUGO);
 static bool __read_mostly nested = 1;
 module_param(nested, bool, S_IRUGO);
 
-static u64 __read_mostly host_xss;
-
 bool __read_mostly enable_pml = 1;
 module_param_named(pml, enable_pml, bool, S_IRUGO);
 
@@ -450,6 +448,7 @@ const u32 vmx_msr_index[] = {
 	MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
 #endif
 	MSR_EFER, MSR_TSC_AUX, MSR_STAR,
+	MSR_IA32_TSX_CTRL,
 };
 
 #if IS_ENABLED(CONFIG_HYPERV)
@@ -638,6 +637,23 @@ struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr)
 	return NULL;
 }
 
+static int vmx_set_guest_msr(struct vcpu_vmx *vmx, struct shared_msr_entry *msr, u64 data)
+{
+	int ret = 0;
+
+	u64 old_msr_data = msr->data;
+	msr->data = data;
+	if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
+		preempt_disable();
+		ret = kvm_set_shared_msr(msr->index, msr->data,
+					 msr->mask);
+		preempt_enable();
+		if (ret)
+			msr->data = old_msr_data;
+	}
+	return ret;
+}
+
 void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs)
 {
 	vmcs_clear(loaded_vmcs->vmcs);
@@ -726,8 +742,8 @@ static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg,
 	bool ret;
 	u32 mask = 1 << (seg * SEG_FIELD_NR + field);
 
-	if (!(vmx->vcpu.arch.regs_avail & (1 << VCPU_EXREG_SEGMENTS))) {
-		vmx->vcpu.arch.regs_avail |= (1 << VCPU_EXREG_SEGMENTS);
+	if (!kvm_register_is_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS)) {
+		kvm_register_mark_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS);
 		vmx->segment_cache.bitmask = 0;
 	}
 	ret = vmx->segment_cache.bitmask & mask;
@@ -835,7 +851,7 @@ static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 	vm_exit_controls_clearbit(vmx, exit);
 }
 
-static int find_msr(struct vmx_msrs *m, unsigned int msr)
+int vmx_find_msr_index(struct vmx_msrs *m, u32 msr)
 {
 	unsigned int i;
 
@@ -869,7 +885,7 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 		}
 		break;
 	}
-	i = find_msr(&m->guest, msr);
+	i = vmx_find_msr_index(&m->guest, msr);
 	if (i < 0)
 		goto skip_guest;
 	--m->guest.nr;
@@ -877,7 +893,7 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
 
 skip_guest:
-	i = find_msr(&m->host, msr);
+	i = vmx_find_msr_index(&m->host, msr);
 	if (i < 0)
 		return;
 
@@ -936,12 +952,12 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 	}
 
-	i = find_msr(&m->guest, msr);
+	i = vmx_find_msr_index(&m->guest, msr);
 	if (!entry_only)
-		j = find_msr(&m->host, msr);
+		j = vmx_find_msr_index(&m->host, msr);
 
-	if ((i < 0 && m->guest.nr == NR_AUTOLOAD_MSRS) ||
-		(j < 0 &&  m->host.nr == NR_AUTOLOAD_MSRS)) {
+	if ((i < 0 && m->guest.nr == NR_LOADSTORE_MSRS) ||
+		(j < 0 &&  m->host.nr == NR_LOADSTORE_MSRS)) {
 		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
@@ -1418,35 +1434,44 @@ static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu);
 
 unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long rflags, save_rflags;
 
-	if (!test_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail)) {
-		__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_RFLAGS)) {
+		kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS);
 		rflags = vmcs_readl(GUEST_RFLAGS);
-		if (to_vmx(vcpu)->rmode.vm86_active) {
+		if (vmx->rmode.vm86_active) {
 			rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
-			save_rflags = to_vmx(vcpu)->rmode.save_rflags;
+			save_rflags = vmx->rmode.save_rflags;
 			rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
 		}
-		to_vmx(vcpu)->rflags = rflags;
+		vmx->rflags = rflags;
 	}
-	return to_vmx(vcpu)->rflags;
+	return vmx->rflags;
 }
 
 void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
-	unsigned long old_rflags = vmx_get_rflags(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long old_rflags;
 
-	__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
-	to_vmx(vcpu)->rflags = rflags;
-	if (to_vmx(vcpu)->rmode.vm86_active) {
-		to_vmx(vcpu)->rmode.save_rflags = rflags;
+	if (enable_unrestricted_guest) {
+		kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS);
+		vmx->rflags = rflags;
+		vmcs_writel(GUEST_RFLAGS, rflags);
+		return;
+	}
+
+	old_rflags = vmx_get_rflags(vcpu);
+	vmx->rflags = rflags;
+	if (vmx->rmode.vm86_active) {
+		vmx->rmode.save_rflags = rflags;
 		rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
 	}
 	vmcs_writel(GUEST_RFLAGS, rflags);
 
-	if ((old_rflags ^ to_vmx(vcpu)->rflags) & X86_EFLAGS_VM)
-		to_vmx(vcpu)->emulation_required = emulation_required(vcpu);
+	if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM)
+		vmx->emulation_required = emulation_required(vcpu);
 }
 
 u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
@@ -1683,6 +1708,9 @@ static void setup_msrs(struct vcpu_vmx *vmx)
 	index = __find_msr_index(vmx, MSR_TSC_AUX);
 	if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP))
 		move_msr_up(vmx, index, save_nmsrs++);
+	index = __find_msr_index(vmx, MSR_IA32_TSX_CTRL);
+	if (index >= 0)
+		move_msr_up(vmx, index, save_nmsrs++);
 
 	vmx->save_nmsrs = save_nmsrs;
 	vmx->guest_msrs_ready = false;
@@ -1782,6 +1810,11 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 #endif
 	case MSR_EFER:
 		return kvm_get_msr_common(vcpu, msr_info);
+	case MSR_IA32_TSX_CTRL:
+		if (!msr_info->host_initiated &&
+		    !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR))
+			return 1;
+		goto find_shared_msr;
 	case MSR_IA32_UMWAIT_CONTROL:
 		if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx))
 			return 1;
@@ -1826,14 +1859,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		return vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index,
 				       &msr_info->data);
-	case MSR_IA32_XSS:
-		if (!vmx_xsaves_supported() ||
-		    (!msr_info->host_initiated &&
-		     !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-		       guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))))
-			return 1;
-		msr_info->data = vcpu->arch.ia32_xss;
-		break;
 	case MSR_IA32_RTIT_CTL:
 		if (pt_mode != PT_MODE_HOST_GUEST)
 			return 1;
@@ -1884,8 +1909,9 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
 			return 1;
-		/* Else, falls through */
+		goto find_shared_msr;
 	default:
+	find_shared_msr:
 		msr = find_msr_entry(vmx, msr_info->index);
 		if (msr) {
 			msr_info->data = msr->data;
@@ -2001,6 +2027,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 					      MSR_IA32_SPEC_CTRL,
 					      MSR_TYPE_RW);
 		break;
+	case MSR_IA32_TSX_CTRL:
+		if (!msr_info->host_initiated &&
+		    !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR))
+			return 1;
+		if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR))
+			return 1;
+		goto find_shared_msr;
 	case MSR_IA32_PRED_CMD:
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
@@ -2069,25 +2102,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!nested_vmx_allowed(vcpu))
 			return 1;
 		return vmx_set_vmx_msr(vcpu, msr_index, data);
-	case MSR_IA32_XSS:
-		if (!vmx_xsaves_supported() ||
-		    (!msr_info->host_initiated &&
-		     !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-		       guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))))
-			return 1;
-		/*
-		 * The only supported bit as of Skylake is bit 8, but
-		 * it is not supported on KVM.
-		 */
-		if (data != 0)
-			return 1;
-		vcpu->arch.ia32_xss = data;
-		if (vcpu->arch.ia32_xss != host_xss)
-			add_atomic_switch_msr(vmx, MSR_IA32_XSS,
-				vcpu->arch.ia32_xss, host_xss, false);
-		else
-			clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
-		break;
 	case MSR_IA32_RTIT_CTL:
 		if ((pt_mode != PT_MODE_HOST_GUEST) ||
 			vmx_rtit_ctl_check(vcpu, data) ||
@@ -2152,23 +2166,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		/* Check reserved bit, higher 32 bits should be zero */
 		if ((data >> 32) != 0)
 			return 1;
-		/* Else, falls through */
+		goto find_shared_msr;
+
 	default:
+	find_shared_msr:
 		msr = find_msr_entry(vmx, msr_index);
-		if (msr) {
-			u64 old_msr_data = msr->data;
-			msr->data = data;
-			if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
-				preempt_disable();
-				ret = kvm_set_shared_msr(msr->index, msr->data,
-							 msr->mask);
-				preempt_enable();
-				if (ret)
-					msr->data = old_msr_data;
-			}
-			break;
-		}
-		ret = kvm_set_msr_common(vcpu, msr_info);
+		if (msr)
+			ret = vmx_set_guest_msr(vmx, msr, data);
+		else
+			ret = kvm_set_msr_common(vcpu, msr_info);
 	}
 
 	return ret;
@@ -2176,7 +2182,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 {
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, reg);
+
 	switch (reg) {
 	case VCPU_REGS_RSP:
 		vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP);
@@ -2188,7 +2195,12 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 		if (enable_ept)
 			ept_save_pdptrs(vcpu);
 		break;
+	case VCPU_EXREG_CR3:
+		if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu)))
+			vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+		break;
 	default:
+		WARN_ON_ONCE(1);
 		break;
 	}
 }
@@ -2859,13 +2871,6 @@ static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
 	vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits;
 }
 
-static void vmx_decache_cr3(struct kvm_vcpu *vcpu)
-{
-	if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu)))
-		vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
-}
-
 static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 {
 	ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits;
@@ -2878,8 +2883,7 @@ static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
 
-	if (!test_bit(VCPU_EXREG_PDPTR,
-		      (unsigned long *)&vcpu->arch.regs_dirty))
+	if (!kvm_register_is_dirty(vcpu, VCPU_EXREG_PDPTR))
 		return;
 
 	if (is_pae_paging(vcpu)) {
@@ -2901,10 +2905,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu)
 		mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
 	}
 
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_avail);
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_dirty);
+	kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR);
 }
 
 static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
@@ -2913,8 +2914,8 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
-		vmx_decache_cr3(vcpu);
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3))
+		vmx_cache_reg(vcpu, VCPU_EXREG_CR3);
 	if (!(cr0 & X86_CR0_PG)) {
 		/* From paging/starting to nonpaging */
 		exec_controls_setbit(vmx, CPU_BASED_CR3_LOAD_EXITING |
@@ -2995,6 +2996,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa)
 void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
 	struct kvm *kvm = vcpu->kvm;
+	bool update_guest_cr3 = true;
 	unsigned long guest_cr3;
 	u64 eptp;
 
@@ -3011,15 +3013,20 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 			spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
 		}
 
-		if (enable_unrestricted_guest || is_paging(vcpu) ||
-		    is_guest_mode(vcpu))
-			guest_cr3 = kvm_read_cr3(vcpu);
-		else
+		/* Loading vmcs02.GUEST_CR3 is handled by nested VM-Enter. */
+		if (is_guest_mode(vcpu))
+			update_guest_cr3 = false;
+		else if (!enable_unrestricted_guest && !is_paging(vcpu))
 			guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr;
+		else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
+			guest_cr3 = vcpu->arch.cr3;
+		else /* vmcs01.GUEST_CR3 is already up-to-date. */
+			update_guest_cr3 = false;
 		ept_load_pdptrs(vcpu);
 	}
 
-	vmcs_writel(GUEST_CR3, guest_cr3);
+	if (update_guest_cr3)
+		vmcs_writel(GUEST_CR3, guest_cr3);
 }
 
 int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
@@ -3753,7 +3760,7 @@ void pt_update_intercept_for_msr(struct vcpu_vmx *vmx)
 	}
 }
 
-static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu)
+static bool vmx_get_enable_apicv(struct kvm *kvm)
 {
 	return enable_apicv;
 }
@@ -4046,6 +4053,8 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 			guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
 			guest_cpuid_has(vcpu, X86_FEATURE_XSAVES);
 
+		vcpu->arch.xsaves_enabled = xsaves_enabled;
+
 		if (!xsaves_enabled)
 			exec_control &= ~SECONDARY_EXEC_XSAVES;
 
@@ -4158,14 +4167,13 @@ static void ept_set_mmio_spte_mask(void)
 #define VMX_XSS_EXIT_BITMAP 0
 
 /*
- * Sets up the vmcs for emulated real mode.
+ * Noting that the initialization of Guest-state Area of VMCS is in
+ * vmx_vcpu_reset().
  */
-static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
+static void init_vmcs(struct vcpu_vmx *vmx)
 {
-	int i;
-
 	if (nested)
-		nested_vmx_vcpu_setup();
+		nested_vmx_set_vmcs_shadowing_bitmap();
 
 	if (cpu_has_vmx_msr_bitmap())
 		vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap));
@@ -4174,7 +4182,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	/* Control */
 	pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx));
-	vmx->hv_deadline_tsc = -1;
 
 	exec_controls_set(vmx, vmx_exec_control(vmx));
 
@@ -4223,21 +4230,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
 		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
 
-	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) {
-		u32 index = vmx_msr_index[i];
-		u32 data_low, data_high;
-		int j = vmx->nmsrs;
-
-		if (rdmsr_safe(index, &data_low, &data_high) < 0)
-			continue;
-		if (wrmsr_safe(index, data_low, data_high) < 0)
-			continue;
-		vmx->guest_msrs[j].index = i;
-		vmx->guest_msrs[j].data = 0;
-		vmx->guest_msrs[j].mask = -1ull;
-		++vmx->nmsrs;
-	}
-
 	vm_exit_controls_set(vmx, vmx_vmexit_ctrl());
 
 	/* 22.2.1, 20.8.1 */
@@ -4248,6 +4240,9 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	set_cr4_guest_host_mask(vmx);
 
+	if (vmx->vpid != 0)
+		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
+
 	if (vmx_xsaves_supported())
 		vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
 
@@ -4350,9 +4345,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
 
-	if (vmx->vpid != 0)
-		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
-
 	cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
 	vmx->vcpu.arch.cr0 = cr0;
 	vmx_set_cr0(vcpu, cr0); /* enter rmode */
@@ -4707,7 +4699,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static int handle_external_interrupt(struct kvm_vcpu *vcpu)
+static __always_inline int handle_external_interrupt(struct kvm_vcpu *vcpu)
 {
 	++vcpu->stat.irq_exits;
 	return 1;
@@ -4979,21 +4971,6 @@ static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
 	vmcs_writel(GUEST_DR7, val);
 }
 
-static int handle_cpuid(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_cpuid(vcpu);
-}
-
-static int handle_rdmsr(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_rdmsr(vcpu);
-}
-
-static int handle_wrmsr(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_wrmsr(vcpu);
-}
-
 static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu)
 {
 	kvm_apic_update_ppr(vcpu);
@@ -5010,11 +4987,6 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static int handle_halt(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_halt(vcpu);
-}
-
 static int handle_vmcall(struct kvm_vcpu *vcpu)
 {
 	return kvm_emulate_hypercall(vcpu);
@@ -5562,11 +5534,11 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_IO_INSTRUCTION]          = handle_io,
 	[EXIT_REASON_CR_ACCESS]               = handle_cr,
 	[EXIT_REASON_DR_ACCESS]               = handle_dr,
-	[EXIT_REASON_CPUID]                   = handle_cpuid,
-	[EXIT_REASON_MSR_READ]                = handle_rdmsr,
-	[EXIT_REASON_MSR_WRITE]               = handle_wrmsr,
+	[EXIT_REASON_CPUID]                   = kvm_emulate_cpuid,
+	[EXIT_REASON_MSR_READ]                = kvm_emulate_rdmsr,
+	[EXIT_REASON_MSR_WRITE]               = kvm_emulate_wrmsr,
 	[EXIT_REASON_PENDING_INTERRUPT]       = handle_interrupt_window,
-	[EXIT_REASON_HLT]                     = handle_halt,
+	[EXIT_REASON_HLT]                     = kvm_emulate_halt,
 	[EXIT_REASON_INVD]		      = handle_invd,
 	[EXIT_REASON_INVLPG]		      = handle_invlpg,
 	[EXIT_REASON_RDPMC]                   = handle_rdpmc,
@@ -5939,9 +5911,23 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	}
 
 	if (exit_reason < kvm_vmx_max_exit_handlers
-	    && kvm_vmx_exit_handlers[exit_reason])
+	    && kvm_vmx_exit_handlers[exit_reason]) {
+#ifdef CONFIG_RETPOLINE
+		if (exit_reason == EXIT_REASON_MSR_WRITE)
+			return kvm_emulate_wrmsr(vcpu);
+		else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER)
+			return handle_preemption_timer(vcpu);
+		else if (exit_reason == EXIT_REASON_PENDING_INTERRUPT)
+			return handle_interrupt_window(vcpu);
+		else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT)
+			return handle_external_interrupt(vcpu);
+		else if (exit_reason == EXIT_REASON_HLT)
+			return kvm_emulate_halt(vcpu);
+		else if (exit_reason == EXIT_REASON_EPT_MISCONFIG)
+			return handle_ept_misconfig(vcpu);
+#endif
 		return kvm_vmx_exit_handlers[exit_reason](vcpu);
-	else {
+	} else {
 		vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
 				exit_reason);
 		dump_vmcs();
@@ -6027,17 +6013,17 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	int tpr_threshold;
 
 	if (is_guest_mode(vcpu) &&
 		nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
 		return;
 
-	if (irr == -1 || tpr < irr) {
-		vmcs_write32(TPR_THRESHOLD, 0);
-		return;
-	}
-
-	vmcs_write32(TPR_THRESHOLD, irr);
+	tpr_threshold = (irr == -1 || tpr < irr) ? 0 : irr;
+	if (is_guest_mode(vcpu))
+		to_vmx(vcpu)->nested.l1_tpr_threshold = tpr_threshold;
+	else
+		vmcs_write32(TPR_THRESHOLD, tpr_threshold);
 }
 
 void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
@@ -6514,9 +6500,9 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vmx->nested.need_vmcs12_to_shadow_sync)
 		nested_sync_vmcs12_to_shadow(vcpu);
 
-	if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
+	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP))
 		vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
-	if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
+	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RIP))
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 
 	cr3 = __get_current_cr3_fast();
@@ -6539,7 +6525,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
 		vmx_set_interrupt_shadow(vcpu, 0);
 
-	kvm_load_guest_xcr0(vcpu);
+	kvm_load_guest_xsave_state(vcpu);
 
 	if (static_cpu_has(X86_FEATURE_PKU) &&
 	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
@@ -6646,7 +6632,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 			__write_pkru(vmx->host_pkru);
 	}
 
-	kvm_put_guest_xcr0(vcpu);
+	kvm_load_host_xsave_state(vcpu);
 
 	vmx->nested.nested_run_pending = 0;
 	vmx->idt_vectoring_info = 0;
@@ -6700,7 +6686,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	int err;
 	struct vcpu_vmx *vmx;
 	unsigned long *msr_bitmap;
-	int cpu;
+	int i, cpu;
 
 	BUILD_BUG_ON_MSG(offsetof(struct vcpu_vmx, vcpu) != 0,
 		"struct kvm_vcpu must be at offset 0 for arch usercopy region");
@@ -6752,6 +6738,34 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (!vmx->guest_msrs)
 		goto free_pml;
 
+	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) {
+		u32 index = vmx_msr_index[i];
+		u32 data_low, data_high;
+		int j = vmx->nmsrs;
+
+		if (rdmsr_safe(index, &data_low, &data_high) < 0)
+			continue;
+		if (wrmsr_safe(index, data_low, data_high) < 0)
+			continue;
+
+		vmx->guest_msrs[j].index = i;
+		vmx->guest_msrs[j].data = 0;
+		switch (index) {
+		case MSR_IA32_TSX_CTRL:
+			/*
+			 * No need to pass TSX_CTRL_CPUID_CLEAR through, so
+			 * let's avoid changing CPUID bits under the host
+			 * kernel's feet.
+			 */
+			vmx->guest_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
+			break;
+		default:
+			vmx->guest_msrs[j].mask = -1ull;
+			break;
+		}
+		++vmx->nmsrs;
+	}
+
 	err = alloc_loaded_vmcs(&vmx->vmcs01);
 	if (err < 0)
 		goto free_msrs;
@@ -6776,7 +6790,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	cpu = get_cpu();
 	vmx_vcpu_load(&vmx->vcpu, cpu);
 	vmx->vcpu.cpu = cpu;
-	vmx_vcpu_setup(vmx);
+	init_vmcs(vmx);
 	vmx_vcpu_put(&vmx->vcpu);
 	put_cpu();
 	if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) {
@@ -6996,6 +7010,7 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
 	cr4_fixed1_update(X86_CR4_SMAP,       ebx, bit(X86_FEATURE_SMAP));
 	cr4_fixed1_update(X86_CR4_PKE,        ecx, bit(X86_FEATURE_PKU));
 	cr4_fixed1_update(X86_CR4_UMIP,       ecx, bit(X86_FEATURE_UMIP));
+	cr4_fixed1_update(X86_CR4_LA57,       ecx, bit(X86_FEATURE_LA57));
 
 #undef cr4_fixed1_update
 }
@@ -7090,6 +7105,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	/* xsaves_enabled is recomputed in vmx_compute_secondary_exec_control(). */
+	vcpu->arch.xsaves_enabled = false;
+
 	if (cpu_has_secondary_exec_ctrls()) {
 		vmx_compute_secondary_exec_control(vmx);
 		vmcs_set_secondary_exec_control(vmx);
@@ -7097,10 +7115,12 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 
 	if (nested_vmx_allowed(vcpu))
 		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
+			FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX |
 			FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
 	else
 		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
-			~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+			~(FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX |
+			  FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX);
 
 	if (nested_vmx_allowed(vcpu)) {
 		nested_vmx_cr_fixed1_bits_update(vcpu);
@@ -7110,6 +7130,15 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 	if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
 			guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT))
 		update_intel_pt_cfg(vcpu);
+
+	if (boot_cpu_has(X86_FEATURE_RTM)) {
+		struct shared_msr_entry *msr;
+		msr = find_msr_entry(vmx, MSR_IA32_TSX_CTRL);
+		if (msr) {
+			bool enabled = guest_cpuid_has(vcpu, X86_FEATURE_RTM);
+			vmx_set_guest_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE);
+		}
+	}
 }
 
 static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
@@ -7598,9 +7627,6 @@ static __init int hardware_setup(void)
 		WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost");
 	}
 
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		rdmsrl(MSR_IA32_XSS, host_xss);
-
 	if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||
 	    !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))
 		enable_vpid = 0;
@@ -7781,7 +7807,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.get_cpl = vmx_get_cpl,
 	.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
 	.decache_cr0_guest_bits = vmx_decache_cr0_guest_bits,
-	.decache_cr3 = vmx_decache_cr3,
 	.decache_cr4_guest_bits = vmx_decache_cr4_guest_bits,
 	.set_cr0 = vmx_set_cr0,
 	.set_cr3 = vmx_set_cr3,
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 5a0f34b1e226..7c1b978b2df4 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -22,11 +22,11 @@ extern u32 get_umwait_control_msr(void);
 
 #define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
 
-#define NR_AUTOLOAD_MSRS 8
+#define NR_LOADSTORE_MSRS 8
 
 struct vmx_msrs {
 	unsigned int		nr;
-	struct vmx_msr_entry	val[NR_AUTOLOAD_MSRS];
+	struct vmx_msr_entry	val[NR_LOADSTORE_MSRS];
 };
 
 struct shared_msr_entry {
@@ -167,6 +167,9 @@ struct nested_vmx {
 	u64 vmcs01_debugctl;
 	u64 vmcs01_guest_bndcfgs;
 
+	/* to migrate it to L1 if L2 writes to L1's CR8 directly */
+	int l1_tpr_threshold;
+
 	u16 vpid02;
 	u16 last_vpid;
 
@@ -230,6 +233,10 @@ struct vcpu_vmx {
 		struct vmx_msrs host;
 	} msr_autoload;
 
+	struct msr_autostore {
+		struct vmx_msrs guest;
+	} msr_autostore;
+
 	struct {
 		int vm86_active;
 		ulong save_rflags;
@@ -334,6 +341,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
 struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr);
 void pt_update_intercept_for_msr(struct vcpu_vmx *vmx);
 void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp);
+int vmx_find_msr_index(struct vmx_msrs *m, u32 msr);
 
 #define POSTED_INTR_ON  0
 #define POSTED_INTR_SN  1
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5d530521f11d..3ed167e039e5 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -176,6 +176,8 @@ struct kvm_shared_msrs {
 static struct kvm_shared_msrs_global __read_mostly shared_msrs_global;
 static struct kvm_shared_msrs __percpu *shared_msrs;
 
+static u64 __read_mostly host_xss;
+
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "pf_fixed", VCPU_STAT(pf_fixed) },
 	{ "pf_guest", VCPU_STAT(pf_guest) },
@@ -260,23 +262,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 	}
 }
 
-static void shared_msr_update(unsigned slot, u32 msr)
-{
-	u64 value;
-	unsigned int cpu = smp_processor_id();
-	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
-
-	/* only read, and nobody should modify it at this time,
-	 * so don't need lock */
-	if (slot >= shared_msrs_global.nr) {
-		printk(KERN_ERR "kvm: invalid MSR slot!");
-		return;
-	}
-	rdmsrl_safe(msr, &value);
-	smsr->values[slot].host = value;
-	smsr->values[slot].curr = value;
-}
-
 void kvm_define_shared_msr(unsigned slot, u32 msr)
 {
 	BUG_ON(slot >= KVM_NR_SHARED_MSRS);
@@ -288,10 +273,16 @@ EXPORT_SYMBOL_GPL(kvm_define_shared_msr);
 
 static void kvm_shared_msr_cpu_online(void)
 {
-	unsigned i;
+	unsigned int cpu = smp_processor_id();
+	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
+	u64 value;
+	int i;
 
-	for (i = 0; i < shared_msrs_global.nr; ++i)
-		shared_msr_update(i, shared_msrs_global.msrs[i]);
+	for (i = 0; i < shared_msrs_global.nr; ++i) {
+		rdmsrl_safe(shared_msrs_global.msrs[i], &value);
+		smsr->values[i].host = value;
+		smsr->values[i].curr = value;
+	}
 }
 
 int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
@@ -300,13 +291,14 @@ int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
 	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
 	int err;
 
-	if (((value ^ smsr->values[slot].curr) & mask) == 0)
+	value = (value & mask) | (smsr->values[slot].host & ~mask);
+	if (value == smsr->values[slot].curr)
 		return 0;
-	smsr->values[slot].curr = value;
 	err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
 	if (err)
 		return 1;
 
+	smsr->values[slot].curr = value;
 	if (!smsr->registered) {
 		smsr->urn.on_user_return = kvm_on_user_return;
 		user_return_notifier_register(&smsr->urn);
@@ -709,10 +701,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
 	ret = 1;
 
 	memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs));
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_avail);
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_dirty);
+	kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR);
+
 out:
 
 	return ret;
@@ -722,7 +712,6 @@ EXPORT_SYMBOL_GPL(load_pdptrs);
 bool pdptrs_changed(struct kvm_vcpu *vcpu)
 {
 	u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)];
-	bool changed = true;
 	int offset;
 	gfn_t gfn;
 	int r;
@@ -730,8 +719,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 	if (!is_pae_paging(vcpu))
 		return false;
 
-	if (!test_bit(VCPU_EXREG_PDPTR,
-		      (unsigned long *)&vcpu->arch.regs_avail))
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR))
 		return true;
 
 	gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT;
@@ -739,11 +727,9 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 	r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte),
 				       PFERR_USER_MASK | PFERR_WRITE_MASK);
 	if (r < 0)
-		goto out;
-	changed = memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0;
-out:
+		return true;
 
-	return changed;
+	return memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0;
 }
 EXPORT_SYMBOL_GPL(pdptrs_changed);
 
@@ -812,27 +798,34 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
 }
 EXPORT_SYMBOL_GPL(kvm_lmsw);
 
-void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
 {
-	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
-			!vcpu->guest_xcr0_loaded) {
-		/* kvm_set_xcr() also depends on this */
+	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
+
 		if (vcpu->arch.xcr0 != host_xcr0)
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
-		vcpu->guest_xcr0_loaded = 1;
+
+		if (vcpu->arch.xsaves_enabled &&
+		    vcpu->arch.ia32_xss != host_xss)
+			wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss);
 	}
 }
-EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
+EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state);
 
-void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->guest_xcr0_loaded) {
+	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
+
 		if (vcpu->arch.xcr0 != host_xcr0)
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
-		vcpu->guest_xcr0_loaded = 0;
+
+		if (vcpu->arch.xsaves_enabled &&
+		    vcpu->arch.ia32_xss != host_xss)
+			wrmsrl(MSR_IA32_XSS, host_xss);
 	}
+
 }
-EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0);
+EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state);
 
 static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
@@ -984,7 +977,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 
 	kvm_mmu_new_cr3(vcpu, cr3, skip_tlb_flush);
 	vcpu->arch.cr3 = cr3;
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
 
 	return 0;
 }
@@ -1313,23 +1306,15 @@ static u64 kvm_get_arch_capabilities(void)
 		data |= ARCH_CAP_MDS_NO;
 
 	/*
-	 * On TAA affected systems, export MDS_NO=0 when:
-	 *	- TSX is enabled on the host, i.e. X86_FEATURE_RTM=1.
-	 *	- Updated microcode is present. This is detected by
-	 *	  the presence of ARCH_CAP_TSX_CTRL_MSR and ensures
-	 *	  that VERW clears CPU buffers.
-	 *
-	 * When MDS_NO=0 is exported, guests deploy clear CPU buffer
-	 * mitigation and don't complain:
-	 *
-	 *	"Vulnerable: Clear CPU buffers attempted, no microcode"
-	 *
-	 * If TSX is disabled on the system, guests are also mitigated against
-	 * TAA and clear CPU buffer mitigation is not required for guests.
+	 * On TAA affected systems:
+	 *      - nothing to do if TSX is disabled on the host.
+	 *      - we emulate TSX_CTRL if present on the host.
+	 *	  This lets the guest use VERW to clear CPU buffers.
 	 */
-	if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) &&
-	    (data & ARCH_CAP_TSX_CTRL_MSR))
-		data &= ~ARCH_CAP_MDS_NO;
+	if (!boot_cpu_has(X86_FEATURE_RTM))
+		data &= ~(ARCH_CAP_TAA_NO | ARCH_CAP_TSX_CTRL_MSR);
+	else if (!boot_cpu_has_bug(X86_BUG_TAA))
+		data |= ARCH_CAP_TAA_NO;
 
 	return data;
 }
@@ -1477,8 +1462,8 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
  * Returns 0 on success, non-0 otherwise.
  * Assumes vcpu_load() was already called.
  */
-static int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
-			 bool host_initiated)
+int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
+		  bool host_initiated)
 {
 	struct msr_data msr;
 	int ret;
@@ -1553,20 +1538,25 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 }
 
 #ifdef CONFIG_X86_64
+struct pvclock_clock {
+	int vclock_mode;
+	u64 cycle_last;
+	u64 mask;
+	u32 mult;
+	u32 shift;
+};
+
 struct pvclock_gtod_data {
 	seqcount_t	seq;
 
-	struct { /* extract of a clocksource struct */
-		int vclock_mode;
-		u64	cycle_last;
-		u64	mask;
-		u32	mult;
-		u32	shift;
-	} clock;
+	struct pvclock_clock clock; /* extract of a clocksource struct */
+	struct pvclock_clock raw_clock; /* extract of a clocksource struct */
 
+	u64		boot_ns_raw;
 	u64		boot_ns;
 	u64		nsec_base;
 	u64		wall_time_sec;
+	u64		monotonic_raw_nsec;
 };
 
 static struct pvclock_gtod_data pvclock_gtod_data;
@@ -1574,9 +1564,10 @@ static struct pvclock_gtod_data pvclock_gtod_data;
 static void update_pvclock_gtod(struct timekeeper *tk)
 {
 	struct pvclock_gtod_data *vdata = &pvclock_gtod_data;
-	u64 boot_ns;
+	u64 boot_ns, boot_ns_raw;
 
 	boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot));
+	boot_ns_raw = ktime_to_ns(ktime_add(tk->tkr_raw.base, tk->offs_boot));
 
 	write_seqcount_begin(&vdata->seq);
 
@@ -1587,11 +1578,20 @@ static void update_pvclock_gtod(struct timekeeper *tk)
 	vdata->clock.mult		= tk->tkr_mono.mult;
 	vdata->clock.shift		= tk->tkr_mono.shift;
 
+	vdata->raw_clock.vclock_mode	= tk->tkr_raw.clock->archdata.vclock_mode;
+	vdata->raw_clock.cycle_last	= tk->tkr_raw.cycle_last;
+	vdata->raw_clock.mask		= tk->tkr_raw.mask;
+	vdata->raw_clock.mult		= tk->tkr_raw.mult;
+	vdata->raw_clock.shift		= tk->tkr_raw.shift;
+
 	vdata->boot_ns			= boot_ns;
 	vdata->nsec_base		= tk->tkr_mono.xtime_nsec;
 
 	vdata->wall_time_sec            = tk->xtime_sec;
 
+	vdata->boot_ns_raw		= boot_ns_raw;
+	vdata->monotonic_raw_nsec	= tk->tkr_raw.xtime_nsec;
+
 	write_seqcount_end(&vdata->seq);
 }
 #endif
@@ -2015,21 +2015,21 @@ static u64 read_tsc(void)
 	return last;
 }
 
-static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
+static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp,
+			  int *mode)
 {
 	long v;
-	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 	u64 tsc_pg_val;
 
-	switch (gtod->clock.vclock_mode) {
+	switch (clock->vclock_mode) {
 	case VCLOCK_HVCLOCK:
 		tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(),
 						  tsc_timestamp);
 		if (tsc_pg_val != U64_MAX) {
 			/* TSC page valid */
 			*mode = VCLOCK_HVCLOCK;
-			v = (tsc_pg_val - gtod->clock.cycle_last) &
-				gtod->clock.mask;
+			v = (tsc_pg_val - clock->cycle_last) &
+				clock->mask;
 		} else {
 			/* TSC page invalid */
 			*mode = VCLOCK_NONE;
@@ -2038,8 +2038,8 @@ static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
 	case VCLOCK_TSC:
 		*mode = VCLOCK_TSC;
 		*tsc_timestamp = read_tsc();
-		v = (*tsc_timestamp - gtod->clock.cycle_last) &
-			gtod->clock.mask;
+		v = (*tsc_timestamp - clock->cycle_last) &
+			clock->mask;
 		break;
 	default:
 		*mode = VCLOCK_NONE;
@@ -2048,10 +2048,10 @@ static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
 	if (*mode == VCLOCK_NONE)
 		*tsc_timestamp = v = 0;
 
-	return v * gtod->clock.mult;
+	return v * clock->mult;
 }
 
-static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp)
+static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp)
 {
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 	unsigned long seq;
@@ -2060,10 +2060,10 @@ static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp)
 
 	do {
 		seq = read_seqcount_begin(&gtod->seq);
-		ns = gtod->nsec_base;
-		ns += vgettsc(tsc_timestamp, &mode);
+		ns = gtod->monotonic_raw_nsec;
+		ns += vgettsc(&gtod->raw_clock, tsc_timestamp, &mode);
 		ns >>= gtod->clock.shift;
-		ns += gtod->boot_ns;
+		ns += gtod->boot_ns_raw;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 	*t = ns;
 
@@ -2081,7 +2081,7 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp)
 		seq = read_seqcount_begin(&gtod->seq);
 		ts->tv_sec = gtod->wall_time_sec;
 		ns = gtod->nsec_base;
-		ns += vgettsc(tsc_timestamp, &mode);
+		ns += vgettsc(&gtod->clock, tsc_timestamp, &mode);
 		ns >>= gtod->clock.shift;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 
@@ -2098,7 +2098,7 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp)
 	if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
 		return false;
 
-	return gtod_is_based_on_tsc(do_monotonic_boot(kernel_ns,
+	return gtod_is_based_on_tsc(do_monotonic_raw(kernel_ns,
 						      tsc_timestamp));
 }
 
@@ -2721,6 +2721,20 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_TSC:
 		kvm_write_tsc(vcpu, msr_info);
 		break;
+	case MSR_IA32_XSS:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
+			return 1;
+		/*
+		 * We do support PT if kvm_x86_ops->pt_supported(), but we do
+		 * not support IA32_XSS[bit 8]. Guests will have to use
+		 * RDMSR/WRMSR rather than XSAVES/XRSTORS to save/restore PT
+		 * MSRs.
+		 */
+		if (data != 0)
+			return 1;
+		vcpu->arch.ia32_xss = data;
+		break;
 	case MSR_SMI_COUNT:
 		if (!msr_info->host_initiated)
 			return 1;
@@ -3048,6 +3062,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
 		return get_msr_mce(vcpu, msr_info->index, &msr_info->data,
 				   msr_info->host_initiated);
+	case MSR_IA32_XSS:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
+			return 1;
+		msr_info->data = vcpu->arch.ia32_xss;
+		break;
 	case MSR_K7_CLK_CTL:
 		/*
 		 * Provide expected ramp-up count for K7. All other
@@ -3825,12 +3845,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 				vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
 			else
 				vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
-			if (lapic_in_kernel(vcpu)) {
-				if (events->smi.latched_init)
-					set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
-				else
-					clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
-			}
+		}
+
+		if (lapic_in_kernel(vcpu)) {
+			if (events->smi.latched_init)
+				set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+			else
+				clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
 		}
 	}
 
@@ -4421,6 +4442,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	case KVM_SET_NESTED_STATE: {
 		struct kvm_nested_state __user *user_kvm_nested_state = argp;
 		struct kvm_nested_state kvm_state;
+		int idx;
 
 		r = -EINVAL;
 		if (!kvm_x86_ops->set_nested_state)
@@ -4444,7 +4466,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		    && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE))
 			break;
 
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_GET_SUPPORTED_HV_CPUID: {
@@ -4946,9 +4970,6 @@ set_identity_unlock:
 		if (!irqchip_kernel(kvm))
 			goto set_irqchip_out;
 		r = kvm_vm_ioctl_set_irqchip(kvm, chip);
-		if (r)
-			goto set_irqchip_out;
-		r = 0;
 	set_irqchip_out:
 		kfree(chip);
 		break;
@@ -6136,7 +6157,7 @@ static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase)
 static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt,
 			      u32 pmc)
 {
-	return kvm_pmu_is_valid_msr_idx(emul_to_vcpu(ctxt), pmc);
+	return kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc);
 }
 
 static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt,
@@ -7866,6 +7887,19 @@ static void process_smi(struct kvm_vcpu *vcpu)
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 }
 
+void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
+				       unsigned long *vcpu_bitmap)
+{
+	cpumask_var_t cpus;
+
+	zalloc_cpumask_var(&cpus, GFP_ATOMIC);
+
+	kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC,
+				    vcpu_bitmap, cpus);
+
+	free_cpumask_var(cpus);
+}
+
 void kvm_make_scan_ioapic_request(struct kvm *kvm)
 {
 	kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
@@ -7943,7 +7977,6 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 	 */
 	put_page(page);
 }
-EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
 
 void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu)
 {
@@ -8702,8 +8735,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	    mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
 		goto out;
 
-	/* INITs are latched while in SMM */
-	if ((is_smm(vcpu) || vcpu->arch.smi_pending) &&
+	/*
+	 * KVM_MP_STATE_INIT_RECEIVED means the processor is in
+	 * INIT state; latched init should be reported using
+	 * KVM_SET_VCPU_EVENTS, so reject it here.
+	 */
+	if ((kvm_vcpu_latch_init(vcpu) || vcpu->arch.smi_pending) &&
 	    (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED ||
 	     mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED))
 		goto out;
@@ -8795,7 +8832,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	vcpu->arch.cr2 = sregs->cr2;
 	mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3;
 	vcpu->arch.cr3 = sregs->cr3;
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
 
 	kvm_set_cr8(vcpu, sregs->cr8);
 
@@ -9322,6 +9359,9 @@ int kvm_arch_hardware_setup(void)
 		kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits;
 	}
 
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		rdmsrl(MSR_IA32_XSS, host_xss);
+
 	kvm_init_msr_list();
 	return 0;
 }
@@ -9375,7 +9415,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 		goto fail_free_pio_data;
 
 	if (irqchip_in_kernel(vcpu->kvm)) {
-		vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu);
+		vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu->kvm);
 		r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
 		if (r < 0)
 			goto fail_mmu_destroy;
@@ -9444,7 +9484,13 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 
 void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
 	vcpu->arch.l1tf_flush_l1d = true;
+	if (pmu->version && unlikely(pmu->event_count)) {
+		pmu->need_cleanup = true;
+		kvm_make_request(KVM_REQ_PMU, vcpu);
+	}
 	kvm_x86_ops->sched_in(vcpu, cpu);
 }
 
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index dbf7442a822b..29391af8871d 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -238,8 +238,7 @@ static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
 	return false;
 }
 
-static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu,
-					       enum kvm_reg reg)
+static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu, int reg)
 {
 	unsigned long val = kvm_register_read(vcpu, reg);
 
@@ -247,8 +246,7 @@ static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu,
 }
 
 static inline void kvm_register_writel(struct kvm_vcpu *vcpu,
-				       enum kvm_reg reg,
-				       unsigned long val)
+				       int reg, unsigned long val)
 {
 	if (!is_64_bit_mode(vcpu))
 		val = (u32)val;
@@ -260,6 +258,11 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
 	return !(kvm->arch.disabled_quirks & quirk);
 }
 
+static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu)
+{
+	return is_smm(vcpu) || kvm_x86_ops->apic_init_signal_blocked(vcpu);
+}
+
 void kvm_set_pending_timer(struct kvm_vcpu *vcpu);
 void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
 
@@ -366,7 +369,7 @@ static inline bool kvm_pat_valid(u64 data)
 	return (data | ((data & 0x0202020202020202ull) << 1)) == data;
 }
 
-void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu);
-void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu);
+void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu);
+void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu);
 
 #endif
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 79eb55ce69a9..49d7814b59a9 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -193,8 +193,8 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
 	int ret;
 	WARN_ONCE(f->armed, KERN_ERR pr_fmt("kmmio page already armed.\n"));
 	if (f->armed) {
-		pr_warning("double-arm: addr 0x%08lx, ref %d, old %d\n",
-			   f->addr, f->count, !!f->old_presence);
+		pr_warn("double-arm: addr 0x%08lx, ref %d, old %d\n",
+			f->addr, f->count, !!f->old_presence);
 	}
 	ret = clear_page_presence(f, true);
 	WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming at 0x%08lx failed.\n"),
@@ -341,8 +341,7 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
 		 * something external causing them (f.e. using a debugger while
 		 * mmio tracing enabled), or erroneous behaviour
 		 */
-		pr_warning("unexpected debug trap on CPU %d.\n",
-			   smp_processor_id());
+		pr_warn("unexpected debug trap on CPU %d.\n", smp_processor_id());
 		goto out;
 	}
 
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index b8ef8557d4b3..673de6063345 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -394,7 +394,7 @@ static void enter_uniprocessor(void)
 	}
 out:
 	if (num_online_cpus() > 1)
-		pr_warning("multiple CPUs still online, may miss events.\n");
+		pr_warn("multiple CPUs still online, may miss events.\n");
 }
 
 static void leave_uniprocessor(void)
@@ -418,8 +418,8 @@ static void leave_uniprocessor(void)
 static void enter_uniprocessor(void)
 {
 	if (num_online_cpus() > 1)
-		pr_warning("multiple CPUs are online, may miss events. "
-			   "Suggest booting with maxcpus=1 kernel argument.\n");
+		pr_warn("multiple CPUs are online, may miss events. "
+			"Suggest booting with maxcpus=1 kernel argument.\n");
 }
 
 static void leave_uniprocessor(void)
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index abffa0be80da..7f1d2034df1e 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -438,7 +438,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 		goto no_emu;
 
 	if (numa_cleanup_meminfo(&ei) < 0) {
-		pr_warning("NUMA: Warning: constructed meminfo invalid, disabling emulation\n");
+		pr_warn("NUMA: Warning: constructed meminfo invalid, disabling emulation\n");
 		goto no_emu;
 	}
 
@@ -449,7 +449,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 		phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
 					      phys_size, PAGE_SIZE);
 		if (!phys) {
-			pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
+			pr_warn("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
 			goto no_emu;
 		}
 		memblock_reserve(phys, phys_size);
diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c
index a8bd952e136d..92153d054d6c 100644
--- a/arch/x86/mm/testmmiotrace.c
+++ b/arch/x86/mm/testmmiotrace.c
@@ -127,9 +127,9 @@ static int __init init(void)
 		return -ENXIO;
 	}
 
-	pr_warning("WARNING: mapping %lu kB @ 0x%08lx in PCI address space, "
-		   "and writing 16 kB of rubbish in there.\n",
-		   size >> 10, mmio_address);
+	pr_warn("WARNING: mapping %lu kB @ 0x%08lx in PCI address space, "
+		"and writing 16 kB of rubbish in there.\n",
+		size >> 10, mmio_address);
 	do_test(size);
 	do_test_bulk_ioremapping();
 	pr_info("All done.\n");
diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h
index 71e8a67337e2..276cf79b5d24 100644
--- a/arch/x86/oprofile/op_x86_model.h
+++ b/arch/x86/oprofile/op_x86_model.h
@@ -67,13 +67,13 @@ static inline void op_x86_warn_in_use(int counter)
 	 * cannot be monitored by any other counter, contact your
 	 * hardware or BIOS vendor.
 	 */
-	pr_warning("oprofile: counter #%d on cpu #%d may already be used\n",
-		   counter, smp_processor_id());
+	pr_warn("oprofile: counter #%d on cpu #%d may already be used\n",
+		counter, smp_processor_id());
 }
 
 static inline void op_x86_warn_reserved(int counter)
 {
-	pr_warning("oprofile: counter #%d is already reserved\n", counter);
+	pr_warn("oprofile: counter #%d is already reserved\n", counter);
 }
 
 extern u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c
index 6d193bb36021..089413cd944e 100644
--- a/arch/x86/platform/olpc/olpc-xo15-sci.c
+++ b/arch/x86/platform/olpc/olpc-xo15-sci.c
@@ -39,7 +39,7 @@ static int set_lid_wake_behavior(bool wake_on_close)
 
 	status = acpi_execute_simple_method(NULL, "\\_SB.PCI0.LID.LIDW", wake_on_close);
 	if (ACPI_FAILURE(status)) {
-		pr_warning(PFX "failed to set lid behavior\n");
+		pr_warn(PFX "failed to set lid behavior\n");
 		return 1;
 	}
 
diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c
index bf6016f8db4e..6259563760f9 100644
--- a/arch/x86/platform/sfi/sfi.c
+++ b/arch/x86/platform/sfi/sfi.c
@@ -26,8 +26,7 @@ static unsigned long sfi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
 static void __init mp_sfi_register_lapic(u8 id)
 {
 	if (MAX_LOCAL_APIC - id <= 0) {
-		pr_warning("Processor #%d invalid (max %d)\n",
-			id, MAX_LOCAL_APIC);
+		pr_warn("Processor #%d invalid (max %d)\n", id, MAX_LOCAL_APIC);
 		return;
 	}
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 548d1e0a5ba1..33b0e20df7fc 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -412,7 +412,7 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 
 		remap_range_size = xen_find_pfn_range(&remap_pfn);
 		if (!remap_range_size) {
-			pr_warning("Unable to find available pfn range, not remapping identity pages\n");
+			pr_warn("Unable to find available pfn range, not remapping identity pages\n");
 			xen_set_identity_and_release_chunk(cur_pfn,
 						cur_pfn + left, nr_pages);
 			break;
diff --git a/block/Kconfig b/block/Kconfig
index 41c0917ce622..c23094a14a2b 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -32,6 +32,9 @@ config BLK_RQ_ALLOC_TIME
 config BLK_SCSI_REQUEST
 	bool
 
+config BLK_CGROUP_RWSTAT
+	bool
+
 config BLK_DEV_BSG
 	bool "Block layer SG support v4"
 	default y
@@ -86,6 +89,7 @@ config BLK_DEV_ZONED
 config BLK_DEV_THROTTLING
 	bool "Block layer bio throttling support"
 	depends on BLK_CGROUP=y
+	select BLK_CGROUP_RWSTAT
 	---help---
 	Block layer bio throttling support. It can be used to limit
 	the IO rate to a device. IO rate policies are per cgroup and
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index b89310a022ad..7df14133adc8 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -31,6 +31,7 @@ config IOSCHED_BFQ
 config BFQ_GROUP_IOSCHED
        bool "BFQ hierarchical scheduling support"
        depends on IOSCHED_BFQ && BLK_CGROUP
+       select BLK_CGROUP_RWSTAT
        ---help---
 
        Enable hierarchical scheduling in BFQ, using the blkio
diff --git a/block/Makefile b/block/Makefile
index 9ef57ace90d4..205a5f2fef17 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_ioctl.o
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
+obj-$(CONFIG_BLK_CGROUP_RWSTAT)	+= blk-cgroup-rwstat.o
 obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
 obj-$(CONFIG_BLK_CGROUP_IOLATENCY)	+= blk-iolatency.o
 obj-$(CONFIG_BLK_CGROUP_IOCOST)	+= blk-iocost.o
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 86a607cf19a1..cea0ae12f937 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -347,6 +347,14 @@ void bfqg_and_blkg_put(struct bfq_group *bfqg)
 	bfqg_put(bfqg);
 }
 
+void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq)
+{
+	struct bfq_group *bfqg = blkg_to_bfqg(rq->bio->bi_blkg);
+
+	blkg_rwstat_add(&bfqg->stats.bytes, rq->cmd_flags, blk_rq_bytes(rq));
+	blkg_rwstat_add(&bfqg->stats.ios, rq->cmd_flags, 1);
+}
+
 /* @stats = 0 */
 static void bfqg_stats_reset(struct bfqg_stats *stats)
 {
@@ -431,6 +439,8 @@ void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg)
 
 static void bfqg_stats_exit(struct bfqg_stats *stats)
 {
+	blkg_rwstat_exit(&stats->bytes);
+	blkg_rwstat_exit(&stats->ios);
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	blkg_rwstat_exit(&stats->merged);
 	blkg_rwstat_exit(&stats->service_time);
@@ -448,6 +458,10 @@ static void bfqg_stats_exit(struct bfqg_stats *stats)
 
 static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
 {
+	if (blkg_rwstat_init(&stats->bytes, gfp) ||
+	    blkg_rwstat_init(&stats->ios, gfp))
+		return -ENOMEM;
+
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	if (blkg_rwstat_init(&stats->merged, gfp) ||
 	    blkg_rwstat_init(&stats->service_time, gfp) ||
@@ -1057,18 +1071,35 @@ static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
 	return bfq_io_set_device_weight(of, buf, nbytes, off);
 }
 
-#ifdef CONFIG_BFQ_CGROUP_DEBUG
-static int bfqg_print_stat(struct seq_file *sf, void *v)
+static int bfqg_print_rwstat(struct seq_file *sf, void *v)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
-			  &blkcg_policy_bfq, seq_cft(sf)->private, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat,
+			  &blkcg_policy_bfq, seq_cft(sf)->private, true);
 	return 0;
 }
 
-static int bfqg_print_rwstat(struct seq_file *sf, void *v)
+static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf,
+					struct blkg_policy_data *pd, int off)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat,
-			  &blkcg_policy_bfq, seq_cft(sf)->private, true);
+	struct blkg_rwstat_sample sum;
+
+	blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, off, &sum);
+	return __blkg_prfill_rwstat(sf, pd, &sum);
+}
+
+static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq,
+			  seq_cft(sf)->private, true);
+	return 0;
+}
+
+#ifdef CONFIG_BFQ_CGROUP_DEBUG
+static int bfqg_print_stat(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
+			  &blkcg_policy_bfq, seq_cft(sf)->private, false);
 	return 0;
 }
 
@@ -1097,15 +1128,6 @@ static u64 bfqg_prfill_stat_recursive(struct seq_file *sf,
 	return __blkg_prfill_u64(sf, pd, sum);
 }
 
-static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf,
-					struct blkg_policy_data *pd, int off)
-{
-	struct blkg_rwstat_sample sum;
-
-	blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, off, &sum);
-	return __blkg_prfill_rwstat(sf, pd, &sum);
-}
-
 static int bfqg_print_stat_recursive(struct seq_file *sf, void *v)
 {
 	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
@@ -1114,18 +1136,11 @@ static int bfqg_print_stat_recursive(struct seq_file *sf, void *v)
 	return 0;
 }
 
-static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
-{
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
-			  bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq,
-			  seq_cft(sf)->private, true);
-	return 0;
-}
-
 static u64 bfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd,
 			       int off)
 {
-	u64 sum = blkg_rwstat_total(&pd->blkg->stat_bytes);
+	struct bfq_group *bfqg = blkg_to_bfqg(pd->blkg);
+	u64 sum = blkg_rwstat_total(&bfqg->stats.bytes);
 
 	return __blkg_prfill_u64(sf, pd, sum >> 9);
 }
@@ -1142,8 +1157,8 @@ static u64 bfqg_prfill_sectors_recursive(struct seq_file *sf,
 {
 	struct blkg_rwstat_sample tmp;
 
-	blkg_rwstat_recursive_sum(pd->blkg, NULL,
-			offsetof(struct blkcg_gq, stat_bytes), &tmp);
+	blkg_rwstat_recursive_sum(pd->blkg, &blkcg_policy_bfq,
+			offsetof(struct bfq_group, stats.bytes), &tmp);
 
 	return __blkg_prfill_u64(sf, pd,
 		(tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]) >> 9);
@@ -1226,13 +1241,13 @@ struct cftype bfq_blkcg_legacy_files[] = {
 	/* statistics, covers only the tasks in the bfqg */
 	{
 		.name = "bfq.io_service_bytes",
-		.private = (unsigned long)&blkcg_policy_bfq,
-		.seq_show = blkg_print_stat_bytes,
+		.private = offsetof(struct bfq_group, stats.bytes),
+		.seq_show = bfqg_print_rwstat,
 	},
 	{
 		.name = "bfq.io_serviced",
-		.private = (unsigned long)&blkcg_policy_bfq,
-		.seq_show = blkg_print_stat_ios,
+		.private = offsetof(struct bfq_group, stats.ios),
+		.seq_show = bfqg_print_rwstat,
 	},
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	{
@@ -1269,13 +1284,13 @@ struct cftype bfq_blkcg_legacy_files[] = {
 	/* the same statistics which cover the bfqg and its descendants */
 	{
 		.name = "bfq.io_service_bytes_recursive",
-		.private = (unsigned long)&blkcg_policy_bfq,
-		.seq_show = blkg_print_stat_bytes_recursive,
+		.private = offsetof(struct bfq_group, stats.bytes),
+		.seq_show = bfqg_print_rwstat_recursive,
 	},
 	{
 		.name = "bfq.io_serviced_recursive",
-		.private = (unsigned long)&blkcg_policy_bfq,
-		.seq_show = blkg_print_stat_ios_recursive,
+		.private = offsetof(struct bfq_group, stats.ios),
+		.seq_show = bfqg_print_rwstat_recursive,
 	},
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	{
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 0c6214497fcc..ad4af4aaf2ce 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -5484,6 +5484,10 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	bool idle_timer_disabled = false;
 	unsigned int cmd_flags;
 
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	if (!cgroup_subsys_on_dfl(io_cgrp_subsys) && rq->bio)
+		bfqg_stats_update_legacy_io(q, rq);
+#endif
 	spin_lock_irq(&bfqd->lock);
 	if (blk_mq_sched_try_insert_merge(q, rq)) {
 		spin_unlock_irq(&bfqd->lock);
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 5d1a519640f6..8526f20c53bc 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -10,6 +10,8 @@
 #include <linux/hrtimer.h>
 #include <linux/blk-cgroup.h>
 
+#include "blk-cgroup-rwstat.h"
+
 #define BFQ_IOPRIO_CLASSES	3
 #define BFQ_CL_IDLE_TIMEOUT	(HZ/5)
 
@@ -809,6 +811,9 @@ struct bfq_stat {
 };
 
 struct bfqg_stats {
+	/* basic stats */
+	struct blkg_rwstat		bytes;
+	struct blkg_rwstat		ios;
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	/* number of ios merged */
 	struct blkg_rwstat		merged;
@@ -956,6 +961,7 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
 
 /* ---------------- cgroups-support interface ---------------- */
 
+void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq);
 void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
 			      unsigned int op);
 void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op);
@@ -1062,6 +1068,8 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 
 #define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	do {			\
 	char pid_str[MAX_PID_STR_LENGTH];	\
+	if (likely(!blk_trace_note_message_enabled((bfqd)->queue)))	\
+		break;							\
 	bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH);	\
 	blk_add_cgroup_trace_msg((bfqd)->queue,				\
 			bfqg_to_blkg(bfqq_group(bfqq))->blkcg,		\
@@ -1078,6 +1086,8 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 
 #define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do {	\
 	char pid_str[MAX_PID_STR_LENGTH];	\
+	if (likely(!blk_trace_note_message_enabled((bfqd)->queue)))	\
+		break;							\
 	bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH);	\
 	blk_add_trace_msg((bfqd)->queue, "bfq%s%c " fmt, pid_str,	\
 			bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
diff --git a/block/blk-cgroup-rwstat.c b/block/blk-cgroup-rwstat.c
new file mode 100644
index 000000000000..85d5790ac49b
--- /dev/null
+++ b/block/blk-cgroup-rwstat.c
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Legacy blkg rwstat helpers enabled by CONFIG_BLK_CGROUP_RWSTAT.
+ * Do not use in new code.
+ */
+#include "blk-cgroup-rwstat.h"
+
+int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp)
+{
+	int i, ret;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++) {
+		ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp);
+		if (ret) {
+			while (--i >= 0)
+				percpu_counter_destroy(&rwstat->cpu_cnt[i]);
+			return ret;
+		}
+		atomic64_set(&rwstat->aux_cnt[i], 0);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(blkg_rwstat_init);
+
+void blkg_rwstat_exit(struct blkg_rwstat *rwstat)
+{
+	int i;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		percpu_counter_destroy(&rwstat->cpu_cnt[i]);
+}
+EXPORT_SYMBOL_GPL(blkg_rwstat_exit);
+
+/**
+ * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat
+ * @sf: seq_file to print to
+ * @pd: policy private data of interest
+ * @rwstat: rwstat to print
+ *
+ * Print @rwstat to @sf for the device assocaited with @pd.
+ */
+u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
+			 const struct blkg_rwstat_sample *rwstat)
+{
+	static const char *rwstr[] = {
+		[BLKG_RWSTAT_READ]	= "Read",
+		[BLKG_RWSTAT_WRITE]	= "Write",
+		[BLKG_RWSTAT_SYNC]	= "Sync",
+		[BLKG_RWSTAT_ASYNC]	= "Async",
+		[BLKG_RWSTAT_DISCARD]	= "Discard",
+	};
+	const char *dname = blkg_dev_name(pd->blkg);
+	u64 v;
+	int i;
+
+	if (!dname)
+		return 0;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		seq_printf(sf, "%s %s %llu\n", dname, rwstr[i],
+			   rwstat->cnt[i]);
+
+	v = rwstat->cnt[BLKG_RWSTAT_READ] +
+		rwstat->cnt[BLKG_RWSTAT_WRITE] +
+		rwstat->cnt[BLKG_RWSTAT_DISCARD];
+	seq_printf(sf, "%s Total %llu\n", dname, v);
+	return v;
+}
+EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat);
+
+/**
+ * blkg_prfill_rwstat - prfill callback for blkg_rwstat
+ * @sf: seq_file to print to
+ * @pd: policy private data of interest
+ * @off: offset to the blkg_rwstat in @pd
+ *
+ * prfill callback for printing a blkg_rwstat.
+ */
+u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
+		       int off)
+{
+	struct blkg_rwstat_sample rwstat = { };
+
+	blkg_rwstat_read((void *)pd + off, &rwstat);
+	return __blkg_prfill_rwstat(sf, pd, &rwstat);
+}
+EXPORT_SYMBOL_GPL(blkg_prfill_rwstat);
+
+/**
+ * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat
+ * @blkg: blkg of interest
+ * @pol: blkcg_policy which contains the blkg_rwstat
+ * @off: offset to the blkg_rwstat in blkg_policy_data or @blkg
+ * @sum: blkg_rwstat_sample structure containing the results
+ *
+ * Collect the blkg_rwstat specified by @blkg, @pol and @off and all its
+ * online descendants and their aux counts.  The caller must be holding the
+ * queue lock for online tests.
+ *
+ * If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it
+ * is at @off bytes into @blkg's blkg_policy_data of the policy.
+ */
+void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
+		int off, struct blkg_rwstat_sample *sum)
+{
+	struct blkcg_gq *pos_blkg;
+	struct cgroup_subsys_state *pos_css;
+	unsigned int i;
+
+	lockdep_assert_held(&blkg->q->queue_lock);
+
+	rcu_read_lock();
+	blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
+		struct blkg_rwstat *rwstat;
+
+		if (!pos_blkg->online)
+			continue;
+
+		if (pol)
+			rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off;
+		else
+			rwstat = (void *)pos_blkg + off;
+
+		for (i = 0; i < BLKG_RWSTAT_NR; i++)
+			sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum);
diff --git a/block/blk-cgroup-rwstat.h b/block/blk-cgroup-rwstat.h
new file mode 100644
index 000000000000..ee746919c41f
--- /dev/null
+++ b/block/blk-cgroup-rwstat.h
@@ -0,0 +1,149 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Legacy blkg rwstat helpers enabled by CONFIG_BLK_CGROUP_RWSTAT.
+ * Do not use in new code.
+ */
+#ifndef _BLK_CGROUP_RWSTAT_H
+#define _BLK_CGROUP_RWSTAT_H
+
+#include <linux/blk-cgroup.h>
+
+enum blkg_rwstat_type {
+	BLKG_RWSTAT_READ,
+	BLKG_RWSTAT_WRITE,
+	BLKG_RWSTAT_SYNC,
+	BLKG_RWSTAT_ASYNC,
+	BLKG_RWSTAT_DISCARD,
+
+	BLKG_RWSTAT_NR,
+	BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
+};
+
+/*
+ * blkg_[rw]stat->aux_cnt is excluded for local stats but included for
+ * recursive.  Used to carry stats of dead children.
+ */
+struct blkg_rwstat {
+	struct percpu_counter		cpu_cnt[BLKG_RWSTAT_NR];
+	atomic64_t			aux_cnt[BLKG_RWSTAT_NR];
+};
+
+struct blkg_rwstat_sample {
+	u64				cnt[BLKG_RWSTAT_NR];
+};
+
+static inline u64 blkg_rwstat_read_counter(struct blkg_rwstat *rwstat,
+		unsigned int idx)
+{
+	return atomic64_read(&rwstat->aux_cnt[idx]) +
+		percpu_counter_sum_positive(&rwstat->cpu_cnt[idx]);
+}
+
+int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp);
+void blkg_rwstat_exit(struct blkg_rwstat *rwstat);
+u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
+			 const struct blkg_rwstat_sample *rwstat);
+u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
+		       int off);
+void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
+		int off, struct blkg_rwstat_sample *sum);
+
+
+/**
+ * blkg_rwstat_add - add a value to a blkg_rwstat
+ * @rwstat: target blkg_rwstat
+ * @op: REQ_OP and flags
+ * @val: value to add
+ *
+ * Add @val to @rwstat.  The counters are chosen according to @rw.  The
+ * caller is responsible for synchronizing calls to this function.
+ */
+static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
+				   unsigned int op, uint64_t val)
+{
+	struct percpu_counter *cnt;
+
+	if (op_is_discard(op))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD];
+	else if (op_is_write(op))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE];
+	else
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ];
+
+	percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
+
+	if (op_is_sync(op))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC];
+	else
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC];
+
+	percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
+}
+
+/**
+ * blkg_rwstat_read - read the current values of a blkg_rwstat
+ * @rwstat: blkg_rwstat to read
+ *
+ * Read the current snapshot of @rwstat and return it in the aux counts.
+ */
+static inline void blkg_rwstat_read(struct blkg_rwstat *rwstat,
+		struct blkg_rwstat_sample *result)
+{
+	int i;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		result->cnt[i] =
+			percpu_counter_sum_positive(&rwstat->cpu_cnt[i]);
+}
+
+/**
+ * blkg_rwstat_total - read the total count of a blkg_rwstat
+ * @rwstat: blkg_rwstat to read
+ *
+ * Return the total count of @rwstat regardless of the IO direction.  This
+ * function can be called without synchronization and takes care of u64
+ * atomicity.
+ */
+static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat)
+{
+	struct blkg_rwstat_sample tmp = { };
+
+	blkg_rwstat_read(rwstat, &tmp);
+	return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE];
+}
+
+/**
+ * blkg_rwstat_reset - reset a blkg_rwstat
+ * @rwstat: blkg_rwstat to reset
+ */
+static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat)
+{
+	int i;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++) {
+		percpu_counter_set(&rwstat->cpu_cnt[i], 0);
+		atomic64_set(&rwstat->aux_cnt[i], 0);
+	}
+}
+
+/**
+ * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count
+ * @to: the destination blkg_rwstat
+ * @from: the source
+ *
+ * Add @from's count including the aux one to @to's aux count.
+ */
+static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to,
+				       struct blkg_rwstat *from)
+{
+	u64 sum[BLKG_RWSTAT_NR];
+	int i;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]);
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		atomic64_add(sum[i] + atomic64_read(&from->aux_cnt[i]),
+			     &to->aux_cnt[i]);
+}
+#endif	/* _BLK_CGROUP_RWSTAT_H */
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1eb8895be4c6..708dea92dac8 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -80,8 +80,7 @@ static void blkg_free(struct blkcg_gq *blkg)
 		if (blkg->pd[i])
 			blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
 
-	blkg_rwstat_exit(&blkg->stat_ios);
-	blkg_rwstat_exit(&blkg->stat_bytes);
+	free_percpu(blkg->iostat_cpu);
 	percpu_ref_exit(&blkg->refcnt);
 	kfree(blkg);
 }
@@ -146,7 +145,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 				   gfp_t gfp_mask)
 {
 	struct blkcg_gq *blkg;
-	int i;
+	int i, cpu;
 
 	/* alloc and init base part */
 	blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node);
@@ -156,8 +155,8 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 	if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask))
 		goto err_free;
 
-	if (blkg_rwstat_init(&blkg->stat_bytes, gfp_mask) ||
-	    blkg_rwstat_init(&blkg->stat_ios, gfp_mask))
+	blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask);
+	if (!blkg->iostat_cpu)
 		goto err_free;
 
 	blkg->q = q;
@@ -167,6 +166,10 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 	INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn);
 	blkg->blkcg = blkcg;
 
+	u64_stats_init(&blkg->iostat.sync);
+	for_each_possible_cpu(cpu)
+		u64_stats_init(&per_cpu_ptr(blkg->iostat_cpu, cpu)->sync);
+
 	for (i = 0; i < BLKCG_MAX_POLS; i++) {
 		struct blkcg_policy *pol = blkcg_policy[i];
 		struct blkg_policy_data *pd;
@@ -393,7 +396,6 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 static void blkg_destroy(struct blkcg_gq *blkg)
 {
 	struct blkcg *blkcg = blkg->blkcg;
-	struct blkcg_gq *parent = blkg->parent;
 	int i;
 
 	lockdep_assert_held(&blkg->q->queue_lock);
@@ -410,11 +412,6 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 			pol->pd_offline_fn(blkg->pd[i]);
 	}
 
-	if (parent) {
-		blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes);
-		blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios);
-	}
-
 	blkg->online = false;
 
 	radix_tree_delete(&blkcg->blkg_tree, blkg->q->id);
@@ -464,7 +461,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 {
 	struct blkcg *blkcg = css_to_blkcg(css);
 	struct blkcg_gq *blkg;
-	int i;
+	int i, cpu;
 
 	mutex_lock(&blkcg_pol_mutex);
 	spin_lock_irq(&blkcg->lock);
@@ -475,8 +472,12 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 	 * anyway.  If you get hit by a race, retry.
 	 */
 	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
-		blkg_rwstat_reset(&blkg->stat_bytes);
-		blkg_rwstat_reset(&blkg->stat_ios);
+		for_each_possible_cpu(cpu) {
+			struct blkg_iostat_set *bis =
+				per_cpu_ptr(blkg->iostat_cpu, cpu);
+			memset(bis, 0, sizeof(*bis));
+		}
+		memset(&blkg->iostat, 0, sizeof(blkg->iostat));
 
 		for (i = 0; i < BLKCG_MAX_POLS; i++) {
 			struct blkcg_policy *pol = blkcg_policy[i];
@@ -560,186 +561,6 @@ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v)
 }
 EXPORT_SYMBOL_GPL(__blkg_prfill_u64);
 
-/**
- * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat
- * @sf: seq_file to print to
- * @pd: policy private data of interest
- * @rwstat: rwstat to print
- *
- * Print @rwstat to @sf for the device assocaited with @pd.
- */
-u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
-			 const struct blkg_rwstat_sample *rwstat)
-{
-	static const char *rwstr[] = {
-		[BLKG_RWSTAT_READ]	= "Read",
-		[BLKG_RWSTAT_WRITE]	= "Write",
-		[BLKG_RWSTAT_SYNC]	= "Sync",
-		[BLKG_RWSTAT_ASYNC]	= "Async",
-		[BLKG_RWSTAT_DISCARD]	= "Discard",
-	};
-	const char *dname = blkg_dev_name(pd->blkg);
-	u64 v;
-	int i;
-
-	if (!dname)
-		return 0;
-
-	for (i = 0; i < BLKG_RWSTAT_NR; i++)
-		seq_printf(sf, "%s %s %llu\n", dname, rwstr[i],
-			   rwstat->cnt[i]);
-
-	v = rwstat->cnt[BLKG_RWSTAT_READ] +
-		rwstat->cnt[BLKG_RWSTAT_WRITE] +
-		rwstat->cnt[BLKG_RWSTAT_DISCARD];
-	seq_printf(sf, "%s Total %llu\n", dname, v);
-	return v;
-}
-EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat);
-
-/**
- * blkg_prfill_rwstat - prfill callback for blkg_rwstat
- * @sf: seq_file to print to
- * @pd: policy private data of interest
- * @off: offset to the blkg_rwstat in @pd
- *
- * prfill callback for printing a blkg_rwstat.
- */
-u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
-		       int off)
-{
-	struct blkg_rwstat_sample rwstat = { };
-
-	blkg_rwstat_read((void *)pd + off, &rwstat);
-	return __blkg_prfill_rwstat(sf, pd, &rwstat);
-}
-EXPORT_SYMBOL_GPL(blkg_prfill_rwstat);
-
-static u64 blkg_prfill_rwstat_field(struct seq_file *sf,
-				    struct blkg_policy_data *pd, int off)
-{
-	struct blkg_rwstat_sample rwstat = { };
-
-	blkg_rwstat_read((void *)pd->blkg + off, &rwstat);
-	return __blkg_prfill_rwstat(sf, pd, &rwstat);
-}
-
-/**
- * blkg_print_stat_bytes - seq_show callback for blkg->stat_bytes
- * @sf: seq_file to print to
- * @v: unused
- *
- * To be used as cftype->seq_show to print blkg->stat_bytes.
- * cftype->private must be set to the blkcg_policy.
- */
-int blkg_print_stat_bytes(struct seq_file *sf, void *v)
-{
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
-			  blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private,
-			  offsetof(struct blkcg_gq, stat_bytes), true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blkg_print_stat_bytes);
-
-/**
- * blkg_print_stat_bytes - seq_show callback for blkg->stat_ios
- * @sf: seq_file to print to
- * @v: unused
- *
- * To be used as cftype->seq_show to print blkg->stat_ios.  cftype->private
- * must be set to the blkcg_policy.
- */
-int blkg_print_stat_ios(struct seq_file *sf, void *v)
-{
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
-			  blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private,
-			  offsetof(struct blkcg_gq, stat_ios), true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blkg_print_stat_ios);
-
-static u64 blkg_prfill_rwstat_field_recursive(struct seq_file *sf,
-					      struct blkg_policy_data *pd,
-					      int off)
-{
-	struct blkg_rwstat_sample rwstat;
-
-	blkg_rwstat_recursive_sum(pd->blkg, NULL, off, &rwstat);
-	return __blkg_prfill_rwstat(sf, pd, &rwstat);
-}
-
-/**
- * blkg_print_stat_bytes_recursive - recursive version of blkg_print_stat_bytes
- * @sf: seq_file to print to
- * @v: unused
- */
-int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v)
-{
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
-			  blkg_prfill_rwstat_field_recursive,
-			  (void *)seq_cft(sf)->private,
-			  offsetof(struct blkcg_gq, stat_bytes), true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blkg_print_stat_bytes_recursive);
-
-/**
- * blkg_print_stat_ios_recursive - recursive version of blkg_print_stat_ios
- * @sf: seq_file to print to
- * @v: unused
- */
-int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v)
-{
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
-			  blkg_prfill_rwstat_field_recursive,
-			  (void *)seq_cft(sf)->private,
-			  offsetof(struct blkcg_gq, stat_ios), true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blkg_print_stat_ios_recursive);
-
-/**
- * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat
- * @blkg: blkg of interest
- * @pol: blkcg_policy which contains the blkg_rwstat
- * @off: offset to the blkg_rwstat in blkg_policy_data or @blkg
- * @sum: blkg_rwstat_sample structure containing the results
- *
- * Collect the blkg_rwstat specified by @blkg, @pol and @off and all its
- * online descendants and their aux counts.  The caller must be holding the
- * queue lock for online tests.
- *
- * If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it
- * is at @off bytes into @blkg's blkg_policy_data of the policy.
- */
-void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
-		int off, struct blkg_rwstat_sample *sum)
-{
-	struct blkcg_gq *pos_blkg;
-	struct cgroup_subsys_state *pos_css;
-	unsigned int i;
-
-	lockdep_assert_held(&blkg->q->queue_lock);
-
-	rcu_read_lock();
-	blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
-		struct blkg_rwstat *rwstat;
-
-		if (!pos_blkg->online)
-			continue;
-
-		if (pol)
-			rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off;
-		else
-			rwstat = (void *)pos_blkg + off;
-
-		for (i = 0; i < BLKG_RWSTAT_NR; i++)
-			sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i);
-	}
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum);
-
 /* Performs queue bypass and policy enabled checks then looks up blkg. */
 static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg,
 					  const struct blkcg_policy *pol,
@@ -923,16 +744,18 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
 	struct blkcg_gq *blkg;
 
+	cgroup_rstat_flush(blkcg->css.cgroup);
 	rcu_read_lock();
 
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
+		struct blkg_iostat_set *bis = &blkg->iostat;
 		const char *dname;
 		char *buf;
-		struct blkg_rwstat_sample rwstat;
 		u64 rbytes, wbytes, rios, wios, dbytes, dios;
 		size_t size = seq_get_buf(sf, &buf), off = 0;
 		int i;
 		bool has_stats = false;
+		unsigned seq;
 
 		spin_lock_irq(&blkg->q->queue_lock);
 
@@ -951,17 +774,16 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 		 */
 		off += scnprintf(buf+off, size-off, "%s ", dname);
 
-		blkg_rwstat_recursive_sum(blkg, NULL,
-				offsetof(struct blkcg_gq, stat_bytes), &rwstat);
-		rbytes = rwstat.cnt[BLKG_RWSTAT_READ];
-		wbytes = rwstat.cnt[BLKG_RWSTAT_WRITE];
-		dbytes = rwstat.cnt[BLKG_RWSTAT_DISCARD];
+		do {
+			seq = u64_stats_fetch_begin(&bis->sync);
 
-		blkg_rwstat_recursive_sum(blkg, NULL,
-					offsetof(struct blkcg_gq, stat_ios), &rwstat);
-		rios = rwstat.cnt[BLKG_RWSTAT_READ];
-		wios = rwstat.cnt[BLKG_RWSTAT_WRITE];
-		dios = rwstat.cnt[BLKG_RWSTAT_DISCARD];
+			rbytes = bis->cur.bytes[BLKG_IOSTAT_READ];
+			wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE];
+			dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD];
+			rios = bis->cur.ios[BLKG_IOSTAT_READ];
+			wios = bis->cur.ios[BLKG_IOSTAT_WRITE];
+			dios = bis->cur.ios[BLKG_IOSTAT_DISCARD];
+		} while (u64_stats_fetch_retry(&bis->sync, seq));
 
 		if (rbytes || wbytes || rios || wios) {
 			has_stats = true;
@@ -1297,6 +1119,77 @@ static int blkcg_can_attach(struct cgroup_taskset *tset)
 	return ret;
 }
 
+static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src)
+{
+	int i;
+
+	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
+		dst->bytes[i] = src->bytes[i];
+		dst->ios[i] = src->ios[i];
+	}
+}
+
+static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src)
+{
+	int i;
+
+	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
+		dst->bytes[i] += src->bytes[i];
+		dst->ios[i] += src->ios[i];
+	}
+}
+
+static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src)
+{
+	int i;
+
+	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
+		dst->bytes[i] -= src->bytes[i];
+		dst->ios[i] -= src->ios[i];
+	}
+}
+
+static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
+{
+	struct blkcg *blkcg = css_to_blkcg(css);
+	struct blkcg_gq *blkg;
+
+	rcu_read_lock();
+
+	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
+		struct blkcg_gq *parent = blkg->parent;
+		struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu);
+		struct blkg_iostat cur, delta;
+		unsigned seq;
+
+		/* fetch the current per-cpu values */
+		do {
+			seq = u64_stats_fetch_begin(&bisc->sync);
+			blkg_iostat_set(&cur, &bisc->cur);
+		} while (u64_stats_fetch_retry(&bisc->sync, seq));
+
+		/* propagate percpu delta to global */
+		u64_stats_update_begin(&blkg->iostat.sync);
+		blkg_iostat_set(&delta, &cur);
+		blkg_iostat_sub(&delta, &bisc->last);
+		blkg_iostat_add(&blkg->iostat.cur, &delta);
+		blkg_iostat_add(&bisc->last, &delta);
+		u64_stats_update_end(&blkg->iostat.sync);
+
+		/* propagate global delta to parent */
+		if (parent) {
+			u64_stats_update_begin(&parent->iostat.sync);
+			blkg_iostat_set(&delta, &blkg->iostat.cur);
+			blkg_iostat_sub(&delta, &blkg->iostat.last);
+			blkg_iostat_add(&parent->iostat.cur, &delta);
+			blkg_iostat_add(&blkg->iostat.last, &delta);
+			u64_stats_update_end(&parent->iostat.sync);
+		}
+	}
+
+	rcu_read_unlock();
+}
+
 static void blkcg_bind(struct cgroup_subsys_state *root_css)
 {
 	int i;
@@ -1329,6 +1222,7 @@ struct cgroup_subsys io_cgrp_subsys = {
 	.css_offline = blkcg_css_offline,
 	.css_free = blkcg_css_free,
 	.can_attach = blkcg_can_attach,
+	.css_rstat_flush = blkcg_rstat_flush,
 	.bind = blkcg_bind,
 	.dfl_cftypes = blkcg_files,
 	.legacy_cftypes = blkcg_legacy_files,
diff --git a/block/blk-core.c b/block/blk-core.c
index d5e668ec751b..a1e228752083 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -132,6 +132,9 @@ static const char *const blk_op_name[] = {
 	REQ_OP_NAME(SECURE_ERASE),
 	REQ_OP_NAME(ZONE_RESET),
 	REQ_OP_NAME(ZONE_RESET_ALL),
+	REQ_OP_NAME(ZONE_OPEN),
+	REQ_OP_NAME(ZONE_CLOSE),
+	REQ_OP_NAME(ZONE_FINISH),
 	REQ_OP_NAME(WRITE_SAME),
 	REQ_OP_NAME(WRITE_ZEROES),
 	REQ_OP_NAME(SCSI_IN),
@@ -336,14 +339,14 @@ EXPORT_SYMBOL_GPL(blk_set_queue_dying);
  */
 void blk_cleanup_queue(struct request_queue *q)
 {
+	WARN_ON_ONCE(blk_queue_registered(q));
+
 	/* mark @q DYING, no new request or merges will be allowed afterwards */
-	mutex_lock(&q->sysfs_lock);
 	blk_set_queue_dying(q);
 
 	blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q);
 	blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
 	blk_queue_flag_set(QUEUE_FLAG_DYING, q);
-	mutex_unlock(&q->sysfs_lock);
 
 	/*
 	 * Drain all requests queued before DYING marking. Set DEAD flag to
@@ -848,11 +851,7 @@ static inline int blk_partition_remap(struct bio *bio)
 	if (unlikely(bio_check_ro(bio, p)))
 		goto out;
 
-	/*
-	 * Zone reset does not include bi_size so bio_sectors() is always 0.
-	 * Include a test for the reset op code and perform the remap if needed.
-	 */
-	if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) {
+	if (bio_sectors(bio)) {
 		if (bio_check_eod(bio, part_nr_sects_read(p)))
 			goto out;
 		bio->bi_iter.bi_sector += p->start_sect;
@@ -936,6 +935,9 @@ generic_make_request_checks(struct bio *bio)
 			goto not_supported;
 		break;
 	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_OPEN:
+	case REQ_OP_ZONE_CLOSE:
+	case REQ_OP_ZONE_FINISH:
 		if (!blk_queue_is_zoned(q))
 			goto not_supported;
 		break;
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 1db44ca0f4a6..e20a852ae432 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -55,6 +55,8 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	rq->rq_disk = bd_disk;
 	rq->end_io = done;
 
+	blk_account_io_start(rq, true);
+
 	/*
 	 * don't check dying flag for MQ because the request won't
 	 * be reused after dying flag is set
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 1eec9cbe5a0a..1777346baf06 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -136,6 +136,17 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front)
 	blk_mq_add_to_requeue_list(rq, add_front, true);
 }
 
+static void blk_account_io_flush(struct request *rq)
+{
+	struct hd_struct *part = &rq->rq_disk->part0;
+
+	part_stat_lock();
+	part_stat_inc(part, ios[STAT_FLUSH]);
+	part_stat_add(part, nsecs[STAT_FLUSH],
+		      ktime_get_ns() - rq->start_time_ns);
+	part_stat_unlock();
+}
+
 /**
  * blk_flush_complete_seq - complete flush sequence
  * @rq: PREFLUSH/FUA request being sequenced
@@ -185,7 +196,7 @@ static void blk_flush_complete_seq(struct request *rq,
 
 	case REQ_FSEQ_DONE:
 		/*
-		 * @rq was previously adjusted by blk_flush_issue() for
+		 * @rq was previously adjusted by blk_insert_flush() for
 		 * flush sequencing and may already have gone through the
 		 * flush data request completion path.  Restore @rq for
 		 * normal completion and end it.
@@ -212,6 +223,8 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
 	struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx);
 	struct blk_mq_hw_ctx *hctx;
 
+	blk_account_io_flush(flush_rq);
+
 	/* release the tag's ownership to the req cloned from */
 	spin_lock_irqsave(&fq->mq_flush_lock, flags);
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 48e6725b32ee..d783bdc4559b 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -293,7 +293,7 @@ split:
 void __blk_queue_split(struct request_queue *q, struct bio **bio,
 		unsigned int *nr_segs)
 {
-	struct bio *split;
+	struct bio *split = NULL;
 
 	switch (bio_op(*bio)) {
 	case REQ_OP_DISCARD:
@@ -309,6 +309,21 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio,
 				nr_segs);
 		break;
 	default:
+		/*
+		 * All drivers must accept single-segments bios that are <=
+		 * PAGE_SIZE.  This is a quick and dirty check that relies on
+		 * the fact that bi_io_vec[0] is always valid if a bio has data.
+		 * The check might lead to occasional false negatives when bios
+		 * are cloned, but compared to the performance impact of cloned
+		 * bios themselves the loop below doesn't matter anyway.
+		 */
+		if (!q->limits.chunk_sectors &&
+		    (*bio)->bi_vcnt == 1 &&
+		    ((*bio)->bi_io_vec[0].bv_len +
+		     (*bio)->bi_io_vec[0].bv_offset) <= PAGE_SIZE) {
+			*nr_segs = 1;
+			break;
+		}
 		split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs);
 		break;
 	}
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index a0d3ce30fa08..062229395a50 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -74,10 +74,8 @@ static ssize_t blk_mq_sysfs_show(struct kobject *kobj, struct attribute *attr,
 	if (!entry->show)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->show(ctx, page);
+	res = entry->show(ctx, page);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -97,10 +95,8 @@ static ssize_t blk_mq_sysfs_store(struct kobject *kobj, struct attribute *attr,
 	if (!entry->store)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->store(ctx, page, length);
+	res = entry->store(ctx, page, length);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -120,10 +116,8 @@ static ssize_t blk_mq_hw_sysfs_show(struct kobject *kobj,
 	if (!entry->show)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->show(hctx, page);
+	res = entry->show(hctx, page);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -144,10 +138,8 @@ static ssize_t blk_mq_hw_sysfs_store(struct kobject *kobj,
 	if (!entry->store)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->store(hctx, page, length);
+	res = entry->store(hctx, page, length);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -166,20 +158,25 @@ static ssize_t blk_mq_hw_sysfs_nr_reserved_tags_show(struct blk_mq_hw_ctx *hctx,
 
 static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
 {
+	const size_t size = PAGE_SIZE - 1;
 	unsigned int i, first = 1;
-	ssize_t ret = 0;
+	int ret = 0, pos = 0;
 
 	for_each_cpu(i, hctx->cpumask) {
 		if (first)
-			ret += sprintf(ret + page, "%u", i);
+			ret = snprintf(pos + page, size - pos, "%u", i);
 		else
-			ret += sprintf(ret + page, ", %u", i);
+			ret = snprintf(pos + page, size - pos, ", %u", i);
+
+		if (ret >= size - pos)
+			break;
 
 		first = 0;
+		pos += ret;
 	}
 
-	ret += sprintf(ret + page, "\n");
-	return ret;
+	ret = snprintf(pos + page, size + 1 - pos, "\n");
+	return pos + ret;
 }
 
 static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_tags = {
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 008388e82b5c..fbacde454718 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -15,14 +15,6 @@
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
 
-bool blk_mq_has_free_tags(struct blk_mq_tags *tags)
-{
-	if (!tags)
-		return true;
-
-	return sbitmap_any_bit_clear(&tags->bitmap_tags.sb);
-}
-
 /*
  * If a previously inactive queue goes active, bump the active user count.
  * We need to do this before try to allocate driver tag, then even if fail
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 61deab0b5a5a..15bc74acb57e 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -28,7 +28,6 @@ extern void blk_mq_free_tags(struct blk_mq_tags *tags);
 extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
 extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags,
 			   struct blk_mq_ctx *ctx, unsigned int tag);
-extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags);
 extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_tags **tags,
 					unsigned int depth, bool can_grow);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ec791156e9cc..323c9cb28066 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -93,7 +93,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
 
 struct mq_inflight {
 	struct hd_struct *part;
-	unsigned int *inflight;
+	unsigned int inflight[2];
 };
 
 static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
@@ -102,45 +102,29 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
 {
 	struct mq_inflight *mi = priv;
 
-	/*
-	 * index[0] counts the specific partition that was asked for.
-	 */
 	if (rq->part == mi->part)
-		mi->inflight[0]++;
+		mi->inflight[rq_data_dir(rq)]++;
 
 	return true;
 }
 
 unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part)
 {
-	unsigned inflight[2];
-	struct mq_inflight mi = { .part = part, .inflight = inflight, };
+	struct mq_inflight mi = { .part = part };
 
-	inflight[0] = inflight[1] = 0;
 	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
 
-	return inflight[0];
-}
-
-static bool blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx,
-				     struct request *rq, void *priv,
-				     bool reserved)
-{
-	struct mq_inflight *mi = priv;
-
-	if (rq->part == mi->part)
-		mi->inflight[rq_data_dir(rq)]++;
-
-	return true;
+	return mi.inflight[0] + mi.inflight[1];
 }
 
 void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
 			 unsigned int inflight[2])
 {
-	struct mq_inflight mi = { .part = part, .inflight = inflight, };
+	struct mq_inflight mi = { .part = part };
 
-	inflight[0] = inflight[1] = 0;
-	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi);
+	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
+	inflight[0] = mi.inflight[0];
+	inflight[1] = mi.inflight[1];
 }
 
 void blk_freeze_queue_start(struct request_queue *q)
@@ -276,12 +260,6 @@ void blk_mq_wake_waiters(struct request_queue *q)
 			blk_mq_tag_wakeup_all(hctx->tags, true);
 }
 
-bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
-{
-	return blk_mq_has_free_tags(hctx->tags);
-}
-EXPORT_SYMBOL(blk_mq_can_queue);
-
 /*
  * Only need start/end time stamping if we have iostat or
  * blk stats enabled, or using an IO scheduler.
@@ -663,18 +641,6 @@ bool blk_mq_complete_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
-int blk_mq_request_started(struct request *rq)
-{
-	return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
-}
-EXPORT_SYMBOL_GPL(blk_mq_request_started);
-
-int blk_mq_request_completed(struct request *rq)
-{
-	return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE;
-}
-EXPORT_SYMBOL_GPL(blk_mq_request_completed);
-
 void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
@@ -1064,7 +1030,7 @@ bool blk_mq_get_driver_tag(struct request *rq)
 	bool shared;
 
 	if (rq->tag != -1)
-		goto done;
+		return true;
 
 	if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
 		data.flags |= BLK_MQ_REQ_RESERVED;
@@ -1079,7 +1045,6 @@ bool blk_mq_get_driver_tag(struct request *rq)
 		data.hctx->tags->rqs[rq->tag] = rq;
 	}
 
-done:
 	return rq->tag != -1;
 }
 
@@ -1486,7 +1451,7 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 }
 EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
 
-bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 {
 	int srcu_idx;
 	bool need_run;
@@ -1504,12 +1469,8 @@ bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 		blk_mq_hctx_has_pending(hctx);
 	hctx_unlock(hctx, srcu_idx);
 
-	if (need_run) {
+	if (need_run)
 		__blk_mq_delay_run_hw_queue(hctx, async, 0);
-		return true;
-	}
-
-	return false;
 }
 EXPORT_SYMBOL(blk_mq_run_hw_queue);
 
@@ -2789,6 +2750,23 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	int i, j, end;
 	struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx;
 
+	if (q->nr_hw_queues < set->nr_hw_queues) {
+		struct blk_mq_hw_ctx **new_hctxs;
+
+		new_hctxs = kcalloc_node(set->nr_hw_queues,
+				       sizeof(*new_hctxs), GFP_KERNEL,
+				       set->numa_node);
+		if (!new_hctxs)
+			return;
+		if (hctxs)
+			memcpy(new_hctxs, hctxs, q->nr_hw_queues *
+			       sizeof(*hctxs));
+		q->queue_hw_ctx = new_hctxs;
+		q->nr_hw_queues = set->nr_hw_queues;
+		kfree(hctxs);
+		hctxs = new_hctxs;
+	}
+
 	/* protect against switching io scheduler  */
 	mutex_lock(&q->sysfs_lock);
 	for (i = 0; i < set->nr_hw_queues; i++) {
@@ -2844,19 +2822,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	mutex_unlock(&q->sysfs_lock);
 }
 
-/*
- * Maximum number of hardware queues we support. For single sets, we'll never
- * have more than the CPUs (software queues). For multiple sets, the tag_set
- * user may have set ->nr_hw_queues larger.
- */
-static unsigned int nr_hw_queues(struct blk_mq_tag_set *set)
-{
-	if (set->nr_maps == 1)
-		return nr_cpu_ids;
-
-	return max(set->nr_hw_queues, nr_cpu_ids);
-}
-
 struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 						  struct request_queue *q,
 						  bool elevator_init)
@@ -2876,12 +2841,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	/* init q->mq_kobj and sw queues' kobjects */
 	blk_mq_sysfs_init(q);
 
-	q->nr_queues = nr_hw_queues(set);
-	q->queue_hw_ctx = kcalloc_node(q->nr_queues, sizeof(*(q->queue_hw_ctx)),
-						GFP_KERNEL, set->numa_node);
-	if (!q->queue_hw_ctx)
-		goto err_sys_init;
-
 	INIT_LIST_HEAD(&q->unused_hctx_list);
 	spin_lock_init(&q->unused_hctx_lock);
 
@@ -2929,7 +2888,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 err_hctxs:
 	kfree(q->queue_hw_ctx);
 	q->nr_hw_queues = 0;
-err_sys_init:
 	blk_mq_sysfs_deinit(q);
 err_poll:
 	blk_stat_free_callback(q->poll_cb);
@@ -3030,6 +2988,29 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 	}
 }
 
+static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set,
+				  int cur_nr_hw_queues, int new_nr_hw_queues)
+{
+	struct blk_mq_tags **new_tags;
+
+	if (cur_nr_hw_queues >= new_nr_hw_queues)
+		return 0;
+
+	new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *),
+				GFP_KERNEL, set->numa_node);
+	if (!new_tags)
+		return -ENOMEM;
+
+	if (set->tags)
+		memcpy(new_tags, set->tags, cur_nr_hw_queues *
+		       sizeof(*set->tags));
+	kfree(set->tags);
+	set->tags = new_tags;
+	set->nr_hw_queues = new_nr_hw_queues;
+
+	return 0;
+}
+
 /*
  * Alloc a tag set to be associated with one or more request queues.
  * May fail with EINVAL for various error conditions. May adjust the
@@ -3083,9 +3064,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids)
 		set->nr_hw_queues = nr_cpu_ids;
 
-	set->tags = kcalloc_node(nr_hw_queues(set), sizeof(struct blk_mq_tags *),
-				 GFP_KERNEL, set->numa_node);
-	if (!set->tags)
+	if (blk_mq_realloc_tag_set_tags(set, 0, set->nr_hw_queues) < 0)
 		return -ENOMEM;
 
 	ret = -ENOMEM;
@@ -3126,7 +3105,7 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 {
 	int i, j;
 
-	for (i = 0; i < nr_hw_queues(set); i++)
+	for (i = 0; i < set->nr_hw_queues; i++)
 		blk_mq_free_map_and_requests(set, i);
 
 	for (j = 0; j < set->nr_maps; j++) {
@@ -3271,10 +3250,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_freeze_queue(q);
 	/*
-	 * Sync with blk_mq_queue_tag_busy_iter.
-	 */
-	synchronize_rcu();
-	/*
 	 * Switch IO scheduler to 'none', cleaning up the data associated
 	 * with the previous scheduler. We will switch back once we are done
 	 * updating the new sw to hw queue mappings.
@@ -3288,6 +3263,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		blk_mq_sysfs_unregister(q);
 	}
 
+	if (blk_mq_realloc_tag_set_tags(set, set->nr_hw_queues, nr_hw_queues) <
+	    0)
+		goto reregister;
+
 	prev_nr_hw_queues = set->nr_hw_queues;
 	set->nr_hw_queues = nr_hw_queues;
 	blk_mq_update_queue_map(set);
@@ -3304,6 +3283,7 @@ fallback:
 		blk_mq_map_swqueue(q);
 	}
 
+reregister:
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_sysfs_register(q);
 		blk_mq_debugfs_register_hctxs(q);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 32c62c64e6c2..eaaca8fc1c28 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -128,15 +128,6 @@ extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
 
 void blk_mq_release(struct request_queue *q);
 
-/**
- * blk_mq_rq_state() - read the current MQ_RQ_* state of a request
- * @rq: target request.
- */
-static inline enum mq_rq_state blk_mq_rq_state(struct request *rq)
-{
-	return READ_ONCE(rq->state);
-}
-
 static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
 					   unsigned int cpu)
 {
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 457d9ba3eb20..6e7ec87d49fa 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -42,17 +42,13 @@ static __latent_entropy void blk_done_softirq(struct softirq_action *h)
 static void trigger_softirq(void *data)
 {
 	struct request *rq = data;
-	unsigned long flags;
 	struct list_head *list;
 
-	local_irq_save(flags);
 	list = this_cpu_ptr(&blk_cpu_done);
 	list_add_tail(&rq->ipi_list, list);
 
 	if (list->next == &rq->ipi_list)
 		raise_softirq_irqoff(BLOCK_SOFTIRQ);
-
-	local_irq_restore(flags);
 }
 
 /*
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 940f15d600f8..7da302ff88d0 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -53,7 +53,7 @@ void blk_stat_add(struct request *rq, u64 now)
 	struct request_queue *q = rq->q;
 	struct blk_stat_callback *cb;
 	struct blk_rq_stat *stat;
-	int bucket;
+	int bucket, cpu;
 	u64 value;
 
 	value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0;
@@ -61,6 +61,7 @@ void blk_stat_add(struct request *rq, u64 now)
 	blk_throtl_stat_add(rq, value);
 
 	rcu_read_lock();
+	cpu = get_cpu();
 	list_for_each_entry_rcu(cb, &q->stats->callbacks, list) {
 		if (!blk_stat_is_active(cb))
 			continue;
@@ -69,10 +70,10 @@ void blk_stat_add(struct request *rq, u64 now)
 		if (bucket < 0)
 			continue;
 
-		stat = &get_cpu_ptr(cb->cpu_stat)[bucket];
+		stat = &per_cpu_ptr(cb->cpu_stat, cpu)[bucket];
 		blk_rq_stat_add(stat, value);
-		put_cpu_ptr(cb->cpu_stat);
 	}
+	put_cpu();
 	rcu_read_unlock();
 }
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 46f5198be017..fca9b158f4a0 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -801,10 +801,6 @@ queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 	if (!entry->show)
 		return -EIO;
 	mutex_lock(&q->sysfs_lock);
-	if (blk_queue_dying(q)) {
-		mutex_unlock(&q->sysfs_lock);
-		return -ENOENT;
-	}
 	res = entry->show(q, page);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
@@ -823,10 +819,6 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
 
 	q = container_of(kobj, struct request_queue, kobj);
 	mutex_lock(&q->sysfs_lock);
-	if (blk_queue_dying(q)) {
-		mutex_unlock(&q->sysfs_lock);
-		return -ENOENT;
-	}
 	res = entry->store(q, page, length);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 18f773e52dfb..98233c9c65a8 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -12,6 +12,7 @@
 #include <linux/blktrace_api.h>
 #include <linux/blk-cgroup.h>
 #include "blk.h"
+#include "blk-cgroup-rwstat.h"
 
 /* Max dispatch from a group in 1 round */
 static int throtl_grp_quantum = 8;
@@ -176,6 +177,9 @@ struct throtl_grp {
 	unsigned int bio_cnt; /* total bios */
 	unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
 	unsigned long bio_cnt_reset_time;
+
+	struct blkg_rwstat stat_bytes;
+	struct blkg_rwstat stat_ios;
 };
 
 /* We measure latency for request size from <= 4k to >= 1M */
@@ -489,6 +493,12 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp,
 	if (!tg)
 		return NULL;
 
+	if (blkg_rwstat_init(&tg->stat_bytes, gfp))
+		goto err_free_tg;
+
+	if (blkg_rwstat_init(&tg->stat_ios, gfp))
+		goto err_exit_stat_bytes;
+
 	throtl_service_queue_init(&tg->service_queue);
 
 	for (rw = READ; rw <= WRITE; rw++) {
@@ -513,6 +523,12 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp,
 	tg->idletime_threshold_conf = DFL_IDLE_THRESHOLD;
 
 	return &tg->pd;
+
+err_exit_stat_bytes:
+	blkg_rwstat_exit(&tg->stat_bytes);
+err_free_tg:
+	kfree(tg);
+	return NULL;
 }
 
 static void throtl_pd_init(struct blkg_policy_data *pd)
@@ -611,6 +627,8 @@ static void throtl_pd_free(struct blkg_policy_data *pd)
 	struct throtl_grp *tg = pd_to_tg(pd);
 
 	del_timer_sync(&tg->service_queue.pending_timer);
+	blkg_rwstat_exit(&tg->stat_bytes);
+	blkg_rwstat_exit(&tg->stat_ios);
 	kfree(tg);
 }
 
@@ -1464,6 +1482,32 @@ static ssize_t tg_set_conf_uint(struct kernfs_open_file *of,
 	return tg_set_conf(of, buf, nbytes, off, false);
 }
 
+static int tg_print_rwstat(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  blkg_prfill_rwstat, &blkcg_policy_throtl,
+			  seq_cft(sf)->private, true);
+	return 0;
+}
+
+static u64 tg_prfill_rwstat_recursive(struct seq_file *sf,
+				      struct blkg_policy_data *pd, int off)
+{
+	struct blkg_rwstat_sample sum;
+
+	blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_throtl, off,
+				  &sum);
+	return __blkg_prfill_rwstat(sf, pd, &sum);
+}
+
+static int tg_print_rwstat_recursive(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  tg_prfill_rwstat_recursive, &blkcg_policy_throtl,
+			  seq_cft(sf)->private, true);
+	return 0;
+}
+
 static struct cftype throtl_legacy_files[] = {
 	{
 		.name = "throttle.read_bps_device",
@@ -1491,23 +1535,23 @@ static struct cftype throtl_legacy_files[] = {
 	},
 	{
 		.name = "throttle.io_service_bytes",
-		.private = (unsigned long)&blkcg_policy_throtl,
-		.seq_show = blkg_print_stat_bytes,
+		.private = offsetof(struct throtl_grp, stat_bytes),
+		.seq_show = tg_print_rwstat,
 	},
 	{
 		.name = "throttle.io_service_bytes_recursive",
-		.private = (unsigned long)&blkcg_policy_throtl,
-		.seq_show = blkg_print_stat_bytes_recursive,
+		.private = offsetof(struct throtl_grp, stat_bytes),
+		.seq_show = tg_print_rwstat_recursive,
 	},
 	{
 		.name = "throttle.io_serviced",
-		.private = (unsigned long)&blkcg_policy_throtl,
-		.seq_show = blkg_print_stat_ios,
+		.private = offsetof(struct throtl_grp, stat_ios),
+		.seq_show = tg_print_rwstat,
 	},
 	{
 		.name = "throttle.io_serviced_recursive",
-		.private = (unsigned long)&blkcg_policy_throtl,
-		.seq_show = blkg_print_stat_ios_recursive,
+		.private = offsetof(struct throtl_grp, stat_ios),
+		.seq_show = tg_print_rwstat_recursive,
 	},
 	{ }	/* terminate */
 };
@@ -2127,7 +2171,16 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	/* see throtl_charge_bio() */
-	if (bio_flagged(bio, BIO_THROTTLED) || !tg->has_rules[rw])
+	if (bio_flagged(bio, BIO_THROTTLED))
+		goto out;
+
+	if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) {
+		blkg_rwstat_add(&tg->stat_bytes, bio->bi_opf,
+				bio->bi_iter.bi_size);
+		blkg_rwstat_add(&tg->stat_ios, bio->bi_opf, 1);
+	}
+
+	if (!tg->has_rules[rw])
 		goto out;
 
 	spin_lock_irq(&q->queue_lock);
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 4bc5f260248a..6fad6f3f6980 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -93,172 +93,85 @@ unsigned int blkdev_nr_zones(struct block_device *bdev)
 	if (!blk_queue_is_zoned(q))
 		return 0;
 
-	return __blkdev_nr_zones(q, bdev->bd_part->nr_sects);
+	return __blkdev_nr_zones(q, get_capacity(bdev->bd_disk));
 }
 EXPORT_SYMBOL_GPL(blkdev_nr_zones);
 
-/*
- * Check that a zone report belongs to this partition, and if yes, fix its start
- * sector and write pointer and return true. Return false otherwise.
- */
-static bool blkdev_report_zone(struct block_device *bdev, struct blk_zone *rep)
-{
-	sector_t offset = get_start_sect(bdev);
-
-	if (rep->start < offset)
-		return false;
-
-	rep->start -= offset;
-	if (rep->start + rep->len > bdev->bd_part->nr_sects)
-		return false;
-
-	if (rep->type == BLK_ZONE_TYPE_CONVENTIONAL)
-		rep->wp = rep->start + rep->len;
-	else
-		rep->wp -= offset;
-	return true;
-}
-
-static int blk_report_zones(struct gendisk *disk, sector_t sector,
-			    struct blk_zone *zones, unsigned int *nr_zones)
-{
-	struct request_queue *q = disk->queue;
-	unsigned int z = 0, n, nrz = *nr_zones;
-	sector_t capacity = get_capacity(disk);
-	int ret;
-
-	while (z < nrz && sector < capacity) {
-		n = nrz - z;
-		ret = disk->fops->report_zones(disk, sector, &zones[z], &n);
-		if (ret)
-			return ret;
-		if (!n)
-			break;
-		sector += blk_queue_zone_sectors(q) * n;
-		z += n;
-	}
-
-	WARN_ON(z > *nr_zones);
-	*nr_zones = z;
-
-	return 0;
-}
-
 /**
  * blkdev_report_zones - Get zones information
  * @bdev:	Target block device
  * @sector:	Sector from which to report zones
- * @zones:	Array of zone structures where to return the zones information
- * @nr_zones:	Number of zone structures in the zone array
+ * @nr_zones:	Maximum number of zones to report
+ * @cb:		Callback function called for each reported zone
+ * @data:	Private data for the callback
  *
  * Description:
- *    Get zone information starting from the zone containing @sector.
- *    The number of zone information reported may be less than the number
- *    requested by @nr_zones. The number of zones actually reported is
- *    returned in @nr_zones.
- *    The caller must use memalloc_noXX_save/restore() calls to control
- *    memory allocations done within this function (zone array and command
- *    buffer allocation by the device driver).
+ *    Get zone information starting from the zone containing @sector for at most
+ *    @nr_zones, and call @cb for each zone reported by the device.
+ *    To report all zones in a device starting from @sector, the BLK_ALL_ZONES
+ *    constant can be passed to @nr_zones.
+ *    Returns the number of zones reported by the device, or a negative errno
+ *    value in case of failure.
+ *
+ *    Note: The caller must use memalloc_noXX_save/restore() calls to control
+ *    memory allocations done within this function.
  */
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
-			struct blk_zone *zones, unsigned int *nr_zones)
+			unsigned int nr_zones, report_zones_cb cb, void *data)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-	unsigned int i, nrz;
-	int ret;
-
-	if (!blk_queue_is_zoned(q))
-		return -EOPNOTSUPP;
+	struct gendisk *disk = bdev->bd_disk;
+	sector_t capacity = get_capacity(disk);
 
-	/*
-	 * A block device that advertized itself as zoned must have a
-	 * report_zones method. If it does not have one defined, the device
-	 * driver has a bug. So warn about that.
-	 */
-	if (WARN_ON_ONCE(!bdev->bd_disk->fops->report_zones))
+	if (!blk_queue_is_zoned(bdev_get_queue(bdev)) ||
+	    WARN_ON_ONCE(!disk->fops->report_zones))
 		return -EOPNOTSUPP;
 
-	if (!*nr_zones || sector >= bdev->bd_part->nr_sects) {
-		*nr_zones = 0;
+	if (!nr_zones || sector >= capacity)
 		return 0;
-	}
-
-	nrz = min(*nr_zones,
-		  __blkdev_nr_zones(q, bdev->bd_part->nr_sects - sector));
-	ret = blk_report_zones(bdev->bd_disk, get_start_sect(bdev) + sector,
-			       zones, &nrz);
-	if (ret)
-		return ret;
-
-	for (i = 0; i < nrz; i++) {
-		if (!blkdev_report_zone(bdev, zones))
-			break;
-		zones++;
-	}
 
-	*nr_zones = i;
-
-	return 0;
+	return disk->fops->report_zones(disk, sector, nr_zones, cb, data);
 }
 EXPORT_SYMBOL_GPL(blkdev_report_zones);
 
-/*
- * Special case of zone reset operation to reset all zones in one command,
- * useful for applications like mkfs.
- */
-static int __blkdev_reset_all_zones(struct block_device *bdev, gfp_t gfp_mask)
-{
-	struct bio *bio = bio_alloc(gfp_mask, 0);
-	int ret;
-
-	/* across the zones operations, don't need any sectors */
-	bio_set_dev(bio, bdev);
-	bio_set_op_attrs(bio, REQ_OP_ZONE_RESET_ALL, 0);
-
-	ret = submit_bio_wait(bio);
-	bio_put(bio);
-
-	return ret;
-}
-
 static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev,
+						sector_t sector,
 						sector_t nr_sectors)
 {
 	if (!blk_queue_zone_resetall(bdev_get_queue(bdev)))
 		return false;
 
-	if (nr_sectors != part_nr_sects_read(bdev->bd_part))
-		return false;
 	/*
-	 * REQ_OP_ZONE_RESET_ALL can be executed only if the block device is
-	 * the entire disk, that is, if the blocks device start offset is 0 and
-	 * its capacity is the same as the entire disk.
+	 * REQ_OP_ZONE_RESET_ALL can be executed only if the number of sectors
+	 * of the applicable zone range is the entire disk.
 	 */
-	return get_start_sect(bdev) == 0 &&
-	       part_nr_sects_read(bdev->bd_part) == get_capacity(bdev->bd_disk);
+	return !sector && nr_sectors == get_capacity(bdev->bd_disk);
 }
 
 /**
- * blkdev_reset_zones - Reset zones write pointer
+ * blkdev_zone_mgmt - Execute a zone management operation on a range of zones
  * @bdev:	Target block device
- * @sector:	Start sector of the first zone to reset
- * @nr_sectors:	Number of sectors, at least the length of one zone
+ * @op:		Operation to be performed on the zones
+ * @sector:	Start sector of the first zone to operate on
+ * @nr_sectors:	Number of sectors, should be at least the length of one zone and
+ *		must be zone size aligned.
  * @gfp_mask:	Memory allocation flags (for bio_alloc)
  *
  * Description:
- *    Reset the write pointer of the zones contained in the range
+ *    Perform the specified operation on the range of zones specified by
  *    @sector..@sector+@nr_sectors. Specifying the entire disk sector range
  *    is valid, but the specified range should not contain conventional zones.
+ *    The operation to execute on each zone can be a zone reset, open, close
+ *    or finish request.
  */
-int blkdev_reset_zones(struct block_device *bdev,
-		       sector_t sector, sector_t nr_sectors,
-		       gfp_t gfp_mask)
+int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
+		     sector_t sector, sector_t nr_sectors,
+		     gfp_t gfp_mask)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
-	sector_t zone_sectors;
+	sector_t zone_sectors = blk_queue_zone_sectors(q);
+	sector_t capacity = get_capacity(bdev->bd_disk);
 	sector_t end_sector = sector + nr_sectors;
 	struct bio *bio = NULL;
-	struct blk_plug plug;
 	int ret;
 
 	if (!blk_queue_is_zoned(q))
@@ -267,45 +180,62 @@ int blkdev_reset_zones(struct block_device *bdev,
 	if (bdev_read_only(bdev))
 		return -EPERM;
 
-	if (!nr_sectors || end_sector > bdev->bd_part->nr_sects)
+	if (!op_is_zone_mgmt(op))
+		return -EOPNOTSUPP;
+
+	if (!nr_sectors || end_sector > capacity)
 		/* Out of range */
 		return -EINVAL;
 
-	if (blkdev_allow_reset_all_zones(bdev, nr_sectors))
-		return  __blkdev_reset_all_zones(bdev, gfp_mask);
-
 	/* Check alignment (handle eventual smaller last zone) */
-	zone_sectors = blk_queue_zone_sectors(q);
 	if (sector & (zone_sectors - 1))
 		return -EINVAL;
 
-	if ((nr_sectors & (zone_sectors - 1)) &&
-	    end_sector != bdev->bd_part->nr_sects)
+	if ((nr_sectors & (zone_sectors - 1)) && end_sector != capacity)
 		return -EINVAL;
 
-	blk_start_plug(&plug);
 	while (sector < end_sector) {
-
 		bio = blk_next_bio(bio, 0, gfp_mask);
-		bio->bi_iter.bi_sector = sector;
 		bio_set_dev(bio, bdev);
-		bio_set_op_attrs(bio, REQ_OP_ZONE_RESET, 0);
 
+		/*
+		 * Special case for the zone reset operation that reset all
+		 * zones, this is useful for applications like mkfs.
+		 */
+		if (op == REQ_OP_ZONE_RESET &&
+		    blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) {
+			bio->bi_opf = REQ_OP_ZONE_RESET_ALL;
+			break;
+		}
+
+		bio->bi_opf = op;
+		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
 
 		/* This may take a while, so be nice to others */
 		cond_resched();
-
 	}
 
 	ret = submit_bio_wait(bio);
 	bio_put(bio);
 
-	blk_finish_plug(&plug);
-
 	return ret;
 }
-EXPORT_SYMBOL_GPL(blkdev_reset_zones);
+EXPORT_SYMBOL_GPL(blkdev_zone_mgmt);
+
+struct zone_report_args {
+	struct blk_zone __user *zones;
+};
+
+static int blkdev_copy_zone_to_user(struct blk_zone *zone, unsigned int idx,
+				    void *data)
+{
+	struct zone_report_args *args = data;
+
+	if (copy_to_user(&args->zones[idx], zone, sizeof(struct blk_zone)))
+		return -EFAULT;
+	return 0;
+}
 
 /*
  * BLKREPORTZONE ioctl processing.
@@ -315,9 +245,9 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 			      unsigned int cmd, unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
+	struct zone_report_args args;
 	struct request_queue *q;
 	struct blk_zone_report rep;
-	struct blk_zone *zones;
 	int ret;
 
 	if (!argp)
@@ -339,44 +269,29 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	if (!rep.nr_zones)
 		return -EINVAL;
 
-	rep.nr_zones = min(blkdev_nr_zones(bdev), rep.nr_zones);
-
-	zones = kvmalloc_array(rep.nr_zones, sizeof(struct blk_zone),
-			       GFP_KERNEL | __GFP_ZERO);
-	if (!zones)
-		return -ENOMEM;
-
-	ret = blkdev_report_zones(bdev, rep.sector, zones, &rep.nr_zones);
-	if (ret)
-		goto out;
-
-	if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	if (rep.nr_zones) {
-		if (copy_to_user(argp + sizeof(struct blk_zone_report), zones,
-				 sizeof(struct blk_zone) * rep.nr_zones))
-			ret = -EFAULT;
-	}
-
- out:
-	kvfree(zones);
+	args.zones = argp + sizeof(struct blk_zone_report);
+	ret = blkdev_report_zones(bdev, rep.sector, rep.nr_zones,
+				  blkdev_copy_zone_to_user, &args);
+	if (ret < 0)
+		return ret;
 
-	return ret;
+	rep.nr_zones = ret;
+	if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report)))
+		return -EFAULT;
+	return 0;
 }
 
 /*
- * BLKRESETZONE ioctl processing.
+ * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing.
  * Called from blkdev_ioctl.
  */
-int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
-			     unsigned int cmd, unsigned long arg)
+int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
+			   unsigned int cmd, unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
 	struct request_queue *q;
 	struct blk_zone_range zrange;
+	enum req_opf op;
 
 	if (!argp)
 		return -EINVAL;
@@ -397,8 +312,25 @@ int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range)))
 		return -EFAULT;
 
-	return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors,
-				  GFP_KERNEL);
+	switch (cmd) {
+	case BLKRESETZONE:
+		op = REQ_OP_ZONE_RESET;
+		break;
+	case BLKOPENZONE:
+		op = REQ_OP_ZONE_OPEN;
+		break;
+	case BLKCLOSEZONE:
+		op = REQ_OP_ZONE_CLOSE;
+		break;
+	case BLKFINISHZONE:
+		op = REQ_OP_ZONE_FINISH;
+		break;
+	default:
+		return -ENOTTY;
+	}
+
+	return blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors,
+				GFP_KERNEL);
 }
 
 static inline unsigned long *blk_alloc_zone_bitmap(int node,
@@ -408,37 +340,99 @@ static inline unsigned long *blk_alloc_zone_bitmap(int node,
 			    GFP_NOIO, node);
 }
 
+void blk_queue_free_zone_bitmaps(struct request_queue *q)
+{
+	kfree(q->seq_zones_bitmap);
+	q->seq_zones_bitmap = NULL;
+	kfree(q->seq_zones_wlock);
+	q->seq_zones_wlock = NULL;
+}
+
+struct blk_revalidate_zone_args {
+	struct gendisk	*disk;
+	unsigned long	*seq_zones_bitmap;
+	unsigned long	*seq_zones_wlock;
+	sector_t	sector;
+};
+
 /*
- * Allocate an array of struct blk_zone to get nr_zones zone information.
- * The allocated array may be smaller than nr_zones.
+ * Helper function to check the validity of zones of a zoned block device.
  */
-static struct blk_zone *blk_alloc_zones(unsigned int *nr_zones)
+static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
+				  void *data)
 {
-	struct blk_zone *zones;
-	size_t nrz = min(*nr_zones, BLK_ZONED_REPORT_MAX_ZONES);
+	struct blk_revalidate_zone_args *args = data;
+	struct gendisk *disk = args->disk;
+	struct request_queue *q = disk->queue;
+	sector_t zone_sectors = blk_queue_zone_sectors(q);
+	sector_t capacity = get_capacity(disk);
 
 	/*
-	 * GFP_KERNEL here is meaningless as the caller task context has
-	 * the PF_MEMALLOC_NOIO flag set in blk_revalidate_disk_zones()
-	 * with memalloc_noio_save().
+	 * All zones must have the same size, with the exception on an eventual
+	 * smaller last zone.
 	 */
-	zones = kvcalloc(nrz, sizeof(struct blk_zone), GFP_KERNEL);
-	if (!zones) {
-		*nr_zones = 0;
-		return NULL;
+	if (zone->start + zone_sectors < capacity &&
+	    zone->len != zone_sectors) {
+		pr_warn("%s: Invalid zoned device with non constant zone size\n",
+			disk->disk_name);
+		return false;
 	}
 
-	*nr_zones = nrz;
+	if (zone->start + zone->len >= capacity &&
+	    zone->len > zone_sectors) {
+		pr_warn("%s: Invalid zoned device with larger last zone size\n",
+			disk->disk_name);
+		return -ENODEV;
+	}
+
+	/* Check for holes in the zone report */
+	if (zone->start != args->sector) {
+		pr_warn("%s: Zone gap at sectors %llu..%llu\n",
+			disk->disk_name, args->sector, zone->start);
+		return -ENODEV;
+	}
 
-	return zones;
+	/* Check zone type */
+	switch (zone->type) {
+	case BLK_ZONE_TYPE_CONVENTIONAL:
+	case BLK_ZONE_TYPE_SEQWRITE_REQ:
+	case BLK_ZONE_TYPE_SEQWRITE_PREF:
+		break;
+	default:
+		pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n",
+			disk->disk_name, (int)zone->type, zone->start);
+		return -ENODEV;
+	}
+
+	if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL)
+		set_bit(idx, args->seq_zones_bitmap);
+
+	args->sector += zone->len;
+	return 0;
 }
 
-void blk_queue_free_zone_bitmaps(struct request_queue *q)
+static int blk_update_zone_info(struct gendisk *disk, unsigned int nr_zones,
+				struct blk_revalidate_zone_args *args)
 {
-	kfree(q->seq_zones_bitmap);
-	q->seq_zones_bitmap = NULL;
-	kfree(q->seq_zones_wlock);
-	q->seq_zones_wlock = NULL;
+	/*
+	 * Ensure that all memory allocations in this context are done as
+	 * if GFP_NOIO was specified.
+	 */
+	unsigned int noio_flag = memalloc_noio_save();
+	struct request_queue *q = disk->queue;
+	int ret;
+
+	args->seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones);
+	if (!args->seq_zones_wlock)
+		return -ENOMEM;
+	args->seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones);
+	if (!args->seq_zones_bitmap)
+		return -ENOMEM;
+
+	ret = disk->fops->report_zones(disk, 0, nr_zones,
+				       blk_revalidate_zone_cb, args);
+	memalloc_noio_restore(noio_flag);
+	return ret;
 }
 
 /**
@@ -454,13 +448,12 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
 	unsigned int nr_zones = __blkdev_nr_zones(q, get_capacity(disk));
-	unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL;
-	unsigned int i, rep_nr_zones = 0, z = 0, nrz;
-	struct blk_zone *zones = NULL;
-	unsigned int noio_flag;
-	sector_t sector = 0;
+	struct blk_revalidate_zone_args args = { .disk = disk };
 	int ret = 0;
 
+	if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
+		return -EIO;
+
 	/*
 	 * BIO based queues do not use a scheduler so only q->nr_zones
 	 * needs to be updated so that the sysfs exposed value is correct.
@@ -470,78 +463,28 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 		return 0;
 	}
 
-	/*
-	 * Ensure that all memory allocations in this context are done as
-	 * if GFP_NOIO was specified.
-	 */
-	noio_flag = memalloc_noio_save();
-
-	if (!blk_queue_is_zoned(q) || !nr_zones) {
-		nr_zones = 0;
-		goto update;
-	}
-
-	/* Allocate bitmaps */
-	ret = -ENOMEM;
-	seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones);
-	if (!seq_zones_wlock)
-		goto out;
-	seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones);
-	if (!seq_zones_bitmap)
-		goto out;
-
-	/* Get zone information and initialize seq_zones_bitmap */
-	rep_nr_zones = nr_zones;
-	zones = blk_alloc_zones(&rep_nr_zones);
-	if (!zones)
-		goto out;
-
-	while (z < nr_zones) {
-		nrz = min(nr_zones - z, rep_nr_zones);
-		ret = blk_report_zones(disk, sector, zones, &nrz);
-		if (ret)
-			goto out;
-		if (!nrz)
-			break;
-		for (i = 0; i < nrz; i++) {
-			if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL)
-				set_bit(z, seq_zones_bitmap);
-			z++;
-		}
-		sector += nrz * blk_queue_zone_sectors(q);
-	}
-
-	if (WARN_ON(z != nr_zones)) {
-		ret = -EIO;
-		goto out;
-	}
+	if (nr_zones)
+		ret = blk_update_zone_info(disk, nr_zones, &args);
 
-update:
 	/*
 	 * Install the new bitmaps, making sure the queue is stopped and
 	 * all I/Os are completed (i.e. a scheduler is not referencing the
 	 * bitmaps).
 	 */
 	blk_mq_freeze_queue(q);
-	q->nr_zones = nr_zones;
-	swap(q->seq_zones_wlock, seq_zones_wlock);
-	swap(q->seq_zones_bitmap, seq_zones_bitmap);
-	blk_mq_unfreeze_queue(q);
-
-out:
-	memalloc_noio_restore(noio_flag);
-
-	kvfree(zones);
-	kfree(seq_zones_wlock);
-	kfree(seq_zones_bitmap);
-
-	if (ret) {
+	if (ret >= 0) {
+		q->nr_zones = nr_zones;
+		swap(q->seq_zones_wlock, args.seq_zones_wlock);
+		swap(q->seq_zones_bitmap, args.seq_zones_bitmap);
+		ret = 0;
+	} else {
 		pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
-		blk_mq_freeze_queue(q);
 		blk_queue_free_zone_bitmaps(q);
-		blk_mq_unfreeze_queue(q);
 	}
+	blk_mq_unfreeze_queue(q);
 
+	kfree(args.seq_zones_wlock);
+	kfree(args.seq_zones_bitmap);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
diff --git a/block/blk.h b/block/blk.h
index 47fba9362e60..2bea40180b6f 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -242,14 +242,11 @@ int blk_dev_init(void);
  * Contribute to IO statistics IFF:
  *
  *	a) it's attached to a gendisk, and
- *	b) the queue had IO stats enabled when this request was started, and
- *	c) it's a file system request
+ *	b) the queue had IO stats enabled when this request was started
  */
 static inline bool blk_do_io_stat(struct request *rq)
 {
-	return rq->rq_disk &&
-	       (rq->rq_flags & RQF_IO_STAT) &&
-		!blk_rq_is_passthrough(rq);
+	return rq->rq_disk && (rq->rq_flags & RQF_IO_STAT);
 }
 
 static inline void req_set_nomerge(struct request_queue *q, struct request *req)
diff --git a/block/elevator.c b/block/elevator.c
index 076ba7308e65..4eab3d70e880 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -832,3 +832,12 @@ struct request *elv_rb_latter_request(struct request_queue *q,
 	return NULL;
 }
 EXPORT_SYMBOL(elv_rb_latter_request);
+
+static int __init elevator_setup(char *str)
+{
+	pr_warn("Kernel parameter elevator= does not have any effect anymore.\n"
+		"Please use sysfs to set IO scheduler for individual devices.\n");
+	return 1;
+}
+
+__setup("elevator=", elevator_setup);
diff --git a/block/genhd.c b/block/genhd.c
index 26b31fcae217..ff6268970ddc 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1385,7 +1385,9 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   "%lu %lu %lu %u "
 			   "%lu %lu %lu %u "
 			   "%u %u %u "
-			   "%lu %lu %lu %u\n",
+			   "%lu %lu %lu %u "
+			   "%lu %u"
+			   "\n",
 			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
 			   disk_name(gp, hd->partno, buf),
 			   part_stat_read(hd, ios[STAT_READ]),
@@ -1402,7 +1404,9 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   part_stat_read(hd, ios[STAT_DISCARD]),
 			   part_stat_read(hd, merges[STAT_DISCARD]),
 			   part_stat_read(hd, sectors[STAT_DISCARD]),
-			   (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD)
+			   (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD),
+			   part_stat_read(hd, ios[STAT_FLUSH]),
+			   (unsigned int)part_stat_read_msecs(hd, STAT_FLUSH)
 			);
 	}
 	disk_part_iter_exit(&piter);
diff --git a/block/ioctl.c b/block/ioctl.c
index 15a0eb80ada9..7ac8a66c9787 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -155,48 +155,21 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
 	}
 }
 
-/*
- * This is an exported API for the block driver, and will not
- * acquire bd_mutex. This API should be used in case that
- * caller has held bd_mutex already.
- */
-int __blkdev_reread_part(struct block_device *bdev)
+static int blkdev_reread_part(struct block_device *bdev)
 {
-	struct gendisk *disk = bdev->bd_disk;
+	int ret;
 
-	if (!disk_part_scan_enabled(disk) || bdev != bdev->bd_contains)
+	if (!disk_part_scan_enabled(bdev->bd_disk) || bdev != bdev->bd_contains)
 		return -EINVAL;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
-	lockdep_assert_held(&bdev->bd_mutex);
-
-	return rescan_partitions(disk, bdev);
-}
-EXPORT_SYMBOL(__blkdev_reread_part);
-
-/*
- * This is an exported API for the block driver, and will
- * try to acquire bd_mutex. If bd_mutex has been held already
- * in current context, please call __blkdev_reread_part().
- *
- * Make sure the held locks in current context aren't required
- * in open()/close() handler and I/O path for avoiding ABBA deadlock:
- * - bd_mutex is held before calling block driver's open/close
- *   handler
- * - reading partition table may submit I/O to the block device
- */
-int blkdev_reread_part(struct block_device *bdev)
-{
-	int res;
-
 	mutex_lock(&bdev->bd_mutex);
-	res = __blkdev_reread_part(bdev);
+	ret = bdev_disk_changed(bdev, false);
 	mutex_unlock(&bdev->bd_mutex);
 
-	return res;
+	return ret;
 }
-EXPORT_SYMBOL(blkdev_reread_part);
 
 static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 		unsigned long arg, unsigned long flags)
@@ -532,7 +505,10 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKREPORTZONE:
 		return blkdev_report_zones_ioctl(bdev, mode, cmd, arg);
 	case BLKRESETZONE:
-		return blkdev_reset_zones_ioctl(bdev, mode, cmd, arg);
+	case BLKOPENZONE:
+	case BLKCLOSEZONE:
+	case BLKFINISHZONE:
+		return blkdev_zone_mgmt_ioctl(bdev, mode, cmd, arg);
 	case BLKGETZONESZ:
 		return put_uint(arg, bdev_zone_sectors(bdev));
 	case BLKGETNRZONES:
diff --git a/block/opal_proto.h b/block/opal_proto.h
index 5532412d567c..325cbba2465f 100644
--- a/block/opal_proto.h
+++ b/block/opal_proto.h
@@ -76,7 +76,6 @@ enum opal_response_token {
  * Derived from: TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
  * Section: 6.3 Assigned UIDs
  */
-#define OPAL_UID_LENGTH 8
 #define OPAL_METHOD_LENGTH 8
 #define OPAL_MSID_KEYLEN 15
 #define OPAL_UID_LENGTH_HALF 4
@@ -108,6 +107,7 @@ enum opal_uid {
 	OPAL_C_PIN_TABLE,
 	OPAL_LOCKING_INFO_TABLE,
 	OPAL_ENTERPRISE_LOCKING_INFO_TABLE,
+	OPAL_DATASTORE,
 	/* C_PIN_TABLE object ID's */
 	OPAL_C_PIN_MSID,
 	OPAL_C_PIN_SID,
@@ -205,6 +205,10 @@ enum opal_lockingstate {
 	OPAL_LOCKING_LOCKED = 0x03,
 };
 
+enum opal_parameter {
+	OPAL_SUM_SET_LIST = 0x060000,
+};
+
 /* Packets derived from:
  * TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
  * Secion: 3.2.3 ComPackets, Packets & Subpackets
diff --git a/block/partition-generic.c b/block/partition-generic.c
index aee643ce13d1..1d20c9cf213f 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -127,7 +127,8 @@ ssize_t part_stat_show(struct device *dev,
 		"%8lu %8lu %8llu %8u "
 		"%8lu %8lu %8llu %8u "
 		"%8u %8u %8u "
-		"%8lu %8lu %8llu %8u"
+		"%8lu %8lu %8llu %8u "
+		"%8lu %8u"
 		"\n",
 		part_stat_read(p, ios[STAT_READ]),
 		part_stat_read(p, merges[STAT_READ]),
@@ -143,7 +144,9 @@ ssize_t part_stat_show(struct device *dev,
 		part_stat_read(p, ios[STAT_DISCARD]),
 		part_stat_read(p, merges[STAT_DISCARD]),
 		(unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]),
-		(unsigned int)part_stat_read_msecs(p, STAT_DISCARD));
+		(unsigned int)part_stat_read_msecs(p, STAT_DISCARD),
+		part_stat_read(p, ios[STAT_FLUSH]),
+		(unsigned int)part_stat_read_msecs(p, STAT_FLUSH));
 }
 
 ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
@@ -439,12 +442,14 @@ static bool disk_unlock_native_capacity(struct gendisk *disk)
 	}
 }
 
-static int drop_partitions(struct gendisk *disk, struct block_device *bdev)
+int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev)
 {
 	struct disk_part_iter piter;
 	struct hd_struct *part;
 	int res;
 
+	if (!disk_part_scan_enabled(disk))
+		return 0;
 	if (bdev->bd_part_count || bdev->bd_super)
 		return -EBUSY;
 	res = invalidate_partition(disk, 0);
@@ -459,204 +464,124 @@ static int drop_partitions(struct gendisk *disk, struct block_device *bdev)
 	return 0;
 }
 
-static bool part_zone_aligned(struct gendisk *disk,
-			      struct block_device *bdev,
-			      sector_t from, sector_t size)
+static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev,
+		struct parsed_partitions *state, int p)
 {
-	unsigned int zone_sectors = bdev_zone_sectors(bdev);
+	sector_t size = state->parts[p].size;
+	sector_t from = state->parts[p].from;
+	struct hd_struct *part;
 
-	/*
-	 * If this function is called, then the disk is a zoned block device
-	 * (host-aware or host-managed). This can be detected even if the
-	 * zoned block device support is disabled (CONFIG_BLK_DEV_ZONED not
-	 * set). In this case, however, only host-aware devices will be seen
-	 * as a block device is not created for host-managed devices. Without
-	 * zoned block device support, host-aware drives can still be used as
-	 * regular block devices (no zone operation) and their zone size will
-	 * be reported as 0. Allow this case.
-	 */
-	if (!zone_sectors)
+	if (!size)
 		return true;
 
-	/*
-	 * Check partition start and size alignement. If the drive has a
-	 * smaller last runt zone, ignore it and allow the partition to
-	 * use it. Check the zone size too: it should be a power of 2 number
-	 * of sectors.
-	 */
-	if (WARN_ON_ONCE(!is_power_of_2(zone_sectors))) {
-		u32 rem;
-
-		div_u64_rem(from, zone_sectors, &rem);
-		if (rem)
+	if (from >= get_capacity(disk)) {
+		printk(KERN_WARNING
+		       "%s: p%d start %llu is beyond EOD, ",
+		       disk->disk_name, p, (unsigned long long) from);
+		if (disk_unlock_native_capacity(disk))
 			return false;
-		if ((from + size) < get_capacity(disk)) {
-			div_u64_rem(size, zone_sectors, &rem);
-			if (rem)
-				return false;
-		}
+		return true;
+	}
 
-	} else {
+	if (from + size > get_capacity(disk)) {
+		printk(KERN_WARNING
+		       "%s: p%d size %llu extends beyond EOD, ",
+		       disk->disk_name, p, (unsigned long long) size);
 
-		if (from & (zone_sectors - 1))
-			return false;
-		if ((from + size) < get_capacity(disk) &&
-		    (size & (zone_sectors - 1)))
+		if (disk_unlock_native_capacity(disk))
 			return false;
 
+		/*
+		 * We can not ignore partitions of broken tables created by for
+		 * example camera firmware, but we limit them to the end of the
+		 * disk to avoid creating invalid block devices.
+		 */
+		size = get_capacity(disk) - from;
+	}
+
+	part = add_partition(disk, p, from, size, state->parts[p].flags,
+			     &state->parts[p].info);
+	if (IS_ERR(part)) {
+		printk(KERN_ERR " %s: p%d could not be added: %ld\n",
+		       disk->disk_name, p, -PTR_ERR(part));
+		return true;
 	}
 
+#ifdef CONFIG_BLK_DEV_MD
+	if (state->parts[p].flags & ADDPART_FLAG_RAID)
+		md_autodetect_dev(part_to_dev(part)->devt);
+#endif
 	return true;
 }
 
-int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
+int blk_add_partitions(struct gendisk *disk, struct block_device *bdev)
 {
-	struct parsed_partitions *state = NULL;
-	struct hd_struct *part;
-	int p, highest, res;
-rescan:
-	if (state && !IS_ERR(state)) {
-		free_partitions(state);
-		state = NULL;
-	}
+	struct parsed_partitions *state;
+	int ret = -EAGAIN, p, highest;
 
-	res = drop_partitions(disk, bdev);
-	if (res)
-		return res;
+	if (!disk_part_scan_enabled(disk))
+		return 0;
 
-	if (disk->fops->revalidate_disk)
-		disk->fops->revalidate_disk(disk);
-	check_disk_size_change(disk, bdev, true);
-	bdev->bd_invalidated = 0;
-	if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))
+	state = check_partition(disk, bdev);
+	if (!state)
 		return 0;
 	if (IS_ERR(state)) {
 		/*
-		 * I/O error reading the partition table.  If any
-		 * partition code tried to read beyond EOD, retry
-		 * after unlocking native capacity.
+		 * I/O error reading the partition table.  If we tried to read
+		 * beyond EOD, retry after unlocking the native capacity.
 		 */
 		if (PTR_ERR(state) == -ENOSPC) {
 			printk(KERN_WARNING "%s: partition table beyond EOD, ",
 			       disk->disk_name);
 			if (disk_unlock_native_capacity(disk))
-				goto rescan;
+				return -EAGAIN;
 		}
 		return -EIO;
 	}
+
 	/*
-	 * If any partition code tried to read beyond EOD, try
-	 * unlocking native capacity even if partition table is
-	 * successfully read as we could be missing some partitions.
+	 * Partitions are not supported on zoned block devices.
+	 */
+	if (bdev_is_zoned(bdev)) {
+		pr_warn("%s: ignoring partition table on zoned block device\n",
+			disk->disk_name);
+		ret = 0;
+		goto out_free_state;
+	}
+
+	/*
+	 * If we read beyond EOD, try unlocking native capacity even if the
+	 * partition table was successfully read as we could be missing some
+	 * partitions.
 	 */
 	if (state->access_beyond_eod) {
 		printk(KERN_WARNING
 		       "%s: partition table partially beyond EOD, ",
 		       disk->disk_name);
 		if (disk_unlock_native_capacity(disk))
-			goto rescan;
+			goto out_free_state;
 	}
 
 	/* tell userspace that the media / partition table may have changed */
 	kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
 
-	/* Detect the highest partition number and preallocate
-	 * disk->part_tbl.  This is an optimization and not strictly
-	 * necessary.
+	/*
+	 * Detect the highest partition number and preallocate disk->part_tbl.
+	 * This is an optimization and not strictly necessary.
 	 */
 	for (p = 1, highest = 0; p < state->limit; p++)
 		if (state->parts[p].size)
 			highest = p;
-
 	disk_expand_part_tbl(disk, highest);
 
-	/* add partitions */
-	for (p = 1; p < state->limit; p++) {
-		sector_t size, from;
-
-		size = state->parts[p].size;
-		if (!size)
-			continue;
-
-		from = state->parts[p].from;
-		if (from >= get_capacity(disk)) {
-			printk(KERN_WARNING
-			       "%s: p%d start %llu is beyond EOD, ",
-			       disk->disk_name, p, (unsigned long long) from);
-			if (disk_unlock_native_capacity(disk))
-				goto rescan;
-			continue;
-		}
-
-		if (from + size > get_capacity(disk)) {
-			printk(KERN_WARNING
-			       "%s: p%d size %llu extends beyond EOD, ",
-			       disk->disk_name, p, (unsigned long long) size);
-
-			if (disk_unlock_native_capacity(disk)) {
-				/* free state and restart */
-				goto rescan;
-			} else {
-				/*
-				 * we can not ignore partitions of broken tables
-				 * created by for example camera firmware, but
-				 * we limit them to the end of the disk to avoid
-				 * creating invalid block devices
-				 */
-				size = get_capacity(disk) - from;
-			}
-		}
-
-		/*
-		 * On a zoned block device, partitions should be aligned on the
-		 * device zone size (i.e. zone boundary crossing not allowed).
-		 * Otherwise, resetting the write pointer of the last zone of
-		 * one partition may impact the following partition.
-		 */
-		if (bdev_is_zoned(bdev) &&
-		    !part_zone_aligned(disk, bdev, from, size)) {
-			printk(KERN_WARNING
-			       "%s: p%d start %llu+%llu is not zone aligned\n",
-			       disk->disk_name, p, (unsigned long long) from,
-			       (unsigned long long) size);
-			continue;
-		}
+	for (p = 1; p < state->limit; p++)
+		if (!blk_add_partition(disk, bdev, state, p))
+			goto out_free_state;
 
-		part = add_partition(disk, p, from, size,
-				     state->parts[p].flags,
-				     &state->parts[p].info);
-		if (IS_ERR(part)) {
-			printk(KERN_ERR " %s: p%d could not be added: %ld\n",
-			       disk->disk_name, p, -PTR_ERR(part));
-			continue;
-		}
-#ifdef CONFIG_BLK_DEV_MD
-		if (state->parts[p].flags & ADDPART_FLAG_RAID)
-			md_autodetect_dev(part_to_dev(part)->devt);
-#endif
-	}
+	ret = 0;
+out_free_state:
 	free_partitions(state);
-	return 0;
-}
-
-int invalidate_partitions(struct gendisk *disk, struct block_device *bdev)
-{
-	int res;
-
-	if (!bdev->bd_invalidated)
-		return 0;
-
-	res = drop_partitions(disk, bdev);
-	if (res)
-		return res;
-
-	set_capacity(disk, 0);
-	check_disk_size_change(disk, bdev, false);
-	bdev->bd_invalidated = 0;
-	/* tell userspace that the media / partition table may have changed */
-	kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
-
-	return 0;
+	return ret;
 }
 
 unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p)
diff --git a/block/sed-opal.c b/block/sed-opal.c
index b4c761973ac1..880cc57a5f6b 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -149,6 +149,8 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = {
 		{ 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x01 },
 	[OPAL_ENTERPRISE_LOCKING_INFO_TABLE] =
 		{ 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x00 },
+	[OPAL_DATASTORE] =
+		{ 0x00, 0x00, 0x10, 0x01, 0x00, 0x00, 0x00, 0x00 },
 
 	/* C_PIN_TABLE object ID's */
 	[OPAL_C_PIN_MSID] =
@@ -1139,11 +1141,11 @@ static int generic_get_column(struct opal_dev *dev, const u8 *table,
  *
  * the result is provided in dev->resp->tok[4]
  */
-static int generic_get_table_info(struct opal_dev *dev, enum opal_uid table,
+static int generic_get_table_info(struct opal_dev *dev, const u8 *table_uid,
 				  u64 column)
 {
 	u8 uid[OPAL_UID_LENGTH];
-	const unsigned int half = OPAL_UID_LENGTH/2;
+	const unsigned int half = OPAL_UID_LENGTH_HALF;
 
 	/* sed-opal UIDs can be split in two halves:
 	 *  first:  actual table index
@@ -1152,7 +1154,7 @@ static int generic_get_table_info(struct opal_dev *dev, enum opal_uid table,
 	 * first part of the target table as relative index into that table
 	 */
 	memcpy(uid, opaluid[OPAL_TABLE_TABLE], half);
-	memcpy(uid+half, opaluid[table], half);
+	memcpy(uid + half, table_uid, half);
 
 	return generic_get_column(dev, uid, column);
 }
@@ -1221,6 +1223,75 @@ static int get_active_key(struct opal_dev *dev, void *data)
 	return get_active_key_cont(dev);
 }
 
+static int generic_table_write_data(struct opal_dev *dev, const u64 data,
+				    u64 offset, u64 size, const u8 *uid)
+{
+	const u8 __user *src = (u8 __user *)(uintptr_t)data;
+	u8 *dst;
+	u64 len;
+	size_t off = 0;
+	int err;
+
+	/* do we fit in the available space? */
+	err = generic_get_table_info(dev, uid, OPAL_TABLE_ROWS);
+	if (err) {
+		pr_debug("Couldn't get the table size\n");
+		return err;
+	}
+
+	len = response_get_u64(&dev->parsed, 4);
+	if (size > len || offset > len - size) {
+		pr_debug("Does not fit in the table (%llu vs. %llu)\n",
+			  offset + size, len);
+		return -ENOSPC;
+	}
+
+	/* do the actual transmission(s) */
+	while (off < size) {
+		err = cmd_start(dev, uid, opalmethod[OPAL_SET]);
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_WHERE);
+		add_token_u64(&err, dev, offset + off);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_VALUES);
+
+		/*
+		 * The bytestring header is either 1 or 2 bytes, so assume 2.
+		 * There also needs to be enough space to accommodate the
+		 * trailing OPAL_ENDNAME (1 byte) and tokens added by
+		 * cmd_finalize.
+		 */
+		len = min(remaining_size(dev) - (2+1+CMD_FINALIZE_BYTES_NEEDED),
+			  (size_t)(size - off));
+		pr_debug("Write bytes %zu+%llu/%llu\n", off, len, size);
+
+		dst = add_bytestring_header(&err, dev, len);
+		if (!dst)
+			break;
+
+		if (copy_from_user(dst, src + off, len)) {
+			err = -EFAULT;
+			break;
+		}
+
+		dev->pos += len;
+
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		if (err)
+			break;
+
+		err = finalize_and_send(dev, parse_and_check_status);
+		if (err)
+			break;
+
+		off += len;
+	}
+
+	return err;
+}
+
 static int generic_lr_enable_disable(struct opal_dev *dev,
 				     u8 *uid, bool rle, bool wle,
 				     bool rl, bool wl)
@@ -1583,68 +1654,9 @@ static int set_mbr_enable_disable(struct opal_dev *dev, void *data)
 static int write_shadow_mbr(struct opal_dev *dev, void *data)
 {
 	struct opal_shadow_mbr *shadow = data;
-	const u8 __user *src;
-	u8 *dst;
-	size_t off = 0;
-	u64 len;
-	int err = 0;
-
-	/* do we fit in the available shadow mbr space? */
-	err = generic_get_table_info(dev, OPAL_MBR, OPAL_TABLE_ROWS);
-	if (err) {
-		pr_debug("MBR: could not get shadow size\n");
-		return err;
-	}
-
-	len = response_get_u64(&dev->parsed, 4);
-	if (shadow->size > len || shadow->offset > len - shadow->size) {
-		pr_debug("MBR: does not fit in shadow (%llu vs. %llu)\n",
-			 shadow->offset + shadow->size, len);
-		return -ENOSPC;
-	}
-
-	/* do the actual transmission(s) */
-	src = (u8 __user *)(uintptr_t)shadow->data;
-	while (off < shadow->size) {
-		err = cmd_start(dev, opaluid[OPAL_MBR], opalmethod[OPAL_SET]);
-		add_token_u8(&err, dev, OPAL_STARTNAME);
-		add_token_u8(&err, dev, OPAL_WHERE);
-		add_token_u64(&err, dev, shadow->offset + off);
-		add_token_u8(&err, dev, OPAL_ENDNAME);
-
-		add_token_u8(&err, dev, OPAL_STARTNAME);
-		add_token_u8(&err, dev, OPAL_VALUES);
-
-		/*
-		 * The bytestring header is either 1 or 2 bytes, so assume 2.
-		 * There also needs to be enough space to accommodate the
-		 * trailing OPAL_ENDNAME (1 byte) and tokens added by
-		 * cmd_finalize.
-		 */
-		len = min(remaining_size(dev) - (2+1+CMD_FINALIZE_BYTES_NEEDED),
-			  (size_t)(shadow->size - off));
-		pr_debug("MBR: write bytes %zu+%llu/%llu\n",
-			 off, len, shadow->size);
-
-		dst = add_bytestring_header(&err, dev, len);
-		if (!dst)
-			break;
-		if (copy_from_user(dst, src + off, len))
-			err = -EFAULT;
-		dev->pos += len;
-
-		add_token_u8(&err, dev, OPAL_ENDNAME);
-		if (err)
-			break;
-
-		err = finalize_and_send(dev, parse_and_check_status);
-		if (err)
-			break;
-
-		off += len;
-	}
 
-	return err;
+	return generic_table_write_data(dev, shadow->data, shadow->offset,
+					shadow->size, opaluid[OPAL_MBR]);
 }
 
 static int generic_pw_cmd(u8 *key, size_t key_len, u8 *cpin_uid,
@@ -1874,7 +1886,6 @@ static int activate_lsp(struct opal_dev *dev, void *data)
 {
 	struct opal_lr_act *opal_act = data;
 	u8 user_lr[OPAL_UID_LENGTH];
-	u8 uint_3 = 0x83;
 	int err, i;
 
 	err = cmd_start(dev, opaluid[OPAL_LOCKINGSP_UID],
@@ -1887,10 +1898,7 @@ static int activate_lsp(struct opal_dev *dev, void *data)
 			return err;
 
 		add_token_u8(&err, dev, OPAL_STARTNAME);
-		add_token_u8(&err, dev, uint_3);
-		add_token_u8(&err, dev, 6);
-		add_token_u8(&err, dev, 0);
-		add_token_u8(&err, dev, 0);
+		add_token_u64(&err, dev, OPAL_SUM_SET_LIST);
 
 		add_token_u8(&err, dev, OPAL_STARTLIST);
 		add_token_bytestring(&err, dev, user_lr, OPAL_UID_LENGTH);
@@ -1957,6 +1965,113 @@ static int get_msid_cpin_pin(struct opal_dev *dev, void *data)
 	return 0;
 }
 
+static int write_table_data(struct opal_dev *dev, void *data)
+{
+	struct opal_read_write_table *write_tbl = data;
+
+	return generic_table_write_data(dev, write_tbl->data, write_tbl->offset,
+					write_tbl->size, write_tbl->table_uid);
+}
+
+static int read_table_data_cont(struct opal_dev *dev)
+{
+	int err;
+	const char *data_read;
+
+	err = parse_and_check_status(dev);
+	if (err)
+		return err;
+
+	dev->prev_d_len = response_get_string(&dev->parsed, 1, &data_read);
+	dev->prev_data = (void *)data_read;
+	if (!dev->prev_data) {
+		pr_debug("%s: Couldn't read data from the table.\n", __func__);
+		return OPAL_INVAL_PARAM;
+	}
+
+	return 0;
+}
+
+/*
+ * IO_BUFFER_LENGTH = 2048
+ * sizeof(header) = 56
+ * No. of Token Bytes in the Response = 11
+ * MAX size of data that can be carried in response buffer
+ * at a time is : 2048 - (56 + 11) = 1981 = 0x7BD.
+ */
+#define OPAL_MAX_READ_TABLE (0x7BD)
+
+static int read_table_data(struct opal_dev *dev, void *data)
+{
+	struct opal_read_write_table *read_tbl = data;
+	int err;
+	size_t off = 0, max_read_size = OPAL_MAX_READ_TABLE;
+	u64 table_len, len;
+	u64 offset = read_tbl->offset, read_size = read_tbl->size - 1;
+	u8 __user *dst;
+
+	err = generic_get_table_info(dev, read_tbl->table_uid, OPAL_TABLE_ROWS);
+	if (err) {
+		pr_debug("Couldn't get the table size\n");
+		return err;
+	}
+
+	table_len = response_get_u64(&dev->parsed, 4);
+
+	/* Check if the user is trying to read from the table limits */
+	if (read_size > table_len || offset > table_len - read_size) {
+		pr_debug("Read size exceeds the Table size limits (%llu vs. %llu)\n",
+			  offset + read_size, table_len);
+		return -EINVAL;
+	}
+
+	while (off < read_size) {
+		err = cmd_start(dev, read_tbl->table_uid, opalmethod[OPAL_GET]);
+
+		add_token_u8(&err, dev, OPAL_STARTLIST);
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_STARTROW);
+		add_token_u64(&err, dev, offset + off); /* start row value */
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_ENDROW);
+
+		len = min(max_read_size, (size_t)(read_size - off));
+		add_token_u64(&err, dev, offset + off + len); /* end row value
+							       */
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+
+		if (err) {
+			pr_debug("Error building read table data command.\n");
+			break;
+		}
+
+		err = finalize_and_send(dev, read_table_data_cont);
+		if (err)
+			break;
+
+		/* len+1: This includes the NULL terminator at the end*/
+		if (dev->prev_d_len > len + 1) {
+			err = -EOVERFLOW;
+			break;
+		}
+
+		dst = (u8 __user *)(uintptr_t)read_tbl->data;
+		if (copy_to_user(dst + off, dev->prev_data, dev->prev_d_len)) {
+			pr_debug("Error copying data to userspace\n");
+			err = -EFAULT;
+			break;
+		}
+		dev->prev_data = NULL;
+
+		off += len;
+	}
+
+	return err;
+}
+
 static int end_opal_session(struct opal_dev *dev, void *data)
 {
 	int err = 0;
@@ -2443,6 +2558,68 @@ bool opal_unlock_from_suspend(struct opal_dev *dev)
 }
 EXPORT_SYMBOL(opal_unlock_from_suspend);
 
+static int opal_read_table(struct opal_dev *dev,
+			   struct opal_read_write_table *rw_tbl)
+{
+	const struct opal_step read_table_steps[] = {
+		{ start_admin1LSP_opal_session, &rw_tbl->key },
+		{ read_table_data, rw_tbl },
+		{ end_opal_session, }
+	};
+	int ret = 0;
+
+	if (!rw_tbl->size)
+		return ret;
+
+	return execute_steps(dev, read_table_steps,
+			     ARRAY_SIZE(read_table_steps));
+}
+
+static int opal_write_table(struct opal_dev *dev,
+			    struct opal_read_write_table *rw_tbl)
+{
+	const struct opal_step write_table_steps[] = {
+		{ start_admin1LSP_opal_session, &rw_tbl->key },
+		{ write_table_data, rw_tbl },
+		{ end_opal_session, }
+	};
+	int ret = 0;
+
+	if (!rw_tbl->size)
+		return ret;
+
+	return execute_steps(dev, write_table_steps,
+			     ARRAY_SIZE(write_table_steps));
+}
+
+static int opal_generic_read_write_table(struct opal_dev *dev,
+					 struct opal_read_write_table *rw_tbl)
+{
+	int ret, bit_set;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev);
+
+	bit_set = fls64(rw_tbl->flags) - 1;
+	switch (bit_set) {
+	case OPAL_READ_TABLE:
+		ret = opal_read_table(dev, rw_tbl);
+		break;
+	case OPAL_WRITE_TABLE:
+		ret = opal_write_table(dev, rw_tbl);
+		break;
+	default:
+		pr_debug("Invalid bit set in the flag (%016llx).\n",
+			 rw_tbl->flags);
+		ret = -EINVAL;
+		break;
+	}
+
+	mutex_unlock(&dev->dev_lock);
+
+	return ret;
+}
+
 int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
 {
 	void *p;
@@ -2505,6 +2682,9 @@ int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
 	case IOC_OPAL_PSID_REVERT_TPR:
 		ret = opal_reverttper(dev, p, true);
 		break;
+	case IOC_OPAL_GENERIC_TABLE_RW:
+		ret = opal_generic_read_write_table(dev, p);
+		break;
 	default:
 		break;
 	}
diff --git a/block/t10-pi.c b/block/t10-pi.c
index 9803c7e0376e..f4907d941f03 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -235,16 +235,12 @@ static blk_status_t t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
 	return t10_pi_verify(iter, t10_pi_ip_fn, T10_PI_TYPE3_PROTECTION);
 }
 
-/**
- * Type 3 does not have a reference tag so no remapping is required.
- */
+/* Type 3 does not have a reference tag so no remapping is required. */
 static void t10_pi_type3_prepare(struct request *rq)
 {
 }
 
-/**
- * Type 3 does not have a reference tag so no remapping is required.
- */
+/* Type 3 does not have a reference tag so no remapping is required. */
 static void t10_pi_type3_complete(struct request *rq, unsigned int nr_bytes)
 {
 }
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 9e524044d312..5575d48473bd 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -52,12 +52,12 @@ config CRYPTO_AEAD2
 	select CRYPTO_NULL2
 	select CRYPTO_RNG2
 
-config CRYPTO_BLKCIPHER
+config CRYPTO_SKCIPHER
 	tristate
-	select CRYPTO_BLKCIPHER2
+	select CRYPTO_SKCIPHER2
 	select CRYPTO_ALGAPI
 
-config CRYPTO_BLKCIPHER2
+config CRYPTO_SKCIPHER2
 	tristate
 	select CRYPTO_ALGAPI2
 	select CRYPTO_RNG2
@@ -123,7 +123,7 @@ config CRYPTO_MANAGER2
 	def_tristate CRYPTO_MANAGER || (CRYPTO_MANAGER!=n && CRYPTO_ALGAPI=y)
 	select CRYPTO_AEAD2
 	select CRYPTO_HASH2
-	select CRYPTO_BLKCIPHER2
+	select CRYPTO_SKCIPHER2
 	select CRYPTO_AKCIPHER2
 	select CRYPTO_KPP2
 	select CRYPTO_ACOMP2
@@ -169,7 +169,7 @@ config CRYPTO_NULL
 config CRYPTO_NULL2
 	tristate
 	select CRYPTO_ALGAPI2
-	select CRYPTO_BLKCIPHER2
+	select CRYPTO_SKCIPHER2
 	select CRYPTO_HASH2
 
 config CRYPTO_PCRYPT
@@ -184,7 +184,7 @@ config CRYPTO_PCRYPT
 
 config CRYPTO_CRYPTD
 	tristate "Software async crypto daemon"
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_HASH
 	select CRYPTO_MANAGER
 	help
@@ -195,7 +195,7 @@ config CRYPTO_CRYPTD
 config CRYPTO_AUTHENC
 	tristate "Authenc support"
 	select CRYPTO_AEAD
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_MANAGER
 	select CRYPTO_HASH
 	select CRYPTO_NULL
@@ -217,7 +217,7 @@ config CRYPTO_SIMD
 config CRYPTO_GLUE_HELPER_X86
 	tristate
 	depends on X86
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 
 config CRYPTO_ENGINE
 	tristate
@@ -264,6 +264,17 @@ config CRYPTO_ECRDSA
 	  standard algorithms (called GOST algorithms). Only signature verification
 	  is implemented.
 
+config CRYPTO_CURVE25519
+	tristate "Curve25519 algorithm"
+	select CRYPTO_KPP
+	select CRYPTO_LIB_CURVE25519_GENERIC
+
+config CRYPTO_CURVE25519_X86
+	tristate "x86_64 accelerated Curve25519 scalar multiplication library"
+	depends on X86 && 64BIT
+	select CRYPTO_LIB_CURVE25519_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_CURVE25519
+
 comment "Authenticated Encryption with Associated Data"
 
 config CRYPTO_CCM
@@ -309,6 +320,7 @@ config CRYPTO_AEGIS128
 config CRYPTO_AEGIS128_SIMD
 	bool "Support SIMD acceleration for AEGIS-128"
 	depends on CRYPTO_AEGIS128 && ((ARM || ARM64) && KERNEL_MODE_NEON)
+	depends on !ARM || CC_IS_CLANG || GCC_VERSION >= 40800
 	default y
 
 config CRYPTO_AEGIS128_AESNI_SSE2
@@ -322,7 +334,7 @@ config CRYPTO_AEGIS128_AESNI_SSE2
 config CRYPTO_SEQIV
 	tristate "Sequence Number IV Generator"
 	select CRYPTO_AEAD
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_NULL
 	select CRYPTO_RNG_DEFAULT
 	select CRYPTO_MANAGER
@@ -345,7 +357,7 @@ comment "Block modes"
 
 config CRYPTO_CBC
 	tristate "CBC support"
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_MANAGER
 	help
 	  CBC: Cipher Block Chaining mode
@@ -353,7 +365,7 @@ config CRYPTO_CBC
 
 config CRYPTO_CFB
 	tristate "CFB support"
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_MANAGER
 	help
 	  CFB: Cipher FeedBack mode
@@ -361,7 +373,7 @@ config CRYPTO_CFB
 
 config CRYPTO_CTR
 	tristate "CTR support"
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_SEQIV
 	select CRYPTO_MANAGER
 	help
@@ -370,7 +382,7 @@ config CRYPTO_CTR
 
 config CRYPTO_CTS
 	tristate "CTS support"
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_MANAGER
 	help
 	  CTS: Cipher Text Stealing
@@ -385,7 +397,7 @@ config CRYPTO_CTS
 
 config CRYPTO_ECB
 	tristate "ECB support"
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_MANAGER
 	help
 	  ECB: Electronic CodeBook mode
@@ -394,7 +406,7 @@ config CRYPTO_ECB
 
 config CRYPTO_LRW
 	tristate "LRW support"
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_MANAGER
 	select CRYPTO_GF128MUL
 	help
@@ -406,7 +418,7 @@ config CRYPTO_LRW
 
 config CRYPTO_OFB
 	tristate "OFB support"
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_MANAGER
 	help
 	  OFB: the Output Feedback mode makes a block cipher into a synchronous
@@ -418,7 +430,7 @@ config CRYPTO_OFB
 
 config CRYPTO_PCBC
 	tristate "PCBC support"
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_MANAGER
 	help
 	  PCBC: Propagating Cipher Block Chaining mode
@@ -426,7 +438,7 @@ config CRYPTO_PCBC
 
 config CRYPTO_XTS
 	tristate "XTS support"
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_MANAGER
 	select CRYPTO_ECB
 	help
@@ -436,7 +448,7 @@ config CRYPTO_XTS
 
 config CRYPTO_KEYWRAP
 	tristate "Key wrapping support"
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_MANAGER
 	help
 	  Support for key wrapping (NIST SP800-38F / RFC3394) without
@@ -445,7 +457,7 @@ config CRYPTO_KEYWRAP
 config CRYPTO_NHPOLY1305
 	tristate
 	select CRYPTO_HASH
-	select CRYPTO_POLY1305
+	select CRYPTO_LIB_POLY1305_GENERIC
 
 config CRYPTO_NHPOLY1305_SSE2
 	tristate "NHPoly1305 hash function (x86_64 SSE2 implementation)"
@@ -466,7 +478,7 @@ config CRYPTO_NHPOLY1305_AVX2
 config CRYPTO_ADIANTUM
 	tristate "Adiantum support"
 	select CRYPTO_CHACHA20
-	select CRYPTO_POLY1305
+	select CRYPTO_LIB_POLY1305_GENERIC
 	select CRYPTO_NHPOLY1305
 	select CRYPTO_MANAGER
 	help
@@ -638,6 +650,47 @@ config CRYPTO_XXHASH
 	  xxHash non-cryptographic hash algorithm. Extremely fast, working at
 	  speeds close to RAM limits.
 
+config CRYPTO_BLAKE2B
+	tristate "BLAKE2b digest algorithm"
+	select CRYPTO_HASH
+	help
+	  Implementation of cryptographic hash function BLAKE2b (or just BLAKE2),
+	  optimized for 64bit platforms and can produce digests of any size
+	  between 1 to 64.  The keyed hash is also implemented.
+
+	  This module provides the following algorithms:
+
+	  - blake2b-160
+	  - blake2b-256
+	  - blake2b-384
+	  - blake2b-512
+
+	  See https://blake2.net for further information.
+
+config CRYPTO_BLAKE2S
+	tristate "BLAKE2s digest algorithm"
+	select CRYPTO_LIB_BLAKE2S_GENERIC
+	select CRYPTO_HASH
+	help
+	  Implementation of cryptographic hash function BLAKE2s
+	  optimized for 8-32bit platforms and can produce digests of any size
+	  between 1 to 32.  The keyed hash is also implemented.
+
+	  This module provides the following algorithms:
+
+	  - blake2s-128
+	  - blake2s-160
+	  - blake2s-224
+	  - blake2s-256
+
+	  See https://blake2.net for further information.
+
+config CRYPTO_BLAKE2S_X86
+	tristate "BLAKE2s digest algorithm (x86 accelerated version)"
+	depends on X86 && 64BIT
+	select CRYPTO_LIB_BLAKE2S_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_BLAKE2S
+
 config CRYPTO_CRCT10DIF
 	tristate "CRCT10DIF algorithm"
 	select CRYPTO_HASH
@@ -685,6 +738,7 @@ config CRYPTO_GHASH
 config CRYPTO_POLY1305
 	tristate "Poly1305 authenticator algorithm"
 	select CRYPTO_HASH
+	select CRYPTO_LIB_POLY1305_GENERIC
 	help
 	  Poly1305 authenticator algorithm, RFC7539.
 
@@ -695,7 +749,8 @@ config CRYPTO_POLY1305
 config CRYPTO_POLY1305_X86_64
 	tristate "Poly1305 authenticator algorithm (x86_64/SSE2/AVX2)"
 	depends on X86 && 64BIT
-	select CRYPTO_POLY1305
+	select CRYPTO_LIB_POLY1305_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_POLY1305
 	help
 	  Poly1305 authenticator algorithm, RFC7539.
 
@@ -704,6 +759,11 @@ config CRYPTO_POLY1305_X86_64
 	  in IETF protocols. This is the x86_64 assembler implementation using SIMD
 	  instructions.
 
+config CRYPTO_POLY1305_MIPS
+	tristate "Poly1305 authenticator algorithm (MIPS optimized)"
+	depends on CPU_MIPS32 || (CPU_MIPS64 && 64BIT)
+	select CRYPTO_ARCH_HAVE_LIB_POLY1305
+
 config CRYPTO_MD4
 	tristate "MD4 digest algorithm"
 	select CRYPTO_HASH
@@ -877,9 +937,6 @@ config CRYPTO_SHA1_PPC_SPE
 	  SHA-1 secure hash standard (DFIPS 180-4) implemented
 	  using powerpc SPE SIMD instruction set.
 
-config CRYPTO_LIB_SHA256
-	tristate
-
 config CRYPTO_SHA256
 	tristate "SHA224 and SHA256 digest algorithm"
 	select CRYPTO_HASH
@@ -1018,9 +1075,6 @@ config CRYPTO_GHASH_CLMUL_NI_INTEL
 
 comment "Ciphers"
 
-config CRYPTO_LIB_AES
-	tristate
-
 config CRYPTO_AES
 	tristate "AES cipher algorithms"
 	select CRYPTO_ALGAPI
@@ -1067,7 +1121,7 @@ config CRYPTO_AES_NI_INTEL
 	select CRYPTO_AEAD
 	select CRYPTO_LIB_AES
 	select CRYPTO_ALGAPI
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_GLUE_HELPER_X86 if 64BIT
 	select CRYPTO_SIMD
 	help
@@ -1097,8 +1151,7 @@ config CRYPTO_AES_NI_INTEL
 config CRYPTO_AES_SPARC64
 	tristate "AES cipher algorithms (SPARC64)"
 	depends on SPARC64
-	select CRYPTO_CRYPTD
-	select CRYPTO_ALGAPI
+	select CRYPTO_SKCIPHER
 	help
 	  Use SPARC64 crypto opcodes for AES algorithm.
 
@@ -1125,6 +1178,7 @@ config CRYPTO_AES_SPARC64
 config CRYPTO_AES_PPC_SPE
 	tristate "AES cipher algorithms (PPC SPE)"
 	depends on PPC && SPE
+	select CRYPTO_SKCIPHER
 	help
 	  AES cipher algorithms (FIPS-197). Additionally the acceleration
 	  for popular block cipher modes ECB, CBC, CTR and XTS is supported.
@@ -1149,12 +1203,9 @@ config CRYPTO_ANUBIS
 	  <https://www.cosic.esat.kuleuven.be/nessie/reports/>
 	  <http://www.larc.usp.br/~pbarreto/AnubisPage.html>
 
-config CRYPTO_LIB_ARC4
-	tristate
-
 config CRYPTO_ARC4
 	tristate "ARC4 cipher algorithm"
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_ARC4
 	help
 	  ARC4 cipher algorithm.
@@ -1190,7 +1241,7 @@ config CRYPTO_BLOWFISH_COMMON
 config CRYPTO_BLOWFISH_X86_64
 	tristate "Blowfish cipher algorithm (x86_64)"
 	depends on X86 && 64BIT
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_BLOWFISH_COMMON
 	help
 	  Blowfish cipher algorithm (x86_64), by Bruce Schneier.
@@ -1221,7 +1272,7 @@ config CRYPTO_CAMELLIA_X86_64
 	tristate "Camellia cipher algorithm (x86_64)"
 	depends on X86 && 64BIT
 	depends on CRYPTO
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_GLUE_HELPER_X86
 	help
 	  Camellia cipher algorithm module (x86_64).
@@ -1238,7 +1289,7 @@ config CRYPTO_CAMELLIA_AESNI_AVX_X86_64
 	tristate "Camellia cipher algorithm (x86_64/AES-NI/AVX)"
 	depends on X86 && 64BIT
 	depends on CRYPTO
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_CAMELLIA_X86_64
 	select CRYPTO_GLUE_HELPER_X86
 	select CRYPTO_SIMD
@@ -1275,6 +1326,7 @@ config CRYPTO_CAMELLIA_SPARC64
 	depends on SPARC64
 	depends on CRYPTO
 	select CRYPTO_ALGAPI
+	select CRYPTO_SKCIPHER
 	help
 	  Camellia cipher algorithm module (SPARC64).
 
@@ -1303,7 +1355,7 @@ config CRYPTO_CAST5
 config CRYPTO_CAST5_AVX_X86_64
 	tristate "CAST5 (CAST-128) cipher algorithm (x86_64/AVX)"
 	depends on X86 && 64BIT
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_CAST5
 	select CRYPTO_CAST_COMMON
 	select CRYPTO_SIMD
@@ -1325,7 +1377,7 @@ config CRYPTO_CAST6
 config CRYPTO_CAST6_AVX_X86_64
 	tristate "CAST6 (CAST-256) cipher algorithm (x86_64/AVX)"
 	depends on X86 && 64BIT
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_CAST6
 	select CRYPTO_CAST_COMMON
 	select CRYPTO_GLUE_HELPER_X86
@@ -1338,9 +1390,6 @@ config CRYPTO_CAST6_AVX_X86_64
 	  This module provides the Cast6 cipher algorithm that processes
 	  eight blocks parallel using the AVX instruction set.
 
-config CRYPTO_LIB_DES
-	tristate
-
 config CRYPTO_DES
 	tristate "DES and Triple DES EDE cipher algorithms"
 	select CRYPTO_ALGAPI
@@ -1353,6 +1402,7 @@ config CRYPTO_DES_SPARC64
 	depends on SPARC64
 	select CRYPTO_ALGAPI
 	select CRYPTO_LIB_DES
+	select CRYPTO_SKCIPHER
 	help
 	  DES cipher algorithm (FIPS 46-2), and Triple DES EDE (FIPS 46-3),
 	  optimized using SPARC64 crypto opcodes.
@@ -1360,7 +1410,7 @@ config CRYPTO_DES_SPARC64
 config CRYPTO_DES3_EDE_X86_64
 	tristate "Triple DES EDE cipher algorithm (x86-64)"
 	depends on X86 && 64BIT
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_DES
 	help
 	  Triple DES EDE (FIPS 46-3) algorithm.
@@ -1373,7 +1423,7 @@ config CRYPTO_DES3_EDE_X86_64
 config CRYPTO_FCRYPT
 	tristate "FCrypt cipher algorithm"
 	select CRYPTO_ALGAPI
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	help
 	  FCrypt algorithm used by RxRPC.
 
@@ -1392,7 +1442,7 @@ config CRYPTO_KHAZAD
 
 config CRYPTO_SALSA20
 	tristate "Salsa20 stream cipher algorithm"
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	help
 	  Salsa20 stream cipher algorithm.
 
@@ -1404,7 +1454,8 @@ config CRYPTO_SALSA20
 
 config CRYPTO_CHACHA20
 	tristate "ChaCha stream cipher algorithms"
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_LIB_CHACHA_GENERIC
+	select CRYPTO_SKCIPHER
 	help
 	  The ChaCha20, XChaCha20, and XChaCha12 stream cipher algorithms.
 
@@ -1426,12 +1477,19 @@ config CRYPTO_CHACHA20
 config CRYPTO_CHACHA20_X86_64
 	tristate "ChaCha stream cipher algorithms (x86_64/SSSE3/AVX2/AVX-512VL)"
 	depends on X86 && 64BIT
-	select CRYPTO_BLKCIPHER
-	select CRYPTO_CHACHA20
+	select CRYPTO_SKCIPHER
+	select CRYPTO_LIB_CHACHA_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_CHACHA
 	help
 	  SSSE3, AVX2, and AVX-512VL optimized implementations of the ChaCha20,
 	  XChaCha20, and XChaCha12 stream ciphers.
 
+config CRYPTO_CHACHA_MIPS
+	tristate "ChaCha stream cipher algorithms (MIPS 32r2 optimized)"
+	depends on CPU_MIPS32_R2
+	select CRYPTO_SKCIPHER
+	select CRYPTO_ARCH_HAVE_LIB_CHACHA
+
 config CRYPTO_SEED
 	tristate "SEED cipher algorithm"
 	select CRYPTO_ALGAPI
@@ -1462,7 +1520,7 @@ config CRYPTO_SERPENT
 config CRYPTO_SERPENT_SSE2_X86_64
 	tristate "Serpent cipher algorithm (x86_64/SSE2)"
 	depends on X86 && 64BIT
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_GLUE_HELPER_X86
 	select CRYPTO_SERPENT
 	select CRYPTO_SIMD
@@ -1481,7 +1539,7 @@ config CRYPTO_SERPENT_SSE2_X86_64
 config CRYPTO_SERPENT_SSE2_586
 	tristate "Serpent cipher algorithm (i586/SSE2)"
 	depends on X86 && !64BIT
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_GLUE_HELPER_X86
 	select CRYPTO_SERPENT
 	select CRYPTO_SIMD
@@ -1500,7 +1558,7 @@ config CRYPTO_SERPENT_SSE2_586
 config CRYPTO_SERPENT_AVX_X86_64
 	tristate "Serpent cipher algorithm (x86_64/AVX)"
 	depends on X86 && 64BIT
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_GLUE_HELPER_X86
 	select CRYPTO_SERPENT
 	select CRYPTO_SIMD
@@ -1631,7 +1689,7 @@ config CRYPTO_TWOFISH_X86_64
 config CRYPTO_TWOFISH_X86_64_3WAY
 	tristate "Twofish cipher algorithm (x86_64, 3-way parallel)"
 	depends on X86 && 64BIT
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_TWOFISH_COMMON
 	select CRYPTO_TWOFISH_X86_64
 	select CRYPTO_GLUE_HELPER_X86
@@ -1652,7 +1710,7 @@ config CRYPTO_TWOFISH_X86_64_3WAY
 config CRYPTO_TWOFISH_AVX_X86_64
 	tristate "Twofish cipher algorithm (x86_64/AVX)"
 	depends on X86 && 64BIT
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_GLUE_HELPER_X86
 	select CRYPTO_SIMD
 	select CRYPTO_TWOFISH_COMMON
@@ -1803,7 +1861,7 @@ config CRYPTO_USER_API_HASH
 config CRYPTO_USER_API_SKCIPHER
 	tristate "User-space interface for symmetric key cipher algorithms"
 	depends on NET
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_USER_API
 	help
 	  This option enables the user-spaces interface for symmetric
@@ -1822,7 +1880,7 @@ config CRYPTO_USER_API_AEAD
 	tristate "User-space interface for AEAD cipher algorithms"
 	depends on NET
 	select CRYPTO_AEAD
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_NULL
 	select CRYPTO_USER_API
 	help
@@ -1844,6 +1902,7 @@ config CRYPTO_STATS
 config CRYPTO_HASH_INFO
 	bool
 
+source "lib/crypto/Kconfig"
 source "drivers/crypto/Kconfig"
 source "crypto/asymmetric_keys/Kconfig"
 source "certs/Kconfig"
diff --git a/crypto/Makefile b/crypto/Makefile
index fcb1ee679782..4ca12b6044f7 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -14,11 +14,9 @@ crypto_algapi-y := algapi.o scatterwalk.o $(crypto_algapi-y)
 obj-$(CONFIG_CRYPTO_ALGAPI2) += crypto_algapi.o
 
 obj-$(CONFIG_CRYPTO_AEAD2) += aead.o
+obj-$(CONFIG_CRYPTO_AEAD2) += geniv.o
 
-crypto_blkcipher-y := ablkcipher.o
-crypto_blkcipher-y += blkcipher.o
-crypto_blkcipher-y += skcipher.o
-obj-$(CONFIG_CRYPTO_BLKCIPHER2) += crypto_blkcipher.o
+obj-$(CONFIG_CRYPTO_SKCIPHER2) += skcipher.o
 obj-$(CONFIG_CRYPTO_SEQIV) += seqiv.o
 obj-$(CONFIG_CRYPTO_ECHAINIV) += echainiv.o
 
@@ -74,6 +72,8 @@ obj-$(CONFIG_CRYPTO_STREEBOG) += streebog_generic.o
 obj-$(CONFIG_CRYPTO_WP512) += wp512.o
 CFLAGS_wp512.o := $(call cc-option,-fno-schedule-insns)  # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149
 obj-$(CONFIG_CRYPTO_TGR192) += tgr192.o
+obj-$(CONFIG_CRYPTO_BLAKE2B) += blake2b_generic.o
+obj-$(CONFIG_CRYPTO_BLAKE2S) += blake2s_generic.o
 obj-$(CONFIG_CRYPTO_GF128MUL) += gf128mul.o
 obj-$(CONFIG_CRYPTO_ECB) += ecb.o
 obj-$(CONFIG_CRYPTO_CBC) += cbc.o
@@ -93,7 +93,7 @@ obj-$(CONFIG_CRYPTO_AEGIS128) += aegis128.o
 aegis128-y := aegis128-core.o
 
 ifeq ($(ARCH),arm)
-CFLAGS_aegis128-neon-inner.o += -ffreestanding -march=armv7-a -mfloat-abi=softfp
+CFLAGS_aegis128-neon-inner.o += -ffreestanding -march=armv8-a -mfloat-abi=softfp
 CFLAGS_aegis128-neon-inner.o += -mfpu=crypto-neon-fp-armv8
 aegis128-$(CONFIG_CRYPTO_AEGIS128_SIMD) += aegis128-neon.o aegis128-neon-inner.o
 endif
@@ -166,6 +166,7 @@ obj-$(CONFIG_CRYPTO_ZSTD) += zstd.o
 obj-$(CONFIG_CRYPTO_OFB) += ofb.o
 obj-$(CONFIG_CRYPTO_ECC) += ecc.o
 obj-$(CONFIG_CRYPTO_ESSIV) += essiv.o
+obj-$(CONFIG_CRYPTO_CURVE25519) += curve25519-generic.o
 
 ecdh_generic-y += ecdh.o
 ecdh_generic-y += ecdh_helper.o
diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c
deleted file mode 100644
index 072b5646a0a3..000000000000
--- a/crypto/ablkcipher.c
+++ /dev/null
@@ -1,407 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Asynchronous block chaining cipher operations.
- *
- * This is the asynchronous version of blkcipher.c indicating completion
- * via a callback.
- *
- * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
- */
-
-#include <crypto/internal/skcipher.h>
-#include <linux/err.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/seq_file.h>
-#include <linux/cryptouser.h>
-#include <linux/compiler.h>
-#include <net/netlink.h>
-
-#include <crypto/scatterwalk.h>
-
-#include "internal.h"
-
-struct ablkcipher_buffer {
-	struct list_head	entry;
-	struct scatter_walk	dst;
-	unsigned int		len;
-	void			*data;
-};
-
-enum {
-	ABLKCIPHER_WALK_SLOW = 1 << 0,
-};
-
-static inline void ablkcipher_buffer_write(struct ablkcipher_buffer *p)
-{
-	scatterwalk_copychunks(p->data, &p->dst, p->len, 1);
-}
-
-void __ablkcipher_walk_complete(struct ablkcipher_walk *walk)
-{
-	struct ablkcipher_buffer *p, *tmp;
-
-	list_for_each_entry_safe(p, tmp, &walk->buffers, entry) {
-		ablkcipher_buffer_write(p);
-		list_del(&p->entry);
-		kfree(p);
-	}
-}
-EXPORT_SYMBOL_GPL(__ablkcipher_walk_complete);
-
-static inline void ablkcipher_queue_write(struct ablkcipher_walk *walk,
-					  struct ablkcipher_buffer *p)
-{
-	p->dst = walk->out;
-	list_add_tail(&p->entry, &walk->buffers);
-}
-
-/* Get a spot of the specified length that does not straddle a page.
- * The caller needs to ensure that there is enough space for this operation.
- */
-static inline u8 *ablkcipher_get_spot(u8 *start, unsigned int len)
-{
-	u8 *end_page = (u8 *)(((unsigned long)(start + len - 1)) & PAGE_MASK);
-
-	return max(start, end_page);
-}
-
-static inline void ablkcipher_done_slow(struct ablkcipher_walk *walk,
-					unsigned int n)
-{
-	for (;;) {
-		unsigned int len_this_page = scatterwalk_pagelen(&walk->out);
-
-		if (len_this_page > n)
-			len_this_page = n;
-		scatterwalk_advance(&walk->out, n);
-		if (n == len_this_page)
-			break;
-		n -= len_this_page;
-		scatterwalk_start(&walk->out, sg_next(walk->out.sg));
-	}
-}
-
-static inline void ablkcipher_done_fast(struct ablkcipher_walk *walk,
-					unsigned int n)
-{
-	scatterwalk_advance(&walk->in, n);
-	scatterwalk_advance(&walk->out, n);
-}
-
-static int ablkcipher_walk_next(struct ablkcipher_request *req,
-				struct ablkcipher_walk *walk);
-
-int ablkcipher_walk_done(struct ablkcipher_request *req,
-			 struct ablkcipher_walk *walk, int err)
-{
-	struct crypto_tfm *tfm = req->base.tfm;
-	unsigned int n; /* bytes processed */
-	bool more;
-
-	if (unlikely(err < 0))
-		goto finish;
-
-	n = walk->nbytes - err;
-	walk->total -= n;
-	more = (walk->total != 0);
-
-	if (likely(!(walk->flags & ABLKCIPHER_WALK_SLOW))) {
-		ablkcipher_done_fast(walk, n);
-	} else {
-		if (WARN_ON(err)) {
-			/* unexpected case; didn't process all bytes */
-			err = -EINVAL;
-			goto finish;
-		}
-		ablkcipher_done_slow(walk, n);
-	}
-
-	scatterwalk_done(&walk->in, 0, more);
-	scatterwalk_done(&walk->out, 1, more);
-
-	if (more) {
-		crypto_yield(req->base.flags);
-		return ablkcipher_walk_next(req, walk);
-	}
-	err = 0;
-finish:
-	walk->nbytes = 0;
-	if (walk->iv != req->info)
-		memcpy(req->info, walk->iv, tfm->crt_ablkcipher.ivsize);
-	kfree(walk->iv_buffer);
-	return err;
-}
-EXPORT_SYMBOL_GPL(ablkcipher_walk_done);
-
-static inline int ablkcipher_next_slow(struct ablkcipher_request *req,
-				       struct ablkcipher_walk *walk,
-				       unsigned int bsize,
-				       unsigned int alignmask,
-				       void **src_p, void **dst_p)
-{
-	unsigned aligned_bsize = ALIGN(bsize, alignmask + 1);
-	struct ablkcipher_buffer *p;
-	void *src, *dst, *base;
-	unsigned int n;
-
-	n = ALIGN(sizeof(struct ablkcipher_buffer), alignmask + 1);
-	n += (aligned_bsize * 3 - (alignmask + 1) +
-	      (alignmask & ~(crypto_tfm_ctx_alignment() - 1)));
-
-	p = kmalloc(n, GFP_ATOMIC);
-	if (!p)
-		return ablkcipher_walk_done(req, walk, -ENOMEM);
-
-	base = p + 1;
-
-	dst = (u8 *)ALIGN((unsigned long)base, alignmask + 1);
-	src = dst = ablkcipher_get_spot(dst, bsize);
-
-	p->len = bsize;
-	p->data = dst;
-
-	scatterwalk_copychunks(src, &walk->in, bsize, 0);
-
-	ablkcipher_queue_write(walk, p);
-
-	walk->nbytes = bsize;
-	walk->flags |= ABLKCIPHER_WALK_SLOW;
-
-	*src_p = src;
-	*dst_p = dst;
-
-	return 0;
-}
-
-static inline int ablkcipher_copy_iv(struct ablkcipher_walk *walk,
-				     struct crypto_tfm *tfm,
-				     unsigned int alignmask)
-{
-	unsigned bs = walk->blocksize;
-	unsigned int ivsize = tfm->crt_ablkcipher.ivsize;
-	unsigned aligned_bs = ALIGN(bs, alignmask + 1);
-	unsigned int size = aligned_bs * 2 + ivsize + max(aligned_bs, ivsize) -
-			    (alignmask + 1);
-	u8 *iv;
-
-	size += alignmask & ~(crypto_tfm_ctx_alignment() - 1);
-	walk->iv_buffer = kmalloc(size, GFP_ATOMIC);
-	if (!walk->iv_buffer)
-		return -ENOMEM;
-
-	iv = (u8 *)ALIGN((unsigned long)walk->iv_buffer, alignmask + 1);
-	iv = ablkcipher_get_spot(iv, bs) + aligned_bs;
-	iv = ablkcipher_get_spot(iv, bs) + aligned_bs;
-	iv = ablkcipher_get_spot(iv, ivsize);
-
-	walk->iv = memcpy(iv, walk->iv, ivsize);
-	return 0;
-}
-
-static inline int ablkcipher_next_fast(struct ablkcipher_request *req,
-				       struct ablkcipher_walk *walk)
-{
-	walk->src.page = scatterwalk_page(&walk->in);
-	walk->src.offset = offset_in_page(walk->in.offset);
-	walk->dst.page = scatterwalk_page(&walk->out);
-	walk->dst.offset = offset_in_page(walk->out.offset);
-
-	return 0;
-}
-
-static int ablkcipher_walk_next(struct ablkcipher_request *req,
-				struct ablkcipher_walk *walk)
-{
-	struct crypto_tfm *tfm = req->base.tfm;
-	unsigned int alignmask, bsize, n;
-	void *src, *dst;
-	int err;
-
-	alignmask = crypto_tfm_alg_alignmask(tfm);
-	n = walk->total;
-	if (unlikely(n < crypto_tfm_alg_blocksize(tfm))) {
-		req->base.flags |= CRYPTO_TFM_RES_BAD_BLOCK_LEN;
-		return ablkcipher_walk_done(req, walk, -EINVAL);
-	}
-
-	walk->flags &= ~ABLKCIPHER_WALK_SLOW;
-	src = dst = NULL;
-
-	bsize = min(walk->blocksize, n);
-	n = scatterwalk_clamp(&walk->in, n);
-	n = scatterwalk_clamp(&walk->out, n);
-
-	if (n < bsize ||
-	    !scatterwalk_aligned(&walk->in, alignmask) ||
-	    !scatterwalk_aligned(&walk->out, alignmask)) {
-		err = ablkcipher_next_slow(req, walk, bsize, alignmask,
-					   &src, &dst);
-		goto set_phys_lowmem;
-	}
-
-	walk->nbytes = n;
-
-	return ablkcipher_next_fast(req, walk);
-
-set_phys_lowmem:
-	if (err >= 0) {
-		walk->src.page = virt_to_page(src);
-		walk->dst.page = virt_to_page(dst);
-		walk->src.offset = ((unsigned long)src & (PAGE_SIZE - 1));
-		walk->dst.offset = ((unsigned long)dst & (PAGE_SIZE - 1));
-	}
-
-	return err;
-}
-
-static int ablkcipher_walk_first(struct ablkcipher_request *req,
-				 struct ablkcipher_walk *walk)
-{
-	struct crypto_tfm *tfm = req->base.tfm;
-	unsigned int alignmask;
-
-	alignmask = crypto_tfm_alg_alignmask(tfm);
-	if (WARN_ON_ONCE(in_irq()))
-		return -EDEADLK;
-
-	walk->iv = req->info;
-	walk->nbytes = walk->total;
-	if (unlikely(!walk->total))
-		return 0;
-
-	walk->iv_buffer = NULL;
-	if (unlikely(((unsigned long)walk->iv & alignmask))) {
-		int err = ablkcipher_copy_iv(walk, tfm, alignmask);
-
-		if (err)
-			return err;
-	}
-
-	scatterwalk_start(&walk->in, walk->in.sg);
-	scatterwalk_start(&walk->out, walk->out.sg);
-
-	return ablkcipher_walk_next(req, walk);
-}
-
-int ablkcipher_walk_phys(struct ablkcipher_request *req,
-			 struct ablkcipher_walk *walk)
-{
-	walk->blocksize = crypto_tfm_alg_blocksize(req->base.tfm);
-	return ablkcipher_walk_first(req, walk);
-}
-EXPORT_SYMBOL_GPL(ablkcipher_walk_phys);
-
-static int setkey_unaligned(struct crypto_ablkcipher *tfm, const u8 *key,
-			    unsigned int keylen)
-{
-	struct ablkcipher_alg *cipher = crypto_ablkcipher_alg(tfm);
-	unsigned long alignmask = crypto_ablkcipher_alignmask(tfm);
-	int ret;
-	u8 *buffer, *alignbuffer;
-	unsigned long absize;
-
-	absize = keylen + alignmask;
-	buffer = kmalloc(absize, GFP_ATOMIC);
-	if (!buffer)
-		return -ENOMEM;
-
-	alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1);
-	memcpy(alignbuffer, key, keylen);
-	ret = cipher->setkey(tfm, alignbuffer, keylen);
-	memset(alignbuffer, 0, keylen);
-	kfree(buffer);
-	return ret;
-}
-
-static int setkey(struct crypto_ablkcipher *tfm, const u8 *key,
-		  unsigned int keylen)
-{
-	struct ablkcipher_alg *cipher = crypto_ablkcipher_alg(tfm);
-	unsigned long alignmask = crypto_ablkcipher_alignmask(tfm);
-
-	if (keylen < cipher->min_keysize || keylen > cipher->max_keysize) {
-		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
-	}
-
-	if ((unsigned long)key & alignmask)
-		return setkey_unaligned(tfm, key, keylen);
-
-	return cipher->setkey(tfm, key, keylen);
-}
-
-static unsigned int crypto_ablkcipher_ctxsize(struct crypto_alg *alg, u32 type,
-					      u32 mask)
-{
-	return alg->cra_ctxsize;
-}
-
-static int crypto_init_ablkcipher_ops(struct crypto_tfm *tfm, u32 type,
-				      u32 mask)
-{
-	struct ablkcipher_alg *alg = &tfm->__crt_alg->cra_ablkcipher;
-	struct ablkcipher_tfm *crt = &tfm->crt_ablkcipher;
-
-	if (alg->ivsize > PAGE_SIZE / 8)
-		return -EINVAL;
-
-	crt->setkey = setkey;
-	crt->encrypt = alg->encrypt;
-	crt->decrypt = alg->decrypt;
-	crt->base = __crypto_ablkcipher_cast(tfm);
-	crt->ivsize = alg->ivsize;
-
-	return 0;
-}
-
-#ifdef CONFIG_NET
-static int crypto_ablkcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	struct crypto_report_blkcipher rblkcipher;
-
-	memset(&rblkcipher, 0, sizeof(rblkcipher));
-
-	strscpy(rblkcipher.type, "ablkcipher", sizeof(rblkcipher.type));
-	strscpy(rblkcipher.geniv, "<default>", sizeof(rblkcipher.geniv));
-
-	rblkcipher.blocksize = alg->cra_blocksize;
-	rblkcipher.min_keysize = alg->cra_ablkcipher.min_keysize;
-	rblkcipher.max_keysize = alg->cra_ablkcipher.max_keysize;
-	rblkcipher.ivsize = alg->cra_ablkcipher.ivsize;
-
-	return nla_put(skb, CRYPTOCFGA_REPORT_BLKCIPHER,
-		       sizeof(rblkcipher), &rblkcipher);
-}
-#else
-static int crypto_ablkcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	return -ENOSYS;
-}
-#endif
-
-static void crypto_ablkcipher_show(struct seq_file *m, struct crypto_alg *alg)
-	__maybe_unused;
-static void crypto_ablkcipher_show(struct seq_file *m, struct crypto_alg *alg)
-{
-	struct ablkcipher_alg *ablkcipher = &alg->cra_ablkcipher;
-
-	seq_printf(m, "type         : ablkcipher\n");
-	seq_printf(m, "async        : %s\n", alg->cra_flags & CRYPTO_ALG_ASYNC ?
-					     "yes" : "no");
-	seq_printf(m, "blocksize    : %u\n", alg->cra_blocksize);
-	seq_printf(m, "min keysize  : %u\n", ablkcipher->min_keysize);
-	seq_printf(m, "max keysize  : %u\n", ablkcipher->max_keysize);
-	seq_printf(m, "ivsize       : %u\n", ablkcipher->ivsize);
-	seq_printf(m, "geniv        : <default>\n");
-}
-
-const struct crypto_type crypto_ablkcipher_type = {
-	.ctxsize = crypto_ablkcipher_ctxsize,
-	.init = crypto_init_ablkcipher_ops,
-#ifdef CONFIG_PROC_FS
-	.show = crypto_ablkcipher_show,
-#endif
-	.report = crypto_ablkcipher_report,
-};
-EXPORT_SYMBOL_GPL(crypto_ablkcipher_type);
diff --git a/crypto/adiantum.c b/crypto/adiantum.c
index 395a3ddd3707..aded26092268 100644
--- a/crypto/adiantum.c
+++ b/crypto/adiantum.c
@@ -33,6 +33,7 @@
 #include <crypto/b128ops.h>
 #include <crypto/chacha.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/poly1305.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/nhpoly1305.h>
 #include <crypto/scatterwalk.h>
@@ -242,11 +243,11 @@ static void adiantum_hash_header(struct skcipher_request *req)
 
 	BUILD_BUG_ON(sizeof(header) % POLY1305_BLOCK_SIZE != 0);
 	poly1305_core_blocks(&state, &tctx->header_hash_key,
-			     &header, sizeof(header) / POLY1305_BLOCK_SIZE);
+			     &header, sizeof(header) / POLY1305_BLOCK_SIZE, 1);
 
 	BUILD_BUG_ON(TWEAK_SIZE % POLY1305_BLOCK_SIZE != 0);
 	poly1305_core_blocks(&state, &tctx->header_hash_key, req->iv,
-			     TWEAK_SIZE / POLY1305_BLOCK_SIZE);
+			     TWEAK_SIZE / POLY1305_BLOCK_SIZE, 1);
 
 	poly1305_core_emit(&state, &rctx->header_hash);
 }
diff --git a/crypto/aead.c b/crypto/aead.c
index ce035589cf57..47f16d139e8e 100644
--- a/crypto/aead.c
+++ b/crypto/aead.c
@@ -7,19 +7,14 @@
  * Copyright (c) 2007-2015 Herbert Xu <herbert@gondor.apana.org.au>
  */
 
-#include <crypto/internal/geniv.h>
-#include <crypto/internal/rng.h>
-#include <crypto/null.h>
-#include <crypto/scatterwalk.h>
-#include <linux/err.h>
+#include <crypto/internal/aead.h>
+#include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/rtnetlink.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
 #include <linux/cryptouser.h>
-#include <linux/compiler.h>
 #include <net/netlink.h>
 
 #include "internal.h"
@@ -212,162 +207,6 @@ static const struct crypto_type crypto_aead_type = {
 	.tfmsize = offsetof(struct crypto_aead, base),
 };
 
-static int aead_geniv_setkey(struct crypto_aead *tfm,
-			     const u8 *key, unsigned int keylen)
-{
-	struct aead_geniv_ctx *ctx = crypto_aead_ctx(tfm);
-
-	return crypto_aead_setkey(ctx->child, key, keylen);
-}
-
-static int aead_geniv_setauthsize(struct crypto_aead *tfm,
-				  unsigned int authsize)
-{
-	struct aead_geniv_ctx *ctx = crypto_aead_ctx(tfm);
-
-	return crypto_aead_setauthsize(ctx->child, authsize);
-}
-
-struct aead_instance *aead_geniv_alloc(struct crypto_template *tmpl,
-				       struct rtattr **tb, u32 type, u32 mask)
-{
-	const char *name;
-	struct crypto_aead_spawn *spawn;
-	struct crypto_attr_type *algt;
-	struct aead_instance *inst;
-	struct aead_alg *alg;
-	unsigned int ivsize;
-	unsigned int maxauthsize;
-	int err;
-
-	algt = crypto_get_attr_type(tb);
-	if (IS_ERR(algt))
-		return ERR_CAST(algt);
-
-	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
-		return ERR_PTR(-EINVAL);
-
-	name = crypto_attr_alg_name(tb[1]);
-	if (IS_ERR(name))
-		return ERR_CAST(name);
-
-	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
-	if (!inst)
-		return ERR_PTR(-ENOMEM);
-
-	spawn = aead_instance_ctx(inst);
-
-	/* Ignore async algorithms if necessary. */
-	mask |= crypto_requires_sync(algt->type, algt->mask);
-
-	crypto_set_aead_spawn(spawn, aead_crypto_instance(inst));
-	err = crypto_grab_aead(spawn, name, type, mask);
-	if (err)
-		goto err_free_inst;
-
-	alg = crypto_spawn_aead_alg(spawn);
-
-	ivsize = crypto_aead_alg_ivsize(alg);
-	maxauthsize = crypto_aead_alg_maxauthsize(alg);
-
-	err = -EINVAL;
-	if (ivsize < sizeof(u64))
-		goto err_drop_alg;
-
-	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
-		     "%s(%s)", tmpl->name, alg->base.cra_name) >=
-	    CRYPTO_MAX_ALG_NAME)
-		goto err_drop_alg;
-	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "%s(%s)", tmpl->name, alg->base.cra_driver_name) >=
-	    CRYPTO_MAX_ALG_NAME)
-		goto err_drop_alg;
-
-	inst->alg.base.cra_flags = alg->base.cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.base.cra_priority = alg->base.cra_priority;
-	inst->alg.base.cra_blocksize = alg->base.cra_blocksize;
-	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
-	inst->alg.base.cra_ctxsize = sizeof(struct aead_geniv_ctx);
-
-	inst->alg.setkey = aead_geniv_setkey;
-	inst->alg.setauthsize = aead_geniv_setauthsize;
-
-	inst->alg.ivsize = ivsize;
-	inst->alg.maxauthsize = maxauthsize;
-
-out:
-	return inst;
-
-err_drop_alg:
-	crypto_drop_aead(spawn);
-err_free_inst:
-	kfree(inst);
-	inst = ERR_PTR(err);
-	goto out;
-}
-EXPORT_SYMBOL_GPL(aead_geniv_alloc);
-
-void aead_geniv_free(struct aead_instance *inst)
-{
-	crypto_drop_aead(aead_instance_ctx(inst));
-	kfree(inst);
-}
-EXPORT_SYMBOL_GPL(aead_geniv_free);
-
-int aead_init_geniv(struct crypto_aead *aead)
-{
-	struct aead_geniv_ctx *ctx = crypto_aead_ctx(aead);
-	struct aead_instance *inst = aead_alg_instance(aead);
-	struct crypto_aead *child;
-	int err;
-
-	spin_lock_init(&ctx->lock);
-
-	err = crypto_get_default_rng();
-	if (err)
-		goto out;
-
-	err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
-				   crypto_aead_ivsize(aead));
-	crypto_put_default_rng();
-	if (err)
-		goto out;
-
-	ctx->sknull = crypto_get_default_null_skcipher();
-	err = PTR_ERR(ctx->sknull);
-	if (IS_ERR(ctx->sknull))
-		goto out;
-
-	child = crypto_spawn_aead(aead_instance_ctx(inst));
-	err = PTR_ERR(child);
-	if (IS_ERR(child))
-		goto drop_null;
-
-	ctx->child = child;
-	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(child) +
-				      sizeof(struct aead_request));
-
-	err = 0;
-
-out:
-	return err;
-
-drop_null:
-	crypto_put_default_null_skcipher();
-	goto out;
-}
-EXPORT_SYMBOL_GPL(aead_init_geniv);
-
-void aead_exit_geniv(struct crypto_aead *tfm)
-{
-	struct aead_geniv_ctx *ctx = crypto_aead_ctx(tfm);
-
-	crypto_free_aead(ctx->child);
-	crypto_put_default_null_skcipher();
-}
-EXPORT_SYMBOL_GPL(aead_exit_geniv);
-
 int crypto_grab_aead(struct crypto_aead_spawn *spawn, const char *name,
 		     u32 type, u32 mask)
 {
diff --git a/crypto/aegis128-core.c b/crypto/aegis128-core.c
index 80e73611bd5c..71c11cb5bad1 100644
--- a/crypto/aegis128-core.c
+++ b/crypto/aegis128-core.c
@@ -13,6 +13,7 @@
 #include <crypto/scatterwalk.h>
 #include <linux/err.h>
 #include <linux/init.h>
+#include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/scatterlist.h>
@@ -35,15 +36,7 @@ struct aegis_ctx {
 	union aegis_block key;
 };
 
-struct aegis128_ops {
-	int (*skcipher_walk_init)(struct skcipher_walk *walk,
-				  struct aead_request *req, bool atomic);
-
-	void (*crypt_chunk)(struct aegis_state *state, u8 *dst,
-			    const u8 *src, unsigned int size);
-};
-
-static bool have_simd;
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_simd);
 
 static const union aegis_block crypto_aegis_const[2] = {
 	{ .words64 = {
@@ -59,7 +52,7 @@ static const union aegis_block crypto_aegis_const[2] = {
 static bool aegis128_do_simd(void)
 {
 #ifdef CONFIG_CRYPTO_AEGIS128_SIMD
-	if (have_simd)
+	if (static_branch_likely(&have_simd))
 		return crypto_simd_usable();
 #endif
 	return false;
@@ -67,10 +60,16 @@ static bool aegis128_do_simd(void)
 
 bool crypto_aegis128_have_simd(void);
 void crypto_aegis128_update_simd(struct aegis_state *state, const void *msg);
+void crypto_aegis128_init_simd(struct aegis_state *state,
+			       const union aegis_block *key,
+			       const u8 *iv);
 void crypto_aegis128_encrypt_chunk_simd(struct aegis_state *state, u8 *dst,
 					const u8 *src, unsigned int size);
 void crypto_aegis128_decrypt_chunk_simd(struct aegis_state *state, u8 *dst,
 					const u8 *src, unsigned int size);
+void crypto_aegis128_final_simd(struct aegis_state *state,
+				union aegis_block *tag_xor,
+				u64 assoclen, u64 cryptlen);
 
 static void crypto_aegis128_update(struct aegis_state *state)
 {
@@ -323,25 +322,27 @@ static void crypto_aegis128_process_ad(struct aegis_state *state,
 	}
 }
 
-static void crypto_aegis128_process_crypt(struct aegis_state *state,
-					  struct aead_request *req,
-					  const struct aegis128_ops *ops)
+static __always_inline
+int crypto_aegis128_process_crypt(struct aegis_state *state,
+				  struct aead_request *req,
+				  struct skcipher_walk *walk,
+				  void (*crypt)(struct aegis_state *state,
+					        u8 *dst, const u8 *src,
+					        unsigned int size))
 {
-	struct skcipher_walk walk;
+	int err = 0;
 
-	ops->skcipher_walk_init(&walk, req, false);
+	while (walk->nbytes) {
+		unsigned int nbytes = walk->nbytes;
 
-	while (walk.nbytes) {
-		unsigned int nbytes = walk.nbytes;
+		if (nbytes < walk->total)
+			nbytes = round_down(nbytes, walk->stride);
 
-		if (nbytes < walk.total)
-			nbytes = round_down(nbytes, walk.stride);
+		crypt(state, walk->dst.virt.addr, walk->src.virt.addr, nbytes);
 
-		ops->crypt_chunk(state, walk.dst.virt.addr, walk.src.virt.addr,
-				 nbytes);
-
-		skcipher_walk_done(&walk, walk.nbytes - nbytes);
+		err = skcipher_walk_done(walk, walk->nbytes - nbytes);
 	}
+	return err;
 }
 
 static void crypto_aegis128_final(struct aegis_state *state,
@@ -390,39 +391,31 @@ static int crypto_aegis128_setauthsize(struct crypto_aead *tfm,
 	return 0;
 }
 
-static void crypto_aegis128_crypt(struct aead_request *req,
-				  union aegis_block *tag_xor,
-				  unsigned int cryptlen,
-				  const struct aegis128_ops *ops)
-{
-	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	struct aegis_ctx *ctx = crypto_aead_ctx(tfm);
-	struct aegis_state state;
-
-	crypto_aegis128_init(&state, &ctx->key, req->iv);
-	crypto_aegis128_process_ad(&state, req->src, req->assoclen);
-	crypto_aegis128_process_crypt(&state, req, ops);
-	crypto_aegis128_final(&state, tag_xor, req->assoclen, cryptlen);
-}
-
 static int crypto_aegis128_encrypt(struct aead_request *req)
 {
-	const struct aegis128_ops *ops = &(struct aegis128_ops){
-		.skcipher_walk_init = skcipher_walk_aead_encrypt,
-		.crypt_chunk = crypto_aegis128_encrypt_chunk,
-	};
-
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	union aegis_block tag = {};
 	unsigned int authsize = crypto_aead_authsize(tfm);
+	struct aegis_ctx *ctx = crypto_aead_ctx(tfm);
 	unsigned int cryptlen = req->cryptlen;
+	struct skcipher_walk walk;
+	struct aegis_state state;
 
-	if (aegis128_do_simd())
-		ops = &(struct aegis128_ops){
-			.skcipher_walk_init = skcipher_walk_aead_encrypt,
-			.crypt_chunk = crypto_aegis128_encrypt_chunk_simd };
-
-	crypto_aegis128_crypt(req, &tag, cryptlen, ops);
+	skcipher_walk_aead_encrypt(&walk, req, false);
+	if (aegis128_do_simd()) {
+		crypto_aegis128_init_simd(&state, &ctx->key, req->iv);
+		crypto_aegis128_process_ad(&state, req->src, req->assoclen);
+		crypto_aegis128_process_crypt(&state, req, &walk,
+					      crypto_aegis128_encrypt_chunk_simd);
+		crypto_aegis128_final_simd(&state, &tag, req->assoclen,
+					   cryptlen);
+	} else {
+		crypto_aegis128_init(&state, &ctx->key, req->iv);
+		crypto_aegis128_process_ad(&state, req->src, req->assoclen);
+		crypto_aegis128_process_crypt(&state, req, &walk,
+					      crypto_aegis128_encrypt_chunk);
+		crypto_aegis128_final(&state, &tag, req->assoclen, cryptlen);
+	}
 
 	scatterwalk_map_and_copy(tag.bytes, req->dst, req->assoclen + cryptlen,
 				 authsize, 1);
@@ -431,26 +424,33 @@ static int crypto_aegis128_encrypt(struct aead_request *req)
 
 static int crypto_aegis128_decrypt(struct aead_request *req)
 {
-	const struct aegis128_ops *ops = &(struct aegis128_ops){
-		.skcipher_walk_init = skcipher_walk_aead_decrypt,
-		.crypt_chunk = crypto_aegis128_decrypt_chunk,
-	};
 	static const u8 zeros[AEGIS128_MAX_AUTH_SIZE] = {};
-
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	union aegis_block tag;
 	unsigned int authsize = crypto_aead_authsize(tfm);
 	unsigned int cryptlen = req->cryptlen - authsize;
+	struct aegis_ctx *ctx = crypto_aead_ctx(tfm);
+	struct skcipher_walk walk;
+	struct aegis_state state;
 
 	scatterwalk_map_and_copy(tag.bytes, req->src, req->assoclen + cryptlen,
 				 authsize, 0);
 
-	if (aegis128_do_simd())
-		ops = &(struct aegis128_ops){
-			.skcipher_walk_init = skcipher_walk_aead_decrypt,
-			.crypt_chunk = crypto_aegis128_decrypt_chunk_simd };
-
-	crypto_aegis128_crypt(req, &tag, cryptlen, ops);
+	skcipher_walk_aead_decrypt(&walk, req, false);
+	if (aegis128_do_simd()) {
+		crypto_aegis128_init_simd(&state, &ctx->key, req->iv);
+		crypto_aegis128_process_ad(&state, req->src, req->assoclen);
+		crypto_aegis128_process_crypt(&state, req, &walk,
+					      crypto_aegis128_decrypt_chunk_simd);
+		crypto_aegis128_final_simd(&state, &tag, req->assoclen,
+					   cryptlen);
+	} else {
+		crypto_aegis128_init(&state, &ctx->key, req->iv);
+		crypto_aegis128_process_ad(&state, req->src, req->assoclen);
+		crypto_aegis128_process_crypt(&state, req, &walk,
+					      crypto_aegis128_decrypt_chunk);
+		crypto_aegis128_final(&state, &tag, req->assoclen, cryptlen);
+	}
 
 	return crypto_memneq(tag.bytes, zeros, authsize) ? -EBADMSG : 0;
 }
@@ -481,8 +481,9 @@ static struct aead_alg crypto_aegis128_alg = {
 
 static int __init crypto_aegis128_module_init(void)
 {
-	if (IS_ENABLED(CONFIG_CRYPTO_AEGIS128_SIMD))
-		have_simd = crypto_aegis128_have_simd();
+	if (IS_ENABLED(CONFIG_CRYPTO_AEGIS128_SIMD) &&
+	    crypto_aegis128_have_simd())
+		static_branch_enable(&have_simd);
 
 	return crypto_register_aead(&crypto_aegis128_alg);
 }
diff --git a/crypto/aegis128-neon-inner.c b/crypto/aegis128-neon-inner.c
index f05310ca22aa..2a660ac1bc3a 100644
--- a/crypto/aegis128-neon-inner.c
+++ b/crypto/aegis128-neon-inner.c
@@ -132,6 +132,36 @@ void preload_sbox(void)
 	    :: "r"(crypto_aes_sbox));
 }
 
+void crypto_aegis128_init_neon(void *state, const void *key, const void *iv)
+{
+	static const uint8_t const0[] = {
+		0x00, 0x01, 0x01, 0x02, 0x03, 0x05, 0x08, 0x0d,
+		0x15, 0x22, 0x37, 0x59, 0x90, 0xe9, 0x79, 0x62,
+	};
+	static const uint8_t const1[] = {
+		0xdb, 0x3d, 0x18, 0x55, 0x6d, 0xc2, 0x2f, 0xf1,
+		0x20, 0x11, 0x31, 0x42, 0x73, 0xb5, 0x28, 0xdd,
+	};
+	uint8x16_t k = vld1q_u8(key);
+	uint8x16_t kiv = k ^ vld1q_u8(iv);
+	struct aegis128_state st = {{
+		kiv,
+		vld1q_u8(const1),
+		vld1q_u8(const0),
+		k ^ vld1q_u8(const0),
+		k ^ vld1q_u8(const1),
+	}};
+	int i;
+
+	preload_sbox();
+
+	for (i = 0; i < 5; i++) {
+		st = aegis128_update_neon(st, k);
+		st = aegis128_update_neon(st, kiv);
+	}
+	aegis128_save_state_neon(st, state);
+}
+
 void crypto_aegis128_update_neon(void *state, const void *msg)
 {
 	struct aegis128_state st = aegis128_load_state_neon(state);
@@ -210,3 +240,23 @@ void crypto_aegis128_decrypt_chunk_neon(void *state, void *dst, const void *src,
 
 	aegis128_save_state_neon(st, state);
 }
+
+void crypto_aegis128_final_neon(void *state, void *tag_xor, uint64_t assoclen,
+				uint64_t cryptlen)
+{
+	struct aegis128_state st = aegis128_load_state_neon(state);
+	uint8x16_t v;
+	int i;
+
+	preload_sbox();
+
+	v = st.v[3] ^ (uint8x16_t)vcombine_u64(vmov_n_u64(8 * assoclen),
+					       vmov_n_u64(8 * cryptlen));
+
+	for (i = 0; i < 7; i++)
+		st = aegis128_update_neon(st, v);
+
+	v = vld1q_u8(tag_xor);
+	v ^= st.v[0] ^ st.v[1] ^ st.v[2] ^ st.v[3] ^ st.v[4];
+	vst1q_u8(tag_xor, v);
+}
diff --git a/crypto/aegis128-neon.c b/crypto/aegis128-neon.c
index 751f9c195aa4..8271b1fa0fbc 100644
--- a/crypto/aegis128-neon.c
+++ b/crypto/aegis128-neon.c
@@ -8,11 +8,14 @@
 
 #include "aegis.h"
 
+void crypto_aegis128_init_neon(void *state, const void *key, const void *iv);
 void crypto_aegis128_update_neon(void *state, const void *msg);
 void crypto_aegis128_encrypt_chunk_neon(void *state, void *dst, const void *src,
 					unsigned int size);
 void crypto_aegis128_decrypt_chunk_neon(void *state, void *dst, const void *src,
 					unsigned int size);
+void crypto_aegis128_final_neon(void *state, void *tag_xor, uint64_t assoclen,
+				uint64_t cryptlen);
 
 int aegis128_have_aes_insn __ro_after_init;
 
@@ -25,6 +28,15 @@ bool crypto_aegis128_have_simd(void)
 	return IS_ENABLED(CONFIG_ARM64);
 }
 
+void crypto_aegis128_init_simd(union aegis_block *state,
+			       const union aegis_block *key,
+			       const u8 *iv)
+{
+	kernel_neon_begin();
+	crypto_aegis128_init_neon(state, key, iv);
+	kernel_neon_end();
+}
+
 void crypto_aegis128_update_simd(union aegis_block *state, const void *msg)
 {
 	kernel_neon_begin();
@@ -47,3 +59,12 @@ void crypto_aegis128_decrypt_chunk_simd(union aegis_block *state, u8 *dst,
 	crypto_aegis128_decrypt_chunk_neon(state, dst, src, size);
 	kernel_neon_end();
 }
+
+void crypto_aegis128_final_simd(union aegis_block *state,
+				union aegis_block *tag_xor,
+				u64 assoclen, u64 cryptlen)
+{
+	kernel_neon_begin();
+	crypto_aegis128_final_neon(state, tag_xor, assoclen, cryptlen);
+	kernel_neon_end();
+}
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 879cf23f7489..0dceaabc6321 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -1043,7 +1043,7 @@ void af_alg_async_cb(struct crypto_async_request *_req, int err)
 	af_alg_free_resources(areq);
 	sock_put(sk);
 
-	iocb->ki_complete(iocb, err ? err : resultlen, 0);
+	iocb->ki_complete(iocb, err ? err : (int)resultlen, 0);
 }
 EXPORT_SYMBOL_GPL(af_alg_async_cb);
 
diff --git a/crypto/algapi.c b/crypto/algapi.c
index de30ddc952d8..b052f38edba6 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -1052,32 +1052,6 @@ void crypto_stats_get(struct crypto_alg *alg)
 }
 EXPORT_SYMBOL_GPL(crypto_stats_get);
 
-void crypto_stats_ablkcipher_encrypt(unsigned int nbytes, int ret,
-				     struct crypto_alg *alg)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY) {
-		atomic64_inc(&alg->stats.cipher.err_cnt);
-	} else {
-		atomic64_inc(&alg->stats.cipher.encrypt_cnt);
-		atomic64_add(nbytes, &alg->stats.cipher.encrypt_tlen);
-	}
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_ablkcipher_encrypt);
-
-void crypto_stats_ablkcipher_decrypt(unsigned int nbytes, int ret,
-				     struct crypto_alg *alg)
-{
-	if (ret && ret != -EINPROGRESS && ret != -EBUSY) {
-		atomic64_inc(&alg->stats.cipher.err_cnt);
-	} else {
-		atomic64_inc(&alg->stats.cipher.decrypt_cnt);
-		atomic64_add(nbytes, &alg->stats.cipher.decrypt_tlen);
-	}
-	crypto_alg_put(alg);
-}
-EXPORT_SYMBOL_GPL(crypto_stats_ablkcipher_decrypt);
-
 void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg,
 			       int ret)
 {
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index c1601edd70e3..e2c8ab408bed 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -56,7 +56,7 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 	struct alg_sock *pask = alg_sk(psk);
 	struct af_alg_ctx *ctx = ask->private;
 	struct crypto_skcipher *tfm = pask->private;
-	unsigned int bs = crypto_skcipher_blocksize(tfm);
+	unsigned int bs = crypto_skcipher_chunksize(tfm);
 	struct af_alg_async_req *areq;
 	int err = 0;
 	size_t len = 0;
diff --git a/crypto/api.c b/crypto/api.c
index d8ba54142620..55bca28df92d 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -406,7 +406,7 @@ EXPORT_SYMBOL_GPL(__crypto_alloc_tfm);
  *
  *	The returned transform is of a non-determinate type.  Most people
  *	should use one of the more specific allocation functions such as
- *	crypto_alloc_blkcipher.
+ *	crypto_alloc_skcipher().
  *
  *	In case of error the return value is an error pointer.
  */
@@ -608,3 +608,4 @@ EXPORT_SYMBOL_GPL(crypto_req_done);
 
 MODULE_DESCRIPTION("Cryptographic core API");
 MODULE_LICENSE("GPL");
+MODULE_SOFTDEP("pre: cryptomgr");
diff --git a/crypto/asymmetric_keys/asym_tpm.c b/crypto/asymmetric_keys/asym_tpm.c
index 76d2ce3a1b5b..d16d893bd195 100644
--- a/crypto/asymmetric_keys/asym_tpm.c
+++ b/crypto/asymmetric_keys/asym_tpm.c
@@ -13,7 +13,7 @@
 #include <crypto/sha.h>
 #include <asm/unaligned.h>
 #include <keys/asymmetric-subtype.h>
-#include <keys/trusted.h>
+#include <keys/trusted_tpm.h>
 #include <crypto/asym_tpm_subtype.h>
 #include <crypto/public_key.h>
 
@@ -21,10 +21,6 @@
 #define TPM_ORD_LOADKEY2	65
 #define TPM_ORD_UNBIND		30
 #define TPM_ORD_SIGN		60
-#define TPM_LOADKEY2_SIZE		59
-#define TPM_FLUSHSPECIFIC_SIZE		18
-#define TPM_UNBIND_SIZE			63
-#define TPM_SIGN_SIZE			63
 
 #define TPM_RT_KEY                      0x00000001
 
@@ -68,16 +64,13 @@ static int tpm_loadkey2(struct tpm_buf *tb,
 		return ret;
 
 	/* build the request buffer */
-	INIT_BUF(tb);
-	store16(tb, TPM_TAG_RQU_AUTH1_COMMAND);
-	store32(tb, TPM_LOADKEY2_SIZE + keybloblen);
-	store32(tb, TPM_ORD_LOADKEY2);
-	store32(tb, keyhandle);
-	storebytes(tb, keyblob, keybloblen);
-	store32(tb, authhandle);
-	storebytes(tb, nonceodd, TPM_NONCE_SIZE);
-	store8(tb, cont);
-	storebytes(tb, authdata, SHA1_DIGEST_SIZE);
+	tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_LOADKEY2);
+	tpm_buf_append_u32(tb, keyhandle);
+	tpm_buf_append(tb, keyblob, keybloblen);
+	tpm_buf_append_u32(tb, authhandle);
+	tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE);
+	tpm_buf_append_u8(tb, cont);
+	tpm_buf_append(tb, authdata, SHA1_DIGEST_SIZE);
 
 	ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE);
 	if (ret < 0) {
@@ -101,12 +94,9 @@ static int tpm_loadkey2(struct tpm_buf *tb,
  */
 static int tpm_flushspecific(struct tpm_buf *tb, uint32_t handle)
 {
-	INIT_BUF(tb);
-	store16(tb, TPM_TAG_RQU_COMMAND);
-	store32(tb, TPM_FLUSHSPECIFIC_SIZE);
-	store32(tb, TPM_ORD_FLUSHSPECIFIC);
-	store32(tb, handle);
-	store32(tb, TPM_RT_KEY);
+	tpm_buf_reset(tb, TPM_TAG_RQU_COMMAND, TPM_ORD_FLUSHSPECIFIC);
+	tpm_buf_append_u32(tb, handle);
+	tpm_buf_append_u32(tb, TPM_RT_KEY);
 
 	return trusted_tpm_send(tb->data, MAX_BUF_SIZE);
 }
@@ -155,17 +145,14 @@ static int tpm_unbind(struct tpm_buf *tb,
 		return ret;
 
 	/* build the request buffer */
-	INIT_BUF(tb);
-	store16(tb, TPM_TAG_RQU_AUTH1_COMMAND);
-	store32(tb, TPM_UNBIND_SIZE + bloblen);
-	store32(tb, TPM_ORD_UNBIND);
-	store32(tb, keyhandle);
-	store32(tb, bloblen);
-	storebytes(tb, blob, bloblen);
-	store32(tb, authhandle);
-	storebytes(tb, nonceodd, TPM_NONCE_SIZE);
-	store8(tb, cont);
-	storebytes(tb, authdata, SHA1_DIGEST_SIZE);
+	tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_UNBIND);
+	tpm_buf_append_u32(tb, keyhandle);
+	tpm_buf_append_u32(tb, bloblen);
+	tpm_buf_append(tb, blob, bloblen);
+	tpm_buf_append_u32(tb, authhandle);
+	tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE);
+	tpm_buf_append_u8(tb, cont);
+	tpm_buf_append(tb, authdata, SHA1_DIGEST_SIZE);
 
 	ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE);
 	if (ret < 0) {
@@ -241,17 +228,14 @@ static int tpm_sign(struct tpm_buf *tb,
 		return ret;
 
 	/* build the request buffer */
-	INIT_BUF(tb);
-	store16(tb, TPM_TAG_RQU_AUTH1_COMMAND);
-	store32(tb, TPM_SIGN_SIZE + bloblen);
-	store32(tb, TPM_ORD_SIGN);
-	store32(tb, keyhandle);
-	store32(tb, bloblen);
-	storebytes(tb, blob, bloblen);
-	store32(tb, authhandle);
-	storebytes(tb, nonceodd, TPM_NONCE_SIZE);
-	store8(tb, cont);
-	storebytes(tb, authdata, SHA1_DIGEST_SIZE);
+	tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_SIGN);
+	tpm_buf_append_u32(tb, keyhandle);
+	tpm_buf_append_u32(tb, bloblen);
+	tpm_buf_append(tb, blob, bloblen);
+	tpm_buf_append_u32(tb, authhandle);
+	tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE);
+	tpm_buf_append_u8(tb, cont);
+	tpm_buf_append(tb, authdata, SHA1_DIGEST_SIZE);
 
 	ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE);
 	if (ret < 0) {
@@ -519,7 +503,7 @@ static int tpm_key_decrypt(struct tpm_key *tk,
 			   struct kernel_pkey_params *params,
 			   const void *in, void *out)
 {
-	struct tpm_buf *tb;
+	struct tpm_buf tb;
 	uint32_t keyhandle;
 	uint8_t srkauth[SHA1_DIGEST_SIZE];
 	uint8_t keyauth[SHA1_DIGEST_SIZE];
@@ -533,14 +517,14 @@ static int tpm_key_decrypt(struct tpm_key *tk,
 	if (strcmp(params->encoding, "pkcs1"))
 		return -ENOPKG;
 
-	tb = kzalloc(sizeof(*tb), GFP_KERNEL);
-	if (!tb)
-		return -ENOMEM;
+	r = tpm_buf_init(&tb, 0, 0);
+	if (r)
+		return r;
 
 	/* TODO: Handle a non-all zero SRK authorization */
 	memset(srkauth, 0, sizeof(srkauth));
 
-	r = tpm_loadkey2(tb, SRKHANDLE, srkauth,
+	r = tpm_loadkey2(&tb, SRKHANDLE, srkauth,
 				tk->blob, tk->blob_len, &keyhandle);
 	if (r < 0) {
 		pr_devel("loadkey2 failed (%d)\n", r);
@@ -550,16 +534,16 @@ static int tpm_key_decrypt(struct tpm_key *tk,
 	/* TODO: Handle a non-all zero key authorization */
 	memset(keyauth, 0, sizeof(keyauth));
 
-	r = tpm_unbind(tb, keyhandle, keyauth,
+	r = tpm_unbind(&tb, keyhandle, keyauth,
 		       in, params->in_len, out, params->out_len);
 	if (r < 0)
 		pr_devel("tpm_unbind failed (%d)\n", r);
 
-	if (tpm_flushspecific(tb, keyhandle) < 0)
+	if (tpm_flushspecific(&tb, keyhandle) < 0)
 		pr_devel("flushspecific failed (%d)\n", r);
 
 error:
-	kzfree(tb);
+	tpm_buf_destroy(&tb);
 	pr_devel("<==%s() = %d\n", __func__, r);
 	return r;
 }
@@ -643,7 +627,7 @@ static int tpm_key_sign(struct tpm_key *tk,
 			struct kernel_pkey_params *params,
 			const void *in, void *out)
 {
-	struct tpm_buf *tb;
+	struct tpm_buf tb;
 	uint32_t keyhandle;
 	uint8_t srkauth[SHA1_DIGEST_SIZE];
 	uint8_t keyauth[SHA1_DIGEST_SIZE];
@@ -681,15 +665,14 @@ static int tpm_key_sign(struct tpm_key *tk,
 		goto error_free_asn1_wrapped;
 	}
 
-	r = -ENOMEM;
-	tb = kzalloc(sizeof(*tb), GFP_KERNEL);
-	if (!tb)
+	r = tpm_buf_init(&tb, 0, 0);
+	if (r)
 		goto error_free_asn1_wrapped;
 
 	/* TODO: Handle a non-all zero SRK authorization */
 	memset(srkauth, 0, sizeof(srkauth));
 
-	r = tpm_loadkey2(tb, SRKHANDLE, srkauth,
+	r = tpm_loadkey2(&tb, SRKHANDLE, srkauth,
 			 tk->blob, tk->blob_len, &keyhandle);
 	if (r < 0) {
 		pr_devel("loadkey2 failed (%d)\n", r);
@@ -699,15 +682,15 @@ static int tpm_key_sign(struct tpm_key *tk,
 	/* TODO: Handle a non-all zero key authorization */
 	memset(keyauth, 0, sizeof(keyauth));
 
-	r = tpm_sign(tb, keyhandle, keyauth, in, in_len, out, params->out_len);
+	r = tpm_sign(&tb, keyhandle, keyauth, in, in_len, out, params->out_len);
 	if (r < 0)
 		pr_devel("tpm_sign failed (%d)\n", r);
 
-	if (tpm_flushspecific(tb, keyhandle) < 0)
+	if (tpm_flushspecific(&tb, keyhandle) < 0)
 		pr_devel("flushspecific failed (%d)\n", r);
 
 error_free_tb:
-	kzfree(tb);
+	tpm_buf_destroy(&tb);
 error_free_asn1_wrapped:
 	kfree(asn1_wrapped);
 	pr_devel("<==%s() = %d\n", __func__, r);
diff --git a/crypto/blake2b_generic.c b/crypto/blake2b_generic.c
new file mode 100644
index 000000000000..d04b1788dc42
--- /dev/null
+++ b/crypto/blake2b_generic.c
@@ -0,0 +1,320 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR Apache-2.0)
+/*
+ * BLAKE2b reference source code package - reference C implementations
+ *
+ * Copyright 2012, Samuel Neves <sneves@dei.uc.pt>.  You may use this under the
+ * terms of the CC0, the OpenSSL Licence, or the Apache Public License 2.0, at
+ * your option.  The terms of these licenses can be found at:
+ *
+ * - CC0 1.0 Universal : http://creativecommons.org/publicdomain/zero/1.0
+ * - OpenSSL license   : https://www.openssl.org/source/license.html
+ * - Apache 2.0        : http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * More information about the BLAKE2 hash function can be found at
+ * https://blake2.net.
+ *
+ * Note: the original sources have been modified for inclusion in linux kernel
+ * in terms of coding style, using generic helpers and simplifications of error
+ * handling.
+ */
+
+#include <asm/unaligned.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <crypto/internal/hash.h>
+
+#define BLAKE2B_160_DIGEST_SIZE		(160 / 8)
+#define BLAKE2B_256_DIGEST_SIZE		(256 / 8)
+#define BLAKE2B_384_DIGEST_SIZE		(384 / 8)
+#define BLAKE2B_512_DIGEST_SIZE		(512 / 8)
+
+enum blake2b_constant {
+	BLAKE2B_BLOCKBYTES    = 128,
+	BLAKE2B_KEYBYTES      = 64,
+};
+
+struct blake2b_state {
+	u64      h[8];
+	u64      t[2];
+	u64      f[2];
+	u8       buf[BLAKE2B_BLOCKBYTES];
+	size_t   buflen;
+};
+
+static const u64 blake2b_IV[8] = {
+	0x6a09e667f3bcc908ULL, 0xbb67ae8584caa73bULL,
+	0x3c6ef372fe94f82bULL, 0xa54ff53a5f1d36f1ULL,
+	0x510e527fade682d1ULL, 0x9b05688c2b3e6c1fULL,
+	0x1f83d9abfb41bd6bULL, 0x5be0cd19137e2179ULL
+};
+
+static const u8 blake2b_sigma[12][16] = {
+	{  0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15 },
+	{ 14, 10,  4,  8,  9, 15, 13,  6,  1, 12,  0,  2, 11,  7,  5,  3 },
+	{ 11,  8, 12,  0,  5,  2, 15, 13, 10, 14,  3,  6,  7,  1,  9,  4 },
+	{  7,  9,  3,  1, 13, 12, 11, 14,  2,  6,  5, 10,  4,  0, 15,  8 },
+	{  9,  0,  5,  7,  2,  4, 10, 15, 14,  1, 11, 12,  6,  8,  3, 13 },
+	{  2, 12,  6, 10,  0, 11,  8,  3,  4, 13,  7,  5, 15, 14,  1,  9 },
+	{ 12,  5,  1, 15, 14, 13,  4, 10,  0,  7,  6,  3,  9,  2,  8, 11 },
+	{ 13, 11,  7, 14, 12,  1,  3,  9,  5,  0, 15,  4,  8,  6,  2, 10 },
+	{  6, 15, 14,  9, 11,  3,  0,  8, 12,  2, 13,  7,  1,  4, 10,  5 },
+	{ 10,  2,  8,  4,  7,  6,  1,  5, 15, 11,  9, 14,  3, 12, 13,  0 },
+	{  0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15 },
+	{ 14, 10,  4,  8,  9, 15, 13,  6,  1, 12,  0,  2, 11,  7,  5,  3 }
+};
+
+static void blake2b_increment_counter(struct blake2b_state *S, const u64 inc)
+{
+	S->t[0] += inc;
+	S->t[1] += (S->t[0] < inc);
+}
+
+#define G(r,i,a,b,c,d)                                  \
+	do {                                            \
+		a = a + b + m[blake2b_sigma[r][2*i+0]]; \
+		d = ror64(d ^ a, 32);                   \
+		c = c + d;                              \
+		b = ror64(b ^ c, 24);                   \
+		a = a + b + m[blake2b_sigma[r][2*i+1]]; \
+		d = ror64(d ^ a, 16);                   \
+		c = c + d;                              \
+		b = ror64(b ^ c, 63);                   \
+	} while (0)
+
+#define ROUND(r)                                \
+	do {                                    \
+		G(r,0,v[ 0],v[ 4],v[ 8],v[12]); \
+		G(r,1,v[ 1],v[ 5],v[ 9],v[13]); \
+		G(r,2,v[ 2],v[ 6],v[10],v[14]); \
+		G(r,3,v[ 3],v[ 7],v[11],v[15]); \
+		G(r,4,v[ 0],v[ 5],v[10],v[15]); \
+		G(r,5,v[ 1],v[ 6],v[11],v[12]); \
+		G(r,6,v[ 2],v[ 7],v[ 8],v[13]); \
+		G(r,7,v[ 3],v[ 4],v[ 9],v[14]); \
+	} while (0)
+
+static void blake2b_compress(struct blake2b_state *S,
+			     const u8 block[BLAKE2B_BLOCKBYTES])
+{
+	u64 m[16];
+	u64 v[16];
+	size_t i;
+
+	for (i = 0; i < 16; ++i)
+		m[i] = get_unaligned_le64(block + i * sizeof(m[i]));
+
+	for (i = 0; i < 8; ++i)
+		v[i] = S->h[i];
+
+	v[ 8] = blake2b_IV[0];
+	v[ 9] = blake2b_IV[1];
+	v[10] = blake2b_IV[2];
+	v[11] = blake2b_IV[3];
+	v[12] = blake2b_IV[4] ^ S->t[0];
+	v[13] = blake2b_IV[5] ^ S->t[1];
+	v[14] = blake2b_IV[6] ^ S->f[0];
+	v[15] = blake2b_IV[7] ^ S->f[1];
+
+	ROUND(0);
+	ROUND(1);
+	ROUND(2);
+	ROUND(3);
+	ROUND(4);
+	ROUND(5);
+	ROUND(6);
+	ROUND(7);
+	ROUND(8);
+	ROUND(9);
+	ROUND(10);
+	ROUND(11);
+
+	for (i = 0; i < 8; ++i)
+		S->h[i] = S->h[i] ^ v[i] ^ v[i + 8];
+}
+
+#undef G
+#undef ROUND
+
+struct blake2b_tfm_ctx {
+	u8 key[BLAKE2B_KEYBYTES];
+	unsigned int keylen;
+};
+
+static int blake2b_setkey(struct crypto_shash *tfm, const u8 *key,
+			  unsigned int keylen)
+{
+	struct blake2b_tfm_ctx *tctx = crypto_shash_ctx(tfm);
+
+	if (keylen == 0 || keylen > BLAKE2B_KEYBYTES) {
+		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(tctx->key, key, keylen);
+	tctx->keylen = keylen;
+
+	return 0;
+}
+
+static int blake2b_init(struct shash_desc *desc)
+{
+	struct blake2b_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	struct blake2b_state *state = shash_desc_ctx(desc);
+	const int digestsize = crypto_shash_digestsize(desc->tfm);
+
+	memset(state, 0, sizeof(*state));
+	memcpy(state->h, blake2b_IV, sizeof(state->h));
+
+	/* Parameter block is all zeros except index 0, no xor for 1..7 */
+	state->h[0] ^= 0x01010000 | tctx->keylen << 8 | digestsize;
+
+	if (tctx->keylen) {
+		/*
+		 * Prefill the buffer with the key, next call to _update or
+		 * _final will process it
+		 */
+		memcpy(state->buf, tctx->key, tctx->keylen);
+		state->buflen = BLAKE2B_BLOCKBYTES;
+	}
+	return 0;
+}
+
+static int blake2b_update(struct shash_desc *desc, const u8 *in,
+			  unsigned int inlen)
+{
+	struct blake2b_state *state = shash_desc_ctx(desc);
+	const size_t left = state->buflen;
+	const size_t fill = BLAKE2B_BLOCKBYTES - left;
+
+	if (!inlen)
+		return 0;
+
+	if (inlen > fill) {
+		state->buflen = 0;
+		/* Fill buffer */
+		memcpy(state->buf + left, in, fill);
+		blake2b_increment_counter(state, BLAKE2B_BLOCKBYTES);
+		/* Compress */
+		blake2b_compress(state, state->buf);
+		in += fill;
+		inlen -= fill;
+		while (inlen > BLAKE2B_BLOCKBYTES) {
+			blake2b_increment_counter(state, BLAKE2B_BLOCKBYTES);
+			blake2b_compress(state, in);
+			in += BLAKE2B_BLOCKBYTES;
+			inlen -= BLAKE2B_BLOCKBYTES;
+		}
+	}
+	memcpy(state->buf + state->buflen, in, inlen);
+	state->buflen += inlen;
+
+	return 0;
+}
+
+static int blake2b_final(struct shash_desc *desc, u8 *out)
+{
+	struct blake2b_state *state = shash_desc_ctx(desc);
+	const int digestsize = crypto_shash_digestsize(desc->tfm);
+	size_t i;
+
+	blake2b_increment_counter(state, state->buflen);
+	/* Set last block */
+	state->f[0] = (u64)-1;
+	/* Padding */
+	memset(state->buf + state->buflen, 0, BLAKE2B_BLOCKBYTES - state->buflen);
+	blake2b_compress(state, state->buf);
+
+	/* Avoid temporary buffer and switch the internal output to LE order */
+	for (i = 0; i < ARRAY_SIZE(state->h); i++)
+		__cpu_to_le64s(&state->h[i]);
+
+	memcpy(out, state->h, digestsize);
+	return 0;
+}
+
+static struct shash_alg blake2b_algs[] = {
+	{
+		.base.cra_name		= "blake2b-160",
+		.base.cra_driver_name	= "blake2b-160-generic",
+		.base.cra_priority	= 100,
+		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+		.base.cra_blocksize	= BLAKE2B_BLOCKBYTES,
+		.base.cra_ctxsize	= sizeof(struct blake2b_tfm_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.digestsize		= BLAKE2B_160_DIGEST_SIZE,
+		.setkey			= blake2b_setkey,
+		.init			= blake2b_init,
+		.update			= blake2b_update,
+		.final			= blake2b_final,
+		.descsize		= sizeof(struct blake2b_state),
+	}, {
+		.base.cra_name		= "blake2b-256",
+		.base.cra_driver_name	= "blake2b-256-generic",
+		.base.cra_priority	= 100,
+		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+		.base.cra_blocksize	= BLAKE2B_BLOCKBYTES,
+		.base.cra_ctxsize	= sizeof(struct blake2b_tfm_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.digestsize		= BLAKE2B_256_DIGEST_SIZE,
+		.setkey			= blake2b_setkey,
+		.init			= blake2b_init,
+		.update			= blake2b_update,
+		.final			= blake2b_final,
+		.descsize		= sizeof(struct blake2b_state),
+	}, {
+		.base.cra_name		= "blake2b-384",
+		.base.cra_driver_name	= "blake2b-384-generic",
+		.base.cra_priority	= 100,
+		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+		.base.cra_blocksize	= BLAKE2B_BLOCKBYTES,
+		.base.cra_ctxsize	= sizeof(struct blake2b_tfm_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.digestsize		= BLAKE2B_384_DIGEST_SIZE,
+		.setkey			= blake2b_setkey,
+		.init			= blake2b_init,
+		.update			= blake2b_update,
+		.final			= blake2b_final,
+		.descsize		= sizeof(struct blake2b_state),
+	}, {
+		.base.cra_name		= "blake2b-512",
+		.base.cra_driver_name	= "blake2b-512-generic",
+		.base.cra_priority	= 100,
+		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+		.base.cra_blocksize	= BLAKE2B_BLOCKBYTES,
+		.base.cra_ctxsize	= sizeof(struct blake2b_tfm_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.digestsize		= BLAKE2B_512_DIGEST_SIZE,
+		.setkey			= blake2b_setkey,
+		.init			= blake2b_init,
+		.update			= blake2b_update,
+		.final			= blake2b_final,
+		.descsize		= sizeof(struct blake2b_state),
+	}
+};
+
+static int __init blake2b_mod_init(void)
+{
+	return crypto_register_shashes(blake2b_algs, ARRAY_SIZE(blake2b_algs));
+}
+
+static void __exit blake2b_mod_fini(void)
+{
+	crypto_unregister_shashes(blake2b_algs, ARRAY_SIZE(blake2b_algs));
+}
+
+subsys_initcall(blake2b_mod_init);
+module_exit(blake2b_mod_fini);
+
+MODULE_AUTHOR("David Sterba <kdave@kernel.org>");
+MODULE_DESCRIPTION("BLAKE2b generic implementation");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("blake2b-160");
+MODULE_ALIAS_CRYPTO("blake2b-160-generic");
+MODULE_ALIAS_CRYPTO("blake2b-256");
+MODULE_ALIAS_CRYPTO("blake2b-256-generic");
+MODULE_ALIAS_CRYPTO("blake2b-384");
+MODULE_ALIAS_CRYPTO("blake2b-384-generic");
+MODULE_ALIAS_CRYPTO("blake2b-512");
+MODULE_ALIAS_CRYPTO("blake2b-512-generic");
diff --git a/crypto/blake2s_generic.c b/crypto/blake2s_generic.c
new file mode 100644
index 000000000000..ed0c74640470
--- /dev/null
+++ b/crypto/blake2s_generic.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <crypto/internal/blake2s.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/hash.h>
+
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+static int crypto_blake2s_setkey(struct crypto_shash *tfm, const u8 *key,
+				 unsigned int keylen)
+{
+	struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(tfm);
+
+	if (keylen == 0 || keylen > BLAKE2S_KEY_SIZE) {
+		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(tctx->key, key, keylen);
+	tctx->keylen = keylen;
+
+	return 0;
+}
+
+static int crypto_blake2s_init(struct shash_desc *desc)
+{
+	struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	struct blake2s_state *state = shash_desc_ctx(desc);
+	const int outlen = crypto_shash_digestsize(desc->tfm);
+
+	if (tctx->keylen)
+		blake2s_init_key(state, outlen, tctx->key, tctx->keylen);
+	else
+		blake2s_init(state, outlen);
+
+	return 0;
+}
+
+static int crypto_blake2s_update(struct shash_desc *desc, const u8 *in,
+				 unsigned int inlen)
+{
+	struct blake2s_state *state = shash_desc_ctx(desc);
+	const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen;
+
+	if (unlikely(!inlen))
+		return 0;
+	if (inlen > fill) {
+		memcpy(state->buf + state->buflen, in, fill);
+		blake2s_compress_generic(state, state->buf, 1, BLAKE2S_BLOCK_SIZE);
+		state->buflen = 0;
+		in += fill;
+		inlen -= fill;
+	}
+	if (inlen > BLAKE2S_BLOCK_SIZE) {
+		const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE);
+		/* Hash one less (full) block than strictly possible */
+		blake2s_compress_generic(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE);
+		in += BLAKE2S_BLOCK_SIZE * (nblocks - 1);
+		inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1);
+	}
+	memcpy(state->buf + state->buflen, in, inlen);
+	state->buflen += inlen;
+
+	return 0;
+}
+
+static int crypto_blake2s_final(struct shash_desc *desc, u8 *out)
+{
+	struct blake2s_state *state = shash_desc_ctx(desc);
+
+	blake2s_set_lastblock(state);
+	memset(state->buf + state->buflen, 0,
+	       BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */
+	blake2s_compress_generic(state, state->buf, 1, state->buflen);
+	cpu_to_le32_array(state->h, ARRAY_SIZE(state->h));
+	memcpy(out, state->h, state->outlen);
+	memzero_explicit(state, sizeof(*state));
+
+	return 0;
+}
+
+static struct shash_alg blake2s_algs[] = {{
+	.base.cra_name		= "blake2s-128",
+	.base.cra_driver_name	= "blake2s-128-generic",
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
+	.base.cra_priority	= 200,
+	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= BLAKE2S_128_HASH_SIZE,
+	.setkey			= crypto_blake2s_setkey,
+	.init			= crypto_blake2s_init,
+	.update			= crypto_blake2s_update,
+	.final			= crypto_blake2s_final,
+	.descsize		= sizeof(struct blake2s_state),
+}, {
+	.base.cra_name		= "blake2s-160",
+	.base.cra_driver_name	= "blake2s-160-generic",
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
+	.base.cra_priority	= 200,
+	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= BLAKE2S_160_HASH_SIZE,
+	.setkey			= crypto_blake2s_setkey,
+	.init			= crypto_blake2s_init,
+	.update			= crypto_blake2s_update,
+	.final			= crypto_blake2s_final,
+	.descsize		= sizeof(struct blake2s_state),
+}, {
+	.base.cra_name		= "blake2s-224",
+	.base.cra_driver_name	= "blake2s-224-generic",
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
+	.base.cra_priority	= 200,
+	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= BLAKE2S_224_HASH_SIZE,
+	.setkey			= crypto_blake2s_setkey,
+	.init			= crypto_blake2s_init,
+	.update			= crypto_blake2s_update,
+	.final			= crypto_blake2s_final,
+	.descsize		= sizeof(struct blake2s_state),
+}, {
+	.base.cra_name		= "blake2s-256",
+	.base.cra_driver_name	= "blake2s-256-generic",
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
+	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
+	.base.cra_priority	= 200,
+	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= BLAKE2S_256_HASH_SIZE,
+	.setkey			= crypto_blake2s_setkey,
+	.init			= crypto_blake2s_init,
+	.update			= crypto_blake2s_update,
+	.final			= crypto_blake2s_final,
+	.descsize		= sizeof(struct blake2s_state),
+}};
+
+static int __init blake2s_mod_init(void)
+{
+	return crypto_register_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs));
+}
+
+static void __exit blake2s_mod_exit(void)
+{
+	crypto_unregister_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs));
+}
+
+subsys_initcall(blake2s_mod_init);
+module_exit(blake2s_mod_exit);
+
+MODULE_ALIAS_CRYPTO("blake2s-128");
+MODULE_ALIAS_CRYPTO("blake2s-128-generic");
+MODULE_ALIAS_CRYPTO("blake2s-160");
+MODULE_ALIAS_CRYPTO("blake2s-160-generic");
+MODULE_ALIAS_CRYPTO("blake2s-224");
+MODULE_ALIAS_CRYPTO("blake2s-224-generic");
+MODULE_ALIAS_CRYPTO("blake2s-256");
+MODULE_ALIAS_CRYPTO("blake2s-256-generic");
+MODULE_LICENSE("GPL v2");
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
deleted file mode 100644
index 48a33817de11..000000000000
--- a/crypto/blkcipher.c
+++ /dev/null
@@ -1,548 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Block chaining cipher operations.
- *
- * Generic encrypt/decrypt wrapper for ciphers, handles operations across
- * multiple page boundaries by using temporary blocks.  In user context,
- * the kernel is given a chance to schedule us once per page.
- *
- * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
- */
-
-#include <crypto/aead.h>
-#include <crypto/internal/skcipher.h>
-#include <crypto/scatterwalk.h>
-#include <linux/errno.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/seq_file.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/cryptouser.h>
-#include <linux/compiler.h>
-#include <net/netlink.h>
-
-#include "internal.h"
-
-enum {
-	BLKCIPHER_WALK_PHYS = 1 << 0,
-	BLKCIPHER_WALK_SLOW = 1 << 1,
-	BLKCIPHER_WALK_COPY = 1 << 2,
-	BLKCIPHER_WALK_DIFF = 1 << 3,
-};
-
-static int blkcipher_walk_next(struct blkcipher_desc *desc,
-			       struct blkcipher_walk *walk);
-static int blkcipher_walk_first(struct blkcipher_desc *desc,
-				struct blkcipher_walk *walk);
-
-static inline void blkcipher_map_src(struct blkcipher_walk *walk)
-{
-	walk->src.virt.addr = scatterwalk_map(&walk->in);
-}
-
-static inline void blkcipher_map_dst(struct blkcipher_walk *walk)
-{
-	walk->dst.virt.addr = scatterwalk_map(&walk->out);
-}
-
-static inline void blkcipher_unmap_src(struct blkcipher_walk *walk)
-{
-	scatterwalk_unmap(walk->src.virt.addr);
-}
-
-static inline void blkcipher_unmap_dst(struct blkcipher_walk *walk)
-{
-	scatterwalk_unmap(walk->dst.virt.addr);
-}
-
-/* Get a spot of the specified length that does not straddle a page.
- * The caller needs to ensure that there is enough space for this operation.
- */
-static inline u8 *blkcipher_get_spot(u8 *start, unsigned int len)
-{
-	u8 *end_page = (u8 *)(((unsigned long)(start + len - 1)) & PAGE_MASK);
-	return max(start, end_page);
-}
-
-static inline void blkcipher_done_slow(struct blkcipher_walk *walk,
-				       unsigned int bsize)
-{
-	u8 *addr;
-
-	addr = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
-	addr = blkcipher_get_spot(addr, bsize);
-	scatterwalk_copychunks(addr, &walk->out, bsize, 1);
-}
-
-static inline void blkcipher_done_fast(struct blkcipher_walk *walk,
-				       unsigned int n)
-{
-	if (walk->flags & BLKCIPHER_WALK_COPY) {
-		blkcipher_map_dst(walk);
-		memcpy(walk->dst.virt.addr, walk->page, n);
-		blkcipher_unmap_dst(walk);
-	} else if (!(walk->flags & BLKCIPHER_WALK_PHYS)) {
-		if (walk->flags & BLKCIPHER_WALK_DIFF)
-			blkcipher_unmap_dst(walk);
-		blkcipher_unmap_src(walk);
-	}
-
-	scatterwalk_advance(&walk->in, n);
-	scatterwalk_advance(&walk->out, n);
-}
-
-int blkcipher_walk_done(struct blkcipher_desc *desc,
-			struct blkcipher_walk *walk, int err)
-{
-	unsigned int n; /* bytes processed */
-	bool more;
-
-	if (unlikely(err < 0))
-		goto finish;
-
-	n = walk->nbytes - err;
-	walk->total -= n;
-	more = (walk->total != 0);
-
-	if (likely(!(walk->flags & BLKCIPHER_WALK_SLOW))) {
-		blkcipher_done_fast(walk, n);
-	} else {
-		if (WARN_ON(err)) {
-			/* unexpected case; didn't process all bytes */
-			err = -EINVAL;
-			goto finish;
-		}
-		blkcipher_done_slow(walk, n);
-	}
-
-	scatterwalk_done(&walk->in, 0, more);
-	scatterwalk_done(&walk->out, 1, more);
-
-	if (more) {
-		crypto_yield(desc->flags);
-		return blkcipher_walk_next(desc, walk);
-	}
-	err = 0;
-finish:
-	walk->nbytes = 0;
-	if (walk->iv != desc->info)
-		memcpy(desc->info, walk->iv, walk->ivsize);
-	if (walk->buffer != walk->page)
-		kfree(walk->buffer);
-	if (walk->page)
-		free_page((unsigned long)walk->page);
-	return err;
-}
-EXPORT_SYMBOL_GPL(blkcipher_walk_done);
-
-static inline int blkcipher_next_slow(struct blkcipher_desc *desc,
-				      struct blkcipher_walk *walk,
-				      unsigned int bsize,
-				      unsigned int alignmask)
-{
-	unsigned int n;
-	unsigned aligned_bsize = ALIGN(bsize, alignmask + 1);
-
-	if (walk->buffer)
-		goto ok;
-
-	walk->buffer = walk->page;
-	if (walk->buffer)
-		goto ok;
-
-	n = aligned_bsize * 3 - (alignmask + 1) +
-	    (alignmask & ~(crypto_tfm_ctx_alignment() - 1));
-	walk->buffer = kmalloc(n, GFP_ATOMIC);
-	if (!walk->buffer)
-		return blkcipher_walk_done(desc, walk, -ENOMEM);
-
-ok:
-	walk->dst.virt.addr = (u8 *)ALIGN((unsigned long)walk->buffer,
-					  alignmask + 1);
-	walk->dst.virt.addr = blkcipher_get_spot(walk->dst.virt.addr, bsize);
-	walk->src.virt.addr = blkcipher_get_spot(walk->dst.virt.addr +
-						 aligned_bsize, bsize);
-
-	scatterwalk_copychunks(walk->src.virt.addr, &walk->in, bsize, 0);
-
-	walk->nbytes = bsize;
-	walk->flags |= BLKCIPHER_WALK_SLOW;
-
-	return 0;
-}
-
-static inline int blkcipher_next_copy(struct blkcipher_walk *walk)
-{
-	u8 *tmp = walk->page;
-
-	blkcipher_map_src(walk);
-	memcpy(tmp, walk->src.virt.addr, walk->nbytes);
-	blkcipher_unmap_src(walk);
-
-	walk->src.virt.addr = tmp;
-	walk->dst.virt.addr = tmp;
-
-	return 0;
-}
-
-static inline int blkcipher_next_fast(struct blkcipher_desc *desc,
-				      struct blkcipher_walk *walk)
-{
-	unsigned long diff;
-
-	walk->src.phys.page = scatterwalk_page(&walk->in);
-	walk->src.phys.offset = offset_in_page(walk->in.offset);
-	walk->dst.phys.page = scatterwalk_page(&walk->out);
-	walk->dst.phys.offset = offset_in_page(walk->out.offset);
-
-	if (walk->flags & BLKCIPHER_WALK_PHYS)
-		return 0;
-
-	diff = walk->src.phys.offset - walk->dst.phys.offset;
-	diff |= walk->src.virt.page - walk->dst.virt.page;
-
-	blkcipher_map_src(walk);
-	walk->dst.virt.addr = walk->src.virt.addr;
-
-	if (diff) {
-		walk->flags |= BLKCIPHER_WALK_DIFF;
-		blkcipher_map_dst(walk);
-	}
-
-	return 0;
-}
-
-static int blkcipher_walk_next(struct blkcipher_desc *desc,
-			       struct blkcipher_walk *walk)
-{
-	unsigned int bsize;
-	unsigned int n;
-	int err;
-
-	n = walk->total;
-	if (unlikely(n < walk->cipher_blocksize)) {
-		desc->flags |= CRYPTO_TFM_RES_BAD_BLOCK_LEN;
-		return blkcipher_walk_done(desc, walk, -EINVAL);
-	}
-
-	bsize = min(walk->walk_blocksize, n);
-
-	walk->flags &= ~(BLKCIPHER_WALK_SLOW | BLKCIPHER_WALK_COPY |
-			 BLKCIPHER_WALK_DIFF);
-	if (!scatterwalk_aligned(&walk->in, walk->alignmask) ||
-	    !scatterwalk_aligned(&walk->out, walk->alignmask)) {
-		walk->flags |= BLKCIPHER_WALK_COPY;
-		if (!walk->page) {
-			walk->page = (void *)__get_free_page(GFP_ATOMIC);
-			if (!walk->page)
-				n = 0;
-		}
-	}
-
-	n = scatterwalk_clamp(&walk->in, n);
-	n = scatterwalk_clamp(&walk->out, n);
-
-	if (unlikely(n < bsize)) {
-		err = blkcipher_next_slow(desc, walk, bsize, walk->alignmask);
-		goto set_phys_lowmem;
-	}
-
-	walk->nbytes = n;
-	if (walk->flags & BLKCIPHER_WALK_COPY) {
-		err = blkcipher_next_copy(walk);
-		goto set_phys_lowmem;
-	}
-
-	return blkcipher_next_fast(desc, walk);
-
-set_phys_lowmem:
-	if (walk->flags & BLKCIPHER_WALK_PHYS) {
-		walk->src.phys.page = virt_to_page(walk->src.virt.addr);
-		walk->dst.phys.page = virt_to_page(walk->dst.virt.addr);
-		walk->src.phys.offset &= PAGE_SIZE - 1;
-		walk->dst.phys.offset &= PAGE_SIZE - 1;
-	}
-	return err;
-}
-
-static inline int blkcipher_copy_iv(struct blkcipher_walk *walk)
-{
-	unsigned bs = walk->walk_blocksize;
-	unsigned aligned_bs = ALIGN(bs, walk->alignmask + 1);
-	unsigned int size = aligned_bs * 2 +
-			    walk->ivsize + max(aligned_bs, walk->ivsize) -
-			    (walk->alignmask + 1);
-	u8 *iv;
-
-	size += walk->alignmask & ~(crypto_tfm_ctx_alignment() - 1);
-	walk->buffer = kmalloc(size, GFP_ATOMIC);
-	if (!walk->buffer)
-		return -ENOMEM;
-
-	iv = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
-	iv = blkcipher_get_spot(iv, bs) + aligned_bs;
-	iv = blkcipher_get_spot(iv, bs) + aligned_bs;
-	iv = blkcipher_get_spot(iv, walk->ivsize);
-
-	walk->iv = memcpy(iv, walk->iv, walk->ivsize);
-	return 0;
-}
-
-int blkcipher_walk_virt(struct blkcipher_desc *desc,
-			struct blkcipher_walk *walk)
-{
-	walk->flags &= ~BLKCIPHER_WALK_PHYS;
-	walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
-	walk->cipher_blocksize = walk->walk_blocksize;
-	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
-	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
-	return blkcipher_walk_first(desc, walk);
-}
-EXPORT_SYMBOL_GPL(blkcipher_walk_virt);
-
-int blkcipher_walk_phys(struct blkcipher_desc *desc,
-			struct blkcipher_walk *walk)
-{
-	walk->flags |= BLKCIPHER_WALK_PHYS;
-	walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
-	walk->cipher_blocksize = walk->walk_blocksize;
-	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
-	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
-	return blkcipher_walk_first(desc, walk);
-}
-EXPORT_SYMBOL_GPL(blkcipher_walk_phys);
-
-static int blkcipher_walk_first(struct blkcipher_desc *desc,
-				struct blkcipher_walk *walk)
-{
-	if (WARN_ON_ONCE(in_irq()))
-		return -EDEADLK;
-
-	walk->iv = desc->info;
-	walk->nbytes = walk->total;
-	if (unlikely(!walk->total))
-		return 0;
-
-	walk->buffer = NULL;
-	if (unlikely(((unsigned long)walk->iv & walk->alignmask))) {
-		int err = blkcipher_copy_iv(walk);
-		if (err)
-			return err;
-	}
-
-	scatterwalk_start(&walk->in, walk->in.sg);
-	scatterwalk_start(&walk->out, walk->out.sg);
-	walk->page = NULL;
-
-	return blkcipher_walk_next(desc, walk);
-}
-
-int blkcipher_walk_virt_block(struct blkcipher_desc *desc,
-			      struct blkcipher_walk *walk,
-			      unsigned int blocksize)
-{
-	walk->flags &= ~BLKCIPHER_WALK_PHYS;
-	walk->walk_blocksize = blocksize;
-	walk->cipher_blocksize = crypto_blkcipher_blocksize(desc->tfm);
-	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
-	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
-	return blkcipher_walk_first(desc, walk);
-}
-EXPORT_SYMBOL_GPL(blkcipher_walk_virt_block);
-
-int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc,
-				   struct blkcipher_walk *walk,
-				   struct crypto_aead *tfm,
-				   unsigned int blocksize)
-{
-	walk->flags &= ~BLKCIPHER_WALK_PHYS;
-	walk->walk_blocksize = blocksize;
-	walk->cipher_blocksize = crypto_aead_blocksize(tfm);
-	walk->ivsize = crypto_aead_ivsize(tfm);
-	walk->alignmask = crypto_aead_alignmask(tfm);
-	return blkcipher_walk_first(desc, walk);
-}
-EXPORT_SYMBOL_GPL(blkcipher_aead_walk_virt_block);
-
-static int setkey_unaligned(struct crypto_tfm *tfm, const u8 *key,
-			    unsigned int keylen)
-{
-	struct blkcipher_alg *cipher = &tfm->__crt_alg->cra_blkcipher;
-	unsigned long alignmask = crypto_tfm_alg_alignmask(tfm);
-	int ret;
-	u8 *buffer, *alignbuffer;
-	unsigned long absize;
-
-	absize = keylen + alignmask;
-	buffer = kmalloc(absize, GFP_ATOMIC);
-	if (!buffer)
-		return -ENOMEM;
-
-	alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1);
-	memcpy(alignbuffer, key, keylen);
-	ret = cipher->setkey(tfm, alignbuffer, keylen);
-	memset(alignbuffer, 0, keylen);
-	kfree(buffer);
-	return ret;
-}
-
-static int setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen)
-{
-	struct blkcipher_alg *cipher = &tfm->__crt_alg->cra_blkcipher;
-	unsigned long alignmask = crypto_tfm_alg_alignmask(tfm);
-
-	if (keylen < cipher->min_keysize || keylen > cipher->max_keysize) {
-		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
-
-	if ((unsigned long)key & alignmask)
-		return setkey_unaligned(tfm, key, keylen);
-
-	return cipher->setkey(tfm, key, keylen);
-}
-
-static int async_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
-			unsigned int keylen)
-{
-	return setkey(crypto_ablkcipher_tfm(tfm), key, keylen);
-}
-
-static int async_encrypt(struct ablkcipher_request *req)
-{
-	struct crypto_tfm *tfm = req->base.tfm;
-	struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher;
-	struct blkcipher_desc desc = {
-		.tfm = __crypto_blkcipher_cast(tfm),
-		.info = req->info,
-		.flags = req->base.flags,
-	};
-
-
-	return alg->encrypt(&desc, req->dst, req->src, req->nbytes);
-}
-
-static int async_decrypt(struct ablkcipher_request *req)
-{
-	struct crypto_tfm *tfm = req->base.tfm;
-	struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher;
-	struct blkcipher_desc desc = {
-		.tfm = __crypto_blkcipher_cast(tfm),
-		.info = req->info,
-		.flags = req->base.flags,
-	};
-
-	return alg->decrypt(&desc, req->dst, req->src, req->nbytes);
-}
-
-static unsigned int crypto_blkcipher_ctxsize(struct crypto_alg *alg, u32 type,
-					     u32 mask)
-{
-	struct blkcipher_alg *cipher = &alg->cra_blkcipher;
-	unsigned int len = alg->cra_ctxsize;
-
-	if ((mask & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_MASK &&
-	    cipher->ivsize) {
-		len = ALIGN(len, (unsigned long)alg->cra_alignmask + 1);
-		len += cipher->ivsize;
-	}
-
-	return len;
-}
-
-static int crypto_init_blkcipher_ops_async(struct crypto_tfm *tfm)
-{
-	struct ablkcipher_tfm *crt = &tfm->crt_ablkcipher;
-	struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher;
-
-	crt->setkey = async_setkey;
-	crt->encrypt = async_encrypt;
-	crt->decrypt = async_decrypt;
-	crt->base = __crypto_ablkcipher_cast(tfm);
-	crt->ivsize = alg->ivsize;
-
-	return 0;
-}
-
-static int crypto_init_blkcipher_ops_sync(struct crypto_tfm *tfm)
-{
-	struct blkcipher_tfm *crt = &tfm->crt_blkcipher;
-	struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher;
-	unsigned long align = crypto_tfm_alg_alignmask(tfm) + 1;
-	unsigned long addr;
-
-	crt->setkey = setkey;
-	crt->encrypt = alg->encrypt;
-	crt->decrypt = alg->decrypt;
-
-	addr = (unsigned long)crypto_tfm_ctx(tfm);
-	addr = ALIGN(addr, align);
-	addr += ALIGN(tfm->__crt_alg->cra_ctxsize, align);
-	crt->iv = (void *)addr;
-
-	return 0;
-}
-
-static int crypto_init_blkcipher_ops(struct crypto_tfm *tfm, u32 type, u32 mask)
-{
-	struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher;
-
-	if (alg->ivsize > PAGE_SIZE / 8)
-		return -EINVAL;
-
-	if ((mask & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_MASK)
-		return crypto_init_blkcipher_ops_sync(tfm);
-	else
-		return crypto_init_blkcipher_ops_async(tfm);
-}
-
-#ifdef CONFIG_NET
-static int crypto_blkcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	struct crypto_report_blkcipher rblkcipher;
-
-	memset(&rblkcipher, 0, sizeof(rblkcipher));
-
-	strscpy(rblkcipher.type, "blkcipher", sizeof(rblkcipher.type));
-	strscpy(rblkcipher.geniv, "<default>", sizeof(rblkcipher.geniv));
-
-	rblkcipher.blocksize = alg->cra_blocksize;
-	rblkcipher.min_keysize = alg->cra_blkcipher.min_keysize;
-	rblkcipher.max_keysize = alg->cra_blkcipher.max_keysize;
-	rblkcipher.ivsize = alg->cra_blkcipher.ivsize;
-
-	return nla_put(skb, CRYPTOCFGA_REPORT_BLKCIPHER,
-		       sizeof(rblkcipher), &rblkcipher);
-}
-#else
-static int crypto_blkcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	return -ENOSYS;
-}
-#endif
-
-static void crypto_blkcipher_show(struct seq_file *m, struct crypto_alg *alg)
-	__maybe_unused;
-static void crypto_blkcipher_show(struct seq_file *m, struct crypto_alg *alg)
-{
-	seq_printf(m, "type         : blkcipher\n");
-	seq_printf(m, "blocksize    : %u\n", alg->cra_blocksize);
-	seq_printf(m, "min keysize  : %u\n", alg->cra_blkcipher.min_keysize);
-	seq_printf(m, "max keysize  : %u\n", alg->cra_blkcipher.max_keysize);
-	seq_printf(m, "ivsize       : %u\n", alg->cra_blkcipher.ivsize);
-	seq_printf(m, "geniv        : <default>\n");
-}
-
-const struct crypto_type crypto_blkcipher_type = {
-	.ctxsize = crypto_blkcipher_ctxsize,
-	.init = crypto_init_blkcipher_ops,
-#ifdef CONFIG_PROC_FS
-	.show = crypto_blkcipher_show,
-#endif
-	.report = crypto_blkcipher_report,
-};
-EXPORT_SYMBOL_GPL(crypto_blkcipher_type);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Generic block chaining cipher type");
diff --git a/crypto/chacha_generic.c b/crypto/chacha_generic.c
index 085d8d219987..8beea79ab117 100644
--- a/crypto/chacha_generic.c
+++ b/crypto/chacha_generic.c
@@ -8,29 +8,10 @@
 
 #include <asm/unaligned.h>
 #include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/module.h>
 
-static void chacha_docrypt(u32 *state, u8 *dst, const u8 *src,
-			   unsigned int bytes, int nrounds)
-{
-	/* aligned to potentially speed up crypto_xor() */
-	u8 stream[CHACHA_BLOCK_SIZE] __aligned(sizeof(long));
-
-	while (bytes >= CHACHA_BLOCK_SIZE) {
-		chacha_block(state, stream, nrounds);
-		crypto_xor_cpy(dst, src, stream, CHACHA_BLOCK_SIZE);
-		bytes -= CHACHA_BLOCK_SIZE;
-		dst += CHACHA_BLOCK_SIZE;
-		src += CHACHA_BLOCK_SIZE;
-	}
-	if (bytes) {
-		chacha_block(state, stream, nrounds);
-		crypto_xor_cpy(dst, src, stream, bytes);
-	}
-}
-
 static int chacha_stream_xor(struct skcipher_request *req,
 			     const struct chacha_ctx *ctx, const u8 *iv)
 {
@@ -40,7 +21,7 @@ static int chacha_stream_xor(struct skcipher_request *req,
 
 	err = skcipher_walk_virt(&walk, req, false);
 
-	crypto_chacha_init(state, ctx, iv);
+	chacha_init_generic(state, ctx->key, iv);
 
 	while (walk.nbytes > 0) {
 		unsigned int nbytes = walk.nbytes;
@@ -48,75 +29,23 @@ static int chacha_stream_xor(struct skcipher_request *req,
 		if (nbytes < walk.total)
 			nbytes = round_down(nbytes, CHACHA_BLOCK_SIZE);
 
-		chacha_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
-			       nbytes, ctx->nrounds);
+		chacha_crypt_generic(state, walk.dst.virt.addr,
+				     walk.src.virt.addr, nbytes, ctx->nrounds);
 		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
 	return err;
 }
 
-void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv)
-{
-	state[0]  = 0x61707865; /* "expa" */
-	state[1]  = 0x3320646e; /* "nd 3" */
-	state[2]  = 0x79622d32; /* "2-by" */
-	state[3]  = 0x6b206574; /* "te k" */
-	state[4]  = ctx->key[0];
-	state[5]  = ctx->key[1];
-	state[6]  = ctx->key[2];
-	state[7]  = ctx->key[3];
-	state[8]  = ctx->key[4];
-	state[9]  = ctx->key[5];
-	state[10] = ctx->key[6];
-	state[11] = ctx->key[7];
-	state[12] = get_unaligned_le32(iv +  0);
-	state[13] = get_unaligned_le32(iv +  4);
-	state[14] = get_unaligned_le32(iv +  8);
-	state[15] = get_unaligned_le32(iv + 12);
-}
-EXPORT_SYMBOL_GPL(crypto_chacha_init);
-
-static int chacha_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			 unsigned int keysize, int nrounds)
-{
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int i;
-
-	if (keysize != CHACHA_KEY_SIZE)
-		return -EINVAL;
-
-	for (i = 0; i < ARRAY_SIZE(ctx->key); i++)
-		ctx->key[i] = get_unaligned_le32(key + i * sizeof(u32));
-
-	ctx->nrounds = nrounds;
-	return 0;
-}
-
-int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			   unsigned int keysize)
-{
-	return chacha_setkey(tfm, key, keysize, 20);
-}
-EXPORT_SYMBOL_GPL(crypto_chacha20_setkey);
-
-int crypto_chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			   unsigned int keysize)
-{
-	return chacha_setkey(tfm, key, keysize, 12);
-}
-EXPORT_SYMBOL_GPL(crypto_chacha12_setkey);
-
-int crypto_chacha_crypt(struct skcipher_request *req)
+static int crypto_chacha_crypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	return chacha_stream_xor(req, ctx, req->iv);
 }
-EXPORT_SYMBOL_GPL(crypto_chacha_crypt);
 
-int crypto_xchacha_crypt(struct skcipher_request *req)
+static int crypto_xchacha_crypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
@@ -125,8 +54,8 @@ int crypto_xchacha_crypt(struct skcipher_request *req)
 	u8 real_iv[16];
 
 	/* Compute the subkey given the original key and first 128 nonce bits */
-	crypto_chacha_init(state, ctx, req->iv);
-	hchacha_block(state, subctx.key, ctx->nrounds);
+	chacha_init_generic(state, ctx->key, req->iv);
+	hchacha_block_generic(state, subctx.key, ctx->nrounds);
 	subctx.nrounds = ctx->nrounds;
 
 	/* Build the real IV */
@@ -136,7 +65,6 @@ int crypto_xchacha_crypt(struct skcipher_request *req)
 	/* Generate the stream and XOR it with the data */
 	return chacha_stream_xor(req, &subctx, real_iv);
 }
-EXPORT_SYMBOL_GPL(crypto_xchacha_crypt);
 
 static struct skcipher_alg algs[] = {
 	{
@@ -151,7 +79,7 @@ static struct skcipher_alg algs[] = {
 		.max_keysize		= CHACHA_KEY_SIZE,
 		.ivsize			= CHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
+		.setkey			= chacha20_setkey,
 		.encrypt		= crypto_chacha_crypt,
 		.decrypt		= crypto_chacha_crypt,
 	}, {
@@ -166,7 +94,7 @@ static struct skcipher_alg algs[] = {
 		.max_keysize		= CHACHA_KEY_SIZE,
 		.ivsize			= XCHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
+		.setkey			= chacha20_setkey,
 		.encrypt		= crypto_xchacha_crypt,
 		.decrypt		= crypto_xchacha_crypt,
 	}, {
@@ -181,7 +109,7 @@ static struct skcipher_alg algs[] = {
 		.max_keysize		= CHACHA_KEY_SIZE,
 		.ivsize			= XCHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha12_setkey,
+		.setkey			= chacha12_setkey,
 		.encrypt		= crypto_xchacha_crypt,
 		.decrypt		= crypto_xchacha_crypt,
 	}
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index 927760b316a4..2c6649b10923 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -919,7 +919,7 @@ static int cryptd_create(struct crypto_template *tmpl, struct rtattr **tb)
 		return PTR_ERR(algt);
 
 	switch (algt->type & algt->mask & CRYPTO_ALG_TYPE_MASK) {
-	case CRYPTO_ALG_TYPE_BLKCIPHER:
+	case CRYPTO_ALG_TYPE_SKCIPHER:
 		return cryptd_create_skcipher(tmpl, tb, &queue);
 	case CRYPTO_ALG_TYPE_HASH:
 		return cryptd_create_hash(tmpl, tb, &queue);
diff --git a/crypto/crypto_engine.c b/crypto/crypto_engine.c
index 055d17977280..eb029ff1e05a 100644
--- a/crypto/crypto_engine.c
+++ b/crypto/crypto_engine.c
@@ -214,20 +214,6 @@ static int crypto_transfer_request_to_engine(struct crypto_engine *engine,
 }
 
 /**
- * crypto_transfer_ablkcipher_request_to_engine - transfer one ablkcipher_request
- * to list into the engine queue
- * @engine: the hardware engine
- * @req: the request need to be listed into the engine queue
- * TODO: Remove this function when skcipher conversion is finished
- */
-int crypto_transfer_ablkcipher_request_to_engine(struct crypto_engine *engine,
-						 struct ablkcipher_request *req)
-{
-	return crypto_transfer_request_to_engine(engine, &req->base);
-}
-EXPORT_SYMBOL_GPL(crypto_transfer_ablkcipher_request_to_engine);
-
-/**
  * crypto_transfer_aead_request_to_engine - transfer one aead_request
  * to list into the engine queue
  * @engine: the hardware engine
@@ -280,21 +266,6 @@ int crypto_transfer_skcipher_request_to_engine(struct crypto_engine *engine,
 EXPORT_SYMBOL_GPL(crypto_transfer_skcipher_request_to_engine);
 
 /**
- * crypto_finalize_ablkcipher_request - finalize one ablkcipher_request if
- * the request is done
- * @engine: the hardware engine
- * @req: the request need to be finalized
- * @err: error number
- * TODO: Remove this function when skcipher conversion is finished
- */
-void crypto_finalize_ablkcipher_request(struct crypto_engine *engine,
-					struct ablkcipher_request *req, int err)
-{
-	return crypto_finalize_request(engine, &req->base, err);
-}
-EXPORT_SYMBOL_GPL(crypto_finalize_ablkcipher_request);
-
-/**
  * crypto_finalize_aead_request - finalize one aead_request if
  * the request is done
  * @engine: the hardware engine
diff --git a/crypto/crypto_user_base.c b/crypto/crypto_user_base.c
index 910e0b46012e..b785c476de67 100644
--- a/crypto/crypto_user_base.c
+++ b/crypto/crypto_user_base.c
@@ -213,8 +213,10 @@ static int crypto_report(struct sk_buff *in_skb, struct nlmsghdr *in_nlh,
 drop_alg:
 	crypto_mod_put(alg);
 
-	if (err)
+	if (err) {
+		kfree_skb(skb);
 		return err;
+	}
 
 	return nlmsg_unicast(net->crypto_nlsk, skb, NETLINK_CB(in_skb).portid);
 }
diff --git a/crypto/crypto_user_stat.c b/crypto/crypto_user_stat.c
index 8bad88413de1..154884bf9275 100644
--- a/crypto/crypto_user_stat.c
+++ b/crypto/crypto_user_stat.c
@@ -213,10 +213,6 @@ static int crypto_reportstat_one(struct crypto_alg *alg,
 		if (crypto_report_cipher(skb, alg))
 			goto nla_put_failure;
 		break;
-	case CRYPTO_ALG_TYPE_BLKCIPHER:
-		if (crypto_report_cipher(skb, alg))
-			goto nla_put_failure;
-		break;
 	case CRYPTO_ALG_TYPE_CIPHER:
 		if (crypto_report_cipher(skb, alg))
 			goto nla_put_failure;
@@ -328,8 +324,10 @@ int crypto_reportstat(struct sk_buff *in_skb, struct nlmsghdr *in_nlh,
 drop_alg:
 	crypto_mod_put(alg);
 
-	if (err)
+	if (err) {
+		kfree_skb(skb);
 		return err;
+	}
 
 	return nlmsg_unicast(net->crypto_nlsk, skb, NETLINK_CB(in_skb).portid);
 }
diff --git a/crypto/curve25519-generic.c b/crypto/curve25519-generic.c
new file mode 100644
index 000000000000..bd88fd571393
--- /dev/null
+++ b/crypto/curve25519-generic.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <crypto/curve25519.h>
+#include <crypto/internal/kpp.h>
+#include <crypto/kpp.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+
+static int curve25519_set_secret(struct crypto_kpp *tfm, const void *buf,
+				 unsigned int len)
+{
+	u8 *secret = kpp_tfm_ctx(tfm);
+
+	if (!len)
+		curve25519_generate_secret(secret);
+	else if (len == CURVE25519_KEY_SIZE &&
+		 crypto_memneq(buf, curve25519_null_point, CURVE25519_KEY_SIZE))
+		memcpy(secret, buf, CURVE25519_KEY_SIZE);
+	else
+		return -EINVAL;
+	return 0;
+}
+
+static int curve25519_compute_value(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	const u8 *secret = kpp_tfm_ctx(tfm);
+	u8 public_key[CURVE25519_KEY_SIZE];
+	u8 buf[CURVE25519_KEY_SIZE];
+	int copied, nbytes;
+	u8 const *bp;
+
+	if (req->src) {
+		copied = sg_copy_to_buffer(req->src,
+					   sg_nents_for_len(req->src,
+							    CURVE25519_KEY_SIZE),
+					   public_key, CURVE25519_KEY_SIZE);
+		if (copied != CURVE25519_KEY_SIZE)
+			return -EINVAL;
+		bp = public_key;
+	} else {
+		bp = curve25519_base_point;
+	}
+
+	curve25519_generic(buf, secret, bp);
+
+	/* might want less than we've got */
+	nbytes = min_t(size_t, CURVE25519_KEY_SIZE, req->dst_len);
+	copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst,
+								nbytes),
+				     buf, nbytes);
+	if (copied != nbytes)
+		return -EINVAL;
+	return 0;
+}
+
+static unsigned int curve25519_max_size(struct crypto_kpp *tfm)
+{
+	return CURVE25519_KEY_SIZE;
+}
+
+static struct kpp_alg curve25519_alg = {
+	.base.cra_name		= "curve25519",
+	.base.cra_driver_name	= "curve25519-generic",
+	.base.cra_priority	= 100,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_ctxsize	= CURVE25519_KEY_SIZE,
+
+	.set_secret		= curve25519_set_secret,
+	.generate_public_key	= curve25519_compute_value,
+	.compute_shared_secret	= curve25519_compute_value,
+	.max_size		= curve25519_max_size,
+};
+
+static int curve25519_init(void)
+{
+	return crypto_register_kpp(&curve25519_alg);
+}
+
+static void curve25519_exit(void)
+{
+	crypto_unregister_kpp(&curve25519_alg);
+}
+
+subsys_initcall(curve25519_init);
+module_exit(curve25519_exit);
+
+MODULE_ALIAS_CRYPTO("curve25519");
+MODULE_ALIAS_CRYPTO("curve25519-generic");
+MODULE_LICENSE("GPL");
diff --git a/crypto/ecc.c b/crypto/ecc.c
index dfe114bc0c4a..02d35be7702b 100644
--- a/crypto/ecc.c
+++ b/crypto/ecc.c
@@ -336,7 +336,7 @@ static u64 vli_usub(u64 *result, const u64 *left, u64 right,
 static uint128_t mul_64_64(u64 left, u64 right)
 {
 	uint128_t result;
-#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+#if defined(CONFIG_ARCH_SUPPORTS_INT128)
 	unsigned __int128 m = (unsigned __int128)left * right;
 
 	result.m_low  = m;
@@ -1284,10 +1284,11 @@ EXPORT_SYMBOL(ecc_point_mult_shamir);
 static inline void ecc_swap_digits(const u64 *in, u64 *out,
 				   unsigned int ndigits)
 {
+	const __be64 *src = (__force __be64 *)in;
 	int i;
 
 	for (i = 0; i < ndigits; i++)
-		out[i] = __swab64(in[ndigits - 1 - i]);
+		out[i] = be64_to_cpu(src[ndigits - 1 - i]);
 }
 
 static int __ecc_is_key_valid(const struct ecc_curve *curve,
diff --git a/crypto/essiv.c b/crypto/essiv.c
index a8befc8fb06e..808f2b362106 100644
--- a/crypto/essiv.c
+++ b/crypto/essiv.c
@@ -188,8 +188,7 @@ static void essiv_aead_done(struct crypto_async_request *areq, int err)
 	struct aead_request *req = areq->data;
 	struct essiv_aead_request_ctx *rctx = aead_request_ctx(req);
 
-	if (rctx->assoc)
-		kfree(rctx->assoc);
+	kfree(rctx->assoc);
 	aead_request_complete(req, err);
 }
 
@@ -486,7 +485,7 @@ static int essiv_create(struct crypto_template *tmpl, struct rtattr **tb)
 	type = algt->type & algt->mask;
 
 	switch (type) {
-	case CRYPTO_ALG_TYPE_BLKCIPHER:
+	case CRYPTO_ALG_TYPE_SKCIPHER:
 		skcipher_inst = kzalloc(sizeof(*skcipher_inst) +
 					sizeof(*ictx), GFP_KERNEL);
 		if (!skcipher_inst)
@@ -586,7 +585,7 @@ static int essiv_create(struct crypto_template *tmpl, struct rtattr **tb)
 	base->cra_alignmask	= block_base->cra_alignmask;
 	base->cra_priority	= block_base->cra_priority;
 
-	if (type == CRYPTO_ALG_TYPE_BLKCIPHER) {
+	if (type == CRYPTO_ALG_TYPE_SKCIPHER) {
 		skcipher_inst->alg.setkey	= essiv_skcipher_setkey;
 		skcipher_inst->alg.encrypt	= essiv_skcipher_encrypt;
 		skcipher_inst->alg.decrypt	= essiv_skcipher_decrypt;
@@ -628,7 +627,7 @@ static int essiv_create(struct crypto_template *tmpl, struct rtattr **tb)
 out_free_hash:
 	crypto_mod_put(_hash_alg);
 out_drop_skcipher:
-	if (type == CRYPTO_ALG_TYPE_BLKCIPHER)
+	if (type == CRYPTO_ALG_TYPE_SKCIPHER)
 		crypto_drop_skcipher(&ictx->u.skcipher_spawn);
 	else
 		crypto_drop_aead(&ictx->u.aead_spawn);
diff --git a/crypto/geniv.c b/crypto/geniv.c
new file mode 100644
index 000000000000..b9e45a2a98b5
--- /dev/null
+++ b/crypto/geniv.c
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * geniv: Shared IV generator code
+ *
+ * This file provides common code to IV generators such as seqiv.
+ *
+ * Copyright (c) 2007-2019 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+
+#include <crypto/internal/geniv.h>
+#include <crypto/internal/rng.h>
+#include <crypto/null.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/rtnetlink.h>
+#include <linux/slab.h>
+
+static int aead_geniv_setkey(struct crypto_aead *tfm,
+			     const u8 *key, unsigned int keylen)
+{
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(tfm);
+
+	return crypto_aead_setkey(ctx->child, key, keylen);
+}
+
+static int aead_geniv_setauthsize(struct crypto_aead *tfm,
+				  unsigned int authsize)
+{
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(tfm);
+
+	return crypto_aead_setauthsize(ctx->child, authsize);
+}
+
+struct aead_instance *aead_geniv_alloc(struct crypto_template *tmpl,
+				       struct rtattr **tb, u32 type, u32 mask)
+{
+	const char *name;
+	struct crypto_aead_spawn *spawn;
+	struct crypto_attr_type *algt;
+	struct aead_instance *inst;
+	struct aead_alg *alg;
+	unsigned int ivsize;
+	unsigned int maxauthsize;
+	int err;
+
+	algt = crypto_get_attr_type(tb);
+	if (IS_ERR(algt))
+		return ERR_CAST(algt);
+
+	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
+		return ERR_PTR(-EINVAL);
+
+	name = crypto_attr_alg_name(tb[1]);
+	if (IS_ERR(name))
+		return ERR_CAST(name);
+
+	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
+	if (!inst)
+		return ERR_PTR(-ENOMEM);
+
+	spawn = aead_instance_ctx(inst);
+
+	/* Ignore async algorithms if necessary. */
+	mask |= crypto_requires_sync(algt->type, algt->mask);
+
+	crypto_set_aead_spawn(spawn, aead_crypto_instance(inst));
+	err = crypto_grab_aead(spawn, name, type, mask);
+	if (err)
+		goto err_free_inst;
+
+	alg = crypto_spawn_aead_alg(spawn);
+
+	ivsize = crypto_aead_alg_ivsize(alg);
+	maxauthsize = crypto_aead_alg_maxauthsize(alg);
+
+	err = -EINVAL;
+	if (ivsize < sizeof(u64))
+		goto err_drop_alg;
+
+	err = -ENAMETOOLONG;
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "%s(%s)", tmpl->name, alg->base.cra_name) >=
+	    CRYPTO_MAX_ALG_NAME)
+		goto err_drop_alg;
+	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "%s(%s)", tmpl->name, alg->base.cra_driver_name) >=
+	    CRYPTO_MAX_ALG_NAME)
+		goto err_drop_alg;
+
+	inst->alg.base.cra_flags = alg->base.cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = alg->base.cra_priority;
+	inst->alg.base.cra_blocksize = alg->base.cra_blocksize;
+	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
+	inst->alg.base.cra_ctxsize = sizeof(struct aead_geniv_ctx);
+
+	inst->alg.setkey = aead_geniv_setkey;
+	inst->alg.setauthsize = aead_geniv_setauthsize;
+
+	inst->alg.ivsize = ivsize;
+	inst->alg.maxauthsize = maxauthsize;
+
+out:
+	return inst;
+
+err_drop_alg:
+	crypto_drop_aead(spawn);
+err_free_inst:
+	kfree(inst);
+	inst = ERR_PTR(err);
+	goto out;
+}
+EXPORT_SYMBOL_GPL(aead_geniv_alloc);
+
+void aead_geniv_free(struct aead_instance *inst)
+{
+	crypto_drop_aead(aead_instance_ctx(inst));
+	kfree(inst);
+}
+EXPORT_SYMBOL_GPL(aead_geniv_free);
+
+int aead_init_geniv(struct crypto_aead *aead)
+{
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(aead);
+	struct aead_instance *inst = aead_alg_instance(aead);
+	struct crypto_aead *child;
+	int err;
+
+	spin_lock_init(&ctx->lock);
+
+	err = crypto_get_default_rng();
+	if (err)
+		goto out;
+
+	err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
+				   crypto_aead_ivsize(aead));
+	crypto_put_default_rng();
+	if (err)
+		goto out;
+
+	ctx->sknull = crypto_get_default_null_skcipher();
+	err = PTR_ERR(ctx->sknull);
+	if (IS_ERR(ctx->sknull))
+		goto out;
+
+	child = crypto_spawn_aead(aead_instance_ctx(inst));
+	err = PTR_ERR(child);
+	if (IS_ERR(child))
+		goto drop_null;
+
+	ctx->child = child;
+	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(child) +
+				      sizeof(struct aead_request));
+
+	err = 0;
+
+out:
+	return err;
+
+drop_null:
+	crypto_put_default_null_skcipher();
+	goto out;
+}
+EXPORT_SYMBOL_GPL(aead_init_geniv);
+
+void aead_exit_geniv(struct crypto_aead *tfm)
+{
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(tfm);
+
+	crypto_free_aead(ctx->child);
+	crypto_put_default_null_skcipher();
+}
+EXPORT_SYMBOL_GPL(aead_exit_geniv);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Shared IV generator code");
diff --git a/crypto/jitterentropy-kcapi.c b/crypto/jitterentropy-kcapi.c
index 701b8d86ab49..a5ce8f96790f 100644
--- a/crypto/jitterentropy-kcapi.c
+++ b/crypto/jitterentropy-kcapi.c
@@ -44,13 +44,7 @@
 #include <linux/crypto.h>
 #include <crypto/internal/rng.h>
 
-struct rand_data;
-int jent_read_entropy(struct rand_data *ec, unsigned char *data,
-		      unsigned int len);
-int jent_entropy_init(void);
-struct rand_data *jent_entropy_collector_alloc(unsigned int osr,
-					       unsigned int flags);
-void jent_entropy_collector_free(struct rand_data *entropy_collector);
+#include "jitterentropy.h"
 
 /***************************************************************************
  * Helper function
diff --git a/crypto/jitterentropy.c b/crypto/jitterentropy.c
index 77fa2120fe0c..042157f0d28b 100644
--- a/crypto/jitterentropy.c
+++ b/crypto/jitterentropy.c
@@ -103,12 +103,7 @@ struct rand_data {
  * Helper functions
  ***************************************************************************/
 
-void jent_get_nstime(__u64 *out);
-void *jent_zalloc(unsigned int len);
-void jent_zfree(void *ptr);
-int jent_fips_enabled(void);
-void jent_panic(char *s);
-void jent_memcpy(void *dest, const void *src, unsigned int n);
+#include "jitterentropy.h"
 
 /**
  * Update of the loop count used for the next round of
@@ -172,7 +167,7 @@ static __u64 jent_loop_shuffle(struct rand_data *ec,
  * implies that careful retesting must be done.
  *
  * Input:
- * @ec entropy collector struct -- may be NULL
+ * @ec entropy collector struct
  * @time time stamp to be injected
  * @loop_cnt if a value not equal to 0 is set, use the given value as number of
  *	     loops to perform the folding
@@ -400,8 +395,8 @@ static void jent_gen_entropy(struct rand_data *ec)
  * primes the test if needed.
  *
  * Return:
- * 0 if FIPS test passed
- * < 0 if FIPS test failed
+ * returns normally if FIPS test passed
+ * panics the kernel if FIPS test failed
  */
 static void jent_fips_test(struct rand_data *ec)
 {
diff --git a/crypto/jitterentropy.h b/crypto/jitterentropy.h
new file mode 100644
index 000000000000..c83fff32d130
--- /dev/null
+++ b/crypto/jitterentropy.h
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+extern void *jent_zalloc(unsigned int len);
+extern void jent_zfree(void *ptr);
+extern int jent_fips_enabled(void);
+extern void jent_panic(char *s);
+extern void jent_memcpy(void *dest, const void *src, unsigned int n);
+extern void jent_get_nstime(__u64 *out);
+
+struct rand_data;
+extern int jent_entropy_init(void);
+extern int jent_read_entropy(struct rand_data *ec, unsigned char *data,
+			     unsigned int len);
+
+extern struct rand_data *jent_entropy_collector_alloc(unsigned int osr,
+						      unsigned int flags);
+extern void jent_entropy_collector_free(struct rand_data *entropy_collector);
diff --git a/crypto/nhpoly1305.c b/crypto/nhpoly1305.c
index 9ab4e07cde4d..f6b6a52092b4 100644
--- a/crypto/nhpoly1305.c
+++ b/crypto/nhpoly1305.c
@@ -33,6 +33,7 @@
 #include <asm/unaligned.h>
 #include <crypto/algapi.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/poly1305.h>
 #include <crypto/nhpoly1305.h>
 #include <linux/crypto.h>
 #include <linux/kernel.h>
@@ -78,7 +79,7 @@ static void process_nh_hash_value(struct nhpoly1305_state *state,
 	BUILD_BUG_ON(NH_HASH_BYTES % POLY1305_BLOCK_SIZE != 0);
 
 	poly1305_core_blocks(&state->poly_state, &key->poly_key, state->nh_hash,
-			     NH_HASH_BYTES / POLY1305_BLOCK_SIZE);
+			     NH_HASH_BYTES / POLY1305_BLOCK_SIZE, 1);
 }
 
 /*
diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c
index adc40298c749..21edbd8c99fb 100644
--- a/crypto/poly1305_generic.c
+++ b/crypto/poly1305_generic.c
@@ -13,158 +13,26 @@
 
 #include <crypto/algapi.h>
 #include <crypto/internal/hash.h>
-#include <crypto/poly1305.h>
+#include <crypto/internal/poly1305.h>
 #include <linux/crypto.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <asm/unaligned.h>
 
-static inline u64 mlt(u64 a, u64 b)
-{
-	return a * b;
-}
-
-static inline u32 sr(u64 v, u_char n)
-{
-	return v >> n;
-}
-
-static inline u32 and(u32 v, u32 mask)
-{
-	return v & mask;
-}
-
-int crypto_poly1305_init(struct shash_desc *desc)
+static int crypto_poly1305_init(struct shash_desc *desc)
 {
 	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
 
 	poly1305_core_init(&dctx->h);
 	dctx->buflen = 0;
-	dctx->rset = false;
+	dctx->rset = 0;
 	dctx->sset = false;
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(crypto_poly1305_init);
-
-void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key)
-{
-	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
-	key->r[0] = (get_unaligned_le32(raw_key +  0) >> 0) & 0x3ffffff;
-	key->r[1] = (get_unaligned_le32(raw_key +  3) >> 2) & 0x3ffff03;
-	key->r[2] = (get_unaligned_le32(raw_key +  6) >> 4) & 0x3ffc0ff;
-	key->r[3] = (get_unaligned_le32(raw_key +  9) >> 6) & 0x3f03fff;
-	key->r[4] = (get_unaligned_le32(raw_key + 12) >> 8) & 0x00fffff;
-}
-EXPORT_SYMBOL_GPL(poly1305_core_setkey);
-
-/*
- * Poly1305 requires a unique key for each tag, which implies that we can't set
- * it on the tfm that gets accessed by multiple users simultaneously. Instead we
- * expect the key as the first 32 bytes in the update() call.
- */
-unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
-					const u8 *src, unsigned int srclen)
-{
-	if (!dctx->sset) {
-		if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) {
-			poly1305_core_setkey(&dctx->r, src);
-			src += POLY1305_BLOCK_SIZE;
-			srclen -= POLY1305_BLOCK_SIZE;
-			dctx->rset = true;
-		}
-		if (srclen >= POLY1305_BLOCK_SIZE) {
-			dctx->s[0] = get_unaligned_le32(src +  0);
-			dctx->s[1] = get_unaligned_le32(src +  4);
-			dctx->s[2] = get_unaligned_le32(src +  8);
-			dctx->s[3] = get_unaligned_le32(src + 12);
-			src += POLY1305_BLOCK_SIZE;
-			srclen -= POLY1305_BLOCK_SIZE;
-			dctx->sset = true;
-		}
-	}
-	return srclen;
-}
-EXPORT_SYMBOL_GPL(crypto_poly1305_setdesckey);
-
-static void poly1305_blocks_internal(struct poly1305_state *state,
-				     const struct poly1305_key *key,
-				     const void *src, unsigned int nblocks,
-				     u32 hibit)
-{
-	u32 r0, r1, r2, r3, r4;
-	u32 s1, s2, s3, s4;
-	u32 h0, h1, h2, h3, h4;
-	u64 d0, d1, d2, d3, d4;
-
-	if (!nblocks)
-		return;
-
-	r0 = key->r[0];
-	r1 = key->r[1];
-	r2 = key->r[2];
-	r3 = key->r[3];
-	r4 = key->r[4];
-
-	s1 = r1 * 5;
-	s2 = r2 * 5;
-	s3 = r3 * 5;
-	s4 = r4 * 5;
-
-	h0 = state->h[0];
-	h1 = state->h[1];
-	h2 = state->h[2];
-	h3 = state->h[3];
-	h4 = state->h[4];
-
-	do {
-		/* h += m[i] */
-		h0 += (get_unaligned_le32(src +  0) >> 0) & 0x3ffffff;
-		h1 += (get_unaligned_le32(src +  3) >> 2) & 0x3ffffff;
-		h2 += (get_unaligned_le32(src +  6) >> 4) & 0x3ffffff;
-		h3 += (get_unaligned_le32(src +  9) >> 6) & 0x3ffffff;
-		h4 += (get_unaligned_le32(src + 12) >> 8) | hibit;
-
-		/* h *= r */
-		d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) +
-		     mlt(h3, s2) + mlt(h4, s1);
-		d1 = mlt(h0, r1) + mlt(h1, r0) + mlt(h2, s4) +
-		     mlt(h3, s3) + mlt(h4, s2);
-		d2 = mlt(h0, r2) + mlt(h1, r1) + mlt(h2, r0) +
-		     mlt(h3, s4) + mlt(h4, s3);
-		d3 = mlt(h0, r3) + mlt(h1, r2) + mlt(h2, r1) +
-		     mlt(h3, r0) + mlt(h4, s4);
-		d4 = mlt(h0, r4) + mlt(h1, r3) + mlt(h2, r2) +
-		     mlt(h3, r1) + mlt(h4, r0);
-
-		/* (partial) h %= p */
-		d1 += sr(d0, 26);     h0 = and(d0, 0x3ffffff);
-		d2 += sr(d1, 26);     h1 = and(d1, 0x3ffffff);
-		d3 += sr(d2, 26);     h2 = and(d2, 0x3ffffff);
-		d4 += sr(d3, 26);     h3 = and(d3, 0x3ffffff);
-		h0 += sr(d4, 26) * 5; h4 = and(d4, 0x3ffffff);
-		h1 += h0 >> 26;       h0 = h0 & 0x3ffffff;
-
-		src += POLY1305_BLOCK_SIZE;
-	} while (--nblocks);
-
-	state->h[0] = h0;
-	state->h[1] = h1;
-	state->h[2] = h2;
-	state->h[3] = h3;
-	state->h[4] = h4;
-}
-
-void poly1305_core_blocks(struct poly1305_state *state,
-			  const struct poly1305_key *key,
-			  const void *src, unsigned int nblocks)
-{
-	poly1305_blocks_internal(state, key, src, nblocks, 1 << 24);
-}
-EXPORT_SYMBOL_GPL(poly1305_core_blocks);
 
-static void poly1305_blocks(struct poly1305_desc_ctx *dctx,
-			    const u8 *src, unsigned int srclen, u32 hibit)
+static void poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
+			    unsigned int srclen)
 {
 	unsigned int datalen;
 
@@ -174,12 +42,12 @@ static void poly1305_blocks(struct poly1305_desc_ctx *dctx,
 		srclen = datalen;
 	}
 
-	poly1305_blocks_internal(&dctx->h, &dctx->r,
-				 src, srclen / POLY1305_BLOCK_SIZE, hibit);
+	poly1305_core_blocks(&dctx->h, dctx->r, src,
+			     srclen / POLY1305_BLOCK_SIZE, 1);
 }
 
-int crypto_poly1305_update(struct shash_desc *desc,
-			   const u8 *src, unsigned int srclen)
+static int crypto_poly1305_update(struct shash_desc *desc,
+				  const u8 *src, unsigned int srclen)
 {
 	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
 	unsigned int bytes;
@@ -193,13 +61,13 @@ int crypto_poly1305_update(struct shash_desc *desc,
 
 		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
 			poly1305_blocks(dctx, dctx->buf,
-					POLY1305_BLOCK_SIZE, 1 << 24);
+					POLY1305_BLOCK_SIZE);
 			dctx->buflen = 0;
 		}
 	}
 
 	if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
-		poly1305_blocks(dctx, src, srclen, 1 << 24);
+		poly1305_blocks(dctx, src, srclen);
 		src += srclen - (srclen % POLY1305_BLOCK_SIZE);
 		srclen %= POLY1305_BLOCK_SIZE;
 	}
@@ -211,87 +79,17 @@ int crypto_poly1305_update(struct shash_desc *desc,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(crypto_poly1305_update);
-
-void poly1305_core_emit(const struct poly1305_state *state, void *dst)
-{
-	u32 h0, h1, h2, h3, h4;
-	u32 g0, g1, g2, g3, g4;
-	u32 mask;
-
-	/* fully carry h */
-	h0 = state->h[0];
-	h1 = state->h[1];
-	h2 = state->h[2];
-	h3 = state->h[3];
-	h4 = state->h[4];
-
-	h2 += (h1 >> 26);     h1 = h1 & 0x3ffffff;
-	h3 += (h2 >> 26);     h2 = h2 & 0x3ffffff;
-	h4 += (h3 >> 26);     h3 = h3 & 0x3ffffff;
-	h0 += (h4 >> 26) * 5; h4 = h4 & 0x3ffffff;
-	h1 += (h0 >> 26);     h0 = h0 & 0x3ffffff;
-
-	/* compute h + -p */
-	g0 = h0 + 5;
-	g1 = h1 + (g0 >> 26);             g0 &= 0x3ffffff;
-	g2 = h2 + (g1 >> 26);             g1 &= 0x3ffffff;
-	g3 = h3 + (g2 >> 26);             g2 &= 0x3ffffff;
-	g4 = h4 + (g3 >> 26) - (1 << 26); g3 &= 0x3ffffff;
-
-	/* select h if h < p, or h + -p if h >= p */
-	mask = (g4 >> ((sizeof(u32) * 8) - 1)) - 1;
-	g0 &= mask;
-	g1 &= mask;
-	g2 &= mask;
-	g3 &= mask;
-	g4 &= mask;
-	mask = ~mask;
-	h0 = (h0 & mask) | g0;
-	h1 = (h1 & mask) | g1;
-	h2 = (h2 & mask) | g2;
-	h3 = (h3 & mask) | g3;
-	h4 = (h4 & mask) | g4;
-
-	/* h = h % (2^128) */
-	put_unaligned_le32((h0 >>  0) | (h1 << 26), dst +  0);
-	put_unaligned_le32((h1 >>  6) | (h2 << 20), dst +  4);
-	put_unaligned_le32((h2 >> 12) | (h3 << 14), dst +  8);
-	put_unaligned_le32((h3 >> 18) | (h4 <<  8), dst + 12);
-}
-EXPORT_SYMBOL_GPL(poly1305_core_emit);
 
-int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
+static int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
 {
 	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-	__le32 digest[4];
-	u64 f = 0;
 
 	if (unlikely(!dctx->sset))
 		return -ENOKEY;
 
-	if (unlikely(dctx->buflen)) {
-		dctx->buf[dctx->buflen++] = 1;
-		memset(dctx->buf + dctx->buflen, 0,
-		       POLY1305_BLOCK_SIZE - dctx->buflen);
-		poly1305_blocks(dctx, dctx->buf, POLY1305_BLOCK_SIZE, 0);
-	}
-
-	poly1305_core_emit(&dctx->h, digest);
-
-	/* mac = (h + s) % (2^128) */
-	f = (f >> 32) + le32_to_cpu(digest[0]) + dctx->s[0];
-	put_unaligned_le32(f, dst + 0);
-	f = (f >> 32) + le32_to_cpu(digest[1]) + dctx->s[1];
-	put_unaligned_le32(f, dst + 4);
-	f = (f >> 32) + le32_to_cpu(digest[2]) + dctx->s[2];
-	put_unaligned_le32(f, dst + 8);
-	f = (f >> 32) + le32_to_cpu(digest[3]) + dctx->s[3];
-	put_unaligned_le32(f, dst + 12);
-
+	poly1305_final_generic(dctx, dst);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(crypto_poly1305_final);
 
 static struct shash_alg poly1305_alg = {
 	.digestsize	= POLY1305_DIGEST_SIZE,
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index 22753c1c7202..13da43c84b64 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -580,12 +580,6 @@ EXPORT_SYMBOL_GPL(skcipher_walk_aead_decrypt);
 
 static unsigned int crypto_skcipher_extsize(struct crypto_alg *alg)
 {
-	if (alg->cra_type == &crypto_blkcipher_type)
-		return sizeof(struct crypto_blkcipher *);
-
-	if (alg->cra_type == &crypto_ablkcipher_type)
-		return sizeof(struct crypto_ablkcipher *);
-
 	return crypto_alg_extsize(alg);
 }
 
@@ -595,205 +589,6 @@ static void skcipher_set_needkey(struct crypto_skcipher *tfm)
 		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_NEED_KEY);
 }
 
-static int skcipher_setkey_blkcipher(struct crypto_skcipher *tfm,
-				     const u8 *key, unsigned int keylen)
-{
-	struct crypto_blkcipher **ctx = crypto_skcipher_ctx(tfm);
-	struct crypto_blkcipher *blkcipher = *ctx;
-	int err;
-
-	crypto_blkcipher_clear_flags(blkcipher, ~0);
-	crypto_blkcipher_set_flags(blkcipher, crypto_skcipher_get_flags(tfm) &
-					      CRYPTO_TFM_REQ_MASK);
-	err = crypto_blkcipher_setkey(blkcipher, key, keylen);
-	crypto_skcipher_set_flags(tfm, crypto_blkcipher_get_flags(blkcipher) &
-				       CRYPTO_TFM_RES_MASK);
-	if (unlikely(err)) {
-		skcipher_set_needkey(tfm);
-		return err;
-	}
-
-	crypto_skcipher_clear_flags(tfm, CRYPTO_TFM_NEED_KEY);
-	return 0;
-}
-
-static int skcipher_crypt_blkcipher(struct skcipher_request *req,
-				    int (*crypt)(struct blkcipher_desc *,
-						 struct scatterlist *,
-						 struct scatterlist *,
-						 unsigned int))
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct crypto_blkcipher **ctx = crypto_skcipher_ctx(tfm);
-	struct blkcipher_desc desc = {
-		.tfm = *ctx,
-		.info = req->iv,
-		.flags = req->base.flags,
-	};
-
-
-	return crypt(&desc, req->dst, req->src, req->cryptlen);
-}
-
-static int skcipher_encrypt_blkcipher(struct skcipher_request *req)
-{
-	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
-	struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher);
-	struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher;
-
-	return skcipher_crypt_blkcipher(req, alg->encrypt);
-}
-
-static int skcipher_decrypt_blkcipher(struct skcipher_request *req)
-{
-	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
-	struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher);
-	struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher;
-
-	return skcipher_crypt_blkcipher(req, alg->decrypt);
-}
-
-static void crypto_exit_skcipher_ops_blkcipher(struct crypto_tfm *tfm)
-{
-	struct crypto_blkcipher **ctx = crypto_tfm_ctx(tfm);
-
-	crypto_free_blkcipher(*ctx);
-}
-
-static int crypto_init_skcipher_ops_blkcipher(struct crypto_tfm *tfm)
-{
-	struct crypto_alg *calg = tfm->__crt_alg;
-	struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm);
-	struct crypto_blkcipher **ctx = crypto_tfm_ctx(tfm);
-	struct crypto_blkcipher *blkcipher;
-	struct crypto_tfm *btfm;
-
-	if (!crypto_mod_get(calg))
-		return -EAGAIN;
-
-	btfm = __crypto_alloc_tfm(calg, CRYPTO_ALG_TYPE_BLKCIPHER,
-					CRYPTO_ALG_TYPE_MASK);
-	if (IS_ERR(btfm)) {
-		crypto_mod_put(calg);
-		return PTR_ERR(btfm);
-	}
-
-	blkcipher = __crypto_blkcipher_cast(btfm);
-	*ctx = blkcipher;
-	tfm->exit = crypto_exit_skcipher_ops_blkcipher;
-
-	skcipher->setkey = skcipher_setkey_blkcipher;
-	skcipher->encrypt = skcipher_encrypt_blkcipher;
-	skcipher->decrypt = skcipher_decrypt_blkcipher;
-
-	skcipher->ivsize = crypto_blkcipher_ivsize(blkcipher);
-	skcipher->keysize = calg->cra_blkcipher.max_keysize;
-
-	skcipher_set_needkey(skcipher);
-
-	return 0;
-}
-
-static int skcipher_setkey_ablkcipher(struct crypto_skcipher *tfm,
-				      const u8 *key, unsigned int keylen)
-{
-	struct crypto_ablkcipher **ctx = crypto_skcipher_ctx(tfm);
-	struct crypto_ablkcipher *ablkcipher = *ctx;
-	int err;
-
-	crypto_ablkcipher_clear_flags(ablkcipher, ~0);
-	crypto_ablkcipher_set_flags(ablkcipher,
-				    crypto_skcipher_get_flags(tfm) &
-				    CRYPTO_TFM_REQ_MASK);
-	err = crypto_ablkcipher_setkey(ablkcipher, key, keylen);
-	crypto_skcipher_set_flags(tfm,
-				  crypto_ablkcipher_get_flags(ablkcipher) &
-				  CRYPTO_TFM_RES_MASK);
-	if (unlikely(err)) {
-		skcipher_set_needkey(tfm);
-		return err;
-	}
-
-	crypto_skcipher_clear_flags(tfm, CRYPTO_TFM_NEED_KEY);
-	return 0;
-}
-
-static int skcipher_crypt_ablkcipher(struct skcipher_request *req,
-				     int (*crypt)(struct ablkcipher_request *))
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct crypto_ablkcipher **ctx = crypto_skcipher_ctx(tfm);
-	struct ablkcipher_request *subreq = skcipher_request_ctx(req);
-
-	ablkcipher_request_set_tfm(subreq, *ctx);
-	ablkcipher_request_set_callback(subreq, skcipher_request_flags(req),
-					req->base.complete, req->base.data);
-	ablkcipher_request_set_crypt(subreq, req->src, req->dst, req->cryptlen,
-				     req->iv);
-
-	return crypt(subreq);
-}
-
-static int skcipher_encrypt_ablkcipher(struct skcipher_request *req)
-{
-	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
-	struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher);
-	struct ablkcipher_alg *alg = &tfm->__crt_alg->cra_ablkcipher;
-
-	return skcipher_crypt_ablkcipher(req, alg->encrypt);
-}
-
-static int skcipher_decrypt_ablkcipher(struct skcipher_request *req)
-{
-	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
-	struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher);
-	struct ablkcipher_alg *alg = &tfm->__crt_alg->cra_ablkcipher;
-
-	return skcipher_crypt_ablkcipher(req, alg->decrypt);
-}
-
-static void crypto_exit_skcipher_ops_ablkcipher(struct crypto_tfm *tfm)
-{
-	struct crypto_ablkcipher **ctx = crypto_tfm_ctx(tfm);
-
-	crypto_free_ablkcipher(*ctx);
-}
-
-static int crypto_init_skcipher_ops_ablkcipher(struct crypto_tfm *tfm)
-{
-	struct crypto_alg *calg = tfm->__crt_alg;
-	struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm);
-	struct crypto_ablkcipher **ctx = crypto_tfm_ctx(tfm);
-	struct crypto_ablkcipher *ablkcipher;
-	struct crypto_tfm *abtfm;
-
-	if (!crypto_mod_get(calg))
-		return -EAGAIN;
-
-	abtfm = __crypto_alloc_tfm(calg, 0, 0);
-	if (IS_ERR(abtfm)) {
-		crypto_mod_put(calg);
-		return PTR_ERR(abtfm);
-	}
-
-	ablkcipher = __crypto_ablkcipher_cast(abtfm);
-	*ctx = ablkcipher;
-	tfm->exit = crypto_exit_skcipher_ops_ablkcipher;
-
-	skcipher->setkey = skcipher_setkey_ablkcipher;
-	skcipher->encrypt = skcipher_encrypt_ablkcipher;
-	skcipher->decrypt = skcipher_decrypt_ablkcipher;
-
-	skcipher->ivsize = crypto_ablkcipher_ivsize(ablkcipher);
-	skcipher->reqsize = crypto_ablkcipher_reqsize(ablkcipher) +
-			    sizeof(struct ablkcipher_request);
-	skcipher->keysize = calg->cra_ablkcipher.max_keysize;
-
-	skcipher_set_needkey(skcipher);
-
-	return 0;
-}
-
 static int skcipher_setkey_unaligned(struct crypto_skcipher *tfm,
 				     const u8 *key, unsigned int keylen)
 {
@@ -888,12 +683,6 @@ static int crypto_skcipher_init_tfm(struct crypto_tfm *tfm)
 	struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm);
 	struct skcipher_alg *alg = crypto_skcipher_alg(skcipher);
 
-	if (tfm->__crt_alg->cra_type == &crypto_blkcipher_type)
-		return crypto_init_skcipher_ops_blkcipher(tfm);
-
-	if (tfm->__crt_alg->cra_type == &crypto_ablkcipher_type)
-		return crypto_init_skcipher_ops_ablkcipher(tfm);
-
 	skcipher->setkey = skcipher_setkey;
 	skcipher->encrypt = alg->encrypt;
 	skcipher->decrypt = alg->decrypt;
@@ -964,7 +753,7 @@ static int crypto_skcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
 }
 #endif
 
-static const struct crypto_type crypto_skcipher_type2 = {
+static const struct crypto_type crypto_skcipher_type = {
 	.extsize = crypto_skcipher_extsize,
 	.init_tfm = crypto_skcipher_init_tfm,
 	.free = crypto_skcipher_free_instance,
@@ -973,7 +762,7 @@ static const struct crypto_type crypto_skcipher_type2 = {
 #endif
 	.report = crypto_skcipher_report,
 	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
-	.maskset = CRYPTO_ALG_TYPE_BLKCIPHER_MASK,
+	.maskset = CRYPTO_ALG_TYPE_MASK,
 	.type = CRYPTO_ALG_TYPE_SKCIPHER,
 	.tfmsize = offsetof(struct crypto_skcipher, base),
 };
@@ -981,7 +770,7 @@ static const struct crypto_type crypto_skcipher_type2 = {
 int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn,
 			  const char *name, u32 type, u32 mask)
 {
-	spawn->base.frontend = &crypto_skcipher_type2;
+	spawn->base.frontend = &crypto_skcipher_type;
 	return crypto_grab_spawn(&spawn->base, name, type, mask);
 }
 EXPORT_SYMBOL_GPL(crypto_grab_skcipher);
@@ -989,7 +778,7 @@ EXPORT_SYMBOL_GPL(crypto_grab_skcipher);
 struct crypto_skcipher *crypto_alloc_skcipher(const char *alg_name,
 					      u32 type, u32 mask)
 {
-	return crypto_alloc_tfm(alg_name, &crypto_skcipher_type2, type, mask);
+	return crypto_alloc_tfm(alg_name, &crypto_skcipher_type, type, mask);
 }
 EXPORT_SYMBOL_GPL(crypto_alloc_skcipher);
 
@@ -1001,7 +790,7 @@ struct crypto_sync_skcipher *crypto_alloc_sync_skcipher(
 	/* Only sync algorithms allowed. */
 	mask |= CRYPTO_ALG_ASYNC;
 
-	tfm = crypto_alloc_tfm(alg_name, &crypto_skcipher_type2, type, mask);
+	tfm = crypto_alloc_tfm(alg_name, &crypto_skcipher_type, type, mask);
 
 	/*
 	 * Make sure we do not allocate something that might get used with
@@ -1017,12 +806,11 @@ struct crypto_sync_skcipher *crypto_alloc_sync_skcipher(
 }
 EXPORT_SYMBOL_GPL(crypto_alloc_sync_skcipher);
 
-int crypto_has_skcipher2(const char *alg_name, u32 type, u32 mask)
+int crypto_has_skcipher(const char *alg_name, u32 type, u32 mask)
 {
-	return crypto_type_has_alg(alg_name, &crypto_skcipher_type2,
-				   type, mask);
+	return crypto_type_has_alg(alg_name, &crypto_skcipher_type, type, mask);
 }
-EXPORT_SYMBOL_GPL(crypto_has_skcipher2);
+EXPORT_SYMBOL_GPL(crypto_has_skcipher);
 
 static int skcipher_prepare_alg(struct skcipher_alg *alg)
 {
@@ -1037,7 +825,7 @@ static int skcipher_prepare_alg(struct skcipher_alg *alg)
 	if (!alg->walksize)
 		alg->walksize = alg->chunksize;
 
-	base->cra_type = &crypto_skcipher_type2;
+	base->cra_type = &crypto_skcipher_type;
 	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
 	base->cra_flags |= CRYPTO_ALG_TYPE_SKCIPHER;
 
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 83ad0b1fab30..f42f486e90e8 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -65,7 +65,7 @@ static int mode;
 static u32 num_mb = 8;
 static char *tvmem[TVMEMSIZE];
 
-static char *check[] = {
+static const char *check[] = {
 	"des", "md5", "des3_ede", "rot13", "sha1", "sha224", "sha256", "sm3",
 	"blowfish", "twofish", "serpent", "sha384", "sha512", "md4", "aes",
 	"cast6", "arc4", "michael_mic", "deflate", "crc32c", "tea", "xtea",
@@ -1634,7 +1634,7 @@ static void test_cipher_speed(const char *algo, int enc, unsigned int secs,
 
 static void test_available(void)
 {
-	char **name = check;
+	const char **name = check;
 
 	while (*name) {
 		printk("alg %s ", *name);
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index c39e39e55dc2..82513b6b0abd 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -4023,6 +4023,58 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.test = alg_test_null,
 		.fips_allowed = 1,
 	}, {
+		.alg = "blake2b-160",
+		.test = alg_test_hash,
+		.fips_allowed = 0,
+		.suite = {
+			.hash = __VECS(blake2b_160_tv_template)
+		}
+	}, {
+		.alg = "blake2b-256",
+		.test = alg_test_hash,
+		.fips_allowed = 0,
+		.suite = {
+			.hash = __VECS(blake2b_256_tv_template)
+		}
+	}, {
+		.alg = "blake2b-384",
+		.test = alg_test_hash,
+		.fips_allowed = 0,
+		.suite = {
+			.hash = __VECS(blake2b_384_tv_template)
+		}
+	}, {
+		.alg = "blake2b-512",
+		.test = alg_test_hash,
+		.fips_allowed = 0,
+		.suite = {
+			.hash = __VECS(blake2b_512_tv_template)
+		}
+	}, {
+		.alg = "blake2s-128",
+		.test = alg_test_hash,
+		.suite = {
+			.hash = __VECS(blakes2s_128_tv_template)
+		}
+	}, {
+		.alg = "blake2s-160",
+		.test = alg_test_hash,
+		.suite = {
+			.hash = __VECS(blakes2s_160_tv_template)
+		}
+	}, {
+		.alg = "blake2s-224",
+		.test = alg_test_hash,
+		.suite = {
+			.hash = __VECS(blakes2s_224_tv_template)
+		}
+	}, {
+		.alg = "blake2s-256",
+		.test = alg_test_hash,
+		.suite = {
+			.hash = __VECS(blakes2s_256_tv_template)
+		}
+	}, {
 		.alg = "cbc(aes)",
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
@@ -4126,6 +4178,12 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.cipher = __VECS(aes_cfb_tv_template)
 		},
 	}, {
+		.alg = "cfb(sm4)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = __VECS(sm4_cfb_tv_template)
+		}
+	}, {
 		.alg = "chacha20",
 		.test = alg_test_skcipher,
 		.suite = {
@@ -4260,6 +4318,12 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.test = alg_test_null,
 		.fips_allowed = 1,
 	}, {
+		.alg = "curve25519",
+		.test = alg_test_kpp,
+		.suite = {
+			.kpp = __VECS(curve25519_tv_template)
+		}
+	}, {
 		.alg = "deflate",
 		.test = alg_test_comp,
 		.fips_allowed = 1,
@@ -4655,6 +4719,12 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.hash = __VECS(hmac_sha512_tv_template)
 		}
 	}, {
+		.alg = "hmac(sm3)",
+		.test = alg_test_hash,
+		.suite = {
+			.hash = __VECS(hmac_sm3_tv_template)
+		}
+	}, {
 		.alg = "hmac(streebog256)",
 		.test = alg_test_hash,
 		.suite = {
@@ -4791,6 +4861,12 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.test = alg_test_null,
 		.fips_allowed = 1,
 	}, {
+		.alg = "ofb(sm4)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = __VECS(sm4_ofb_tv_template)
+		}
+	}, {
 		.alg = "pcbc(fcrypt)",
 		.test = alg_test_skcipher,
 		.suite = {
@@ -4829,6 +4905,12 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.cipher = __VECS(aes_ctr_rfc3686_tv_template)
 		}
 	}, {
+		.alg = "rfc3686(ctr(sm4))",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = __VECS(sm4_ctr_rfc3686_tv_template)
+		}
+	}, {
 		.alg = "rfc4106(gcm(aes))",
 		.generic_driver = "rfc4106(gcm_base(ctr(aes-generic),ghash-generic))",
 		.test = alg_test_aead,
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index ef7d21f39d4a..48da646651cb 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -1030,6 +1030,1231 @@ static const struct kpp_testvec dh_tv_template[] = {
 	}
 };
 
+static const struct kpp_testvec curve25519_tv_template[] = {
+{
+	.secret = (u8[32]){ 0x77, 0x07, 0x6d, 0x0a, 0x73, 0x18, 0xa5, 0x7d,
+		     0x3c, 0x16, 0xc1, 0x72, 0x51, 0xb2, 0x66, 0x45,
+		     0xdf, 0x4c, 0x2f, 0x87, 0xeb, 0xc0, 0x99, 0x2a,
+		     0xb1, 0x77, 0xfb, 0xa5, 0x1d, 0xb9, 0x2c, 0x2a },
+	.b_public = (u8[32]){ 0xde, 0x9e, 0xdb, 0x7d, 0x7b, 0x7d, 0xc1, 0xb4,
+		    0xd3, 0x5b, 0x61, 0xc2, 0xec, 0xe4, 0x35, 0x37,
+		    0x3f, 0x83, 0x43, 0xc8, 0x5b, 0x78, 0x67, 0x4d,
+		    0xad, 0xfc, 0x7e, 0x14, 0x6f, 0x88, 0x2b, 0x4f },
+	.expected_ss = (u8[32]){ 0x4a, 0x5d, 0x9d, 0x5b, 0xa4, 0xce, 0x2d, 0xe1,
+		    0x72, 0x8e, 0x3b, 0xf4, 0x80, 0x35, 0x0f, 0x25,
+		    0xe0, 0x7e, 0x21, 0xc9, 0x47, 0xd1, 0x9e, 0x33,
+		    0x76, 0xf0, 0x9b, 0x3c, 0x1e, 0x16, 0x17, 0x42 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+{
+	.secret = (u8[32]){ 0x5d, 0xab, 0x08, 0x7e, 0x62, 0x4a, 0x8a, 0x4b,
+		     0x79, 0xe1, 0x7f, 0x8b, 0x83, 0x80, 0x0e, 0xe6,
+		     0x6f, 0x3b, 0xb1, 0x29, 0x26, 0x18, 0xb6, 0xfd,
+		     0x1c, 0x2f, 0x8b, 0x27, 0xff, 0x88, 0xe0, 0xeb },
+	.b_public = (u8[32]){ 0x85, 0x20, 0xf0, 0x09, 0x89, 0x30, 0xa7, 0x54,
+		    0x74, 0x8b, 0x7d, 0xdc, 0xb4, 0x3e, 0xf7, 0x5a,
+		    0x0d, 0xbf, 0x3a, 0x0d, 0x26, 0x38, 0x1a, 0xf4,
+		    0xeb, 0xa4, 0xa9, 0x8e, 0xaa, 0x9b, 0x4e, 0x6a },
+	.expected_ss = (u8[32]){ 0x4a, 0x5d, 0x9d, 0x5b, 0xa4, 0xce, 0x2d, 0xe1,
+		    0x72, 0x8e, 0x3b, 0xf4, 0x80, 0x35, 0x0f, 0x25,
+		    0xe0, 0x7e, 0x21, 0xc9, 0x47, 0xd1, 0x9e, 0x33,
+		    0x76, 0xf0, 0x9b, 0x3c, 0x1e, 0x16, 0x17, 0x42 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+{
+	.secret = (u8[32]){ 1 },
+	.b_public = (u8[32]){ 0x25, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 },
+	.expected_ss = (u8[32]){ 0x3c, 0x77, 0x77, 0xca, 0xf9, 0x97, 0xb2, 0x64,
+		    0x41, 0x60, 0x77, 0x66, 0x5b, 0x4e, 0x22, 0x9d,
+		    0x0b, 0x95, 0x48, 0xdc, 0x0c, 0xd8, 0x19, 0x98,
+		    0xdd, 0xcd, 0xc5, 0xc8, 0x53, 0x3c, 0x79, 0x7f },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+{
+	.secret = (u8[32]){ 1 },
+	.b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
+	.expected_ss = (u8[32]){ 0xb3, 0x2d, 0x13, 0x62, 0xc2, 0x48, 0xd6, 0x2f,
+		    0xe6, 0x26, 0x19, 0xcf, 0xf0, 0x4d, 0xd4, 0x3d,
+		    0xb7, 0x3f, 0xfc, 0x1b, 0x63, 0x08, 0xed, 0xe3,
+		    0x0b, 0x78, 0xd8, 0x73, 0x80, 0xf1, 0xe8, 0x34 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+{
+	.secret = (u8[32]){ 0xa5, 0x46, 0xe3, 0x6b, 0xf0, 0x52, 0x7c, 0x9d,
+		     0x3b, 0x16, 0x15, 0x4b, 0x82, 0x46, 0x5e, 0xdd,
+		     0x62, 0x14, 0x4c, 0x0a, 0xc1, 0xfc, 0x5a, 0x18,
+		     0x50, 0x6a, 0x22, 0x44, 0xba, 0x44, 0x9a, 0xc4 },
+	.b_public = (u8[32]){ 0xe6, 0xdb, 0x68, 0x67, 0x58, 0x30, 0x30, 0xdb,
+		    0x35, 0x94, 0xc1, 0xa4, 0x24, 0xb1, 0x5f, 0x7c,
+		    0x72, 0x66, 0x24, 0xec, 0x26, 0xb3, 0x35, 0x3b,
+		    0x10, 0xa9, 0x03, 0xa6, 0xd0, 0xab, 0x1c, 0x4c },
+	.expected_ss = (u8[32]){ 0xc3, 0xda, 0x55, 0x37, 0x9d, 0xe9, 0xc6, 0x90,
+		    0x8e, 0x94, 0xea, 0x4d, 0xf2, 0x8d, 0x08, 0x4f,
+		    0x32, 0xec, 0xcf, 0x03, 0x49, 0x1c, 0x71, 0xf7,
+		    0x54, 0xb4, 0x07, 0x55, 0x77, 0xa2, 0x85, 0x52 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+{
+	.secret = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0x0a, 0xff, 0xff, 0xff,
+		     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
+	.b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0x0a, 0x00, 0xfb, 0x9f },
+	.expected_ss = (u8[32]){ 0x77, 0x52, 0xb6, 0x18, 0xc1, 0x2d, 0x48, 0xd2,
+		    0xc6, 0x93, 0x46, 0x83, 0x81, 0x7c, 0xc6, 0x57,
+		    0xf3, 0x31, 0x03, 0x19, 0x49, 0x48, 0x20, 0x05,
+		    0x42, 0x2b, 0x4e, 0xae, 0x8d, 0x1d, 0x43, 0x23 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+{
+	.secret = (u8[32]){ 0x8e, 0x0a, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		     0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		     0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		     0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 },
+	.b_public = (u8[32]){ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x8e, 0x06 },
+	.expected_ss = (u8[32]){ 0x5a, 0xdf, 0xaa, 0x25, 0x86, 0x8e, 0x32, 0x3d,
+		    0xae, 0x49, 0x62, 0xc1, 0x01, 0x5c, 0xb3, 0x12,
+		    0xe1, 0xc5, 0xc7, 0x9e, 0x95, 0x3f, 0x03, 0x99,
+		    0xb0, 0xba, 0x16, 0x22, 0xf3, 0xb6, 0xf7, 0x0c },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - normal case */
+{
+	.secret = (u8[32]){ 0x48, 0x52, 0x83, 0x4d, 0x9d, 0x6b, 0x77, 0xda,
+		     0xde, 0xab, 0xaa, 0xf2, 0xe1, 0x1d, 0xca, 0x66,
+		     0xd1, 0x9f, 0xe7, 0x49, 0x93, 0xa7, 0xbe, 0xc3,
+		     0x6c, 0x6e, 0x16, 0xa0, 0x98, 0x3f, 0xea, 0xba },
+	.b_public = (u8[32]){ 0x9c, 0x64, 0x7d, 0x9a, 0xe5, 0x89, 0xb9, 0xf5,
+		    0x8f, 0xdc, 0x3c, 0xa4, 0x94, 0x7e, 0xfb, 0xc9,
+		    0x15, 0xc4, 0xb2, 0xe0, 0x8e, 0x74, 0x4a, 0x0e,
+		    0xdf, 0x46, 0x9d, 0xac, 0x59, 0xc8, 0xf8, 0x5a },
+	.expected_ss = (u8[32]){ 0x87, 0xb7, 0xf2, 0x12, 0xb6, 0x27, 0xf7, 0xa5,
+		    0x4c, 0xa5, 0xe0, 0xbc, 0xda, 0xdd, 0xd5, 0x38,
+		    0x9d, 0x9d, 0xe6, 0x15, 0x6c, 0xdb, 0xcf, 0x8e,
+		    0xbe, 0x14, 0xff, 0xbc, 0xfb, 0x43, 0x65, 0x51 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key on twist */
+{
+	.secret = (u8[32]){ 0x58, 0x8c, 0x06, 0x1a, 0x50, 0x80, 0x4a, 0xc4,
+		     0x88, 0xad, 0x77, 0x4a, 0xc7, 0x16, 0xc3, 0xf5,
+		     0xba, 0x71, 0x4b, 0x27, 0x12, 0xe0, 0x48, 0x49,
+		     0x13, 0x79, 0xa5, 0x00, 0x21, 0x19, 0x98, 0xa8 },
+	.b_public = (u8[32]){ 0x63, 0xaa, 0x40, 0xc6, 0xe3, 0x83, 0x46, 0xc5,
+		    0xca, 0xf2, 0x3a, 0x6d, 0xf0, 0xa5, 0xe6, 0xc8,
+		    0x08, 0x89, 0xa0, 0x86, 0x47, 0xe5, 0x51, 0xb3,
+		    0x56, 0x34, 0x49, 0xbe, 0xfc, 0xfc, 0x97, 0x33 },
+	.expected_ss = (u8[32]){ 0xb1, 0xa7, 0x07, 0x51, 0x94, 0x95, 0xff, 0xff,
+		    0xb2, 0x98, 0xff, 0x94, 0x17, 0x16, 0xb0, 0x6d,
+		    0xfa, 0xb8, 0x7c, 0xf8, 0xd9, 0x11, 0x23, 0xfe,
+		    0x2b, 0xe9, 0xa2, 0x33, 0xdd, 0xa2, 0x22, 0x12 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key on twist */
+{
+	.secret = (u8[32]){ 0xb0, 0x5b, 0xfd, 0x32, 0xe5, 0x53, 0x25, 0xd9,
+		     0xfd, 0x64, 0x8c, 0xb3, 0x02, 0x84, 0x80, 0x39,
+		     0x00, 0x0b, 0x39, 0x0e, 0x44, 0xd5, 0x21, 0xe5,
+		     0x8a, 0xab, 0x3b, 0x29, 0xa6, 0x96, 0x0b, 0xa8 },
+	.b_public = (u8[32]){ 0x0f, 0x83, 0xc3, 0x6f, 0xde, 0xd9, 0xd3, 0x2f,
+		    0xad, 0xf4, 0xef, 0xa3, 0xae, 0x93, 0xa9, 0x0b,
+		    0xb5, 0xcf, 0xa6, 0x68, 0x93, 0xbc, 0x41, 0x2c,
+		    0x43, 0xfa, 0x72, 0x87, 0xdb, 0xb9, 0x97, 0x79 },
+	.expected_ss = (u8[32]){ 0x67, 0xdd, 0x4a, 0x6e, 0x16, 0x55, 0x33, 0x53,
+		    0x4c, 0x0e, 0x3f, 0x17, 0x2e, 0x4a, 0xb8, 0x57,
+		    0x6b, 0xca, 0x92, 0x3a, 0x5f, 0x07, 0xb2, 0xc0,
+		    0x69, 0xb4, 0xc3, 0x10, 0xff, 0x2e, 0x93, 0x5b },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key on twist */
+{
+	.secret = (u8[32]){ 0x70, 0xe3, 0x4b, 0xcb, 0xe1, 0xf4, 0x7f, 0xbc,
+		     0x0f, 0xdd, 0xfd, 0x7c, 0x1e, 0x1a, 0xa5, 0x3d,
+		     0x57, 0xbf, 0xe0, 0xf6, 0x6d, 0x24, 0x30, 0x67,
+		     0xb4, 0x24, 0xbb, 0x62, 0x10, 0xbe, 0xd1, 0x9c },
+	.b_public = (u8[32]){ 0x0b, 0x82, 0x11, 0xa2, 0xb6, 0x04, 0x90, 0x97,
+		    0xf6, 0x87, 0x1c, 0x6c, 0x05, 0x2d, 0x3c, 0x5f,
+		    0xc1, 0xba, 0x17, 0xda, 0x9e, 0x32, 0xae, 0x45,
+		    0x84, 0x03, 0xb0, 0x5b, 0xb2, 0x83, 0x09, 0x2a },
+	.expected_ss = (u8[32]){ 0x4a, 0x06, 0x38, 0xcf, 0xaa, 0x9e, 0xf1, 0x93,
+		    0x3b, 0x47, 0xf8, 0x93, 0x92, 0x96, 0xa6, 0xb2,
+		    0x5b, 0xe5, 0x41, 0xef, 0x7f, 0x70, 0xe8, 0x44,
+		    0xc0, 0xbc, 0xc0, 0x0b, 0x13, 0x4d, 0xe6, 0x4a },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key on twist */
+{
+	.secret = (u8[32]){ 0x68, 0xc1, 0xf3, 0xa6, 0x53, 0xa4, 0xcd, 0xb1,
+		     0xd3, 0x7b, 0xba, 0x94, 0x73, 0x8f, 0x8b, 0x95,
+		     0x7a, 0x57, 0xbe, 0xb2, 0x4d, 0x64, 0x6e, 0x99,
+		     0x4d, 0xc2, 0x9a, 0x27, 0x6a, 0xad, 0x45, 0x8d },
+	.b_public = (u8[32]){ 0x34, 0x3a, 0xc2, 0x0a, 0x3b, 0x9c, 0x6a, 0x27,
+		    0xb1, 0x00, 0x81, 0x76, 0x50, 0x9a, 0xd3, 0x07,
+		    0x35, 0x85, 0x6e, 0xc1, 0xc8, 0xd8, 0xfc, 0xae,
+		    0x13, 0x91, 0x2d, 0x08, 0xd1, 0x52, 0xf4, 0x6c },
+	.expected_ss = (u8[32]){ 0x39, 0x94, 0x91, 0xfc, 0xe8, 0xdf, 0xab, 0x73,
+		    0xb4, 0xf9, 0xf6, 0x11, 0xde, 0x8e, 0xa0, 0xb2,
+		    0x7b, 0x28, 0xf8, 0x59, 0x94, 0x25, 0x0b, 0x0f,
+		    0x47, 0x5d, 0x58, 0x5d, 0x04, 0x2a, 0xc2, 0x07 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key on twist */
+{
+	.secret = (u8[32]){ 0xd8, 0x77, 0xb2, 0x6d, 0x06, 0xdf, 0xf9, 0xd9,
+		     0xf7, 0xfd, 0x4c, 0x5b, 0x37, 0x69, 0xf8, 0xcd,
+		     0xd5, 0xb3, 0x05, 0x16, 0xa5, 0xab, 0x80, 0x6b,
+		     0xe3, 0x24, 0xff, 0x3e, 0xb6, 0x9e, 0xa0, 0xb2 },
+	.b_public = (u8[32]){ 0xfa, 0x69, 0x5f, 0xc7, 0xbe, 0x8d, 0x1b, 0xe5,
+		    0xbf, 0x70, 0x48, 0x98, 0xf3, 0x88, 0xc4, 0x52,
+		    0xba, 0xfd, 0xd3, 0xb8, 0xea, 0xe8, 0x05, 0xf8,
+		    0x68, 0x1a, 0x8d, 0x15, 0xc2, 0xd4, 0xe1, 0x42 },
+	.expected_ss = (u8[32]){ 0x2c, 0x4f, 0xe1, 0x1d, 0x49, 0x0a, 0x53, 0x86,
+		    0x17, 0x76, 0xb1, 0x3b, 0x43, 0x54, 0xab, 0xd4,
+		    0xcf, 0x5a, 0x97, 0x69, 0x9d, 0xb6, 0xe6, 0xc6,
+		    0x8c, 0x16, 0x26, 0xd0, 0x76, 0x62, 0xf7, 0x58 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case on twist */
+{
+	.secret = (u8[32]){ 0x38, 0xdd, 0xe9, 0xf3, 0xe7, 0xb7, 0x99, 0x04,
+		     0x5f, 0x9a, 0xc3, 0x79, 0x3d, 0x4a, 0x92, 0x77,
+		     0xda, 0xde, 0xad, 0xc4, 0x1b, 0xec, 0x02, 0x90,
+		     0xf8, 0x1f, 0x74, 0x4f, 0x73, 0x77, 0x5f, 0x84 },
+	.b_public = (u8[32]){ 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 },
+	.expected_ss = (u8[32]){ 0x9a, 0x2c, 0xfe, 0x84, 0xff, 0x9c, 0x4a, 0x97,
+		    0x39, 0x62, 0x5c, 0xae, 0x4a, 0x3b, 0x82, 0xa9,
+		    0x06, 0x87, 0x7a, 0x44, 0x19, 0x46, 0xf8, 0xd7,
+		    0xb3, 0xd7, 0x95, 0xfe, 0x8f, 0x5d, 0x16, 0x39 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case on twist */
+{
+	.secret = (u8[32]){ 0x98, 0x57, 0xa9, 0x14, 0xe3, 0xc2, 0x90, 0x36,
+		     0xfd, 0x9a, 0x44, 0x2b, 0xa5, 0x26, 0xb5, 0xcd,
+		     0xcd, 0xf2, 0x82, 0x16, 0x15, 0x3e, 0x63, 0x6c,
+		     0x10, 0x67, 0x7a, 0xca, 0xb6, 0xbd, 0x6a, 0xa5 },
+	.b_public = (u8[32]){ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 },
+	.expected_ss = (u8[32]){ 0x4d, 0xa4, 0xe0, 0xaa, 0x07, 0x2c, 0x23, 0x2e,
+		    0xe2, 0xf0, 0xfa, 0x4e, 0x51, 0x9a, 0xe5, 0x0b,
+		    0x52, 0xc1, 0xed, 0xd0, 0x8a, 0x53, 0x4d, 0x4e,
+		    0xf3, 0x46, 0xc2, 0xe1, 0x06, 0xd2, 0x1d, 0x60 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case on twist */
+{
+	.secret = (u8[32]){ 0x48, 0xe2, 0x13, 0x0d, 0x72, 0x33, 0x05, 0xed,
+		     0x05, 0xe6, 0xe5, 0x89, 0x4d, 0x39, 0x8a, 0x5e,
+		     0x33, 0x36, 0x7a, 0x8c, 0x6a, 0xac, 0x8f, 0xcd,
+		     0xf0, 0xa8, 0x8e, 0x4b, 0x42, 0x82, 0x0d, 0xb7 },
+	.b_public = (u8[32]){ 0xff, 0xff, 0xff, 0x03, 0x00, 0x00, 0xf8, 0xff,
+		    0xff, 0x1f, 0x00, 0x00, 0xc0, 0xff, 0xff, 0xff,
+		    0x00, 0x00, 0x00, 0xfe, 0xff, 0xff, 0x07, 0x00,
+		    0x00, 0xf0, 0xff, 0xff, 0x3f, 0x00, 0x00, 0x00 },
+	.expected_ss = (u8[32]){ 0x9e, 0xd1, 0x0c, 0x53, 0x74, 0x7f, 0x64, 0x7f,
+		    0x82, 0xf4, 0x51, 0x25, 0xd3, 0xde, 0x15, 0xa1,
+		    0xe6, 0xb8, 0x24, 0x49, 0x6a, 0xb4, 0x04, 0x10,
+		    0xff, 0xcc, 0x3c, 0xfe, 0x95, 0x76, 0x0f, 0x3b },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case on twist */
+{
+	.secret = (u8[32]){ 0x28, 0xf4, 0x10, 0x11, 0x69, 0x18, 0x51, 0xb3,
+		     0xa6, 0x2b, 0x64, 0x15, 0x53, 0xb3, 0x0d, 0x0d,
+		     0xfd, 0xdc, 0xb8, 0xff, 0xfc, 0xf5, 0x37, 0x00,
+		     0xa7, 0xbe, 0x2f, 0x6a, 0x87, 0x2e, 0x9f, 0xb0 },
+	.b_public = (u8[32]){ 0x00, 0x00, 0x00, 0xfc, 0xff, 0xff, 0x07, 0x00,
+		    0x00, 0xe0, 0xff, 0xff, 0x3f, 0x00, 0x00, 0x00,
+		    0xff, 0xff, 0xff, 0x01, 0x00, 0x00, 0xf8, 0xff,
+		    0xff, 0x0f, 0x00, 0x00, 0xc0, 0xff, 0xff, 0x7f },
+	.expected_ss = (u8[32]){ 0xcf, 0x72, 0xb4, 0xaa, 0x6a, 0xa1, 0xc9, 0xf8,
+		    0x94, 0xf4, 0x16, 0x5b, 0x86, 0x10, 0x9a, 0xa4,
+		    0x68, 0x51, 0x76, 0x48, 0xe1, 0xf0, 0xcc, 0x70,
+		    0xe1, 0xab, 0x08, 0x46, 0x01, 0x76, 0x50, 0x6b },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case on twist */
+{
+	.secret = (u8[32]){ 0x18, 0xa9, 0x3b, 0x64, 0x99, 0xb9, 0xf6, 0xb3,
+		     0x22, 0x5c, 0xa0, 0x2f, 0xef, 0x41, 0x0e, 0x0a,
+		     0xde, 0xc2, 0x35, 0x32, 0x32, 0x1d, 0x2d, 0x8e,
+		     0xf1, 0xa6, 0xd6, 0x02, 0xa8, 0xc6, 0x5b, 0x83 },
+	.b_public = (u8[32]){ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+		    0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+		    0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+		    0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0x7f },
+	.expected_ss = (u8[32]){ 0x5d, 0x50, 0xb6, 0x28, 0x36, 0xbb, 0x69, 0x57,
+		    0x94, 0x10, 0x38, 0x6c, 0xf7, 0xbb, 0x81, 0x1c,
+		    0x14, 0xbf, 0x85, 0xb1, 0xc7, 0xb1, 0x7e, 0x59,
+		    0x24, 0xc7, 0xff, 0xea, 0x91, 0xef, 0x9e, 0x12 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case on twist */
+{
+	.secret = (u8[32]){ 0xc0, 0x1d, 0x13, 0x05, 0xa1, 0x33, 0x8a, 0x1f,
+		     0xca, 0xc2, 0xba, 0x7e, 0x2e, 0x03, 0x2b, 0x42,
+		     0x7e, 0x0b, 0x04, 0x90, 0x31, 0x65, 0xac, 0xa9,
+		     0x57, 0xd8, 0xd0, 0x55, 0x3d, 0x87, 0x17, 0xb0 },
+	.b_public = (u8[32]){ 0xea, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f },
+	.expected_ss = (u8[32]){ 0x19, 0x23, 0x0e, 0xb1, 0x48, 0xd5, 0xd6, 0x7c,
+		    0x3c, 0x22, 0xab, 0x1d, 0xae, 0xff, 0x80, 0xa5,
+		    0x7e, 0xae, 0x42, 0x65, 0xce, 0x28, 0x72, 0x65,
+		    0x7b, 0x2c, 0x80, 0x99, 0xfc, 0x69, 0x8e, 0x50 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for public key */
+{
+	.secret = (u8[32]){ 0x38, 0x6f, 0x7f, 0x16, 0xc5, 0x07, 0x31, 0xd6,
+		     0x4f, 0x82, 0xe6, 0xa1, 0x70, 0xb1, 0x42, 0xa4,
+		     0xe3, 0x4f, 0x31, 0xfd, 0x77, 0x68, 0xfc, 0xb8,
+		     0x90, 0x29, 0x25, 0xe7, 0xd1, 0xe2, 0x1a, 0xbe },
+	.b_public = (u8[32]){ 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 },
+	.expected_ss = (u8[32]){ 0x0f, 0xca, 0xb5, 0xd8, 0x42, 0xa0, 0x78, 0xd7,
+		    0xa7, 0x1f, 0xc5, 0x9b, 0x57, 0xbf, 0xb4, 0xca,
+		    0x0b, 0xe6, 0x87, 0x3b, 0x49, 0xdc, 0xdb, 0x9f,
+		    0x44, 0xe1, 0x4a, 0xe8, 0xfb, 0xdf, 0xa5, 0x42 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for public key */
+{
+	.secret = (u8[32]){ 0xe0, 0x23, 0xa2, 0x89, 0xbd, 0x5e, 0x90, 0xfa,
+		     0x28, 0x04, 0xdd, 0xc0, 0x19, 0xa0, 0x5e, 0xf3,
+		     0xe7, 0x9d, 0x43, 0x4b, 0xb6, 0xea, 0x2f, 0x52,
+		     0x2e, 0xcb, 0x64, 0x3a, 0x75, 0x29, 0x6e, 0x95 },
+	.b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+		    0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+		    0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+		    0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 },
+	.expected_ss = (u8[32]){ 0x54, 0xce, 0x8f, 0x22, 0x75, 0xc0, 0x77, 0xe3,
+		    0xb1, 0x30, 0x6a, 0x39, 0x39, 0xc5, 0xe0, 0x3e,
+		    0xef, 0x6b, 0xbb, 0x88, 0x06, 0x05, 0x44, 0x75,
+		    0x8d, 0x9f, 0xef, 0x59, 0xb0, 0xbc, 0x3e, 0x4f },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for public key */
+{
+	.secret = (u8[32]){ 0x68, 0xf0, 0x10, 0xd6, 0x2e, 0xe8, 0xd9, 0x26,
+		     0x05, 0x3a, 0x36, 0x1c, 0x3a, 0x75, 0xc6, 0xea,
+		     0x4e, 0xbd, 0xc8, 0x60, 0x6a, 0xb2, 0x85, 0x00,
+		     0x3a, 0x6f, 0x8f, 0x40, 0x76, 0xb0, 0x1e, 0x83 },
+	.b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x03 },
+	.expected_ss = (u8[32]){ 0xf1, 0x36, 0x77, 0x5c, 0x5b, 0xeb, 0x0a, 0xf8,
+		    0x11, 0x0a, 0xf1, 0x0b, 0x20, 0x37, 0x23, 0x32,
+		    0x04, 0x3c, 0xab, 0x75, 0x24, 0x19, 0x67, 0x87,
+		    0x75, 0xa2, 0x23, 0xdf, 0x57, 0xc9, 0xd3, 0x0d },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for public key */
+{
+	.secret = (u8[32]){ 0x58, 0xeb, 0xcb, 0x35, 0xb0, 0xf8, 0x84, 0x5c,
+		     0xaf, 0x1e, 0xc6, 0x30, 0xf9, 0x65, 0x76, 0xb6,
+		     0x2c, 0x4b, 0x7b, 0x6c, 0x36, 0xb2, 0x9d, 0xeb,
+		     0x2c, 0xb0, 0x08, 0x46, 0x51, 0x75, 0x5c, 0x96 },
+	.b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xfb, 0xff, 0xff, 0xfb, 0xff,
+		    0xff, 0xdf, 0xff, 0xff, 0xdf, 0xff, 0xff, 0xff,
+		    0xfe, 0xff, 0xff, 0xfe, 0xff, 0xff, 0xf7, 0xff,
+		    0xff, 0xf7, 0xff, 0xff, 0xbf, 0xff, 0xff, 0x3f },
+	.expected_ss = (u8[32]){ 0xbf, 0x9a, 0xff, 0xd0, 0x6b, 0x84, 0x40, 0x85,
+		    0x58, 0x64, 0x60, 0x96, 0x2e, 0xf2, 0x14, 0x6f,
+		    0xf3, 0xd4, 0x53, 0x3d, 0x94, 0x44, 0xaa, 0xb0,
+		    0x06, 0xeb, 0x88, 0xcc, 0x30, 0x54, 0x40, 0x7d },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for public key */
+{
+	.secret = (u8[32]){ 0x18, 0x8c, 0x4b, 0xc5, 0xb9, 0xc4, 0x4b, 0x38,
+		     0xbb, 0x65, 0x8b, 0x9b, 0x2a, 0xe8, 0x2d, 0x5b,
+		     0x01, 0x01, 0x5e, 0x09, 0x31, 0x84, 0xb1, 0x7c,
+		     0xb7, 0x86, 0x35, 0x03, 0xa7, 0x83, 0xe1, 0xbb },
+	.b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f },
+	.expected_ss = (u8[32]){ 0xd4, 0x80, 0xde, 0x04, 0xf6, 0x99, 0xcb, 0x3b,
+		    0xe0, 0x68, 0x4a, 0x9c, 0xc2, 0xe3, 0x12, 0x81,
+		    0xea, 0x0b, 0xc5, 0xa9, 0xdc, 0xc1, 0x57, 0xd3,
+		    0xd2, 0x01, 0x58, 0xd4, 0x6c, 0xa5, 0x24, 0x6d },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for public key */
+{
+	.secret = (u8[32]){ 0xe0, 0x6c, 0x11, 0xbb, 0x2e, 0x13, 0xce, 0x3d,
+		     0xc7, 0x67, 0x3f, 0x67, 0xf5, 0x48, 0x22, 0x42,
+		     0x90, 0x94, 0x23, 0xa9, 0xae, 0x95, 0xee, 0x98,
+		     0x6a, 0x98, 0x8d, 0x98, 0xfa, 0xee, 0x23, 0xa2 },
+	.b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xfe, 0xff, 0xff, 0x7f,
+		    0xff, 0xff, 0xff, 0xff, 0xfe, 0xff, 0xff, 0x7f,
+		    0xff, 0xff, 0xff, 0xff, 0xfe, 0xff, 0xff, 0x7f,
+		    0xff, 0xff, 0xff, 0xff, 0xfe, 0xff, 0xff, 0x7f },
+	.expected_ss = (u8[32]){ 0x4c, 0x44, 0x01, 0xcc, 0xe6, 0xb5, 0x1e, 0x4c,
+		    0xb1, 0x8f, 0x27, 0x90, 0x24, 0x6c, 0x9b, 0xf9,
+		    0x14, 0xdb, 0x66, 0x77, 0x50, 0xa1, 0xcb, 0x89,
+		    0x06, 0x90, 0x92, 0xaf, 0x07, 0x29, 0x22, 0x76 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for public key */
+{
+	.secret = (u8[32]){ 0xc0, 0x65, 0x8c, 0x46, 0xdd, 0xe1, 0x81, 0x29,
+		     0x29, 0x38, 0x77, 0x53, 0x5b, 0x11, 0x62, 0xb6,
+		     0xf9, 0xf5, 0x41, 0x4a, 0x23, 0xcf, 0x4d, 0x2c,
+		     0xbc, 0x14, 0x0a, 0x4d, 0x99, 0xda, 0x2b, 0x8f },
+	.b_public = (u8[32]){ 0xeb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f },
+	.expected_ss = (u8[32]){ 0x57, 0x8b, 0xa8, 0xcc, 0x2d, 0xbd, 0xc5, 0x75,
+		    0xaf, 0xcf, 0x9d, 0xf2, 0xb3, 0xee, 0x61, 0x89,
+		    0xf5, 0x33, 0x7d, 0x68, 0x54, 0xc7, 0x9b, 0x4c,
+		    0xe1, 0x65, 0xea, 0x12, 0x29, 0x3b, 0x3a, 0x0f },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0xf0, 0x1e, 0x48, 0xda, 0xfa, 0xc9, 0xd7, 0xbc,
+		     0xf5, 0x89, 0xcb, 0xc3, 0x82, 0xc8, 0x78, 0xd1,
+		     0x8b, 0xda, 0x35, 0x50, 0x58, 0x9f, 0xfb, 0x5d,
+		     0x50, 0xb5, 0x23, 0xbe, 0xbe, 0x32, 0x9d, 0xae },
+	.b_public = (u8[32]){ 0xef, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f },
+	.expected_ss = (u8[32]){ 0xbd, 0x36, 0xa0, 0x79, 0x0e, 0xb8, 0x83, 0x09,
+		    0x8c, 0x98, 0x8b, 0x21, 0x78, 0x67, 0x73, 0xde,
+		    0x0b, 0x3a, 0x4d, 0xf1, 0x62, 0x28, 0x2c, 0xf1,
+		    0x10, 0xde, 0x18, 0xdd, 0x48, 0x4c, 0xe7, 0x4b },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0x28, 0x87, 0x96, 0xbc, 0x5a, 0xff, 0x4b, 0x81,
+		     0xa3, 0x75, 0x01, 0x75, 0x7b, 0xc0, 0x75, 0x3a,
+		     0x3c, 0x21, 0x96, 0x47, 0x90, 0xd3, 0x86, 0x99,
+		     0x30, 0x8d, 0xeb, 0xc1, 0x7a, 0x6e, 0xaf, 0x8d },
+	.b_public = (u8[32]){ 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f },
+	.expected_ss = (u8[32]){ 0xb4, 0xe0, 0xdd, 0x76, 0xda, 0x7b, 0x07, 0x17,
+		    0x28, 0xb6, 0x1f, 0x85, 0x67, 0x71, 0xaa, 0x35,
+		    0x6e, 0x57, 0xed, 0xa7, 0x8a, 0x5b, 0x16, 0x55,
+		    0xcc, 0x38, 0x20, 0xfb, 0x5f, 0x85, 0x4c, 0x5c },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0x98, 0xdf, 0x84, 0x5f, 0x66, 0x51, 0xbf, 0x11,
+		     0x38, 0x22, 0x1f, 0x11, 0x90, 0x41, 0xf7, 0x2b,
+		     0x6d, 0xbc, 0x3c, 0x4a, 0xce, 0x71, 0x43, 0xd9,
+		     0x9f, 0xd5, 0x5a, 0xd8, 0x67, 0x48, 0x0d, 0xa8 },
+	.b_public = (u8[32]){ 0xf1, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f },
+	.expected_ss = (u8[32]){ 0x6f, 0xdf, 0x6c, 0x37, 0x61, 0x1d, 0xbd, 0x53,
+		    0x04, 0xdc, 0x0f, 0x2e, 0xb7, 0xc9, 0x51, 0x7e,
+		    0xb3, 0xc5, 0x0e, 0x12, 0xfd, 0x05, 0x0a, 0xc6,
+		    0xde, 0xc2, 0x70, 0x71, 0xd4, 0xbf, 0xc0, 0x34 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0xf0, 0x94, 0x98, 0xe4, 0x6f, 0x02, 0xf8, 0x78,
+		     0x82, 0x9e, 0x78, 0xb8, 0x03, 0xd3, 0x16, 0xa2,
+		     0xed, 0x69, 0x5d, 0x04, 0x98, 0xa0, 0x8a, 0xbd,
+		     0xf8, 0x27, 0x69, 0x30, 0xe2, 0x4e, 0xdc, 0xb0 },
+	.b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f },
+	.expected_ss = (u8[32]){ 0x4c, 0x8f, 0xc4, 0xb1, 0xc6, 0xab, 0x88, 0xfb,
+		    0x21, 0xf1, 0x8f, 0x6d, 0x4c, 0x81, 0x02, 0x40,
+		    0xd4, 0xe9, 0x46, 0x51, 0xba, 0x44, 0xf7, 0xa2,
+		    0xc8, 0x63, 0xce, 0xc7, 0xdc, 0x56, 0x60, 0x2d },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0x18, 0x13, 0xc1, 0x0a, 0x5c, 0x7f, 0x21, 0xf9,
+		     0x6e, 0x17, 0xf2, 0x88, 0xc0, 0xcc, 0x37, 0x60,
+		     0x7c, 0x04, 0xc5, 0xf5, 0xae, 0xa2, 0xdb, 0x13,
+		     0x4f, 0x9e, 0x2f, 0xfc, 0x66, 0xbd, 0x9d, 0xb8 },
+	.b_public = (u8[32]){ 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80 },
+	.expected_ss = (u8[32]){ 0x1c, 0xd0, 0xb2, 0x82, 0x67, 0xdc, 0x54, 0x1c,
+		    0x64, 0x2d, 0x6d, 0x7d, 0xca, 0x44, 0xa8, 0xb3,
+		    0x8a, 0x63, 0x73, 0x6e, 0xef, 0x5c, 0x4e, 0x65,
+		    0x01, 0xff, 0xbb, 0xb1, 0x78, 0x0c, 0x03, 0x3c },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0x78, 0x57, 0xfb, 0x80, 0x86, 0x53, 0x64, 0x5a,
+		     0x0b, 0xeb, 0x13, 0x8a, 0x64, 0xf5, 0xf4, 0xd7,
+		     0x33, 0xa4, 0x5e, 0xa8, 0x4c, 0x3c, 0xda, 0x11,
+		     0xa9, 0xc0, 0x6f, 0x7e, 0x71, 0x39, 0x14, 0x9e },
+	.b_public = (u8[32]){ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80 },
+	.expected_ss = (u8[32]){ 0x87, 0x55, 0xbe, 0x01, 0xc6, 0x0a, 0x7e, 0x82,
+		    0x5c, 0xff, 0x3e, 0x0e, 0x78, 0xcb, 0x3a, 0xa4,
+		    0x33, 0x38, 0x61, 0x51, 0x6a, 0xa5, 0x9b, 0x1c,
+		    0x51, 0xa8, 0xb2, 0xa5, 0x43, 0xdf, 0xa8, 0x22 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0xe0, 0x3a, 0xa8, 0x42, 0xe2, 0xab, 0xc5, 0x6e,
+		     0x81, 0xe8, 0x7b, 0x8b, 0x9f, 0x41, 0x7b, 0x2a,
+		     0x1e, 0x59, 0x13, 0xc7, 0x23, 0xee, 0xd2, 0x8d,
+		     0x75, 0x2f, 0x8d, 0x47, 0xa5, 0x9f, 0x49, 0x8f },
+	.b_public = (u8[32]){ 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80 },
+	.expected_ss = (u8[32]){ 0x54, 0xc9, 0xa1, 0xed, 0x95, 0xe5, 0x46, 0xd2,
+		    0x78, 0x22, 0xa3, 0x60, 0x93, 0x1d, 0xda, 0x60,
+		    0xa1, 0xdf, 0x04, 0x9d, 0xa6, 0xf9, 0x04, 0x25,
+		    0x3c, 0x06, 0x12, 0xbb, 0xdc, 0x08, 0x74, 0x76 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0xf8, 0xf7, 0x07, 0xb7, 0x99, 0x9b, 0x18, 0xcb,
+		     0x0d, 0x6b, 0x96, 0x12, 0x4f, 0x20, 0x45, 0x97,
+		     0x2c, 0xa2, 0x74, 0xbf, 0xc1, 0x54, 0xad, 0x0c,
+		     0x87, 0x03, 0x8c, 0x24, 0xc6, 0xd0, 0xd4, 0xb2 },
+	.b_public = (u8[32]){ 0xda, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
+	.expected_ss = (u8[32]){ 0xcc, 0x1f, 0x40, 0xd7, 0x43, 0xcd, 0xc2, 0x23,
+		    0x0e, 0x10, 0x43, 0xda, 0xba, 0x8b, 0x75, 0xe8,
+		    0x10, 0xf1, 0xfb, 0xab, 0x7f, 0x25, 0x52, 0x69,
+		    0xbd, 0x9e, 0xbb, 0x29, 0xe6, 0xbf, 0x49, 0x4f },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0xa0, 0x34, 0xf6, 0x84, 0xfa, 0x63, 0x1e, 0x1a,
+		     0x34, 0x81, 0x18, 0xc1, 0xce, 0x4c, 0x98, 0x23,
+		     0x1f, 0x2d, 0x9e, 0xec, 0x9b, 0xa5, 0x36, 0x5b,
+		     0x4a, 0x05, 0xd6, 0x9a, 0x78, 0x5b, 0x07, 0x96 },
+	.b_public = (u8[32]){ 0xdb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
+	.expected_ss = (u8[32]){ 0x54, 0x99, 0x8e, 0xe4, 0x3a, 0x5b, 0x00, 0x7b,
+		    0xf4, 0x99, 0xf0, 0x78, 0xe7, 0x36, 0x52, 0x44,
+		    0x00, 0xa8, 0xb5, 0xc7, 0xe9, 0xb9, 0xb4, 0x37,
+		    0x71, 0x74, 0x8c, 0x7c, 0xdf, 0x88, 0x04, 0x12 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0x30, 0xb6, 0xc6, 0xa0, 0xf2, 0xff, 0xa6, 0x80,
+		     0x76, 0x8f, 0x99, 0x2b, 0xa8, 0x9e, 0x15, 0x2d,
+		     0x5b, 0xc9, 0x89, 0x3d, 0x38, 0xc9, 0x11, 0x9b,
+		     0xe4, 0xf7, 0x67, 0xbf, 0xab, 0x6e, 0x0c, 0xa5 },
+	.b_public = (u8[32]){ 0xdc, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
+	.expected_ss = (u8[32]){ 0xea, 0xd9, 0xb3, 0x8e, 0xfd, 0xd7, 0x23, 0x63,
+		    0x79, 0x34, 0xe5, 0x5a, 0xb7, 0x17, 0xa7, 0xae,
+		    0x09, 0xeb, 0x86, 0xa2, 0x1d, 0xc3, 0x6a, 0x3f,
+		    0xee, 0xb8, 0x8b, 0x75, 0x9e, 0x39, 0x1e, 0x09 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0x90, 0x1b, 0x9d, 0xcf, 0x88, 0x1e, 0x01, 0xe0,
+		     0x27, 0x57, 0x50, 0x35, 0xd4, 0x0b, 0x43, 0xbd,
+		     0xc1, 0xc5, 0x24, 0x2e, 0x03, 0x08, 0x47, 0x49,
+		     0x5b, 0x0c, 0x72, 0x86, 0x46, 0x9b, 0x65, 0x91 },
+	.b_public = (u8[32]){ 0xea, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
+	.expected_ss = (u8[32]){ 0x60, 0x2f, 0xf4, 0x07, 0x89, 0xb5, 0x4b, 0x41,
+		    0x80, 0x59, 0x15, 0xfe, 0x2a, 0x62, 0x21, 0xf0,
+		    0x7a, 0x50, 0xff, 0xc2, 0xc3, 0xfc, 0x94, 0xcf,
+		    0x61, 0xf1, 0x3d, 0x79, 0x04, 0xe8, 0x8e, 0x0e },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0x80, 0x46, 0x67, 0x7c, 0x28, 0xfd, 0x82, 0xc9,
+		     0xa1, 0xbd, 0xb7, 0x1a, 0x1a, 0x1a, 0x34, 0xfa,
+		     0xba, 0x12, 0x25, 0xe2, 0x50, 0x7f, 0xe3, 0xf5,
+		     0x4d, 0x10, 0xbd, 0x5b, 0x0d, 0x86, 0x5f, 0x8e },
+	.b_public = (u8[32]){ 0xeb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
+	.expected_ss = (u8[32]){ 0xe0, 0x0a, 0xe8, 0xb1, 0x43, 0x47, 0x12, 0x47,
+		    0xba, 0x24, 0xf1, 0x2c, 0x88, 0x55, 0x36, 0xc3,
+		    0xcb, 0x98, 0x1b, 0x58, 0xe1, 0xe5, 0x6b, 0x2b,
+		    0xaf, 0x35, 0xc1, 0x2a, 0xe1, 0xf7, 0x9c, 0x26 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0x60, 0x2f, 0x7e, 0x2f, 0x68, 0xa8, 0x46, 0xb8,
+		     0x2c, 0xc2, 0x69, 0xb1, 0xd4, 0x8e, 0x93, 0x98,
+		     0x86, 0xae, 0x54, 0xfd, 0x63, 0x6c, 0x1f, 0xe0,
+		     0x74, 0xd7, 0x10, 0x12, 0x7d, 0x47, 0x24, 0x91 },
+	.b_public = (u8[32]){ 0xef, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
+	.expected_ss = (u8[32]){ 0x98, 0xcb, 0x9b, 0x50, 0xdd, 0x3f, 0xc2, 0xb0,
+		    0xd4, 0xf2, 0xd2, 0xbf, 0x7c, 0x5c, 0xfd, 0xd1,
+		    0x0c, 0x8f, 0xcd, 0x31, 0xfc, 0x40, 0xaf, 0x1a,
+		    0xd4, 0x4f, 0x47, 0xc1, 0x31, 0x37, 0x63, 0x62 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0x60, 0x88, 0x7b, 0x3d, 0xc7, 0x24, 0x43, 0x02,
+		     0x6e, 0xbe, 0xdb, 0xbb, 0xb7, 0x06, 0x65, 0xf4,
+		     0x2b, 0x87, 0xad, 0xd1, 0x44, 0x0e, 0x77, 0x68,
+		     0xfb, 0xd7, 0xe8, 0xe2, 0xce, 0x5f, 0x63, 0x9d },
+	.b_public = (u8[32]){ 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
+	.expected_ss = (u8[32]){ 0x38, 0xd6, 0x30, 0x4c, 0x4a, 0x7e, 0x6d, 0x9f,
+		    0x79, 0x59, 0x33, 0x4f, 0xb5, 0x24, 0x5b, 0xd2,
+		    0xc7, 0x54, 0x52, 0x5d, 0x4c, 0x91, 0xdb, 0x95,
+		    0x02, 0x06, 0x92, 0x62, 0x34, 0xc1, 0xf6, 0x33 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0x78, 0xd3, 0x1d, 0xfa, 0x85, 0x44, 0x97, 0xd7,
+		     0x2d, 0x8d, 0xef, 0x8a, 0x1b, 0x7f, 0xb0, 0x06,
+		     0xce, 0xc2, 0xd8, 0xc4, 0x92, 0x46, 0x47, 0xc9,
+		     0x38, 0x14, 0xae, 0x56, 0xfa, 0xed, 0xa4, 0x95 },
+	.b_public = (u8[32]){ 0xf1, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
+	.expected_ss = (u8[32]){ 0x78, 0x6c, 0xd5, 0x49, 0x96, 0xf0, 0x14, 0xa5,
+		    0xa0, 0x31, 0xec, 0x14, 0xdb, 0x81, 0x2e, 0xd0,
+		    0x83, 0x55, 0x06, 0x1f, 0xdb, 0x5d, 0xe6, 0x80,
+		    0xa8, 0x00, 0xac, 0x52, 0x1f, 0x31, 0x8e, 0x23 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - public key >= p */
+{
+	.secret = (u8[32]){ 0xc0, 0x4c, 0x5b, 0xae, 0xfa, 0x83, 0x02, 0xdd,
+		     0xde, 0xd6, 0xa4, 0xbb, 0x95, 0x77, 0x61, 0xb4,
+		     0xeb, 0x97, 0xae, 0xfa, 0x4f, 0xc3, 0xb8, 0x04,
+		     0x30, 0x85, 0xf9, 0x6a, 0x56, 0x59, 0xb3, 0xa5 },
+	.b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
+	.expected_ss = (u8[32]){ 0x29, 0xae, 0x8b, 0xc7, 0x3e, 0x9b, 0x10, 0xa0,
+		    0x8b, 0x4f, 0x68, 0x1c, 0x43, 0xc3, 0xe0, 0xac,
+		    0x1a, 0x17, 0x1d, 0x31, 0xb3, 0x8f, 0x1a, 0x48,
+		    0xef, 0xba, 0x29, 0xae, 0x63, 0x9e, 0xa1, 0x34 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - RFC 7748 */
+{
+	.secret = (u8[32]){ 0xa0, 0x46, 0xe3, 0x6b, 0xf0, 0x52, 0x7c, 0x9d,
+		     0x3b, 0x16, 0x15, 0x4b, 0x82, 0x46, 0x5e, 0xdd,
+		     0x62, 0x14, 0x4c, 0x0a, 0xc1, 0xfc, 0x5a, 0x18,
+		     0x50, 0x6a, 0x22, 0x44, 0xba, 0x44, 0x9a, 0x44 },
+	.b_public = (u8[32]){ 0xe6, 0xdb, 0x68, 0x67, 0x58, 0x30, 0x30, 0xdb,
+		    0x35, 0x94, 0xc1, 0xa4, 0x24, 0xb1, 0x5f, 0x7c,
+		    0x72, 0x66, 0x24, 0xec, 0x26, 0xb3, 0x35, 0x3b,
+		    0x10, 0xa9, 0x03, 0xa6, 0xd0, 0xab, 0x1c, 0x4c },
+	.expected_ss = (u8[32]){ 0xc3, 0xda, 0x55, 0x37, 0x9d, 0xe9, 0xc6, 0x90,
+		    0x8e, 0x94, 0xea, 0x4d, 0xf2, 0x8d, 0x08, 0x4f,
+		    0x32, 0xec, 0xcf, 0x03, 0x49, 0x1c, 0x71, 0xf7,
+		    0x54, 0xb4, 0x07, 0x55, 0x77, 0xa2, 0x85, 0x52 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - RFC 7748 */
+{
+	.secret = (u8[32]){ 0x48, 0x66, 0xe9, 0xd4, 0xd1, 0xb4, 0x67, 0x3c,
+		     0x5a, 0xd2, 0x26, 0x91, 0x95, 0x7d, 0x6a, 0xf5,
+		     0xc1, 0x1b, 0x64, 0x21, 0xe0, 0xea, 0x01, 0xd4,
+		     0x2c, 0xa4, 0x16, 0x9e, 0x79, 0x18, 0xba, 0x4d },
+	.b_public = (u8[32]){ 0xe5, 0x21, 0x0f, 0x12, 0x78, 0x68, 0x11, 0xd3,
+		    0xf4, 0xb7, 0x95, 0x9d, 0x05, 0x38, 0xae, 0x2c,
+		    0x31, 0xdb, 0xe7, 0x10, 0x6f, 0xc0, 0x3c, 0x3e,
+		    0xfc, 0x4c, 0xd5, 0x49, 0xc7, 0x15, 0xa4, 0x13 },
+	.expected_ss = (u8[32]){ 0x95, 0xcb, 0xde, 0x94, 0x76, 0xe8, 0x90, 0x7d,
+		    0x7a, 0xad, 0xe4, 0x5c, 0xb4, 0xb8, 0x73, 0xf8,
+		    0x8b, 0x59, 0x5a, 0x68, 0x79, 0x9f, 0xa1, 0x52,
+		    0xe6, 0xf8, 0xf7, 0x64, 0x7a, 0xac, 0x79, 0x57 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for shared secret */
+{
+	.secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4,
+		     0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3,
+		     0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc,
+		     0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 },
+	.b_public = (u8[32]){ 0x0a, 0xb4, 0xe7, 0x63, 0x80, 0xd8, 0x4d, 0xde,
+		    0x4f, 0x68, 0x33, 0xc5, 0x8f, 0x2a, 0x9f, 0xb8,
+		    0xf8, 0x3b, 0xb0, 0x16, 0x9b, 0x17, 0x2b, 0xe4,
+		    0xb6, 0xe0, 0x59, 0x28, 0x87, 0x74, 0x1a, 0x36 },
+	.expected_ss = (u8[32]){ 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for shared secret */
+{
+	.secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4,
+		     0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3,
+		     0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc,
+		     0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 },
+	.b_public = (u8[32]){ 0x89, 0xe1, 0x0d, 0x57, 0x01, 0xb4, 0x33, 0x7d,
+		    0x2d, 0x03, 0x21, 0x81, 0x53, 0x8b, 0x10, 0x64,
+		    0xbd, 0x40, 0x84, 0x40, 0x1c, 0xec, 0xa1, 0xfd,
+		    0x12, 0x66, 0x3a, 0x19, 0x59, 0x38, 0x80, 0x00 },
+	.expected_ss = (u8[32]){ 0x09, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for shared secret */
+{
+	.secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4,
+		     0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3,
+		     0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc,
+		     0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 },
+	.b_public = (u8[32]){ 0x2b, 0x55, 0xd3, 0xaa, 0x4a, 0x8f, 0x80, 0xc8,
+		    0xc0, 0xb2, 0xae, 0x5f, 0x93, 0x3e, 0x85, 0xaf,
+		    0x49, 0xbe, 0xac, 0x36, 0xc2, 0xfa, 0x73, 0x94,
+		    0xba, 0xb7, 0x6c, 0x89, 0x33, 0xf8, 0xf8, 0x1d },
+	.expected_ss = (u8[32]){ 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for shared secret */
+{
+	.secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4,
+		     0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3,
+		     0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc,
+		     0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 },
+	.b_public = (u8[32]){ 0x63, 0xe5, 0xb1, 0xfe, 0x96, 0x01, 0xfe, 0x84,
+		    0x38, 0x5d, 0x88, 0x66, 0xb0, 0x42, 0x12, 0x62,
+		    0xf7, 0x8f, 0xbf, 0xa5, 0xaf, 0xf9, 0x58, 0x5e,
+		    0x62, 0x66, 0x79, 0xb1, 0x85, 0x47, 0xd9, 0x59 },
+	.expected_ss = (u8[32]){ 0xfe, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for shared secret */
+{
+	.secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4,
+		     0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3,
+		     0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc,
+		     0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 },
+	.b_public = (u8[32]){ 0xe4, 0x28, 0xf3, 0xda, 0xc1, 0x78, 0x09, 0xf8,
+		    0x27, 0xa5, 0x22, 0xce, 0x32, 0x35, 0x50, 0x58,
+		    0xd0, 0x73, 0x69, 0x36, 0x4a, 0xa7, 0x89, 0x02,
+		    0xee, 0x10, 0x13, 0x9b, 0x9f, 0x9d, 0xd6, 0x53 },
+	.expected_ss = (u8[32]){ 0xfc, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for shared secret */
+{
+	.secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4,
+		     0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3,
+		     0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc,
+		     0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 },
+	.b_public = (u8[32]){ 0xb3, 0xb5, 0x0e, 0x3e, 0xd3, 0xa4, 0x07, 0xb9,
+		    0x5d, 0xe9, 0x42, 0xef, 0x74, 0x57, 0x5b, 0x5a,
+		    0xb8, 0xa1, 0x0c, 0x09, 0xee, 0x10, 0x35, 0x44,
+		    0xd6, 0x0b, 0xdf, 0xed, 0x81, 0x38, 0xab, 0x2b },
+	.expected_ss = (u8[32]){ 0xf9, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for shared secret */
+{
+	.secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4,
+		     0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3,
+		     0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc,
+		     0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 },
+	.b_public = (u8[32]){ 0x21, 0x3f, 0xff, 0xe9, 0x3d, 0x5e, 0xa8, 0xcd,
+		    0x24, 0x2e, 0x46, 0x28, 0x44, 0x02, 0x99, 0x22,
+		    0xc4, 0x3c, 0x77, 0xc9, 0xe3, 0xe4, 0x2f, 0x56,
+		    0x2f, 0x48, 0x5d, 0x24, 0xc5, 0x01, 0xa2, 0x0b },
+	.expected_ss = (u8[32]){ 0xf3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for shared secret */
+{
+	.secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4,
+		     0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3,
+		     0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc,
+		     0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 },
+	.b_public = (u8[32]){ 0x91, 0xb2, 0x32, 0xa1, 0x78, 0xb3, 0xcd, 0x53,
+		    0x09, 0x32, 0x44, 0x1e, 0x61, 0x39, 0x41, 0x8f,
+		    0x72, 0x17, 0x22, 0x92, 0xf1, 0xda, 0x4c, 0x18,
+		    0x34, 0xfc, 0x5e, 0xbf, 0xef, 0xb5, 0x1e, 0x3f },
+	.expected_ss = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x03 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for shared secret */
+{
+	.secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4,
+		     0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3,
+		     0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc,
+		     0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 },
+	.b_public = (u8[32]){ 0x04, 0x5c, 0x6e, 0x11, 0xc5, 0xd3, 0x32, 0x55,
+		    0x6c, 0x78, 0x22, 0xfe, 0x94, 0xeb, 0xf8, 0x9b,
+		    0x56, 0xa3, 0x87, 0x8d, 0xc2, 0x7c, 0xa0, 0x79,
+		    0x10, 0x30, 0x58, 0x84, 0x9f, 0xab, 0xcb, 0x4f },
+	.expected_ss = (u8[32]){ 0xe5, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for shared secret */
+{
+	.secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4,
+		     0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3,
+		     0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc,
+		     0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 },
+	.b_public = (u8[32]){ 0x1c, 0xa2, 0x19, 0x0b, 0x71, 0x16, 0x35, 0x39,
+		    0x06, 0x3c, 0x35, 0x77, 0x3b, 0xda, 0x0c, 0x9c,
+		    0x92, 0x8e, 0x91, 0x36, 0xf0, 0x62, 0x0a, 0xeb,
+		    0x09, 0x3f, 0x09, 0x91, 0x97, 0xb7, 0xf7, 0x4e },
+	.expected_ss = (u8[32]){ 0xe3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for shared secret */
+{
+	.secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4,
+		     0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3,
+		     0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc,
+		     0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 },
+	.b_public = (u8[32]){ 0xf7, 0x6e, 0x90, 0x10, 0xac, 0x33, 0xc5, 0x04,
+		    0x3b, 0x2d, 0x3b, 0x76, 0xa8, 0x42, 0x17, 0x10,
+		    0x00, 0xc4, 0x91, 0x62, 0x22, 0xe9, 0xe8, 0x58,
+		    0x97, 0xa0, 0xae, 0xc7, 0xf6, 0x35, 0x0b, 0x3c },
+	.expected_ss = (u8[32]){ 0xdd, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for shared secret */
+{
+	.secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4,
+		     0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3,
+		     0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc,
+		     0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 },
+	.b_public = (u8[32]){ 0xbb, 0x72, 0x68, 0x8d, 0x8f, 0x8a, 0xa7, 0xa3,
+		    0x9c, 0xd6, 0x06, 0x0c, 0xd5, 0xc8, 0x09, 0x3c,
+		    0xde, 0xc6, 0xfe, 0x34, 0x19, 0x37, 0xc3, 0x88,
+		    0x6a, 0x99, 0x34, 0x6c, 0xd0, 0x7f, 0xaa, 0x55 },
+	.expected_ss = (u8[32]){ 0xdb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for shared secret */
+{
+	.secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4,
+		     0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3,
+		     0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc,
+		     0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 },
+	.b_public = (u8[32]){ 0x88, 0xfd, 0xde, 0xa1, 0x93, 0x39, 0x1c, 0x6a,
+		    0x59, 0x33, 0xef, 0x9b, 0x71, 0x90, 0x15, 0x49,
+		    0x44, 0x72, 0x05, 0xaa, 0xe9, 0xda, 0x92, 0x8a,
+		    0x6b, 0x91, 0xa3, 0x52, 0xba, 0x10, 0xf4, 0x1f },
+	.expected_ss = (u8[32]){ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - edge case for shared secret */
+{
+	.secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4,
+		     0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3,
+		     0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc,
+		     0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 },
+	.b_public = (u8[32]){ 0x30, 0x3b, 0x39, 0x2f, 0x15, 0x31, 0x16, 0xca,
+		    0xd9, 0xcc, 0x68, 0x2a, 0x00, 0xcc, 0xc4, 0x4c,
+		    0x95, 0xff, 0x0d, 0x3b, 0xbe, 0x56, 0x8b, 0xeb,
+		    0x6c, 0x4e, 0x73, 0x9b, 0xaf, 0xdc, 0x2c, 0x68 },
+	.expected_ss = (u8[32]){ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80, 0x00 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - checking for overflow */
+{
+	.secret = (u8[32]){ 0xc8, 0x17, 0x24, 0x70, 0x40, 0x00, 0xb2, 0x6d,
+		     0x31, 0x70, 0x3c, 0xc9, 0x7e, 0x3a, 0x37, 0x8d,
+		     0x56, 0xfa, 0xd8, 0x21, 0x93, 0x61, 0xc8, 0x8c,
+		     0xca, 0x8b, 0xd7, 0xc5, 0x71, 0x9b, 0x12, 0xb2 },
+	.b_public = (u8[32]){ 0xfd, 0x30, 0x0a, 0xeb, 0x40, 0xe1, 0xfa, 0x58,
+		    0x25, 0x18, 0x41, 0x2b, 0x49, 0xb2, 0x08, 0xa7,
+		    0x84, 0x2b, 0x1e, 0x1f, 0x05, 0x6a, 0x04, 0x01,
+		    0x78, 0xea, 0x41, 0x41, 0x53, 0x4f, 0x65, 0x2d },
+	.expected_ss = (u8[32]){ 0xb7, 0x34, 0x10, 0x5d, 0xc2, 0x57, 0x58, 0x5d,
+		    0x73, 0xb5, 0x66, 0xcc, 0xb7, 0x6f, 0x06, 0x27,
+		    0x95, 0xcc, 0xbe, 0xc8, 0x91, 0x28, 0xe5, 0x2b,
+		    0x02, 0xf3, 0xe5, 0x96, 0x39, 0xf1, 0x3c, 0x46 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - checking for overflow */
+{
+	.secret = (u8[32]){ 0xc8, 0x17, 0x24, 0x70, 0x40, 0x00, 0xb2, 0x6d,
+		     0x31, 0x70, 0x3c, 0xc9, 0x7e, 0x3a, 0x37, 0x8d,
+		     0x56, 0xfa, 0xd8, 0x21, 0x93, 0x61, 0xc8, 0x8c,
+		     0xca, 0x8b, 0xd7, 0xc5, 0x71, 0x9b, 0x12, 0xb2 },
+	.b_public = (u8[32]){ 0xc8, 0xef, 0x79, 0xb5, 0x14, 0xd7, 0x68, 0x26,
+		    0x77, 0xbc, 0x79, 0x31, 0xe0, 0x6e, 0xe5, 0xc2,
+		    0x7c, 0x9b, 0x39, 0x2b, 0x4a, 0xe9, 0x48, 0x44,
+		    0x73, 0xf5, 0x54, 0xe6, 0x67, 0x8e, 0xcc, 0x2e },
+	.expected_ss = (u8[32]){ 0x64, 0x7a, 0x46, 0xb6, 0xfc, 0x3f, 0x40, 0xd6,
+		    0x21, 0x41, 0xee, 0x3c, 0xee, 0x70, 0x6b, 0x4d,
+		    0x7a, 0x92, 0x71, 0x59, 0x3a, 0x7b, 0x14, 0x3e,
+		    0x8e, 0x2e, 0x22, 0x79, 0x88, 0x3e, 0x45, 0x50 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - checking for overflow */
+{
+	.secret = (u8[32]){ 0xc8, 0x17, 0x24, 0x70, 0x40, 0x00, 0xb2, 0x6d,
+		     0x31, 0x70, 0x3c, 0xc9, 0x7e, 0x3a, 0x37, 0x8d,
+		     0x56, 0xfa, 0xd8, 0x21, 0x93, 0x61, 0xc8, 0x8c,
+		     0xca, 0x8b, 0xd7, 0xc5, 0x71, 0x9b, 0x12, 0xb2 },
+	.b_public = (u8[32]){ 0x64, 0xae, 0xac, 0x25, 0x04, 0x14, 0x48, 0x61,
+		    0x53, 0x2b, 0x7b, 0xbc, 0xb6, 0xc8, 0x7d, 0x67,
+		    0xdd, 0x4c, 0x1f, 0x07, 0xeb, 0xc2, 0xe0, 0x6e,
+		    0xff, 0xb9, 0x5a, 0xec, 0xc6, 0x17, 0x0b, 0x2c },
+	.expected_ss = (u8[32]){ 0x4f, 0xf0, 0x3d, 0x5f, 0xb4, 0x3c, 0xd8, 0x65,
+		    0x7a, 0x3c, 0xf3, 0x7c, 0x13, 0x8c, 0xad, 0xce,
+		    0xcc, 0xe5, 0x09, 0xe4, 0xeb, 0xa0, 0x89, 0xd0,
+		    0xef, 0x40, 0xb4, 0xe4, 0xfb, 0x94, 0x61, 0x55 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - checking for overflow */
+{
+	.secret = (u8[32]){ 0xc8, 0x17, 0x24, 0x70, 0x40, 0x00, 0xb2, 0x6d,
+		     0x31, 0x70, 0x3c, 0xc9, 0x7e, 0x3a, 0x37, 0x8d,
+		     0x56, 0xfa, 0xd8, 0x21, 0x93, 0x61, 0xc8, 0x8c,
+		     0xca, 0x8b, 0xd7, 0xc5, 0x71, 0x9b, 0x12, 0xb2 },
+	.b_public = (u8[32]){ 0xbf, 0x68, 0xe3, 0x5e, 0x9b, 0xdb, 0x7e, 0xee,
+		    0x1b, 0x50, 0x57, 0x02, 0x21, 0x86, 0x0f, 0x5d,
+		    0xcd, 0xad, 0x8a, 0xcb, 0xab, 0x03, 0x1b, 0x14,
+		    0x97, 0x4c, 0xc4, 0x90, 0x13, 0xc4, 0x98, 0x31 },
+	.expected_ss = (u8[32]){ 0x21, 0xce, 0xe5, 0x2e, 0xfd, 0xbc, 0x81, 0x2e,
+		    0x1d, 0x02, 0x1a, 0x4a, 0xf1, 0xe1, 0xd8, 0xbc,
+		    0x4d, 0xb3, 0xc4, 0x00, 0xe4, 0xd2, 0xa2, 0xc5,
+		    0x6a, 0x39, 0x26, 0xdb, 0x4d, 0x99, 0xc6, 0x5b },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - checking for overflow */
+{
+	.secret = (u8[32]){ 0xc8, 0x17, 0x24, 0x70, 0x40, 0x00, 0xb2, 0x6d,
+		     0x31, 0x70, 0x3c, 0xc9, 0x7e, 0x3a, 0x37, 0x8d,
+		     0x56, 0xfa, 0xd8, 0x21, 0x93, 0x61, 0xc8, 0x8c,
+		     0xca, 0x8b, 0xd7, 0xc5, 0x71, 0x9b, 0x12, 0xb2 },
+	.b_public = (u8[32]){ 0x53, 0x47, 0xc4, 0x91, 0x33, 0x1a, 0x64, 0xb4,
+		    0x3d, 0xdc, 0x68, 0x30, 0x34, 0xe6, 0x77, 0xf5,
+		    0x3d, 0xc3, 0x2b, 0x52, 0xa5, 0x2a, 0x57, 0x7c,
+		    0x15, 0xa8, 0x3b, 0xf2, 0x98, 0xe9, 0x9f, 0x19 },
+	.expected_ss = (u8[32]){ 0x18, 0xcb, 0x89, 0xe4, 0xe2, 0x0c, 0x0c, 0x2b,
+		    0xd3, 0x24, 0x30, 0x52, 0x45, 0x26, 0x6c, 0x93,
+		    0x27, 0x69, 0x0b, 0xbe, 0x79, 0xac, 0xb8, 0x8f,
+		    0x5b, 0x8f, 0xb3, 0xf7, 0x4e, 0xca, 0x3e, 0x52 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - private key == -1 (mod order) */
+{
+	.secret = (u8[32]){ 0xa0, 0x23, 0xcd, 0xd0, 0x83, 0xef, 0x5b, 0xb8,
+		     0x2f, 0x10, 0xd6, 0x2e, 0x59, 0xe1, 0x5a, 0x68,
+		     0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		     0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x50 },
+	.b_public = (u8[32]){ 0x25, 0x8e, 0x04, 0x52, 0x3b, 0x8d, 0x25, 0x3e,
+		    0xe6, 0x57, 0x19, 0xfc, 0x69, 0x06, 0xc6, 0x57,
+		    0x19, 0x2d, 0x80, 0x71, 0x7e, 0xdc, 0x82, 0x8f,
+		    0xa0, 0xaf, 0x21, 0x68, 0x6e, 0x2f, 0xaa, 0x75 },
+	.expected_ss = (u8[32]){ 0x25, 0x8e, 0x04, 0x52, 0x3b, 0x8d, 0x25, 0x3e,
+		    0xe6, 0x57, 0x19, 0xfc, 0x69, 0x06, 0xc6, 0x57,
+		    0x19, 0x2d, 0x80, 0x71, 0x7e, 0xdc, 0x82, 0x8f,
+		    0xa0, 0xaf, 0x21, 0x68, 0x6e, 0x2f, 0xaa, 0x75 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+},
+/* wycheproof - private key == 1 (mod order) on twist */
+{
+	.secret = (u8[32]){ 0x58, 0x08, 0x3d, 0xd2, 0x61, 0xad, 0x91, 0xef,
+		     0xf9, 0x52, 0x32, 0x2e, 0xc8, 0x24, 0xc6, 0x82,
+		     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+		     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x5f },
+	.b_public = (u8[32]){ 0x2e, 0xae, 0x5e, 0xc3, 0xdd, 0x49, 0x4e, 0x9f,
+		    0x2d, 0x37, 0xd2, 0x58, 0xf8, 0x73, 0xa8, 0xe6,
+		    0xe9, 0xd0, 0xdb, 0xd1, 0xe3, 0x83, 0xef, 0x64,
+		    0xd9, 0x8b, 0xb9, 0x1b, 0x3e, 0x0b, 0xe0, 0x35 },
+	.expected_ss = (u8[32]){ 0x2e, 0xae, 0x5e, 0xc3, 0xdd, 0x49, 0x4e, 0x9f,
+		    0x2d, 0x37, 0xd2, 0x58, 0xf8, 0x73, 0xa8, 0xe6,
+		    0xe9, 0xd0, 0xdb, 0xd1, 0xe3, 0x83, 0xef, 0x64,
+		    0xd9, 0x8b, 0xb9, 0x1b, 0x3e, 0x0b, 0xe0, 0x35 },
+	.secret_size = 32,
+	.b_public_size = 32,
+	.expected_ss_size = 32,
+
+}
+};
+
 static const struct kpp_testvec ecdh_tv_template[] = {
 	{
 #ifndef CONFIG_CRYPTO_FIPS
@@ -2628,6 +3853,62 @@ static const struct hash_testvec sm3_tv_template[] = {
 	}
 };
 
+/* Example vectors below taken from
+ * GM/T 0042-2015 Appendix D.3
+ */
+static const struct hash_testvec hmac_sm3_tv_template[] = {
+	{
+		.key	= "\x01\x02\x03\x04\x05\x06\x07\x08"
+			  "\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10"
+			  "\x11\x12\x13\x14\x15\x16\x17\x18"
+			  "\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20",
+		.ksize	= 32,
+		.plaintext = "abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq"
+			     "abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq",
+		.psize	= 112,
+		.digest	= "\xca\x05\xe1\x44\xed\x05\xd1\x85"
+			  "\x78\x40\xd1\xf3\x18\xa4\xa8\x66"
+			  "\x9e\x55\x9f\xc8\x39\x1f\x41\x44"
+			  "\x85\xbf\xdf\x7b\xb4\x08\x96\x3a",
+	}, {
+		.key	= "\x01\x02\x03\x04\x05\x06\x07\x08"
+			  "\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10"
+			  "\x11\x12\x13\x14\x15\x16\x17\x18"
+			  "\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20"
+			  "\x21\x22\x23\x24\x25",
+		.ksize	= 37,
+		.plaintext = "\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd"
+			"\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd"
+			"\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd"
+			"\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd",
+		.psize	= 50,
+		.digest	= "\x22\x0b\xf5\x79\xde\xd5\x55\x39"
+			  "\x3f\x01\x59\xf6\x6c\x99\x87\x78"
+			  "\x22\xa3\xec\xf6\x10\xd1\x55\x21"
+			  "\x54\xb4\x1d\x44\xb9\x4d\xb3\xae",
+	}, {
+		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			 "\x0b\x0b\x0b\x0b\x0b\x0b",
+		.ksize	= 32,
+		.plaintext = "Hi There",
+		.psize	= 8,
+		.digest	= "\xc0\xba\x18\xc6\x8b\x90\xc8\x8b"
+			  "\xc0\x7d\xe7\x94\xbf\xc7\xd2\xc8"
+			  "\xd1\x9e\xc3\x1e\xd8\x77\x3b\xc2"
+			  "\xb3\x90\xc9\x60\x4e\x0b\xe1\x1e",
+	}, {
+		.key	= "Jefe",
+		.ksize	= 4,
+		.plaintext = "what do ya want for nothing?",
+		.psize	= 28,
+		.digest	= "\x2e\x87\xf1\xd1\x68\x62\xe6\xd9"
+			  "\x64\xb5\x0a\x52\x00\xbf\x2b\x10"
+			  "\xb7\x64\xfa\xa9\x68\x0a\x29\x6a"
+			  "\x24\x05\xf2\x4b\xec\x39\xf8\x82",
+	},
+};
+
 /*
  * SHA1 test vectors  from from FIPS PUB 180-1
  * Long vector from CAVS 5.0
@@ -11846,6 +13127,133 @@ static const struct cipher_testvec sm4_ctr_tv_template[] = {
 	}
 };
 
+static const struct cipher_testvec sm4_ctr_rfc3686_tv_template[] = {
+	{
+		.key	= "\xae\x68\x52\xf8\x12\x10\x67\xcc"
+			  "\x4b\xf7\xa5\x76\x55\x77\xf3\x9e"
+			  "\x00\x00\x00\x30",
+		.klen	= 20,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.ptext	= "Single block msg",
+		.ctext	= "\x20\x9b\x77\x31\xd3\x65\xdb\xab"
+			  "\x9e\x48\x74\x7e\xbd\x13\x83\xeb",
+		.len	= 16,
+	}, {
+		.key	= "\x7e\x24\x06\x78\x17\xfa\xe0\xd7"
+			  "\x43\xd6\xce\x1f\x32\x53\x91\x63"
+			  "\x00\x6c\xb6\xdb",
+		.klen	= 20,
+		.iv	= "\xc0\x54\x3b\x59\xda\x48\xd9\x0b",
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
+		.ctext	= "\x33\xe0\x28\x01\x92\xed\xc9\x1e"
+			  "\x97\x35\xd9\x4a\xec\xd4\xbc\x23"
+			  "\x4f\x35\x9f\x1c\x55\x1f\xe0\x27"
+			  "\xe0\xdf\xc5\x43\xbc\xb0\x23\x94",
+		.len	= 32,
+	}
+};
+
+static const struct cipher_testvec sm4_ofb_tv_template[] = {
+	{ /* From: draft-ribose-cfrg-sm4-02, paragraph 12.2.3 */
+		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
+			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
+		.klen	= 16,
+		.iv	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
+			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
+			  "\xfe\xdc\xba\x98\x76\x54\x32\x10"
+			  "\x01\x23\x45\x67\x89\xab\xcd\xef"
+			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
+		.ctext	= "\x69\x3d\x9a\x53\x5b\xad\x5b\xb1"
+			  "\x78\x6f\x53\xd7\x25\x3a\x70\x56"
+			  "\xf2\x07\x5d\x28\xb5\x23\x5f\x58"
+			  "\xd5\x00\x27\xe4\x17\x7d\x2b\xce",
+		.len	= 32,
+	}, { /* From: draft-ribose-cfrg-sm4-09, appendix A.2.3, Example 1 */
+		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
+			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
+		.klen	= 16,
+		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.ptext	= "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb"
+			  "\xcc\xcc\xcc\xcc\xdd\xdd\xdd\xdd"
+			  "\xee\xee\xee\xee\xff\xff\xff\xff"
+			  "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb",
+		.ctext	= "\xac\x32\x36\xcb\x86\x1d\xd3\x16"
+			  "\xe6\x41\x3b\x4e\x3c\x75\x24\xb7"
+			  "\x1d\x01\xac\xa2\x48\x7c\xa5\x82"
+			  "\xcb\xf5\x46\x3e\x66\x98\x53\x9b",
+		.len	= 32,
+	}, { /* From: draft-ribose-cfrg-sm4-09, appendix A.2.3, Example 2 */
+		.key	= "\xfe\xdc\xba\x98\x76\x54\x32\x10"
+			  "\x01\x23\x45\x67\x89\xab\xcd\xef",
+		.klen	= 16,
+		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.ptext	= "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb"
+			  "\xcc\xcc\xcc\xcc\xdd\xdd\xdd\xdd"
+			  "\xee\xee\xee\xee\xff\xff\xff\xff"
+			  "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb",
+		.ctext	= "\x5d\xcc\xcd\x25\xa8\x4b\xa1\x65"
+			  "\x60\xd7\xf2\x65\x88\x70\x68\x49"
+			  "\x33\xfa\x16\xbd\x5c\xd9\xc8\x56"
+			  "\xca\xca\xa1\xe1\x01\x89\x7a\x97",
+		.len	= 32,
+	}
+};
+
+static const struct cipher_testvec sm4_cfb_tv_template[] = {
+	{ /* From: draft-ribose-cfrg-sm4-02, paragraph 12.2.4 */
+		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
+			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
+		.klen	= 16,
+		.iv	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
+			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
+			  "\xfe\xdc\xba\x98\x76\x54\x32\x10"
+			  "\x01\x23\x45\x67\x89\xab\xcd\xef"
+			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
+		.ctext	= "\x69\x3d\x9a\x53\x5b\xad\x5b\xb1"
+			  "\x78\x6f\x53\xd7\x25\x3a\x70\x56"
+			  "\x9e\xd2\x58\xa8\x5a\x04\x67\xcc"
+			  "\x92\xaa\xb3\x93\xdd\x97\x89\x95",
+		.len	= 32,
+	}, { /* From: draft-ribose-cfrg-sm4-09, appendix A.2.4, Example 1 */
+		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
+			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
+		.klen	= 16,
+		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.ptext	= "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb"
+			  "\xcc\xcc\xcc\xcc\xdd\xdd\xdd\xdd"
+			  "\xee\xee\xee\xee\xff\xff\xff\xff"
+			  "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb",
+		.ctext	= "\xac\x32\x36\xcb\x86\x1d\xd3\x16"
+			  "\xe6\x41\x3b\x4e\x3c\x75\x24\xb7"
+			  "\x69\xd4\xc5\x4e\xd4\x33\xb9\xa0"
+			  "\x34\x60\x09\xbe\xb3\x7b\x2b\x3f",
+		.len	= 32,
+	}, { /* From: draft-ribose-cfrg-sm4-09, appendix A.2.4, Example 2 */
+		.key	= "\xfe\xdc\xba\x98\x76\x54\x32\x10"
+			  "\x01\x23\x45\x67\x89\xab\xcd\xef",
+		.klen	= 16,
+		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.ptext	= "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb"
+			  "\xcc\xcc\xcc\xcc\xdd\xdd\xdd\xdd"
+			  "\xee\xee\xee\xee\xff\xff\xff\xff"
+			  "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb",
+		.ctext	= "\x5d\xcc\xcd\x25\xa8\x4b\xa1\x65"
+			  "\x60\xd7\xf2\x65\x88\x70\x68\x49"
+			  "\x0d\x9b\x86\xff\x20\xc3\xbf\xe1"
+			  "\x15\xff\xa0\x2c\xa6\x19\x2c\xc5",
+		.len	= 32,
+	}
+};
+
 /* Cast6 test vectors from RFC 2612 */
 static const struct cipher_testvec cast6_tv_template[] = {
 	{
@@ -17043,6 +18451,198 @@ static const struct aead_testvec aes_gcm_tv_template[] = {
 			  "\x25\x19\x49\x8e\x80\xf1\x47\x8f"
 			  "\x37\xba\x55\xbd\x6d\x27\x61\x8c",
 		.clen	= 76,
+	}, {
+		.key	= "\x62\x35\xf8\x95\xfc\xa5\xeb\xf6"
+			  "\x0e\x92\x12\x04\xd3\xa1\x3f\x2e"
+			  "\x8b\x32\xcf\xe7\x44\xed\x13\x59"
+			  "\x04\x38\x77\xb0\xb9\xad\xb4\x38",
+		.klen	= 32,
+		.iv	= "\x00\xff\xff\xff\xff\x00\x00\xff"
+			  "\xff\xff\x00\xff",
+		.ptext	= "\x42\xc1\xcc\x08\x48\x6f\x41\x3f"
+			  "\x2f\x11\x66\x8b\x2a\x16\xf0\xe0"
+			  "\x58\x83\xf0\xc3\x70\x14\xc0\x5b"
+			  "\x3f\xec\x1d\x25\x3c\x51\xd2\x03"
+			  "\xcf\x59\x74\x1f\xb2\x85\xb4\x07"
+			  "\xc6\x6a\x63\x39\x8a\x5b\xde\xcb"
+			  "\xaf\x08\x44\xbd\x6f\x91\x15\xe1"
+			  "\xf5\x7a\x6e\x18\xbd\xdd\x61\x50"
+			  "\x59\xa9\x97\xab\xbb\x0e\x74\x5c"
+			  "\x00\xa4\x43\x54\x04\x54\x9b\x3b"
+			  "\x77\xec\xfd\x5c\xa6\xe8\x7b\x08"
+			  "\xae\xe6\x10\x3f\x32\x65\xd1\xfc"
+			  "\xa4\x1d\x2c\x31\xfb\x33\x7a\xb3"
+			  "\x35\x23\xf4\x20\x41\xd4\xad\x82"
+			  "\x8b\xa4\xad\x96\x1c\x20\x53\xbe"
+			  "\x0e\xa6\xf4\xdc\x78\x49\x3e\x72"
+			  "\xb1\xa9\xb5\x83\xcb\x08\x54\xb7"
+			  "\xad\x49\x3a\xae\x98\xce\xa6\x66"
+			  "\x10\x30\x90\x8c\x55\x83\xd7\x7c"
+			  "\x8b\xe6\x53\xde\xd2\x6e\x18\x21"
+			  "\x01\x52\xd1\x9f\x9d\xbb\x9c\x73"
+			  "\x57\xcc\x89\x09\x75\x9b\x78\x70"
+			  "\xed\x26\x97\x4d\xb4\xe4\x0c\xa5"
+			  "\xfa\x70\x04\x70\xc6\x96\x1c\x7d"
+			  "\x54\x41\x77\xa8\xe3\xb0\x7e\x96"
+			  "\x82\xd9\xec\xa2\x87\x68\x55\xf9"
+			  "\x8f\x9e\x73\x43\x47\x6a\x08\x36"
+			  "\x93\x67\xa8\x2d\xde\xac\x41\xa9"
+			  "\x5c\x4d\x73\x97\x0f\x70\x68\xfa"
+			  "\x56\x4d\x00\xc2\x3b\x1f\xc8\xb9"
+			  "\x78\x1f\x51\x07\xe3\x9a\x13\x4e"
+			  "\xed\x2b\x2e\xa3\xf7\x44\xb2\xe7"
+			  "\xab\x19\x37\xd9\xba\x76\x5e\xd2"
+			  "\xf2\x53\x15\x17\x4c\x6b\x16\x9f"
+			  "\x02\x66\x49\xca\x7c\x91\x05\xf2"
+			  "\x45\x36\x1e\xf5\x77\xad\x1f\x46"
+			  "\xa8\x13\xfb\x63\xb6\x08\x99\x63"
+			  "\x82\xa2\xed\xb3\xac\xdf\x43\x19"
+			  "\x45\xea\x78\x73\xd9\xb7\x39\x11"
+			  "\xa3\x13\x7c\xf8\x3f\xf7\xad\x81"
+			  "\x48\x2f\xa9\x5c\x5f\xa0\xf0\x79"
+			  "\xa4\x47\x7d\x80\x20\x26\xfd\x63"
+			  "\x0a\xc7\x7e\x6d\x75\x47\xff\x76"
+			  "\x66\x2e\x8a\x6c\x81\x35\xaf\x0b"
+			  "\x2e\x6a\x49\x60\xc1\x10\xe1\xe1"
+			  "\x54\x03\xa4\x09\x0c\x37\x7a\x15"
+			  "\x23\x27\x5b\x8b\x4b\xa5\x64\x97"
+			  "\xae\x4a\x50\x73\x1f\x66\x1c\x5c"
+			  "\x03\x25\x3c\x8d\x48\x58\x71\x34"
+			  "\x0e\xec\x4e\x55\x1a\x03\x6a\xe5"
+			  "\xb6\x19\x2b\x84\x2a\x20\xd1\xea"
+			  "\x80\x6f\x96\x0e\x05\x62\xc7\x78"
+			  "\x87\x79\x60\x38\x46\xb4\x25\x57"
+			  "\x6e\x16\x63\xf8\xad\x6e\xd7\x42"
+			  "\x69\xe1\x88\xef\x6e\xd5\xb4\x9a"
+			  "\x3c\x78\x6c\x3b\xe5\xa0\x1d\x22"
+			  "\x86\x5c\x74\x3a\xeb\x24\x26\xc7"
+			  "\x09\xfc\x91\x96\x47\x87\x4f\x1a"
+			  "\xd6\x6b\x2c\x18\x47\xc0\xb8\x24"
+			  "\xa8\x5a\x4a\x9e\xcb\x03\xe7\x2a"
+			  "\x09\xe6\x4d\x9c\x6d\x86\x60\xf5"
+			  "\x2f\x48\x69\x37\x9f\xf2\xd2\xcb"
+			  "\x0e\x5a\xdd\x6e\x8a\xfb\x6a\xfe"
+			  "\x0b\x63\xde\x87\x42\x79\x8a\x68"
+			  "\x51\x28\x9b\x7a\xeb\xaf\xb8\x2f"
+			  "\x9d\xd1\xc7\x45\x90\x08\xc9\x83"
+			  "\xe9\x83\x84\xcb\x28\x69\x09\x69"
+			  "\xce\x99\x46\x00\x54\xcb\xd8\x38"
+			  "\xf9\x53\x4a\xbf\x31\xce\x57\x15"
+			  "\x33\xfa\x96\x04\x33\x42\xe3\xc0"
+			  "\xb7\x54\x4a\x65\x7a\x7c\x02\xe6"
+			  "\x19\x95\xd0\x0e\x82\x07\x63\xf9"
+			  "\xe1\x2b\x2a\xfc\x55\x92\x52\xc9"
+			  "\xb5\x9f\x23\x28\x60\xe7\x20\x51"
+			  "\x10\xd3\xed\x6d\x9b\xab\xb8\xe2"
+			  "\x5d\x9a\x34\xb3\xbe\x9c\x64\xcb"
+			  "\x78\xc6\x91\x22\x40\x91\x80\xbe"
+			  "\xd7\x78\x5c\x0e\x0a\xdc\x08\xe9"
+			  "\x67\x10\xa4\x83\x98\x79\x23\xe7"
+			  "\x92\xda\xa9\x22\x16\xb1\xe7\x78"
+			  "\xa3\x1c\x6c\x8f\x35\x7c\x4d\x37"
+			  "\x2f\x6e\x0b\x50\x5c\x34\xb9\xf9"
+			  "\xe6\x3d\x91\x0d\x32\x95\xaa\x3d"
+			  "\x48\x11\x06\xbb\x2d\xf2\x63\x88"
+			  "\x3f\x73\x09\xe2\x45\x56\x31\x51"
+			  "\xfa\x5e\x4e\x62\xf7\x90\xf9\xa9"
+			  "\x7d\x7b\x1b\xb1\xc8\x26\x6e\x66"
+			  "\xf6\x90\x9a\x7f\xf2\x57\xcc\x23"
+			  "\x59\xfa\xfa\xaa\x44\x04\x01\xa7"
+			  "\xa4\x78\xdb\x74\x3d\x8b\xb5",
+		.plen	= 719,
+		.ctext	= "\x84\x0b\xdb\xd5\xb7\xa8\xfe\x20"
+			  "\xbb\xb1\x12\x7f\x41\xea\xb3\xc0"
+			  "\xa2\xb4\x37\x19\x11\x58\xb6\x0b"
+			  "\x4c\x1d\x38\x05\x54\xd1\x16\x73"
+			  "\x8e\x1c\x20\x90\xa2\x9a\xb7\x74"
+			  "\x47\xe6\xd8\xfc\x18\x3a\xb4\xea"
+			  "\xd5\x16\x5a\x2c\x53\x01\x46\xb3"
+			  "\x18\x33\x74\x6c\x50\xf2\xe8\xc0"
+			  "\x73\xda\x60\x22\xeb\xe3\xe5\x9b"
+			  "\x20\x93\x6c\x4b\x37\x99\xb8\x23"
+			  "\x3b\x4e\xac\xe8\x5b\xe8\x0f\xb7"
+			  "\xc3\x8f\xfb\x4a\x37\xd9\x39\x95"
+			  "\x34\xf1\xdb\x8f\x71\xd9\xc7\x0b"
+			  "\x02\xf1\x63\xfc\x9b\xfc\xc5\xab"
+			  "\xb9\x14\x13\x21\xdf\xce\xaa\x88"
+			  "\x44\x30\x1e\xce\x26\x01\x92\xf8"
+			  "\x9f\x00\x4b\x0c\x4b\xf7\x5f\xe0"
+			  "\x89\xca\x94\x66\x11\x21\x97\xca"
+			  "\x3e\x83\x74\x2d\xdb\x4d\x11\xeb"
+			  "\x97\xc2\x14\xff\x9e\x1e\xa0\x6b"
+			  "\x08\xb4\x31\x2b\x85\xc6\x85\x6c"
+			  "\x90\xec\x39\xc0\xec\xb3\xb5\x4e"
+			  "\xf3\x9c\xe7\x83\x3a\x77\x0a\xf4"
+			  "\x56\xfe\xce\x18\x33\x6d\x0b\x2d"
+			  "\x33\xda\xc8\x05\x5c\xb4\x09\x2a"
+			  "\xde\x6b\x52\x98\x01\xef\x36\x3d"
+			  "\xbd\xf9\x8f\xa8\x3e\xaa\xcd\xd1"
+			  "\x01\x2d\x42\x49\xc3\xb6\x84\xbb"
+			  "\x48\x96\xe0\x90\x93\x6c\x48\x64"
+			  "\xd4\xfa\x7f\x93\x2c\xa6\x21\xc8"
+			  "\x7a\x23\x7b\xaa\x20\x56\x12\xae"
+			  "\x16\x9d\x94\x0f\x54\xa1\xec\xca"
+			  "\x51\x4e\xf2\x39\xf4\xf8\x5f\x04"
+			  "\x5a\x0d\xbf\xf5\x83\xa1\x15\xe1"
+			  "\xf5\x3c\xd8\x62\xa3\xed\x47\x89"
+			  "\x85\x4c\xe5\xdb\xac\x9e\x17\x1d"
+			  "\x0c\x09\xe3\x3e\x39\x5b\x4d\x74"
+			  "\x0e\xf5\x34\xee\x70\x11\x4c\xfd"
+			  "\xdb\x34\xb1\xb5\x10\x3f\x73\xb7"
+			  "\xf5\xfa\xed\xb0\x1f\xa5\xcd\x3c"
+			  "\x8d\x35\x83\xd4\x11\x44\x6e\x6c"
+			  "\x5b\xe0\x0e\x69\xa5\x39\xe5\xbb"
+			  "\xa9\x57\x24\x37\xe6\x1f\xdd\xcf"
+			  "\x16\x2a\x13\xf9\x6a\x2d\x90\xa0"
+			  "\x03\x60\x7a\xed\x69\xd5\x00\x8b"
+			  "\x7e\x4f\xcb\xb9\xfa\x91\xb9\x37"
+			  "\xc1\x26\xce\x90\x97\x22\x64\x64"
+			  "\xc1\x72\x43\x1b\xf6\xac\xc1\x54"
+			  "\x8a\x10\x9c\xdd\x8d\xd5\x8e\xb2"
+			  "\xe4\x85\xda\xe0\x20\x5f\xf4\xb4"
+			  "\x15\xb5\xa0\x8d\x12\x74\x49\x23"
+			  "\x3a\xdf\x4a\xd3\xf0\x3b\x89\xeb"
+			  "\xf8\xcc\x62\x7b\xfb\x93\x07\x41"
+			  "\x61\x26\x94\x58\x70\xa6\x3c\xe4"
+			  "\xff\x58\xc4\x13\x3d\xcb\x36\x6b"
+			  "\x32\xe5\xb2\x6d\x03\x74\x6f\x76"
+			  "\x93\x77\xde\x48\xc4\xfa\x30\x4a"
+			  "\xda\x49\x80\x77\x0f\x1c\xbe\x11"
+			  "\xc8\x48\xb1\xe5\xbb\xf2\x8a\xe1"
+			  "\x96\x2f\x9f\xd1\x8e\x8a\x5c\xe2"
+			  "\xf7\xd7\xd8\x54\xf3\x3f\xc4\x91"
+			  "\xb8\xfb\x86\xdc\x46\x24\x91\x60"
+			  "\x6c\x2f\xc9\x41\x37\x51\x49\x54"
+			  "\x09\x81\x21\xf3\x03\x9f\x2b\xe3"
+			  "\x1f\x39\x63\xaf\xf4\xd7\x53\x60"
+			  "\xa7\xc7\x54\xf9\xee\xb1\xb1\x7d"
+			  "\x75\x54\x65\x93\xfe\xb1\x68\x6b"
+			  "\x57\x02\xf9\xbb\x0e\xf9\xf8\xbf"
+			  "\x01\x12\x27\xb4\xfe\xe4\x79\x7a"
+			  "\x40\x5b\x51\x4b\xdf\x38\xec\xb1"
+			  "\x6a\x56\xff\x35\x4d\x42\x33\xaa"
+			  "\x6f\x1b\xe4\xdc\xe0\xdb\x85\x35"
+			  "\x62\x10\xd4\xec\xeb\xc5\x7e\x45"
+			  "\x1c\x6f\x17\xca\x3b\x8e\x2d\x66"
+			  "\x4f\x4b\x36\x56\xcd\x1b\x59\xaa"
+			  "\xd2\x9b\x17\xb9\x58\xdf\x7b\x64"
+			  "\x8a\xff\x3b\x9c\xa6\xb5\x48\x9e"
+			  "\xaa\xe2\x5d\x09\x71\x32\x5f\xb6"
+			  "\x29\xbe\xe7\xc7\x52\x7e\x91\x82"
+			  "\x6b\x6d\x33\xe1\x34\x06\x36\x21"
+			  "\x5e\xbe\x1e\x2f\x3e\xc1\xfb\xea"
+			  "\x49\x2c\xb5\xca\xf7\xb0\x37\xea"
+			  "\x1f\xed\x10\x04\xd9\x48\x0d\x1a"
+			  "\x1c\xfb\xe7\x84\x0e\x83\x53\x74"
+			  "\xc7\x65\xe2\x5c\xe5\xba\x73\x4c"
+			  "\x0e\xe1\xb5\x11\x45\x61\x43\x46"
+			  "\xaa\x25\x8f\xbd\x85\x08\xfa\x4c"
+			  "\x15\xc1\xc0\xd8\xf5\xdc\x16\xbb"
+			  "\x7b\x1d\xe3\x87\x57\xa7\x2a\x1d"
+			  "\x38\x58\x9e\x8a\x43\xdc\x57"
+			  "\xd1\x81\x7d\x2b\xe9\xff\x99\x3a"
+			  "\x4b\x24\x52\x58\x55\xe1\x49\x14",
+		.clen	= 735,
 	}
 };
 
@@ -31567,4 +33167,528 @@ static const struct aead_testvec essiv_hmac_sha256_aes_cbc_tv_temp[] = {
 	},
 };
 
+static const char blake2_ordered_sequence[] =
+	"\x00\x01\x02\x03\x04\x05\x06\x07"
+	"\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+	"\x10\x11\x12\x13\x14\x15\x16\x17"
+	"\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+	"\x20\x21\x22\x23\x24\x25\x26\x27"
+	"\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+	"\x30\x31\x32\x33\x34\x35\x36\x37"
+	"\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+	"\x40\x41\x42\x43\x44\x45\x46\x47"
+	"\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+	"\x50\x51\x52\x53\x54\x55\x56\x57"
+	"\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+	"\x60\x61\x62\x63\x64\x65\x66\x67"
+	"\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+	"\x70\x71\x72\x73\x74\x75\x76\x77"
+	"\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+	"\x80\x81\x82\x83\x84\x85\x86\x87"
+	"\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+	"\x90\x91\x92\x93\x94\x95\x96\x97"
+	"\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+	"\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+	"\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+	"\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+	"\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+	"\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+	"\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+	"\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+	"\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+	"\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+	"\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+	"\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+	"\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff";
+
+static const struct hash_testvec blake2b_160_tv_template[] = {{
+	.digest = (u8[]){ 0x33, 0x45, 0x52, 0x4a, 0xbf, 0x6b, 0xbe, 0x18,
+			  0x09, 0x44, 0x92, 0x24, 0xb5, 0x97, 0x2c, 0x41,
+			  0x79, 0x0b, 0x6c, 0xf2, },
+}, {
+	.plaintext = blake2_ordered_sequence,
+	.psize = 64,
+	.digest = (u8[]){ 0x11, 0xcc, 0x66, 0x61, 0xe9, 0x22, 0xb0, 0xe4,
+			  0x07, 0xe0, 0xa5, 0x72, 0x49, 0xc3, 0x8d, 0x4f,
+			  0xf7, 0x6d, 0x8e, 0xc8, },
+}, {
+	.ksize = 32,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 1,
+	.digest = (u8[]){ 0x31, 0xe3, 0xd9, 0xd5, 0x4e, 0x72, 0xd8, 0x0b,
+			  0x2b, 0x3b, 0xd7, 0x6b, 0x82, 0x7a, 0x1d, 0xfb,
+			  0x56, 0x2f, 0x79, 0x4c, },
+}, {
+	.ksize = 64,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 7,
+	.digest = (u8[]){ 0x28, 0x20, 0xd1, 0xbe, 0x7f, 0xcc, 0xc1, 0x62,
+			  0xd9, 0x0d, 0x9a, 0x4b, 0x47, 0xd1, 0x5e, 0x04,
+			  0x74, 0x2a, 0x53, 0x17, },
+}, {
+	.ksize = 1,
+	.key = "B",
+	.plaintext = blake2_ordered_sequence,
+	.psize = 15,
+	.digest = (u8[]){ 0x45, 0xe9, 0x95, 0xb6, 0xc4, 0xe8, 0x22, 0xea,
+			  0xfe, 0xd2, 0x37, 0xdb, 0x46, 0xbf, 0xf1, 0x25,
+			  0xd5, 0x03, 0x1d, 0x81, },
+}, {
+	.ksize = 32,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 247,
+	.digest = (u8[]){ 0x7e, 0xb9, 0xf2, 0x9b, 0x2f, 0xc2, 0x01, 0xd4,
+			  0xb0, 0x4f, 0x08, 0x2b, 0x8e, 0xbd, 0x06, 0xef,
+			  0x1c, 0xc4, 0x25, 0x95, },
+}, {
+	.ksize = 64,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 256,
+	.digest = (u8[]){ 0x6e, 0x35, 0x01, 0x70, 0xbf, 0xb6, 0xc4, 0xba,
+			  0x33, 0x1b, 0xa6, 0xd3, 0xc2, 0x5d, 0xb4, 0x03,
+			  0x95, 0xaf, 0x29, 0x16, },
+}};
+
+static const struct hash_testvec blake2b_256_tv_template[] = {{
+	.plaintext = blake2_ordered_sequence,
+	.psize = 7,
+	.digest = (u8[]){ 0x9d, 0xf1, 0x4b, 0x72, 0x48, 0x76, 0x4a, 0x86,
+			  0x91, 0x97, 0xc3, 0x5e, 0x39, 0x2d, 0x2a, 0x6d,
+			  0x6f, 0xdc, 0x5b, 0x79, 0xd5, 0x97, 0x29, 0x79,
+			  0x20, 0xfd, 0x3f, 0x14, 0x91, 0xb4, 0x42, 0xd2, },
+}, {
+	.plaintext = blake2_ordered_sequence,
+	.psize = 256,
+	.digest = (u8[]){ 0x39, 0xa7, 0xeb, 0x9f, 0xed, 0xc1, 0x9a, 0xab,
+			  0xc8, 0x34, 0x25, 0xc6, 0x75, 0x5d, 0xd9, 0x0e,
+			  0x6f, 0x9d, 0x0c, 0x80, 0x49, 0x64, 0xa1, 0xf4,
+			  0xaa, 0xee, 0xa3, 0xb9, 0xfb, 0x59, 0x98, 0x35, },
+}, {
+	.ksize = 1,
+	.key = "B",
+	.digest = (u8[]){ 0xc3, 0x08, 0xb1, 0xbf, 0xe4, 0xf9, 0xbc, 0xb4,
+			  0x75, 0xaf, 0x3f, 0x59, 0x6e, 0xae, 0xde, 0x6a,
+			  0xa3, 0x8e, 0xb5, 0x94, 0xad, 0x30, 0xf0, 0x17,
+			  0x1c, 0xfb, 0xd8, 0x3e, 0x8a, 0xbe, 0xed, 0x9c, },
+}, {
+	.ksize = 64,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 1,
+	.digest = (u8[]){ 0x34, 0x75, 0x8b, 0x64, 0x71, 0x35, 0x62, 0x82,
+			  0x97, 0xfb, 0x09, 0xc7, 0x93, 0x0c, 0xd0, 0x4e,
+			  0x95, 0x28, 0xe5, 0x66, 0x91, 0x12, 0xf5, 0xb1,
+			  0x31, 0x84, 0x93, 0xe1, 0x4d, 0xe7, 0x7e, 0x55, },
+}, {
+	.ksize = 32,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 15,
+	.digest = (u8[]){ 0xce, 0x74, 0xa9, 0x2e, 0xe9, 0x40, 0x3d, 0xa2,
+			  0x11, 0x4a, 0x99, 0x25, 0x7a, 0x34, 0x5d, 0x35,
+			  0xdf, 0x6a, 0x48, 0x79, 0x2a, 0x93, 0x93, 0xff,
+			  0x1f, 0x3c, 0x39, 0xd0, 0x71, 0x1f, 0x20, 0x7b, },
+}, {
+	.ksize = 1,
+	.key = "B",
+	.plaintext = blake2_ordered_sequence,
+	.psize = 64,
+	.digest = (u8[]){ 0x2e, 0x84, 0xdb, 0xa2, 0x5f, 0x0e, 0xe9, 0x52,
+			  0x79, 0x50, 0x69, 0x9f, 0xf1, 0xfd, 0xfc, 0x9d,
+			  0x89, 0x83, 0xa9, 0xb6, 0xa4, 0xd5, 0xfa, 0xb5,
+			  0xbe, 0x35, 0x1a, 0x17, 0x8a, 0x2c, 0x7f, 0x7d, },
+}, {
+	.ksize = 64,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 247,
+	.digest = (u8[]){ 0x2e, 0x26, 0xf0, 0x09, 0x02, 0x65, 0x90, 0x09,
+			  0xcc, 0xf5, 0x4c, 0x44, 0x74, 0x0e, 0xa0, 0xa8,
+			  0x25, 0x4a, 0xda, 0x61, 0x56, 0x95, 0x7d, 0x3f,
+			  0x6d, 0xc0, 0x43, 0x17, 0x95, 0x89, 0xcd, 0x9d, },
+}};
+
+static const struct hash_testvec blake2b_384_tv_template[] = {{
+	.plaintext = blake2_ordered_sequence,
+	.psize = 1,
+	.digest = (u8[]){ 0xcc, 0x01, 0x08, 0x85, 0x36, 0xf7, 0x84, 0xf0,
+			  0xbb, 0x76, 0x9e, 0x41, 0xc4, 0x95, 0x7b, 0x6d,
+			  0x0c, 0xde, 0x1f, 0xcc, 0x8c, 0xf1, 0xd9, 0x1f,
+			  0xc4, 0x77, 0xd4, 0xdd, 0x6e, 0x3f, 0xbf, 0xcd,
+			  0x43, 0xd1, 0x69, 0x8d, 0x14, 0x6f, 0x34, 0x8b,
+			  0x2c, 0x36, 0xa3, 0x39, 0x68, 0x2b, 0xec, 0x3f, },
+}, {
+	.plaintext = blake2_ordered_sequence,
+	.psize = 247,
+	.digest = (u8[]){ 0xc8, 0xf8, 0xf0, 0xa2, 0x69, 0xfa, 0xcc, 0x4d,
+			  0x32, 0x5f, 0x13, 0x88, 0xca, 0x71, 0x99, 0x8f,
+			  0xf7, 0x30, 0x41, 0x5d, 0x6e, 0x34, 0xb7, 0x6e,
+			  0x3e, 0xd0, 0x46, 0xb6, 0xca, 0x30, 0x66, 0xb2,
+			  0x6f, 0x0c, 0x35, 0x54, 0x17, 0xcd, 0x26, 0x1b,
+			  0xef, 0x48, 0x98, 0xe0, 0x56, 0x7c, 0x05, 0xd2, },
+}, {
+	.ksize = 32,
+	.key = blake2_ordered_sequence,
+	.digest = (u8[]){ 0x15, 0x09, 0x7a, 0x90, 0x13, 0x23, 0xab, 0x0c,
+			  0x0b, 0x43, 0x21, 0x9a, 0xb5, 0xc6, 0x0c, 0x2e,
+			  0x7c, 0x57, 0xfc, 0xcc, 0x4b, 0x0f, 0xf0, 0x57,
+			  0xb7, 0x9c, 0xe7, 0x0f, 0xe1, 0x57, 0xac, 0x37,
+			  0x77, 0xd4, 0xf4, 0x2f, 0x03, 0x3b, 0x64, 0x09,
+			  0x84, 0xa0, 0xb3, 0x24, 0xb7, 0xae, 0x47, 0x5e, },
+}, {
+	.ksize = 1,
+	.key = "B",
+	.plaintext = blake2_ordered_sequence,
+	.psize = 7,
+	.digest = (u8[]){ 0x0b, 0x82, 0x88, 0xca, 0x05, 0x2f, 0x1b, 0x15,
+			  0xdc, 0xbb, 0x22, 0x27, 0x11, 0x6b, 0xf4, 0xd1,
+			  0xe9, 0x8f, 0x1b, 0x0b, 0x58, 0x3f, 0x5e, 0x86,
+			  0x80, 0x82, 0x6f, 0x8e, 0x54, 0xc1, 0x9f, 0x12,
+			  0xcf, 0xe9, 0x56, 0xc1, 0xfc, 0x1a, 0x08, 0xb9,
+			  0x4a, 0x57, 0x0a, 0x76, 0x3c, 0x15, 0x33, 0x18, },
+}, {
+	.ksize = 64,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 15,
+	.digest = (u8[]){ 0x4a, 0x81, 0x55, 0xb9, 0x79, 0x42, 0x8c, 0xc6,
+			  0x4f, 0xfe, 0xca, 0x82, 0x3b, 0xb2, 0xf7, 0xbc,
+			  0x5e, 0xfc, 0xab, 0x09, 0x1c, 0xd6, 0x3b, 0xe1,
+			  0x50, 0x82, 0x3b, 0xde, 0xc7, 0x06, 0xee, 0x3b,
+			  0x29, 0xce, 0xe5, 0x68, 0xe0, 0xff, 0xfa, 0xe1,
+			  0x7a, 0xf1, 0xc0, 0xfe, 0x57, 0xf4, 0x60, 0x49, },
+}, {
+	.ksize = 32,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 64,
+	.digest = (u8[]){ 0x34, 0xbd, 0xe1, 0x99, 0x43, 0x9f, 0x82, 0x72,
+			  0xe7, 0xed, 0x94, 0x9e, 0xe1, 0x84, 0xee, 0x82,
+			  0xfd, 0x26, 0x23, 0xc4, 0x17, 0x8d, 0xf5, 0x04,
+			  0xeb, 0xb7, 0xbc, 0xb8, 0xf3, 0x68, 0xb7, 0xad,
+			  0x94, 0x8e, 0x05, 0x3f, 0x8a, 0x5d, 0x8d, 0x81,
+			  0x3e, 0x88, 0xa7, 0x8c, 0xa2, 0xd5, 0xdc, 0x76, },
+}, {
+	.ksize = 1,
+	.key = "B",
+	.plaintext = blake2_ordered_sequence,
+	.psize = 256,
+	.digest = (u8[]){ 0x22, 0x14, 0xf4, 0xb0, 0x4c, 0xa8, 0xb5, 0x7d,
+			  0xa7, 0x5c, 0x04, 0xeb, 0xd8, 0x8d, 0x04, 0x71,
+			  0xc7, 0x3c, 0xc7, 0x6e, 0x8b, 0x20, 0x36, 0x40,
+			  0x9d, 0xd0, 0x60, 0xc6, 0xe3, 0x0b, 0x6e, 0x50,
+			  0xf5, 0xaf, 0xf5, 0xc6, 0x3b, 0xe3, 0x84, 0x6a,
+			  0x93, 0x1b, 0x12, 0xd6, 0x18, 0x27, 0xba, 0x36, },
+}};
+
+static const struct hash_testvec blake2b_512_tv_template[] = {{
+	.plaintext = blake2_ordered_sequence,
+	.psize = 15,
+	.digest = (u8[]){ 0x44, 0x4b, 0x24, 0x0f, 0xe3, 0xed, 0x86, 0xd0,
+			  0xe2, 0xef, 0x4c, 0xe7, 0xd8, 0x51, 0xed, 0xde,
+			  0x22, 0x15, 0x55, 0x82, 0xaa, 0x09, 0x14, 0x79,
+			  0x7b, 0x72, 0x6c, 0xd0, 0x58, 0xb6, 0xf4, 0x59,
+			  0x32, 0xe0, 0xe1, 0x29, 0x51, 0x68, 0x76, 0x52,
+			  0x7b, 0x1d, 0xd8, 0x8f, 0xc6, 0x6d, 0x71, 0x19,
+			  0xf4, 0xab, 0x3b, 0xed, 0x93, 0xa6, 0x1a, 0x0e,
+			  0x2d, 0x2d, 0x2a, 0xea, 0xc3, 0x36, 0xd9, 0x58, },
+}, {
+	.ksize = 64,
+	.key = blake2_ordered_sequence,
+	.digest = (u8[]){ 0x10, 0xeb, 0xb6, 0x77, 0x00, 0xb1, 0x86, 0x8e,
+			  0xfb, 0x44, 0x17, 0x98, 0x7a, 0xcf, 0x46, 0x90,
+			  0xae, 0x9d, 0x97, 0x2f, 0xb7, 0xa5, 0x90, 0xc2,
+			  0xf0, 0x28, 0x71, 0x79, 0x9a, 0xaa, 0x47, 0x86,
+			  0xb5, 0xe9, 0x96, 0xe8, 0xf0, 0xf4, 0xeb, 0x98,
+			  0x1f, 0xc2, 0x14, 0xb0, 0x05, 0xf4, 0x2d, 0x2f,
+			  0xf4, 0x23, 0x34, 0x99, 0x39, 0x16, 0x53, 0xdf,
+			  0x7a, 0xef, 0xcb, 0xc1, 0x3f, 0xc5, 0x15, 0x68, },
+}, {
+	.ksize = 1,
+	.key = "B",
+	.plaintext = blake2_ordered_sequence,
+	.psize = 1,
+	.digest = (u8[]){ 0xd2, 0x11, 0x31, 0x29, 0x3f, 0xea, 0xca, 0x72,
+			  0x21, 0xe4, 0x06, 0x65, 0x05, 0x2a, 0xd1, 0x02,
+			  0xc0, 0x8d, 0x7b, 0xf1, 0x09, 0x3c, 0xef, 0x88,
+			  0xe1, 0x68, 0x0c, 0xf1, 0x3b, 0xa4, 0xe3, 0x03,
+			  0xed, 0xa0, 0xe3, 0x60, 0x58, 0xa0, 0xdb, 0x52,
+			  0x8a, 0x66, 0x43, 0x09, 0x60, 0x1a, 0xbb, 0x67,
+			  0xc5, 0x84, 0x31, 0x40, 0xfa, 0xde, 0xc1, 0xd0,
+			  0xff, 0x3f, 0x4a, 0x69, 0xd9, 0x92, 0x26, 0x86, },
+}, {
+	.ksize = 32,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 7,
+	.digest = (u8[]){ 0xa3, 0x3e, 0x50, 0xbc, 0xfb, 0xd9, 0xf0, 0x82,
+			  0xa6, 0xd1, 0xdf, 0xaf, 0x82, 0xd0, 0xcf, 0x84,
+			  0x9a, 0x25, 0x3c, 0xae, 0x6d, 0xb5, 0xaf, 0x01,
+			  0xd7, 0xaf, 0xed, 0x50, 0xdc, 0xe2, 0xba, 0xcc,
+			  0x8c, 0x38, 0xf5, 0x16, 0x89, 0x38, 0x86, 0xce,
+			  0x68, 0x10, 0x63, 0x64, 0xa5, 0x79, 0x53, 0xb5,
+			  0x2e, 0x8e, 0xbc, 0x0a, 0xce, 0x95, 0xc0, 0x1e,
+			  0x69, 0x59, 0x1d, 0x3b, 0xd8, 0x19, 0x90, 0xd7, },
+}, {
+	.ksize = 64,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 64,
+	.digest = (u8[]){ 0x65, 0x67, 0x6d, 0x80, 0x06, 0x17, 0x97, 0x2f,
+			  0xbd, 0x87, 0xe4, 0xb9, 0x51, 0x4e, 0x1c, 0x67,
+			  0x40, 0x2b, 0x7a, 0x33, 0x10, 0x96, 0xd3, 0xbf,
+			  0xac, 0x22, 0xf1, 0xab, 0xb9, 0x53, 0x74, 0xab,
+			  0xc9, 0x42, 0xf1, 0x6e, 0x9a, 0xb0, 0xea, 0xd3,
+			  0x3b, 0x87, 0xc9, 0x19, 0x68, 0xa6, 0xe5, 0x09,
+			  0xe1, 0x19, 0xff, 0x07, 0x78, 0x7b, 0x3e, 0xf4,
+			  0x83, 0xe1, 0xdc, 0xdc, 0xcf, 0x6e, 0x30, 0x22, },
+}, {
+	.ksize = 1,
+	.key = "B",
+	.plaintext = blake2_ordered_sequence,
+	.psize = 247,
+	.digest = (u8[]){ 0xc2, 0x96, 0x2c, 0x6b, 0x84, 0xff, 0xee, 0xea,
+			  0x9b, 0xb8, 0x55, 0x2d, 0x6b, 0xa5, 0xd5, 0xe5,
+			  0xbd, 0xb1, 0x54, 0xb6, 0x1e, 0xfb, 0x63, 0x16,
+			  0x6e, 0x22, 0x04, 0xf0, 0x82, 0x7a, 0xc6, 0x99,
+			  0xf7, 0x4c, 0xff, 0x93, 0x71, 0x57, 0x64, 0xd0,
+			  0x08, 0x60, 0x39, 0x98, 0xb8, 0xd2, 0x2b, 0x4e,
+			  0x81, 0x8d, 0xe4, 0x8f, 0xb2, 0x1e, 0x8f, 0x99,
+			  0x98, 0xf1, 0x02, 0x9b, 0x4c, 0x7c, 0x97, 0x1a, },
+}, {
+	.ksize = 32,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 256,
+	.digest = (u8[]){ 0x0f, 0x32, 0x05, 0x09, 0xad, 0x9f, 0x25, 0xf7,
+			  0xf2, 0x00, 0x71, 0xc9, 0x9f, 0x08, 0x58, 0xd1,
+			  0x67, 0xc3, 0xa6, 0x2c, 0x0d, 0xe5, 0x7c, 0x15,
+			  0x35, 0x18, 0x5a, 0x68, 0xc1, 0xca, 0x1c, 0x6e,
+			  0x0f, 0xc4, 0xf6, 0x0c, 0x43, 0xe1, 0xb4, 0x3d,
+			  0x28, 0xe4, 0xc7, 0xa1, 0xcf, 0x6b, 0x17, 0x4e,
+			  0xf1, 0x5b, 0xb5, 0x53, 0xd4, 0xa7, 0xd0, 0x5b,
+			  0xae, 0x15, 0x81, 0x15, 0xd0, 0x88, 0xa0, 0x3c, },
+}};
+
+static const struct hash_testvec blakes2s_128_tv_template[] = {{
+	.digest = (u8[]){ 0x64, 0x55, 0x0d, 0x6f, 0xfe, 0x2c, 0x0a, 0x01,
+			  0xa1, 0x4a, 0xba, 0x1e, 0xad, 0xe0, 0x20, 0x0c, },
+}, {
+	.plaintext = blake2_ordered_sequence,
+	.psize = 64,
+	.digest = (u8[]){ 0xdc, 0x66, 0xca, 0x8f, 0x03, 0x86, 0x58, 0x01,
+			  0xb0, 0xff, 0xe0, 0x6e, 0xd8, 0xa1, 0xa9, 0x0e, },
+}, {
+	.ksize = 16,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 1,
+	.digest = (u8[]){ 0x88, 0x1e, 0x42, 0xe7, 0xbb, 0x35, 0x80, 0x82,
+			  0x63, 0x7c, 0x0a, 0x0f, 0xd7, 0xec, 0x6c, 0x2f, },
+}, {
+	.ksize = 32,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 7,
+	.digest = (u8[]){ 0xcf, 0x9e, 0x07, 0x2a, 0xd5, 0x22, 0xf2, 0xcd,
+			  0xa2, 0xd8, 0x25, 0x21, 0x80, 0x86, 0x73, 0x1c, },
+}, {
+	.ksize = 1,
+	.key = "B",
+	.plaintext = blake2_ordered_sequence,
+	.psize = 15,
+	.digest = (u8[]){ 0xf6, 0x33, 0x5a, 0x2c, 0x22, 0xa0, 0x64, 0xb2,
+			  0xb6, 0x3f, 0xeb, 0xbc, 0xd1, 0xc3, 0xe5, 0xb2, },
+}, {
+	.ksize = 16,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 247,
+	.digest = (u8[]){ 0x72, 0x66, 0x49, 0x60, 0xf9, 0x4a, 0xea, 0xbe,
+			  0x1f, 0xf4, 0x60, 0xce, 0xb7, 0x81, 0xcb, 0x09, },
+}, {
+	.ksize = 32,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 256,
+	.digest = (u8[]){ 0xd5, 0xa4, 0x0e, 0xc3, 0x16, 0xc7, 0x51, 0xa6,
+			  0x3c, 0xd0, 0xd9, 0x11, 0x57, 0xfa, 0x1e, 0xbb, },
+}};
+
+static const struct hash_testvec blakes2s_160_tv_template[] = {{
+	.plaintext = blake2_ordered_sequence,
+	.psize = 7,
+	.digest = (u8[]){ 0xb4, 0xf2, 0x03, 0x49, 0x37, 0xed, 0xb1, 0x3e,
+			  0x5b, 0x2a, 0xca, 0x64, 0x82, 0x74, 0xf6, 0x62,
+			  0xe3, 0xf2, 0x84, 0xff, },
+}, {
+	.plaintext = blake2_ordered_sequence,
+	.psize = 256,
+	.digest = (u8[]){ 0xaa, 0x56, 0x9b, 0xdc, 0x98, 0x17, 0x75, 0xf2,
+			  0xb3, 0x68, 0x83, 0xb7, 0x9b, 0x8d, 0x48, 0xb1,
+			  0x9b, 0x2d, 0x35, 0x05, },
+}, {
+	.ksize = 1,
+	.key = "B",
+	.digest = (u8[]){ 0x50, 0x16, 0xe7, 0x0c, 0x01, 0xd0, 0xd3, 0xc3,
+			  0xf4, 0x3e, 0xb1, 0x6e, 0x97, 0xa9, 0x4e, 0xd1,
+			  0x79, 0x65, 0x32, 0x93, },
+}, {
+	.ksize = 32,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 1,
+	.digest = (u8[]){ 0x1c, 0x2b, 0xcd, 0x9a, 0x68, 0xca, 0x8c, 0x71,
+			  0x90, 0x29, 0x6c, 0x54, 0xfa, 0x56, 0x4a, 0xef,
+			  0xa2, 0x3a, 0x56, 0x9c, },
+}, {
+	.ksize = 16,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 15,
+	.digest = (u8[]){ 0x36, 0xc3, 0x5f, 0x9a, 0xdc, 0x7e, 0xbf, 0x19,
+			  0x68, 0xaa, 0xca, 0xd8, 0x81, 0xbf, 0x09, 0x34,
+			  0x83, 0x39, 0x0f, 0x30, },
+}, {
+	.ksize = 1,
+	.key = "B",
+	.plaintext = blake2_ordered_sequence,
+	.psize = 64,
+	.digest = (u8[]){ 0x86, 0x80, 0x78, 0xa4, 0x14, 0xec, 0x03, 0xe5,
+			  0xb6, 0x9a, 0x52, 0x0e, 0x42, 0xee, 0x39, 0x9d,
+			  0xac, 0xa6, 0x81, 0x63, },
+}, {
+	.ksize = 32,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 247,
+	.digest = (u8[]){ 0x2d, 0xd8, 0xd2, 0x53, 0x66, 0xfa, 0xa9, 0x01,
+			  0x1c, 0x9c, 0xaf, 0xa3, 0xe2, 0x9d, 0x9b, 0x10,
+			  0x0a, 0xf6, 0x73, 0xe8, },
+}};
+
+static const struct hash_testvec blakes2s_224_tv_template[] = {{
+	.plaintext = blake2_ordered_sequence,
+	.psize = 1,
+	.digest = (u8[]){ 0x61, 0xb9, 0x4e, 0xc9, 0x46, 0x22, 0xa3, 0x91,
+			  0xd2, 0xae, 0x42, 0xe6, 0x45, 0x6c, 0x90, 0x12,
+			  0xd5, 0x80, 0x07, 0x97, 0xb8, 0x86, 0x5a, 0xfc,
+			  0x48, 0x21, 0x97, 0xbb, },
+}, {
+	.plaintext = blake2_ordered_sequence,
+	.psize = 247,
+	.digest = (u8[]){ 0x9e, 0xda, 0xc7, 0x20, 0x2c, 0xd8, 0x48, 0x2e,
+			  0x31, 0x94, 0xab, 0x46, 0x6d, 0x94, 0xd8, 0xb4,
+			  0x69, 0xcd, 0xae, 0x19, 0x6d, 0x9e, 0x41, 0xcc,
+			  0x2b, 0xa4, 0xd5, 0xf6, },
+}, {
+	.ksize = 16,
+	.key = blake2_ordered_sequence,
+	.digest = (u8[]){ 0x32, 0xc0, 0xac, 0xf4, 0x3b, 0xd3, 0x07, 0x9f,
+			  0xbe, 0xfb, 0xfa, 0x4d, 0x6b, 0x4e, 0x56, 0xb3,
+			  0xaa, 0xd3, 0x27, 0xf6, 0x14, 0xbf, 0xb9, 0x32,
+			  0xa7, 0x19, 0xfc, 0xb8, },
+}, {
+	.ksize = 1,
+	.key = "B",
+	.plaintext = blake2_ordered_sequence,
+	.psize = 7,
+	.digest = (u8[]){ 0x73, 0xad, 0x5e, 0x6d, 0xb9, 0x02, 0x8e, 0x76,
+			  0xf2, 0x66, 0x42, 0x4b, 0x4c, 0xfa, 0x1f, 0xe6,
+			  0x2e, 0x56, 0x40, 0xe5, 0xa2, 0xb0, 0x3c, 0xe8,
+			  0x7b, 0x45, 0xfe, 0x05, },
+}, {
+	.ksize = 32,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 15,
+	.digest = (u8[]){ 0x16, 0x60, 0xfb, 0x92, 0x54, 0xb3, 0x6e, 0x36,
+			  0x81, 0xf4, 0x16, 0x41, 0xc3, 0x3d, 0xd3, 0x43,
+			  0x84, 0xed, 0x10, 0x6f, 0x65, 0x80, 0x7a, 0x3e,
+			  0x25, 0xab, 0xc5, 0x02, },
+}, {
+	.ksize = 16,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 64,
+	.digest = (u8[]){ 0xca, 0xaa, 0x39, 0x67, 0x9c, 0xf7, 0x6b, 0xc7,
+			  0xb6, 0x82, 0xca, 0x0e, 0x65, 0x36, 0x5b, 0x7c,
+			  0x24, 0x00, 0xfa, 0x5f, 0xda, 0x06, 0x91, 0x93,
+			  0x6a, 0x31, 0x83, 0xb5, },
+}, {
+	.ksize = 1,
+	.key = "B",
+	.plaintext = blake2_ordered_sequence,
+	.psize = 256,
+	.digest = (u8[]){ 0x90, 0x02, 0x26, 0xb5, 0x06, 0x9c, 0x36, 0x86,
+			  0x94, 0x91, 0x90, 0x1e, 0x7d, 0x2a, 0x71, 0xb2,
+			  0x48, 0xb5, 0xe8, 0x16, 0xfd, 0x64, 0x33, 0x45,
+			  0xb3, 0xd7, 0xec, 0xcc, },
+}};
+
+static const struct hash_testvec blakes2s_256_tv_template[] = {{
+	.plaintext = blake2_ordered_sequence,
+	.psize = 15,
+	.digest = (u8[]){ 0xd9, 0x7c, 0x82, 0x8d, 0x81, 0x82, 0xa7, 0x21,
+			  0x80, 0xa0, 0x6a, 0x78, 0x26, 0x83, 0x30, 0x67,
+			  0x3f, 0x7c, 0x4e, 0x06, 0x35, 0x94, 0x7c, 0x04,
+			  0xc0, 0x23, 0x23, 0xfd, 0x45, 0xc0, 0xa5, 0x2d, },
+}, {
+	.ksize = 32,
+	.key = blake2_ordered_sequence,
+	.digest = (u8[]){ 0x48, 0xa8, 0x99, 0x7d, 0xa4, 0x07, 0x87, 0x6b,
+			  0x3d, 0x79, 0xc0, 0xd9, 0x23, 0x25, 0xad, 0x3b,
+			  0x89, 0xcb, 0xb7, 0x54, 0xd8, 0x6a, 0xb7, 0x1a,
+			  0xee, 0x04, 0x7a, 0xd3, 0x45, 0xfd, 0x2c, 0x49, },
+}, {
+	.ksize = 1,
+	.key = "B",
+	.plaintext = blake2_ordered_sequence,
+	.psize = 1,
+	.digest = (u8[]){ 0x22, 0x27, 0xae, 0xaa, 0x6e, 0x81, 0x56, 0x03,
+			  0xa7, 0xe3, 0xa1, 0x18, 0xa5, 0x9a, 0x2c, 0x18,
+			  0xf4, 0x63, 0xbc, 0x16, 0x70, 0xf1, 0xe7, 0x4b,
+			  0x00, 0x6d, 0x66, 0x16, 0xae, 0x9e, 0x74, 0x4e, },
+}, {
+	.ksize = 16,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 7,
+	.digest = (u8[]){ 0x58, 0x5d, 0xa8, 0x60, 0x1c, 0xa4, 0xd8, 0x03,
+			  0x86, 0x86, 0x84, 0x64, 0xd7, 0xa0, 0x8e, 0x15,
+			  0x2f, 0x05, 0xa2, 0x1b, 0xbc, 0xef, 0x7a, 0x34,
+			  0xb3, 0xc5, 0xbc, 0x4b, 0xf0, 0x32, 0xeb, 0x12, },
+}, {
+	.ksize = 32,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 64,
+	.digest = (u8[]){ 0x89, 0x75, 0xb0, 0x57, 0x7f, 0xd3, 0x55, 0x66,
+			  0xd7, 0x50, 0xb3, 0x62, 0xb0, 0x89, 0x7a, 0x26,
+			  0xc3, 0x99, 0x13, 0x6d, 0xf0, 0x7b, 0xab, 0xab,
+			  0xbd, 0xe6, 0x20, 0x3f, 0xf2, 0x95, 0x4e, 0xd4, },
+}, {
+	.ksize = 1,
+	.key = "B",
+	.plaintext = blake2_ordered_sequence,
+	.psize = 247,
+	.digest = (u8[]){ 0x2e, 0x74, 0x1c, 0x1d, 0x03, 0xf4, 0x9d, 0x84,
+			  0x6f, 0xfc, 0x86, 0x32, 0x92, 0x49, 0x7e, 0x66,
+			  0xd7, 0xc3, 0x10, 0x88, 0xfe, 0x28, 0xb3, 0xe0,
+			  0xbf, 0x50, 0x75, 0xad, 0x8e, 0xa4, 0xe6, 0xb2, },
+}, {
+	.ksize = 16,
+	.key = blake2_ordered_sequence,
+	.plaintext = blake2_ordered_sequence,
+	.psize = 256,
+	.digest = (u8[]){ 0xb9, 0xd2, 0x81, 0x0e, 0x3a, 0xb1, 0x62, 0x9b,
+			  0xad, 0x44, 0x05, 0xf4, 0x92, 0x2e, 0x99, 0xc1,
+			  0x4a, 0x47, 0xbb, 0x5b, 0x6f, 0xb2, 0x96, 0xed,
+			  0xd5, 0x06, 0xb5, 0x3a, 0x7c, 0x7a, 0x65, 0x1d, },
+}};
+
 #endif	/* _CRYPTO_TESTMGR_H */
diff --git a/crypto/tgr192.c b/crypto/tgr192.c
index 052648e24909..aa29c529b44e 100644
--- a/crypto/tgr192.c
+++ b/crypto/tgr192.c
@@ -555,7 +555,7 @@ static int tgr192_final(struct shash_desc *desc, u8 * out)
 	__le32 *le32p;
 	u32 t, msb, lsb;
 
-	tgr192_update(desc, NULL, 0); /* flush */ ;
+	tgr192_update(desc, NULL, 0); /* flush */
 
 	msb = 0;
 	t = tctx->nblocks;
@@ -583,7 +583,7 @@ static int tgr192_final(struct shash_desc *desc, u8 * out)
 		while (tctx->count < 64) {
 			tctx->hash[tctx->count++] = 0;
 		}
-		tgr192_update(desc, NULL, 0); /* flush */ ;
+		tgr192_update(desc, NULL, 0); /* flush */
 		memset(tctx->hash, 0, 56);    /* fill next block with zeroes */
 	}
 	/* append the 64 bit count */
diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index 131c35ee9ed3..e358d0046494 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -170,9 +170,9 @@ rewind:
 		if (ip == ctx->ip) {
 			if (entry->instruction >= ctx->instructions ||
 			    !ctx->ins_table[entry->instruction].run) {
-				pr_warning(FW_WARN APEI_PFX
-			"Invalid action table, unknown instruction type: %d\n",
-					   entry->instruction);
+				pr_warn(FW_WARN APEI_PFX
+					"Invalid action table, unknown instruction type: %d\n",
+					entry->instruction);
 				return -EINVAL;
 			}
 			run = ctx->ins_table[entry->instruction].run;
@@ -211,9 +211,9 @@ static int apei_exec_for_each_entry(struct apei_exec_context *ctx,
 		if (end)
 			*end = i;
 		if (ins >= ctx->instructions || !ins_table[ins].run) {
-			pr_warning(FW_WARN APEI_PFX
-			"Invalid action table, unknown instruction type: %d\n",
-				   ins);
+			pr_warn(FW_WARN APEI_PFX
+				"Invalid action table, unknown instruction type: %d\n",
+				ins);
 			return -EINVAL;
 		}
 		rc = func(ctx, entry, data);
@@ -579,18 +579,18 @@ static int apei_check_gar(struct acpi_generic_address *reg, u64 *paddr,
 	space_id = reg->space_id;
 	*paddr = get_unaligned(&reg->address);
 	if (!*paddr) {
-		pr_warning(FW_BUG APEI_PFX
-			   "Invalid physical address in GAR [0x%llx/%u/%u/%u/%u]\n",
-			   *paddr, bit_width, bit_offset, access_size_code,
-			   space_id);
+		pr_warn(FW_BUG APEI_PFX
+			"Invalid physical address in GAR [0x%llx/%u/%u/%u/%u]\n",
+			*paddr, bit_width, bit_offset, access_size_code,
+			space_id);
 		return -EINVAL;
 	}
 
 	if (access_size_code < 1 || access_size_code > 4) {
-		pr_warning(FW_BUG APEI_PFX
-			   "Invalid access size code in GAR [0x%llx/%u/%u/%u/%u]\n",
-			   *paddr, bit_width, bit_offset, access_size_code,
-			   space_id);
+		pr_warn(FW_BUG APEI_PFX
+			"Invalid access size code in GAR [0x%llx/%u/%u/%u/%u]\n",
+			*paddr, bit_width, bit_offset, access_size_code,
+			space_id);
 		return -EINVAL;
 	}
 	*access_bit_width = 1UL << (access_size_code + 2);
@@ -604,19 +604,19 @@ static int apei_check_gar(struct acpi_generic_address *reg, u64 *paddr,
 		*access_bit_width = 64;
 
 	if ((bit_width + bit_offset) > *access_bit_width) {
-		pr_warning(FW_BUG APEI_PFX
-			   "Invalid bit width + offset in GAR [0x%llx/%u/%u/%u/%u]\n",
-			   *paddr, bit_width, bit_offset, access_size_code,
-			   space_id);
+		pr_warn(FW_BUG APEI_PFX
+			"Invalid bit width + offset in GAR [0x%llx/%u/%u/%u/%u]\n",
+			*paddr, bit_width, bit_offset, access_size_code,
+			space_id);
 		return -EINVAL;
 	}
 
 	if (space_id != ACPI_ADR_SPACE_SYSTEM_MEMORY &&
 	    space_id != ACPI_ADR_SPACE_SYSTEM_IO) {
-		pr_warning(FW_BUG APEI_PFX
-			   "Invalid address space type in GAR [0x%llx/%u/%u/%u/%u]\n",
-			   *paddr, bit_width, bit_offset, access_size_code,
-			   space_id);
+		pr_warn(FW_BUG APEI_PFX
+			"Invalid address space type in GAR [0x%llx/%u/%u/%u/%u]\n",
+			*paddr, bit_width, bit_offset, access_size_code,
+			space_id);
 		return -EINVAL;
 	}
 
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index e430cf4caec2..086373f8ccb1 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -172,7 +172,7 @@ static int einj_get_available_error_type(u32 *type)
 static int einj_timedout(u64 *t)
 {
 	if ((s64)*t < SPIN_UNIT) {
-		pr_warning(FW_WARN "Firmware does not respond in time\n");
+		pr_warn(FW_WARN "Firmware does not respond in time\n");
 		return 1;
 	}
 	*t -= SPIN_UNIT;
@@ -312,7 +312,7 @@ static int __einj_error_trigger(u64 trigger_paddr, u32 type,
 	}
 	rc = einj_check_trigger_header(trigger_tab);
 	if (rc) {
-		pr_warning(FW_BUG "Invalid trigger error action table.\n");
+		pr_warn(FW_BUG "Invalid trigger error action table.\n");
 		goto out_rel_header;
 	}
 
diff --git a/drivers/acpi/apei/erst-dbg.c b/drivers/acpi/apei/erst-dbg.c
index d0f3a46716e9..c740f0faad39 100644
--- a/drivers/acpi/apei/erst-dbg.c
+++ b/drivers/acpi/apei/erst-dbg.c
@@ -118,9 +118,8 @@ retry:
 	if (rc < 0)
 		goto out;
 	if (len > ERST_DBG_RECORD_LEN_MAX) {
-		pr_warning(ERST_DBG_PFX
-			   "Record (ID: 0x%llx) length is too long: %zd\n",
-			   id, len);
+		pr_warn(ERST_DBG_PFX
+			"Record (ID: 0x%llx) length is too long: %zd\n", id, len);
 		rc = -EIO;
 		goto out;
 	}
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 777f6f7122b4..8906c80175e6 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -235,10 +235,10 @@ static struct ghes *ghes_new(struct acpi_hest_generic *generic)
 		goto err_unmap_read_ack_addr;
 	error_block_length = generic->error_block_length;
 	if (error_block_length > GHES_ESTATUS_MAX_SIZE) {
-		pr_warning(FW_WARN GHES_PFX
-			   "Error status block length is too long: %u for "
-			   "generic hardware error source: %d.\n",
-			   error_block_length, generic->header.source_id);
+		pr_warn(FW_WARN GHES_PFX
+			"Error status block length is too long: %u for "
+			"generic hardware error source: %d.\n",
+			error_block_length, generic->header.source_id);
 		error_block_length = GHES_ESTATUS_MAX_SIZE;
 	}
 	ghes->estatus = kmalloc(error_block_length, GFP_KERNEL);
@@ -748,8 +748,8 @@ static void ghes_add_timer(struct ghes *ghes)
 	unsigned long expire;
 
 	if (!g->notify.poll_interval) {
-		pr_warning(FW_WARN GHES_PFX "Poll interval is 0 for generic hardware error source: %d, disabled.\n",
-			   g->header.source_id);
+		pr_warn(FW_WARN GHES_PFX "Poll interval is 0 for generic hardware error source: %d, disabled.\n",
+			g->header.source_id);
 		return;
 	}
 	expire = jiffies + msecs_to_jiffies(g->notify.poll_interval);
@@ -1155,21 +1155,20 @@ static int ghes_probe(struct platform_device *ghes_dev)
 		}
 		break;
 	case ACPI_HEST_NOTIFY_LOCAL:
-		pr_warning(GHES_PFX "Generic hardware error source: %d notified via local interrupt is not supported!\n",
-			   generic->header.source_id);
+		pr_warn(GHES_PFX "Generic hardware error source: %d notified via local interrupt is not supported!\n",
+			generic->header.source_id);
 		goto err;
 	default:
-		pr_warning(FW_WARN GHES_PFX "Unknown notification type: %u for generic hardware error source: %d\n",
-			   generic->notify.type, generic->header.source_id);
+		pr_warn(FW_WARN GHES_PFX "Unknown notification type: %u for generic hardware error source: %d\n",
+			generic->notify.type, generic->header.source_id);
 		goto err;
 	}
 
 	rc = -EIO;
 	if (generic->error_block_length <
 	    sizeof(struct acpi_hest_generic_status)) {
-		pr_warning(FW_BUG GHES_PFX "Invalid error block length: %u for generic hardware error source: %d\n",
-			   generic->error_block_length,
-			   generic->header.source_id);
+		pr_warn(FW_BUG GHES_PFX "Invalid error block length: %u for generic hardware error source: %d\n",
+			generic->error_block_length, generic->header.source_id);
 		goto err;
 	}
 	ghes = ghes_new(generic);
diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c
index 267bdbf6a7bf..822402480f7d 100644
--- a/drivers/acpi/apei/hest.c
+++ b/drivers/acpi/apei/hest.c
@@ -92,15 +92,15 @@ int apei_hest_parse(apei_hest_func_t func, void *data)
 	for (i = 0; i < hest_tab->error_source_count; i++) {
 		len = hest_esrc_len(hest_hdr);
 		if (!len) {
-			pr_warning(FW_WARN HEST_PFX
-				   "Unknown or unused hardware error source "
-				   "type: %d for hardware error source: %d.\n",
-				   hest_hdr->type, hest_hdr->source_id);
+			pr_warn(FW_WARN HEST_PFX
+				"Unknown or unused hardware error source "
+				"type: %d for hardware error source: %d.\n",
+				hest_hdr->type, hest_hdr->source_id);
 			return -EINVAL;
 		}
 		if ((void *)hest_hdr + len >
 		    (void *)hest_tab + hest_tab->header.length) {
-			pr_warning(FW_BUG HEST_PFX
+			pr_warn(FW_BUG HEST_PFX
 		"Table contents overflow for hardware error source: %d.\n",
 				hest_hdr->source_id);
 			return -EINVAL;
@@ -164,8 +164,8 @@ static int __init hest_parse_ghes(struct acpi_hest_header *hest_hdr, void *data)
 		ghes_dev = ghes_arr->ghes_devs[i];
 		hdr = *(struct acpi_hest_header **)ghes_dev->dev.platform_data;
 		if (hdr->source_id == hest_hdr->source_id) {
-			pr_warning(FW_WARN HEST_PFX "Duplicated hardware error source ID: %d.\n",
-				   hdr->source_id);
+			pr_warn(FW_WARN HEST_PFX "Duplicated hardware error source ID: %d.\n",
+				hdr->source_id);
 			return -EIO;
 		}
 	}
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 558fedf8a7a1..8f0e0c8d8c3d 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -1176,7 +1176,7 @@ static const struct file_operations acpi_battery_alarm_fops = {
 
 static int acpi_battery_add_fs(struct acpi_device *device)
 {
-	pr_warning(PREFIX "Deprecated procfs I/F for battery is loaded, please retry with CONFIG_ACPI_PROCFS_POWER cleared\n");
+	pr_warn(PREFIX "Deprecated procfs I/F for battery is loaded, please retry with CONFIG_ACPI_PROCFS_POWER cleared\n");
 	if (!acpi_device_dir(device)) {
 		acpi_device_dir(device) = proc_mkdir(acpi_device_bid(device),
 						     acpi_battery_dir);
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 2a3e392751e0..3b4448972374 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -413,8 +413,8 @@ static void acpi_dev_get_irqresource(struct resource *res, u32 gsi,
 		u8 pol = p ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
 
 		if (triggering != trig || polarity != pol) {
-			pr_warning("ACPI: IRQ %d override to %s, %s\n", gsi,
-				   t ? "level" : "edge", p ? "low" : "high");
+			pr_warn("ACPI: IRQ %d override to %s, %s\n", gsi,
+				t ? "level" : "edge", p ? "low" : "high");
 			triggering = trig;
 			polarity = pol;
 		}
diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c
index 753985c01517..46dc54d18f0b 100644
--- a/drivers/ata/acard-ahci.c
+++ b/drivers/ata/acard-ahci.c
@@ -56,7 +56,7 @@ struct acard_sg {
 	__le32			size;	 /* bit 31 (EOT) max==0x10000 (64k) */
 };
 
-static void acard_ahci_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc);
 static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc);
 static int acard_ahci_port_start(struct ata_port *ap);
 static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
@@ -210,7 +210,7 @@ static unsigned int acard_ahci_fill_sg(struct ata_queued_cmd *qc, void *cmd_tbl)
 	return si;
 }
 
-static void acard_ahci_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct ahci_port_priv *pp = ap->private_data;
@@ -248,6 +248,8 @@ static void acard_ahci_qc_prep(struct ata_queued_cmd *qc)
 		opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH;
 
 	ahci_fill_cmd_slot(pp, qc->hw_tag, opts);
+
+	return AC_ERR_OK;
 }
 
 static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 05c2b32dcc4d..ec6c64fce74a 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -56,6 +56,7 @@ enum board_ids {
 	board_ahci_yes_fbs,
 
 	/* board IDs for specific chipsets in alphabetical order */
+	board_ahci_al,
 	board_ahci_avn,
 	board_ahci_mcp65,
 	board_ahci_mcp77,
@@ -167,6 +168,13 @@ static const struct ata_port_info ahci_port_info[] = {
 		.port_ops	= &ahci_ops,
 	},
 	/* by chipsets */
+	[board_ahci_al] = {
+		AHCI_HFLAGS	(AHCI_HFLAG_NO_PMP | AHCI_HFLAG_NO_MSI),
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= ATA_PIO4,
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &ahci_ops,
+	},
 	[board_ahci_avn] = {
 		.flags		= AHCI_FLAG_COMMON,
 		.pio_mask	= ATA_PIO4,
@@ -415,6 +423,11 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(ATI, 0x4394), board_ahci_sb700 }, /* ATI SB700/800 */
 	{ PCI_VDEVICE(ATI, 0x4395), board_ahci_sb700 }, /* ATI SB700/800 */
 
+	/* Amazon's Annapurna Labs support */
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031),
+		.class = PCI_CLASS_STORAGE_SATA_AHCI,
+		.class_mask = 0xffffff,
+		board_ahci_al },
 	/* AMD */
 	{ PCI_VDEVICE(AMD, 0x7800), board_ahci }, /* AMD Hudson-2 */
 	{ PCI_VDEVICE(AMD, 0x7900), board_ahci }, /* AMD CZ */
diff --git a/drivers/ata/ahci_tegra.c b/drivers/ata/ahci_tegra.c
index e3163dae5e85..cb55ebc1725b 100644
--- a/drivers/ata/ahci_tegra.c
+++ b/drivers/ata/ahci_tegra.c
@@ -483,7 +483,6 @@ static int tegra_ahci_probe(struct platform_device *pdev)
 	struct tegra_ahci_priv *tegra;
 	struct resource *res;
 	int ret;
-	unsigned int i;
 
 	hpriv = ahci_platform_get_resources(pdev, 0);
 	if (IS_ERR(hpriv))
@@ -543,8 +542,9 @@ static int tegra_ahci_probe(struct platform_device *pdev)
 	if (!tegra->supplies)
 		return -ENOMEM;
 
-	for (i = 0; i < tegra->soc->num_supplies; i++)
-		tegra->supplies[i].supply = tegra->soc->supply_names[i];
+	regulator_bulk_set_supply_names(tegra->supplies,
+					tegra->soc->supply_names,
+					tegra->soc->num_supplies);
 
 	ret = devm_regulator_bulk_get(&pdev->dev,
 				      tegra->soc->num_supplies,
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index e4da725381d3..3ca7720e7d8f 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -841,6 +841,12 @@ static int piix_broken_suspend(void)
 			},
 		},
 		{
+			.ident = "TECRA M3",
+			.matches = {
+				DMI_MATCH(DMI_OEM_STRING, "Tecra M3,"),
+			},
+		},
+		{
 			.ident = "TECRA M4",
 			.matches = {
 				DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
@@ -955,18 +961,10 @@ static int piix_broken_suspend(void)
 
 		{ }	/* terminate list */
 	};
-	static const char *oemstrs[] = {
-		"Tecra M3,",
-	};
-	int i;
 
 	if (dmi_check_system(sysids))
 		return 1;
 
-	for (i = 0; i < ARRAY_SIZE(oemstrs); i++)
-		if (dmi_find_device(DMI_DEV_TYPE_OEM_STRING, oemstrs[i], NULL))
-			return 1;
-
 	/* TECRA M4 sometimes forgets its identify and reports bogus
 	 * DMI information.  As the bogus information is a bit
 	 * generic, match as many entries as possible.  This manual
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index bff369d9a1a7..ea5bf5f4cbed 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -57,7 +57,7 @@ static int ahci_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val);
 static bool ahci_qc_fill_rtf(struct ata_queued_cmd *qc);
 static int ahci_port_start(struct ata_port *ap);
 static void ahci_port_stop(struct ata_port *ap);
-static void ahci_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc);
 static int ahci_pmp_qc_defer(struct ata_queued_cmd *qc);
 static void ahci_freeze(struct ata_port *ap);
 static void ahci_thaw(struct ata_port *ap);
@@ -1624,7 +1624,7 @@ static int ahci_pmp_qc_defer(struct ata_queued_cmd *qc)
 		return sata_pmp_qc_defer_cmd_switch(qc);
 }
 
-static void ahci_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct ahci_port_priv *pp = ap->private_data;
@@ -1660,6 +1660,8 @@ static void ahci_qc_prep(struct ata_queued_cmd *qc)
 		opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH;
 
 	ahci_fill_cmd_slot(pp, qc->hw_tag, opts);
+
+	return AC_ERR_OK;
 }
 
 static void ahci_fbs_dec_intr(struct ata_port *ap)
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 28c492be0a57..e9017c570bc5 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4980,7 +4980,10 @@ int ata_std_qc_defer(struct ata_queued_cmd *qc)
 	return ATA_DEFER_LINK;
 }
 
-void ata_noop_qc_prep(struct ata_queued_cmd *qc) { }
+enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc)
+{
+	return AC_ERR_OK;
+}
 
 /**
  *	ata_sg_init - Associate command with scatter-gather table.
@@ -5443,7 +5446,9 @@ void ata_qc_issue(struct ata_queued_cmd *qc)
 		return;
 	}
 
-	ap->ops->qc_prep(qc);
+	qc->err_mask |= ap->ops->qc_prep(qc);
+	if (unlikely(qc->err_mask))
+		goto err;
 	trace_ata_qc_issue(qc);
 	qc->err_mask |= ap->ops->qc_issue(qc);
 	if (unlikely(qc->err_mask))
@@ -6708,6 +6713,9 @@ void ata_host_detach(struct ata_host *host)
 {
 	int i;
 
+	/* Ensure ata_port probe has completed */
+	async_synchronize_full();
+
 	for (i = 0; i < host->n_ports; i++)
 		ata_port_detach(host->ports[i]);
 
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index 4ed682da52ae..038db94216a9 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -2679,12 +2679,14 @@ static void ata_bmdma_fill_sg_dumb(struct ata_queued_cmd *qc)
  *	LOCKING:
  *	spin_lock_irqsave(host lock)
  */
-void ata_bmdma_qc_prep(struct ata_queued_cmd *qc)
+enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	ata_bmdma_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep);
 
@@ -2697,12 +2699,14 @@ EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep);
  *	LOCKING:
  *	spin_lock_irqsave(host lock)
  */
-void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc)
+enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	ata_bmdma_fill_sg_dumb(qc);
+
+	return AC_ERR_OK;
 }
 EXPORT_SYMBOL_GPL(ata_bmdma_dumb_qc_prep);
 
diff --git a/drivers/ata/pata_artop.c b/drivers/ata/pata_artop.c
index 3aa006c5ed0c..6bd2228bb6ff 100644
--- a/drivers/ata/pata_artop.c
+++ b/drivers/ata/pata_artop.c
@@ -100,7 +100,7 @@ static void artop6210_load_piomode(struct ata_port *ap, struct ata_device *adev,
 {
 	struct pci_dev *pdev	= to_pci_dev(ap->host->dev);
 	int dn = adev->devno + 2 * ap->port_no;
-	const u16 timing[2][5] = {
+	static const u16 timing[2][5] = {
 		{ 0x0000, 0x000A, 0x0008, 0x0303, 0x0301 },
 		{ 0x0700, 0x070A, 0x0708, 0x0403, 0x0401 }
 
@@ -154,7 +154,7 @@ static void artop6260_load_piomode (struct ata_port *ap, struct ata_device *adev
 {
 	struct pci_dev *pdev	= to_pci_dev(ap->host->dev);
 	int dn = adev->devno + 2 * ap->port_no;
-	const u8 timing[2][5] = {
+	static const u8 timing[2][5] = {
 		{ 0x00, 0x0A, 0x08, 0x33, 0x31 },
 		{ 0x70, 0x7A, 0x78, 0x43, 0x41 }
 
diff --git a/drivers/ata/pata_falcon.c b/drivers/ata/pata_falcon.c
index 41e0d6a6cd05..27b0952fde6b 100644
--- a/drivers/ata/pata_falcon.c
+++ b/drivers/ata/pata_falcon.c
@@ -33,7 +33,6 @@
 #define DRV_NAME "pata_falcon"
 #define DRV_VERSION "0.1.0"
 
-#define ATA_HD_BASE	0xfff00000
 #define ATA_HD_CONTROL	0x39
 
 static struct scsi_host_template pata_falcon_sht = {
@@ -120,24 +119,22 @@ static struct ata_port_operations pata_falcon_ops = {
 	.set_mode	= pata_falcon_set_mode,
 };
 
-static int pata_falcon_init_one(void)
+static int __init pata_falcon_init_one(struct platform_device *pdev)
 {
+	struct resource *res;
 	struct ata_host *host;
 	struct ata_port *ap;
-	struct platform_device *pdev;
 	void __iomem *base;
 
-	if (!MACH_IS_ATARI || !ATARIHW_PRESENT(IDE))
-		return -ENODEV;
-
-	pr_info(DRV_NAME ": Atari Falcon PATA controller\n");
+	dev_info(&pdev->dev, "Atari Falcon PATA controller\n");
 
-	pdev = platform_device_register_simple(DRV_NAME, 0, NULL, 0);
-	if (IS_ERR(pdev))
-		return PTR_ERR(pdev);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENODEV;
 
-	if (!devm_request_mem_region(&pdev->dev, ATA_HD_BASE, 0x40, DRV_NAME)) {
-		pr_err(DRV_NAME ": resources busy\n");
+	if (!devm_request_mem_region(&pdev->dev, res->start,
+				     resource_size(res), DRV_NAME)) {
+		dev_err(&pdev->dev, "resources busy\n");
 		return -EBUSY;
 	}
 
@@ -152,7 +149,7 @@ static int pata_falcon_init_one(void)
 	ap->flags |= ATA_FLAG_SLAVE_POSS | ATA_FLAG_NO_IORDY;
 	ap->flags |= ATA_FLAG_PIO_POLLING;
 
-	base = (void __iomem *)ATA_HD_BASE;
+	base = (void __iomem *)res->start;
 	ap->ioaddr.data_addr		= base;
 	ap->ioaddr.error_addr		= base + 1 + 1 * 4;
 	ap->ioaddr.feature_addr		= base + 1 + 1 * 4;
@@ -174,9 +171,26 @@ static int pata_falcon_init_one(void)
 	return ata_host_activate(host, 0, NULL, 0, &pata_falcon_sht);
 }
 
-module_init(pata_falcon_init_one);
+static int __exit pata_falcon_remove_one(struct platform_device *pdev)
+{
+	struct ata_host *host = platform_get_drvdata(pdev);
+
+	ata_host_detach(host);
+
+	return 0;
+}
+
+static struct platform_driver pata_falcon_driver = {
+	.remove = __exit_p(pata_falcon_remove_one),
+	.driver   = {
+		.name	= "atari-falcon-ide",
+	},
+};
+
+module_platform_driver_probe(pata_falcon_driver, pata_falcon_init_one);
 
 MODULE_AUTHOR("Bartlomiej Zolnierkiewicz");
 MODULE_DESCRIPTION("low-level driver for Atari Falcon PATA");
 MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:atari-falcon-ide");
 MODULE_VERSION(DRV_VERSION);
diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
index 57f2ec71cfc3..1bfd0154dad5 100644
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@@ -510,7 +510,7 @@ static int pata_macio_cable_detect(struct ata_port *ap)
 	return ATA_CBL_PATA40;
 }
 
-static void pata_macio_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc)
 {
 	unsigned int write = (qc->tf.flags & ATA_TFLAG_WRITE);
 	struct ata_port *ap = qc->ap;
@@ -523,7 +523,7 @@ static void pata_macio_qc_prep(struct ata_queued_cmd *qc)
 		   __func__, qc, qc->flags, write, qc->dev->devno);
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	table = (struct dbdma_cmd *) priv->dma_table_cpu;
 
@@ -568,6 +568,8 @@ static void pata_macio_qc_prep(struct ata_queued_cmd *qc)
 	table->command = cpu_to_le16(DBDMA_STOP);
 
 	dev_dbgdma(priv->dev, "%s: %d DMA list entries\n", __func__, pi);
+
+	return AC_ERR_OK;
 }
 
 
diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c
index 4afcb8e63e21..41430f79663c 100644
--- a/drivers/ata/pata_pxa.c
+++ b/drivers/ata/pata_pxa.c
@@ -44,25 +44,27 @@ static void pxa_ata_dma_irq(void *d)
 /*
  * Prepare taskfile for submission.
  */
-static void pxa_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pxa_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct pata_pxa_data *pd = qc->ap->private_data;
 	struct dma_async_tx_descriptor *tx;
 	enum dma_transfer_direction dir;
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	dir = (qc->dma_dir == DMA_TO_DEVICE ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM);
 	tx = dmaengine_prep_slave_sg(pd->dma_chan, qc->sg, qc->n_elem, dir,
 				     DMA_PREP_INTERRUPT);
 	if (!tx) {
 		ata_dev_err(qc->dev, "prep_slave_sg() failed\n");
-		return;
+		return AC_ERR_OK;
 	}
 	tx->callback = pxa_ata_dma_irq;
 	tx->callback_param = pd;
 	pd->dma_cookie = dmaengine_submit(tx);
+
+	return AC_ERR_OK;
 }
 
 /*
diff --git a/drivers/ata/pdc_adma.c b/drivers/ata/pdc_adma.c
index cb490531b62e..5db55e1e2a61 100644
--- a/drivers/ata/pdc_adma.c
+++ b/drivers/ata/pdc_adma.c
@@ -116,7 +116,7 @@ static int adma_ata_init_one(struct pci_dev *pdev,
 				const struct pci_device_id *ent);
 static int adma_port_start(struct ata_port *ap);
 static void adma_port_stop(struct ata_port *ap);
-static void adma_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int adma_qc_issue(struct ata_queued_cmd *qc);
 static int adma_check_atapi_dma(struct ata_queued_cmd *qc);
 static void adma_freeze(struct ata_port *ap);
@@ -295,7 +295,7 @@ static int adma_fill_sg(struct ata_queued_cmd *qc)
 	return i;
 }
 
-static void adma_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct adma_port_priv *pp = qc->ap->private_data;
 	u8  *buf = pp->pkt;
@@ -306,7 +306,7 @@ static void adma_qc_prep(struct ata_queued_cmd *qc)
 
 	adma_enter_reg_mode(qc->ap);
 	if (qc->tf.protocol != ATA_PROT_DMA)
-		return;
+		return AC_ERR_OK;
 
 	buf[i++] = 0;	/* Response flags */
 	buf[i++] = 0;	/* reserved */
@@ -371,6 +371,7 @@ static void adma_qc_prep(struct ata_queued_cmd *qc)
 			printk("%s\n", obuf);
 	}
 #endif
+	return AC_ERR_OK;
 }
 
 static inline void adma_packet_start(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index 8e9cb198fcd1..9239615d8a04 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -502,7 +502,7 @@ static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc,
 	return num_prde;
 }
 
-static void sata_fsl_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sata_fsl_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct sata_fsl_port_priv *pp = ap->private_data;
@@ -548,6 +548,8 @@ static void sata_fsl_qc_prep(struct ata_queued_cmd *qc)
 
 	VPRINTK("SATA FSL : xx_qc_prep, di = 0x%x, ttl = %d, num_prde = %d\n",
 		desc_info, ttl_dwords, num_prde);
+
+	return AC_ERR_OK;
 }
 
 static unsigned int sata_fsl_qc_issue(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c
index 7f99e23bff88..a6b76cc12a66 100644
--- a/drivers/ata/sata_inic162x.c
+++ b/drivers/ata/sata_inic162x.c
@@ -478,7 +478,7 @@ static void inic_fill_sg(struct inic_prd *prd, struct ata_queued_cmd *qc)
 	prd[-1].flags |= PRD_END;
 }
 
-static void inic_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors inic_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct inic_port_priv *pp = qc->ap->private_data;
 	struct inic_pkt *pkt = pp->pkt;
@@ -538,6 +538,8 @@ static void inic_qc_prep(struct ata_queued_cmd *qc)
 		inic_fill_sg(prd, qc);
 
 	pp->cpb_tbl[0] = pp->pkt_dma;
+
+	return AC_ERR_OK;
 }
 
 static unsigned int inic_qc_issue(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index ad385a113391..277f11909fc1 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -592,8 +592,8 @@ static int mv5_scr_write(struct ata_link *link, unsigned int sc_reg_in, u32 val)
 static int mv_port_start(struct ata_port *ap);
 static void mv_port_stop(struct ata_port *ap);
 static int mv_qc_defer(struct ata_queued_cmd *qc);
-static void mv_qc_prep(struct ata_queued_cmd *qc);
-static void mv_qc_prep_iie(struct ata_queued_cmd *qc);
+static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc);
 static unsigned int mv_qc_issue(struct ata_queued_cmd *qc);
 static int mv_hardreset(struct ata_link *link, unsigned int *class,
 			unsigned long deadline);
@@ -2031,7 +2031,7 @@ static void mv_rw_multi_errata_sata24(struct ata_queued_cmd *qc)
  *      LOCKING:
  *      Inherited from caller.
  */
-static void mv_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct mv_port_priv *pp = ap->private_data;
@@ -2043,15 +2043,15 @@ static void mv_qc_prep(struct ata_queued_cmd *qc)
 	switch (tf->protocol) {
 	case ATA_PROT_DMA:
 		if (tf->command == ATA_CMD_DSM)
-			return;
+			return AC_ERR_OK;
 		/* fall-thru */
 	case ATA_PROT_NCQ:
 		break;	/* continue below */
 	case ATA_PROT_PIO:
 		mv_rw_multi_errata_sata24(qc);
-		return;
+		return AC_ERR_OK;
 	default:
-		return;
+		return AC_ERR_OK;
 	}
 
 	/* Fill in command request block
@@ -2098,12 +2098,10 @@ static void mv_qc_prep(struct ata_queued_cmd *qc)
 		 * non-NCQ mode are: [RW] STREAM DMA and W DMA FUA EXT, none
 		 * of which are defined/used by Linux.  If we get here, this
 		 * driver needs work.
-		 *
-		 * FIXME: modify libata to give qc_prep a return value and
-		 * return error here.
 		 */
-		BUG_ON(tf->command);
-		break;
+		ata_port_err(ap, "%s: unsupported command: %.2x\n", __func__,
+				tf->command);
+		return AC_ERR_INVALID;
 	}
 	mv_crqb_pack_cmd(cw++, tf->nsect, ATA_REG_NSECT, 0);
 	mv_crqb_pack_cmd(cw++, tf->hob_lbal, ATA_REG_LBAL, 0);
@@ -2116,8 +2114,10 @@ static void mv_qc_prep(struct ata_queued_cmd *qc)
 	mv_crqb_pack_cmd(cw++, tf->command, ATA_REG_CMD, 1);	/* last */
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 	mv_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 /**
@@ -2132,7 +2132,7 @@ static void mv_qc_prep(struct ata_queued_cmd *qc)
  *      LOCKING:
  *      Inherited from caller.
  */
-static void mv_qc_prep_iie(struct ata_queued_cmd *qc)
+static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct mv_port_priv *pp = ap->private_data;
@@ -2143,9 +2143,9 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc)
 
 	if ((tf->protocol != ATA_PROT_DMA) &&
 	    (tf->protocol != ATA_PROT_NCQ))
-		return;
+		return AC_ERR_OK;
 	if (tf->command == ATA_CMD_DSM)
-		return;  /* use bmdma for this */
+		return AC_ERR_OK;  /* use bmdma for this */
 
 	/* Fill in Gen IIE command request block */
 	if (!(tf->flags & ATA_TFLAG_WRITE))
@@ -2186,8 +2186,10 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc)
 		);
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 	mv_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 /**
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index 56946012d113..65ec8dff1c51 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -297,7 +297,7 @@ static void nv_ck804_freeze(struct ata_port *ap);
 static void nv_ck804_thaw(struct ata_port *ap);
 static int nv_adma_slave_config(struct scsi_device *sdev);
 static int nv_adma_check_atapi_dma(struct ata_queued_cmd *qc);
-static void nv_adma_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc);
 static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance);
 static void nv_adma_irq_clear(struct ata_port *ap);
@@ -319,7 +319,7 @@ static void nv_mcp55_freeze(struct ata_port *ap);
 static void nv_swncq_error_handler(struct ata_port *ap);
 static int nv_swncq_slave_config(struct scsi_device *sdev);
 static int nv_swncq_port_start(struct ata_port *ap);
-static void nv_swncq_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc);
 static void nv_swncq_fill_sg(struct ata_queued_cmd *qc);
 static unsigned int nv_swncq_qc_issue(struct ata_queued_cmd *qc);
 static void nv_swncq_irq_clear(struct ata_port *ap, u16 fis);
@@ -1344,7 +1344,7 @@ static int nv_adma_use_reg_mode(struct ata_queued_cmd *qc)
 	return 1;
 }
 
-static void nv_adma_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct nv_adma_port_priv *pp = qc->ap->private_data;
 	struct nv_adma_cpb *cpb = &pp->cpb[qc->hw_tag];
@@ -1356,7 +1356,7 @@ static void nv_adma_qc_prep(struct ata_queued_cmd *qc)
 			(qc->flags & ATA_QCFLAG_DMAMAP));
 		nv_adma_register_mode(qc->ap);
 		ata_bmdma_qc_prep(qc);
-		return;
+		return AC_ERR_OK;
 	}
 
 	cpb->resp_flags = NV_CPB_RESP_DONE;
@@ -1388,6 +1388,8 @@ static void nv_adma_qc_prep(struct ata_queued_cmd *qc)
 	cpb->ctl_flags = ctl_flags;
 	wmb();
 	cpb->resp_flags = 0;
+
+	return AC_ERR_OK;
 }
 
 static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc)
@@ -1950,17 +1952,19 @@ static int nv_swncq_port_start(struct ata_port *ap)
 	return 0;
 }
 
-static void nv_swncq_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (qc->tf.protocol != ATA_PROT_NCQ) {
 		ata_bmdma_qc_prep(qc);
-		return;
+		return AC_ERR_OK;
 	}
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	nv_swncq_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 static void nv_swncq_fill_sg(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c
index 5fd464765ddc..c451d7d1c817 100644
--- a/drivers/ata/sata_promise.c
+++ b/drivers/ata/sata_promise.c
@@ -139,7 +139,7 @@ static int pdc_sata_scr_write(struct ata_link *link, unsigned int sc_reg, u32 va
 static int pdc_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 static int pdc_common_port_start(struct ata_port *ap);
 static int pdc_sata_port_start(struct ata_port *ap);
-static void pdc_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc);
 static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static int pdc_check_atapi_dma(struct ata_queued_cmd *qc);
@@ -633,7 +633,7 @@ static void pdc_fill_sg(struct ata_queued_cmd *qc)
 	prd[idx - 1].flags_len |= cpu_to_le32(ATA_PRD_EOT);
 }
 
-static void pdc_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct pdc_port_priv *pp = qc->ap->private_data;
 	unsigned int i;
@@ -665,6 +665,8 @@ static void pdc_qc_prep(struct ata_queued_cmd *qc)
 	default:
 		break;
 	}
+
+	return AC_ERR_OK;
 }
 
 static int pdc_is_sataii_tx4(unsigned long flags)
diff --git a/drivers/ata/sata_qstor.c b/drivers/ata/sata_qstor.c
index c53c5a47204d..ef00ab644afb 100644
--- a/drivers/ata/sata_qstor.c
+++ b/drivers/ata/sata_qstor.c
@@ -100,7 +100,7 @@ static int qs_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val);
 static int qs_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 static int qs_port_start(struct ata_port *ap);
 static void qs_host_stop(struct ata_host *host);
-static void qs_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int qs_qc_issue(struct ata_queued_cmd *qc);
 static int qs_check_atapi_dma(struct ata_queued_cmd *qc);
 static void qs_freeze(struct ata_port *ap);
@@ -260,7 +260,7 @@ static unsigned int qs_fill_sg(struct ata_queued_cmd *qc)
 	return si;
 }
 
-static void qs_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct qs_port_priv *pp = qc->ap->private_data;
 	u8 dflags = QS_DF_PORD, *buf = pp->pkt;
@@ -272,7 +272,7 @@ static void qs_qc_prep(struct ata_queued_cmd *qc)
 
 	qs_enter_reg_mode(qc->ap);
 	if (qc->tf.protocol != ATA_PROT_DMA)
-		return;
+		return AC_ERR_OK;
 
 	nelem = qs_fill_sg(qc);
 
@@ -295,6 +295,8 @@ static void qs_qc_prep(struct ata_queued_cmd *qc)
 
 	/* frame information structure (FIS) */
 	ata_tf_to_fis(&qc->tf, 0, 1, &buf[32]);
+
+	return AC_ERR_OK;
 }
 
 static inline void qs_packet_start(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c
index 3495e1733a8e..980aacdbcf3b 100644
--- a/drivers/ata/sata_rcar.c
+++ b/drivers/ata/sata_rcar.c
@@ -550,12 +550,14 @@ static void sata_rcar_bmdma_fill_sg(struct ata_queued_cmd *qc)
 	prd[si - 1].addr |= cpu_to_le32(SATA_RCAR_DTEND);
 }
 
-static void sata_rcar_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sata_rcar_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	sata_rcar_bmdma_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 static void sata_rcar_bmdma_setup(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index e6fbae2f645a..75321f1ceba5 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -103,7 +103,7 @@ static void sil_dev_config(struct ata_device *dev);
 static int sil_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val);
 static int sil_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val);
 static int sil_set_mode(struct ata_link *link, struct ata_device **r_failed);
-static void sil_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc);
 static void sil_bmdma_setup(struct ata_queued_cmd *qc);
 static void sil_bmdma_start(struct ata_queued_cmd *qc);
 static void sil_bmdma_stop(struct ata_queued_cmd *qc);
@@ -317,12 +317,14 @@ static void sil_fill_sg(struct ata_queued_cmd *qc)
 		last_prd->flags_len |= cpu_to_le32(ATA_PRD_EOT);
 }
 
-static void sil_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	sil_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 static unsigned char sil_get_device_cache_line(struct pci_dev *pdev)
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index 7bef82de53ca..560070d4f1d0 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -326,7 +326,7 @@ static void sil24_dev_config(struct ata_device *dev);
 static int sil24_scr_read(struct ata_link *link, unsigned sc_reg, u32 *val);
 static int sil24_scr_write(struct ata_link *link, unsigned sc_reg, u32 val);
 static int sil24_qc_defer(struct ata_queued_cmd *qc);
-static void sil24_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc);
 static bool sil24_qc_fill_rtf(struct ata_queued_cmd *qc);
 static void sil24_pmp_attach(struct ata_port *ap);
@@ -830,7 +830,7 @@ static int sil24_qc_defer(struct ata_queued_cmd *qc)
 	return ata_std_qc_defer(qc);
 }
 
-static void sil24_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct sil24_port_priv *pp = ap->private_data;
@@ -874,6 +874,8 @@ static void sil24_qc_prep(struct ata_queued_cmd *qc)
 
 	if (qc->flags & ATA_QCFLAG_DMAMAP)
 		sil24_fill_sg(qc, sge);
+
+	return AC_ERR_OK;
 }
 
 static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index 2277ba0c9c7f..2c7b30c5ea3d 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -202,7 +202,7 @@ static void pdc_error_handler(struct ata_port *ap);
 static void pdc_freeze(struct ata_port *ap);
 static void pdc_thaw(struct ata_port *ap);
 static int pdc_port_start(struct ata_port *ap);
-static void pdc20621_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc);
 static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static unsigned int pdc20621_dimm_init(struct ata_host *host);
@@ -530,7 +530,7 @@ static void pdc20621_nodata_prep(struct ata_queued_cmd *qc)
 	VPRINTK("ata pkt buf ofs %u, mmio copied\n", i);
 }
 
-static void pdc20621_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc)
 {
 	switch (qc->tf.protocol) {
 	case ATA_PROT_DMA:
@@ -542,6 +542,8 @@ static void pdc20621_qc_prep(struct ata_queued_cmd *qc)
 	default:
 		break;
 	}
+
+	return AC_ERR_OK;
 }
 
 static void __pdc20621_push_hdma(struct ata_queued_cmd *qc,
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 5d52a2d32155..de2f94d0103a 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -268,19 +268,18 @@ static int drbd_adm_prepare(struct drbd_config_context *adm_ctx,
 	/* some more paranoia, if the request was over-determined */
 	if (adm_ctx->device && adm_ctx->resource &&
 	    adm_ctx->device->resource != adm_ctx->resource) {
-		pr_warning("request: minor=%u, resource=%s; but that minor belongs to resource %s\n",
-				adm_ctx->minor, adm_ctx->resource->name,
-				adm_ctx->device->resource->name);
+		pr_warn("request: minor=%u, resource=%s; but that minor belongs to resource %s\n",
+			adm_ctx->minor, adm_ctx->resource->name,
+			adm_ctx->device->resource->name);
 		drbd_msg_put_info(adm_ctx->reply_skb, "minor exists in different resource");
 		return ERR_INVALID_REQUEST;
 	}
 	if (adm_ctx->device &&
 	    adm_ctx->volume != VOLUME_UNSPECIFIED &&
 	    adm_ctx->volume != adm_ctx->device->vnr) {
-		pr_warning("request: minor=%u, volume=%u; but that minor is volume %u in %s\n",
-				adm_ctx->minor, adm_ctx->volume,
-				adm_ctx->device->vnr,
-				adm_ctx->device->resource->name);
+		pr_warn("request: minor=%u, volume=%u; but that minor is volume %u in %s\n",
+			adm_ctx->minor, adm_ctx->volume,
+			adm_ctx->device->vnr, adm_ctx->device->resource->name);
 		drbd_msg_put_info(adm_ctx->reply_skb, "minor exists as different volume");
 		return ERR_INVALID_REQUEST;
 	}
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f6f77eaa7217..739b372a5112 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -417,18 +417,20 @@ out_free_page:
 	return ret;
 }
 
-static int lo_discard(struct loop_device *lo, struct request *rq, loff_t pos)
+static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
+			int mode)
 {
 	/*
-	 * We use punch hole to reclaim the free space used by the
-	 * image a.k.a. discard. However we do not support discard if
-	 * encryption is enabled, because it may give an attacker
-	 * useful information.
+	 * We use fallocate to manipulate the space mappings used by the image
+	 * a.k.a. discard/zerorange. However we do not support this if
+	 * encryption is enabled, because it may give an attacker useful
+	 * information.
 	 */
 	struct file *file = lo->lo_backing_file;
-	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
 	int ret;
 
+	mode |= FALLOC_FL_KEEP_SIZE;
+
 	if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) {
 		ret = -EOPNOTSUPP;
 		goto out;
@@ -596,9 +598,17 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	switch (req_op(rq)) {
 	case REQ_OP_FLUSH:
 		return lo_req_flush(lo, rq);
-	case REQ_OP_DISCARD:
 	case REQ_OP_WRITE_ZEROES:
-		return lo_discard(lo, rq, pos);
+		/*
+		 * If the caller doesn't want deallocation, call zeroout to
+		 * write zeroes the range.  Otherwise, punch them out.
+		 */
+		return lo_fallocate(lo, rq, pos,
+			(rq->cmd_flags & REQ_NOUNMAP) ?
+				FALLOC_FL_ZERO_RANGE :
+				FALLOC_FL_PUNCH_HOLE);
+	case REQ_OP_DISCARD:
+		return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE);
 	case REQ_OP_WRITE:
 		if (lo->transfer)
 			return lo_write_transfer(lo, rq, pos);
@@ -630,7 +640,9 @@ static void loop_reread_partitions(struct loop_device *lo,
 {
 	int rc;
 
-	rc = blkdev_reread_part(bdev);
+	mutex_lock(&bdev->bd_mutex);
+	rc = bdev_disk_changed(bdev, false);
+	mutex_unlock(&bdev->bd_mutex);
 	if (rc)
 		pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n",
 			__func__, lo->lo_number, lo->lo_file_name, rc);
@@ -1154,10 +1166,11 @@ out_unlock:
 		 * must be at least one and it can only become zero when the
 		 * current holder is released.
 		 */
-		if (release)
-			err = __blkdev_reread_part(bdev);
-		else
-			err = blkdev_reread_part(bdev);
+		if (!release)
+			mutex_lock(&bdev->bd_mutex);
+		err = bdev_disk_changed(bdev, false);
+		if (!release)
+			mutex_unlock(&bdev->bd_mutex);
 		if (err)
 			pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
 				__func__, lo_number, err);
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 964f78cfffa0..f6bafa9a68b9 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -129,7 +129,7 @@ struct mtip_compat_ide_task_request_s {
 /*
  * This function check_for_surprise_removal is called
  * while card is removed from the system and it will
- * read the vendor id from the configration space
+ * read the vendor id from the configuration space
  *
  * @pdev Pointer to the pci_dev structure.
  *
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 19e75999bb15..57532465fb83 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1032,14 +1032,15 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 		sockfd_put(sock);
 		return -ENOMEM;
 	}
+
+	config->socks = socks;
+
 	nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL);
 	if (!nsock) {
 		sockfd_put(sock);
 		return -ENOMEM;
 	}
 
-	config->socks = socks;
-
 	nsock->fallback_index = -1;
 	nsock->dead = false;
 	mutex_init(&nsock->tx_lock);
diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h
index a235c45e22a7..bc837862b767 100644
--- a/drivers/block/null_blk.h
+++ b/drivers/block/null_blk.h
@@ -91,11 +91,13 @@ struct nullb {
 #ifdef CONFIG_BLK_DEV_ZONED
 int null_zone_init(struct nullb_device *dev);
 void null_zone_exit(struct nullb_device *dev);
-int null_zone_report(struct gendisk *disk, sector_t sector,
-		     struct blk_zone *zones, unsigned int *nr_zones);
+int null_report_zones(struct gendisk *disk, sector_t sector,
+		      unsigned int nr_zones, report_zones_cb cb, void *data);
 blk_status_t null_handle_zoned(struct nullb_cmd *cmd,
 				enum req_opf op, sector_t sector,
 				sector_t nr_sectors);
+size_t null_zone_valid_read_len(struct nullb *nullb,
+				sector_t sector, unsigned int len);
 #else
 static inline int null_zone_init(struct nullb_device *dev)
 {
@@ -103,17 +105,18 @@ static inline int null_zone_init(struct nullb_device *dev)
 	return -EINVAL;
 }
 static inline void null_zone_exit(struct nullb_device *dev) {}
-static inline int null_zone_report(struct gendisk *disk, sector_t sector,
-				   struct blk_zone *zones,
-				   unsigned int *nr_zones)
-{
-	return -EOPNOTSUPP;
-}
 static inline blk_status_t null_handle_zoned(struct nullb_cmd *cmd,
 					     enum req_opf op, sector_t sector,
 					     sector_t nr_sectors)
 {
 	return BLK_STS_NOTSUPP;
 }
+static inline size_t null_zone_valid_read_len(struct nullb *nullb,
+					      sector_t sector,
+					      unsigned int len)
+{
+	return len;
+}
+#define null_report_zones	NULL
 #endif /* CONFIG_BLK_DEV_ZONED */
 #endif /* __NULL_BLK_H */
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index 0e7da5015ccd..795fda576824 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk_main.c
@@ -227,7 +227,7 @@ static ssize_t nullb_device_uint_attr_store(unsigned int *val,
 	int result;
 
 	result = kstrtouint(page, 0, &tmp);
-	if (result)
+	if (result < 0)
 		return result;
 
 	*val = tmp;
@@ -241,7 +241,7 @@ static ssize_t nullb_device_ulong_attr_store(unsigned long *val,
 	unsigned long tmp;
 
 	result = kstrtoul(page, 0, &tmp);
-	if (result)
+	if (result < 0)
 		return result;
 
 	*val = tmp;
@@ -255,7 +255,7 @@ static ssize_t nullb_device_bool_attr_store(bool *val, const char *page,
 	int result;
 
 	result = kstrtobool(page,  &tmp);
-	if (result)
+	if (result < 0)
 		return result;
 
 	*val = tmp;
@@ -263,7 +263,7 @@ static ssize_t nullb_device_bool_attr_store(bool *val, const char *page,
 }
 
 /* The following macro should only be used with TYPE = {uint, ulong, bool}. */
-#define NULLB_DEVICE_ATTR(NAME, TYPE)						\
+#define NULLB_DEVICE_ATTR(NAME, TYPE, APPLY)					\
 static ssize_t									\
 nullb_device_##NAME##_show(struct config_item *item, char *page)		\
 {										\
@@ -274,31 +274,57 @@ static ssize_t									\
 nullb_device_##NAME##_store(struct config_item *item, const char *page,		\
 			    size_t count)					\
 {										\
-	if (test_bit(NULLB_DEV_FL_CONFIGURED, &to_nullb_device(item)->flags))	\
-		return -EBUSY;							\
-	return nullb_device_##TYPE##_attr_store(				\
-			&to_nullb_device(item)->NAME, page, count);		\
+	int (*apply_fn)(struct nullb_device *dev, TYPE new_value) = APPLY;	\
+	struct nullb_device *dev = to_nullb_device(item);			\
+	TYPE new_value;								\
+	int ret;								\
+										\
+	ret = nullb_device_##TYPE##_attr_store(&new_value, page, count);	\
+	if (ret < 0)								\
+		return ret;							\
+	if (apply_fn)								\
+		ret = apply_fn(dev, new_value);					\
+	else if (test_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags)) 		\
+		ret = -EBUSY;							\
+	if (ret < 0)								\
+		return ret;							\
+	dev->NAME = new_value;							\
+	return count;								\
 }										\
 CONFIGFS_ATTR(nullb_device_, NAME);
 
-NULLB_DEVICE_ATTR(size, ulong);
-NULLB_DEVICE_ATTR(completion_nsec, ulong);
-NULLB_DEVICE_ATTR(submit_queues, uint);
-NULLB_DEVICE_ATTR(home_node, uint);
-NULLB_DEVICE_ATTR(queue_mode, uint);
-NULLB_DEVICE_ATTR(blocksize, uint);
-NULLB_DEVICE_ATTR(irqmode, uint);
-NULLB_DEVICE_ATTR(hw_queue_depth, uint);
-NULLB_DEVICE_ATTR(index, uint);
-NULLB_DEVICE_ATTR(blocking, bool);
-NULLB_DEVICE_ATTR(use_per_node_hctx, bool);
-NULLB_DEVICE_ATTR(memory_backed, bool);
-NULLB_DEVICE_ATTR(discard, bool);
-NULLB_DEVICE_ATTR(mbps, uint);
-NULLB_DEVICE_ATTR(cache_size, ulong);
-NULLB_DEVICE_ATTR(zoned, bool);
-NULLB_DEVICE_ATTR(zone_size, ulong);
-NULLB_DEVICE_ATTR(zone_nr_conv, uint);
+static int nullb_apply_submit_queues(struct nullb_device *dev,
+				     unsigned int submit_queues)
+{
+	struct nullb *nullb = dev->nullb;
+	struct blk_mq_tag_set *set;
+
+	if (!nullb)
+		return 0;
+
+	set = nullb->tag_set;
+	blk_mq_update_nr_hw_queues(set, submit_queues);
+	return set->nr_hw_queues == submit_queues ? 0 : -ENOMEM;
+}
+
+NULLB_DEVICE_ATTR(size, ulong, NULL);
+NULLB_DEVICE_ATTR(completion_nsec, ulong, NULL);
+NULLB_DEVICE_ATTR(submit_queues, uint, nullb_apply_submit_queues);
+NULLB_DEVICE_ATTR(home_node, uint, NULL);
+NULLB_DEVICE_ATTR(queue_mode, uint, NULL);
+NULLB_DEVICE_ATTR(blocksize, uint, NULL);
+NULLB_DEVICE_ATTR(irqmode, uint, NULL);
+NULLB_DEVICE_ATTR(hw_queue_depth, uint, NULL);
+NULLB_DEVICE_ATTR(index, uint, NULL);
+NULLB_DEVICE_ATTR(blocking, bool, NULL);
+NULLB_DEVICE_ATTR(use_per_node_hctx, bool, NULL);
+NULLB_DEVICE_ATTR(memory_backed, bool, NULL);
+NULLB_DEVICE_ATTR(discard, bool, NULL);
+NULLB_DEVICE_ATTR(mbps, uint, NULL);
+NULLB_DEVICE_ATTR(cache_size, ulong, NULL);
+NULLB_DEVICE_ATTR(zoned, bool, NULL);
+NULLB_DEVICE_ATTR(zone_size, ulong, NULL);
+NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
 {
@@ -467,7 +493,7 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
 
 static ssize_t memb_group_features_show(struct config_item *item, char *page)
 {
-	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size\n");
+	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_nr_conv\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -996,6 +1022,16 @@ next:
 	return 0;
 }
 
+static void nullb_fill_pattern(struct nullb *nullb, struct page *page,
+			       unsigned int len, unsigned int off)
+{
+	void *dst;
+
+	dst = kmap_atomic(page);
+	memset(dst + off, 0xFF, len);
+	kunmap_atomic(dst);
+}
+
 static void null_handle_discard(struct nullb *nullb, sector_t sector, size_t n)
 {
 	size_t temp;
@@ -1036,10 +1072,24 @@ static int null_transfer(struct nullb *nullb, struct page *page,
 	unsigned int len, unsigned int off, bool is_write, sector_t sector,
 	bool is_fua)
 {
+	struct nullb_device *dev = nullb->dev;
+	unsigned int valid_len = len;
 	int err = 0;
 
 	if (!is_write) {
-		err = copy_from_nullb(nullb, page, off, sector, len);
+		if (dev->zoned)
+			valid_len = null_zone_valid_read_len(nullb,
+				sector, len);
+
+		if (valid_len) {
+			err = copy_from_nullb(nullb, page, off,
+				sector, valid_len);
+			off += valid_len;
+			len -= valid_len;
+		}
+
+		if (len)
+			nullb_fill_pattern(nullb, page, len, off);
 		flush_dcache_page(page);
 	} else {
 		flush_dcache_page(page);
@@ -1418,20 +1468,9 @@ static void null_config_discard(struct nullb *nullb)
 	blk_queue_flag_set(QUEUE_FLAG_DISCARD, nullb->q);
 }
 
-static int null_open(struct block_device *bdev, fmode_t mode)
-{
-	return 0;
-}
-
-static void null_release(struct gendisk *disk, fmode_t mode)
-{
-}
-
-static const struct block_device_operations null_fops = {
-	.owner =	THIS_MODULE,
-	.open =		null_open,
-	.release =	null_release,
-	.report_zones =	null_zone_report,
+static const struct block_device_operations null_ops = {
+	.owner		= THIS_MODULE,
+	.report_zones	= null_report_zones,
 };
 
 static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
@@ -1532,7 +1571,7 @@ static int null_gendisk_register(struct nullb *nullb)
 	disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO;
 	disk->major		= null_major;
 	disk->first_minor	= nullb->index;
-	disk->fops		= &null_fops;
+	disk->fops		= &null_ops;
 	disk->private_data	= nullb;
 	disk->queue		= nullb->q;
 	strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
index 3d7fdea872f8..d4d88b581822 100644
--- a/drivers/block/null_blk_zoned.c
+++ b/drivers/block/null_blk_zoned.c
@@ -66,22 +66,53 @@ void null_zone_exit(struct nullb_device *dev)
 	kvfree(dev->zones);
 }
 
-int null_zone_report(struct gendisk *disk, sector_t sector,
-		     struct blk_zone *zones, unsigned int *nr_zones)
+int null_report_zones(struct gendisk *disk, sector_t sector,
+		unsigned int nr_zones, report_zones_cb cb, void *data)
 {
 	struct nullb *nullb = disk->private_data;
 	struct nullb_device *dev = nullb->dev;
-	unsigned int zno, nrz = 0;
-
-	zno = null_zone_no(dev, sector);
-	if (zno < dev->nr_zones) {
-		nrz = min_t(unsigned int, *nr_zones, dev->nr_zones - zno);
-		memcpy(zones, &dev->zones[zno], nrz * sizeof(struct blk_zone));
+	unsigned int first_zone, i;
+	struct blk_zone zone;
+	int error;
+
+	first_zone = null_zone_no(dev, sector);
+	if (first_zone >= dev->nr_zones)
+		return 0;
+
+	nr_zones = min(nr_zones, dev->nr_zones - first_zone);
+	for (i = 0; i < nr_zones; i++) {
+		/*
+		 * Stacked DM target drivers will remap the zone information by
+		 * modifying the zone information passed to the report callback.
+		 * So use a local copy to avoid corruption of the device zone
+		 * array.
+		 */
+		memcpy(&zone, &dev->zones[first_zone + i],
+		       sizeof(struct blk_zone));
+		error = cb(&zone, i, data);
+		if (error)
+			return error;
 	}
 
-	*nr_zones = nrz;
+	return nr_zones;
+}
 
-	return 0;
+size_t null_zone_valid_read_len(struct nullb *nullb,
+				sector_t sector, unsigned int len)
+{
+	struct nullb_device *dev = nullb->dev;
+	struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)];
+	unsigned int nr_sectors = len >> SECTOR_SHIFT;
+
+	/* Read must be below the write pointer position */
+	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL ||
+	    sector + nr_sectors <= zone->wp)
+		return len;
+
+	if (sector > zone->wp)
+		return 0;
+
+	return (zone->wp - sector) << SECTOR_SHIFT;
 }
 
 static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
@@ -118,14 +149,14 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 	return BLK_STS_OK;
 }
 
-static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector)
+static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
+				   sector_t sector)
 {
 	struct nullb_device *dev = cmd->nq->dev;
-	unsigned int zno = null_zone_no(dev, sector);
-	struct blk_zone *zone = &dev->zones[zno];
+	struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)];
 	size_t i;
 
-	switch (req_op(cmd->rq)) {
+	switch (op) {
 	case REQ_OP_ZONE_RESET_ALL:
 		for (i = 0; i < dev->nr_zones; i++) {
 			if (zone[i].type == BLK_ZONE_TYPE_CONVENTIONAL)
@@ -141,6 +172,29 @@ static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector)
 		zone->cond = BLK_ZONE_COND_EMPTY;
 		zone->wp = zone->start;
 		break;
+	case REQ_OP_ZONE_OPEN:
+		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+			return BLK_STS_IOERR;
+		if (zone->cond == BLK_ZONE_COND_FULL)
+			return BLK_STS_IOERR;
+
+		zone->cond = BLK_ZONE_COND_EXP_OPEN;
+		break;
+	case REQ_OP_ZONE_CLOSE:
+		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+			return BLK_STS_IOERR;
+		if (zone->cond == BLK_ZONE_COND_FULL)
+			return BLK_STS_IOERR;
+
+		zone->cond = BLK_ZONE_COND_CLOSED;
+		break;
+	case REQ_OP_ZONE_FINISH:
+		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+			return BLK_STS_IOERR;
+
+		zone->cond = BLK_ZONE_COND_FULL;
+		zone->wp = zone->start + zone->len;
+		break;
 	default:
 		return BLK_STS_NOTSUPP;
 	}
@@ -155,7 +209,10 @@ blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op,
 		return null_zone_write(cmd, sector, nr_sectors);
 	case REQ_OP_ZONE_RESET:
 	case REQ_OP_ZONE_RESET_ALL:
-		return null_zone_reset(cmd, sector);
+	case REQ_OP_ZONE_OPEN:
+	case REQ_OP_ZONE_CLOSE:
+	case REQ_OP_ZONE_FINISH:
+		return null_zone_mgmt(cmd, op, sector);
 	default:
 		return BLK_STS_OK;
 	}
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index 6626c84f66d1..5b21dc421c94 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -742,7 +742,7 @@ static int probe_gdrom(struct platform_device *devptr)
 	int err;
 	/* Start the device */
 	if (gdrom_execute_diagnostic() != 1) {
-		pr_warning("ATA Probe for GDROM failed\n");
+		pr_warn("ATA Probe for GDROM failed\n");
 		return -ENODEV;
 	}
 	/* Print out firmware ID */
@@ -814,7 +814,7 @@ probe_fail_no_disk:
 probe_fail_no_mem:
 	unregister_blkdev(gdrom_major, GDROM_DEV_NAME);
 	gdrom_major = 0;
-	pr_warning("Probe failed - error is 0x%X\n", err);
+	pr_warn("Probe failed - error is 0x%X\n", err);
 	return err;
 }
 
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index 59f25286befe..3daae8ddd511 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -308,6 +308,19 @@ config HW_RANDOM_HISI
 
 	  If unsure, say Y.
 
+config HW_RANDOM_HISI_V2
+	tristate "HiSilicon True Random Number Generator V2 support"
+	depends on HW_RANDOM && ARM64 && ACPI
+	default HW_RANDOM
+	help
+	  This driver provides kernel-side support for the True Random Number
+	  Generator V2 hardware found on HiSilicon Hi1620 SoC.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called hisi-trng-v2.
+
+	  If unsure, say Y.
+
 config HW_RANDOM_ST
 	tristate "ST Microelectronics HW Random Number Generator support"
 	depends on HW_RANDOM && ARCH_STI
@@ -440,6 +453,19 @@ config HW_RANDOM_OPTEE
 
 	  If unsure, say Y.
 
+config HW_RANDOM_NPCM
+	tristate "NPCM Random Number Generator support"
+	depends on ARCH_NPCM || COMPILE_TEST
+	default HW_RANDOM
+	help
+ 	  This driver provides support for the Random Number
+	  Generator hardware available in Nuvoton NPCM SoCs.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called npcm-rng.
+
+ 	  If unsure, say Y.
+
 endif # HW_RANDOM
 
 config UML_RANDOM
@@ -458,7 +484,7 @@ config UML_RANDOM
 	  /dev/hwrng and injects the entropy into /dev/random.
 
 config HW_RANDOM_KEYSTONE
-	depends on ARCH_KEYSTONE
+	depends on ARCH_KEYSTONE || COMPILE_TEST
 	default HW_RANDOM
 	tristate "TI Keystone NETCP SA Hardware random number generator"
 	help
diff --git a/drivers/char/hw_random/Makefile b/drivers/char/hw_random/Makefile
index 7c9ef4a7667f..a7801b49ce6c 100644
--- a/drivers/char/hw_random/Makefile
+++ b/drivers/char/hw_random/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_HW_RANDOM_NOMADIK) += nomadik-rng.o
 obj-$(CONFIG_HW_RANDOM_PSERIES) += pseries-rng.o
 obj-$(CONFIG_HW_RANDOM_POWERNV) += powernv-rng.o
 obj-$(CONFIG_HW_RANDOM_HISI)	+= hisi-rng.o
+obj-$(CONFIG_HW_RANDOM_HISI_V2) += hisi-trng-v2.o
 obj-$(CONFIG_HW_RANDOM_BCM2835) += bcm2835-rng.o
 obj-$(CONFIG_HW_RANDOM_IPROC_RNG200) += iproc-rng200.o
 obj-$(CONFIG_HW_RANDOM_ST) += st-rng.o
@@ -39,3 +40,4 @@ obj-$(CONFIG_HW_RANDOM_MTK)	+= mtk-rng.o
 obj-$(CONFIG_HW_RANDOM_S390) += s390-trng.o
 obj-$(CONFIG_HW_RANDOM_KEYSTONE) += ks-sa-rng.o
 obj-$(CONFIG_HW_RANDOM_OPTEE) += optee-rng.o
+obj-$(CONFIG_HW_RANDOM_NPCM) += npcm-rng.o
diff --git a/drivers/char/hw_random/atmel-rng.c b/drivers/char/hw_random/atmel-rng.c
index e55705745d5e..ecb71c4317a5 100644
--- a/drivers/char/hw_random/atmel-rng.c
+++ b/drivers/char/hw_random/atmel-rng.c
@@ -14,14 +14,22 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/hw_random.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 
 #define TRNG_CR		0x00
+#define TRNG_MR		0x04
 #define TRNG_ISR	0x1c
 #define TRNG_ODATA	0x50
 
 #define TRNG_KEY	0x524e4700 /* RNG */
 
+#define TRNG_HALFR	BIT(0) /* generate RN every 168 cycles */
+
+struct atmel_trng_data {
+	bool has_half_rate;
+};
+
 struct atmel_trng {
 	struct clk *clk;
 	void __iomem *base;
@@ -62,21 +70,31 @@ static void atmel_trng_disable(struct atmel_trng *trng)
 static int atmel_trng_probe(struct platform_device *pdev)
 {
 	struct atmel_trng *trng;
-	struct resource *res;
+	const struct atmel_trng_data *data;
 	int ret;
 
 	trng = devm_kzalloc(&pdev->dev, sizeof(*trng), GFP_KERNEL);
 	if (!trng)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	trng->base = devm_ioremap_resource(&pdev->dev, res);
+	trng->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(trng->base))
 		return PTR_ERR(trng->base);
 
 	trng->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(trng->clk))
 		return PTR_ERR(trng->clk);
+	data = of_device_get_match_data(&pdev->dev);
+	if (!data)
+		return -ENODEV;
+
+	if (data->has_half_rate) {
+		unsigned long rate = clk_get_rate(trng->clk);
+
+		/* if peripheral clk is above 100MHz, set HALFR */
+		if (rate > 100000000)
+			writel(TRNG_HALFR, trng->base + TRNG_MR);
+	}
 
 	ret = clk_prepare_enable(trng->clk);
 	if (ret)
@@ -141,9 +159,24 @@ static const struct dev_pm_ops atmel_trng_pm_ops = {
 };
 #endif /* CONFIG_PM */
 
+static const struct atmel_trng_data at91sam9g45_config = {
+	.has_half_rate = false,
+};
+
+static const struct atmel_trng_data sam9x60_config = {
+	.has_half_rate = true,
+};
+
 static const struct of_device_id atmel_trng_dt_ids[] = {
-	{ .compatible = "atmel,at91sam9g45-trng" },
-	{ /* sentinel */ }
+	{
+		.compatible = "atmel,at91sam9g45-trng",
+		.data = &at91sam9g45_config,
+	}, {
+		.compatible = "microchip,sam9x60-trng",
+		.data = &sam9x60_config,
+	}, {
+		/* sentinel */
+	}
 };
 MODULE_DEVICE_TABLE(of, atmel_trng_dt_ids);
 
diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c
index f759790c3cdb..d2a5791eb49f 100644
--- a/drivers/char/hw_random/bcm2835-rng.c
+++ b/drivers/char/hw_random/bcm2835-rng.c
@@ -142,7 +142,6 @@ static int bcm2835_rng_probe(struct platform_device *pdev)
 	struct device_node *np = dev->of_node;
 	const struct of_device_id *rng_id;
 	struct bcm2835_rng_priv *priv;
-	struct resource *r;
 	int err;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
@@ -151,10 +150,8 @@ static int bcm2835_rng_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, priv);
 
-	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-
 	/* map peripheral */
-	priv->base = devm_ioremap_resource(dev, r);
+	priv->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(priv->base))
 		return PTR_ERR(priv->base);
 
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index 8d53b8ef545c..d2d7a42d7e0d 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -111,6 +111,14 @@ static void drop_current_rng(void)
 }
 
 /* Returns ERR_PTR(), NULL or refcounted hwrng */
+static struct hwrng *get_current_rng_nolock(void)
+{
+	if (current_rng)
+		kref_get(&current_rng->ref);
+
+	return current_rng;
+}
+
 static struct hwrng *get_current_rng(void)
 {
 	struct hwrng *rng;
@@ -118,9 +126,7 @@ static struct hwrng *get_current_rng(void)
 	if (mutex_lock_interruptible(&rng_mutex))
 		return ERR_PTR(-ERESTARTSYS);
 
-	rng = current_rng;
-	if (rng)
-		kref_get(&rng->ref);
+	rng = get_current_rng_nolock();
 
 	mutex_unlock(&rng_mutex);
 	return rng;
@@ -155,8 +161,6 @@ static int hwrng_init(struct hwrng *rng)
 	reinit_completion(&rng->cleanup_done);
 
 skip_init:
-	add_early_randomness(rng);
-
 	current_quality = rng->quality ? : default_quality;
 	if (current_quality > 1024)
 		current_quality = 1024;
@@ -320,12 +324,13 @@ static ssize_t hwrng_attr_current_store(struct device *dev,
 					const char *buf, size_t len)
 {
 	int err = -ENODEV;
-	struct hwrng *rng;
+	struct hwrng *rng, *old_rng, *new_rng;
 
 	err = mutex_lock_interruptible(&rng_mutex);
 	if (err)
 		return -ERESTARTSYS;
 
+	old_rng = current_rng;
 	if (sysfs_streq(buf, "")) {
 		err = enable_best_rng();
 	} else {
@@ -337,9 +342,15 @@ static ssize_t hwrng_attr_current_store(struct device *dev,
 			}
 		}
 	}
-
+	new_rng = get_current_rng_nolock();
 	mutex_unlock(&rng_mutex);
 
+	if (new_rng) {
+		if (new_rng != old_rng)
+			add_early_randomness(new_rng);
+		put_rng(new_rng);
+	}
+
 	return err ? : len;
 }
 
@@ -457,13 +468,15 @@ static void start_khwrngd(void)
 int hwrng_register(struct hwrng *rng)
 {
 	int err = -EINVAL;
-	struct hwrng *old_rng, *tmp;
+	struct hwrng *tmp;
 	struct list_head *rng_list_ptr;
+	bool is_new_current = false;
 
 	if (!rng->name || (!rng->data_read && !rng->read))
 		goto out;
 
 	mutex_lock(&rng_mutex);
+
 	/* Must not register two RNGs with the same name. */
 	err = -EEXIST;
 	list_for_each_entry(tmp, &rng_list, list) {
@@ -482,10 +495,8 @@ int hwrng_register(struct hwrng *rng)
 	}
 	list_add_tail(&rng->list, rng_list_ptr);
 
-	old_rng = current_rng;
-	err = 0;
-	if (!old_rng ||
-	    (!cur_rng_set_by_user && rng->quality > old_rng->quality)) {
+	if (!current_rng ||
+	    (!cur_rng_set_by_user && rng->quality > current_rng->quality)) {
 		/*
 		 * Set new rng as current as the new rng source
 		 * provides better entropy quality and was not
@@ -494,19 +505,26 @@ int hwrng_register(struct hwrng *rng)
 		err = set_current_rng(rng);
 		if (err)
 			goto out_unlock;
+		/* to use current_rng in add_early_randomness() we need
+		 * to take a ref
+		 */
+		is_new_current = true;
+		kref_get(&rng->ref);
 	}
-
-	if (old_rng && !rng->init) {
+	mutex_unlock(&rng_mutex);
+	if (is_new_current || !rng->init) {
 		/*
 		 * Use a new device's input to add some randomness to
 		 * the system.  If this rng device isn't going to be
 		 * used right away, its init function hasn't been
-		 * called yet; so only use the randomness from devices
-		 * that don't need an init callback.
+		 * called yet by set_current_rng(); so only use the
+		 * randomness from devices that don't need an init callback
 		 */
 		add_early_randomness(rng);
 	}
-
+	if (is_new_current)
+		put_rng(rng);
+	return 0;
 out_unlock:
 	mutex_unlock(&rng_mutex);
 out:
@@ -516,10 +534,12 @@ EXPORT_SYMBOL_GPL(hwrng_register);
 
 void hwrng_unregister(struct hwrng *rng)
 {
+	struct hwrng *old_rng, *new_rng;
 	int err;
 
 	mutex_lock(&rng_mutex);
 
+	old_rng = current_rng;
 	list_del(&rng->list);
 	if (current_rng == rng) {
 		err = enable_best_rng();
@@ -529,6 +549,7 @@ void hwrng_unregister(struct hwrng *rng)
 		}
 	}
 
+	new_rng = get_current_rng_nolock();
 	if (list_empty(&rng_list)) {
 		mutex_unlock(&rng_mutex);
 		if (hwrng_fill)
@@ -536,6 +557,12 @@ void hwrng_unregister(struct hwrng *rng)
 	} else
 		mutex_unlock(&rng_mutex);
 
+	if (new_rng) {
+		if (old_rng != new_rng)
+			add_early_randomness(new_rng);
+		put_rng(new_rng);
+	}
+
 	wait_for_completion(&rng->cleanup_done);
 }
 EXPORT_SYMBOL_GPL(hwrng_unregister);
diff --git a/drivers/char/hw_random/exynos-trng.c b/drivers/char/hw_random/exynos-trng.c
index b4b52ab23b6b..8e1fe3f8dd2d 100644
--- a/drivers/char/hw_random/exynos-trng.c
+++ b/drivers/char/hw_random/exynos-trng.c
@@ -109,7 +109,6 @@ static int exynos_trng_init(struct hwrng *rng)
 static int exynos_trng_probe(struct platform_device *pdev)
 {
 	struct exynos_trng_dev *trng;
-	struct resource *res;
 	int ret = -ENOMEM;
 
 	trng = devm_kzalloc(&pdev->dev, sizeof(*trng), GFP_KERNEL);
@@ -128,8 +127,7 @@ static int exynos_trng_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, trng);
 	trng->dev = &pdev->dev;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	trng->mem = devm_ioremap_resource(&pdev->dev, res);
+	trng->mem = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(trng->mem))
 		return PTR_ERR(trng->mem);
 
diff --git a/drivers/char/hw_random/hisi-rng.c b/drivers/char/hw_random/hisi-rng.c
index c663d5dd85bb..6815e17a9834 100644
--- a/drivers/char/hw_random/hisi-rng.c
+++ b/drivers/char/hw_random/hisi-rng.c
@@ -73,7 +73,6 @@ static int hisi_rng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
 static int hisi_rng_probe(struct platform_device *pdev)
 {
 	struct hisi_rng *rng;
-	struct resource *res;
 	int ret;
 
 	rng = devm_kzalloc(&pdev->dev, sizeof(*rng), GFP_KERNEL);
@@ -82,8 +81,7 @@ static int hisi_rng_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, rng);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	rng->base = devm_ioremap_resource(&pdev->dev, res);
+	rng->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(rng->base))
 		return PTR_ERR(rng->base);
 
diff --git a/drivers/char/hw_random/hisi-trng-v2.c b/drivers/char/hw_random/hisi-trng-v2.c
new file mode 100644
index 000000000000..6a65b8232ce0
--- /dev/null
+++ b/drivers/char/hw_random/hisi-trng-v2.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 HiSilicon Limited. */
+
+#include <linux/acpi.h>
+#include <linux/err.h>
+#include <linux/hw_random.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/random.h>
+
+#define HISI_TRNG_REG		0x00F0
+#define HISI_TRNG_BYTES		4
+#define HISI_TRNG_QUALITY	512
+#define SLEEP_US		10
+#define TIMEOUT_US		10000
+
+struct hisi_trng {
+	void __iomem *base;
+	struct hwrng rng;
+};
+
+static int hisi_trng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
+{
+	struct hisi_trng *trng;
+	int currsize = 0;
+	u32 val = 0;
+	u32 ret;
+
+	trng = container_of(rng, struct hisi_trng, rng);
+
+	do {
+		ret = readl_poll_timeout(trng->base + HISI_TRNG_REG, val,
+					 val, SLEEP_US, TIMEOUT_US);
+		if (ret)
+			return currsize;
+
+		if (max - currsize >= HISI_TRNG_BYTES) {
+			memcpy(buf + currsize, &val, HISI_TRNG_BYTES);
+			currsize += HISI_TRNG_BYTES;
+			if (currsize == max)
+				return currsize;
+			continue;
+		}
+
+		/* copy remaining bytes */
+		memcpy(buf + currsize, &val, max - currsize);
+		currsize = max;
+	} while (currsize < max);
+
+	return currsize;
+}
+
+static int hisi_trng_probe(struct platform_device *pdev)
+{
+	struct hisi_trng *trng;
+	int ret;
+
+	trng = devm_kzalloc(&pdev->dev, sizeof(*trng), GFP_KERNEL);
+	if (!trng)
+		return -ENOMEM;
+
+	trng->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(trng->base))
+		return PTR_ERR(trng->base);
+
+	trng->rng.name = pdev->name;
+	trng->rng.read = hisi_trng_read;
+	trng->rng.quality = HISI_TRNG_QUALITY;
+
+	ret = devm_hwrng_register(&pdev->dev, &trng->rng);
+	if (ret)
+		dev_err(&pdev->dev, "failed to register hwrng!\n");
+
+	return ret;
+}
+
+static const struct acpi_device_id hisi_trng_acpi_match[] = {
+	{ "HISI02B3", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, hisi_trng_acpi_match);
+
+static struct platform_driver hisi_trng_driver = {
+	.probe		= hisi_trng_probe,
+	.driver		= {
+		.name	= "hisi-trng-v2",
+		.acpi_match_table = ACPI_PTR(hisi_trng_acpi_match),
+	},
+};
+
+module_platform_driver(hisi_trng_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Weili Qian <qianweili@huawei.com>");
+MODULE_AUTHOR("Zaibo Xu <xuzaibo@huawei.com>");
+MODULE_DESCRIPTION("HiSilicon true random number generator V2 driver");
diff --git a/drivers/char/hw_random/iproc-rng200.c b/drivers/char/hw_random/iproc-rng200.c
index 92be1c0ab99f..899ff25f4f28 100644
--- a/drivers/char/hw_random/iproc-rng200.c
+++ b/drivers/char/hw_random/iproc-rng200.c
@@ -181,7 +181,6 @@ static void iproc_rng200_cleanup(struct hwrng *rng)
 static int iproc_rng200_probe(struct platform_device *pdev)
 {
 	struct iproc_rng200_dev *priv;
-	struct resource *res;
 	struct device *dev = &pdev->dev;
 	int ret;
 
@@ -190,13 +189,7 @@ static int iproc_rng200_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	/* Map peripheral */
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(dev, "failed to get rng resources\n");
-		return -EINVAL;
-	}
-
-	priv->base = devm_ioremap_resource(dev, res);
+	priv->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(priv->base)) {
 		dev_err(dev, "failed to remap rng regs\n");
 		return PTR_ERR(priv->base);
diff --git a/drivers/char/hw_random/ks-sa-rng.c b/drivers/char/hw_random/ks-sa-rng.c
index a67430010aa6..e2330e757f1f 100644
--- a/drivers/char/hw_random/ks-sa-rng.c
+++ b/drivers/char/hw_random/ks-sa-rng.c
@@ -21,6 +21,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/delay.h>
+#include <linux/timekeeping.h>
 
 #define SA_CMD_STATUS_OFS			0x8
 
@@ -84,14 +85,37 @@ struct ks_sa_rng {
 	struct hwrng	rng;
 	struct clk	*clk;
 	struct regmap	*regmap_cfg;
-	struct trng_regs *reg_rng;
+	struct trng_regs __iomem *reg_rng;
+	u64 ready_ts;
+	unsigned int refill_delay_ns;
 };
 
+static unsigned int cycles_to_ns(unsigned long clk_rate, unsigned int cycles)
+{
+	return DIV_ROUND_UP_ULL((TRNG_DEF_CLK_DIV_CYCLES + 1) * 1000000000ull *
+				cycles, clk_rate);
+}
+
+static unsigned int startup_delay_ns(unsigned long clk_rate)
+{
+	if (!TRNG_DEF_STARTUP_CYCLES)
+		return cycles_to_ns(clk_rate, BIT(24));
+	return cycles_to_ns(clk_rate, 256 * TRNG_DEF_STARTUP_CYCLES);
+}
+
+static unsigned int refill_delay_ns(unsigned long clk_rate)
+{
+	if (!TRNG_DEF_MAX_REFILL_CYCLES)
+		return cycles_to_ns(clk_rate, BIT(24));
+	return cycles_to_ns(clk_rate, 256 * TRNG_DEF_MAX_REFILL_CYCLES);
+}
+
 static int ks_sa_rng_init(struct hwrng *rng)
 {
 	u32 value;
 	struct device *dev = (struct device *)rng->priv;
 	struct ks_sa_rng *ks_sa_rng = dev_get_drvdata(dev);
+	unsigned long clk_rate = clk_get_rate(ks_sa_rng->clk);
 
 	/* Enable RNG module */
 	regmap_write_bits(ks_sa_rng->regmap_cfg, SA_CMD_STATUS_OFS,
@@ -120,6 +144,10 @@ static int ks_sa_rng_init(struct hwrng *rng)
 	value |= TRNG_CNTL_REG_TRNG_ENABLE;
 	writel(value, &ks_sa_rng->reg_rng->control);
 
+	ks_sa_rng->refill_delay_ns = refill_delay_ns(clk_rate);
+	ks_sa_rng->ready_ts = ktime_get_ns() +
+			      startup_delay_ns(clk_rate);
+
 	return 0;
 }
 
@@ -144,6 +172,7 @@ static int ks_sa_rng_data_read(struct hwrng *rng, u32 *data)
 	data[1] = readl(&ks_sa_rng->reg_rng->output_h);
 
 	writel(TRNG_INTACK_REG_READY, &ks_sa_rng->reg_rng->intack);
+	ks_sa_rng->ready_ts = ktime_get_ns() + ks_sa_rng->refill_delay_ns;
 
 	return sizeof(u32) * 2;
 }
@@ -152,10 +181,19 @@ static int ks_sa_rng_data_present(struct hwrng *rng, int wait)
 {
 	struct device *dev = (struct device *)rng->priv;
 	struct ks_sa_rng *ks_sa_rng = dev_get_drvdata(dev);
+	u64 now = ktime_get_ns();
 
 	u32	ready;
 	int	j;
 
+	if (wait && now < ks_sa_rng->ready_ts) {
+		/* Max delay expected here is 81920000 ns */
+		unsigned long min_delay =
+			DIV_ROUND_UP((u32)(ks_sa_rng->ready_ts - now), 1000);
+
+		usleep_range(min_delay, min_delay + SA_RNG_DATA_RETRY_DELAY);
+	}
+
 	for (j = 0; j < SA_MAX_RNG_DATA_RETRIES; j++) {
 		ready = readl(&ks_sa_rng->reg_rng->status);
 		ready &= TRNG_STATUS_REG_READY;
@@ -174,7 +212,6 @@ static int ks_sa_rng_probe(struct platform_device *pdev)
 	struct ks_sa_rng	*ks_sa_rng;
 	struct device		*dev = &pdev->dev;
 	int			ret;
-	struct resource		*mem;
 
 	ks_sa_rng = devm_kzalloc(dev, sizeof(*ks_sa_rng), GFP_KERNEL);
 	if (!ks_sa_rng)
@@ -190,8 +227,7 @@ static int ks_sa_rng_probe(struct platform_device *pdev)
 	};
 	ks_sa_rng->rng.priv = (unsigned long)dev;
 
-	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	ks_sa_rng->reg_rng = devm_ioremap_resource(dev, mem);
+	ks_sa_rng->reg_rng = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(ks_sa_rng->reg_rng))
 		return PTR_ERR(ks_sa_rng->reg_rng);
 
diff --git a/drivers/char/hw_random/meson-rng.c b/drivers/char/hw_random/meson-rng.c
index 76e693da5dde..e446236e81f2 100644
--- a/drivers/char/hw_random/meson-rng.c
+++ b/drivers/char/hw_random/meson-rng.c
@@ -42,7 +42,6 @@ static int meson_rng_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct meson_rng_data *data;
-	struct resource *res;
 	int ret;
 
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
@@ -51,8 +50,7 @@ static int meson_rng_probe(struct platform_device *pdev)
 
 	data->pdev = pdev;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	data->base = devm_ioremap_resource(dev, res);
+	data->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(data->base))
 		return PTR_ERR(data->base);
 
diff --git a/drivers/char/hw_random/mtk-rng.c b/drivers/char/hw_random/mtk-rng.c
index e649be5a5f13..8ad7b515a51b 100644
--- a/drivers/char/hw_random/mtk-rng.c
+++ b/drivers/char/hw_random/mtk-rng.c
@@ -105,16 +105,9 @@ static int mtk_rng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
 
 static int mtk_rng_probe(struct platform_device *pdev)
 {
-	struct resource *res;
 	int ret;
 	struct mtk_rng *priv;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "no iomem resource\n");
-		return -ENXIO;
-	}
-
 	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
@@ -135,7 +128,7 @@ static int mtk_rng_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	priv->base = devm_ioremap_resource(&pdev->dev, res);
+	priv->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(priv->base))
 		return PTR_ERR(priv->base);
 
diff --git a/drivers/char/hw_random/npcm-rng.c b/drivers/char/hw_random/npcm-rng.c
new file mode 100644
index 000000000000..01d04404d8c0
--- /dev/null
+++ b/drivers/char/hw_random/npcm-rng.c
@@ -0,0 +1,184 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Nuvoton Technology corporation.
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/init.h>
+#include <linux/random.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/hw_random.h>
+#include <linux/delay.h>
+#include <linux/of_irq.h>
+#include <linux/pm_runtime.h>
+
+#define NPCM_RNGCS_REG		0x00	/* Control and status register */
+#define NPCM_RNGD_REG		0x04	/* Data register */
+#define NPCM_RNGMODE_REG	0x08	/* Mode register */
+
+#define NPCM_RNG_CLK_SET_25MHZ	GENMASK(4, 3) /* 20-25 MHz */
+#define NPCM_RNG_DATA_VALID	BIT(1)
+#define NPCM_RNG_ENABLE		BIT(0)
+#define NPCM_RNG_M1ROSEL	BIT(1)
+
+#define NPCM_RNG_TIMEOUT_USEC	20000
+#define NPCM_RNG_POLL_USEC	1000
+
+#define to_npcm_rng(p)	container_of(p, struct npcm_rng, rng)
+
+struct npcm_rng {
+	void __iomem *base;
+	struct hwrng rng;
+};
+
+static int npcm_rng_init(struct hwrng *rng)
+{
+	struct npcm_rng *priv = to_npcm_rng(rng);
+
+	writel(NPCM_RNG_CLK_SET_25MHZ | NPCM_RNG_ENABLE,
+	       priv->base + NPCM_RNGCS_REG);
+
+	return 0;
+}
+
+static void npcm_rng_cleanup(struct hwrng *rng)
+{
+	struct npcm_rng *priv = to_npcm_rng(rng);
+
+	writel(NPCM_RNG_CLK_SET_25MHZ, priv->base + NPCM_RNGCS_REG);
+}
+
+static int npcm_rng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
+{
+	struct npcm_rng *priv = to_npcm_rng(rng);
+	int retval = 0;
+	int ready;
+
+	pm_runtime_get_sync((struct device *)priv->rng.priv);
+
+	while (max >= sizeof(u32)) {
+		if (wait) {
+			if (readl_poll_timeout(priv->base + NPCM_RNGCS_REG,
+					       ready,
+					       ready & NPCM_RNG_DATA_VALID,
+					       NPCM_RNG_POLL_USEC,
+					       NPCM_RNG_TIMEOUT_USEC))
+				break;
+		} else {
+			if ((readl(priv->base + NPCM_RNGCS_REG) &
+			    NPCM_RNG_DATA_VALID) == 0)
+				break;
+		}
+
+		*(u32 *)buf = readl(priv->base + NPCM_RNGD_REG);
+		retval += sizeof(u32);
+		buf += sizeof(u32);
+		max -= sizeof(u32);
+	}
+
+	pm_runtime_mark_last_busy((struct device *)priv->rng.priv);
+	pm_runtime_put_sync_autosuspend((struct device *)priv->rng.priv);
+
+	return retval || !wait ? retval : -EIO;
+}
+
+static int npcm_rng_probe(struct platform_device *pdev)
+{
+	struct npcm_rng *priv;
+	int ret;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
+
+	dev_set_drvdata(&pdev->dev, priv);
+	pm_runtime_set_autosuspend_delay(&pdev->dev, 100);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
+#ifndef CONFIG_PM
+	priv->rng.init = npcm_rng_init;
+	priv->rng.cleanup = npcm_rng_cleanup;
+#endif
+	priv->rng.name = pdev->name;
+	priv->rng.read = npcm_rng_read;
+	priv->rng.priv = (unsigned long)&pdev->dev;
+	priv->rng.quality = 1000;
+
+	writel(NPCM_RNG_M1ROSEL, priv->base + NPCM_RNGMODE_REG);
+
+	ret = devm_hwrng_register(&pdev->dev, &priv->rng);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to register rng device: %d\n",
+			ret);
+		pm_runtime_disable(&pdev->dev);
+		pm_runtime_set_suspended(&pdev->dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int npcm_rng_remove(struct platform_device *pdev)
+{
+	struct npcm_rng *priv = platform_get_drvdata(pdev);
+
+	devm_hwrng_unregister(&pdev->dev, &priv->rng);
+	pm_runtime_disable(&pdev->dev);
+	pm_runtime_set_suspended(&pdev->dev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int npcm_rng_runtime_suspend(struct device *dev)
+{
+	struct npcm_rng *priv = dev_get_drvdata(dev);
+
+	npcm_rng_cleanup(&priv->rng);
+
+	return 0;
+}
+
+static int npcm_rng_runtime_resume(struct device *dev)
+{
+	struct npcm_rng *priv = dev_get_drvdata(dev);
+
+	return npcm_rng_init(&priv->rng);
+}
+#endif
+
+static const struct dev_pm_ops npcm_rng_pm_ops = {
+	SET_RUNTIME_PM_OPS(npcm_rng_runtime_suspend,
+			   npcm_rng_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+};
+
+static const struct of_device_id rng_dt_id[] = {
+	{ .compatible = "nuvoton,npcm750-rng",  },
+	{},
+};
+MODULE_DEVICE_TABLE(of, rng_dt_id);
+
+static struct platform_driver npcm_rng_driver = {
+	.driver = {
+		.name		= "npcm-rng",
+		.pm		= &npcm_rng_pm_ops,
+		.of_match_table = of_match_ptr(rng_dt_id),
+	},
+	.probe		= npcm_rng_probe,
+	.remove		= npcm_rng_remove,
+};
+
+module_platform_driver(npcm_rng_driver);
+
+MODULE_DESCRIPTION("Nuvoton NPCM Random Number Generator Driver");
+MODULE_AUTHOR("Tomer Maimon <tomer.maimon@nuvoton.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c
index b27f39688b5e..0ed07d16ec8e 100644
--- a/drivers/char/hw_random/omap-rng.c
+++ b/drivers/char/hw_random/omap-rng.c
@@ -66,6 +66,13 @@
 #define OMAP4_RNG_OUTPUT_SIZE			0x8
 #define EIP76_RNG_OUTPUT_SIZE			0x10
 
+/*
+ * EIP76 RNG takes approx. 700us to produce 16 bytes of output data
+ * as per testing results. And to account for the lack of udelay()'s
+ * reliability, we keep the timeout as 1000us.
+ */
+#define RNG_DATA_FILL_TIMEOUT			100
+
 enum {
 	RNG_OUTPUT_0_REG = 0,
 	RNG_OUTPUT_1_REG,
@@ -176,7 +183,7 @@ static int omap_rng_do_read(struct hwrng *rng, void *data, size_t max,
 	if (max < priv->pdata->data_size)
 		return 0;
 
-	for (i = 0; i < 20; i++) {
+	for (i = 0; i < RNG_DATA_FILL_TIMEOUT; i++) {
 		present = priv->pdata->data_present(priv);
 		if (present || !wait)
 			break;
@@ -432,7 +439,6 @@ static int get_omap_rng_device_details(struct omap_rng_dev *omap_rng)
 static int omap_rng_probe(struct platform_device *pdev)
 {
 	struct omap_rng_dev *priv;
-	struct resource *res;
 	struct device *dev = &pdev->dev;
 	int ret;
 
@@ -449,8 +455,7 @@ static int omap_rng_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, priv);
 	priv->dev = dev;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->base = devm_ioremap_resource(dev, res);
+	priv->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(priv->base)) {
 		ret = PTR_ERR(priv->base);
 		goto err_ioremap;
diff --git a/drivers/char/hw_random/omap3-rom-rng.c b/drivers/char/hw_random/omap3-rom-rng.c
index 38b719017186..e08a8887e718 100644
--- a/drivers/char/hw_random/omap3-rom-rng.c
+++ b/drivers/char/hw_random/omap3-rom-rng.c
@@ -11,8 +11,6 @@
  * warranty of any kind, whether express or implied.
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/random.h>
@@ -20,117 +18,159 @@
 #include <linux/workqueue.h>
 #include <linux/clk.h>
 #include <linux/err.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 
 #define RNG_RESET			0x01
 #define RNG_GEN_PRNG_HW_INIT		0x02
 #define RNG_GEN_HW			0x08
 
-/* param1: ptr, param2: count, param3: flag */
-static u32 (*omap3_rom_rng_call)(u32, u32, u32);
-
-static struct delayed_work idle_work;
-static int rng_idle;
-static struct clk *rng_clk;
+struct omap_rom_rng {
+	struct clk *clk;
+	struct device *dev;
+	struct hwrng ops;
+	u32 (*rom_rng_call)(u32 ptr, u32 count, u32 flag);
+};
 
-static void omap3_rom_rng_idle(struct work_struct *work)
+static int omap3_rom_rng_read(struct hwrng *rng, void *data, size_t max, bool w)
 {
+	struct omap_rom_rng *ddata;
+	u32 ptr;
 	int r;
 
-	r = omap3_rom_rng_call(0, 0, RNG_RESET);
-	if (r != 0) {
-		pr_err("reset failed: %d\n", r);
-		return;
+	ddata = (struct omap_rom_rng *)rng->priv;
+
+	r = pm_runtime_get_sync(ddata->dev);
+	if (r < 0) {
+		pm_runtime_put_noidle(ddata->dev);
+
+		return r;
 	}
-	clk_disable_unprepare(rng_clk);
-	rng_idle = 1;
+
+	ptr = virt_to_phys(data);
+	r = ddata->rom_rng_call(ptr, 4, RNG_GEN_HW);
+	if (r != 0)
+		r = -EINVAL;
+	else
+		r = 4;
+
+	pm_runtime_mark_last_busy(ddata->dev);
+	pm_runtime_put_autosuspend(ddata->dev);
+
+	return r;
 }
 
-static int omap3_rom_rng_get_random(void *buf, unsigned int count)
+static int __maybe_unused omap_rom_rng_runtime_suspend(struct device *dev)
 {
-	u32 r;
-	u32 ptr;
+	struct omap_rom_rng *ddata;
+	int r;
 
-	cancel_delayed_work_sync(&idle_work);
-	if (rng_idle) {
-		r = clk_prepare_enable(rng_clk);
-		if (r)
-			return r;
-
-		r = omap3_rom_rng_call(0, 0, RNG_GEN_PRNG_HW_INIT);
-		if (r != 0) {
-			clk_disable_unprepare(rng_clk);
-			pr_err("HW init failed: %d\n", r);
-			return -EIO;
-		}
-		rng_idle = 0;
-	}
+	ddata = dev_get_drvdata(dev);
 
-	ptr = virt_to_phys(buf);
-	r = omap3_rom_rng_call(ptr, count, RNG_GEN_HW);
-	schedule_delayed_work(&idle_work, msecs_to_jiffies(500));
+	r = ddata->rom_rng_call(0, 0, RNG_RESET);
 	if (r != 0)
-		return -EINVAL;
+		dev_err(dev, "reset failed: %d\n", r);
+
+	clk_disable_unprepare(ddata->clk);
+
 	return 0;
 }
 
-static int omap3_rom_rng_read(struct hwrng *rng, void *data, size_t max, bool w)
+static int __maybe_unused omap_rom_rng_runtime_resume(struct device *dev)
 {
+	struct omap_rom_rng *ddata;
 	int r;
 
-	r = omap3_rom_rng_get_random(data, 4);
+	ddata = dev_get_drvdata(dev);
+
+	r = clk_prepare_enable(ddata->clk);
 	if (r < 0)
 		return r;
-	return 4;
+
+	r = ddata->rom_rng_call(0, 0, RNG_GEN_PRNG_HW_INIT);
+	if (r != 0) {
+		clk_disable(ddata->clk);
+		dev_err(dev, "HW init failed: %d\n", r);
+
+		return -EIO;
+	}
+
+	return 0;
 }
 
-static struct hwrng omap3_rom_rng_ops = {
-	.name		= "omap3-rom",
-	.read		= omap3_rom_rng_read,
-};
+static void omap_rom_rng_finish(void *data)
+{
+	struct omap_rom_rng *ddata = data;
+
+	pm_runtime_dont_use_autosuspend(ddata->dev);
+	pm_runtime_disable(ddata->dev);
+}
 
 static int omap3_rom_rng_probe(struct platform_device *pdev)
 {
+	struct omap_rom_rng *ddata;
 	int ret = 0;
 
-	pr_info("initializing\n");
+	ddata = devm_kzalloc(&pdev->dev, sizeof(*ddata), GFP_KERNEL);
+	if (!ddata)
+		return -ENOMEM;
 
-	omap3_rom_rng_call = pdev->dev.platform_data;
-	if (!omap3_rom_rng_call) {
-		pr_err("omap3_rom_rng_call is NULL\n");
+	ddata->dev = &pdev->dev;
+	ddata->ops.priv = (unsigned long)ddata;
+	ddata->ops.name = "omap3-rom";
+	ddata->ops.read = of_device_get_match_data(&pdev->dev);
+	ddata->ops.quality = 900;
+	if (!ddata->ops.read) {
+		dev_err(&pdev->dev, "missing rom code handler\n");
+
+		return -ENODEV;
+	}
+	dev_set_drvdata(ddata->dev, ddata);
+
+	ddata->rom_rng_call = pdev->dev.platform_data;
+	if (!ddata->rom_rng_call) {
+		dev_err(ddata->dev, "rom_rng_call is NULL\n");
 		return -EINVAL;
 	}
 
-	INIT_DELAYED_WORK(&idle_work, omap3_rom_rng_idle);
-	rng_clk = devm_clk_get(&pdev->dev, "ick");
-	if (IS_ERR(rng_clk)) {
-		pr_err("unable to get RNG clock\n");
-		return PTR_ERR(rng_clk);
+	ddata->clk = devm_clk_get(ddata->dev, "ick");
+	if (IS_ERR(ddata->clk)) {
+		dev_err(ddata->dev, "unable to get RNG clock\n");
+		return PTR_ERR(ddata->clk);
 	}
 
-	/* Leave the RNG in reset state. */
-	ret = clk_prepare_enable(rng_clk);
+	pm_runtime_enable(&pdev->dev);
+	pm_runtime_set_autosuspend_delay(&pdev->dev, 500);
+	pm_runtime_use_autosuspend(&pdev->dev);
+
+	ret = devm_add_action_or_reset(ddata->dev, omap_rom_rng_finish,
+				       ddata);
 	if (ret)
 		return ret;
-	omap3_rom_rng_idle(0);
 
-	return hwrng_register(&omap3_rom_rng_ops);
+	return devm_hwrng_register(ddata->dev, &ddata->ops);
 }
 
-static int omap3_rom_rng_remove(struct platform_device *pdev)
-{
-	cancel_delayed_work_sync(&idle_work);
-	hwrng_unregister(&omap3_rom_rng_ops);
-	clk_disable_unprepare(rng_clk);
-	return 0;
-}
+static const struct of_device_id omap_rom_rng_match[] = {
+	{ .compatible = "nokia,n900-rom-rng", .data = omap3_rom_rng_read, },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, omap_rom_rng_match);
+
+static const struct dev_pm_ops omap_rom_rng_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(omap_rom_rng_runtime_suspend,
+				omap_rom_rng_runtime_resume)
+};
 
 static struct platform_driver omap3_rom_rng_driver = {
 	.driver = {
 		.name		= "omap3-rom-rng",
+		.of_match_table = omap_rom_rng_match,
+		.pm = &omap_rom_rng_pm_ops,
 	},
 	.probe		= omap3_rom_rng_probe,
-	.remove		= omap3_rom_rng_remove,
 };
 
 module_platform_driver(omap3_rom_rng_driver);
diff --git a/drivers/char/hw_random/pasemi-rng.c b/drivers/char/hw_random/pasemi-rng.c
index 24b1460b49d4..2498d4ef9fe2 100644
--- a/drivers/char/hw_random/pasemi-rng.c
+++ b/drivers/char/hw_random/pasemi-rng.c
@@ -86,10 +86,8 @@ static struct hwrng pasemi_rng = {
 static int rng_probe(struct platform_device *pdev)
 {
 	void __iomem *rng_regs;
-	struct resource *res;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	rng_regs = devm_ioremap_resource(&pdev->dev, res);
+	rng_regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(rng_regs))
 		return PTR_ERR(rng_regs);
 
diff --git a/drivers/char/hw_random/pic32-rng.c b/drivers/char/hw_random/pic32-rng.c
index 90f498c98947..81080cb2294e 100644
--- a/drivers/char/hw_random/pic32-rng.c
+++ b/drivers/char/hw_random/pic32-rng.c
@@ -70,7 +70,6 @@ static int pic32_rng_read(struct hwrng *rng, void *buf, size_t max,
 static int pic32_rng_probe(struct platform_device *pdev)
 {
 	struct pic32_rng *priv;
-	struct resource *res;
 	u32 v;
 	int ret;
 
@@ -78,8 +77,7 @@ static int pic32_rng_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->base = devm_ioremap_resource(&pdev->dev, res);
+	priv->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(priv->base))
 		return PTR_ERR(priv->base);
 
diff --git a/drivers/char/hw_random/st-rng.c b/drivers/char/hw_random/st-rng.c
index 863448360a7d..783c24e3f8b7 100644
--- a/drivers/char/hw_random/st-rng.c
+++ b/drivers/char/hw_random/st-rng.c
@@ -72,7 +72,6 @@ static int st_rng_read(struct hwrng *rng, void *data, size_t max, bool wait)
 static int st_rng_probe(struct platform_device *pdev)
 {
 	struct st_rng_data *ddata;
-	struct resource *res;
 	struct clk *clk;
 	void __iomem *base;
 	int ret;
@@ -81,8 +80,7 @@ static int st_rng_probe(struct platform_device *pdev)
 	if (!ddata)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	base = devm_ioremap_resource(&pdev->dev, res);
+	base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(base))
 		return PTR_ERR(base);
 
diff --git a/drivers/char/hw_random/tx4939-rng.c b/drivers/char/hw_random/tx4939-rng.c
index 1093583b579c..c8bd34e740fd 100644
--- a/drivers/char/hw_random/tx4939-rng.c
+++ b/drivers/char/hw_random/tx4939-rng.c
@@ -107,14 +107,12 @@ static int tx4939_rng_data_read(struct hwrng *rng, u32 *buffer)
 static int __init tx4939_rng_probe(struct platform_device *dev)
 {
 	struct tx4939_rng *rngdev;
-	struct resource *r;
 	int i;
 
 	rngdev = devm_kzalloc(&dev->dev, sizeof(*rngdev), GFP_KERNEL);
 	if (!rngdev)
 		return -ENOMEM;
-	r = platform_get_resource(dev, IORESOURCE_MEM, 0);
-	rngdev->base = devm_ioremap_resource(&dev->dev, r);
+	rngdev->base = devm_platform_ioremap_resource(dev, 0);
 	if (IS_ERR(rngdev->base))
 		return PTR_ERR(rngdev->base);
 
diff --git a/drivers/char/hw_random/xgene-rng.c b/drivers/char/hw_random/xgene-rng.c
index 7e568db87ae2..d7516a446987 100644
--- a/drivers/char/hw_random/xgene-rng.c
+++ b/drivers/char/hw_random/xgene-rng.c
@@ -313,7 +313,6 @@ static struct hwrng xgene_rng_func = {
 
 static int xgene_rng_probe(struct platform_device *pdev)
 {
-	struct resource *res;
 	struct xgene_rng_dev *ctx;
 	int rc = 0;
 
@@ -324,8 +323,7 @@ static int xgene_rng_probe(struct platform_device *pdev)
 	ctx->dev = &pdev->dev;
 	platform_set_drvdata(pdev, ctx);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	ctx->csr_base = devm_ioremap_resource(&pdev->dev, res);
+	ctx->csr_base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(ctx->csr_base))
 		return PTR_ERR(ctx->csr_base);
 
diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig
index 9c37047f4b56..aacdeed93320 100644
--- a/drivers/char/tpm/Kconfig
+++ b/drivers/char/tpm/Kconfig
@@ -67,6 +67,13 @@ config TCG_TIS_SPI
 	  within Linux. To compile this driver as a module, choose  M here;
 	  the module will be called tpm_tis_spi.
 
+config TCG_TIS_SPI_CR50
+	bool "Cr50 SPI Interface"
+	depends on TCG_TIS_SPI
+	help
+	  If you have a H1 secure module running Cr50 firmware on SPI bus,
+	  say Yes and it will be accessible from within Linux.
+
 config TCG_TIS_I2C_ATMEL
 	tristate "TPM Interface Specification 1.2 Interface (I2C - Atmel)"
 	depends on I2C
diff --git a/drivers/char/tpm/Makefile b/drivers/char/tpm/Makefile
index c354cdff9c62..5a0d99d4fec0 100644
--- a/drivers/char/tpm/Makefile
+++ b/drivers/char/tpm/Makefile
@@ -21,7 +21,9 @@ tpm-$(CONFIG_EFI) += eventlog/efi.o
 tpm-$(CONFIG_OF) += eventlog/of.o
 obj-$(CONFIG_TCG_TIS_CORE) += tpm_tis_core.o
 obj-$(CONFIG_TCG_TIS) += tpm_tis.o
-obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi.o
+obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi_mod.o
+tpm_tis_spi_mod-y := tpm_tis_spi.o
+tpm_tis_spi_mod-$(CONFIG_TCG_TIS_SPI_CR50) += tpm_tis_spi_cr50.o
 obj-$(CONFIG_TCG_TIS_I2C_ATMEL) += tpm_i2c_atmel.o
 obj-$(CONFIG_TCG_TIS_I2C_INFINEON) += tpm_i2c_infineon.o
 obj-$(CONFIG_TCG_TIS_I2C_NUVOTON) += tpm_i2c_nuvoton.o
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index d7a3888ad80f..a438b1206fcb 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
+#include <linux/suspend.h>
 #include <linux/freezer.h>
 #include <linux/tpm_eventlog.h>
 
@@ -394,7 +395,11 @@ int tpm_pm_suspend(struct device *dev)
 		return -ENODEV;
 
 	if (chip->flags & TPM_CHIP_FLAG_ALWAYS_POWERED)
-		return 0;
+		goto suspended;
+
+	if ((chip->flags & TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED) &&
+	    !pm_suspend_via_firmware())
+		goto suspended;
 
 	if (!tpm_chip_start(chip)) {
 		if (chip->flags & TPM_CHIP_FLAG_TPM2)
@@ -405,6 +410,7 @@ int tpm_pm_suspend(struct device *dev)
 		tpm_chip_stop(chip);
 	}
 
+suspended:
 	return rc;
 }
 EXPORT_SYMBOL_GPL(tpm_pm_suspend);
@@ -453,62 +459,6 @@ int tpm_get_random(struct tpm_chip *chip, u8 *out, size_t max)
 }
 EXPORT_SYMBOL_GPL(tpm_get_random);
 
-/**
- * tpm_seal_trusted() - seal a trusted key payload
- * @chip:	a &struct tpm_chip instance, %NULL for the default chip
- * @options:	authentication values and other options
- * @payload:	the key data in clear and encrypted form
- *
- * Note: only TPM 2.0 chip are supported. TPM 1.x implementation is located in
- * the keyring subsystem.
- *
- * Return: same as with tpm_transmit_cmd()
- */
-int tpm_seal_trusted(struct tpm_chip *chip, struct trusted_key_payload *payload,
-		     struct trusted_key_options *options)
-{
-	int rc;
-
-	chip = tpm_find_get_ops(chip);
-	if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2))
-		return -ENODEV;
-
-	rc = tpm2_seal_trusted(chip, payload, options);
-
-	tpm_put_ops(chip);
-	return rc;
-}
-EXPORT_SYMBOL_GPL(tpm_seal_trusted);
-
-/**
- * tpm_unseal_trusted() - unseal a trusted key
- * @chip:	a &struct tpm_chip instance, %NULL for the default chip
- * @options:	authentication values and other options
- * @payload:	the key data in clear and encrypted form
- *
- * Note: only TPM 2.0 chip are supported. TPM 1.x implementation is located in
- * the keyring subsystem.
- *
- * Return: same as with tpm_transmit_cmd()
- */
-int tpm_unseal_trusted(struct tpm_chip *chip,
-		       struct trusted_key_payload *payload,
-		       struct trusted_key_options *options)
-{
-	int rc;
-
-	chip = tpm_find_get_ops(chip);
-	if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2))
-		return -ENODEV;
-
-	rc = tpm2_unseal_trusted(chip, payload, options);
-
-	tpm_put_ops(chip);
-
-	return rc;
-}
-EXPORT_SYMBOL_GPL(tpm_unseal_trusted);
-
 static int __init tpm_init(void)
 {
 	int rc;
diff --git a/drivers/char/tpm/tpm-sysfs.c b/drivers/char/tpm/tpm-sysfs.c
index edfa89160010..3b53b3e5ec3e 100644
--- a/drivers/char/tpm/tpm-sysfs.c
+++ b/drivers/char/tpm/tpm-sysfs.c
@@ -217,6 +217,7 @@ static ssize_t caps_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {
 	struct tpm_chip *chip = to_tpm_chip(dev);
+	struct tpm1_version *version;
 	ssize_t rc = 0;
 	char *str = buf;
 	cap_t cap;
@@ -232,31 +233,31 @@ static ssize_t caps_show(struct device *dev, struct device_attribute *attr,
 	str += sprintf(str, "Manufacturer: 0x%x\n",
 		       be32_to_cpu(cap.manufacturer_id));
 
-	/* Try to get a TPM version 1.2 TPM_CAP_VERSION_INFO */
-	rc = tpm1_getcap(chip, TPM_CAP_VERSION_1_2, &cap,
+	/* TPM 1.2 */
+	if (!tpm1_getcap(chip, TPM_CAP_VERSION_1_2, &cap,
 			 "attempting to determine the 1.2 version",
-			 sizeof(cap.tpm_version_1_2));
-	if (!rc) {
-		str += sprintf(str,
-			       "TCG version: %d.%d\nFirmware version: %d.%d\n",
-			       cap.tpm_version_1_2.Major,
-			       cap.tpm_version_1_2.Minor,
-			       cap.tpm_version_1_2.revMajor,
-			       cap.tpm_version_1_2.revMinor);
-	} else {
-		/* Otherwise just use TPM_STRUCT_VER */
-		if (tpm1_getcap(chip, TPM_CAP_VERSION_1_1, &cap,
-				"attempting to determine the 1.1 version",
-				sizeof(cap.tpm_version)))
-			goto out_ops;
-		str += sprintf(str,
-			       "TCG version: %d.%d\nFirmware version: %d.%d\n",
-			       cap.tpm_version.Major,
-			       cap.tpm_version.Minor,
-			       cap.tpm_version.revMajor,
-			       cap.tpm_version.revMinor);
+			 sizeof(cap.version2))) {
+		version = &cap.version2.version;
+		goto out_print;
 	}
+
+	/* TPM 1.1 */
+	if (tpm1_getcap(chip, TPM_CAP_VERSION_1_1, &cap,
+			"attempting to determine the 1.1 version",
+			sizeof(cap.version1))) {
+		goto out_ops;
+	}
+
+	version = &cap.version1;
+
+out_print:
+	str += sprintf(str,
+		       "TCG version: %d.%d\nFirmware version: %d.%d\n",
+		       version->major, version->minor,
+		       version->rev_major, version->rev_minor);
+
 	rc = str - buf;
+
 out_ops:
 	tpm_put_ops(chip);
 	return rc;
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index a7fea3e0ca86..b9e1547be6b5 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -25,7 +25,6 @@
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/tpm.h>
-#include <linux/highmem.h>
 #include <linux/tpm_eventlog.h>
 
 #ifdef CONFIG_X86
@@ -58,123 +57,6 @@ enum tpm_addr {
 #define TPM_ERR_DISABLED        0x7
 #define TPM_ERR_INVALID_POSTINIT 38
 
-#define TPM_HEADER_SIZE		10
-
-enum tpm2_const {
-	TPM2_PLATFORM_PCR       =     24,
-	TPM2_PCR_SELECT_MIN     = ((TPM2_PLATFORM_PCR + 7) / 8),
-};
-
-enum tpm2_timeouts {
-	TPM2_TIMEOUT_A          =    750,
-	TPM2_TIMEOUT_B          =   2000,
-	TPM2_TIMEOUT_C          =    200,
-	TPM2_TIMEOUT_D          =     30,
-	TPM2_DURATION_SHORT     =     20,
-	TPM2_DURATION_MEDIUM    =    750,
-	TPM2_DURATION_LONG      =   2000,
-	TPM2_DURATION_LONG_LONG = 300000,
-	TPM2_DURATION_DEFAULT   = 120000,
-};
-
-enum tpm2_structures {
-	TPM2_ST_NO_SESSIONS	= 0x8001,
-	TPM2_ST_SESSIONS	= 0x8002,
-};
-
-/* Indicates from what layer of the software stack the error comes from */
-#define TSS2_RC_LAYER_SHIFT	 16
-#define TSS2_RESMGR_TPM_RC_LAYER (11 << TSS2_RC_LAYER_SHIFT)
-
-enum tpm2_return_codes {
-	TPM2_RC_SUCCESS		= 0x0000,
-	TPM2_RC_HASH		= 0x0083, /* RC_FMT1 */
-	TPM2_RC_HANDLE		= 0x008B,
-	TPM2_RC_INITIALIZE	= 0x0100, /* RC_VER1 */
-	TPM2_RC_FAILURE		= 0x0101,
-	TPM2_RC_DISABLED	= 0x0120,
-	TPM2_RC_COMMAND_CODE    = 0x0143,
-	TPM2_RC_TESTING		= 0x090A, /* RC_WARN */
-	TPM2_RC_REFERENCE_H0	= 0x0910,
-	TPM2_RC_RETRY		= 0x0922,
-};
-
-enum tpm2_command_codes {
-	TPM2_CC_FIRST		        = 0x011F,
-	TPM2_CC_HIERARCHY_CONTROL       = 0x0121,
-	TPM2_CC_HIERARCHY_CHANGE_AUTH   = 0x0129,
-	TPM2_CC_CREATE_PRIMARY          = 0x0131,
-	TPM2_CC_SEQUENCE_COMPLETE       = 0x013E,
-	TPM2_CC_SELF_TEST	        = 0x0143,
-	TPM2_CC_STARTUP		        = 0x0144,
-	TPM2_CC_SHUTDOWN	        = 0x0145,
-	TPM2_CC_NV_READ                 = 0x014E,
-	TPM2_CC_CREATE		        = 0x0153,
-	TPM2_CC_LOAD		        = 0x0157,
-	TPM2_CC_SEQUENCE_UPDATE         = 0x015C,
-	TPM2_CC_UNSEAL		        = 0x015E,
-	TPM2_CC_CONTEXT_LOAD	        = 0x0161,
-	TPM2_CC_CONTEXT_SAVE	        = 0x0162,
-	TPM2_CC_FLUSH_CONTEXT	        = 0x0165,
-	TPM2_CC_VERIFY_SIGNATURE        = 0x0177,
-	TPM2_CC_GET_CAPABILITY	        = 0x017A,
-	TPM2_CC_GET_RANDOM	        = 0x017B,
-	TPM2_CC_PCR_READ	        = 0x017E,
-	TPM2_CC_PCR_EXTEND	        = 0x0182,
-	TPM2_CC_EVENT_SEQUENCE_COMPLETE = 0x0185,
-	TPM2_CC_HASH_SEQUENCE_START     = 0x0186,
-	TPM2_CC_CREATE_LOADED           = 0x0191,
-	TPM2_CC_LAST		        = 0x0193, /* Spec 1.36 */
-};
-
-enum tpm2_permanent_handles {
-	TPM2_RS_PW		= 0x40000009,
-};
-
-enum tpm2_capabilities {
-	TPM2_CAP_HANDLES	= 1,
-	TPM2_CAP_COMMANDS	= 2,
-	TPM2_CAP_PCRS		= 5,
-	TPM2_CAP_TPM_PROPERTIES = 6,
-};
-
-enum tpm2_properties {
-	TPM_PT_TOTAL_COMMANDS	= 0x0129,
-};
-
-enum tpm2_startup_types {
-	TPM2_SU_CLEAR	= 0x0000,
-	TPM2_SU_STATE	= 0x0001,
-};
-
-enum tpm2_cc_attrs {
-	TPM2_CC_ATTR_CHANDLES	= 25,
-	TPM2_CC_ATTR_RHANDLE	= 28,
-};
-
-#define TPM_VID_INTEL    0x8086
-#define TPM_VID_WINBOND  0x1050
-#define TPM_VID_STM      0x104A
-
-enum tpm_chip_flags {
-	TPM_CHIP_FLAG_TPM2		= BIT(1),
-	TPM_CHIP_FLAG_IRQ		= BIT(2),
-	TPM_CHIP_FLAG_VIRTUAL		= BIT(3),
-	TPM_CHIP_FLAG_HAVE_TIMEOUTS	= BIT(4),
-	TPM_CHIP_FLAG_ALWAYS_POWERED	= BIT(5),
-};
-
-#define to_tpm_chip(d) container_of(d, struct tpm_chip, dev)
-
-struct tpm_header {
-	__be16 tag;
-	__be32 length;
-	union {
-		__be32 ordinal;
-		__be32 return_code;
-	};
-} __packed;
-
 #define TPM_TAG_RQU_COMMAND 193
 
 struct	stclear_flags_t {
@@ -186,19 +68,16 @@ struct	stclear_flags_t {
 	u8	bGlobalLock;
 } __packed;
 
-struct	tpm_version_t {
-	u8	Major;
-	u8	Minor;
-	u8	revMajor;
-	u8	revMinor;
+struct tpm1_version {
+	u8 major;
+	u8 minor;
+	u8 rev_major;
+	u8 rev_minor;
 } __packed;
 
-struct	tpm_version_1_2_t {
-	__be16	tag;
-	u8	Major;
-	u8	Minor;
-	u8	revMajor;
-	u8	revMinor;
+struct tpm1_version2 {
+	__be16 tag;
+	struct tpm1_version version;
 } __packed;
 
 struct	timeout_t {
@@ -243,8 +122,8 @@ typedef union {
 	struct	stclear_flags_t	stclear_flags;
 	__u8	owned;
 	__be32	num_pcrs;
-	struct	tpm_version_t	tpm_version;
-	struct	tpm_version_1_2_t tpm_version_1_2;
+	struct tpm1_version version1;
+	struct tpm1_version2 version2;
 	__be32	manufacturer_id;
 	struct timeout_t  timeout;
 	struct duration_t duration;
@@ -274,102 +153,6 @@ enum tpm_sub_capabilities {
  * compiler warnings about stack frame size. */
 #define TPM_MAX_RNG_DATA	128
 
-/* A string buffer type for constructing TPM commands. This is based on the
- * ideas of string buffer code in security/keys/trusted.h but is heap based
- * in order to keep the stack usage minimal.
- */
-
-enum tpm_buf_flags {
-	TPM_BUF_OVERFLOW	= BIT(0),
-};
-
-struct tpm_buf {
-	struct page *data_page;
-	unsigned int flags;
-	u8 *data;
-};
-
-static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal)
-{
-	struct tpm_header *head = (struct tpm_header *)buf->data;
-
-	head->tag = cpu_to_be16(tag);
-	head->length = cpu_to_be32(sizeof(*head));
-	head->ordinal = cpu_to_be32(ordinal);
-}
-
-static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal)
-{
-	buf->data_page = alloc_page(GFP_HIGHUSER);
-	if (!buf->data_page)
-		return -ENOMEM;
-
-	buf->flags = 0;
-	buf->data = kmap(buf->data_page);
-	tpm_buf_reset(buf, tag, ordinal);
-	return 0;
-}
-
-static inline void tpm_buf_destroy(struct tpm_buf *buf)
-{
-	kunmap(buf->data_page);
-	__free_page(buf->data_page);
-}
-
-static inline u32 tpm_buf_length(struct tpm_buf *buf)
-{
-	struct tpm_header *head = (struct tpm_header *)buf->data;
-
-	return be32_to_cpu(head->length);
-}
-
-static inline u16 tpm_buf_tag(struct tpm_buf *buf)
-{
-	struct tpm_header *head = (struct tpm_header *)buf->data;
-
-	return be16_to_cpu(head->tag);
-}
-
-static inline void tpm_buf_append(struct tpm_buf *buf,
-				  const unsigned char *new_data,
-				  unsigned int new_len)
-{
-	struct tpm_header *head = (struct tpm_header *)buf->data;
-	u32 len = tpm_buf_length(buf);
-
-	/* Return silently if overflow has already happened. */
-	if (buf->flags & TPM_BUF_OVERFLOW)
-		return;
-
-	if ((len + new_len) > PAGE_SIZE) {
-		WARN(1, "tpm_buf: overflow\n");
-		buf->flags |= TPM_BUF_OVERFLOW;
-		return;
-	}
-
-	memcpy(&buf->data[len], new_data, new_len);
-	head->length = cpu_to_be32(len + new_len);
-}
-
-static inline void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value)
-{
-	tpm_buf_append(buf, &value, 1);
-}
-
-static inline void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value)
-{
-	__be16 value2 = cpu_to_be16(value);
-
-	tpm_buf_append(buf, (u8 *) &value2, 2);
-}
-
-static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value)
-{
-	__be32 value2 = cpu_to_be32(value);
-
-	tpm_buf_append(buf, (u8 *) &value2, 4);
-}
-
 extern struct class *tpm_class;
 extern struct class *tpmrm_class;
 extern dev_t tpm_devt;
@@ -429,11 +212,6 @@ static inline void tpm_add_ppi(struct tpm_chip *chip)
 }
 #endif
 
-static inline u32 tpm2_rc_value(u32 rc)
-{
-	return (rc & BIT(7)) ? rc & 0xff : rc;
-}
-
 int tpm2_get_timeouts(struct tpm_chip *chip);
 int tpm2_pcr_read(struct tpm_chip *chip, u32 pcr_idx,
 		  struct tpm_digest *digest, u16 *digest_size_ptr);
@@ -441,12 +219,6 @@ int tpm2_pcr_extend(struct tpm_chip *chip, u32 pcr_idx,
 		    struct tpm_digest *digests);
 int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max);
 void tpm2_flush_context(struct tpm_chip *chip, u32 handle);
-int tpm2_seal_trusted(struct tpm_chip *chip,
-		      struct trusted_key_payload *payload,
-		      struct trusted_key_options *options);
-int tpm2_unseal_trusted(struct tpm_chip *chip,
-			struct trusted_key_payload *payload,
-			struct trusted_key_options *options);
 ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id,
 			u32 *value, const char *desc);
 
diff --git a/drivers/char/tpm/tpm1-cmd.c b/drivers/char/tpm/tpm1-cmd.c
index 149e953ca369..ca7158fa6e6c 100644
--- a/drivers/char/tpm/tpm1-cmd.c
+++ b/drivers/char/tpm/tpm1-cmd.c
@@ -343,6 +343,7 @@ int tpm1_get_timeouts(struct tpm_chip *chip)
 {
 	cap_t cap;
 	unsigned long timeout_old[4], timeout_chip[4], timeout_eff[4];
+	unsigned long durations[3];
 	ssize_t rc;
 
 	rc = tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, NULL,
@@ -427,6 +428,20 @@ int tpm1_get_timeouts(struct tpm_chip *chip)
 		usecs_to_jiffies(be32_to_cpu(cap.duration.tpm_long));
 	chip->duration[TPM_LONG_LONG] = 0; /* not used under 1.2 */
 
+	/*
+	 * Provide the ability for vendor overrides of duration values in case
+	 * of misreporting.
+	 */
+	if (chip->ops->update_durations)
+		chip->ops->update_durations(chip, durations);
+
+	if (chip->duration_adjusted) {
+		dev_info(&chip->dev, HW_ERR "Adjusting reported durations.");
+		chip->duration[TPM_SHORT] = durations[0];
+		chip->duration[TPM_MEDIUM] = durations[1];
+		chip->duration[TPM_LONG] = durations[2];
+	}
+
 	/* The Broadcom BCM0102 chipset in a Dell Latitude D820 gets the above
 	 * value wrong and apparently reports msecs rather than usecs. So we
 	 * fix up the resulting too-small TPM_SHORT value to make things work.
diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index ba9acae83bff..fdb457704aa7 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -13,20 +13,6 @@
 
 #include "tpm.h"
 #include <crypto/hash_info.h>
-#include <keys/trusted-type.h>
-
-enum tpm2_object_attributes {
-	TPM2_OA_USER_WITH_AUTH		= BIT(6),
-};
-
-enum tpm2_session_attributes {
-	TPM2_SA_CONTINUE_SESSION	= BIT(0),
-};
-
-struct tpm2_hash {
-	unsigned int crypto_id;
-	unsigned int tpm_id;
-};
 
 static struct tpm2_hash tpm2_hash_map[] = {
 	{HASH_ALGO_SHA1, TPM_ALG_SHA1},
@@ -377,299 +363,6 @@ void tpm2_flush_context(struct tpm_chip *chip, u32 handle)
 	tpm_buf_destroy(&buf);
 }
 
-/**
- * tpm_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer.
- *
- * @buf: an allocated tpm_buf instance
- * @session_handle: session handle
- * @nonce: the session nonce, may be NULL if not used
- * @nonce_len: the session nonce length, may be 0 if not used
- * @attributes: the session attributes
- * @hmac: the session HMAC or password, may be NULL if not used
- * @hmac_len: the session HMAC or password length, maybe 0 if not used
- */
-static void tpm2_buf_append_auth(struct tpm_buf *buf, u32 session_handle,
-				 const u8 *nonce, u16 nonce_len,
-				 u8 attributes,
-				 const u8 *hmac, u16 hmac_len)
-{
-	tpm_buf_append_u32(buf, 9 + nonce_len + hmac_len);
-	tpm_buf_append_u32(buf, session_handle);
-	tpm_buf_append_u16(buf, nonce_len);
-
-	if (nonce && nonce_len)
-		tpm_buf_append(buf, nonce, nonce_len);
-
-	tpm_buf_append_u8(buf, attributes);
-	tpm_buf_append_u16(buf, hmac_len);
-
-	if (hmac && hmac_len)
-		tpm_buf_append(buf, hmac, hmac_len);
-}
-
-/**
- * tpm2_seal_trusted() - seal the payload of a trusted key
- *
- * @chip: TPM chip to use
- * @payload: the key data in clear and encrypted form
- * @options: authentication values and other options
- *
- * Return: < 0 on error and 0 on success.
- */
-int tpm2_seal_trusted(struct tpm_chip *chip,
-		      struct trusted_key_payload *payload,
-		      struct trusted_key_options *options)
-{
-	unsigned int blob_len;
-	struct tpm_buf buf;
-	u32 hash;
-	int i;
-	int rc;
-
-	for (i = 0; i < ARRAY_SIZE(tpm2_hash_map); i++) {
-		if (options->hash == tpm2_hash_map[i].crypto_id) {
-			hash = tpm2_hash_map[i].tpm_id;
-			break;
-		}
-	}
-
-	if (i == ARRAY_SIZE(tpm2_hash_map))
-		return -EINVAL;
-
-	rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE);
-	if (rc)
-		return rc;
-
-	tpm_buf_append_u32(&buf, options->keyhandle);
-	tpm2_buf_append_auth(&buf, TPM2_RS_PW,
-			     NULL /* nonce */, 0,
-			     0 /* session_attributes */,
-			     options->keyauth /* hmac */,
-			     TPM_DIGEST_SIZE);
-
-	/* sensitive */
-	tpm_buf_append_u16(&buf, 4 + TPM_DIGEST_SIZE + payload->key_len + 1);
-
-	tpm_buf_append_u16(&buf, TPM_DIGEST_SIZE);
-	tpm_buf_append(&buf, options->blobauth, TPM_DIGEST_SIZE);
-	tpm_buf_append_u16(&buf, payload->key_len + 1);
-	tpm_buf_append(&buf, payload->key, payload->key_len);
-	tpm_buf_append_u8(&buf, payload->migratable);
-
-	/* public */
-	tpm_buf_append_u16(&buf, 14 + options->policydigest_len);
-	tpm_buf_append_u16(&buf, TPM_ALG_KEYEDHASH);
-	tpm_buf_append_u16(&buf, hash);
-
-	/* policy */
-	if (options->policydigest_len) {
-		tpm_buf_append_u32(&buf, 0);
-		tpm_buf_append_u16(&buf, options->policydigest_len);
-		tpm_buf_append(&buf, options->policydigest,
-			       options->policydigest_len);
-	} else {
-		tpm_buf_append_u32(&buf, TPM2_OA_USER_WITH_AUTH);
-		tpm_buf_append_u16(&buf, 0);
-	}
-
-	/* public parameters */
-	tpm_buf_append_u16(&buf, TPM_ALG_NULL);
-	tpm_buf_append_u16(&buf, 0);
-
-	/* outside info */
-	tpm_buf_append_u16(&buf, 0);
-
-	/* creation PCR */
-	tpm_buf_append_u32(&buf, 0);
-
-	if (buf.flags & TPM_BUF_OVERFLOW) {
-		rc = -E2BIG;
-		goto out;
-	}
-
-	rc = tpm_transmit_cmd(chip, &buf, 4, "sealing data");
-	if (rc)
-		goto out;
-
-	blob_len = be32_to_cpup((__be32 *) &buf.data[TPM_HEADER_SIZE]);
-	if (blob_len > MAX_BLOB_SIZE) {
-		rc = -E2BIG;
-		goto out;
-	}
-	if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 4 + blob_len) {
-		rc = -EFAULT;
-		goto out;
-	}
-
-	memcpy(payload->blob, &buf.data[TPM_HEADER_SIZE + 4], blob_len);
-	payload->blob_len = blob_len;
-
-out:
-	tpm_buf_destroy(&buf);
-
-	if (rc > 0) {
-		if (tpm2_rc_value(rc) == TPM2_RC_HASH)
-			rc = -EINVAL;
-		else
-			rc = -EPERM;
-	}
-
-	return rc;
-}
-
-/**
- * tpm2_load_cmd() - execute a TPM2_Load command
- *
- * @chip: TPM chip to use
- * @payload: the key data in clear and encrypted form
- * @options: authentication values and other options
- * @blob_handle: returned blob handle
- *
- * Return: 0 on success.
- *        -E2BIG on wrong payload size.
- *        -EPERM on tpm error status.
- *        < 0 error from tpm_transmit_cmd.
- */
-static int tpm2_load_cmd(struct tpm_chip *chip,
-			 struct trusted_key_payload *payload,
-			 struct trusted_key_options *options,
-			 u32 *blob_handle)
-{
-	struct tpm_buf buf;
-	unsigned int private_len;
-	unsigned int public_len;
-	unsigned int blob_len;
-	int rc;
-
-	private_len = be16_to_cpup((__be16 *) &payload->blob[0]);
-	if (private_len > (payload->blob_len - 2))
-		return -E2BIG;
-
-	public_len = be16_to_cpup((__be16 *) &payload->blob[2 + private_len]);
-	blob_len = private_len + public_len + 4;
-	if (blob_len > payload->blob_len)
-		return -E2BIG;
-
-	rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_LOAD);
-	if (rc)
-		return rc;
-
-	tpm_buf_append_u32(&buf, options->keyhandle);
-	tpm2_buf_append_auth(&buf, TPM2_RS_PW,
-			     NULL /* nonce */, 0,
-			     0 /* session_attributes */,
-			     options->keyauth /* hmac */,
-			     TPM_DIGEST_SIZE);
-
-	tpm_buf_append(&buf, payload->blob, blob_len);
-
-	if (buf.flags & TPM_BUF_OVERFLOW) {
-		rc = -E2BIG;
-		goto out;
-	}
-
-	rc = tpm_transmit_cmd(chip, &buf, 4, "loading blob");
-	if (!rc)
-		*blob_handle = be32_to_cpup(
-			(__be32 *) &buf.data[TPM_HEADER_SIZE]);
-
-out:
-	tpm_buf_destroy(&buf);
-
-	if (rc > 0)
-		rc = -EPERM;
-
-	return rc;
-}
-
-/**
- * tpm2_unseal_cmd() - execute a TPM2_Unload command
- *
- * @chip: TPM chip to use
- * @payload: the key data in clear and encrypted form
- * @options: authentication values and other options
- * @blob_handle: blob handle
- *
- * Return: 0 on success
- *         -EPERM on tpm error status
- *         < 0 error from tpm_transmit_cmd
- */
-static int tpm2_unseal_cmd(struct tpm_chip *chip,
-			   struct trusted_key_payload *payload,
-			   struct trusted_key_options *options,
-			   u32 blob_handle)
-{
-	struct tpm_buf buf;
-	u16 data_len;
-	u8 *data;
-	int rc;
-
-	rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_UNSEAL);
-	if (rc)
-		return rc;
-
-	tpm_buf_append_u32(&buf, blob_handle);
-	tpm2_buf_append_auth(&buf,
-			     options->policyhandle ?
-			     options->policyhandle : TPM2_RS_PW,
-			     NULL /* nonce */, 0,
-			     TPM2_SA_CONTINUE_SESSION,
-			     options->blobauth /* hmac */,
-			     TPM_DIGEST_SIZE);
-
-	rc = tpm_transmit_cmd(chip, &buf, 6, "unsealing");
-	if (rc > 0)
-		rc = -EPERM;
-
-	if (!rc) {
-		data_len = be16_to_cpup(
-			(__be16 *) &buf.data[TPM_HEADER_SIZE + 4]);
-		if (data_len < MIN_KEY_SIZE ||  data_len > MAX_KEY_SIZE + 1) {
-			rc = -EFAULT;
-			goto out;
-		}
-
-		if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 6 + data_len) {
-			rc = -EFAULT;
-			goto out;
-		}
-		data = &buf.data[TPM_HEADER_SIZE + 6];
-
-		memcpy(payload->key, data, data_len - 1);
-		payload->key_len = data_len - 1;
-		payload->migratable = data[data_len - 1];
-	}
-
-out:
-	tpm_buf_destroy(&buf);
-	return rc;
-}
-
-/**
- * tpm2_unseal_trusted() - unseal the payload of a trusted key
- *
- * @chip: TPM chip to use
- * @payload: the key data in clear and encrypted form
- * @options: authentication values and other options
- *
- * Return: Same as with tpm_transmit_cmd.
- */
-int tpm2_unseal_trusted(struct tpm_chip *chip,
-			struct trusted_key_payload *payload,
-			struct trusted_key_options *options)
-{
-	u32 blob_handle;
-	int rc;
-
-	rc = tpm2_load_cmd(chip, payload, options, &blob_handle);
-	if (rc)
-		return rc;
-
-	rc = tpm2_unseal_cmd(chip, payload, options, blob_handle);
-	tpm2_flush_context(chip, blob_handle);
-	return rc;
-}
-
 struct tpm2_get_cap_out {
 	u8 more_data;
 	__be32 subcap_id;
@@ -939,6 +632,10 @@ static int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip)
 
 	chip->cc_attrs_tbl = devm_kcalloc(&chip->dev, 4, nr_commands,
 					  GFP_KERNEL);
+	if (!chip->cc_attrs_tbl) {
+		rc = -ENOMEM;
+		goto out;
+	}
 
 	rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY);
 	if (rc)
diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c
index e59f1f91d7f3..a9dcf31eadd2 100644
--- a/drivers/char/tpm/tpm_crb.c
+++ b/drivers/char/tpm/tpm_crb.c
@@ -22,6 +22,7 @@
 #include "tpm.h"
 
 #define ACPI_SIG_TPM2 "TPM2"
+#define TPM_CRB_MAX_RESOURCES 3
 
 static const guid_t crb_acpi_start_guid =
 	GUID_INIT(0x6BBF6CAB, 0x5463, 0x4714,
@@ -91,7 +92,6 @@ enum crb_status {
 struct crb_priv {
 	u32 sm;
 	const char *hid;
-	void __iomem *iobase;
 	struct crb_regs_head __iomem *regs_h;
 	struct crb_regs_tail __iomem *regs_t;
 	u8 __iomem *cmd;
@@ -434,21 +434,27 @@ static const struct tpm_class_ops tpm_crb = {
 
 static int crb_check_resource(struct acpi_resource *ares, void *data)
 {
-	struct resource *io_res = data;
+	struct resource *iores_array = data;
 	struct resource_win win;
 	struct resource *res = &(win.res);
+	int i;
 
 	if (acpi_dev_resource_memory(ares, res) ||
 	    acpi_dev_resource_address_space(ares, &win)) {
-		*io_res = *res;
-		io_res->name = NULL;
+		for (i = 0; i < TPM_CRB_MAX_RESOURCES + 1; ++i) {
+			if (resource_type(iores_array + i) != IORESOURCE_MEM) {
+				iores_array[i] = *res;
+				iores_array[i].name = NULL;
+				break;
+			}
+		}
 	}
 
 	return 1;
 }
 
-static void __iomem *crb_map_res(struct device *dev, struct crb_priv *priv,
-				 struct resource *io_res, u64 start, u32 size)
+static void __iomem *crb_map_res(struct device *dev, struct resource *iores,
+				 void __iomem **iobase_ptr, u64 start, u32 size)
 {
 	struct resource new_res = {
 		.start	= start,
@@ -460,10 +466,16 @@ static void __iomem *crb_map_res(struct device *dev, struct crb_priv *priv,
 	if (start != new_res.start)
 		return (void __iomem *) ERR_PTR(-EINVAL);
 
-	if (!resource_contains(io_res, &new_res))
+	if (!iores)
 		return devm_ioremap_resource(dev, &new_res);
 
-	return priv->iobase + (new_res.start - io_res->start);
+	if (!*iobase_ptr) {
+		*iobase_ptr = devm_ioremap_resource(dev, iores);
+		if (IS_ERR(*iobase_ptr))
+			return *iobase_ptr;
+	}
+
+	return *iobase_ptr + (new_res.start - iores->start);
 }
 
 /*
@@ -490,9 +502,13 @@ static u64 crb_fixup_cmd_size(struct device *dev, struct resource *io_res,
 static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,
 		      struct acpi_table_tpm2 *buf)
 {
-	struct list_head resources;
-	struct resource io_res;
+	struct list_head acpi_resource_list;
+	struct resource iores_array[TPM_CRB_MAX_RESOURCES + 1] = { {0} };
+	void __iomem *iobase_array[TPM_CRB_MAX_RESOURCES] = {NULL};
 	struct device *dev = &device->dev;
+	struct resource *iores;
+	void __iomem **iobase_ptr;
+	int i;
 	u32 pa_high, pa_low;
 	u64 cmd_pa;
 	u32 cmd_size;
@@ -501,21 +517,41 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,
 	u32 rsp_size;
 	int ret;
 
-	INIT_LIST_HEAD(&resources);
-	ret = acpi_dev_get_resources(device, &resources, crb_check_resource,
-				     &io_res);
+	INIT_LIST_HEAD(&acpi_resource_list);
+	ret = acpi_dev_get_resources(device, &acpi_resource_list,
+				     crb_check_resource, iores_array);
 	if (ret < 0)
 		return ret;
-	acpi_dev_free_resource_list(&resources);
+	acpi_dev_free_resource_list(&acpi_resource_list);
 
-	if (resource_type(&io_res) != IORESOURCE_MEM) {
+	if (resource_type(iores_array) != IORESOURCE_MEM) {
 		dev_err(dev, FW_BUG "TPM2 ACPI table does not define a memory resource\n");
 		return -EINVAL;
+	} else if (resource_type(iores_array + TPM_CRB_MAX_RESOURCES) ==
+		IORESOURCE_MEM) {
+		dev_warn(dev, "TPM2 ACPI table defines too many memory resources\n");
+		memset(iores_array + TPM_CRB_MAX_RESOURCES,
+		       0, sizeof(*iores_array));
+		iores_array[TPM_CRB_MAX_RESOURCES].flags = 0;
 	}
 
-	priv->iobase = devm_ioremap_resource(dev, &io_res);
-	if (IS_ERR(priv->iobase))
-		return PTR_ERR(priv->iobase);
+	iores = NULL;
+	iobase_ptr = NULL;
+	for (i = 0; resource_type(iores_array + i) == IORESOURCE_MEM; ++i) {
+		if (buf->control_address >= iores_array[i].start &&
+		    buf->control_address + sizeof(struct crb_regs_tail) - 1 <=
+		    iores_array[i].end) {
+			iores = iores_array + i;
+			iobase_ptr = iobase_array + i;
+			break;
+		}
+	}
+
+	priv->regs_t = crb_map_res(dev, iores, iobase_ptr, buf->control_address,
+				   sizeof(struct crb_regs_tail));
+
+	if (IS_ERR(priv->regs_t))
+		return PTR_ERR(priv->regs_t);
 
 	/* The ACPI IO region starts at the head area and continues to include
 	 * the control area, as one nice sane region except for some older
@@ -523,9 +559,10 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,
 	 */
 	if ((priv->sm == ACPI_TPM2_COMMAND_BUFFER) ||
 	    (priv->sm == ACPI_TPM2_MEMORY_MAPPED)) {
-		if (buf->control_address == io_res.start +
+		if (iores &&
+		    buf->control_address == iores->start +
 		    sizeof(*priv->regs_h))
-			priv->regs_h = priv->iobase;
+			priv->regs_h = *iobase_ptr;
 		else
 			dev_warn(dev, FW_BUG "Bad ACPI memory layout");
 	}
@@ -534,13 +571,6 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,
 	if (ret)
 		return ret;
 
-	priv->regs_t = crb_map_res(dev, priv, &io_res, buf->control_address,
-				   sizeof(struct crb_regs_tail));
-	if (IS_ERR(priv->regs_t)) {
-		ret = PTR_ERR(priv->regs_t);
-		goto out_relinquish_locality;
-	}
-
 	/*
 	 * PTT HW bug w/a: wake up the device to access
 	 * possibly not retained registers.
@@ -552,13 +582,26 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,
 	pa_high = ioread32(&priv->regs_t->ctrl_cmd_pa_high);
 	pa_low  = ioread32(&priv->regs_t->ctrl_cmd_pa_low);
 	cmd_pa = ((u64)pa_high << 32) | pa_low;
-	cmd_size = crb_fixup_cmd_size(dev, &io_res, cmd_pa,
-				      ioread32(&priv->regs_t->ctrl_cmd_size));
+	cmd_size = ioread32(&priv->regs_t->ctrl_cmd_size);
+
+	iores = NULL;
+	iobase_ptr = NULL;
+	for (i = 0; iores_array[i].end; ++i) {
+		if (cmd_pa >= iores_array[i].start &&
+		    cmd_pa <= iores_array[i].end) {
+			iores = iores_array + i;
+			iobase_ptr = iobase_array + i;
+			break;
+		}
+	}
+
+	if (iores)
+		cmd_size = crb_fixup_cmd_size(dev, iores, cmd_pa, cmd_size);
 
 	dev_dbg(dev, "cmd_hi = %X cmd_low = %X cmd_size %X\n",
 		pa_high, pa_low, cmd_size);
 
-	priv->cmd = crb_map_res(dev, priv, &io_res, cmd_pa, cmd_size);
+	priv->cmd = crb_map_res(dev, iores, iobase_ptr,	cmd_pa, cmd_size);
 	if (IS_ERR(priv->cmd)) {
 		ret = PTR_ERR(priv->cmd);
 		goto out;
@@ -566,11 +609,25 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,
 
 	memcpy_fromio(&__rsp_pa, &priv->regs_t->ctrl_rsp_pa, 8);
 	rsp_pa = le64_to_cpu(__rsp_pa);
-	rsp_size = crb_fixup_cmd_size(dev, &io_res, rsp_pa,
-				      ioread32(&priv->regs_t->ctrl_rsp_size));
+	rsp_size = ioread32(&priv->regs_t->ctrl_rsp_size);
+
+	iores = NULL;
+	iobase_ptr = NULL;
+	for (i = 0; resource_type(iores_array + i) == IORESOURCE_MEM; ++i) {
+		if (rsp_pa >= iores_array[i].start &&
+		    rsp_pa <= iores_array[i].end) {
+			iores = iores_array + i;
+			iobase_ptr = iobase_array + i;
+			break;
+		}
+	}
+
+	if (iores)
+		rsp_size = crb_fixup_cmd_size(dev, iores, rsp_pa, rsp_size);
 
 	if (cmd_pa != rsp_pa) {
-		priv->rsp = crb_map_res(dev, priv, &io_res, rsp_pa, rsp_size);
+		priv->rsp = crb_map_res(dev, iores, iobase_ptr,
+					rsp_pa, rsp_size);
 		ret = PTR_ERR_OR_ZERO(priv->rsp);
 		goto out;
 	}
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index e4fdde93ed4c..e7df342a317d 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -286,7 +286,7 @@ static int tpm_tis_plat_probe(struct platform_device *pdev)
 	}
 	tpm_info.res = *res;
 
-	tpm_info.irq = platform_get_irq(pdev, 0);
+	tpm_info.irq = platform_get_irq_optional(pdev, 0);
 	if (tpm_info.irq <= 0) {
 		if (pdev != force_pdev)
 			tpm_info.irq = -1;
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index 270f43acbb77..8af2cee1a762 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -506,6 +506,84 @@ static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len)
 	return rc;
 }
 
+struct tis_vendor_durations_override {
+	u32 did_vid;
+	struct tpm1_version version;
+	unsigned long durations[3];
+};
+
+static const struct  tis_vendor_durations_override vendor_dur_overrides[] = {
+	/* STMicroelectronics 0x104a */
+	{ 0x0000104a,
+	  { 1, 2, 8, 28 },
+	  { (2 * 60 * HZ), (2 * 60 * HZ), (2 * 60 * HZ) } },
+};
+
+static void tpm_tis_update_durations(struct tpm_chip *chip,
+				     unsigned long *duration_cap)
+{
+	struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev);
+	struct tpm1_version *version;
+	u32 did_vid;
+	int i, rc;
+	cap_t cap;
+
+	chip->duration_adjusted = false;
+
+	if (chip->ops->clk_enable != NULL)
+		chip->ops->clk_enable(chip, true);
+
+	rc = tpm_tis_read32(priv, TPM_DID_VID(0), &did_vid);
+	if (rc < 0) {
+		dev_warn(&chip->dev, "%s: failed to read did_vid. %d\n",
+			 __func__, rc);
+		goto out;
+	}
+
+	/* Try to get a TPM version 1.2 or 1.1 TPM_CAP_VERSION_INFO */
+	rc = tpm1_getcap(chip, TPM_CAP_VERSION_1_2, &cap,
+			 "attempting to determine the 1.2 version",
+			 sizeof(cap.version2));
+	if (!rc) {
+		version = &cap.version2.version;
+	} else {
+		rc = tpm1_getcap(chip, TPM_CAP_VERSION_1_1, &cap,
+				 "attempting to determine the 1.1 version",
+				 sizeof(cap.version1));
+
+		if (rc)
+			goto out;
+
+		version = &cap.version1;
+	}
+
+	for (i = 0; i != ARRAY_SIZE(vendor_dur_overrides); i++) {
+		if (vendor_dur_overrides[i].did_vid != did_vid)
+			continue;
+
+		if ((version->major ==
+		     vendor_dur_overrides[i].version.major) &&
+		    (version->minor ==
+		     vendor_dur_overrides[i].version.minor) &&
+		    (version->rev_major ==
+		     vendor_dur_overrides[i].version.rev_major) &&
+		    (version->rev_minor ==
+		     vendor_dur_overrides[i].version.rev_minor)) {
+
+			memcpy(duration_cap,
+			       vendor_dur_overrides[i].durations,
+			       sizeof(vendor_dur_overrides[i].durations));
+
+			chip->duration_adjusted = true;
+			goto out;
+		}
+	}
+
+out:
+	if (chip->ops->clk_enable != NULL)
+		chip->ops->clk_enable(chip, false);
+}
+
 struct tis_vendor_timeout_override {
 	u32 did_vid;
 	unsigned long timeout_us[4];
@@ -842,6 +920,7 @@ static const struct tpm_class_ops tpm_tis = {
 	.send = tpm_tis_send,
 	.cancel = tpm_tis_ready,
 	.update_timeouts = tpm_tis_update_timeouts,
+	.update_durations = tpm_tis_update_durations,
 	.req_complete_mask = TPM_STS_DATA_AVAIL | TPM_STS_VALID,
 	.req_complete_val = TPM_STS_DATA_AVAIL | TPM_STS_VALID,
 	.req_canceled = tpm_tis_req_canceled,
diff --git a/drivers/char/tpm/tpm_tis_spi.c b/drivers/char/tpm/tpm_tis_spi.c
index 19513e622053..d1754fd6c573 100644
--- a/drivers/char/tpm/tpm_tis_spi.c
+++ b/drivers/char/tpm/tpm_tis_spi.c
@@ -20,42 +20,64 @@
  * Dorn and Kyleen Hall and Jarko Sakkinnen.
  */
 
+#include <linux/acpi.h>
+#include <linux/completion.h>
 #include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/moduleparam.h>
 #include <linux/slab.h>
-#include <linux/interrupt.h>
-#include <linux/wait.h>
-#include <linux/acpi.h>
-#include <linux/freezer.h>
 
+#include <linux/of_device.h>
 #include <linux/spi/spi.h>
-#include <linux/gpio.h>
-#include <linux/of_irq.h>
-#include <linux/of_gpio.h>
 #include <linux/tpm.h>
+
 #include "tpm.h"
 #include "tpm_tis_core.h"
+#include "tpm_tis_spi.h"
 
 #define MAX_SPI_FRAMESIZE 64
 
-struct tpm_tis_spi_phy {
-	struct tpm_tis_data priv;
-	struct spi_device *spi_device;
-	u8 *iobuf;
-};
-
-static inline struct tpm_tis_spi_phy *to_tpm_tis_spi_phy(struct tpm_tis_data *data)
+/*
+ * TCG SPI flow control is documented in section 6.4 of the spec[1]. In short,
+ * keep trying to read from the device until MISO goes high indicating the
+ * wait state has ended.
+ *
+ * [1] https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/
+ */
+static int tpm_tis_spi_flow_control(struct tpm_tis_spi_phy *phy,
+				    struct spi_transfer *spi_xfer)
 {
-	return container_of(data, struct tpm_tis_spi_phy, priv);
+	struct spi_message m;
+	int ret, i;
+
+	if ((phy->iobuf[3] & 0x01) == 0) {
+		// handle SPI wait states
+		phy->iobuf[0] = 0;
+
+		for (i = 0; i < TPM_RETRY; i++) {
+			spi_xfer->len = 1;
+			spi_message_init(&m);
+			spi_message_add_tail(spi_xfer, &m);
+			ret = spi_sync_locked(phy->spi_device, &m);
+			if (ret < 0)
+				return ret;
+			if (phy->iobuf[0] & 0x01)
+				break;
+		}
+
+		if (i == TPM_RETRY)
+			return -ETIMEDOUT;
+	}
+
+	return 0;
 }
 
-static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
-				u8 *in, const u8 *out)
+int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
+			 u8 *in, const u8 *out)
 {
 	struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data);
 	int ret = 0;
-	int i;
 	struct spi_message m;
 	struct spi_transfer spi_xfer;
 	u8 transfer_len;
@@ -82,26 +104,9 @@ static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
 		if (ret < 0)
 			goto exit;
 
-		if ((phy->iobuf[3] & 0x01) == 0) {
-			// handle SPI wait states
-			phy->iobuf[0] = 0;
-
-			for (i = 0; i < TPM_RETRY; i++) {
-				spi_xfer.len = 1;
-				spi_message_init(&m);
-				spi_message_add_tail(&spi_xfer, &m);
-				ret = spi_sync_locked(phy->spi_device, &m);
-				if (ret < 0)
-					goto exit;
-				if (phy->iobuf[0] & 0x01)
-					break;
-			}
-
-			if (i == TPM_RETRY) {
-				ret = -ETIMEDOUT;
-				goto exit;
-			}
-		}
+		ret = phy->flow_control(phy, &spi_xfer);
+		if (ret < 0)
+			goto exit;
 
 		spi_xfer.cs_change = 0;
 		spi_xfer.len = transfer_len;
@@ -117,6 +122,7 @@ static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
 
 		spi_message_init(&m);
 		spi_message_add_tail(&spi_xfer, &m);
+		reinit_completion(&phy->ready);
 		ret = spi_sync_locked(phy->spi_device, &m);
 		if (ret < 0)
 			goto exit;
@@ -146,7 +152,7 @@ static int tpm_tis_spi_write_bytes(struct tpm_tis_data *data, u32 addr,
 	return tpm_tis_spi_transfer(data, addr, len, NULL, value);
 }
 
-static int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result)
+int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result)
 {
 	__le16 result_le;
 	int rc;
@@ -159,7 +165,7 @@ static int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result)
 	return rc;
 }
 
-static int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result)
+int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result)
 {
 	__le32 result_le;
 	int rc;
@@ -172,7 +178,7 @@ static int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result)
 	return rc;
 }
 
-static int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value)
+int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value)
 {
 	__le32 value_le;
 	int rc;
@@ -184,6 +190,18 @@ static int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value)
 	return rc;
 }
 
+int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy,
+		     int irq, const struct tpm_tis_phy_ops *phy_ops)
+{
+	phy->iobuf = devm_kmalloc(&spi->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL);
+	if (!phy->iobuf)
+		return -ENOMEM;
+
+	phy->spi_device = spi;
+
+	return tpm_tis_core_init(&spi->dev, &phy->priv, irq, phy_ops, NULL);
+}
+
 static const struct tpm_tis_phy_ops tpm_spi_phy_ops = {
 	.read_bytes = tpm_tis_spi_read_bytes,
 	.write_bytes = tpm_tis_spi_write_bytes,
@@ -202,11 +220,7 @@ static int tpm_tis_spi_probe(struct spi_device *dev)
 	if (!phy)
 		return -ENOMEM;
 
-	phy->spi_device = dev;
-
-	phy->iobuf = devm_kmalloc(&dev->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL);
-	if (!phy->iobuf)
-		return -ENOMEM;
+	phy->flow_control = tpm_tis_spi_flow_control;
 
 	/* If the SPI device has an IRQ then use that */
 	if (dev->irq > 0)
@@ -214,11 +228,27 @@ static int tpm_tis_spi_probe(struct spi_device *dev)
 	else
 		irq = -1;
 
-	return tpm_tis_core_init(&dev->dev, &phy->priv, irq, &tpm_spi_phy_ops,
-				 NULL);
+	init_completion(&phy->ready);
+	return tpm_tis_spi_init(dev, phy, irq, &tpm_spi_phy_ops);
+}
+
+typedef int (*tpm_tis_spi_probe_func)(struct spi_device *);
+
+static int tpm_tis_spi_driver_probe(struct spi_device *spi)
+{
+	const struct spi_device_id *spi_dev_id = spi_get_device_id(spi);
+	tpm_tis_spi_probe_func probe_func;
+
+	probe_func = of_device_get_match_data(&spi->dev);
+	if (!probe_func && spi_dev_id)
+		probe_func = (tpm_tis_spi_probe_func)spi_dev_id->driver_data;
+	if (!probe_func)
+		return -ENODEV;
+
+	return probe_func(spi);
 }
 
-static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_resume);
+static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_spi_resume);
 
 static int tpm_tis_spi_remove(struct spi_device *dev)
 {
@@ -230,15 +260,17 @@ static int tpm_tis_spi_remove(struct spi_device *dev)
 }
 
 static const struct spi_device_id tpm_tis_spi_id[] = {
-	{"tpm_tis_spi", 0},
+	{ "tpm_tis_spi", (unsigned long)tpm_tis_spi_probe },
+	{ "cr50", (unsigned long)cr50_spi_probe },
 	{}
 };
 MODULE_DEVICE_TABLE(spi, tpm_tis_spi_id);
 
 static const struct of_device_id of_tis_spi_match[] = {
-	{ .compatible = "st,st33htpm-spi", },
-	{ .compatible = "infineon,slb9670", },
-	{ .compatible = "tcg,tpm_tis-spi", },
+	{ .compatible = "st,st33htpm-spi", .data = tpm_tis_spi_probe },
+	{ .compatible = "infineon,slb9670", .data = tpm_tis_spi_probe },
+	{ .compatible = "tcg,tpm_tis-spi", .data = tpm_tis_spi_probe },
+	{ .compatible = "google,cr50", .data = cr50_spi_probe },
 	{}
 };
 MODULE_DEVICE_TABLE(of, of_tis_spi_match);
@@ -251,13 +283,12 @@ MODULE_DEVICE_TABLE(acpi, acpi_tis_spi_match);
 
 static struct spi_driver tpm_tis_spi_driver = {
 	.driver = {
-		.owner = THIS_MODULE,
 		.name = "tpm_tis_spi",
 		.pm = &tpm_tis_pm,
 		.of_match_table = of_match_ptr(of_tis_spi_match),
 		.acpi_match_table = ACPI_PTR(acpi_tis_spi_match),
 	},
-	.probe = tpm_tis_spi_probe,
+	.probe = tpm_tis_spi_driver_probe,
 	.remove = tpm_tis_spi_remove,
 	.id_table = tpm_tis_spi_id,
 };
diff --git a/drivers/char/tpm/tpm_tis_spi.h b/drivers/char/tpm/tpm_tis_spi.h
new file mode 100644
index 000000000000..bba73979c368
--- /dev/null
+++ b/drivers/char/tpm/tpm_tis_spi.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2015 Infineon Technologies AG
+ * Copyright (C) 2016 STMicroelectronics SAS
+ */
+
+#ifndef TPM_TIS_SPI_H
+#define TPM_TIS_SPI_H
+
+#include "tpm_tis_core.h"
+
+struct tpm_tis_spi_phy {
+	struct tpm_tis_data priv;
+	struct spi_device *spi_device;
+	int (*flow_control)(struct tpm_tis_spi_phy *phy,
+			     struct spi_transfer *xfer);
+	struct completion ready;
+	unsigned long wake_after;
+
+	u8 *iobuf;
+};
+
+static inline struct tpm_tis_spi_phy *to_tpm_tis_spi_phy(struct tpm_tis_data *data)
+{
+	return container_of(data, struct tpm_tis_spi_phy, priv);
+}
+
+extern int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy,
+			    int irq, const struct tpm_tis_phy_ops *phy_ops);
+
+extern int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
+				u8 *in, const u8 *out);
+
+extern int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result);
+extern int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result);
+extern int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value);
+
+#ifdef CONFIG_TCG_TIS_SPI_CR50
+extern int cr50_spi_probe(struct spi_device *spi);
+#else
+static inline int cr50_spi_probe(struct spi_device *spi)
+{
+	return -ENODEV;
+}
+#endif
+
+#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_TCG_TIS_SPI_CR50)
+extern int tpm_tis_spi_resume(struct device *dev);
+#else
+#define tpm_tis_spi_resume	NULL
+#endif
+
+#endif
diff --git a/drivers/char/tpm/tpm_tis_spi_cr50.c b/drivers/char/tpm/tpm_tis_spi_cr50.c
new file mode 100644
index 000000000000..37d72e818335
--- /dev/null
+++ b/drivers/char/tpm/tpm_tis_spi_cr50.c
@@ -0,0 +1,322 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2016 Google, Inc
+ *
+ * This device driver implements a TCG PTP FIFO interface over SPI for chips
+ * with Cr50 firmware.
+ * It is based on tpm_tis_spi driver by Peter Huewe and Christophe Ricard.
+ */
+
+#include <linux/completion.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/pm.h>
+#include <linux/spi/spi.h>
+#include <linux/wait.h>
+
+#include "tpm_tis_core.h"
+#include "tpm_tis_spi.h"
+
+/*
+ * Cr50 timing constants:
+ * - can go to sleep not earlier than after CR50_SLEEP_DELAY_MSEC.
+ * - needs up to CR50_WAKE_START_DELAY_USEC to wake after sleep.
+ * - requires waiting for "ready" IRQ, if supported; or waiting for at least
+ *   CR50_NOIRQ_ACCESS_DELAY_MSEC between transactions, if IRQ is not supported.
+ * - waits for up to CR50_FLOW_CONTROL for flow control 'ready' indication.
+ */
+#define CR50_SLEEP_DELAY_MSEC			1000
+#define CR50_WAKE_START_DELAY_USEC		1000
+#define CR50_NOIRQ_ACCESS_DELAY			msecs_to_jiffies(2)
+#define CR50_READY_IRQ_TIMEOUT			msecs_to_jiffies(TPM2_TIMEOUT_A)
+#define CR50_FLOW_CONTROL			msecs_to_jiffies(TPM2_TIMEOUT_A)
+#define MAX_IRQ_CONFIRMATION_ATTEMPTS		3
+
+#define TPM_CR50_FW_VER(l)			(0x0f90 | ((l) << 12))
+#define TPM_CR50_MAX_FW_VER_LEN			64
+
+struct cr50_spi_phy {
+	struct tpm_tis_spi_phy spi_phy;
+
+	struct mutex time_track_mutex;
+	unsigned long last_access;
+
+	unsigned long access_delay;
+
+	unsigned int irq_confirmation_attempt;
+	bool irq_needs_confirmation;
+	bool irq_confirmed;
+};
+
+static inline struct cr50_spi_phy *to_cr50_spi_phy(struct tpm_tis_spi_phy *phy)
+{
+	return container_of(phy, struct cr50_spi_phy, spi_phy);
+}
+
+/*
+ * The cr50 interrupt handler just signals waiting threads that the
+ * interrupt was asserted.  It does not do any processing triggered
+ * by interrupts but is instead used to avoid fixed delays.
+ */
+static irqreturn_t cr50_spi_irq_handler(int dummy, void *dev_id)
+{
+	struct cr50_spi_phy *cr50_phy = dev_id;
+
+	cr50_phy->irq_confirmed = true;
+	complete(&cr50_phy->spi_phy.ready);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * Cr50 needs to have at least some delay between consecutive
+ * transactions. Make sure we wait.
+ */
+static void cr50_ensure_access_delay(struct cr50_spi_phy *phy)
+{
+	unsigned long allowed_access = phy->last_access + phy->access_delay;
+	unsigned long time_now = jiffies;
+	struct device *dev = &phy->spi_phy.spi_device->dev;
+
+	/*
+	 * Note: There is a small chance, if Cr50 is not accessed in a few days,
+	 * that time_in_range will not provide the correct result after the wrap
+	 * around for jiffies. In this case, we'll have an unneeded short delay,
+	 * which is fine.
+	 */
+	if (time_in_range_open(time_now, phy->last_access, allowed_access)) {
+		unsigned long remaining, timeout = allowed_access - time_now;
+
+		remaining = wait_for_completion_timeout(&phy->spi_phy.ready,
+							timeout);
+		if (!remaining && phy->irq_confirmed)
+			dev_warn(dev, "Timeout waiting for TPM ready IRQ\n");
+	}
+
+	if (phy->irq_needs_confirmation) {
+		unsigned int attempt = ++phy->irq_confirmation_attempt;
+
+		if (phy->irq_confirmed) {
+			phy->irq_needs_confirmation = false;
+			phy->access_delay = CR50_READY_IRQ_TIMEOUT;
+			dev_info(dev, "TPM ready IRQ confirmed on attempt %u\n",
+				 attempt);
+		} else if (attempt > MAX_IRQ_CONFIRMATION_ATTEMPTS) {
+			phy->irq_needs_confirmation = false;
+			dev_warn(dev, "IRQ not confirmed - will use delays\n");
+		}
+	}
+}
+
+/*
+ * Cr50 might go to sleep if there is no SPI activity for some time and
+ * miss the first few bits/bytes on the bus. In such case, wake it up
+ * by asserting CS and give it time to start up.
+ */
+static bool cr50_needs_waking(struct cr50_spi_phy *phy)
+{
+	/*
+	 * Note: There is a small chance, if Cr50 is not accessed in a few days,
+	 * that time_in_range will not provide the correct result after the wrap
+	 * around for jiffies. In this case, we'll probably timeout or read
+	 * incorrect value from TPM_STS and just retry the operation.
+	 */
+	return !time_in_range_open(jiffies, phy->last_access,
+				   phy->spi_phy.wake_after);
+}
+
+static void cr50_wake_if_needed(struct cr50_spi_phy *cr50_phy)
+{
+	struct tpm_tis_spi_phy *phy = &cr50_phy->spi_phy;
+
+	if (cr50_needs_waking(cr50_phy)) {
+		/* Assert CS, wait 1 msec, deassert CS */
+		struct spi_transfer spi_cs_wake = { .delay_usecs = 1000 };
+
+		spi_sync_transfer(phy->spi_device, &spi_cs_wake, 1);
+		/* Wait for it to fully wake */
+		usleep_range(CR50_WAKE_START_DELAY_USEC,
+			     CR50_WAKE_START_DELAY_USEC * 2);
+	}
+
+	/* Reset the time when we need to wake Cr50 again */
+	phy->wake_after = jiffies + msecs_to_jiffies(CR50_SLEEP_DELAY_MSEC);
+}
+
+/*
+ * Flow control: clock the bus and wait for cr50 to set LSB before
+ * sending/receiving data. TCG PTP spec allows it to happen during
+ * the last byte of header, but cr50 never does that in practice,
+ * and earlier versions had a bug when it was set too early, so don't
+ * check for it during header transfer.
+ */
+static int cr50_spi_flow_control(struct tpm_tis_spi_phy *phy,
+				 struct spi_transfer *spi_xfer)
+{
+	struct device *dev = &phy->spi_device->dev;
+	unsigned long timeout = jiffies + CR50_FLOW_CONTROL;
+	struct spi_message m;
+	int ret;
+
+	spi_xfer->len = 1;
+
+	do {
+		spi_message_init(&m);
+		spi_message_add_tail(spi_xfer, &m);
+		ret = spi_sync_locked(phy->spi_device, &m);
+		if (ret < 0)
+			return ret;
+
+		if (time_after(jiffies, timeout)) {
+			dev_warn(dev, "Timeout during flow control\n");
+			return -EBUSY;
+		}
+	} while (!(phy->iobuf[0] & 0x01));
+
+	return 0;
+}
+
+static int tpm_tis_spi_cr50_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
+				     u8 *in, const u8 *out)
+{
+	struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data);
+	struct cr50_spi_phy *cr50_phy = to_cr50_spi_phy(phy);
+	int ret;
+
+	mutex_lock(&cr50_phy->time_track_mutex);
+	/*
+	 * Do this outside of spi_bus_lock in case cr50 is not the
+	 * only device on that spi bus.
+	 */
+	cr50_ensure_access_delay(cr50_phy);
+	cr50_wake_if_needed(cr50_phy);
+
+	ret = tpm_tis_spi_transfer(data, addr, len, in, out);
+
+	cr50_phy->last_access = jiffies;
+	mutex_unlock(&cr50_phy->time_track_mutex);
+
+	return ret;
+}
+
+static int tpm_tis_spi_cr50_read_bytes(struct tpm_tis_data *data, u32 addr,
+				       u16 len, u8 *result)
+{
+	return tpm_tis_spi_cr50_transfer(data, addr, len, result, NULL);
+}
+
+static int tpm_tis_spi_cr50_write_bytes(struct tpm_tis_data *data, u32 addr,
+					u16 len, const u8 *value)
+{
+	return tpm_tis_spi_cr50_transfer(data, addr, len, NULL, value);
+}
+
+static const struct tpm_tis_phy_ops tpm_spi_cr50_phy_ops = {
+	.read_bytes = tpm_tis_spi_cr50_read_bytes,
+	.write_bytes = tpm_tis_spi_cr50_write_bytes,
+	.read16 = tpm_tis_spi_read16,
+	.read32 = tpm_tis_spi_read32,
+	.write32 = tpm_tis_spi_write32,
+};
+
+static void cr50_print_fw_version(struct tpm_tis_data *data)
+{
+	struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data);
+	int i, len = 0;
+	char fw_ver[TPM_CR50_MAX_FW_VER_LEN + 1];
+	char fw_ver_block[4];
+
+	/*
+	 * Write anything to TPM_CR50_FW_VER to start from the beginning
+	 * of the version string
+	 */
+	tpm_tis_write8(data, TPM_CR50_FW_VER(data->locality), 0);
+
+	/* Read the string, 4 bytes at a time, until we get '\0' */
+	do {
+		tpm_tis_read_bytes(data, TPM_CR50_FW_VER(data->locality), 4,
+				   fw_ver_block);
+		for (i = 0; i < 4 && fw_ver_block[i]; ++len, ++i)
+			fw_ver[len] = fw_ver_block[i];
+	} while (i == 4 && len < TPM_CR50_MAX_FW_VER_LEN);
+	fw_ver[len] = '\0';
+
+	dev_info(&phy->spi_device->dev, "Cr50 firmware version: %s\n", fw_ver);
+}
+
+int cr50_spi_probe(struct spi_device *spi)
+{
+	struct tpm_tis_spi_phy *phy;
+	struct cr50_spi_phy *cr50_phy;
+	int ret;
+	struct tpm_chip *chip;
+
+	cr50_phy = devm_kzalloc(&spi->dev, sizeof(*cr50_phy), GFP_KERNEL);
+	if (!cr50_phy)
+		return -ENOMEM;
+
+	phy = &cr50_phy->spi_phy;
+	phy->flow_control = cr50_spi_flow_control;
+	phy->wake_after = jiffies;
+	init_completion(&phy->ready);
+
+	cr50_phy->access_delay = CR50_NOIRQ_ACCESS_DELAY;
+	cr50_phy->last_access = jiffies;
+	mutex_init(&cr50_phy->time_track_mutex);
+
+	if (spi->irq > 0) {
+		ret = devm_request_irq(&spi->dev, spi->irq,
+				       cr50_spi_irq_handler,
+				       IRQF_TRIGGER_RISING | IRQF_ONESHOT,
+				       "cr50_spi", cr50_phy);
+		if (ret < 0) {
+			if (ret == -EPROBE_DEFER)
+				return ret;
+			dev_warn(&spi->dev, "Requesting IRQ %d failed: %d\n",
+				 spi->irq, ret);
+			/*
+			 * This is not fatal, the driver will fall back to
+			 * delays automatically, since ready will never
+			 * be completed without a registered irq handler.
+			 * So, just fall through.
+			 */
+		} else {
+			/*
+			 * IRQ requested, let's verify that it is actually
+			 * triggered, before relying on it.
+			 */
+			cr50_phy->irq_needs_confirmation = true;
+		}
+	} else {
+		dev_warn(&spi->dev,
+			 "No IRQ - will use delays between transactions.\n");
+	}
+
+	ret = tpm_tis_spi_init(spi, phy, -1, &tpm_spi_cr50_phy_ops);
+	if (ret)
+		return ret;
+
+	cr50_print_fw_version(&phy->priv);
+
+	chip = dev_get_drvdata(&spi->dev);
+	chip->flags |= TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED;
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+int tpm_tis_spi_resume(struct device *dev)
+{
+	struct tpm_chip *chip = dev_get_drvdata(dev);
+	struct tpm_tis_data *data = dev_get_drvdata(&chip->dev);
+	struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data);
+	/*
+	 * Jiffies not increased during suspend, so we need to reset
+	 * the time to wake Cr50 after resume.
+	 */
+	phy->wake_after = jiffies;
+
+	return tpm_tis_resume(dev);
+}
+#endif
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 7270e7b69262..3259426f01dc 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1325,24 +1325,24 @@ static void set_console_size(struct port *port, u16 rows, u16 cols)
 	port->cons.ws.ws_col = cols;
 }
 
-static unsigned int fill_queue(struct virtqueue *vq, spinlock_t *lock)
+static int fill_queue(struct virtqueue *vq, spinlock_t *lock)
 {
 	struct port_buffer *buf;
-	unsigned int nr_added_bufs;
+	int nr_added_bufs;
 	int ret;
 
 	nr_added_bufs = 0;
 	do {
 		buf = alloc_buf(vq->vdev, PAGE_SIZE, 0);
 		if (!buf)
-			break;
+			return -ENOMEM;
 
 		spin_lock_irq(lock);
 		ret = add_inbuf(vq, buf);
 		if (ret < 0) {
 			spin_unlock_irq(lock);
 			free_buf(buf, true);
-			break;
+			return ret;
 		}
 		nr_added_bufs++;
 		spin_unlock_irq(lock);
@@ -1362,7 +1362,6 @@ static int add_port(struct ports_device *portdev, u32 id)
 	char debugfs_name[16];
 	struct port *port;
 	dev_t devt;
-	unsigned int nr_added_bufs;
 	int err;
 
 	port = kmalloc(sizeof(*port), GFP_KERNEL);
@@ -1421,11 +1420,13 @@ static int add_port(struct ports_device *portdev, u32 id)
 	spin_lock_init(&port->outvq_lock);
 	init_waitqueue_head(&port->waitqueue);
 
-	/* Fill the in_vq with buffers so the host can send us data. */
-	nr_added_bufs = fill_queue(port->in_vq, &port->inbuf_lock);
-	if (!nr_added_bufs) {
+	/* We can safely ignore ENOSPC because it means
+	 * the queue already has buffers. Buffers are removed
+	 * only by virtcons_remove(), not by unplug_port()
+	 */
+	err = fill_queue(port->in_vq, &port->inbuf_lock);
+	if (err < 0 && err != -ENOSPC) {
 		dev_err(port->dev, "Error allocating inbufs\n");
-		err = -ENOMEM;
 		goto free_device;
 	}
 
@@ -2059,14 +2060,11 @@ static int virtcons_probe(struct virtio_device *vdev)
 	INIT_WORK(&portdev->control_work, &control_work_handler);
 
 	if (multiport) {
-		unsigned int nr_added_bufs;
-
 		spin_lock_init(&portdev->c_ivq_lock);
 		spin_lock_init(&portdev->c_ovq_lock);
 
-		nr_added_bufs = fill_queue(portdev->c_ivq,
-					   &portdev->c_ivq_lock);
-		if (!nr_added_bufs) {
+		err = fill_queue(portdev->c_ivq, &portdev->c_ivq_lock);
+		if (err < 0) {
 			dev_err(&vdev->dev,
 				"Error allocating buffers for control queue\n");
 			/*
@@ -2077,7 +2075,7 @@ static int virtcons_probe(struct virtio_device *vdev)
 					   VIRTIO_CONSOLE_DEVICE_READY, 0);
 			/* Device was functional: we need full cleanup. */
 			virtcons_remove(vdev);
-			return -ENOMEM;
+			return err;
 		}
 	} else {
 		/*
diff --git a/drivers/clocksource/samsung_pwm_timer.c b/drivers/clocksource/samsung_pwm_timer.c
index 895f53eb5771..dae1b2b5a0c5 100644
--- a/drivers/clocksource/samsung_pwm_timer.c
+++ b/drivers/clocksource/samsung_pwm_timer.c
@@ -430,8 +430,7 @@ static int __init samsung_pwm_alloc(struct device_node *np,
 
 	of_property_for_each_u32(np, "samsung,pwm-outputs", prop, cur, val) {
 		if (val >= SAMSUNG_PWM_NUM) {
-			pr_warning("%s: invalid channel index in samsung,pwm-outputs property\n",
-								__func__);
+			pr_warn("%s: invalid channel index in samsung,pwm-outputs property\n", __func__);
 			continue;
 		}
 		pwm.variant.output_mask |= 1 << val;
diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index 890813e0bb76..e9caa9586982 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -23,7 +23,7 @@
 #include <asm/clock.h>
 #include <asm/idle.h>
 
-#include <asm/mach-loongson64/loongson.h>
+#include <asm/mach-loongson2ef/loongson.h>
 
 static uint nowait;
 
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 1fb622f2a87d..43ed1b621718 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -11,6 +11,8 @@ menuconfig CRYPTO_HW
 
 if CRYPTO_HW
 
+source "drivers/crypto/allwinner/Kconfig"
+
 config CRYPTO_DEV_PADLOCK
 	tristate "Support for VIA PadLock ACE"
 	depends on X86 && !UML
@@ -26,7 +28,7 @@ config CRYPTO_DEV_PADLOCK
 config CRYPTO_DEV_PADLOCK_AES
 	tristate "PadLock driver for AES algorithm"
 	depends on CRYPTO_DEV_PADLOCK
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_AES
 	help
 	  Use VIA PadLock for AES algorithm.
@@ -54,7 +56,7 @@ config CRYPTO_DEV_GEODE
 	tristate "Support for the Geode LX AES engine"
 	depends on X86_32 && PCI
 	select CRYPTO_ALGAPI
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	help
 	  Say 'Y' here to use the AMD Geode LX processor on-board AES
 	  engine for the CryptoAPI AES algorithm.
@@ -107,7 +109,7 @@ config CRYPTO_PAES_S390
 	depends on ZCRYPT
 	depends on PKEY
 	select CRYPTO_ALGAPI
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	help
 	  This is the s390 hardware accelerated implementation of the
 	  AES cipher algorithms for use with protected key.
@@ -169,7 +171,7 @@ config CRYPTO_DES_S390
 	tristate "DES and Triple DES cipher algorithms"
 	depends on S390
 	select CRYPTO_ALGAPI
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_DES
 	help
 	  This is the s390 hardware accelerated implementation of the
@@ -182,7 +184,7 @@ config CRYPTO_AES_S390
 	tristate "AES cipher algorithms"
 	depends on S390
 	select CRYPTO_ALGAPI
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	help
 	  This is the s390 hardware accelerated implementation of the
 	  AES cipher algorithms (FIPS-197).
@@ -236,7 +238,7 @@ config CRYPTO_DEV_MARVELL_CESA
 	depends on PLAT_ORION || ARCH_MVEBU
 	select CRYPTO_LIB_AES
 	select CRYPTO_LIB_DES
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_HASH
 	select SRAM
 	help
@@ -248,7 +250,7 @@ config CRYPTO_DEV_MARVELL_CESA
 config CRYPTO_DEV_NIAGARA2
        tristate "Niagara2 Stream Processing Unit driver"
        select CRYPTO_LIB_DES
-       select CRYPTO_BLKCIPHER
+       select CRYPTO_SKCIPHER
        select CRYPTO_HASH
        select CRYPTO_MD5
        select CRYPTO_SHA1
@@ -265,7 +267,7 @@ config CRYPTO_DEV_NIAGARA2
 config CRYPTO_DEV_HIFN_795X
 	tristate "Driver HIFN 795x crypto accelerator chips"
 	select CRYPTO_LIB_DES
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select HW_RANDOM if CRYPTO_DEV_HIFN_795X_RNG
 	depends on PCI
 	depends on !ARCH_DMA_ADDR_T_64BIT
@@ -285,7 +287,7 @@ config CRYPTO_DEV_TALITOS
 	tristate "Talitos Freescale Security Engine (SEC)"
 	select CRYPTO_AEAD
 	select CRYPTO_AUTHENC
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_HASH
 	select HW_RANDOM
 	depends on FSL_SOC
@@ -323,7 +325,7 @@ config CRYPTO_DEV_IXP4XX
 	select CRYPTO_LIB_DES
 	select CRYPTO_AEAD
 	select CRYPTO_AUTHENC
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	help
 	  Driver for the IXP4xx NPE crypto engine.
 
@@ -332,11 +334,12 @@ config CRYPTO_DEV_PPC4XX
 	depends on PPC && 4xx
 	select CRYPTO_HASH
 	select CRYPTO_AEAD
+	select CRYPTO_AES
 	select CRYPTO_LIB_AES
 	select CRYPTO_CCM
 	select CRYPTO_CTR
 	select CRYPTO_GCM
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	help
 	  This option allows you to have support for AMCC crypto acceleration.
 
@@ -373,7 +376,7 @@ config CRYPTO_DEV_OMAP_AES
 	tristate "Support for OMAP AES hw engine"
 	depends on ARCH_OMAP2 || ARCH_OMAP3 || ARCH_OMAP2PLUS
 	select CRYPTO_AES
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_ENGINE
 	select CRYPTO_CBC
 	select CRYPTO_ECB
@@ -387,7 +390,7 @@ config CRYPTO_DEV_OMAP_DES
 	tristate "Support for OMAP DES/3DES hw engine"
 	depends on ARCH_OMAP2PLUS
 	select CRYPTO_LIB_DES
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_ENGINE
 	help
 	  OMAP processors have DES/3DES module accelerator. Select this if you
@@ -403,7 +406,7 @@ config CRYPTO_DEV_PICOXCELL
 	select CRYPTO_AEAD
 	select CRYPTO_AES
 	select CRYPTO_AUTHENC
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_DES
 	select CRYPTO_CBC
 	select CRYPTO_ECB
@@ -418,7 +421,7 @@ config CRYPTO_DEV_PICOXCELL
 config CRYPTO_DEV_SAHARA
 	tristate "Support for SAHARA crypto accelerator"
 	depends on ARCH_MXC && OF
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_AES
 	select CRYPTO_ECB
 	help
@@ -445,7 +448,7 @@ config CRYPTO_DEV_S5P
 	depends on ARCH_S5PV210 || ARCH_EXYNOS || COMPILE_TEST
 	depends on HAS_IOMEM
 	select CRYPTO_AES
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	help
 	  This option allows you to have support for S5P crypto acceleration.
 	  Select this to offload Samsung S5PV210 or S5PC110, Exynos from AES
@@ -489,11 +492,9 @@ if CRYPTO_DEV_UX500
 endif # if CRYPTO_DEV_UX500
 
 config CRYPTO_DEV_ATMEL_AUTHENC
-	tristate "Support for Atmel IPSEC/SSL hw accelerator"
+	bool "Support for Atmel IPSEC/SSL hw accelerator"
 	depends on ARCH_AT91 || COMPILE_TEST
-	select CRYPTO_AUTHENC
-	select CRYPTO_DEV_ATMEL_AES
-	select CRYPTO_DEV_ATMEL_SHA
+	depends on CRYPTO_DEV_ATMEL_AES
 	help
 	  Some Atmel processors can combine the AES and SHA hw accelerators
 	  to enhance support of IPSEC/SSL.
@@ -505,7 +506,9 @@ config CRYPTO_DEV_ATMEL_AES
 	depends on ARCH_AT91 || COMPILE_TEST
 	select CRYPTO_AES
 	select CRYPTO_AEAD
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
+	select CRYPTO_AUTHENC if CRYPTO_DEV_ATMEL_AUTHENC
+	select CRYPTO_DEV_ATMEL_SHA if CRYPTO_DEV_ATMEL_AUTHENC
 	help
 	  Some Atmel processors have AES hw accelerator.
 	  Select this if you want to use the Atmel module for
@@ -518,7 +521,7 @@ config CRYPTO_DEV_ATMEL_TDES
 	tristate "Support for Atmel DES/TDES hw accelerator"
 	depends on ARCH_AT91 || COMPILE_TEST
 	select CRYPTO_LIB_DES
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	help
 	  Some Atmel processors have DES/TDES hw accelerator.
 	  Select this if you want to use the Atmel module for
@@ -590,7 +593,7 @@ config CRYPTO_DEV_MXS_DCP
 	select CRYPTO_CBC
 	select CRYPTO_ECB
 	select CRYPTO_AES
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_HASH
 	help
 	  The Freescale i.MX23/i.MX28 has SHA1/SHA256 and AES128 CBC/ECB
@@ -620,7 +623,7 @@ config CRYPTO_DEV_QCE
 	select CRYPTO_CBC
 	select CRYPTO_XTS
 	select CRYPTO_CTR
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	help
 	  This driver supports Qualcomm crypto engine accelerator
 	  hardware. To compile this driver as a module, choose M here. The
@@ -657,31 +660,6 @@ config CRYPTO_DEV_IMGTEC_HASH
 	  hardware hash accelerator. Supporting MD5/SHA1/SHA224/SHA256
 	  hashing algorithms.
 
-config CRYPTO_DEV_SUN4I_SS
-	tristate "Support for Allwinner Security System cryptographic accelerator"
-	depends on ARCH_SUNXI && !64BIT
-	select CRYPTO_MD5
-	select CRYPTO_SHA1
-	select CRYPTO_AES
-	select CRYPTO_LIB_DES
-	select CRYPTO_BLKCIPHER
-	help
-	  Some Allwinner SoC have a crypto accelerator named
-	  Security System. Select this if you want to use it.
-	  The Security System handle AES/DES/3DES ciphers in CBC mode
-	  and SHA1 and MD5 hash algorithms.
-
-	  To compile this driver as a module, choose M here: the module
-	  will be called sun4i-ss.
-
-config CRYPTO_DEV_SUN4I_SS_PRNG
-	bool "Support for Allwinner Security System PRNG"
-	depends on CRYPTO_DEV_SUN4I_SS
-	select CRYPTO_RNG
-	help
-	  Select this option if you want to provide kernel-side support for
-	  the Pseudo-Random Number Generator found in the Security System.
-
 config CRYPTO_DEV_ROCKCHIP
 	tristate "Rockchip's Cryptographic Engine driver"
 	depends on OF && ARCH_ROCKCHIP
@@ -691,7 +669,7 @@ config CRYPTO_DEV_ROCKCHIP
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
 	select CRYPTO_HASH
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 
 	help
 	  This driver interfaces with the hardware crypto accelerator.
@@ -702,7 +680,7 @@ config CRYPTO_DEV_MEDIATEK
 	depends on (ARM && ARCH_MEDIATEK) || COMPILE_TEST
 	select CRYPTO_AES
 	select CRYPTO_AEAD
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_CTR
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
@@ -730,7 +708,7 @@ config CRYPTO_DEV_BCM_SPU
 	select CRYPTO_SHA512
 	help
 	  This driver provides support for Broadcom crypto acceleration using the
-	  Secure Processing Unit (SPU). The SPU driver registers ablkcipher,
+	  Secure Processing Unit (SPU). The SPU driver registers skcipher,
 	  ahash, and aead algorithms with the kernel cryptographic API.
 
 source "drivers/crypto/stm32/Kconfig"
@@ -740,7 +718,7 @@ config CRYPTO_DEV_SAFEXCEL
 	depends on OF || PCI || COMPILE_TEST
 	select CRYPTO_LIB_AES
 	select CRYPTO_AUTHENC
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_DES
 	select CRYPTO_HASH
 	select CRYPTO_HMAC
@@ -748,6 +726,8 @@ config CRYPTO_DEV_SAFEXCEL
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
 	select CRYPTO_SHA512
+	select CRYPTO_CHACHA20POLY1305
+	select CRYPTO_SHA3
 	help
 	  This driver interfaces with the SafeXcel EIP-97 and EIP-197 cryptographic
 	  engines designed by Inside Secure. It currently accelerates DES, 3DES and
@@ -762,7 +742,7 @@ config CRYPTO_DEV_ARTPEC6
 	select CRYPTO_AEAD
 	select CRYPTO_AES
 	select CRYPTO_ALGAPI
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_CTR
 	select CRYPTO_HASH
 	select CRYPTO_SHA1
@@ -779,7 +759,7 @@ config CRYPTO_DEV_CCREE
 	depends on CRYPTO && CRYPTO_HW && OF && HAS_DMA
 	default n
 	select CRYPTO_HASH
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_DES
 	select CRYPTO_AEAD
 	select CRYPTO_AUTHENC
@@ -805,4 +785,6 @@ config CRYPTO_DEV_CCREE
 
 source "drivers/crypto/hisilicon/Kconfig"
 
+source "drivers/crypto/amlogic/Kconfig"
+
 endif # CRYPTO_HW
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index afc4753b5d28..40229d499476 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_CRYPTO_DEV_ALLWINNER) += allwinner/
 obj-$(CONFIG_CRYPTO_DEV_ATMEL_AES) += atmel-aes.o
 obj-$(CONFIG_CRYPTO_DEV_ATMEL_SHA) += atmel-sha.o
 obj-$(CONFIG_CRYPTO_DEV_ATMEL_TDES) += atmel-tdes.o
@@ -39,7 +40,6 @@ obj-$(CONFIG_CRYPTO_DEV_ROCKCHIP) += rockchip/
 obj-$(CONFIG_CRYPTO_DEV_S5P) += s5p-sss.o
 obj-$(CONFIG_CRYPTO_DEV_SAHARA) += sahara.o
 obj-$(CONFIG_ARCH_STM32) += stm32/
-obj-$(CONFIG_CRYPTO_DEV_SUN4I_SS) += sunxi-ss/
 obj-$(CONFIG_CRYPTO_DEV_TALITOS) += talitos.o
 obj-$(CONFIG_CRYPTO_DEV_UX500) += ux500/
 obj-$(CONFIG_CRYPTO_DEV_VIRTIO) += virtio/
@@ -48,3 +48,4 @@ obj-$(CONFIG_CRYPTO_DEV_BCM_SPU) += bcm/
 obj-$(CONFIG_CRYPTO_DEV_SAFEXCEL) += inside-secure/
 obj-$(CONFIG_CRYPTO_DEV_ARTPEC6) += axis/
 obj-y += hisilicon/
+obj-$(CONFIG_CRYPTO_DEV_AMLOGIC_GXL) += amlogic/
diff --git a/drivers/crypto/allwinner/Kconfig b/drivers/crypto/allwinner/Kconfig
new file mode 100644
index 000000000000..12e7c6a85a02
--- /dev/null
+++ b/drivers/crypto/allwinner/Kconfig
@@ -0,0 +1,87 @@
+config CRYPTO_DEV_ALLWINNER
+	bool "Support for Allwinner cryptographic offloader"
+	depends on ARCH_SUNXI || COMPILE_TEST
+	default y if ARCH_SUNXI
+	help
+	  Say Y here to get to see options for Allwinner hardware crypto devices
+
+config CRYPTO_DEV_SUN4I_SS
+	tristate "Support for Allwinner Security System cryptographic accelerator"
+	depends on ARCH_SUNXI
+	depends on PM
+	depends on CRYPTO_DEV_ALLWINNER
+	select CRYPTO_MD5
+	select CRYPTO_SHA1
+	select CRYPTO_AES
+	select CRYPTO_LIB_DES
+	select CRYPTO_SKCIPHER
+	help
+	  Some Allwinner SoC have a crypto accelerator named
+	  Security System. Select this if you want to use it.
+	  The Security System handle AES/DES/3DES ciphers in CBC mode
+	  and SHA1 and MD5 hash algorithms.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called sun4i-ss.
+
+config CRYPTO_DEV_SUN4I_SS_PRNG
+	bool "Support for Allwinner Security System PRNG"
+	depends on CRYPTO_DEV_SUN4I_SS
+	select CRYPTO_RNG
+	help
+	  Select this option if you want to provide kernel-side support for
+	  the Pseudo-Random Number Generator found in the Security System.
+
+config CRYPTO_DEV_SUN8I_CE
+	tristate "Support for Allwinner Crypto Engine cryptographic offloader"
+	select CRYPTO_SKCIPHER
+	select CRYPTO_ENGINE
+	select CRYPTO_ECB
+	select CRYPTO_CBC
+	select CRYPTO_AES
+	select CRYPTO_DES
+	depends on CRYPTO_DEV_ALLWINNER
+	depends on PM
+	help
+	  Select y here to have support for the crypto Engine availlable on
+	  Allwinner SoC H2+, H3, H5, H6, R40 and A64.
+	  The Crypto Engine handle AES/3DES ciphers in ECB/CBC mode.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called sun8i-ce.
+
+config CRYPTO_DEV_SUN8I_CE_DEBUG
+	bool "Enable sun8i-ce stats"
+	depends on CRYPTO_DEV_SUN8I_CE
+	depends on DEBUG_FS
+	help
+	  Say y to enable sun8i-ce debug stats.
+	  This will create /sys/kernel/debug/sun8i-ce/stats for displaying
+	  the number of requests per flow and per algorithm.
+
+config CRYPTO_DEV_SUN8I_SS
+	tristate "Support for Allwinner Security System cryptographic offloader"
+	select CRYPTO_SKCIPHER
+	select CRYPTO_ENGINE
+	select CRYPTO_ECB
+	select CRYPTO_CBC
+	select CRYPTO_AES
+	select CRYPTO_DES
+	depends on CRYPTO_DEV_ALLWINNER
+	depends on PM
+	help
+	  Select y here to have support for the Security System available on
+	  Allwinner SoC A80, A83T.
+	  The Security System handle AES/3DES ciphers in ECB/CBC mode.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called sun8i-ss.
+
+config CRYPTO_DEV_SUN8I_SS_DEBUG
+	bool "Enable sun8i-ss stats"
+	depends on CRYPTO_DEV_SUN8I_SS
+	depends on DEBUG_FS
+	help
+	  Say y to enable sun8i-ss debug stats.
+	  This will create /sys/kernel/debug/sun8i-ss/stats for displaying
+	  the number of requests per flow and per algorithm.
diff --git a/drivers/crypto/allwinner/Makefile b/drivers/crypto/allwinner/Makefile
new file mode 100644
index 000000000000..6effe864d7ff
--- /dev/null
+++ b/drivers/crypto/allwinner/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_CRYPTO_DEV_SUN4I_SS) += sun4i-ss/
+obj-$(CONFIG_CRYPTO_DEV_SUN8I_CE) += sun8i-ce/
+obj-$(CONFIG_CRYPTO_DEV_SUN8I_SS) += sun8i-ss/
diff --git a/drivers/crypto/sunxi-ss/Makefile b/drivers/crypto/allwinner/sun4i-ss/Makefile
index c0a2797d3168..c0a2797d3168 100644
--- a/drivers/crypto/sunxi-ss/Makefile
+++ b/drivers/crypto/allwinner/sun4i-ss/Makefile
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-cipher.c
index 6536fd4bee65..cb2b0874f68f 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
+++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-cipher.c
@@ -72,7 +72,8 @@ static int noinline_for_stack sun4i_ss_opti_poll(struct skcipher_request *areq)
 	oi = 0;
 	oo = 0;
 	do {
-		todo = min3(rx_cnt, ileft, (mi.length - oi) / 4);
+		todo = min(rx_cnt, ileft);
+		todo = min_t(size_t, todo, (mi.length - oi) / 4);
 		if (todo) {
 			ileft -= todo;
 			writesl(ss->base + SS_RXFIFO, mi.addr + oi, todo);
@@ -87,7 +88,8 @@ static int noinline_for_stack sun4i_ss_opti_poll(struct skcipher_request *areq)
 		rx_cnt = SS_RXFIFO_SPACES(spaces);
 		tx_cnt = SS_TXFIFO_SPACES(spaces);
 
-		todo = min3(tx_cnt, oleft, (mo.length - oo) / 4);
+		todo = min(tx_cnt, oleft);
+		todo = min_t(size_t, todo, (mo.length - oo) / 4);
 		if (todo) {
 			oleft -= todo;
 			readsl(ss->base + SS_TXFIFO, mo.addr + oo, todo);
@@ -239,7 +241,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 			 * todo is the number of consecutive 4byte word that we
 			 * can read from current SG
 			 */
-			todo = min3(rx_cnt, ileft / 4, (mi.length - oi) / 4);
+			todo = min(rx_cnt, ileft / 4);
+			todo = min_t(size_t, todo, (mi.length - oi) / 4);
 			if (todo && !ob) {
 				writesl(ss->base + SS_RXFIFO, mi.addr + oi,
 					todo);
@@ -253,8 +256,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 				 * we need to be able to write all buf in one
 				 * pass, so it is why we min() with rx_cnt
 				 */
-				todo = min3(rx_cnt * 4 - ob, ileft,
-					    mi.length - oi);
+				todo = min(rx_cnt * 4 - ob, ileft);
+				todo = min_t(size_t, todo, mi.length - oi);
 				memcpy(buf + ob, mi.addr + oi, todo);
 				ileft -= todo;
 				oi += todo;
@@ -274,7 +277,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 		spaces = readl(ss->base + SS_FCSR);
 		rx_cnt = SS_RXFIFO_SPACES(spaces);
 		tx_cnt = SS_TXFIFO_SPACES(spaces);
-		dev_dbg(ss->dev, "%x %u/%u %u/%u cnt=%u %u/%u %u/%u cnt=%u %u\n",
+		dev_dbg(ss->dev,
+			"%x %u/%zu %u/%u cnt=%u %u/%zu %u/%u cnt=%u %u\n",
 			mode,
 			oi, mi.length, ileft, areq->cryptlen, rx_cnt,
 			oo, mo.length, oleft, areq->cryptlen, tx_cnt, ob);
@@ -282,7 +286,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 		if (!tx_cnt)
 			continue;
 		/* todo in 4bytes word */
-		todo = min3(tx_cnt, oleft / 4, (mo.length - oo) / 4);
+		todo = min(tx_cnt, oleft / 4);
+		todo = min_t(size_t, todo, (mo.length - oo) / 4);
 		if (todo) {
 			readsl(ss->base + SS_TXFIFO, mo.addr + oo, todo);
 			oleft -= todo * 4;
@@ -308,7 +313,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 				 * no more than remaining buffer
 				 * no need to test against oleft
 				 */
-				todo = min(mo.length - oo, obl - obo);
+				todo = min_t(size_t,
+					     mo.length - oo, obl - obo);
 				memcpy(mo.addr + oo, bufo + obo, todo);
 				oleft -= todo;
 				obo += todo;
@@ -480,6 +486,7 @@ int sun4i_ss_cipher_init(struct crypto_tfm *tfm)
 	struct sun4i_tfm_ctx *op = crypto_tfm_ctx(tfm);
 	struct sun4i_ss_alg_template *algt;
 	const char *name = crypto_tfm_alg_name(tfm);
+	int err;
 
 	memset(op, 0, sizeof(struct sun4i_tfm_ctx));
 
@@ -497,13 +504,22 @@ int sun4i_ss_cipher_init(struct crypto_tfm *tfm)
 		return PTR_ERR(op->fallback_tfm);
 	}
 
+	err = pm_runtime_get_sync(op->ss->dev);
+	if (err < 0)
+		goto error_pm;
+
 	return 0;
+error_pm:
+	crypto_free_sync_skcipher(op->fallback_tfm);
+	return err;
 }
 
 void sun4i_ss_cipher_exit(struct crypto_tfm *tfm)
 {
 	struct sun4i_tfm_ctx *op = crypto_tfm_ctx(tfm);
+
 	crypto_free_sync_skcipher(op->fallback_tfm);
+	pm_runtime_put(op->ss->dev);
 }
 
 /* check and set the AES key, prepare the mode to be used */
@@ -524,7 +540,7 @@ int sun4i_ss_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
 		op->keymode = SS_AES_256BITS;
 		break;
 	default:
-		dev_err(ss->dev, "ERROR: Invalid keylen %u\n", keylen);
+		dev_dbg(ss->dev, "ERROR: Invalid keylen %u\n", keylen);
 		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-core.c b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-core.c
index 9aa6fe081a27..814cd12149a9 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-core.c
+++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-core.c
@@ -44,7 +44,8 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 				.cra_module = THIS_MODULE,
-				.cra_init = sun4i_hash_crainit
+				.cra_init = sun4i_hash_crainit,
+				.cra_exit = sun4i_hash_craexit,
 			}
 		}
 	}
@@ -70,7 +71,8 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 				.cra_blocksize = SHA1_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 				.cra_module = THIS_MODULE,
-				.cra_init = sun4i_hash_crainit
+				.cra_init = sun4i_hash_crainit,
+				.cra_exit = sun4i_hash_craexit,
 			}
 		}
 	}
@@ -223,6 +225,82 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 #endif
 };
 
+/*
+ * Power management strategy: The device is suspended unless a TFM exists for
+ * one of the algorithms proposed by this driver.
+ */
+static int sun4i_ss_pm_suspend(struct device *dev)
+{
+	struct sun4i_ss_ctx *ss = dev_get_drvdata(dev);
+
+	if (ss->reset)
+		reset_control_assert(ss->reset);
+
+	clk_disable_unprepare(ss->ssclk);
+	clk_disable_unprepare(ss->busclk);
+	return 0;
+}
+
+static int sun4i_ss_pm_resume(struct device *dev)
+{
+	struct sun4i_ss_ctx *ss = dev_get_drvdata(dev);
+
+	int err;
+
+	err = clk_prepare_enable(ss->busclk);
+	if (err) {
+		dev_err(ss->dev, "Cannot prepare_enable busclk\n");
+		goto err_enable;
+	}
+
+	err = clk_prepare_enable(ss->ssclk);
+	if (err) {
+		dev_err(ss->dev, "Cannot prepare_enable ssclk\n");
+		goto err_enable;
+	}
+
+	if (ss->reset) {
+		err = reset_control_deassert(ss->reset);
+		if (err) {
+			dev_err(ss->dev, "Cannot deassert reset control\n");
+			goto err_enable;
+		}
+	}
+
+	return err;
+err_enable:
+	sun4i_ss_pm_suspend(dev);
+	return err;
+}
+
+const struct dev_pm_ops sun4i_ss_pm_ops = {
+	SET_RUNTIME_PM_OPS(sun4i_ss_pm_suspend, sun4i_ss_pm_resume, NULL)
+};
+
+/*
+ * When power management is enabled, this function enables the PM and set the
+ * device as suspended
+ * When power management is disabled, this function just enables the device
+ */
+static int sun4i_ss_pm_init(struct sun4i_ss_ctx *ss)
+{
+	int err;
+
+	pm_runtime_use_autosuspend(ss->dev);
+	pm_runtime_set_autosuspend_delay(ss->dev, 2000);
+
+	err = pm_runtime_set_suspended(ss->dev);
+	if (err)
+		return err;
+	pm_runtime_enable(ss->dev);
+	return err;
+}
+
+static void sun4i_ss_pm_exit(struct sun4i_ss_ctx *ss)
+{
+	pm_runtime_disable(ss->dev);
+}
+
 static int sun4i_ss_probe(struct platform_device *pdev)
 {
 	u32 v;
@@ -269,18 +347,6 @@ static int sun4i_ss_probe(struct platform_device *pdev)
 		ss->reset = NULL;
 	}
 
-	/* Enable both clocks */
-	err = clk_prepare_enable(ss->busclk);
-	if (err) {
-		dev_err(&pdev->dev, "Cannot prepare_enable busclk\n");
-		return err;
-	}
-	err = clk_prepare_enable(ss->ssclk);
-	if (err) {
-		dev_err(&pdev->dev, "Cannot prepare_enable ssclk\n");
-		goto error_ssclk;
-	}
-
 	/*
 	 * Check that clock have the correct rates given in the datasheet
 	 * Try to set the clock to the maximum allowed
@@ -288,16 +354,7 @@ static int sun4i_ss_probe(struct platform_device *pdev)
 	err = clk_set_rate(ss->ssclk, cr_mod);
 	if (err) {
 		dev_err(&pdev->dev, "Cannot set clock rate to ssclk\n");
-		goto error_clk;
-	}
-
-	/* Deassert reset if we have a reset control */
-	if (ss->reset) {
-		err = reset_control_deassert(ss->reset);
-		if (err) {
-			dev_err(&pdev->dev, "Cannot deassert reset control\n");
-			goto error_clk;
-		}
+		return err;
 	}
 
 	/*
@@ -325,12 +382,26 @@ static int sun4i_ss_probe(struct platform_device *pdev)
 		dev_warn(&pdev->dev, "Clock ss is at %lu (%lu MHz) (must be <= %lu)\n",
 			 cr, cr / 1000000, cr_mod);
 
+	ss->dev = &pdev->dev;
+	platform_set_drvdata(pdev, ss);
+
+	spin_lock_init(&ss->slock);
+
+	err = sun4i_ss_pm_init(ss);
+	if (err)
+		return err;
+
 	/*
 	 * Datasheet named it "Die Bonding ID"
 	 * I expect to be a sort of Security System Revision number.
 	 * Since the A80 seems to have an other version of SS
 	 * this info could be useful
 	 */
+
+	err = pm_runtime_get_sync(ss->dev);
+	if (err < 0)
+		goto error_pm;
+
 	writel(SS_ENABLED, ss->base + SS_CTL);
 	v = readl(ss->base + SS_CTL);
 	v >>= 16;
@@ -338,9 +409,7 @@ static int sun4i_ss_probe(struct platform_device *pdev)
 	dev_info(&pdev->dev, "Die ID %d\n", v);
 	writel(0, ss->base + SS_CTL);
 
-	ss->dev = &pdev->dev;
-
-	spin_lock_init(&ss->slock);
+	pm_runtime_put_sync(ss->dev);
 
 	for (i = 0; i < ARRAY_SIZE(ss_algs); i++) {
 		ss_algs[i].ss = ss;
@@ -370,7 +439,6 @@ static int sun4i_ss_probe(struct platform_device *pdev)
 			break;
 		}
 	}
-	platform_set_drvdata(pdev, ss);
 	return 0;
 error_alg:
 	i--;
@@ -387,12 +455,8 @@ error_alg:
 			break;
 		}
 	}
-	if (ss->reset)
-		reset_control_assert(ss->reset);
-error_clk:
-	clk_disable_unprepare(ss->ssclk);
-error_ssclk:
-	clk_disable_unprepare(ss->busclk);
+error_pm:
+	sun4i_ss_pm_exit(ss);
 	return err;
 }
 
@@ -415,11 +479,7 @@ static int sun4i_ss_remove(struct platform_device *pdev)
 		}
 	}
 
-	writel(0, ss->base + SS_CTL);
-	if (ss->reset)
-		reset_control_assert(ss->reset);
-	clk_disable_unprepare(ss->busclk);
-	clk_disable_unprepare(ss->ssclk);
+	sun4i_ss_pm_exit(ss);
 	return 0;
 }
 
@@ -434,6 +494,7 @@ static struct platform_driver sun4i_ss_driver = {
 	.remove         = sun4i_ss_remove,
 	.driver         = {
 		.name           = "sun4i-ss",
+		.pm		= &sun4i_ss_pm_ops,
 		.of_match_table	= a20ss_crypto_of_match_table,
 	},
 };
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-hash.c b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-hash.c
index fcffba5ef927..fdc0e6cdbb85 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-hash.c
+++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-hash.c
@@ -19,17 +19,29 @@ int sun4i_hash_crainit(struct crypto_tfm *tfm)
 	struct sun4i_tfm_ctx *op = crypto_tfm_ctx(tfm);
 	struct ahash_alg *alg = __crypto_ahash_alg(tfm->__crt_alg);
 	struct sun4i_ss_alg_template *algt;
+	int err;
 
 	memset(op, 0, sizeof(struct sun4i_tfm_ctx));
 
 	algt = container_of(alg, struct sun4i_ss_alg_template, alg.hash);
 	op->ss = algt->ss;
 
+	err = pm_runtime_get_sync(op->ss->dev);
+	if (err < 0)
+		return err;
+
 	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
 				 sizeof(struct sun4i_req_ctx));
 	return 0;
 }
 
+void sun4i_hash_craexit(struct crypto_tfm *tfm)
+{
+	struct sun4i_tfm_ctx *op = crypto_tfm_ctx(tfm);
+
+	pm_runtime_put(op->ss->dev);
+}
+
 /* sun4i_hash_init: initialize request context */
 int sun4i_hash_init(struct ahash_request *areq)
 {
@@ -175,7 +187,7 @@ static int sun4i_hash(struct ahash_request *areq)
 	 */
 	unsigned int i = 0, end, fill, min_fill, nwait, nbw = 0, j = 0, todo;
 	unsigned int in_i = 0;
-	u32 spaces, rx_cnt = SS_RX_DEFAULT, bf[32] = {0}, wb = 0, v, ivmode = 0;
+	u32 spaces, rx_cnt = SS_RX_DEFAULT, bf[32] = {0}, v, ivmode = 0;
 	struct sun4i_req_ctx *op = ahash_request_ctx(areq);
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
 	struct sun4i_tfm_ctx *tfmctx = crypto_ahash_ctx(tfm);
@@ -184,6 +196,7 @@ static int sun4i_hash(struct ahash_request *areq)
 	struct sg_mapping_iter mi;
 	int in_r, err = 0;
 	size_t copied = 0;
+	__le32 wb = 0;
 
 	dev_dbg(ss->dev, "%s %s bc=%llu len=%u mode=%x wl=%u h0=%0x",
 		__func__, crypto_tfm_alg_name(areq->base.tfm),
@@ -215,7 +228,7 @@ static int sun4i_hash(struct ahash_request *areq)
 	 */
 	if (op->byte_count) {
 		ivmode = SS_IV_ARBITRARY;
-		for (i = 0; i < 5; i++)
+		for (i = 0; i < crypto_ahash_digestsize(tfm) / 4; i++)
 			writel(op->hash[i], ss->base + SS_IV0 + i * 4);
 	}
 	/* Enable the device */
@@ -272,8 +285,8 @@ static int sun4i_hash(struct ahash_request *areq)
 			 */
 			while (op->len < 64 && i < end) {
 				/* how many bytes we can read from current SG */
-				in_r = min3(mi.length - in_i, end - i,
-					    64 - op->len);
+				in_r = min(end - i, 64 - op->len);
+				in_r = min_t(size_t, mi.length - in_i, in_r);
 				memcpy(op->buf + op->len, mi.addr + in_i, in_r);
 				op->len += in_r;
 				i += in_r;
@@ -293,8 +306,8 @@ static int sun4i_hash(struct ahash_request *areq)
 		}
 		if (mi.length - in_i > 3 && i < end) {
 			/* how many bytes we can read from current SG */
-			in_r = min3(mi.length - in_i, areq->nbytes - i,
-				    ((mi.length - in_i) / 4) * 4);
+			in_r = min_t(size_t, mi.length - in_i, areq->nbytes - i);
+			in_r = min_t(size_t, ((mi.length - in_i) / 4) * 4, in_r);
 			/* how many bytes we can write in the device*/
 			todo = min3((u32)(end - i) / 4, rx_cnt, (u32)in_r / 4);
 			writesl(ss->base + SS_RXFIFO, mi.addr + in_i, todo);
@@ -320,8 +333,8 @@ static int sun4i_hash(struct ahash_request *areq)
 	if ((areq->nbytes - i) < 64) {
 		while (i < areq->nbytes && in_i < mi.length && op->len < 64) {
 			/* how many bytes we can read from current SG */
-			in_r = min3(mi.length - in_i, areq->nbytes - i,
-				    64 - op->len);
+			in_r = min(areq->nbytes - i, 64 - op->len);
+			in_r = min_t(size_t, mi.length - in_i, in_r);
 			memcpy(op->buf + op->len, mi.addr + in_i, in_r);
 			op->len += in_r;
 			i += in_r;
@@ -395,7 +408,7 @@ hash_final:
 
 		nbw = op->len - 4 * nwait;
 		if (nbw) {
-			wb = *(u32 *)(op->buf + nwait * 4);
+			wb = cpu_to_le32(*(u32 *)(op->buf + nwait * 4));
 			wb &= GENMASK((nbw * 8) - 1, 0);
 
 			op->byte_count += nbw;
@@ -404,7 +417,7 @@ hash_final:
 
 	/* write the remaining bytes of the nbw buffer */
 	wb |= ((1 << 7) << (nbw * 8));
-	bf[j++] = wb;
+	bf[j++] = le32_to_cpu(wb);
 
 	/*
 	 * number of space to pad to obtain 64o minus 8(size) minus 4 (final 1)
@@ -423,13 +436,13 @@ hash_final:
 
 	/* write the length of data */
 	if (op->mode == SS_OP_SHA1) {
-		__be64 bits = cpu_to_be64(op->byte_count << 3);
-		bf[j++] = lower_32_bits(bits);
-		bf[j++] = upper_32_bits(bits);
+		__be64 *bits = (__be64 *)&bf[j];
+		*bits = cpu_to_be64(op->byte_count << 3);
+		j += 2;
 	} else {
-		__le64 bits = op->byte_count << 3;
-		bf[j++] = lower_32_bits(bits);
-		bf[j++] = upper_32_bits(bits);
+		__le64 *bits = (__le64 *)&bf[j];
+		*bits = cpu_to_le64(op->byte_count << 3);
+		j += 2;
 	}
 	writesl(ss->base + SS_RXFIFO, bf, j);
 
@@ -471,7 +484,7 @@ hash_final:
 		}
 	} else {
 		for (i = 0; i < 4; i++) {
-			v = readl(ss->base + SS_MD0 + i * 4);
+			v = cpu_to_le32(readl(ss->base + SS_MD0 + i * 4));
 			memcpy(areq->result + i * 4, &v, 4);
 		}
 	}
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-prng.c b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-prng.c
index 63d636424161..729aafdbea84 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-prng.c
+++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-prng.c
@@ -17,7 +17,7 @@ int sun4i_ss_prng_generate(struct crypto_rng *tfm, const u8 *src,
 {
 	struct sun4i_ss_alg_template *algt;
 	struct rng_alg *alg = crypto_rng_alg(tfm);
-	int i;
+	int i, err;
 	u32 v;
 	u32 *data = (u32 *)dst;
 	const u32 mode = SS_OP_PRNG | SS_PRNG_CONTINUE | SS_ENABLED;
@@ -28,6 +28,10 @@ int sun4i_ss_prng_generate(struct crypto_rng *tfm, const u8 *src,
 	algt = container_of(alg, struct sun4i_ss_alg_template, alg.rng);
 	ss = algt->ss;
 
+	err = pm_runtime_get_sync(ss->dev);
+	if (err < 0)
+		return err;
+
 	spin_lock_bh(&ss->slock);
 
 	writel(mode, ss->base + SS_CTL);
@@ -52,5 +56,8 @@ int sun4i_ss_prng_generate(struct crypto_rng *tfm, const u8 *src,
 
 	writel(0, ss->base + SS_CTL);
 	spin_unlock_bh(&ss->slock);
+
+	pm_runtime_put(ss->dev);
+
 	return 0;
 }
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss.h b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss.h
index 35a27a7145f8..60425ac75d90 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss.h
+++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss.h
@@ -22,6 +22,7 @@
 #include <linux/scatterlist.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
+#include <linux/pm_runtime.h>
 #include <crypto/md5.h>
 #include <crypto/skcipher.h>
 #include <crypto/sha.h>
@@ -177,6 +178,7 @@ struct sun4i_req_ctx {
 };
 
 int sun4i_hash_crainit(struct crypto_tfm *tfm);
+void sun4i_hash_craexit(struct crypto_tfm *tfm);
 int sun4i_hash_init(struct ahash_request *areq);
 int sun4i_hash_update(struct ahash_request *areq);
 int sun4i_hash_final(struct ahash_request *areq);
diff --git a/drivers/crypto/allwinner/sun8i-ce/Makefile b/drivers/crypto/allwinner/sun8i-ce/Makefile
new file mode 100644
index 000000000000..08b68c3c1ca9
--- /dev/null
+++ b/drivers/crypto/allwinner/sun8i-ce/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_CRYPTO_DEV_SUN8I_CE) += sun8i-ce.o
+sun8i-ce-y += sun8i-ce-core.o sun8i-ce-cipher.o
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
new file mode 100644
index 000000000000..37d0b6c386a0
--- /dev/null
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
@@ -0,0 +1,438 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * sun8i-ce-cipher.c - hardware cryptographic offloader for
+ * Allwinner H3/A64/H5/H2+/H6/R40 SoC
+ *
+ * Copyright (C) 2016-2019 Corentin LABBE <clabbe.montjoie@gmail.com>
+ *
+ * This file add support for AES cipher with 128,192,256 bits keysize in
+ * CBC and ECB mode.
+ *
+ * You could find a link for the datasheet in Documentation/arm/sunxi/README
+ */
+
+#include <linux/crypto.h>
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/pm_runtime.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/internal/des.h>
+#include <crypto/internal/skcipher.h>
+#include "sun8i-ce.h"
+
+static int sun8i_ce_cipher_need_fallback(struct skcipher_request *areq)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
+	struct scatterlist *sg;
+
+	if (sg_nents(areq->src) > MAX_SG || sg_nents(areq->dst) > MAX_SG)
+		return true;
+
+	if (areq->cryptlen < crypto_skcipher_ivsize(tfm))
+		return true;
+
+	if (areq->cryptlen == 0 || areq->cryptlen % 16)
+		return true;
+
+	sg = areq->src;
+	while (sg) {
+		if (sg->length % 4 || !IS_ALIGNED(sg->offset, sizeof(u32)))
+			return true;
+		sg = sg_next(sg);
+	}
+	sg = areq->dst;
+	while (sg) {
+		if (sg->length % 4 || !IS_ALIGNED(sg->offset, sizeof(u32)))
+			return true;
+		sg = sg_next(sg);
+	}
+	return false;
+}
+
+static int sun8i_ce_cipher_fallback(struct skcipher_request *areq)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
+	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(areq);
+	int err;
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_CE_DEBUG
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	struct sun8i_ce_alg_template *algt;
+#endif
+	SYNC_SKCIPHER_REQUEST_ON_STACK(subreq, op->fallback_tfm);
+
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_CE_DEBUG
+	algt = container_of(alg, struct sun8i_ce_alg_template, alg.skcipher);
+	algt->stat_fb++;
+#endif
+
+	skcipher_request_set_sync_tfm(subreq, op->fallback_tfm);
+	skcipher_request_set_callback(subreq, areq->base.flags, NULL, NULL);
+	skcipher_request_set_crypt(subreq, areq->src, areq->dst,
+				   areq->cryptlen, areq->iv);
+	if (rctx->op_dir & CE_DECRYPTION)
+		err = crypto_skcipher_decrypt(subreq);
+	else
+		err = crypto_skcipher_encrypt(subreq);
+	skcipher_request_zero(subreq);
+	return err;
+}
+
+static int sun8i_ce_cipher(struct skcipher_request *areq)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
+	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct sun8i_ce_dev *ce = op->ce;
+	struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(areq);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	struct sun8i_ce_alg_template *algt;
+	struct sun8i_ce_flow *chan;
+	struct ce_task *cet;
+	struct scatterlist *sg;
+	unsigned int todo, len, offset, ivsize;
+	dma_addr_t addr_iv = 0, addr_key = 0;
+	void *backup_iv = NULL;
+	u32 common, sym;
+	int flow, i;
+	int nr_sgs = 0;
+	int nr_sgd = 0;
+	int err = 0;
+
+	algt = container_of(alg, struct sun8i_ce_alg_template, alg.skcipher);
+
+	dev_dbg(ce->dev, "%s %s %u %x IV(%p %u) key=%u\n", __func__,
+		crypto_tfm_alg_name(areq->base.tfm),
+		areq->cryptlen,
+		rctx->op_dir, areq->iv, crypto_skcipher_ivsize(tfm),
+		op->keylen);
+
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_CE_DEBUG
+	algt->stat_req++;
+#endif
+
+	flow = rctx->flow;
+
+	chan = &ce->chanlist[flow];
+
+	cet = chan->tl;
+	memset(cet, 0, sizeof(struct ce_task));
+
+	cet->t_id = cpu_to_le32(flow);
+	common = ce->variant->alg_cipher[algt->ce_algo_id];
+	common |= rctx->op_dir | CE_COMM_INT;
+	cet->t_common_ctl = cpu_to_le32(common);
+	/* CTS and recent CE (H6) need length in bytes, in word otherwise */
+	if (ce->variant->has_t_dlen_in_bytes)
+		cet->t_dlen = cpu_to_le32(areq->cryptlen);
+	else
+		cet->t_dlen = cpu_to_le32(areq->cryptlen / 4);
+
+	sym = ce->variant->op_mode[algt->ce_blockmode];
+	len = op->keylen;
+	switch (len) {
+	case 128 / 8:
+		sym |= CE_AES_128BITS;
+		break;
+	case 192 / 8:
+		sym |= CE_AES_192BITS;
+		break;
+	case 256 / 8:
+		sym |= CE_AES_256BITS;
+		break;
+	}
+
+	cet->t_sym_ctl = cpu_to_le32(sym);
+	cet->t_asym_ctl = 0;
+
+	chan->op_mode = ce->variant->op_mode[algt->ce_blockmode];
+	chan->op_dir = rctx->op_dir;
+	chan->method = ce->variant->alg_cipher[algt->ce_algo_id];
+	chan->keylen = op->keylen;
+
+	addr_key = dma_map_single(ce->dev, op->key, op->keylen, DMA_TO_DEVICE);
+	cet->t_key = cpu_to_le32(addr_key);
+	if (dma_mapping_error(ce->dev, addr_key)) {
+		dev_err(ce->dev, "Cannot DMA MAP KEY\n");
+		err = -EFAULT;
+		goto theend;
+	}
+
+	ivsize = crypto_skcipher_ivsize(tfm);
+	if (areq->iv && crypto_skcipher_ivsize(tfm) > 0) {
+		chan->ivlen = ivsize;
+		chan->bounce_iv = kzalloc(ivsize, GFP_KERNEL | GFP_DMA);
+		if (!chan->bounce_iv) {
+			err = -ENOMEM;
+			goto theend_key;
+		}
+		if (rctx->op_dir & CE_DECRYPTION) {
+			backup_iv = kzalloc(ivsize, GFP_KERNEL);
+			if (!backup_iv) {
+				err = -ENOMEM;
+				goto theend_key;
+			}
+			offset = areq->cryptlen - ivsize;
+			scatterwalk_map_and_copy(backup_iv, areq->src, offset,
+						 ivsize, 0);
+		}
+		memcpy(chan->bounce_iv, areq->iv, ivsize);
+		addr_iv = dma_map_single(ce->dev, chan->bounce_iv, chan->ivlen,
+					 DMA_TO_DEVICE);
+		cet->t_iv = cpu_to_le32(addr_iv);
+		if (dma_mapping_error(ce->dev, addr_iv)) {
+			dev_err(ce->dev, "Cannot DMA MAP IV\n");
+			err = -ENOMEM;
+			goto theend_iv;
+		}
+	}
+
+	if (areq->src == areq->dst) {
+		nr_sgs = dma_map_sg(ce->dev, areq->src, sg_nents(areq->src),
+				    DMA_BIDIRECTIONAL);
+		if (nr_sgs <= 0 || nr_sgs > MAX_SG) {
+			dev_err(ce->dev, "Invalid sg number %d\n", nr_sgs);
+			err = -EINVAL;
+			goto theend_iv;
+		}
+		nr_sgd = nr_sgs;
+	} else {
+		nr_sgs = dma_map_sg(ce->dev, areq->src, sg_nents(areq->src),
+				    DMA_TO_DEVICE);
+		if (nr_sgs <= 0 || nr_sgs > MAX_SG) {
+			dev_err(ce->dev, "Invalid sg number %d\n", nr_sgs);
+			err = -EINVAL;
+			goto theend_iv;
+		}
+		nr_sgd = dma_map_sg(ce->dev, areq->dst, sg_nents(areq->dst),
+				    DMA_FROM_DEVICE);
+		if (nr_sgd <= 0 || nr_sgd > MAX_SG) {
+			dev_err(ce->dev, "Invalid sg number %d\n", nr_sgd);
+			err = -EINVAL;
+			goto theend_sgs;
+		}
+	}
+
+	len = areq->cryptlen;
+	for_each_sg(areq->src, sg, nr_sgs, i) {
+		cet->t_src[i].addr = cpu_to_le32(sg_dma_address(sg));
+		todo = min(len, sg_dma_len(sg));
+		cet->t_src[i].len = cpu_to_le32(todo / 4);
+		dev_dbg(ce->dev, "%s total=%u SG(%d %u off=%d) todo=%u\n", __func__,
+			areq->cryptlen, i, cet->t_src[i].len, sg->offset, todo);
+		len -= todo;
+	}
+	if (len > 0) {
+		dev_err(ce->dev, "remaining len %d\n", len);
+		err = -EINVAL;
+		goto theend_sgs;
+	}
+
+	len = areq->cryptlen;
+	for_each_sg(areq->dst, sg, nr_sgd, i) {
+		cet->t_dst[i].addr = cpu_to_le32(sg_dma_address(sg));
+		todo = min(len, sg_dma_len(sg));
+		cet->t_dst[i].len = cpu_to_le32(todo / 4);
+		dev_dbg(ce->dev, "%s total=%u SG(%d %u off=%d) todo=%u\n", __func__,
+			areq->cryptlen, i, cet->t_dst[i].len, sg->offset, todo);
+		len -= todo;
+	}
+	if (len > 0) {
+		dev_err(ce->dev, "remaining len %d\n", len);
+		err = -EINVAL;
+		goto theend_sgs;
+	}
+
+	chan->timeout = areq->cryptlen;
+	err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(areq->base.tfm));
+
+theend_sgs:
+	if (areq->src == areq->dst) {
+		dma_unmap_sg(ce->dev, areq->src, nr_sgs, DMA_BIDIRECTIONAL);
+	} else {
+		if (nr_sgs > 0)
+			dma_unmap_sg(ce->dev, areq->src, nr_sgs, DMA_TO_DEVICE);
+		dma_unmap_sg(ce->dev, areq->dst, nr_sgd, DMA_FROM_DEVICE);
+	}
+
+theend_iv:
+	if (areq->iv && ivsize > 0) {
+		if (addr_iv)
+			dma_unmap_single(ce->dev, addr_iv, chan->ivlen,
+					 DMA_TO_DEVICE);
+		offset = areq->cryptlen - ivsize;
+		if (rctx->op_dir & CE_DECRYPTION) {
+			memcpy(areq->iv, backup_iv, ivsize);
+			kzfree(backup_iv);
+		} else {
+			scatterwalk_map_and_copy(areq->iv, areq->dst, offset,
+						 ivsize, 0);
+		}
+		kfree(chan->bounce_iv);
+	}
+
+theend_key:
+	dma_unmap_single(ce->dev, addr_key, op->keylen, DMA_TO_DEVICE);
+
+theend:
+	return err;
+}
+
+static int sun8i_ce_handle_cipher_request(struct crypto_engine *engine, void *areq)
+{
+	int err;
+	struct skcipher_request *breq = container_of(areq, struct skcipher_request, base);
+
+	err = sun8i_ce_cipher(breq);
+	crypto_finalize_skcipher_request(engine, breq, err);
+
+	return 0;
+}
+
+int sun8i_ce_skdecrypt(struct skcipher_request *areq)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
+	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(areq);
+	struct crypto_engine *engine;
+	int e;
+
+	rctx->op_dir = CE_DECRYPTION;
+	if (sun8i_ce_cipher_need_fallback(areq))
+		return sun8i_ce_cipher_fallback(areq);
+
+	e = sun8i_ce_get_engine_number(op->ce);
+	rctx->flow = e;
+	engine = op->ce->chanlist[e].engine;
+
+	return crypto_transfer_skcipher_request_to_engine(engine, areq);
+}
+
+int sun8i_ce_skencrypt(struct skcipher_request *areq)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
+	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(areq);
+	struct crypto_engine *engine;
+	int e;
+
+	rctx->op_dir = CE_ENCRYPTION;
+	if (sun8i_ce_cipher_need_fallback(areq))
+		return sun8i_ce_cipher_fallback(areq);
+
+	e = sun8i_ce_get_engine_number(op->ce);
+	rctx->flow = e;
+	engine = op->ce->chanlist[e].engine;
+
+	return crypto_transfer_skcipher_request_to_engine(engine, areq);
+}
+
+int sun8i_ce_cipher_init(struct crypto_tfm *tfm)
+{
+	struct sun8i_cipher_tfm_ctx *op = crypto_tfm_ctx(tfm);
+	struct sun8i_ce_alg_template *algt;
+	const char *name = crypto_tfm_alg_name(tfm);
+	struct crypto_skcipher *sktfm = __crypto_skcipher_cast(tfm);
+	struct skcipher_alg *alg = crypto_skcipher_alg(sktfm);
+	int err;
+
+	memset(op, 0, sizeof(struct sun8i_cipher_tfm_ctx));
+
+	algt = container_of(alg, struct sun8i_ce_alg_template, alg.skcipher);
+	op->ce = algt->ce;
+
+	sktfm->reqsize = sizeof(struct sun8i_cipher_req_ctx);
+
+	op->fallback_tfm = crypto_alloc_sync_skcipher(name, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(op->fallback_tfm)) {
+		dev_err(op->ce->dev, "ERROR: Cannot allocate fallback for %s %ld\n",
+			name, PTR_ERR(op->fallback_tfm));
+		return PTR_ERR(op->fallback_tfm);
+	}
+
+	dev_info(op->ce->dev, "Fallback for %s is %s\n",
+		 crypto_tfm_alg_driver_name(&sktfm->base),
+		 crypto_tfm_alg_driver_name(crypto_skcipher_tfm(&op->fallback_tfm->base)));
+
+	op->enginectx.op.do_one_request = sun8i_ce_handle_cipher_request;
+	op->enginectx.op.prepare_request = NULL;
+	op->enginectx.op.unprepare_request = NULL;
+
+	err = pm_runtime_get_sync(op->ce->dev);
+	if (err < 0)
+		goto error_pm;
+
+	return 0;
+error_pm:
+	crypto_free_sync_skcipher(op->fallback_tfm);
+	return err;
+}
+
+void sun8i_ce_cipher_exit(struct crypto_tfm *tfm)
+{
+	struct sun8i_cipher_tfm_ctx *op = crypto_tfm_ctx(tfm);
+
+	if (op->key) {
+		memzero_explicit(op->key, op->keylen);
+		kfree(op->key);
+	}
+	crypto_free_sync_skcipher(op->fallback_tfm);
+	pm_runtime_put_sync_suspend(op->ce->dev);
+}
+
+int sun8i_ce_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			unsigned int keylen)
+{
+	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct sun8i_ce_dev *ce = op->ce;
+
+	switch (keylen) {
+	case 128 / 8:
+		break;
+	case 192 / 8:
+		break;
+	case 256 / 8:
+		break;
+	default:
+		dev_dbg(ce->dev, "ERROR: Invalid keylen %u\n", keylen);
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	if (op->key) {
+		memzero_explicit(op->key, op->keylen);
+		kfree(op->key);
+	}
+	op->keylen = keylen;
+	op->key = kmemdup(key, keylen, GFP_KERNEL | GFP_DMA);
+	if (!op->key)
+		return -ENOMEM;
+
+	crypto_sync_skcipher_clear_flags(op->fallback_tfm, CRYPTO_TFM_REQ_MASK);
+	crypto_sync_skcipher_set_flags(op->fallback_tfm, tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK);
+
+	return crypto_sync_skcipher_setkey(op->fallback_tfm, key, keylen);
+}
+
+int sun8i_ce_des3_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			 unsigned int keylen)
+{
+	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	int err;
+
+	err = verify_skcipher_des3_key(tfm, key);
+	if (err)
+		return err;
+
+	if (op->key) {
+		memzero_explicit(op->key, op->keylen);
+		kfree(op->key);
+	}
+	op->keylen = keylen;
+	op->key = kmemdup(key, keylen, GFP_KERNEL | GFP_DMA);
+	if (!op->key)
+		return -ENOMEM;
+
+	crypto_sync_skcipher_clear_flags(op->fallback_tfm, CRYPTO_TFM_REQ_MASK);
+	crypto_sync_skcipher_set_flags(op->fallback_tfm, tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK);
+
+	return crypto_sync_skcipher_setkey(op->fallback_tfm, key, keylen);
+}
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c
new file mode 100644
index 000000000000..73a7649f915d
--- /dev/null
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c
@@ -0,0 +1,676 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * sun8i-ce-core.c - hardware cryptographic offloader for
+ * Allwinner H3/A64/H5/H2+/H6/R40 SoC
+ *
+ * Copyright (C) 2015-2019 Corentin Labbe <clabbe.montjoie@gmail.com>
+ *
+ * Core file which registers crypto algorithms supported by the CryptoEngine.
+ *
+ * You could find a link for the datasheet in Documentation/arm/sunxi/README
+ */
+#include <linux/clk.h>
+#include <linux/crypto.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+#include <crypto/internal/skcipher.h>
+
+#include "sun8i-ce.h"
+
+/*
+ * mod clock is lower on H3 than other SoC due to some DMA timeout occurring
+ * with high value.
+ * If you want to tune mod clock, loading driver and passing selftest is
+ * insufficient, you need to test with some LUKS test (mount and write to it)
+ */
+static const struct ce_variant ce_h3_variant = {
+	.alg_cipher = { CE_ALG_AES, CE_ALG_DES, CE_ALG_3DES,
+	},
+	.op_mode = { CE_OP_ECB, CE_OP_CBC
+	},
+	.ce_clks = {
+		{ "bus", 0, 200000000 },
+		{ "mod", 50000000, 0 },
+		}
+};
+
+static const struct ce_variant ce_h5_variant = {
+	.alg_cipher = { CE_ALG_AES, CE_ALG_DES, CE_ALG_3DES,
+	},
+	.op_mode = { CE_OP_ECB, CE_OP_CBC
+	},
+	.ce_clks = {
+		{ "bus", 0, 200000000 },
+		{ "mod", 300000000, 0 },
+		}
+};
+
+static const struct ce_variant ce_h6_variant = {
+	.alg_cipher = { CE_ALG_AES, CE_ALG_DES, CE_ALG_3DES,
+	},
+	.op_mode = { CE_OP_ECB, CE_OP_CBC
+	},
+	.has_t_dlen_in_bytes = true,
+	.ce_clks = {
+		{ "bus", 0, 200000000 },
+		{ "mod", 300000000, 0 },
+		{ "ram", 0, 400000000 },
+		}
+};
+
+static const struct ce_variant ce_a64_variant = {
+	.alg_cipher = { CE_ALG_AES, CE_ALG_DES, CE_ALG_3DES,
+	},
+	.op_mode = { CE_OP_ECB, CE_OP_CBC
+	},
+	.ce_clks = {
+		{ "bus", 0, 200000000 },
+		{ "mod", 300000000, 0 },
+		}
+};
+
+static const struct ce_variant ce_r40_variant = {
+	.alg_cipher = { CE_ALG_AES, CE_ALG_DES, CE_ALG_3DES,
+	},
+	.op_mode = { CE_OP_ECB, CE_OP_CBC
+	},
+	.ce_clks = {
+		{ "bus", 0, 200000000 },
+		{ "mod", 300000000, 0 },
+		}
+};
+
+/*
+ * sun8i_ce_get_engine_number() get the next channel slot
+ * This is a simple round-robin way of getting the next channel
+ */
+int sun8i_ce_get_engine_number(struct sun8i_ce_dev *ce)
+{
+	return atomic_inc_return(&ce->flow) % MAXFLOW;
+}
+
+int sun8i_ce_run_task(struct sun8i_ce_dev *ce, int flow, const char *name)
+{
+	u32 v;
+	int err = 0;
+
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_CE_DEBUG
+	ce->chanlist[flow].stat_req++;
+#endif
+
+	mutex_lock(&ce->mlock);
+
+	v = readl(ce->base + CE_ICR);
+	v |= 1 << flow;
+	writel(v, ce->base + CE_ICR);
+
+	reinit_completion(&ce->chanlist[flow].complete);
+	writel(ce->chanlist[flow].t_phy, ce->base + CE_TDQ);
+
+	ce->chanlist[flow].status = 0;
+	/* Be sure all data is written before enabling the task */
+	wmb();
+
+	v = 1 | (ce->chanlist[flow].tl->t_common_ctl & 0x7F) << 8;
+	writel(v, ce->base + CE_TLR);
+	mutex_unlock(&ce->mlock);
+
+	wait_for_completion_interruptible_timeout(&ce->chanlist[flow].complete,
+			msecs_to_jiffies(ce->chanlist[flow].timeout));
+
+	if (ce->chanlist[flow].status == 0) {
+		dev_err(ce->dev, "DMA timeout for %s\n", name);
+		err = -EFAULT;
+	}
+	/* No need to lock for this read, the channel is locked so
+	 * nothing could modify the error value for this channel
+	 */
+	v = readl(ce->base + CE_ESR);
+	if (v) {
+		v >>= (flow * 4);
+		v &= 0xFF;
+		if (v) {
+			dev_err(ce->dev, "CE ERROR: %x for flow %x\n", v, flow);
+			err = -EFAULT;
+		}
+		if (v & CE_ERR_ALGO_NOTSUP)
+			dev_err(ce->dev, "CE ERROR: algorithm not supported\n");
+		if (v & CE_ERR_DATALEN)
+			dev_err(ce->dev, "CE ERROR: data length error\n");
+		if (v & CE_ERR_KEYSRAM)
+			dev_err(ce->dev, "CE ERROR: keysram access error for AES\n");
+		if (v & CE_ERR_ADDR_INVALID)
+			dev_err(ce->dev, "CE ERROR: address invalid\n");
+		}
+
+	return err;
+}
+
+static irqreturn_t ce_irq_handler(int irq, void *data)
+{
+	struct sun8i_ce_dev *ce = (struct sun8i_ce_dev *)data;
+	int flow = 0;
+	u32 p;
+
+	p = readl(ce->base + CE_ISR);
+	for (flow = 0; flow < MAXFLOW; flow++) {
+		if (p & (BIT(flow))) {
+			writel(BIT(flow), ce->base + CE_ISR);
+			ce->chanlist[flow].status = 1;
+			complete(&ce->chanlist[flow].complete);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static struct sun8i_ce_alg_template ce_algs[] = {
+{
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.ce_algo_id = CE_ID_CIPHER_AES,
+	.ce_blockmode = CE_ID_OP_CBC,
+	.alg.skcipher = {
+		.base = {
+			.cra_name = "cbc(aes)",
+			.cra_driver_name = "cbc-aes-sun8i-ce",
+			.cra_priority = 400,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+			.cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 0xf,
+			.cra_init = sun8i_ce_cipher_init,
+			.cra_exit = sun8i_ce_cipher_exit,
+		},
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= sun8i_ce_aes_setkey,
+		.encrypt	= sun8i_ce_skencrypt,
+		.decrypt	= sun8i_ce_skdecrypt,
+	}
+},
+{
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.ce_algo_id = CE_ID_CIPHER_AES,
+	.ce_blockmode = CE_ID_OP_ECB,
+	.alg.skcipher = {
+		.base = {
+			.cra_name = "ecb(aes)",
+			.cra_driver_name = "ecb-aes-sun8i-ce",
+			.cra_priority = 400,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+			.cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 0xf,
+			.cra_init = sun8i_ce_cipher_init,
+			.cra_exit = sun8i_ce_cipher_exit,
+		},
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.setkey		= sun8i_ce_aes_setkey,
+		.encrypt	= sun8i_ce_skencrypt,
+		.decrypt	= sun8i_ce_skdecrypt,
+	}
+},
+{
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.ce_algo_id = CE_ID_CIPHER_DES3,
+	.ce_blockmode = CE_ID_OP_CBC,
+	.alg.skcipher = {
+		.base = {
+			.cra_name = "cbc(des3_ede)",
+			.cra_driver_name = "cbc-des3-sun8i-ce",
+			.cra_priority = 400,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+			.cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 0xf,
+			.cra_init = sun8i_ce_cipher_init,
+			.cra_exit = sun8i_ce_cipher_exit,
+		},
+		.min_keysize	= DES3_EDE_KEY_SIZE,
+		.max_keysize	= DES3_EDE_KEY_SIZE,
+		.ivsize		= DES3_EDE_BLOCK_SIZE,
+		.setkey		= sun8i_ce_des3_setkey,
+		.encrypt	= sun8i_ce_skencrypt,
+		.decrypt	= sun8i_ce_skdecrypt,
+	}
+},
+{
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.ce_algo_id = CE_ID_CIPHER_DES3,
+	.ce_blockmode = CE_ID_OP_ECB,
+	.alg.skcipher = {
+		.base = {
+			.cra_name = "ecb(des3_ede)",
+			.cra_driver_name = "ecb-des3-sun8i-ce",
+			.cra_priority = 400,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+			.cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 0xf,
+			.cra_init = sun8i_ce_cipher_init,
+			.cra_exit = sun8i_ce_cipher_exit,
+		},
+		.min_keysize	= DES3_EDE_KEY_SIZE,
+		.max_keysize	= DES3_EDE_KEY_SIZE,
+		.setkey		= sun8i_ce_des3_setkey,
+		.encrypt	= sun8i_ce_skencrypt,
+		.decrypt	= sun8i_ce_skdecrypt,
+	}
+},
+};
+
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_CE_DEBUG
+static int sun8i_ce_dbgfs_read(struct seq_file *seq, void *v)
+{
+	struct sun8i_ce_dev *ce = seq->private;
+	int i;
+
+	for (i = 0; i < MAXFLOW; i++)
+		seq_printf(seq, "Channel %d: nreq %lu\n", i, ce->chanlist[i].stat_req);
+
+	for (i = 0; i < ARRAY_SIZE(ce_algs); i++) {
+		if (!ce_algs[i].ce)
+			continue;
+		switch (ce_algs[i].type) {
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			seq_printf(seq, "%s %s %lu %lu\n",
+				   ce_algs[i].alg.skcipher.base.cra_driver_name,
+				   ce_algs[i].alg.skcipher.base.cra_name,
+				   ce_algs[i].stat_req, ce_algs[i].stat_fb);
+			break;
+		}
+	}
+	return 0;
+}
+
+static int sun8i_ce_dbgfs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, sun8i_ce_dbgfs_read, inode->i_private);
+}
+
+static const struct file_operations sun8i_ce_debugfs_fops = {
+	.owner = THIS_MODULE,
+	.open = sun8i_ce_dbgfs_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+#endif
+
+static void sun8i_ce_free_chanlist(struct sun8i_ce_dev *ce, int i)
+{
+	while (i >= 0) {
+		crypto_engine_exit(ce->chanlist[i].engine);
+		if (ce->chanlist[i].tl)
+			dma_free_coherent(ce->dev, sizeof(struct ce_task),
+					  ce->chanlist[i].tl,
+					  ce->chanlist[i].t_phy);
+		i--;
+	}
+}
+
+/*
+ * Allocate the channel list structure
+ */
+static int sun8i_ce_allocate_chanlist(struct sun8i_ce_dev *ce)
+{
+	int i, err;
+
+	ce->chanlist = devm_kcalloc(ce->dev, MAXFLOW,
+				    sizeof(struct sun8i_ce_flow), GFP_KERNEL);
+	if (!ce->chanlist)
+		return -ENOMEM;
+
+	for (i = 0; i < MAXFLOW; i++) {
+		init_completion(&ce->chanlist[i].complete);
+
+		ce->chanlist[i].engine = crypto_engine_alloc_init(ce->dev, true);
+		if (!ce->chanlist[i].engine) {
+			dev_err(ce->dev, "Cannot allocate engine\n");
+			i--;
+			err = -ENOMEM;
+			goto error_engine;
+		}
+		err = crypto_engine_start(ce->chanlist[i].engine);
+		if (err) {
+			dev_err(ce->dev, "Cannot start engine\n");
+			goto error_engine;
+		}
+		ce->chanlist[i].tl = dma_alloc_coherent(ce->dev,
+							sizeof(struct ce_task),
+							&ce->chanlist[i].t_phy,
+							GFP_KERNEL);
+		if (!ce->chanlist[i].tl) {
+			dev_err(ce->dev, "Cannot get DMA memory for task %d\n",
+				i);
+			err = -ENOMEM;
+			goto error_engine;
+		}
+	}
+	return 0;
+error_engine:
+	sun8i_ce_free_chanlist(ce, i);
+	return err;
+}
+
+/*
+ * Power management strategy: The device is suspended unless a TFM exists for
+ * one of the algorithms proposed by this driver.
+ */
+static int sun8i_ce_pm_suspend(struct device *dev)
+{
+	struct sun8i_ce_dev *ce = dev_get_drvdata(dev);
+	int i;
+
+	reset_control_assert(ce->reset);
+	for (i = 0; i < CE_MAX_CLOCKS; i++)
+		clk_disable_unprepare(ce->ceclks[i]);
+	return 0;
+}
+
+static int sun8i_ce_pm_resume(struct device *dev)
+{
+	struct sun8i_ce_dev *ce = dev_get_drvdata(dev);
+	int err, i;
+
+	for (i = 0; i < CE_MAX_CLOCKS; i++) {
+		if (!ce->variant->ce_clks[i].name)
+			continue;
+		err = clk_prepare_enable(ce->ceclks[i]);
+		if (err) {
+			dev_err(ce->dev, "Cannot prepare_enable %s\n",
+				ce->variant->ce_clks[i].name);
+			goto error;
+		}
+	}
+	err = reset_control_deassert(ce->reset);
+	if (err) {
+		dev_err(ce->dev, "Cannot deassert reset control\n");
+		goto error;
+	}
+	return 0;
+error:
+	sun8i_ce_pm_suspend(dev);
+	return err;
+}
+
+static const struct dev_pm_ops sun8i_ce_pm_ops = {
+	SET_RUNTIME_PM_OPS(sun8i_ce_pm_suspend, sun8i_ce_pm_resume, NULL)
+};
+
+static int sun8i_ce_pm_init(struct sun8i_ce_dev *ce)
+{
+	int err;
+
+	pm_runtime_use_autosuspend(ce->dev);
+	pm_runtime_set_autosuspend_delay(ce->dev, 2000);
+
+	err = pm_runtime_set_suspended(ce->dev);
+	if (err)
+		return err;
+	pm_runtime_enable(ce->dev);
+	return err;
+}
+
+static void sun8i_ce_pm_exit(struct sun8i_ce_dev *ce)
+{
+	pm_runtime_disable(ce->dev);
+}
+
+static int sun8i_ce_get_clks(struct sun8i_ce_dev *ce)
+{
+	unsigned long cr;
+	int err, i;
+
+	for (i = 0; i < CE_MAX_CLOCKS; i++) {
+		if (!ce->variant->ce_clks[i].name)
+			continue;
+		ce->ceclks[i] = devm_clk_get(ce->dev, ce->variant->ce_clks[i].name);
+		if (IS_ERR(ce->ceclks[i])) {
+			err = PTR_ERR(ce->ceclks[i]);
+			dev_err(ce->dev, "Cannot get %s CE clock err=%d\n",
+				ce->variant->ce_clks[i].name, err);
+			return err;
+		}
+		cr = clk_get_rate(ce->ceclks[i]);
+		if (!cr)
+			return -EINVAL;
+		if (ce->variant->ce_clks[i].freq > 0 &&
+		    cr != ce->variant->ce_clks[i].freq) {
+			dev_info(ce->dev, "Set %s clock to %lu (%lu Mhz) from %lu (%lu Mhz)\n",
+				 ce->variant->ce_clks[i].name,
+				 ce->variant->ce_clks[i].freq,
+				 ce->variant->ce_clks[i].freq / 1000000,
+				 cr, cr / 1000000);
+			err = clk_set_rate(ce->ceclks[i], ce->variant->ce_clks[i].freq);
+			if (err)
+				dev_err(ce->dev, "Fail to set %s clk speed to %lu hz\n",
+					ce->variant->ce_clks[i].name,
+					ce->variant->ce_clks[i].freq);
+		}
+		if (ce->variant->ce_clks[i].max_freq > 0 &&
+		    cr > ce->variant->ce_clks[i].max_freq)
+			dev_warn(ce->dev, "Frequency for %s (%lu hz) is higher than datasheet's recommendation (%lu hz)",
+				 ce->variant->ce_clks[i].name, cr,
+				 ce->variant->ce_clks[i].max_freq);
+	}
+	return 0;
+}
+
+static int sun8i_ce_register_algs(struct sun8i_ce_dev *ce)
+{
+	int ce_method, err, id, i;
+
+	for (i = 0; i < ARRAY_SIZE(ce_algs); i++) {
+		ce_algs[i].ce = ce;
+		switch (ce_algs[i].type) {
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			id = ce_algs[i].ce_algo_id;
+			ce_method = ce->variant->alg_cipher[id];
+			if (ce_method == CE_ID_NOTSUPP) {
+				dev_dbg(ce->dev,
+					"DEBUG: Algo of %s not supported\n",
+					ce_algs[i].alg.skcipher.base.cra_name);
+				ce_algs[i].ce = NULL;
+				break;
+			}
+			id = ce_algs[i].ce_blockmode;
+			ce_method = ce->variant->op_mode[id];
+			if (ce_method == CE_ID_NOTSUPP) {
+				dev_dbg(ce->dev, "DEBUG: Blockmode of %s not supported\n",
+					ce_algs[i].alg.skcipher.base.cra_name);
+				ce_algs[i].ce = NULL;
+				break;
+			}
+			dev_info(ce->dev, "Register %s\n",
+				 ce_algs[i].alg.skcipher.base.cra_name);
+			err = crypto_register_skcipher(&ce_algs[i].alg.skcipher);
+			if (err) {
+				dev_err(ce->dev, "ERROR: Fail to register %s\n",
+					ce_algs[i].alg.skcipher.base.cra_name);
+				ce_algs[i].ce = NULL;
+				return err;
+			}
+			break;
+		default:
+			ce_algs[i].ce = NULL;
+			dev_err(ce->dev, "ERROR: tried to register an unknown algo\n");
+		}
+	}
+	return 0;
+}
+
+static void sun8i_ce_unregister_algs(struct sun8i_ce_dev *ce)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ce_algs); i++) {
+		if (!ce_algs[i].ce)
+			continue;
+		switch (ce_algs[i].type) {
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			dev_info(ce->dev, "Unregister %d %s\n", i,
+				 ce_algs[i].alg.skcipher.base.cra_name);
+			crypto_unregister_skcipher(&ce_algs[i].alg.skcipher);
+			break;
+		}
+	}
+}
+
+static int sun8i_ce_probe(struct platform_device *pdev)
+{
+	struct sun8i_ce_dev *ce;
+	int err, irq;
+	u32 v;
+
+	ce = devm_kzalloc(&pdev->dev, sizeof(*ce), GFP_KERNEL);
+	if (!ce)
+		return -ENOMEM;
+
+	ce->dev = &pdev->dev;
+	platform_set_drvdata(pdev, ce);
+
+	ce->variant = of_device_get_match_data(&pdev->dev);
+	if (!ce->variant) {
+		dev_err(&pdev->dev, "Missing Crypto Engine variant\n");
+		return -EINVAL;
+	}
+
+	ce->base = devm_platform_ioremap_resource(pdev, 0);;
+	if (IS_ERR(ce->base))
+		return PTR_ERR(ce->base);
+
+	err = sun8i_ce_get_clks(ce);
+	if (err)
+		return err;
+
+	/* Get Non Secure IRQ */
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(ce->dev, "Cannot get CryptoEngine Non-secure IRQ\n");
+		return irq;
+	}
+
+	ce->reset = devm_reset_control_get(&pdev->dev, NULL);
+	if (IS_ERR(ce->reset)) {
+		if (PTR_ERR(ce->reset) == -EPROBE_DEFER)
+			return PTR_ERR(ce->reset);
+		dev_err(&pdev->dev, "No reset control found\n");
+		return PTR_ERR(ce->reset);
+	}
+
+	mutex_init(&ce->mlock);
+
+	err = sun8i_ce_allocate_chanlist(ce);
+	if (err)
+		return err;
+
+	err = sun8i_ce_pm_init(ce);
+	if (err)
+		goto error_pm;
+
+	err = devm_request_irq(&pdev->dev, irq, ce_irq_handler, 0,
+			       "sun8i-ce-ns", ce);
+	if (err) {
+		dev_err(ce->dev, "Cannot request CryptoEngine Non-secure IRQ (err=%d)\n", err);
+		goto error_irq;
+	}
+
+	err = sun8i_ce_register_algs(ce);
+	if (err)
+		goto error_alg;
+
+	err = pm_runtime_get_sync(ce->dev);
+	if (err < 0)
+		goto error_alg;
+
+	v = readl(ce->base + CE_CTR);
+	v >>= CE_DIE_ID_SHIFT;
+	v &= CE_DIE_ID_MASK;
+	dev_info(&pdev->dev, "CryptoEngine Die ID %x\n", v);
+
+	pm_runtime_put_sync(ce->dev);
+
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_CE_DEBUG
+	/* Ignore error of debugfs */
+	ce->dbgfs_dir = debugfs_create_dir("sun8i-ce", NULL);
+	ce->dbgfs_stats = debugfs_create_file("stats", 0444,
+					      ce->dbgfs_dir, ce,
+					      &sun8i_ce_debugfs_fops);
+#endif
+
+	return 0;
+error_alg:
+	sun8i_ce_unregister_algs(ce);
+error_irq:
+	sun8i_ce_pm_exit(ce);
+error_pm:
+	sun8i_ce_free_chanlist(ce, MAXFLOW);
+	return err;
+}
+
+static int sun8i_ce_remove(struct platform_device *pdev)
+{
+	struct sun8i_ce_dev *ce = platform_get_drvdata(pdev);
+
+	sun8i_ce_unregister_algs(ce);
+
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_CE_DEBUG
+	debugfs_remove_recursive(ce->dbgfs_dir);
+#endif
+
+	sun8i_ce_free_chanlist(ce, MAXFLOW);
+
+	sun8i_ce_pm_exit(ce);
+	return 0;
+}
+
+static const struct of_device_id sun8i_ce_crypto_of_match_table[] = {
+	{ .compatible = "allwinner,sun8i-h3-crypto",
+	  .data = &ce_h3_variant },
+	{ .compatible = "allwinner,sun8i-r40-crypto",
+	  .data = &ce_r40_variant },
+	{ .compatible = "allwinner,sun50i-a64-crypto",
+	  .data = &ce_a64_variant },
+	{ .compatible = "allwinner,sun50i-h5-crypto",
+	  .data = &ce_h5_variant },
+	{ .compatible = "allwinner,sun50i-h6-crypto",
+	  .data = &ce_h6_variant },
+	{}
+};
+MODULE_DEVICE_TABLE(of, sun8i_ce_crypto_of_match_table);
+
+static struct platform_driver sun8i_ce_driver = {
+	.probe		 = sun8i_ce_probe,
+	.remove		 = sun8i_ce_remove,
+	.driver		 = {
+		.name		= "sun8i-ce",
+		.pm		= &sun8i_ce_pm_ops,
+		.of_match_table	= sun8i_ce_crypto_of_match_table,
+	},
+};
+
+module_platform_driver(sun8i_ce_driver);
+
+MODULE_DESCRIPTION("Allwinner Crypto Engine cryptographic offloader");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Corentin Labbe <clabbe.montjoie@gmail.com>");
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h
new file mode 100644
index 000000000000..43db49ceafe4
--- /dev/null
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h
@@ -0,0 +1,254 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * sun8i-ce.h - hardware cryptographic offloader for
+ * Allwinner H3/A64/H5/H2+/H6 SoC
+ *
+ * Copyright (C) 2016-2019 Corentin LABBE <clabbe.montjoie@gmail.com>
+ */
+#include <crypto/aes.h>
+#include <crypto/des.h>
+#include <crypto/engine.h>
+#include <crypto/skcipher.h>
+#include <linux/atomic.h>
+#include <linux/debugfs.h>
+#include <linux/crypto.h>
+
+/* CE Registers */
+#define CE_TDQ	0x00
+#define CE_CTR	0x04
+#define CE_ICR	0x08
+#define CE_ISR	0x0C
+#define CE_TLR	0x10
+#define CE_TSR	0x14
+#define CE_ESR	0x18
+#define CE_CSSGR	0x1C
+#define CE_CDSGR	0x20
+#define CE_CSAR	0x24
+#define CE_CDAR	0x28
+#define CE_TPR	0x2C
+
+/* Used in struct ce_task */
+/* ce_task common */
+#define CE_ENCRYPTION		0
+#define CE_DECRYPTION		BIT(8)
+
+#define CE_COMM_INT		BIT(31)
+
+/* ce_task symmetric */
+#define CE_AES_128BITS 0
+#define CE_AES_192BITS 1
+#define CE_AES_256BITS 2
+
+#define CE_OP_ECB	0
+#define CE_OP_CBC	(1 << 8)
+
+#define CE_ALG_AES		0
+#define CE_ALG_DES		1
+#define CE_ALG_3DES		2
+
+/* Used in ce_variant */
+#define CE_ID_NOTSUPP		0xFF
+
+#define CE_ID_CIPHER_AES	0
+#define CE_ID_CIPHER_DES	1
+#define CE_ID_CIPHER_DES3	2
+#define CE_ID_CIPHER_MAX	3
+
+#define CE_ID_OP_ECB	0
+#define CE_ID_OP_CBC	1
+#define CE_ID_OP_MAX	2
+
+/* Used in CE registers */
+#define CE_ERR_ALGO_NOTSUP	BIT(0)
+#define CE_ERR_DATALEN		BIT(1)
+#define CE_ERR_KEYSRAM		BIT(2)
+#define CE_ERR_ADDR_INVALID	BIT(5)
+#define CE_ERR_KEYLADDER	BIT(6)
+
+#define CE_DIE_ID_SHIFT	16
+#define CE_DIE_ID_MASK	0x07
+
+#define MAX_SG 8
+
+#define CE_MAX_CLOCKS 3
+
+#define MAXFLOW 4
+
+/*
+ * struct ce_clock - Describe clocks used by sun8i-ce
+ * @name:	Name of clock needed by this variant
+ * @freq:	Frequency to set for each clock
+ * @max_freq:	Maximum frequency for each clock (generally given by datasheet)
+ */
+struct ce_clock {
+	const char *name;
+	unsigned long freq;
+	unsigned long max_freq;
+};
+
+/*
+ * struct ce_variant - Describe CE capability for each variant hardware
+ * @alg_cipher:	list of supported ciphers. for each CE_ID_ this will give the
+ *              coresponding CE_ALG_XXX value
+ * @op_mode:	list of supported block modes
+ * @has_t_dlen_in_bytes:	Does the request size for cipher is in
+ *				bytes or words
+ * @ce_clks:	list of clocks needed by this variant
+ */
+struct ce_variant {
+	char alg_cipher[CE_ID_CIPHER_MAX];
+	u32 op_mode[CE_ID_OP_MAX];
+	bool has_t_dlen_in_bytes;
+	struct ce_clock ce_clks[CE_MAX_CLOCKS];
+};
+
+struct sginfo {
+	__le32 addr;
+	__le32 len;
+} __packed;
+
+/*
+ * struct ce_task - CE Task descriptor
+ * The structure of this descriptor could be found in the datasheet
+ */
+struct ce_task {
+	__le32 t_id;
+	__le32 t_common_ctl;
+	__le32 t_sym_ctl;
+	__le32 t_asym_ctl;
+	__le32 t_key;
+	__le32 t_iv;
+	__le32 t_ctr;
+	__le32 t_dlen;
+	struct sginfo t_src[MAX_SG];
+	struct sginfo t_dst[MAX_SG];
+	__le32 next;
+	__le32 reserved[3];
+} __packed __aligned(8);
+
+/*
+ * struct sun8i_ce_flow - Information used by each flow
+ * @engine:	ptr to the crypto_engine for this flow
+ * @bounce_iv:	buffer which contain the IV
+ * @ivlen:	size of bounce_iv
+ * @keylen:	keylen for this flow operation
+ * @complete:	completion for the current task on this flow
+ * @status:	set to 1 by interrupt if task is done
+ * @method:	current method for flow
+ * @op_dir:	direction (encrypt vs decrypt) of this flow
+ * @op_mode:	op_mode for this flow
+ * @t_phy:	Physical address of task
+ * @tl:		pointer to the current ce_task for this flow
+ * @stat_req:	number of request done by this flow
+ */
+struct sun8i_ce_flow {
+	struct crypto_engine *engine;
+	void *bounce_iv;
+	unsigned int ivlen;
+	unsigned int keylen;
+	struct completion complete;
+	int status;
+	u32 method;
+	u32 op_dir;
+	u32 op_mode;
+	dma_addr_t t_phy;
+	int timeout;
+	struct ce_task *tl;
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_CE_DEBUG
+	unsigned long stat_req;
+#endif
+};
+
+/*
+ * struct sun8i_ce_dev - main container for all this driver information
+ * @base:	base address of CE
+ * @ceclks:	clocks used by CE
+ * @reset:	pointer to reset controller
+ * @dev:	the platform device
+ * @mlock:	Control access to device registers
+ * @chanlist:	array of all flow
+ * @flow:	flow to use in next request
+ * @variant:	pointer to variant specific data
+ * @dbgfs_dir:	Debugfs dentry for statistic directory
+ * @dbgfs_stats: Debugfs dentry for statistic counters
+ */
+struct sun8i_ce_dev {
+	void __iomem *base;
+	struct clk *ceclks[CE_MAX_CLOCKS];
+	struct reset_control *reset;
+	struct device *dev;
+	struct mutex mlock;
+	struct sun8i_ce_flow *chanlist;
+	atomic_t flow;
+	const struct ce_variant *variant;
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_CE_DEBUG
+	struct dentry *dbgfs_dir;
+	struct dentry *dbgfs_stats;
+#endif
+};
+
+/*
+ * struct sun8i_cipher_req_ctx - context for a skcipher request
+ * @op_dir:	direction (encrypt vs decrypt) for this request
+ * @flow:	the flow to use for this request
+ */
+struct sun8i_cipher_req_ctx {
+	u32 op_dir;
+	int flow;
+};
+
+/*
+ * struct sun8i_cipher_tfm_ctx - context for a skcipher TFM
+ * @enginectx:		crypto_engine used by this TFM
+ * @key:		pointer to key data
+ * @keylen:		len of the key
+ * @ce:			pointer to the private data of driver handling this TFM
+ * @fallback_tfm:	pointer to the fallback TFM
+ */
+struct sun8i_cipher_tfm_ctx {
+	struct crypto_engine_ctx enginectx;
+	u32 *key;
+	u32 keylen;
+	struct sun8i_ce_dev *ce;
+	struct crypto_sync_skcipher *fallback_tfm;
+};
+
+/*
+ * struct sun8i_ce_alg_template - crypto_alg template
+ * @type:		the CRYPTO_ALG_TYPE for this template
+ * @ce_algo_id:		the CE_ID for this template
+ * @ce_blockmode:	the type of block operation CE_ID
+ * @ce:			pointer to the sun8i_ce_dev structure associated with
+ *			this template
+ * @alg:		one of sub struct must be used
+ * @stat_req:		number of request done on this template
+ * @stat_fb:		total of all data len done on this template
+ */
+struct sun8i_ce_alg_template {
+	u32 type;
+	u32 ce_algo_id;
+	u32 ce_blockmode;
+	struct sun8i_ce_dev *ce;
+	union {
+		struct skcipher_alg skcipher;
+	} alg;
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_CE_DEBUG
+	unsigned long stat_req;
+	unsigned long stat_fb;
+#endif
+};
+
+int sun8i_ce_enqueue(struct crypto_async_request *areq, u32 type);
+
+int sun8i_ce_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			unsigned int keylen);
+int sun8i_ce_des3_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			 unsigned int keylen);
+int sun8i_ce_cipher_init(struct crypto_tfm *tfm);
+void sun8i_ce_cipher_exit(struct crypto_tfm *tfm);
+int sun8i_ce_skdecrypt(struct skcipher_request *areq);
+int sun8i_ce_skencrypt(struct skcipher_request *areq);
+
+int sun8i_ce_get_engine_number(struct sun8i_ce_dev *ce);
+
+int sun8i_ce_run_task(struct sun8i_ce_dev *ce, int flow, const char *name);
diff --git a/drivers/crypto/allwinner/sun8i-ss/Makefile b/drivers/crypto/allwinner/sun8i-ss/Makefile
new file mode 100644
index 000000000000..add7b0543fd5
--- /dev/null
+++ b/drivers/crypto/allwinner/sun8i-ss/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_CRYPTO_DEV_SUN8I_SS) += sun8i-ss.o
+sun8i-ss-y += sun8i-ss-core.o sun8i-ss-cipher.o
diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
new file mode 100644
index 000000000000..f222979a5623
--- /dev/null
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
@@ -0,0 +1,436 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * sun8i-ss-cipher.c - hardware cryptographic offloader for
+ * Allwinner A80/A83T SoC
+ *
+ * Copyright (C) 2016-2019 Corentin LABBE <clabbe.montjoie@gmail.com>
+ *
+ * This file add support for AES cipher with 128,192,256 bits keysize in
+ * CBC and ECB mode.
+ *
+ * You could find a link for the datasheet in Documentation/arm/sunxi/README
+ */
+
+#include <linux/crypto.h>
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/pm_runtime.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/internal/skcipher.h>
+#include "sun8i-ss.h"
+
+static bool sun8i_ss_need_fallback(struct skcipher_request *areq)
+{
+	struct scatterlist *in_sg = areq->src;
+	struct scatterlist *out_sg = areq->dst;
+	struct scatterlist *sg;
+
+	if (areq->cryptlen == 0 || areq->cryptlen % 16)
+		return true;
+
+	if (sg_nents(areq->src) > 8 || sg_nents(areq->dst) > 8)
+		return true;
+
+	sg = areq->src;
+	while (sg) {
+		if ((sg->length % 16) != 0)
+			return true;
+		if ((sg_dma_len(sg) % 16) != 0)
+			return true;
+		if (!IS_ALIGNED(sg->offset, 16))
+			return true;
+		sg = sg_next(sg);
+	}
+	sg = areq->dst;
+	while (sg) {
+		if ((sg->length % 16) != 0)
+			return true;
+		if ((sg_dma_len(sg) % 16) != 0)
+			return true;
+		if (!IS_ALIGNED(sg->offset, 16))
+			return true;
+		sg = sg_next(sg);
+	}
+
+	/* SS need same numbers of SG (with same length) for source and destination */
+	in_sg = areq->src;
+	out_sg = areq->dst;
+	while (in_sg && out_sg) {
+		if (in_sg->length != out_sg->length)
+			return true;
+		in_sg = sg_next(in_sg);
+		out_sg = sg_next(out_sg);
+	}
+	if (in_sg || out_sg)
+		return true;
+	return false;
+}
+
+static int sun8i_ss_cipher_fallback(struct skcipher_request *areq)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
+	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(areq);
+	int err;
+
+	SYNC_SKCIPHER_REQUEST_ON_STACK(subreq, op->fallback_tfm);
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	struct sun8i_ss_alg_template *algt;
+
+	algt = container_of(alg, struct sun8i_ss_alg_template, alg.skcipher);
+	algt->stat_fb++;
+#endif
+	skcipher_request_set_sync_tfm(subreq, op->fallback_tfm);
+	skcipher_request_set_callback(subreq, areq->base.flags, NULL, NULL);
+	skcipher_request_set_crypt(subreq, areq->src, areq->dst,
+				   areq->cryptlen, areq->iv);
+	if (rctx->op_dir & SS_DECRYPTION)
+		err = crypto_skcipher_decrypt(subreq);
+	else
+		err = crypto_skcipher_encrypt(subreq);
+	skcipher_request_zero(subreq);
+	return err;
+}
+
+static int sun8i_ss_cipher(struct skcipher_request *areq)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
+	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct sun8i_ss_dev *ss = op->ss;
+	struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(areq);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	struct sun8i_ss_alg_template *algt;
+	struct scatterlist *sg;
+	unsigned int todo, len, offset, ivsize;
+	void *backup_iv = NULL;
+	int nr_sgs = 0;
+	int nr_sgd = 0;
+	int err = 0;
+	int i;
+
+	algt = container_of(alg, struct sun8i_ss_alg_template, alg.skcipher);
+
+	dev_dbg(ss->dev, "%s %s %u %x IV(%p %u) key=%u\n", __func__,
+		crypto_tfm_alg_name(areq->base.tfm),
+		areq->cryptlen,
+		rctx->op_dir, areq->iv, crypto_skcipher_ivsize(tfm),
+		op->keylen);
+
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG
+	algt->stat_req++;
+#endif
+
+	rctx->op_mode = ss->variant->op_mode[algt->ss_blockmode];
+	rctx->method = ss->variant->alg_cipher[algt->ss_algo_id];
+	rctx->keylen = op->keylen;
+
+	rctx->p_key = dma_map_single(ss->dev, op->key, op->keylen, DMA_TO_DEVICE);
+	if (dma_mapping_error(ss->dev, rctx->p_key)) {
+		dev_err(ss->dev, "Cannot DMA MAP KEY\n");
+		err = -EFAULT;
+		goto theend;
+	}
+
+	ivsize = crypto_skcipher_ivsize(tfm);
+	if (areq->iv && crypto_skcipher_ivsize(tfm) > 0) {
+		rctx->ivlen = ivsize;
+		rctx->biv = kzalloc(ivsize, GFP_KERNEL | GFP_DMA);
+		if (!rctx->biv) {
+			err = -ENOMEM;
+			goto theend_key;
+		}
+		if (rctx->op_dir & SS_DECRYPTION) {
+			backup_iv = kzalloc(ivsize, GFP_KERNEL);
+			if (!backup_iv) {
+				err = -ENOMEM;
+				goto theend_key;
+			}
+			offset = areq->cryptlen - ivsize;
+			scatterwalk_map_and_copy(backup_iv, areq->src, offset,
+						 ivsize, 0);
+		}
+		memcpy(rctx->biv, areq->iv, ivsize);
+		rctx->p_iv = dma_map_single(ss->dev, rctx->biv, rctx->ivlen,
+					    DMA_TO_DEVICE);
+		if (dma_mapping_error(ss->dev, rctx->p_iv)) {
+			dev_err(ss->dev, "Cannot DMA MAP IV\n");
+			err = -ENOMEM;
+			goto theend_iv;
+		}
+	}
+	if (areq->src == areq->dst) {
+		nr_sgs = dma_map_sg(ss->dev, areq->src, sg_nents(areq->src),
+				    DMA_BIDIRECTIONAL);
+		if (nr_sgs <= 0 || nr_sgs > 8) {
+			dev_err(ss->dev, "Invalid sg number %d\n", nr_sgs);
+			err = -EINVAL;
+			goto theend_iv;
+		}
+		nr_sgd = nr_sgs;
+	} else {
+		nr_sgs = dma_map_sg(ss->dev, areq->src, sg_nents(areq->src),
+				    DMA_TO_DEVICE);
+		if (nr_sgs <= 0 || nr_sgs > 8) {
+			dev_err(ss->dev, "Invalid sg number %d\n", nr_sgs);
+			err = -EINVAL;
+			goto theend_iv;
+		}
+		nr_sgd = dma_map_sg(ss->dev, areq->dst, sg_nents(areq->dst),
+				    DMA_FROM_DEVICE);
+		if (nr_sgd <= 0 || nr_sgd > 8) {
+			dev_err(ss->dev, "Invalid sg number %d\n", nr_sgd);
+			err = -EINVAL;
+			goto theend_sgs;
+		}
+	}
+
+	len = areq->cryptlen;
+	i = 0;
+	sg = areq->src;
+	while (i < nr_sgs && sg && len) {
+		if (sg_dma_len(sg) == 0)
+			goto sgs_next;
+		rctx->t_src[i].addr = sg_dma_address(sg);
+		todo = min(len, sg_dma_len(sg));
+		rctx->t_src[i].len = todo / 4;
+		dev_dbg(ss->dev, "%s total=%u SGS(%d %u off=%d) todo=%u\n", __func__,
+			areq->cryptlen, i, rctx->t_src[i].len, sg->offset, todo);
+		len -= todo;
+		i++;
+sgs_next:
+		sg = sg_next(sg);
+	}
+	if (len > 0) {
+		dev_err(ss->dev, "remaining len %d\n", len);
+		err = -EINVAL;
+		goto theend_sgs;
+	}
+
+	len = areq->cryptlen;
+	i = 0;
+	sg = areq->dst;
+	while (i < nr_sgd && sg && len) {
+		if (sg_dma_len(sg) == 0)
+			goto sgd_next;
+		rctx->t_dst[i].addr = sg_dma_address(sg);
+		todo = min(len, sg_dma_len(sg));
+		rctx->t_dst[i].len = todo / 4;
+		dev_dbg(ss->dev, "%s total=%u SGD(%d %u off=%d) todo=%u\n", __func__,
+			areq->cryptlen, i, rctx->t_dst[i].len, sg->offset, todo);
+		len -= todo;
+		i++;
+sgd_next:
+		sg = sg_next(sg);
+	}
+	if (len > 0) {
+		dev_err(ss->dev, "remaining len %d\n", len);
+		err = -EINVAL;
+		goto theend_sgs;
+	}
+
+	err = sun8i_ss_run_task(ss, rctx, crypto_tfm_alg_name(areq->base.tfm));
+
+theend_sgs:
+	if (areq->src == areq->dst) {
+		dma_unmap_sg(ss->dev, areq->src, nr_sgs, DMA_BIDIRECTIONAL);
+	} else {
+		dma_unmap_sg(ss->dev, areq->src, nr_sgs, DMA_TO_DEVICE);
+		dma_unmap_sg(ss->dev, areq->dst, nr_sgd, DMA_FROM_DEVICE);
+	}
+
+theend_iv:
+	if (rctx->p_iv)
+		dma_unmap_single(ss->dev, rctx->p_iv, rctx->ivlen,
+				 DMA_TO_DEVICE);
+
+	if (areq->iv && ivsize > 0) {
+		if (rctx->biv) {
+			offset = areq->cryptlen - ivsize;
+			if (rctx->op_dir & SS_DECRYPTION) {
+				memcpy(areq->iv, backup_iv, ivsize);
+				memzero_explicit(backup_iv, ivsize);
+				kzfree(backup_iv);
+			} else {
+				scatterwalk_map_and_copy(areq->iv, areq->dst, offset,
+							 ivsize, 0);
+			}
+			kfree(rctx->biv);
+		}
+	}
+
+theend_key:
+	dma_unmap_single(ss->dev, rctx->p_key, op->keylen, DMA_TO_DEVICE);
+
+theend:
+
+	return err;
+}
+
+static int sun8i_ss_handle_cipher_request(struct crypto_engine *engine, void *areq)
+{
+	int err;
+	struct skcipher_request *breq = container_of(areq, struct skcipher_request, base);
+
+	err = sun8i_ss_cipher(breq);
+	crypto_finalize_skcipher_request(engine, breq, err);
+
+	return 0;
+}
+
+int sun8i_ss_skdecrypt(struct skcipher_request *areq)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
+	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(areq);
+	struct crypto_engine *engine;
+	int e;
+
+	memset(rctx, 0, sizeof(struct sun8i_cipher_req_ctx));
+	rctx->op_dir = SS_DECRYPTION;
+
+	if (sun8i_ss_need_fallback(areq))
+		return sun8i_ss_cipher_fallback(areq);
+
+	e = sun8i_ss_get_engine_number(op->ss);
+	engine = op->ss->flows[e].engine;
+	rctx->flow = e;
+
+	return crypto_transfer_skcipher_request_to_engine(engine, areq);
+}
+
+int sun8i_ss_skencrypt(struct skcipher_request *areq)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
+	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(areq);
+	struct crypto_engine *engine;
+	int e;
+
+	memset(rctx, 0, sizeof(struct sun8i_cipher_req_ctx));
+	rctx->op_dir = SS_ENCRYPTION;
+
+	if (sun8i_ss_need_fallback(areq))
+		return sun8i_ss_cipher_fallback(areq);
+
+	e = sun8i_ss_get_engine_number(op->ss);
+	engine = op->ss->flows[e].engine;
+	rctx->flow = e;
+
+	return crypto_transfer_skcipher_request_to_engine(engine, areq);
+}
+
+int sun8i_ss_cipher_init(struct crypto_tfm *tfm)
+{
+	struct sun8i_cipher_tfm_ctx *op = crypto_tfm_ctx(tfm);
+	struct sun8i_ss_alg_template *algt;
+	const char *name = crypto_tfm_alg_name(tfm);
+	struct crypto_skcipher *sktfm = __crypto_skcipher_cast(tfm);
+	struct skcipher_alg *alg = crypto_skcipher_alg(sktfm);
+	int err;
+
+	memset(op, 0, sizeof(struct sun8i_cipher_tfm_ctx));
+
+	algt = container_of(alg, struct sun8i_ss_alg_template, alg.skcipher);
+	op->ss = algt->ss;
+
+	sktfm->reqsize = sizeof(struct sun8i_cipher_req_ctx);
+
+	op->fallback_tfm = crypto_alloc_sync_skcipher(name, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(op->fallback_tfm)) {
+		dev_err(op->ss->dev, "ERROR: Cannot allocate fallback for %s %ld\n",
+			name, PTR_ERR(op->fallback_tfm));
+		return PTR_ERR(op->fallback_tfm);
+	}
+
+	dev_info(op->ss->dev, "Fallback for %s is %s\n",
+		 crypto_tfm_alg_driver_name(&sktfm->base),
+		 crypto_tfm_alg_driver_name(crypto_skcipher_tfm(&op->fallback_tfm->base)));
+
+	op->enginectx.op.do_one_request = sun8i_ss_handle_cipher_request;
+	op->enginectx.op.prepare_request = NULL;
+	op->enginectx.op.unprepare_request = NULL;
+
+	err = pm_runtime_get_sync(op->ss->dev);
+	if (err < 0) {
+		dev_err(op->ss->dev, "pm error %d\n", err);
+		goto error_pm;
+	}
+
+	return 0;
+error_pm:
+	crypto_free_sync_skcipher(op->fallback_tfm);
+	return err;
+}
+
+void sun8i_ss_cipher_exit(struct crypto_tfm *tfm)
+{
+	struct sun8i_cipher_tfm_ctx *op = crypto_tfm_ctx(tfm);
+
+	if (op->key) {
+		memzero_explicit(op->key, op->keylen);
+		kfree(op->key);
+	}
+	crypto_free_sync_skcipher(op->fallback_tfm);
+	pm_runtime_put_sync(op->ss->dev);
+}
+
+int sun8i_ss_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			unsigned int keylen)
+{
+	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct sun8i_ss_dev *ss = op->ss;
+
+	switch (keylen) {
+	case 128 / 8:
+		break;
+	case 192 / 8:
+		break;
+	case 256 / 8:
+		break;
+	default:
+		dev_dbg(ss->dev, "ERROR: Invalid keylen %u\n", keylen);
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	if (op->key) {
+		memzero_explicit(op->key, op->keylen);
+		kfree(op->key);
+	}
+	op->keylen = keylen;
+	op->key = kmemdup(key, keylen, GFP_KERNEL | GFP_DMA);
+	if (!op->key)
+		return -ENOMEM;
+
+	crypto_sync_skcipher_clear_flags(op->fallback_tfm, CRYPTO_TFM_REQ_MASK);
+	crypto_sync_skcipher_set_flags(op->fallback_tfm, tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK);
+
+	return crypto_sync_skcipher_setkey(op->fallback_tfm, key, keylen);
+}
+
+int sun8i_ss_des3_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			 unsigned int keylen)
+{
+	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct sun8i_ss_dev *ss = op->ss;
+
+	if (unlikely(keylen != 3 * DES_KEY_SIZE)) {
+		dev_dbg(ss->dev, "Invalid keylen %u\n", keylen);
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	if (op->key) {
+		memzero_explicit(op->key, op->keylen);
+		kfree(op->key);
+	}
+	op->keylen = keylen;
+	op->key = kmemdup(key, keylen, GFP_KERNEL | GFP_DMA);
+	if (!op->key)
+		return -ENOMEM;
+
+	crypto_sync_skcipher_clear_flags(op->fallback_tfm, CRYPTO_TFM_REQ_MASK);
+	crypto_sync_skcipher_set_flags(op->fallback_tfm, tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK);
+
+	return crypto_sync_skcipher_setkey(op->fallback_tfm, key, keylen);
+}
diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c
new file mode 100644
index 000000000000..90997cc509b8
--- /dev/null
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c
@@ -0,0 +1,642 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * sun8i-ss-core.c - hardware cryptographic offloader for
+ * Allwinner A80/A83T SoC
+ *
+ * Copyright (C) 2015-2019 Corentin Labbe <clabbe.montjoie@gmail.com>
+ *
+ * Core file which registers crypto algorithms supported by the SecuritySystem
+ *
+ * You could find a link for the datasheet in Documentation/arm/sunxi/README
+ */
+#include <linux/clk.h>
+#include <linux/crypto.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+#include <crypto/internal/skcipher.h>
+
+#include "sun8i-ss.h"
+
+static const struct ss_variant ss_a80_variant = {
+	.alg_cipher = { SS_ALG_AES, SS_ALG_DES, SS_ALG_3DES,
+	},
+	.op_mode = { SS_OP_ECB, SS_OP_CBC,
+	},
+	.ss_clks = {
+		{ "bus", 0, 300 * 1000 * 1000 },
+		{ "mod", 0, 300 * 1000 * 1000 },
+	}
+};
+
+static const struct ss_variant ss_a83t_variant = {
+	.alg_cipher = { SS_ALG_AES, SS_ALG_DES, SS_ALG_3DES,
+	},
+	.op_mode = { SS_OP_ECB, SS_OP_CBC,
+	},
+	.ss_clks = {
+		{ "bus", 0, 300 * 1000 * 1000 },
+		{ "mod", 0, 300 * 1000 * 1000 },
+	}
+};
+
+/*
+ * sun8i_ss_get_engine_number() get the next channel slot
+ * This is a simple round-robin way of getting the next channel
+ */
+int sun8i_ss_get_engine_number(struct sun8i_ss_dev *ss)
+{
+	return atomic_inc_return(&ss->flow) % MAXFLOW;
+}
+
+int sun8i_ss_run_task(struct sun8i_ss_dev *ss, struct sun8i_cipher_req_ctx *rctx,
+		      const char *name)
+{
+	int flow = rctx->flow;
+	u32 v = 1;
+	int i;
+
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG
+	ss->flows[flow].stat_req++;
+#endif
+
+	/* choose between stream0/stream1 */
+	if (flow)
+		v |= SS_FLOW1;
+	else
+		v |= SS_FLOW0;
+
+	v |= rctx->op_mode;
+	v |= rctx->method;
+
+	if (rctx->op_dir)
+		v |= SS_DECRYPTION;
+
+	switch (rctx->keylen) {
+	case 128 / 8:
+		v |= SS_AES_128BITS << 7;
+		break;
+	case 192 / 8:
+		v |= SS_AES_192BITS << 7;
+		break;
+	case 256 / 8:
+		v |= SS_AES_256BITS << 7;
+		break;
+	}
+
+	for (i = 0; i < MAX_SG; i++) {
+		if (!rctx->t_dst[i].addr)
+			break;
+
+		mutex_lock(&ss->mlock);
+		writel(rctx->p_key, ss->base + SS_KEY_ADR_REG);
+
+		if (i == 0) {
+			if (rctx->p_iv)
+				writel(rctx->p_iv, ss->base + SS_IV_ADR_REG);
+		} else {
+			if (rctx->biv) {
+				if (rctx->op_dir == SS_ENCRYPTION)
+					writel(rctx->t_dst[i - 1].addr + rctx->t_dst[i - 1].len * 4 - rctx->ivlen, ss->base + SS_IV_ADR_REG);
+				else
+					writel(rctx->t_src[i - 1].addr + rctx->t_src[i - 1].len * 4 - rctx->ivlen, ss->base + SS_IV_ADR_REG);
+			}
+		}
+
+		dev_dbg(ss->dev,
+			"Processing SG %d on flow %d %s ctl=%x %d to %d method=%x opmode=%x opdir=%x srclen=%d\n",
+			i, flow, name, v,
+			rctx->t_src[i].len, rctx->t_dst[i].len,
+			rctx->method, rctx->op_mode,
+			rctx->op_dir, rctx->t_src[i].len);
+
+		writel(rctx->t_src[i].addr, ss->base + SS_SRC_ADR_REG);
+		writel(rctx->t_dst[i].addr, ss->base + SS_DST_ADR_REG);
+		writel(rctx->t_src[i].len, ss->base + SS_LEN_ADR_REG);
+
+		reinit_completion(&ss->flows[flow].complete);
+		ss->flows[flow].status = 0;
+		wmb();
+
+		writel(v, ss->base + SS_CTL_REG);
+		mutex_unlock(&ss->mlock);
+		wait_for_completion_interruptible_timeout(&ss->flows[flow].complete,
+							  msecs_to_jiffies(2000));
+		if (ss->flows[flow].status == 0) {
+			dev_err(ss->dev, "DMA timeout for %s\n", name);
+			return -EFAULT;
+		}
+	}
+
+	return 0;
+}
+
+static irqreturn_t ss_irq_handler(int irq, void *data)
+{
+	struct sun8i_ss_dev *ss = (struct sun8i_ss_dev *)data;
+	int flow = 0;
+	u32 p;
+
+	p = readl(ss->base + SS_INT_STA_REG);
+	for (flow = 0; flow < MAXFLOW; flow++) {
+		if (p & (BIT(flow))) {
+			writel(BIT(flow), ss->base + SS_INT_STA_REG);
+			ss->flows[flow].status = 1;
+			complete(&ss->flows[flow].complete);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static struct sun8i_ss_alg_template ss_algs[] = {
+{
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.ss_algo_id = SS_ID_CIPHER_AES,
+	.ss_blockmode = SS_ID_OP_CBC,
+	.alg.skcipher = {
+		.base = {
+			.cra_name = "cbc(aes)",
+			.cra_driver_name = "cbc-aes-sun8i-ss",
+			.cra_priority = 400,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+			.cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 0xf,
+			.cra_init = sun8i_ss_cipher_init,
+			.cra_exit = sun8i_ss_cipher_exit,
+		},
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= sun8i_ss_aes_setkey,
+		.encrypt	= sun8i_ss_skencrypt,
+		.decrypt	= sun8i_ss_skdecrypt,
+	}
+},
+{
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.ss_algo_id = SS_ID_CIPHER_AES,
+	.ss_blockmode = SS_ID_OP_ECB,
+	.alg.skcipher = {
+		.base = {
+			.cra_name = "ecb(aes)",
+			.cra_driver_name = "ecb-aes-sun8i-ss",
+			.cra_priority = 400,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+			.cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 0xf,
+			.cra_init = sun8i_ss_cipher_init,
+			.cra_exit = sun8i_ss_cipher_exit,
+		},
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.setkey		= sun8i_ss_aes_setkey,
+		.encrypt	= sun8i_ss_skencrypt,
+		.decrypt	= sun8i_ss_skdecrypt,
+	}
+},
+{
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.ss_algo_id = SS_ID_CIPHER_DES3,
+	.ss_blockmode = SS_ID_OP_CBC,
+	.alg.skcipher = {
+		.base = {
+			.cra_name = "cbc(des3_ede)",
+			.cra_driver_name = "cbc-des3-sun8i-ss",
+			.cra_priority = 400,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+			.cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 0xf,
+			.cra_init = sun8i_ss_cipher_init,
+			.cra_exit = sun8i_ss_cipher_exit,
+		},
+		.min_keysize	= DES3_EDE_KEY_SIZE,
+		.max_keysize	= DES3_EDE_KEY_SIZE,
+		.ivsize		= DES3_EDE_BLOCK_SIZE,
+		.setkey		= sun8i_ss_des3_setkey,
+		.encrypt	= sun8i_ss_skencrypt,
+		.decrypt	= sun8i_ss_skdecrypt,
+	}
+},
+{
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.ss_algo_id = SS_ID_CIPHER_DES3,
+	.ss_blockmode = SS_ID_OP_ECB,
+	.alg.skcipher = {
+		.base = {
+			.cra_name = "ecb(des3_ede)",
+			.cra_driver_name = "ecb-des3-sun8i-ss",
+			.cra_priority = 400,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+			.cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 0xf,
+			.cra_init = sun8i_ss_cipher_init,
+			.cra_exit = sun8i_ss_cipher_exit,
+		},
+		.min_keysize	= DES3_EDE_KEY_SIZE,
+		.max_keysize	= DES3_EDE_KEY_SIZE,
+		.setkey		= sun8i_ss_des3_setkey,
+		.encrypt	= sun8i_ss_skencrypt,
+		.decrypt	= sun8i_ss_skdecrypt,
+	}
+},
+};
+
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG
+static int sun8i_ss_dbgfs_read(struct seq_file *seq, void *v)
+{
+	struct sun8i_ss_dev *ss = seq->private;
+	int i;
+
+	for (i = 0; i < MAXFLOW; i++)
+		seq_printf(seq, "Channel %d: nreq %lu\n", i, ss->flows[i].stat_req);
+
+	for (i = 0; i < ARRAY_SIZE(ss_algs); i++) {
+		if (!ss_algs[i].ss)
+			continue;
+		switch (ss_algs[i].type) {
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			seq_printf(seq, "%s %s %lu %lu\n",
+				   ss_algs[i].alg.skcipher.base.cra_driver_name,
+				   ss_algs[i].alg.skcipher.base.cra_name,
+				   ss_algs[i].stat_req, ss_algs[i].stat_fb);
+			break;
+		}
+	}
+	return 0;
+}
+
+static int sun8i_ss_dbgfs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, sun8i_ss_dbgfs_read, inode->i_private);
+}
+
+static const struct file_operations sun8i_ss_debugfs_fops = {
+	.owner = THIS_MODULE,
+	.open = sun8i_ss_dbgfs_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+#endif
+
+static void sun8i_ss_free_flows(struct sun8i_ss_dev *ss, int i)
+{
+	while (i >= 0) {
+		crypto_engine_exit(ss->flows[i].engine);
+		i--;
+	}
+}
+
+/*
+ * Allocate the flow list structure
+ */
+static int allocate_flows(struct sun8i_ss_dev *ss)
+{
+	int i, err;
+
+	ss->flows = devm_kcalloc(ss->dev, MAXFLOW, sizeof(struct sun8i_ss_flow),
+				 GFP_KERNEL);
+	if (!ss->flows)
+		return -ENOMEM;
+
+	for (i = 0; i < MAXFLOW; i++) {
+		init_completion(&ss->flows[i].complete);
+
+		ss->flows[i].engine = crypto_engine_alloc_init(ss->dev, true);
+		if (!ss->flows[i].engine) {
+			dev_err(ss->dev, "Cannot allocate engine\n");
+			i--;
+			err = -ENOMEM;
+			goto error_engine;
+		}
+		err = crypto_engine_start(ss->flows[i].engine);
+		if (err) {
+			dev_err(ss->dev, "Cannot start engine\n");
+			goto error_engine;
+		}
+	}
+	return 0;
+error_engine:
+	sun8i_ss_free_flows(ss, i);
+	return err;
+}
+
+/*
+ * Power management strategy: The device is suspended unless a TFM exists for
+ * one of the algorithms proposed by this driver.
+ */
+static int sun8i_ss_pm_suspend(struct device *dev)
+{
+	struct sun8i_ss_dev *ss = dev_get_drvdata(dev);
+	int i;
+
+	reset_control_assert(ss->reset);
+	for (i = 0; i < SS_MAX_CLOCKS; i++)
+		clk_disable_unprepare(ss->ssclks[i]);
+	return 0;
+}
+
+static int sun8i_ss_pm_resume(struct device *dev)
+{
+	struct sun8i_ss_dev *ss = dev_get_drvdata(dev);
+	int err, i;
+
+	for (i = 0; i < SS_MAX_CLOCKS; i++) {
+		if (!ss->variant->ss_clks[i].name)
+			continue;
+		err = clk_prepare_enable(ss->ssclks[i]);
+		if (err) {
+			dev_err(ss->dev, "Cannot prepare_enable %s\n",
+				ss->variant->ss_clks[i].name);
+			goto error;
+		}
+	}
+	err = reset_control_deassert(ss->reset);
+	if (err) {
+		dev_err(ss->dev, "Cannot deassert reset control\n");
+		goto error;
+	}
+	/* enable interrupts for all flows */
+	writel(BIT(0) | BIT(1), ss->base + SS_INT_CTL_REG);
+
+	return 0;
+error:
+	sun8i_ss_pm_suspend(dev);
+	return err;
+}
+
+static const struct dev_pm_ops sun8i_ss_pm_ops = {
+	SET_RUNTIME_PM_OPS(sun8i_ss_pm_suspend, sun8i_ss_pm_resume, NULL)
+};
+
+static int sun8i_ss_pm_init(struct sun8i_ss_dev *ss)
+{
+	int err;
+
+	pm_runtime_use_autosuspend(ss->dev);
+	pm_runtime_set_autosuspend_delay(ss->dev, 2000);
+
+	err = pm_runtime_set_suspended(ss->dev);
+	if (err)
+		return err;
+	pm_runtime_enable(ss->dev);
+	return err;
+}
+
+static void sun8i_ss_pm_exit(struct sun8i_ss_dev *ss)
+{
+	pm_runtime_disable(ss->dev);
+}
+
+static int sun8i_ss_register_algs(struct sun8i_ss_dev *ss)
+{
+	int ss_method, err, id, i;
+
+	for (i = 0; i < ARRAY_SIZE(ss_algs); i++) {
+		ss_algs[i].ss = ss;
+		switch (ss_algs[i].type) {
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			id = ss_algs[i].ss_algo_id;
+			ss_method = ss->variant->alg_cipher[id];
+			if (ss_method == SS_ID_NOTSUPP) {
+				dev_info(ss->dev,
+					 "DEBUG: Algo of %s not supported\n",
+					 ss_algs[i].alg.skcipher.base.cra_name);
+				ss_algs[i].ss = NULL;
+				break;
+			}
+			id = ss_algs[i].ss_blockmode;
+			ss_method = ss->variant->op_mode[id];
+			if (ss_method == SS_ID_NOTSUPP) {
+				dev_info(ss->dev, "DEBUG: Blockmode of %s not supported\n",
+					 ss_algs[i].alg.skcipher.base.cra_name);
+				ss_algs[i].ss = NULL;
+				break;
+			}
+			dev_info(ss->dev, "DEBUG: Register %s\n",
+				 ss_algs[i].alg.skcipher.base.cra_name);
+			err = crypto_register_skcipher(&ss_algs[i].alg.skcipher);
+			if (err) {
+				dev_err(ss->dev, "Fail to register %s\n",
+					ss_algs[i].alg.skcipher.base.cra_name);
+				ss_algs[i].ss = NULL;
+				return err;
+			}
+			break;
+		default:
+			ss_algs[i].ss = NULL;
+			dev_err(ss->dev, "ERROR: tried to register an unknown algo\n");
+		}
+	}
+	return 0;
+}
+
+static void sun8i_ss_unregister_algs(struct sun8i_ss_dev *ss)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ss_algs); i++) {
+		if (!ss_algs[i].ss)
+			continue;
+		switch (ss_algs[i].type) {
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			dev_info(ss->dev, "Unregister %d %s\n", i,
+				 ss_algs[i].alg.skcipher.base.cra_name);
+			crypto_unregister_skcipher(&ss_algs[i].alg.skcipher);
+			break;
+		}
+	}
+}
+
+static int sun8i_ss_get_clks(struct sun8i_ss_dev *ss)
+{
+	unsigned long cr;
+	int err, i;
+
+	for (i = 0; i < SS_MAX_CLOCKS; i++) {
+		if (!ss->variant->ss_clks[i].name)
+			continue;
+		ss->ssclks[i] = devm_clk_get(ss->dev, ss->variant->ss_clks[i].name);
+		if (IS_ERR(ss->ssclks[i])) {
+			err = PTR_ERR(ss->ssclks[i]);
+			dev_err(ss->dev, "Cannot get %s SS clock err=%d\n",
+				ss->variant->ss_clks[i].name, err);
+			return err;
+		}
+		cr = clk_get_rate(ss->ssclks[i]);
+		if (!cr)
+			return -EINVAL;
+		if (ss->variant->ss_clks[i].freq > 0 &&
+		    cr != ss->variant->ss_clks[i].freq) {
+			dev_info(ss->dev, "Set %s clock to %lu (%lu Mhz) from %lu (%lu Mhz)\n",
+				 ss->variant->ss_clks[i].name,
+				 ss->variant->ss_clks[i].freq,
+				 ss->variant->ss_clks[i].freq / 1000000,
+				 cr, cr / 1000000);
+			err = clk_set_rate(ss->ssclks[i], ss->variant->ss_clks[i].freq);
+			if (err)
+				dev_err(ss->dev, "Fail to set %s clk speed to %lu hz\n",
+					ss->variant->ss_clks[i].name,
+					ss->variant->ss_clks[i].freq);
+		}
+		if (ss->variant->ss_clks[i].max_freq > 0 &&
+		    cr > ss->variant->ss_clks[i].max_freq)
+			dev_warn(ss->dev, "Frequency for %s (%lu hz) is higher than datasheet's recommendation (%lu hz)",
+				 ss->variant->ss_clks[i].name, cr,
+				 ss->variant->ss_clks[i].max_freq);
+	}
+	return 0;
+}
+
+static int sun8i_ss_probe(struct platform_device *pdev)
+{
+	struct sun8i_ss_dev *ss;
+	int err, irq;
+	u32 v;
+
+	ss = devm_kzalloc(&pdev->dev, sizeof(*ss), GFP_KERNEL);
+	if (!ss)
+		return -ENOMEM;
+
+	ss->dev = &pdev->dev;
+	platform_set_drvdata(pdev, ss);
+
+	ss->variant = of_device_get_match_data(&pdev->dev);
+	if (!ss->variant) {
+		dev_err(&pdev->dev, "Missing Crypto Engine variant\n");
+		return -EINVAL;
+	}
+
+	ss->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(ss->base))
+		return PTR_ERR(ss->base);
+
+	err = sun8i_ss_get_clks(ss);
+	if (err)
+		return err;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(ss->dev, "Cannot get SecuritySystem IRQ\n");
+		return irq;
+	}
+
+	ss->reset = devm_reset_control_get(&pdev->dev, NULL);
+	if (IS_ERR(ss->reset)) {
+		if (PTR_ERR(ss->reset) == -EPROBE_DEFER)
+			return PTR_ERR(ss->reset);
+		dev_err(&pdev->dev, "No reset control found\n");
+		return PTR_ERR(ss->reset);
+	}
+
+	mutex_init(&ss->mlock);
+
+	err = allocate_flows(ss);
+	if (err)
+		return err;
+
+	err = sun8i_ss_pm_init(ss);
+	if (err)
+		goto error_pm;
+
+	err = devm_request_irq(&pdev->dev, irq, ss_irq_handler, 0, "sun8i-ss", ss);
+	if (err) {
+		dev_err(ss->dev, "Cannot request SecuritySystem IRQ (err=%d)\n", err);
+		goto error_irq;
+	}
+
+	err = sun8i_ss_register_algs(ss);
+	if (err)
+		goto error_alg;
+
+	err = pm_runtime_get_sync(ss->dev);
+	if (err < 0)
+		goto error_alg;
+
+	v = readl(ss->base + SS_CTL_REG);
+	v >>= SS_DIE_ID_SHIFT;
+	v &= SS_DIE_ID_MASK;
+	dev_info(&pdev->dev, "Security System Die ID %x\n", v);
+
+	pm_runtime_put_sync(ss->dev);
+
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG
+	/* Ignore error of debugfs */
+	ss->dbgfs_dir = debugfs_create_dir("sun8i-ss", NULL);
+	ss->dbgfs_stats = debugfs_create_file("stats", 0444,
+					      ss->dbgfs_dir, ss,
+					      &sun8i_ss_debugfs_fops);
+#endif
+
+	return 0;
+error_alg:
+	sun8i_ss_unregister_algs(ss);
+error_irq:
+	sun8i_ss_pm_exit(ss);
+error_pm:
+	sun8i_ss_free_flows(ss, MAXFLOW);
+	return err;
+}
+
+static int sun8i_ss_remove(struct platform_device *pdev)
+{
+	struct sun8i_ss_dev *ss = platform_get_drvdata(pdev);
+
+	sun8i_ss_unregister_algs(ss);
+
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG
+	debugfs_remove_recursive(ss->dbgfs_dir);
+#endif
+
+	sun8i_ss_free_flows(ss, MAXFLOW);
+
+	sun8i_ss_pm_exit(ss);
+
+	return 0;
+}
+
+static const struct of_device_id sun8i_ss_crypto_of_match_table[] = {
+	{ .compatible = "allwinner,sun8i-a83t-crypto",
+	  .data = &ss_a83t_variant },
+	{ .compatible = "allwinner,sun9i-a80-crypto",
+	  .data = &ss_a80_variant },
+	{}
+};
+MODULE_DEVICE_TABLE(of, sun8i_ss_crypto_of_match_table);
+
+static struct platform_driver sun8i_ss_driver = {
+	.probe		 = sun8i_ss_probe,
+	.remove		 = sun8i_ss_remove,
+	.driver		 = {
+		.name		= "sun8i-ss",
+		.pm             = &sun8i_ss_pm_ops,
+		.of_match_table	= sun8i_ss_crypto_of_match_table,
+	},
+};
+
+module_platform_driver(sun8i_ss_driver);
+
+MODULE_DESCRIPTION("Allwinner SecuritySystem cryptographic offloader");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Corentin Labbe <clabbe.montjoie@gmail.com>");
diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h
new file mode 100644
index 000000000000..b5f855f3de10
--- /dev/null
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h
@@ -0,0 +1,218 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * sun8i-ss.h - hardware cryptographic offloader for
+ * Allwinner A80/A83T SoC
+ *
+ * Copyright (C) 2016-2019 Corentin LABBE <clabbe.montjoie@gmail.com>
+ */
+#include <crypto/aes.h>
+#include <crypto/des.h>
+#include <crypto/engine.h>
+#include <crypto/skcipher.h>
+#include <linux/atomic.h>
+#include <linux/debugfs.h>
+#include <linux/crypto.h>
+
+#define SS_ENCRYPTION		0
+#define SS_DECRYPTION		BIT(6)
+
+#define SS_ALG_AES		0
+#define SS_ALG_DES		(1 << 2)
+#define SS_ALG_3DES		(2 << 2)
+
+#define SS_CTL_REG		0x00
+#define SS_INT_CTL_REG		0x04
+#define SS_INT_STA_REG		0x08
+#define SS_KEY_ADR_REG		0x10
+#define SS_IV_ADR_REG		0x18
+#define SS_SRC_ADR_REG		0x20
+#define SS_DST_ADR_REG		0x28
+#define SS_LEN_ADR_REG		0x30
+
+#define SS_ID_NOTSUPP		0xFF
+
+#define SS_ID_CIPHER_AES	0
+#define SS_ID_CIPHER_DES	1
+#define SS_ID_CIPHER_DES3	2
+#define SS_ID_CIPHER_MAX	3
+
+#define SS_ID_OP_ECB	0
+#define SS_ID_OP_CBC	1
+#define SS_ID_OP_MAX	2
+
+#define SS_AES_128BITS 0
+#define SS_AES_192BITS 1
+#define SS_AES_256BITS 2
+
+#define SS_OP_ECB	0
+#define SS_OP_CBC	(1 << 13)
+
+#define SS_FLOW0	BIT(30)
+#define SS_FLOW1	BIT(31)
+
+#define MAX_SG 8
+
+#define MAXFLOW 2
+
+#define SS_MAX_CLOCKS 2
+
+#define SS_DIE_ID_SHIFT	20
+#define SS_DIE_ID_MASK	0x07
+
+/*
+ * struct ss_clock - Describe clocks used by sun8i-ss
+ * @name:       Name of clock needed by this variant
+ * @freq:       Frequency to set for each clock
+ * @max_freq:   Maximum frequency for each clock
+ */
+struct ss_clock {
+	const char *name;
+	unsigned long freq;
+	unsigned long max_freq;
+};
+
+/*
+ * struct ss_variant - Describe SS capability for each variant hardware
+ * @alg_cipher:	list of supported ciphers. for each SS_ID_ this will give the
+ *              coresponding SS_ALG_XXX value
+ * @op_mode:	list of supported block modes
+ * @ss_clks!	list of clock needed by this variant
+ */
+struct ss_variant {
+	char alg_cipher[SS_ID_CIPHER_MAX];
+	u32 op_mode[SS_ID_OP_MAX];
+	struct ss_clock ss_clks[SS_MAX_CLOCKS];
+};
+
+struct sginfo {
+	u32 addr;
+	u32 len;
+};
+
+/*
+ * struct sun8i_ss_flow - Information used by each flow
+ * @engine:	ptr to the crypto_engine for this flow
+ * @complete:	completion for the current task on this flow
+ * @status:	set to 1 by interrupt if task is done
+ * @stat_req:	number of request done by this flow
+ */
+struct sun8i_ss_flow {
+	struct crypto_engine *engine;
+	struct completion complete;
+	int status;
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG
+	unsigned long stat_req;
+#endif
+};
+
+/*
+ * struct sun8i_ss_dev - main container for all this driver information
+ * @base:	base address of SS
+ * @ssclks:	clocks used by SS
+ * @reset:	pointer to reset controller
+ * @dev:	the platform device
+ * @mlock:	Control access to device registers
+ * @flows:	array of all flow
+ * @flow:	flow to use in next request
+ * @variant:	pointer to variant specific data
+ * @dbgfs_dir:	Debugfs dentry for statistic directory
+ * @dbgfs_stats: Debugfs dentry for statistic counters
+ */
+struct sun8i_ss_dev {
+	void __iomem *base;
+	struct clk *ssclks[SS_MAX_CLOCKS];
+	struct reset_control *reset;
+	struct device *dev;
+	struct mutex mlock;
+	struct sun8i_ss_flow *flows;
+	atomic_t flow;
+	const struct ss_variant *variant;
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG
+	struct dentry *dbgfs_dir;
+	struct dentry *dbgfs_stats;
+#endif
+};
+
+/*
+ * struct sun8i_cipher_req_ctx - context for a skcipher request
+ * @t_src:	list of mapped SGs with their size
+ * @t_dst:	list of mapped SGs with their size
+ * @p_key:	DMA address of the key
+ * @p_iv:	DMA address of the IV
+ * @method:	current algorithm for this request
+ * @op_mode:	op_mode for this request
+ * @op_dir:	direction (encrypt vs decrypt) for this request
+ * @flow:	the flow to use for this request
+ * @ivlen:	size of biv
+ * @keylen:	keylen for this request
+ * @biv:	buffer which contain the IV
+ */
+struct sun8i_cipher_req_ctx {
+	struct sginfo t_src[MAX_SG];
+	struct sginfo t_dst[MAX_SG];
+	u32 p_key;
+	u32 p_iv;
+	u32 method;
+	u32 op_mode;
+	u32 op_dir;
+	int flow;
+	unsigned int ivlen;
+	unsigned int keylen;
+	void *biv;
+};
+
+/*
+ * struct sun8i_cipher_tfm_ctx - context for a skcipher TFM
+ * @enginectx:		crypto_engine used by this TFM
+ * @key:		pointer to key data
+ * @keylen:		len of the key
+ * @ss:			pointer to the private data of driver handling this TFM
+ * @fallback_tfm:	pointer to the fallback TFM
+ */
+struct sun8i_cipher_tfm_ctx {
+	struct crypto_engine_ctx enginectx;
+	u32 *key;
+	u32 keylen;
+	struct sun8i_ss_dev *ss;
+	struct crypto_sync_skcipher *fallback_tfm;
+};
+
+/*
+ * struct sun8i_ss_alg_template - crypto_alg template
+ * @type:		the CRYPTO_ALG_TYPE for this template
+ * @ss_algo_id:		the SS_ID for this template
+ * @ss_blockmode:	the type of block operation SS_ID
+ * @ss:			pointer to the sun8i_ss_dev structure associated with
+ *			this template
+ * @alg:		one of sub struct must be used
+ * @stat_req:		number of request done on this template
+ * @stat_fb:		total of all data len done on this template
+ */
+struct sun8i_ss_alg_template {
+	u32 type;
+	u32 ss_algo_id;
+	u32 ss_blockmode;
+	struct sun8i_ss_dev *ss;
+	union {
+		struct skcipher_alg skcipher;
+	} alg;
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG
+	unsigned long stat_req;
+	unsigned long stat_fb;
+#endif
+};
+
+int sun8i_ss_enqueue(struct crypto_async_request *areq, u32 type);
+
+int sun8i_ss_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			unsigned int keylen);
+int sun8i_ss_des3_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			 unsigned int keylen);
+int sun8i_ss_cipher_init(struct crypto_tfm *tfm);
+void sun8i_ss_cipher_exit(struct crypto_tfm *tfm);
+int sun8i_ss_skdecrypt(struct skcipher_request *areq);
+int sun8i_ss_skencrypt(struct skcipher_request *areq);
+
+int sun8i_ss_get_engine_number(struct sun8i_ss_dev *ss);
+
+int sun8i_ss_run_task(struct sun8i_ss_dev *ss, struct sun8i_cipher_req_ctx *rctx, const char *name);
diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c
index de5e9352e920..7d6b695c4ab3 100644
--- a/drivers/crypto/amcc/crypto4xx_core.c
+++ b/drivers/crypto/amcc/crypto4xx_core.c
@@ -365,12 +365,8 @@ static u32 crypto4xx_build_sdr(struct crypto4xx_device *dev)
 		dma_alloc_coherent(dev->core_dev->device,
 			PPC4XX_SD_BUFFER_SIZE * PPC4XX_NUM_SD,
 			&dev->scatter_buffer_pa, GFP_ATOMIC);
-	if (!dev->scatter_buffer_va) {
-		dma_free_coherent(dev->core_dev->device,
-				  sizeof(struct ce_sd) * PPC4XX_NUM_SD,
-				  dev->sdr, dev->sdr_pa);
+	if (!dev->scatter_buffer_va)
 		return -ENOMEM;
-	}
 
 	for (i = 0; i < PPC4XX_NUM_SD; i++) {
 		dev->sdr[i].ptr = dev->scatter_buffer_pa +
diff --git a/drivers/crypto/amlogic/Kconfig b/drivers/crypto/amlogic/Kconfig
new file mode 100644
index 000000000000..b90850d18965
--- /dev/null
+++ b/drivers/crypto/amlogic/Kconfig
@@ -0,0 +1,24 @@
+config CRYPTO_DEV_AMLOGIC_GXL
+	tristate "Support for amlogic cryptographic offloader"
+	default y if ARCH_MESON
+	select CRYPTO_SKCIPHER
+	select CRYPTO_ENGINE
+	select CRYPTO_ECB
+	select CRYPTO_CBC
+	select CRYPTO_AES
+	help
+	  Select y here to have support for the cryptographic offloader
+	  available on Amlogic GXL SoC.
+	  This hardware handles AES ciphers in ECB/CBC mode.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called amlogic-gxl-crypto.
+
+config CRYPTO_DEV_AMLOGIC_GXL_DEBUG
+	bool "Enable amlogic stats"
+	depends on CRYPTO_DEV_AMLOGIC_GXL
+	depends on DEBUG_FS
+	help
+	  Say y to enable amlogic-crypto debug stats.
+	  This will create /sys/kernel/debug/gxl-crypto/stats for displaying
+	  the number of requests per flow and per algorithm.
diff --git a/drivers/crypto/amlogic/Makefile b/drivers/crypto/amlogic/Makefile
new file mode 100644
index 000000000000..39057e62c13e
--- /dev/null
+++ b/drivers/crypto/amlogic/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_CRYPTO_DEV_AMLOGIC_GXL) += amlogic-gxl-crypto.o
+amlogic-gxl-crypto-y := amlogic-gxl-core.o amlogic-gxl-cipher.o
diff --git a/drivers/crypto/amlogic/amlogic-gxl-cipher.c b/drivers/crypto/amlogic/amlogic-gxl-cipher.c
new file mode 100644
index 000000000000..e589015aac1c
--- /dev/null
+++ b/drivers/crypto/amlogic/amlogic-gxl-cipher.c
@@ -0,0 +1,382 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * amlogic-cipher.c - hardware cryptographic offloader for Amlogic GXL SoC
+ *
+ * Copyright (C) 2018-2019 Corentin LABBE <clabbe@baylibre.com>
+ *
+ * This file add support for AES cipher with 128,192,256 bits keysize in
+ * CBC and ECB mode.
+ */
+
+#include <linux/crypto.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <crypto/scatterwalk.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-mapping.h>
+#include <crypto/internal/skcipher.h>
+#include "amlogic-gxl.h"
+
+static int get_engine_number(struct meson_dev *mc)
+{
+	return atomic_inc_return(&mc->flow) % MAXFLOW;
+}
+
+static bool meson_cipher_need_fallback(struct skcipher_request *areq)
+{
+	struct scatterlist *src_sg = areq->src;
+	struct scatterlist *dst_sg = areq->dst;
+
+	if (areq->cryptlen == 0)
+		return true;
+
+	if (sg_nents(src_sg) != sg_nents(dst_sg))
+		return true;
+
+	/* KEY/IV descriptors use 3 desc */
+	if (sg_nents(src_sg) > MAXDESC - 3 || sg_nents(dst_sg) > MAXDESC - 3)
+		return true;
+
+	while (src_sg && dst_sg) {
+		if ((src_sg->length % 16) != 0)
+			return true;
+		if ((dst_sg->length % 16) != 0)
+			return true;
+		if (src_sg->length != dst_sg->length)
+			return true;
+		if (!IS_ALIGNED(src_sg->offset, sizeof(u32)))
+			return true;
+		if (!IS_ALIGNED(dst_sg->offset, sizeof(u32)))
+			return true;
+		src_sg = sg_next(src_sg);
+		dst_sg = sg_next(dst_sg);
+	}
+
+	return false;
+}
+
+static int meson_cipher_do_fallback(struct skcipher_request *areq)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
+	struct meson_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct meson_cipher_req_ctx *rctx = skcipher_request_ctx(areq);
+	int err;
+#ifdef CONFIG_CRYPTO_DEV_AMLOGIC_GXL_DEBUG
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	struct meson_alg_template *algt;
+#endif
+	SYNC_SKCIPHER_REQUEST_ON_STACK(req, op->fallback_tfm);
+
+#ifdef CONFIG_CRYPTO_DEV_AMLOGIC_GXL_DEBUG
+	algt = container_of(alg, struct meson_alg_template, alg.skcipher);
+	algt->stat_fb++;
+#endif
+	skcipher_request_set_sync_tfm(req, op->fallback_tfm);
+	skcipher_request_set_callback(req, areq->base.flags, NULL, NULL);
+	skcipher_request_set_crypt(req, areq->src, areq->dst,
+				   areq->cryptlen, areq->iv);
+	if (rctx->op_dir == MESON_DECRYPT)
+		err = crypto_skcipher_decrypt(req);
+	else
+		err = crypto_skcipher_encrypt(req);
+	skcipher_request_zero(req);
+	return err;
+}
+
+static int meson_cipher(struct skcipher_request *areq)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
+	struct meson_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct meson_cipher_req_ctx *rctx = skcipher_request_ctx(areq);
+	struct meson_dev *mc = op->mc;
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	struct meson_alg_template *algt;
+	int flow = rctx->flow;
+	unsigned int todo, eat, len;
+	struct scatterlist *src_sg = areq->src;
+	struct scatterlist *dst_sg = areq->dst;
+	struct meson_desc *desc;
+	int nr_sgs, nr_sgd;
+	int i, err = 0;
+	unsigned int keyivlen, ivsize, offset, tloffset;
+	dma_addr_t phykeyiv;
+	void *backup_iv = NULL, *bkeyiv;
+	__le32 v;
+
+	algt = container_of(alg, struct meson_alg_template, alg.skcipher);
+
+	dev_dbg(mc->dev, "%s %s %u %x IV(%u) key=%u flow=%d\n", __func__,
+		crypto_tfm_alg_name(areq->base.tfm),
+		areq->cryptlen,
+		rctx->op_dir, crypto_skcipher_ivsize(tfm),
+		op->keylen, flow);
+
+#ifdef CONFIG_CRYPTO_DEV_AMLOGIC_GXL_DEBUG
+	algt->stat_req++;
+	mc->chanlist[flow].stat_req++;
+#endif
+
+	/*
+	 * The hardware expect a list of meson_desc structures.
+	 * The 2 first structures store key
+	 * The third stores IV
+	 */
+	bkeyiv = kzalloc(48, GFP_KERNEL | GFP_DMA);
+	if (!bkeyiv)
+		return -ENOMEM;
+
+	memcpy(bkeyiv, op->key, op->keylen);
+	keyivlen = op->keylen;
+
+	ivsize = crypto_skcipher_ivsize(tfm);
+	if (areq->iv && ivsize > 0) {
+		if (ivsize > areq->cryptlen) {
+			dev_err(mc->dev, "invalid ivsize=%d vs len=%d\n", ivsize, areq->cryptlen);
+			err = -EINVAL;
+			goto theend;
+		}
+		memcpy(bkeyiv + 32, areq->iv, ivsize);
+		keyivlen = 48;
+		if (rctx->op_dir == MESON_DECRYPT) {
+			backup_iv = kzalloc(ivsize, GFP_KERNEL);
+			if (!backup_iv) {
+				err = -ENOMEM;
+				goto theend;
+			}
+			offset = areq->cryptlen - ivsize;
+			scatterwalk_map_and_copy(backup_iv, areq->src, offset,
+						 ivsize, 0);
+		}
+	}
+	if (keyivlen == 24)
+		keyivlen = 32;
+
+	phykeyiv = dma_map_single(mc->dev, bkeyiv, keyivlen,
+				  DMA_TO_DEVICE);
+	err = dma_mapping_error(mc->dev, phykeyiv);
+	if (err) {
+		dev_err(mc->dev, "Cannot DMA MAP KEY IV\n");
+		goto theend;
+	}
+
+	tloffset = 0;
+	eat = 0;
+	i = 0;
+	while (keyivlen > eat) {
+		desc = &mc->chanlist[flow].tl[tloffset];
+		memset(desc, 0, sizeof(struct meson_desc));
+		todo = min(keyivlen - eat, 16u);
+		desc->t_src = cpu_to_le32(phykeyiv + i * 16);
+		desc->t_dst = cpu_to_le32(i * 16);
+		v = (MODE_KEY << 20) | DESC_OWN | 16;
+		desc->t_status = cpu_to_le32(v);
+
+		eat += todo;
+		i++;
+		tloffset++;
+	}
+
+	if (areq->src == areq->dst) {
+		nr_sgs = dma_map_sg(mc->dev, areq->src, sg_nents(areq->src),
+				    DMA_BIDIRECTIONAL);
+		if (nr_sgs < 0) {
+			dev_err(mc->dev, "Invalid SG count %d\n", nr_sgs);
+			err = -EINVAL;
+			goto theend;
+		}
+		nr_sgd = nr_sgs;
+	} else {
+		nr_sgs = dma_map_sg(mc->dev, areq->src, sg_nents(areq->src),
+				    DMA_TO_DEVICE);
+		if (nr_sgs < 0 || nr_sgs > MAXDESC - 3) {
+			dev_err(mc->dev, "Invalid SG count %d\n", nr_sgs);
+			err = -EINVAL;
+			goto theend;
+		}
+		nr_sgd = dma_map_sg(mc->dev, areq->dst, sg_nents(areq->dst),
+				    DMA_FROM_DEVICE);
+		if (nr_sgd < 0 || nr_sgd > MAXDESC - 3) {
+			dev_err(mc->dev, "Invalid SG count %d\n", nr_sgd);
+			err = -EINVAL;
+			goto theend;
+		}
+	}
+
+	src_sg = areq->src;
+	dst_sg = areq->dst;
+	len = areq->cryptlen;
+	while (src_sg) {
+		desc = &mc->chanlist[flow].tl[tloffset];
+		memset(desc, 0, sizeof(struct meson_desc));
+
+		desc->t_src = cpu_to_le32(sg_dma_address(src_sg));
+		desc->t_dst = cpu_to_le32(sg_dma_address(dst_sg));
+		todo = min(len, sg_dma_len(src_sg));
+		v = (op->keymode << 20) | DESC_OWN | todo | (algt->blockmode << 26);
+		if (rctx->op_dir)
+			v |= DESC_ENCRYPTION;
+		len -= todo;
+
+		if (!sg_next(src_sg))
+			v |= DESC_LAST;
+		desc->t_status = cpu_to_le32(v);
+		tloffset++;
+		src_sg = sg_next(src_sg);
+		dst_sg = sg_next(dst_sg);
+	}
+
+	reinit_completion(&mc->chanlist[flow].complete);
+	mc->chanlist[flow].status = 0;
+	writel(mc->chanlist[flow].t_phy | 2, mc->base + (flow << 2));
+	wait_for_completion_interruptible_timeout(&mc->chanlist[flow].complete,
+						  msecs_to_jiffies(500));
+	if (mc->chanlist[flow].status == 0) {
+		dev_err(mc->dev, "DMA timeout for flow %d\n", flow);
+		err = -EINVAL;
+	}
+
+	dma_unmap_single(mc->dev, phykeyiv, keyivlen, DMA_TO_DEVICE);
+
+	if (areq->src == areq->dst) {
+		dma_unmap_sg(mc->dev, areq->src, nr_sgs, DMA_BIDIRECTIONAL);
+	} else {
+		dma_unmap_sg(mc->dev, areq->src, nr_sgs, DMA_TO_DEVICE);
+		dma_unmap_sg(mc->dev, areq->dst, nr_sgd, DMA_FROM_DEVICE);
+	}
+
+	if (areq->iv && ivsize > 0) {
+		if (rctx->op_dir == MESON_DECRYPT) {
+			memcpy(areq->iv, backup_iv, ivsize);
+		} else {
+			scatterwalk_map_and_copy(areq->iv, areq->dst,
+						 areq->cryptlen - ivsize,
+						 ivsize, 0);
+		}
+	}
+theend:
+	kzfree(bkeyiv);
+	kzfree(backup_iv);
+
+	return err;
+}
+
+static int meson_handle_cipher_request(struct crypto_engine *engine,
+				       void *areq)
+{
+	int err;
+	struct skcipher_request *breq = container_of(areq, struct skcipher_request, base);
+
+	err = meson_cipher(breq);
+	crypto_finalize_skcipher_request(engine, breq, err);
+
+	return 0;
+}
+
+int meson_skdecrypt(struct skcipher_request *areq)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
+	struct meson_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct meson_cipher_req_ctx *rctx = skcipher_request_ctx(areq);
+	struct crypto_engine *engine;
+	int e;
+
+	rctx->op_dir = MESON_DECRYPT;
+	if (meson_cipher_need_fallback(areq))
+		return meson_cipher_do_fallback(areq);
+	e = get_engine_number(op->mc);
+	engine = op->mc->chanlist[e].engine;
+	rctx->flow = e;
+
+	return crypto_transfer_skcipher_request_to_engine(engine, areq);
+}
+
+int meson_skencrypt(struct skcipher_request *areq)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
+	struct meson_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct meson_cipher_req_ctx *rctx = skcipher_request_ctx(areq);
+	struct crypto_engine *engine;
+	int e;
+
+	rctx->op_dir = MESON_ENCRYPT;
+	if (meson_cipher_need_fallback(areq))
+		return meson_cipher_do_fallback(areq);
+	e = get_engine_number(op->mc);
+	engine = op->mc->chanlist[e].engine;
+	rctx->flow = e;
+
+	return crypto_transfer_skcipher_request_to_engine(engine, areq);
+}
+
+int meson_cipher_init(struct crypto_tfm *tfm)
+{
+	struct meson_cipher_tfm_ctx *op = crypto_tfm_ctx(tfm);
+	struct meson_alg_template *algt;
+	const char *name = crypto_tfm_alg_name(tfm);
+	struct crypto_skcipher *sktfm = __crypto_skcipher_cast(tfm);
+	struct skcipher_alg *alg = crypto_skcipher_alg(sktfm);
+
+	memset(op, 0, sizeof(struct meson_cipher_tfm_ctx));
+
+	algt = container_of(alg, struct meson_alg_template, alg.skcipher);
+	op->mc = algt->mc;
+
+	sktfm->reqsize = sizeof(struct meson_cipher_req_ctx);
+
+	op->fallback_tfm = crypto_alloc_sync_skcipher(name, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(op->fallback_tfm)) {
+		dev_err(op->mc->dev, "ERROR: Cannot allocate fallback for %s %ld\n",
+			name, PTR_ERR(op->fallback_tfm));
+		return PTR_ERR(op->fallback_tfm);
+	}
+
+	op->enginectx.op.do_one_request = meson_handle_cipher_request;
+	op->enginectx.op.prepare_request = NULL;
+	op->enginectx.op.unprepare_request = NULL;
+
+	return 0;
+}
+
+void meson_cipher_exit(struct crypto_tfm *tfm)
+{
+	struct meson_cipher_tfm_ctx *op = crypto_tfm_ctx(tfm);
+
+	if (op->key) {
+		memzero_explicit(op->key, op->keylen);
+		kfree(op->key);
+	}
+	crypto_free_sync_skcipher(op->fallback_tfm);
+}
+
+int meson_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
+		     unsigned int keylen)
+{
+	struct meson_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct meson_dev *mc = op->mc;
+
+	switch (keylen) {
+	case 128 / 8:
+		op->keymode = MODE_AES_128;
+		break;
+	case 192 / 8:
+		op->keymode = MODE_AES_192;
+		break;
+	case 256 / 8:
+		op->keymode = MODE_AES_256;
+		break;
+	default:
+		dev_dbg(mc->dev, "ERROR: Invalid keylen %u\n", keylen);
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	if (op->key) {
+		memzero_explicit(op->key, op->keylen);
+		kfree(op->key);
+	}
+	op->keylen = keylen;
+	op->key = kmemdup(key, keylen, GFP_KERNEL | GFP_DMA);
+	if (!op->key)
+		return -ENOMEM;
+
+	return crypto_sync_skcipher_setkey(op->fallback_tfm, key, keylen);
+}
diff --git a/drivers/crypto/amlogic/amlogic-gxl-core.c b/drivers/crypto/amlogic/amlogic-gxl-core.c
new file mode 100644
index 000000000000..fa05fce1c0de
--- /dev/null
+++ b/drivers/crypto/amlogic/amlogic-gxl-core.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * amlgoic-core.c - hardware cryptographic offloader for Amlogic GXL SoC
+ *
+ * Copyright (C) 2018-2019 Corentin Labbe <clabbe@baylibre.com>
+ *
+ * Core file which registers crypto algorithms supported by the hardware.
+ */
+#include <linux/clk.h>
+#include <linux/crypto.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/dma-mapping.h>
+
+#include "amlogic-gxl.h"
+
+static irqreturn_t meson_irq_handler(int irq, void *data)
+{
+	struct meson_dev *mc = (struct meson_dev *)data;
+	int flow;
+	u32 p;
+
+	for (flow = 0; flow < MAXFLOW; flow++) {
+		if (mc->irqs[flow] == irq) {
+			p = readl(mc->base + ((0x04 + flow) << 2));
+			if (p) {
+				writel_relaxed(0xF, mc->base + ((0x4 + flow) << 2));
+				mc->chanlist[flow].status = 1;
+				complete(&mc->chanlist[flow].complete);
+				return IRQ_HANDLED;
+			}
+			dev_err(mc->dev, "%s %d Got irq for flow %d but ctrl is empty\n", __func__, irq, flow);
+		}
+	}
+
+	dev_err(mc->dev, "%s %d from unknown irq\n", __func__, irq);
+	return IRQ_HANDLED;
+}
+
+static struct meson_alg_template mc_algs[] = {
+{
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.blockmode = MESON_OPMODE_CBC,
+	.alg.skcipher = {
+		.base = {
+			.cra_name = "cbc(aes)",
+			.cra_driver_name = "cbc-aes-gxl",
+			.cra_priority = 400,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+			.cra_ctxsize = sizeof(struct meson_cipher_tfm_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 0xf,
+			.cra_init = meson_cipher_init,
+			.cra_exit = meson_cipher_exit,
+		},
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= meson_aes_setkey,
+		.encrypt	= meson_skencrypt,
+		.decrypt	= meson_skdecrypt,
+	}
+},
+{
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.blockmode = MESON_OPMODE_ECB,
+	.alg.skcipher = {
+		.base = {
+			.cra_name = "ecb(aes)",
+			.cra_driver_name = "ecb-aes-gxl",
+			.cra_priority = 400,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+			.cra_ctxsize = sizeof(struct meson_cipher_tfm_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 0xf,
+			.cra_init = meson_cipher_init,
+			.cra_exit = meson_cipher_exit,
+		},
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.setkey		= meson_aes_setkey,
+		.encrypt	= meson_skencrypt,
+		.decrypt	= meson_skdecrypt,
+	}
+},
+};
+
+#ifdef CONFIG_CRYPTO_DEV_AMLOGIC_GXL_DEBUG
+static int meson_dbgfs_read(struct seq_file *seq, void *v)
+{
+	struct meson_dev *mc = seq->private;
+	int i;
+
+	for (i = 0; i < MAXFLOW; i++)
+		seq_printf(seq, "Channel %d: nreq %lu\n", i, mc->chanlist[i].stat_req);
+
+	for (i = 0; i < ARRAY_SIZE(mc_algs); i++) {
+		switch (mc_algs[i].type) {
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			seq_printf(seq, "%s %s %lu %lu\n",
+				   mc_algs[i].alg.skcipher.base.cra_driver_name,
+				   mc_algs[i].alg.skcipher.base.cra_name,
+				   mc_algs[i].stat_req, mc_algs[i].stat_fb);
+			break;
+		}
+	}
+	return 0;
+}
+
+static int meson_dbgfs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, meson_dbgfs_read, inode->i_private);
+}
+
+static const struct file_operations meson_debugfs_fops = {
+	.owner = THIS_MODULE,
+	.open = meson_dbgfs_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+#endif
+
+static void meson_free_chanlist(struct meson_dev *mc, int i)
+{
+	while (i >= 0) {
+		crypto_engine_exit(mc->chanlist[i].engine);
+		if (mc->chanlist[i].tl)
+			dma_free_coherent(mc->dev, sizeof(struct meson_desc) * MAXDESC,
+					  mc->chanlist[i].tl,
+					  mc->chanlist[i].t_phy);
+		i--;
+	}
+}
+
+/*
+ * Allocate the channel list structure
+ */
+static int meson_allocate_chanlist(struct meson_dev *mc)
+{
+	int i, err;
+
+	mc->chanlist = devm_kcalloc(mc->dev, MAXFLOW,
+				    sizeof(struct meson_flow), GFP_KERNEL);
+	if (!mc->chanlist)
+		return -ENOMEM;
+
+	for (i = 0; i < MAXFLOW; i++) {
+		init_completion(&mc->chanlist[i].complete);
+
+		mc->chanlist[i].engine = crypto_engine_alloc_init(mc->dev, true);
+		if (!mc->chanlist[i].engine) {
+			dev_err(mc->dev, "Cannot allocate engine\n");
+			i--;
+			err = -ENOMEM;
+			goto error_engine;
+		}
+		err = crypto_engine_start(mc->chanlist[i].engine);
+		if (err) {
+			dev_err(mc->dev, "Cannot start engine\n");
+			goto error_engine;
+		}
+		mc->chanlist[i].tl = dma_alloc_coherent(mc->dev,
+							sizeof(struct meson_desc) * MAXDESC,
+							&mc->chanlist[i].t_phy,
+							GFP_KERNEL);
+		if (!mc->chanlist[i].tl) {
+			err = -ENOMEM;
+			goto error_engine;
+		}
+	}
+	return 0;
+error_engine:
+	meson_free_chanlist(mc, i);
+	return err;
+}
+
+static int meson_register_algs(struct meson_dev *mc)
+{
+	int err, i;
+
+	for (i = 0; i < ARRAY_SIZE(mc_algs); i++) {
+		mc_algs[i].mc = mc;
+		switch (mc_algs[i].type) {
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			err = crypto_register_skcipher(&mc_algs[i].alg.skcipher);
+			if (err) {
+				dev_err(mc->dev, "Fail to register %s\n",
+					mc_algs[i].alg.skcipher.base.cra_name);
+				mc_algs[i].mc = NULL;
+				return err;
+			}
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static void meson_unregister_algs(struct meson_dev *mc)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mc_algs); i++) {
+		if (!mc_algs[i].mc)
+			continue;
+		switch (mc_algs[i].type) {
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			crypto_unregister_skcipher(&mc_algs[i].alg.skcipher);
+			break;
+		}
+	}
+}
+
+static int meson_crypto_probe(struct platform_device *pdev)
+{
+	struct meson_dev *mc;
+	int err, i;
+
+	if (!pdev->dev.of_node)
+		return -ENODEV;
+
+	mc = devm_kzalloc(&pdev->dev, sizeof(*mc), GFP_KERNEL);
+	if (!mc)
+		return -ENOMEM;
+
+	mc->dev = &pdev->dev;
+	platform_set_drvdata(pdev, mc);
+
+	mc->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(mc->base)) {
+		err = PTR_ERR(mc->base);
+		dev_err(&pdev->dev, "Cannot request MMIO err=%d\n", err);
+		return err;
+	}
+	mc->busclk = devm_clk_get(&pdev->dev, "blkmv");
+	if (IS_ERR(mc->busclk)) {
+		err = PTR_ERR(mc->busclk);
+		dev_err(&pdev->dev, "Cannot get core clock err=%d\n", err);
+		return err;
+	}
+
+	mc->irqs = devm_kcalloc(mc->dev, MAXFLOW, sizeof(int), GFP_KERNEL);
+	for (i = 0; i < MAXFLOW; i++) {
+		mc->irqs[i] = platform_get_irq(pdev, i);
+		if (mc->irqs[i] < 0) {
+			dev_err(mc->dev, "Cannot get IRQ for flow %d\n", i);
+			return mc->irqs[i];
+		}
+
+		err = devm_request_irq(&pdev->dev, mc->irqs[i], meson_irq_handler, 0,
+				       "gxl-crypto", mc);
+		if (err < 0) {
+			dev_err(mc->dev, "Cannot request IRQ for flow %d\n", i);
+			return err;
+		}
+	}
+
+	err = clk_prepare_enable(mc->busclk);
+	if (err != 0) {
+		dev_err(&pdev->dev, "Cannot prepare_enable busclk\n");
+		return err;
+	}
+
+	err = meson_allocate_chanlist(mc);
+	if (err)
+		goto error_flow;
+
+	err = meson_register_algs(mc);
+	if (err)
+		goto error_alg;
+
+#ifdef CONFIG_CRYPTO_DEV_AMLOGIC_GXL_DEBUG
+	mc->dbgfs_dir = debugfs_create_dir("gxl-crypto", NULL);
+	debugfs_create_file("stats", 0444, mc->dbgfs_dir, mc, &meson_debugfs_fops);
+#endif
+
+	return 0;
+error_alg:
+	meson_unregister_algs(mc);
+error_flow:
+	meson_free_chanlist(mc, MAXFLOW);
+	clk_disable_unprepare(mc->busclk);
+	return err;
+}
+
+static int meson_crypto_remove(struct platform_device *pdev)
+{
+	struct meson_dev *mc = platform_get_drvdata(pdev);
+
+#ifdef CONFIG_CRYPTO_DEV_AMLOGIC_GXL_DEBUG
+	debugfs_remove_recursive(mc->dbgfs_dir);
+#endif
+
+	meson_unregister_algs(mc);
+
+	meson_free_chanlist(mc, MAXFLOW);
+
+	clk_disable_unprepare(mc->busclk);
+	return 0;
+}
+
+static const struct of_device_id meson_crypto_of_match_table[] = {
+	{ .compatible = "amlogic,gxl-crypto", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, meson_crypto_of_match_table);
+
+static struct platform_driver meson_crypto_driver = {
+	.probe		 = meson_crypto_probe,
+	.remove		 = meson_crypto_remove,
+	.driver		 = {
+		.name		   = "gxl-crypto",
+		.of_match_table	= meson_crypto_of_match_table,
+	},
+};
+
+module_platform_driver(meson_crypto_driver);
+
+MODULE_DESCRIPTION("Amlogic GXL cryptographic offloader");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Corentin Labbe <clabbe@baylibre.com>");
diff --git a/drivers/crypto/amlogic/amlogic-gxl.h b/drivers/crypto/amlogic/amlogic-gxl.h
new file mode 100644
index 000000000000..b7f2de91ab76
--- /dev/null
+++ b/drivers/crypto/amlogic/amlogic-gxl.h
@@ -0,0 +1,161 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * amlogic.h - hardware cryptographic offloader for Amlogic SoC
+ *
+ * Copyright (C) 2018-2019 Corentin LABBE <clabbe@baylibre.com>
+ */
+#include <crypto/aes.h>
+#include <crypto/engine.h>
+#include <crypto/skcipher.h>
+#include <linux/debugfs.h>
+#include <linux/crypto.h>
+#include <linux/scatterlist.h>
+
+#define MODE_KEY 1
+#define MODE_AES_128 0x8
+#define MODE_AES_192 0x9
+#define MODE_AES_256 0xa
+
+#define MESON_DECRYPT 0
+#define MESON_ENCRYPT 1
+
+#define MESON_OPMODE_ECB 0
+#define MESON_OPMODE_CBC 1
+
+#define MAXFLOW 2
+
+#define MAXDESC 64
+
+#define DESC_LAST BIT(18)
+#define DESC_ENCRYPTION BIT(28)
+#define DESC_OWN BIT(31)
+
+/*
+ * struct meson_desc - Descriptor for DMA operations
+ * Note that without datasheet, some are unknown
+ * @t_status:	Descriptor of the cipher operation (see description below)
+ * @t_src:	Physical address of data to read
+ * @t_dst:	Physical address of data to write
+ * t_status is segmented like this:
+ * @len:	0-16	length of data to operate
+ * @irq:	17	Ignored by hardware
+ * @eoc:	18	End means the descriptor is the last
+ * @loop:	19	Unknown
+ * @mode:	20-23	Type of algorithm (AES, SHA)
+ * @begin:	24	Unknown
+ * @end:	25	Unknown
+ * @op_mode:	26-27	Blockmode (CBC, ECB)
+ * @enc:	28	0 means decryption, 1 is for encryption
+ * @block:	29	Unknown
+ * @error:	30	Unknown
+ * @owner:	31	owner of the descriptor, 1 own by HW
+ */
+struct meson_desc {
+	__le32 t_status;
+	__le32 t_src;
+	__le32 t_dst;
+};
+
+/*
+ * struct meson_flow - Information used by each flow
+ * @engine:	ptr to the crypto_engine for this flow
+ * @keylen:	keylen for this flow operation
+ * @complete:	completion for the current task on this flow
+ * @status:	set to 1 by interrupt if task is done
+ * @t_phy:	Physical address of task
+ * @tl:		pointer to the current ce_task for this flow
+ * @stat_req:	number of request done by this flow
+ */
+struct meson_flow {
+	struct crypto_engine *engine;
+	struct completion complete;
+	int status;
+	unsigned int keylen;
+	dma_addr_t t_phy;
+	struct meson_desc *tl;
+#ifdef CONFIG_CRYPTO_DEV_AMLOGIC_GXL_DEBUG
+	unsigned long stat_req;
+#endif
+};
+
+/*
+ * struct meson_dev - main container for all this driver information
+ * @base:	base address of amlogic-crypto
+ * @busclk:	bus clock for amlogic-crypto
+ * @dev:	the platform device
+ * @chanlist:	array of all flow
+ * @flow:	flow to use in next request
+ * @irqs:	IRQ numbers for amlogic-crypto
+ * @dbgfs_dir:	Debugfs dentry for statistic directory
+ * @dbgfs_stats: Debugfs dentry for statistic counters
+ */
+struct meson_dev {
+	void __iomem *base;
+	struct clk *busclk;
+	struct device *dev;
+	struct meson_flow *chanlist;
+	atomic_t flow;
+	int *irqs;
+#ifdef CONFIG_CRYPTO_DEV_AMLOGIC_GXL_DEBUG
+	struct dentry *dbgfs_dir;
+#endif
+};
+
+/*
+ * struct meson_cipher_req_ctx - context for a skcipher request
+ * @op_dir:	direction (encrypt vs decrypt) for this request
+ * @flow:	the flow to use for this request
+ */
+struct meson_cipher_req_ctx {
+	u32 op_dir;
+	int flow;
+};
+
+/*
+ * struct meson_cipher_tfm_ctx - context for a skcipher TFM
+ * @enginectx:		crypto_engine used by this TFM
+ * @key:		pointer to key data
+ * @keylen:		len of the key
+ * @keymode:		The keymode(type and size of key) associated with this TFM
+ * @mc:			pointer to the private data of driver handling this TFM
+ * @fallback_tfm:	pointer to the fallback TFM
+ */
+struct meson_cipher_tfm_ctx {
+	struct crypto_engine_ctx enginectx;
+	u32 *key;
+	u32 keylen;
+	u32 keymode;
+	struct meson_dev *mc;
+	struct crypto_sync_skcipher *fallback_tfm;
+};
+
+/*
+ * struct meson_alg_template - crypto_alg template
+ * @type:		the CRYPTO_ALG_TYPE for this template
+ * @blockmode:		the type of block operation
+ * @mc:			pointer to the meson_dev structure associated with this template
+ * @alg:		one of sub struct must be used
+ * @stat_req:		number of request done on this template
+ * @stat_fb:		total of all data len done on this template
+ */
+struct meson_alg_template {
+	u32 type;
+	u32 blockmode;
+	union {
+		struct skcipher_alg skcipher;
+	} alg;
+	struct meson_dev *mc;
+#ifdef CONFIG_CRYPTO_DEV_AMLOGIC_GXL_DEBUG
+	unsigned long stat_req;
+	unsigned long stat_fb;
+#endif
+};
+
+int meson_enqueue(struct crypto_async_request *areq, u32 type);
+
+int meson_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
+		     unsigned int keylen);
+int meson_cipher_init(struct crypto_tfm *tfm);
+void meson_cipher_exit(struct crypto_tfm *tfm);
+int meson_skdecrypt(struct skcipher_request *areq);
+int meson_skencrypt(struct skcipher_request *areq);
diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c
index 026f193556f9..91092504bc96 100644
--- a/drivers/crypto/atmel-aes.c
+++ b/drivers/crypto/atmel-aes.c
@@ -36,6 +36,7 @@
 #include <crypto/gcm.h>
 #include <crypto/xts.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
 #include <linux/platform_data/crypto-atmel.h>
 #include <dt-bindings/dma/at91.h>
 #include "atmel-aes-regs.h"
@@ -117,7 +118,7 @@ struct atmel_aes_ctx {
 struct atmel_aes_ctr_ctx {
 	struct atmel_aes_base_ctx	base;
 
-	u32			iv[AES_BLOCK_SIZE / sizeof(u32)];
+	__be32			iv[AES_BLOCK_SIZE / sizeof(u32)];
 	size_t			offset;
 	struct scatterlist	src[2];
 	struct scatterlist	dst[2];
@@ -129,13 +130,13 @@ struct atmel_aes_gcm_ctx {
 	struct scatterlist	src[2];
 	struct scatterlist	dst[2];
 
-	u32			j0[AES_BLOCK_SIZE / sizeof(u32)];
+	__be32			j0[AES_BLOCK_SIZE / sizeof(u32)];
 	u32			tag[AES_BLOCK_SIZE / sizeof(u32)];
-	u32			ghash[AES_BLOCK_SIZE / sizeof(u32)];
+	__be32			ghash[AES_BLOCK_SIZE / sizeof(u32)];
 	size_t			textlen;
 
-	const u32		*ghash_in;
-	u32			*ghash_out;
+	const __be32		*ghash_in;
+	__be32			*ghash_out;
 	atmel_aes_fn_t		ghash_resume;
 };
 
@@ -145,7 +146,7 @@ struct atmel_aes_xts_ctx {
 	u32			key2[AES_KEYSIZE_256 / sizeof(u32)];
 };
 
-#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC
+#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC)
 struct atmel_aes_authenc_ctx {
 	struct atmel_aes_base_ctx	base;
 	struct atmel_sha_authenc_ctx	*auth;
@@ -154,10 +155,10 @@ struct atmel_aes_authenc_ctx {
 
 struct atmel_aes_reqctx {
 	unsigned long		mode;
-	u32			lastc[AES_BLOCK_SIZE / sizeof(u32)];
+	u8			lastc[AES_BLOCK_SIZE];
 };
 
-#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC
+#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC)
 struct atmel_aes_authenc_reqctx {
 	struct atmel_aes_reqctx	base;
 
@@ -388,13 +389,13 @@ static void atmel_aes_write_n(struct atmel_aes_dev *dd, u32 offset,
 }
 
 static inline void atmel_aes_read_block(struct atmel_aes_dev *dd, u32 offset,
-					u32 *value)
+					void *value)
 {
 	atmel_aes_read_n(dd, offset, value, SIZE_IN_WORDS(AES_BLOCK_SIZE));
 }
 
 static inline void atmel_aes_write_block(struct atmel_aes_dev *dd, u32 offset,
-					 const u32 *value)
+					 const void *value)
 {
 	atmel_aes_write_n(dd, offset, value, SIZE_IN_WORDS(AES_BLOCK_SIZE));
 }
@@ -486,13 +487,36 @@ static inline bool atmel_aes_is_encrypt(const struct atmel_aes_dev *dd)
 	return (dd->flags & AES_FLAGS_ENCRYPT);
 }
 
-#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC
+#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC)
 static void atmel_aes_authenc_complete(struct atmel_aes_dev *dd, int err);
 #endif
 
+static void atmel_aes_set_iv_as_last_ciphertext_block(struct atmel_aes_dev *dd)
+{
+	struct skcipher_request *req = skcipher_request_cast(dd->areq);
+	struct atmel_aes_reqctx *rctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
+	unsigned int ivsize = crypto_skcipher_ivsize(skcipher);
+
+	if (req->cryptlen < ivsize)
+		return;
+
+	if (rctx->mode & AES_FLAGS_ENCRYPT) {
+		scatterwalk_map_and_copy(req->iv, req->dst,
+					 req->cryptlen - ivsize, ivsize, 0);
+	} else {
+		if (req->src == req->dst)
+			memcpy(req->iv, rctx->lastc, ivsize);
+		else
+			scatterwalk_map_and_copy(req->iv, req->src,
+						 req->cryptlen - ivsize,
+						 ivsize, 0);
+	}
+}
+
 static inline int atmel_aes_complete(struct atmel_aes_dev *dd, int err)
 {
-#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC
+#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC)
 	if (dd->ctx->is_aead)
 		atmel_aes_authenc_complete(dd, err);
 #endif
@@ -500,26 +524,8 @@ static inline int atmel_aes_complete(struct atmel_aes_dev *dd, int err)
 	clk_disable(dd->iclk);
 	dd->flags &= ~AES_FLAGS_BUSY;
 
-	if (!dd->ctx->is_aead) {
-		struct ablkcipher_request *req =
-			ablkcipher_request_cast(dd->areq);
-		struct atmel_aes_reqctx *rctx = ablkcipher_request_ctx(req);
-		struct crypto_ablkcipher *ablkcipher =
-			crypto_ablkcipher_reqtfm(req);
-		int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
-
-		if (rctx->mode & AES_FLAGS_ENCRYPT) {
-			scatterwalk_map_and_copy(req->info, req->dst,
-				req->nbytes - ivsize, ivsize, 0);
-		} else {
-			if (req->src == req->dst) {
-				memcpy(req->info, rctx->lastc, ivsize);
-			} else {
-				scatterwalk_map_and_copy(req->info, req->src,
-					req->nbytes - ivsize, ivsize, 0);
-			}
-		}
-	}
+	if (!dd->ctx->is_aead)
+		atmel_aes_set_iv_as_last_ciphertext_block(dd);
 
 	if (dd->is_async)
 		dd->areq->complete(dd->areq, err);
@@ -530,7 +536,7 @@ static inline int atmel_aes_complete(struct atmel_aes_dev *dd, int err)
 }
 
 static void atmel_aes_write_ctrl_key(struct atmel_aes_dev *dd, bool use_dma,
-				     const u32 *iv, const u32 *key, int keylen)
+				     const __be32 *iv, const u32 *key, int keylen)
 {
 	u32 valmr = 0;
 
@@ -561,7 +567,7 @@ static void atmel_aes_write_ctrl_key(struct atmel_aes_dev *dd, bool use_dma,
 }
 
 static inline void atmel_aes_write_ctrl(struct atmel_aes_dev *dd, bool use_dma,
-					const u32 *iv)
+					const __be32 *iv)
 
 {
 	atmel_aes_write_ctrl_key(dd, use_dma, iv,
@@ -976,9 +982,9 @@ static int atmel_aes_transfer_complete(struct atmel_aes_dev *dd)
 
 static int atmel_aes_start(struct atmel_aes_dev *dd)
 {
-	struct ablkcipher_request *req = ablkcipher_request_cast(dd->areq);
-	struct atmel_aes_reqctx *rctx = ablkcipher_request_ctx(req);
-	bool use_dma = (req->nbytes >= ATMEL_AES_DMA_THRESHOLD ||
+	struct skcipher_request *req = skcipher_request_cast(dd->areq);
+	struct atmel_aes_reqctx *rctx = skcipher_request_ctx(req);
+	bool use_dma = (req->cryptlen >= ATMEL_AES_DMA_THRESHOLD ||
 			dd->ctx->block_size != AES_BLOCK_SIZE);
 	int err;
 
@@ -988,12 +994,13 @@ static int atmel_aes_start(struct atmel_aes_dev *dd)
 	if (err)
 		return atmel_aes_complete(dd, err);
 
-	atmel_aes_write_ctrl(dd, use_dma, req->info);
+	atmel_aes_write_ctrl(dd, use_dma, (void *)req->iv);
 	if (use_dma)
-		return atmel_aes_dma_start(dd, req->src, req->dst, req->nbytes,
+		return atmel_aes_dma_start(dd, req->src, req->dst,
+					   req->cryptlen,
 					   atmel_aes_transfer_complete);
 
-	return atmel_aes_cpu_start(dd, req->src, req->dst, req->nbytes,
+	return atmel_aes_cpu_start(dd, req->src, req->dst, req->cryptlen,
 				   atmel_aes_transfer_complete);
 }
 
@@ -1006,7 +1013,7 @@ atmel_aes_ctr_ctx_cast(struct atmel_aes_base_ctx *ctx)
 static int atmel_aes_ctr_transfer(struct atmel_aes_dev *dd)
 {
 	struct atmel_aes_ctr_ctx *ctx = atmel_aes_ctr_ctx_cast(dd->ctx);
-	struct ablkcipher_request *req = ablkcipher_request_cast(dd->areq);
+	struct skcipher_request *req = skcipher_request_cast(dd->areq);
 	struct scatterlist *src, *dst;
 	u32 ctr, blocks;
 	size_t datalen;
@@ -1014,11 +1021,11 @@ static int atmel_aes_ctr_transfer(struct atmel_aes_dev *dd)
 
 	/* Check for transfer completion. */
 	ctx->offset += dd->total;
-	if (ctx->offset >= req->nbytes)
+	if (ctx->offset >= req->cryptlen)
 		return atmel_aes_transfer_complete(dd);
 
 	/* Compute data length. */
-	datalen = req->nbytes - ctx->offset;
+	datalen = req->cryptlen - ctx->offset;
 	blocks = DIV_ROUND_UP(datalen, AES_BLOCK_SIZE);
 	ctr = be32_to_cpu(ctx->iv[3]);
 	if (dd->caps.has_ctr32) {
@@ -1071,8 +1078,8 @@ static int atmel_aes_ctr_transfer(struct atmel_aes_dev *dd)
 static int atmel_aes_ctr_start(struct atmel_aes_dev *dd)
 {
 	struct atmel_aes_ctr_ctx *ctx = atmel_aes_ctr_ctx_cast(dd->ctx);
-	struct ablkcipher_request *req = ablkcipher_request_cast(dd->areq);
-	struct atmel_aes_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct skcipher_request *req = skcipher_request_cast(dd->areq);
+	struct atmel_aes_reqctx *rctx = skcipher_request_ctx(req);
 	int err;
 
 	atmel_aes_set_mode(dd, rctx);
@@ -1081,16 +1088,16 @@ static int atmel_aes_ctr_start(struct atmel_aes_dev *dd)
 	if (err)
 		return atmel_aes_complete(dd, err);
 
-	memcpy(ctx->iv, req->info, AES_BLOCK_SIZE);
+	memcpy(ctx->iv, req->iv, AES_BLOCK_SIZE);
 	ctx->offset = 0;
 	dd->total = 0;
 	return atmel_aes_ctr_transfer(dd);
 }
 
-static int atmel_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
+static int atmel_aes_crypt(struct skcipher_request *req, unsigned long mode)
 {
-	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
-	struct atmel_aes_base_ctx *ctx = crypto_ablkcipher_ctx(ablkcipher);
+	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
+	struct atmel_aes_base_ctx *ctx = crypto_skcipher_ctx(skcipher);
 	struct atmel_aes_reqctx *rctx;
 	struct atmel_aes_dev *dd;
 
@@ -1121,28 +1128,30 @@ static int atmel_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 	if (!dd)
 		return -ENODEV;
 
-	rctx = ablkcipher_request_ctx(req);
+	rctx = skcipher_request_ctx(req);
 	rctx->mode = mode;
 
 	if (!(mode & AES_FLAGS_ENCRYPT) && (req->src == req->dst)) {
-		int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
+		unsigned int ivsize = crypto_skcipher_ivsize(skcipher);
 
-		scatterwalk_map_and_copy(rctx->lastc, req->src,
-			(req->nbytes - ivsize), ivsize, 0);
+		if (req->cryptlen >= ivsize)
+			scatterwalk_map_and_copy(rctx->lastc, req->src,
+						 req->cryptlen - ivsize,
+						 ivsize, 0);
 	}
 
 	return atmel_aes_handle_queue(dd, &req->base);
 }
 
-static int atmel_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int atmel_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			   unsigned int keylen)
 {
-	struct atmel_aes_base_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct atmel_aes_base_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	if (keylen != AES_KEYSIZE_128 &&
 	    keylen != AES_KEYSIZE_192 &&
 	    keylen != AES_KEYSIZE_256) {
-		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
@@ -1152,297 +1161,279 @@ static int atmel_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 	return 0;
 }
 
-static int atmel_aes_ecb_encrypt(struct ablkcipher_request *req)
+static int atmel_aes_ecb_encrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_ECB | AES_FLAGS_ENCRYPT);
 }
 
-static int atmel_aes_ecb_decrypt(struct ablkcipher_request *req)
+static int atmel_aes_ecb_decrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_ECB);
 }
 
-static int atmel_aes_cbc_encrypt(struct ablkcipher_request *req)
+static int atmel_aes_cbc_encrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_CBC | AES_FLAGS_ENCRYPT);
 }
 
-static int atmel_aes_cbc_decrypt(struct ablkcipher_request *req)
+static int atmel_aes_cbc_decrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_CBC);
 }
 
-static int atmel_aes_ofb_encrypt(struct ablkcipher_request *req)
+static int atmel_aes_ofb_encrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_OFB | AES_FLAGS_ENCRYPT);
 }
 
-static int atmel_aes_ofb_decrypt(struct ablkcipher_request *req)
+static int atmel_aes_ofb_decrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_OFB);
 }
 
-static int atmel_aes_cfb_encrypt(struct ablkcipher_request *req)
+static int atmel_aes_cfb_encrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_CFB128 | AES_FLAGS_ENCRYPT);
 }
 
-static int atmel_aes_cfb_decrypt(struct ablkcipher_request *req)
+static int atmel_aes_cfb_decrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_CFB128);
 }
 
-static int atmel_aes_cfb64_encrypt(struct ablkcipher_request *req)
+static int atmel_aes_cfb64_encrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_CFB64 | AES_FLAGS_ENCRYPT);
 }
 
-static int atmel_aes_cfb64_decrypt(struct ablkcipher_request *req)
+static int atmel_aes_cfb64_decrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_CFB64);
 }
 
-static int atmel_aes_cfb32_encrypt(struct ablkcipher_request *req)
+static int atmel_aes_cfb32_encrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_CFB32 | AES_FLAGS_ENCRYPT);
 }
 
-static int atmel_aes_cfb32_decrypt(struct ablkcipher_request *req)
+static int atmel_aes_cfb32_decrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_CFB32);
 }
 
-static int atmel_aes_cfb16_encrypt(struct ablkcipher_request *req)
+static int atmel_aes_cfb16_encrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_CFB16 | AES_FLAGS_ENCRYPT);
 }
 
-static int atmel_aes_cfb16_decrypt(struct ablkcipher_request *req)
+static int atmel_aes_cfb16_decrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_CFB16);
 }
 
-static int atmel_aes_cfb8_encrypt(struct ablkcipher_request *req)
+static int atmel_aes_cfb8_encrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_CFB8 | AES_FLAGS_ENCRYPT);
 }
 
-static int atmel_aes_cfb8_decrypt(struct ablkcipher_request *req)
+static int atmel_aes_cfb8_decrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_CFB8);
 }
 
-static int atmel_aes_ctr_encrypt(struct ablkcipher_request *req)
+static int atmel_aes_ctr_encrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_CTR | AES_FLAGS_ENCRYPT);
 }
 
-static int atmel_aes_ctr_decrypt(struct ablkcipher_request *req)
+static int atmel_aes_ctr_decrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_CTR);
 }
 
-static int atmel_aes_cra_init(struct crypto_tfm *tfm)
+static int atmel_aes_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct atmel_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct atmel_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct atmel_aes_reqctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct atmel_aes_reqctx));
 	ctx->base.start = atmel_aes_start;
 
 	return 0;
 }
 
-static int atmel_aes_ctr_cra_init(struct crypto_tfm *tfm)
+static int atmel_aes_ctr_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct atmel_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct atmel_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct atmel_aes_reqctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct atmel_aes_reqctx));
 	ctx->base.start = atmel_aes_ctr_start;
 
 	return 0;
 }
 
-static struct crypto_alg aes_algs[] = {
-{
-	.cra_name		= "ecb(aes)",
-	.cra_driver_name	= "atmel-ecb-aes",
-	.cra_priority		= ATMEL_AES_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_aes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.setkey		= atmel_aes_setkey,
-		.encrypt	= atmel_aes_ecb_encrypt,
-		.decrypt	= atmel_aes_ecb_decrypt,
-	}
+static struct skcipher_alg aes_algs[] = {
+{
+	.base.cra_name		= "ecb(aes)",
+	.base.cra_driver_name	= "atmel-ecb-aes",
+	.base.cra_priority	= ATMEL_AES_PRIORITY,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_aes_init_tfm,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= atmel_aes_setkey,
+	.encrypt		= atmel_aes_ecb_encrypt,
+	.decrypt		= atmel_aes_ecb_decrypt,
 },
 {
-	.cra_name		= "cbc(aes)",
-	.cra_driver_name	= "atmel-cbc-aes",
-	.cra_priority		= ATMEL_AES_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_aes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= atmel_aes_setkey,
-		.encrypt	= atmel_aes_cbc_encrypt,
-		.decrypt	= atmel_aes_cbc_decrypt,
-	}
+	.base.cra_name		= "cbc(aes)",
+	.base.cra_driver_name	= "atmel-cbc-aes",
+	.base.cra_priority	= ATMEL_AES_PRIORITY,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_aes_init_tfm,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= atmel_aes_setkey,
+	.encrypt		= atmel_aes_cbc_encrypt,
+	.decrypt		= atmel_aes_cbc_decrypt,
+	.ivsize			= AES_BLOCK_SIZE,
 },
 {
-	.cra_name		= "ofb(aes)",
-	.cra_driver_name	= "atmel-ofb-aes",
-	.cra_priority		= ATMEL_AES_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_aes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= atmel_aes_setkey,
-		.encrypt	= atmel_aes_ofb_encrypt,
-		.decrypt	= atmel_aes_ofb_decrypt,
-	}
+	.base.cra_name		= "ofb(aes)",
+	.base.cra_driver_name	= "atmel-ofb-aes",
+	.base.cra_priority	= ATMEL_AES_PRIORITY,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_aes_init_tfm,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= atmel_aes_setkey,
+	.encrypt		= atmel_aes_ofb_encrypt,
+	.decrypt		= atmel_aes_ofb_decrypt,
+	.ivsize			= AES_BLOCK_SIZE,
 },
 {
-	.cra_name		= "cfb(aes)",
-	.cra_driver_name	= "atmel-cfb-aes",
-	.cra_priority		= ATMEL_AES_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_aes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= atmel_aes_setkey,
-		.encrypt	= atmel_aes_cfb_encrypt,
-		.decrypt	= atmel_aes_cfb_decrypt,
-	}
+	.base.cra_name		= "cfb(aes)",
+	.base.cra_driver_name	= "atmel-cfb-aes",
+	.base.cra_priority	= ATMEL_AES_PRIORITY,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_aes_init_tfm,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= atmel_aes_setkey,
+	.encrypt		= atmel_aes_cfb_encrypt,
+	.decrypt		= atmel_aes_cfb_decrypt,
+	.ivsize			= AES_BLOCK_SIZE,
 },
 {
-	.cra_name		= "cfb32(aes)",
-	.cra_driver_name	= "atmel-cfb32-aes",
-	.cra_priority		= ATMEL_AES_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CFB32_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
-	.cra_alignmask		= 0x3,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_aes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= atmel_aes_setkey,
-		.encrypt	= atmel_aes_cfb32_encrypt,
-		.decrypt	= atmel_aes_cfb32_decrypt,
-	}
+	.base.cra_name		= "cfb32(aes)",
+	.base.cra_driver_name	= "atmel-cfb32-aes",
+	.base.cra_priority	= ATMEL_AES_PRIORITY,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= CFB32_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_aes_init_tfm,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= atmel_aes_setkey,
+	.encrypt		= atmel_aes_cfb32_encrypt,
+	.decrypt		= atmel_aes_cfb32_decrypt,
+	.ivsize			= AES_BLOCK_SIZE,
 },
 {
-	.cra_name		= "cfb16(aes)",
-	.cra_driver_name	= "atmel-cfb16-aes",
-	.cra_priority		= ATMEL_AES_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CFB16_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
-	.cra_alignmask		= 0x1,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_aes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= atmel_aes_setkey,
-		.encrypt	= atmel_aes_cfb16_encrypt,
-		.decrypt	= atmel_aes_cfb16_decrypt,
-	}
+	.base.cra_name		= "cfb16(aes)",
+	.base.cra_driver_name	= "atmel-cfb16-aes",
+	.base.cra_priority	= ATMEL_AES_PRIORITY,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= CFB16_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_aes_init_tfm,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= atmel_aes_setkey,
+	.encrypt		= atmel_aes_cfb16_encrypt,
+	.decrypt		= atmel_aes_cfb16_decrypt,
+	.ivsize			= AES_BLOCK_SIZE,
 },
 {
-	.cra_name		= "cfb8(aes)",
-	.cra_driver_name	= "atmel-cfb8-aes",
-	.cra_priority		= ATMEL_AES_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CFB8_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
-	.cra_alignmask		= 0x0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_aes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= atmel_aes_setkey,
-		.encrypt	= atmel_aes_cfb8_encrypt,
-		.decrypt	= atmel_aes_cfb8_decrypt,
-	}
+	.base.cra_name		= "cfb8(aes)",
+	.base.cra_driver_name	= "atmel-cfb8-aes",
+	.base.cra_priority	= ATMEL_AES_PRIORITY,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= CFB8_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_aes_init_tfm,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= atmel_aes_setkey,
+	.encrypt		= atmel_aes_cfb8_encrypt,
+	.decrypt		= atmel_aes_cfb8_decrypt,
+	.ivsize			= AES_BLOCK_SIZE,
 },
 {
-	.cra_name		= "ctr(aes)",
-	.cra_driver_name	= "atmel-ctr-aes",
-	.cra_priority		= ATMEL_AES_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct atmel_aes_ctr_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_aes_ctr_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= atmel_aes_setkey,
-		.encrypt	= atmel_aes_ctr_encrypt,
-		.decrypt	= atmel_aes_ctr_decrypt,
-	}
+	.base.cra_name		= "ctr(aes)",
+	.base.cra_driver_name	= "atmel-ctr-aes",
+	.base.cra_priority	= ATMEL_AES_PRIORITY,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctr_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_aes_ctr_init_tfm,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= atmel_aes_setkey,
+	.encrypt		= atmel_aes_ctr_encrypt,
+	.decrypt		= atmel_aes_ctr_decrypt,
+	.ivsize			= AES_BLOCK_SIZE,
 },
 };
 
-static struct crypto_alg aes_cfb64_alg = {
-	.cra_name		= "cfb64(aes)",
-	.cra_driver_name	= "atmel-cfb64-aes",
-	.cra_priority		= ATMEL_AES_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CFB64_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
-	.cra_alignmask		= 0x7,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_aes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= atmel_aes_setkey,
-		.encrypt	= atmel_aes_cfb64_encrypt,
-		.decrypt	= atmel_aes_cfb64_decrypt,
-	}
+static struct skcipher_alg aes_cfb64_alg = {
+	.base.cra_name		= "cfb64(aes)",
+	.base.cra_driver_name	= "atmel-cfb64-aes",
+	.base.cra_priority	= ATMEL_AES_PRIORITY,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= CFB64_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_aes_init_tfm,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= atmel_aes_setkey,
+	.encrypt		= atmel_aes_cfb64_encrypt,
+	.decrypt		= atmel_aes_cfb64_decrypt,
+	.ivsize			= AES_BLOCK_SIZE,
 };
 
 
@@ -1450,7 +1441,7 @@ static struct crypto_alg aes_cfb64_alg = {
 
 static int atmel_aes_gcm_ghash(struct atmel_aes_dev *dd,
 			       const u32 *data, size_t datalen,
-			       const u32 *ghash_in, u32 *ghash_out,
+			       const __be32 *ghash_in, __be32 *ghash_out,
 			       atmel_aes_fn_t resume);
 static int atmel_aes_gcm_ghash_init(struct atmel_aes_dev *dd);
 static int atmel_aes_gcm_ghash_finalize(struct atmel_aes_dev *dd);
@@ -1471,7 +1462,7 @@ atmel_aes_gcm_ctx_cast(struct atmel_aes_base_ctx *ctx)
 
 static int atmel_aes_gcm_ghash(struct atmel_aes_dev *dd,
 			       const u32 *data, size_t datalen,
-			       const u32 *ghash_in, u32 *ghash_out,
+			       const __be32 *ghash_in, __be32 *ghash_out,
 			       atmel_aes_fn_t resume)
 {
 	struct atmel_aes_gcm_ctx *ctx = atmel_aes_gcm_ctx_cast(dd->ctx);
@@ -1558,7 +1549,7 @@ static int atmel_aes_gcm_start(struct atmel_aes_dev *dd)
 
 	memcpy(data, iv, ivsize);
 	memset(data + ivsize, 0, padlen + sizeof(u64));
-	((u64 *)(data + datalen))[-1] = cpu_to_be64(ivsize * 8);
+	((__be64 *)(data + datalen))[-1] = cpu_to_be64(ivsize * 8);
 
 	return atmel_aes_gcm_ghash(dd, (const u32 *)data, datalen,
 				   NULL, ctx->j0, atmel_aes_gcm_process);
@@ -1591,7 +1582,7 @@ static int atmel_aes_gcm_length(struct atmel_aes_dev *dd)
 {
 	struct atmel_aes_gcm_ctx *ctx = atmel_aes_gcm_ctx_cast(dd->ctx);
 	struct aead_request *req = aead_request_cast(dd->areq);
-	u32 j0_lsw, *j0 = ctx->j0;
+	__be32 j0_lsw, *j0 = ctx->j0;
 	size_t padlen;
 
 	/* Write incr32(J0) into IV. */
@@ -1674,7 +1665,7 @@ static int atmel_aes_gcm_tag_init(struct atmel_aes_dev *dd)
 {
 	struct atmel_aes_gcm_ctx *ctx = atmel_aes_gcm_ctx_cast(dd->ctx);
 	struct aead_request *req = aead_request_cast(dd->areq);
-	u64 *data = dd->buf;
+	__be64 *data = dd->buf;
 
 	if (likely(dd->flags & AES_FLAGS_GTAGEN)) {
 		if (!(atmel_aes_read(dd, AES_ISR) & AES_INT_TAGRDY)) {
@@ -1857,8 +1848,8 @@ static int atmel_aes_xts_process_data(struct atmel_aes_dev *dd);
 static int atmel_aes_xts_start(struct atmel_aes_dev *dd)
 {
 	struct atmel_aes_xts_ctx *ctx = atmel_aes_xts_ctx_cast(dd->ctx);
-	struct ablkcipher_request *req = ablkcipher_request_cast(dd->areq);
-	struct atmel_aes_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct skcipher_request *req = skcipher_request_cast(dd->areq);
+	struct atmel_aes_reqctx *rctx = skcipher_request_ctx(req);
 	unsigned long flags;
 	int err;
 
@@ -1868,7 +1859,7 @@ static int atmel_aes_xts_start(struct atmel_aes_dev *dd)
 	if (err)
 		return atmel_aes_complete(dd, err);
 
-	/* Compute the tweak value from req->info with ecb(aes). */
+	/* Compute the tweak value from req->iv with ecb(aes). */
 	flags = dd->flags;
 	dd->flags &= ~AES_FLAGS_MODE_MASK;
 	dd->flags |= (AES_FLAGS_ECB | AES_FLAGS_ENCRYPT);
@@ -1876,16 +1867,16 @@ static int atmel_aes_xts_start(struct atmel_aes_dev *dd)
 				 ctx->key2, ctx->base.keylen);
 	dd->flags = flags;
 
-	atmel_aes_write_block(dd, AES_IDATAR(0), req->info);
+	atmel_aes_write_block(dd, AES_IDATAR(0), req->iv);
 	return atmel_aes_wait_for_data_ready(dd, atmel_aes_xts_process_data);
 }
 
 static int atmel_aes_xts_process_data(struct atmel_aes_dev *dd)
 {
-	struct ablkcipher_request *req = ablkcipher_request_cast(dd->areq);
-	bool use_dma = (req->nbytes >= ATMEL_AES_DMA_THRESHOLD);
+	struct skcipher_request *req = skcipher_request_cast(dd->areq);
+	bool use_dma = (req->cryptlen >= ATMEL_AES_DMA_THRESHOLD);
 	u32 tweak[AES_BLOCK_SIZE / sizeof(u32)];
-	static const u32 one[AES_BLOCK_SIZE / sizeof(u32)] = {cpu_to_le32(1), };
+	static const __le32 one[AES_BLOCK_SIZE / sizeof(u32)] = {cpu_to_le32(1), };
 	u8 *tweak_bytes = (u8 *)tweak;
 	int i;
 
@@ -1908,20 +1899,21 @@ static int atmel_aes_xts_process_data(struct atmel_aes_dev *dd)
 	atmel_aes_write_block(dd, AES_TWR(0), tweak);
 	atmel_aes_write_block(dd, AES_ALPHAR(0), one);
 	if (use_dma)
-		return atmel_aes_dma_start(dd, req->src, req->dst, req->nbytes,
+		return atmel_aes_dma_start(dd, req->src, req->dst,
+					   req->cryptlen,
 					   atmel_aes_transfer_complete);
 
-	return atmel_aes_cpu_start(dd, req->src, req->dst, req->nbytes,
+	return atmel_aes_cpu_start(dd, req->src, req->dst, req->cryptlen,
 				   atmel_aes_transfer_complete);
 }
 
-static int atmel_aes_xts_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int atmel_aes_xts_setkey(struct crypto_skcipher *tfm, const u8 *key,
 				unsigned int keylen)
 {
-	struct atmel_aes_xts_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct atmel_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 	int err;
 
-	err = xts_check_key(crypto_ablkcipher_tfm(tfm), key, keylen);
+	err = xts_check_key(crypto_skcipher_tfm(tfm), key, keylen);
 	if (err)
 		return err;
 
@@ -1932,48 +1924,46 @@ static int atmel_aes_xts_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 	return 0;
 }
 
-static int atmel_aes_xts_encrypt(struct ablkcipher_request *req)
+static int atmel_aes_xts_encrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_XTS | AES_FLAGS_ENCRYPT);
 }
 
-static int atmel_aes_xts_decrypt(struct ablkcipher_request *req)
+static int atmel_aes_xts_decrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_XTS);
 }
 
-static int atmel_aes_xts_cra_init(struct crypto_tfm *tfm)
+static int atmel_aes_xts_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct atmel_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct atmel_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct atmel_aes_reqctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct atmel_aes_reqctx));
 	ctx->base.start = atmel_aes_xts_start;
 
 	return 0;
 }
 
-static struct crypto_alg aes_xts_alg = {
-	.cra_name		= "xts(aes)",
-	.cra_driver_name	= "atmel-xts-aes",
-	.cra_priority		= ATMEL_AES_PRIORITY,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_aes_xts_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_aes_xts_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= 2 * AES_MIN_KEY_SIZE,
-		.max_keysize	= 2 * AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= atmel_aes_xts_setkey,
-		.encrypt	= atmel_aes_xts_encrypt,
-		.decrypt	= atmel_aes_xts_decrypt,
-	}
+static struct skcipher_alg aes_xts_alg = {
+	.base.cra_name		= "xts(aes)",
+	.base.cra_driver_name	= "atmel-xts-aes",
+	.base.cra_priority	= ATMEL_AES_PRIORITY,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_aes_xts_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= 2 * AES_MIN_KEY_SIZE,
+	.max_keysize		= 2 * AES_MAX_KEY_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= atmel_aes_xts_setkey,
+	.encrypt		= atmel_aes_xts_encrypt,
+	.decrypt		= atmel_aes_xts_decrypt,
+	.init			= atmel_aes_xts_init_tfm,
 };
 
-#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC
+#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC)
 /* authenc aead functions */
 
 static int atmel_aes_authenc_start(struct atmel_aes_dev *dd);
@@ -2041,7 +2031,7 @@ static int atmel_aes_authenc_transfer(struct atmel_aes_dev *dd, int err,
 	struct atmel_aes_authenc_reqctx *rctx = aead_request_ctx(req);
 	bool enc = atmel_aes_is_encrypt(dd);
 	struct scatterlist *src, *dst;
-	u32 iv[AES_BLOCK_SIZE / sizeof(u32)];
+	__be32 iv[AES_BLOCK_SIZE / sizeof(u32)];
 	u32 emr;
 
 	if (is_async)
@@ -2460,23 +2450,23 @@ static void atmel_aes_unregister_algs(struct atmel_aes_dev *dd)
 {
 	int i;
 
-#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC
+#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC)
 	if (dd->caps.has_authenc)
 		for (i = 0; i < ARRAY_SIZE(aes_authenc_algs); i++)
 			crypto_unregister_aead(&aes_authenc_algs[i]);
 #endif
 
 	if (dd->caps.has_xts)
-		crypto_unregister_alg(&aes_xts_alg);
+		crypto_unregister_skcipher(&aes_xts_alg);
 
 	if (dd->caps.has_gcm)
 		crypto_unregister_aead(&aes_gcm_alg);
 
 	if (dd->caps.has_cfb64)
-		crypto_unregister_alg(&aes_cfb64_alg);
+		crypto_unregister_skcipher(&aes_cfb64_alg);
 
 	for (i = 0; i < ARRAY_SIZE(aes_algs); i++)
-		crypto_unregister_alg(&aes_algs[i]);
+		crypto_unregister_skcipher(&aes_algs[i]);
 }
 
 static int atmel_aes_register_algs(struct atmel_aes_dev *dd)
@@ -2484,13 +2474,13 @@ static int atmel_aes_register_algs(struct atmel_aes_dev *dd)
 	int err, i, j;
 
 	for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
-		err = crypto_register_alg(&aes_algs[i]);
+		err = crypto_register_skcipher(&aes_algs[i]);
 		if (err)
 			goto err_aes_algs;
 	}
 
 	if (dd->caps.has_cfb64) {
-		err = crypto_register_alg(&aes_cfb64_alg);
+		err = crypto_register_skcipher(&aes_cfb64_alg);
 		if (err)
 			goto err_aes_cfb64_alg;
 	}
@@ -2502,12 +2492,12 @@ static int atmel_aes_register_algs(struct atmel_aes_dev *dd)
 	}
 
 	if (dd->caps.has_xts) {
-		err = crypto_register_alg(&aes_xts_alg);
+		err = crypto_register_skcipher(&aes_xts_alg);
 		if (err)
 			goto err_aes_xts_alg;
 	}
 
-#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC
+#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC)
 	if (dd->caps.has_authenc) {
 		for (i = 0; i < ARRAY_SIZE(aes_authenc_algs); i++) {
 			err = crypto_register_aead(&aes_authenc_algs[i]);
@@ -2519,22 +2509,22 @@ static int atmel_aes_register_algs(struct atmel_aes_dev *dd)
 
 	return 0;
 
-#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC
+#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC)
 	/* i = ARRAY_SIZE(aes_authenc_algs); */
 err_aes_authenc_alg:
 	for (j = 0; j < i; j++)
 		crypto_unregister_aead(&aes_authenc_algs[j]);
-	crypto_unregister_alg(&aes_xts_alg);
+	crypto_unregister_skcipher(&aes_xts_alg);
 #endif
 err_aes_xts_alg:
 	crypto_unregister_aead(&aes_gcm_alg);
 err_aes_gcm_alg:
-	crypto_unregister_alg(&aes_cfb64_alg);
+	crypto_unregister_skcipher(&aes_cfb64_alg);
 err_aes_cfb64_alg:
 	i = ARRAY_SIZE(aes_algs);
 err_aes_algs:
 	for (j = 0; j < i; j++)
-		crypto_unregister_alg(&aes_algs[j]);
+		crypto_unregister_skcipher(&aes_algs[j]);
 
 	return err;
 }
@@ -2709,7 +2699,7 @@ static int atmel_aes_probe(struct platform_device *pdev)
 
 	atmel_aes_get_cap(aes_dd);
 
-#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC
+#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC)
 	if (aes_dd->caps.has_authenc && !atmel_sha_authenc_is_ready()) {
 		err = -EPROBE_DEFER;
 		goto iclk_unprepare;
diff --git a/drivers/crypto/atmel-authenc.h b/drivers/crypto/atmel-authenc.h
index cbd37a2edada..d6de810df44f 100644
--- a/drivers/crypto/atmel-authenc.h
+++ b/drivers/crypto/atmel-authenc.h
@@ -12,7 +12,7 @@
 #ifndef __ATMEL_AUTHENC_H__
 #define __ATMEL_AUTHENC_H__
 
-#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC
+#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC)
 
 #include <crypto/authenc.h>
 #include <crypto/hash.h>
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
index 84cb8748a795..8ea0e4bcde0d 100644
--- a/drivers/crypto/atmel-sha.c
+++ b/drivers/crypto/atmel-sha.c
@@ -360,7 +360,7 @@ static size_t atmel_sha_append_sg(struct atmel_sha_reqctx *ctx)
 static void atmel_sha_fill_padding(struct atmel_sha_reqctx *ctx, int length)
 {
 	unsigned int index, padlen;
-	u64 bits[2];
+	__be64 bits[2];
 	u64 size[2];
 
 	size[0] = ctx->digcnt[0];
@@ -2212,7 +2212,7 @@ static struct ahash_alg sha_hmac_algs[] = {
 },
 };
 
-#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC
+#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC)
 /* authenc functions */
 
 static int atmel_sha_authenc_init2(struct atmel_sha_dev *dd);
diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c
index 1a6c86ae6148..0c1f79b30fc1 100644
--- a/drivers/crypto/atmel-tdes.c
+++ b/drivers/crypto/atmel-tdes.c
@@ -36,6 +36,7 @@
 #include <crypto/internal/des.h>
 #include <crypto/hash.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
 #include <linux/platform_data/crypto-atmel.h>
 #include "atmel-tdes-regs.h"
 
@@ -72,7 +73,7 @@ struct atmel_tdes_ctx {
 	struct atmel_tdes_dev *dd;
 
 	int		keylen;
-	u32		key[3*DES_KEY_SIZE / sizeof(u32)];
+	u32		key[DES3_EDE_KEY_SIZE / sizeof(u32)];
 	unsigned long	flags;
 
 	u16		block_size;
@@ -80,6 +81,7 @@ struct atmel_tdes_ctx {
 
 struct atmel_tdes_reqctx {
 	unsigned long mode;
+	u8 lastc[DES_BLOCK_SIZE];
 };
 
 struct atmel_tdes_dma {
@@ -106,7 +108,7 @@ struct atmel_tdes_dev {
 	struct tasklet_struct	done_task;
 	struct tasklet_struct	queue_task;
 
-	struct ablkcipher_request	*req;
+	struct skcipher_request	*req;
 	size_t				total;
 
 	struct scatterlist	*in_sg;
@@ -307,8 +309,8 @@ static int atmel_tdes_write_ctrl(struct atmel_tdes_dev *dd)
 						dd->ctx->keylen >> 2);
 
 	if (((dd->flags & TDES_FLAGS_CBC) || (dd->flags & TDES_FLAGS_CFB) ||
-		(dd->flags & TDES_FLAGS_OFB)) && dd->req->info) {
-		atmel_tdes_write_n(dd, TDES_IV1R, dd->req->info, 2);
+		(dd->flags & TDES_FLAGS_OFB)) && dd->req->iv) {
+		atmel_tdes_write_n(dd, TDES_IV1R, (void *)dd->req->iv, 2);
 	}
 
 	return 0;
@@ -502,8 +504,8 @@ static int atmel_tdes_crypt_dma(struct crypto_tfm *tfm, dma_addr_t dma_addr_in,
 
 static int atmel_tdes_crypt_start(struct atmel_tdes_dev *dd)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(
-					crypto_ablkcipher_reqtfm(dd->req));
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(
+					crypto_skcipher_reqtfm(dd->req));
 	int err, fast = 0, in, out;
 	size_t count;
 	dma_addr_t addr_in, addr_out;
@@ -571,19 +573,45 @@ static int atmel_tdes_crypt_start(struct atmel_tdes_dev *dd)
 	return err;
 }
 
+static void
+atmel_tdes_set_iv_as_last_ciphertext_block(struct atmel_tdes_dev *dd)
+{
+	struct skcipher_request *req = dd->req;
+	struct atmel_tdes_reqctx *rctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
+	unsigned int ivsize = crypto_skcipher_ivsize(skcipher);
+
+	if (req->cryptlen < ivsize)
+		return;
+
+	if (rctx->mode & TDES_FLAGS_ENCRYPT) {
+		scatterwalk_map_and_copy(req->iv, req->dst,
+					 req->cryptlen - ivsize, ivsize, 0);
+	} else {
+		if (req->src == req->dst)
+			memcpy(req->iv, rctx->lastc, ivsize);
+		else
+			scatterwalk_map_and_copy(req->iv, req->src,
+						 req->cryptlen - ivsize,
+						 ivsize, 0);
+	}
+}
+
 static void atmel_tdes_finish_req(struct atmel_tdes_dev *dd, int err)
 {
-	struct ablkcipher_request *req = dd->req;
+	struct skcipher_request *req = dd->req;
 
 	clk_disable_unprepare(dd->iclk);
 
 	dd->flags &= ~TDES_FLAGS_BUSY;
 
+	atmel_tdes_set_iv_as_last_ciphertext_block(dd);
+
 	req->base.complete(&req->base, err);
 }
 
 static int atmel_tdes_handle_queue(struct atmel_tdes_dev *dd,
-			       struct ablkcipher_request *req)
+			       struct skcipher_request *req)
 {
 	struct crypto_async_request *async_req, *backlog;
 	struct atmel_tdes_ctx *ctx;
@@ -593,7 +621,7 @@ static int atmel_tdes_handle_queue(struct atmel_tdes_dev *dd,
 
 	spin_lock_irqsave(&dd->lock, flags);
 	if (req)
-		ret = ablkcipher_enqueue_request(&dd->queue, req);
+		ret = crypto_enqueue_request(&dd->queue, &req->base);
 	if (dd->flags & TDES_FLAGS_BUSY) {
 		spin_unlock_irqrestore(&dd->lock, flags);
 		return ret;
@@ -610,18 +638,18 @@ static int atmel_tdes_handle_queue(struct atmel_tdes_dev *dd,
 	if (backlog)
 		backlog->complete(backlog, -EINPROGRESS);
 
-	req = ablkcipher_request_cast(async_req);
+	req = skcipher_request_cast(async_req);
 
 	/* assign new request to device */
 	dd->req = req;
-	dd->total = req->nbytes;
+	dd->total = req->cryptlen;
 	dd->in_offset = 0;
 	dd->in_sg = req->src;
 	dd->out_offset = 0;
 	dd->out_sg = req->dst;
 
-	rctx = ablkcipher_request_ctx(req);
-	ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
+	rctx = skcipher_request_ctx(req);
+	ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req));
 	rctx->mode &= TDES_FLAGS_MODE_MASK;
 	dd->flags = (dd->flags & ~TDES_FLAGS_MODE_MASK) | rctx->mode;
 	dd->ctx = ctx;
@@ -665,32 +693,32 @@ static int atmel_tdes_crypt_dma_stop(struct atmel_tdes_dev *dd)
 	return err;
 }
 
-static int atmel_tdes_crypt(struct ablkcipher_request *req, unsigned long mode)
+static int atmel_tdes_crypt(struct skcipher_request *req, unsigned long mode)
 {
-	struct atmel_tdes_ctx *ctx = crypto_ablkcipher_ctx(
-			crypto_ablkcipher_reqtfm(req));
-	struct atmel_tdes_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
+	struct atmel_tdes_ctx *ctx = crypto_skcipher_ctx(skcipher);
+	struct atmel_tdes_reqctx *rctx = skcipher_request_ctx(req);
 
 	if (mode & TDES_FLAGS_CFB8) {
-		if (!IS_ALIGNED(req->nbytes, CFB8_BLOCK_SIZE)) {
+		if (!IS_ALIGNED(req->cryptlen, CFB8_BLOCK_SIZE)) {
 			pr_err("request size is not exact amount of CFB8 blocks\n");
 			return -EINVAL;
 		}
 		ctx->block_size = CFB8_BLOCK_SIZE;
 	} else if (mode & TDES_FLAGS_CFB16) {
-		if (!IS_ALIGNED(req->nbytes, CFB16_BLOCK_SIZE)) {
+		if (!IS_ALIGNED(req->cryptlen, CFB16_BLOCK_SIZE)) {
 			pr_err("request size is not exact amount of CFB16 blocks\n");
 			return -EINVAL;
 		}
 		ctx->block_size = CFB16_BLOCK_SIZE;
 	} else if (mode & TDES_FLAGS_CFB32) {
-		if (!IS_ALIGNED(req->nbytes, CFB32_BLOCK_SIZE)) {
+		if (!IS_ALIGNED(req->cryptlen, CFB32_BLOCK_SIZE)) {
 			pr_err("request size is not exact amount of CFB32 blocks\n");
 			return -EINVAL;
 		}
 		ctx->block_size = CFB32_BLOCK_SIZE;
 	} else {
-		if (!IS_ALIGNED(req->nbytes, DES_BLOCK_SIZE)) {
+		if (!IS_ALIGNED(req->cryptlen, DES_BLOCK_SIZE)) {
 			pr_err("request size is not exact amount of DES blocks\n");
 			return -EINVAL;
 		}
@@ -699,6 +727,15 @@ static int atmel_tdes_crypt(struct ablkcipher_request *req, unsigned long mode)
 
 	rctx->mode = mode;
 
+	if (!(mode & TDES_FLAGS_ENCRYPT) && req->src == req->dst) {
+		unsigned int ivsize = crypto_skcipher_ivsize(skcipher);
+
+		if (req->cryptlen >= ivsize)
+			scatterwalk_map_and_copy(rctx->lastc, req->src,
+						 req->cryptlen - ivsize,
+						 ivsize, 0);
+	}
+
 	return atmel_tdes_handle_queue(ctx->dd, req);
 }
 
@@ -770,13 +807,13 @@ static void atmel_tdes_dma_cleanup(struct atmel_tdes_dev *dd)
 	dma_release_channel(dd->dma_lch_out.chan);
 }
 
-static int atmel_des_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int atmel_des_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			   unsigned int keylen)
 {
-	struct atmel_tdes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct atmel_tdes_ctx *ctx = crypto_skcipher_ctx(tfm);
 	int err;
 
-	err = verify_ablkcipher_des_key(tfm, key);
+	err = verify_skcipher_des_key(tfm, key);
 	if (err)
 		return err;
 
@@ -786,13 +823,13 @@ static int atmel_des_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 	return 0;
 }
 
-static int atmel_tdes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int atmel_tdes_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			   unsigned int keylen)
 {
-	struct atmel_tdes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct atmel_tdes_ctx *ctx = crypto_skcipher_ctx(tfm);
 	int err;
 
-	err = verify_ablkcipher_des3_key(tfm, key);
+	err = verify_skcipher_des3_key(tfm, key);
 	if (err)
 		return err;
 
@@ -802,84 +839,84 @@ static int atmel_tdes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 	return 0;
 }
 
-static int atmel_tdes_ecb_encrypt(struct ablkcipher_request *req)
+static int atmel_tdes_ecb_encrypt(struct skcipher_request *req)
 {
 	return atmel_tdes_crypt(req, TDES_FLAGS_ENCRYPT);
 }
 
-static int atmel_tdes_ecb_decrypt(struct ablkcipher_request *req)
+static int atmel_tdes_ecb_decrypt(struct skcipher_request *req)
 {
 	return atmel_tdes_crypt(req, 0);
 }
 
-static int atmel_tdes_cbc_encrypt(struct ablkcipher_request *req)
+static int atmel_tdes_cbc_encrypt(struct skcipher_request *req)
 {
 	return atmel_tdes_crypt(req, TDES_FLAGS_ENCRYPT | TDES_FLAGS_CBC);
 }
 
-static int atmel_tdes_cbc_decrypt(struct ablkcipher_request *req)
+static int atmel_tdes_cbc_decrypt(struct skcipher_request *req)
 {
 	return atmel_tdes_crypt(req, TDES_FLAGS_CBC);
 }
-static int atmel_tdes_cfb_encrypt(struct ablkcipher_request *req)
+static int atmel_tdes_cfb_encrypt(struct skcipher_request *req)
 {
 	return atmel_tdes_crypt(req, TDES_FLAGS_ENCRYPT | TDES_FLAGS_CFB);
 }
 
-static int atmel_tdes_cfb_decrypt(struct ablkcipher_request *req)
+static int atmel_tdes_cfb_decrypt(struct skcipher_request *req)
 {
 	return atmel_tdes_crypt(req, TDES_FLAGS_CFB);
 }
 
-static int atmel_tdes_cfb8_encrypt(struct ablkcipher_request *req)
+static int atmel_tdes_cfb8_encrypt(struct skcipher_request *req)
 {
 	return atmel_tdes_crypt(req, TDES_FLAGS_ENCRYPT | TDES_FLAGS_CFB |
 						TDES_FLAGS_CFB8);
 }
 
-static int atmel_tdes_cfb8_decrypt(struct ablkcipher_request *req)
+static int atmel_tdes_cfb8_decrypt(struct skcipher_request *req)
 {
 	return atmel_tdes_crypt(req, TDES_FLAGS_CFB | TDES_FLAGS_CFB8);
 }
 
-static int atmel_tdes_cfb16_encrypt(struct ablkcipher_request *req)
+static int atmel_tdes_cfb16_encrypt(struct skcipher_request *req)
 {
 	return atmel_tdes_crypt(req, TDES_FLAGS_ENCRYPT | TDES_FLAGS_CFB |
 						TDES_FLAGS_CFB16);
 }
 
-static int atmel_tdes_cfb16_decrypt(struct ablkcipher_request *req)
+static int atmel_tdes_cfb16_decrypt(struct skcipher_request *req)
 {
 	return atmel_tdes_crypt(req, TDES_FLAGS_CFB | TDES_FLAGS_CFB16);
 }
 
-static int atmel_tdes_cfb32_encrypt(struct ablkcipher_request *req)
+static int atmel_tdes_cfb32_encrypt(struct skcipher_request *req)
 {
 	return atmel_tdes_crypt(req, TDES_FLAGS_ENCRYPT | TDES_FLAGS_CFB |
 						TDES_FLAGS_CFB32);
 }
 
-static int atmel_tdes_cfb32_decrypt(struct ablkcipher_request *req)
+static int atmel_tdes_cfb32_decrypt(struct skcipher_request *req)
 {
 	return atmel_tdes_crypt(req, TDES_FLAGS_CFB | TDES_FLAGS_CFB32);
 }
 
-static int atmel_tdes_ofb_encrypt(struct ablkcipher_request *req)
+static int atmel_tdes_ofb_encrypt(struct skcipher_request *req)
 {
 	return atmel_tdes_crypt(req, TDES_FLAGS_ENCRYPT | TDES_FLAGS_OFB);
 }
 
-static int atmel_tdes_ofb_decrypt(struct ablkcipher_request *req)
+static int atmel_tdes_ofb_decrypt(struct skcipher_request *req)
 {
 	return atmel_tdes_crypt(req, TDES_FLAGS_OFB);
 }
 
-static int atmel_tdes_cra_init(struct crypto_tfm *tfm)
+static int atmel_tdes_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct atmel_tdes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct atmel_tdes_ctx *ctx = crypto_skcipher_ctx(tfm);
 	struct atmel_tdes_dev *dd;
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct atmel_tdes_reqctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct atmel_tdes_reqctx));
 
 	dd = atmel_tdes_find_dev(ctx);
 	if (!dd)
@@ -888,204 +925,184 @@ static int atmel_tdes_cra_init(struct crypto_tfm *tfm)
 	return 0;
 }
 
-static struct crypto_alg tdes_algs[] = {
+static struct skcipher_alg tdes_algs[] = {
 {
-	.cra_name		= "ecb(des)",
-	.cra_driver_name	= "atmel-ecb-des",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
-	.cra_alignmask		= 0x7,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_tdes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= DES_KEY_SIZE,
-		.max_keysize	= DES_KEY_SIZE,
-		.setkey		= atmel_des_setkey,
-		.encrypt	= atmel_tdes_ecb_encrypt,
-		.decrypt	= atmel_tdes_ecb_decrypt,
-	}
+	.base.cra_name		= "ecb(des)",
+	.base.cra_driver_name	= "atmel-ecb-des",
+	.base.cra_priority	= 100,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= DES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_tdes_ctx),
+	.base.cra_alignmask	= 0x7,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_tdes_init_tfm,
+	.min_keysize		= DES_KEY_SIZE,
+	.max_keysize		= DES_KEY_SIZE,
+	.setkey			= atmel_des_setkey,
+	.encrypt		= atmel_tdes_ecb_encrypt,
+	.decrypt		= atmel_tdes_ecb_decrypt,
 },
 {
-	.cra_name		= "cbc(des)",
-	.cra_driver_name	= "atmel-cbc-des",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
-	.cra_alignmask		= 0x7,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_tdes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= DES_KEY_SIZE,
-		.max_keysize	= DES_KEY_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= atmel_des_setkey,
-		.encrypt	= atmel_tdes_cbc_encrypt,
-		.decrypt	= atmel_tdes_cbc_decrypt,
-	}
+	.base.cra_name		= "cbc(des)",
+	.base.cra_driver_name	= "atmel-cbc-des",
+	.base.cra_priority	= 100,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= DES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_tdes_ctx),
+	.base.cra_alignmask	= 0x7,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_tdes_init_tfm,
+	.min_keysize		= DES_KEY_SIZE,
+	.max_keysize		= DES_KEY_SIZE,
+	.ivsize			= DES_BLOCK_SIZE,
+	.setkey			= atmel_des_setkey,
+	.encrypt		= atmel_tdes_cbc_encrypt,
+	.decrypt		= atmel_tdes_cbc_decrypt,
 },
 {
-	.cra_name		= "cfb(des)",
-	.cra_driver_name	= "atmel-cfb-des",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
-	.cra_alignmask		= 0x7,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_tdes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= DES_KEY_SIZE,
-		.max_keysize	= DES_KEY_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= atmel_des_setkey,
-		.encrypt	= atmel_tdes_cfb_encrypt,
-		.decrypt	= atmel_tdes_cfb_decrypt,
-	}
+	.base.cra_name		= "cfb(des)",
+	.base.cra_driver_name	= "atmel-cfb-des",
+	.base.cra_priority	= 100,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= DES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_tdes_ctx),
+	.base.cra_alignmask	= 0x7,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_tdes_init_tfm,
+	.min_keysize		= DES_KEY_SIZE,
+	.max_keysize		= DES_KEY_SIZE,
+	.ivsize			= DES_BLOCK_SIZE,
+	.setkey			= atmel_des_setkey,
+	.encrypt		= atmel_tdes_cfb_encrypt,
+	.decrypt		= atmel_tdes_cfb_decrypt,
 },
 {
-	.cra_name		= "cfb8(des)",
-	.cra_driver_name	= "atmel-cfb8-des",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CFB8_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_tdes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= DES_KEY_SIZE,
-		.max_keysize	= DES_KEY_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= atmel_des_setkey,
-		.encrypt	= atmel_tdes_cfb8_encrypt,
-		.decrypt	= atmel_tdes_cfb8_decrypt,
-	}
+	.base.cra_name		= "cfb8(des)",
+	.base.cra_driver_name	= "atmel-cfb8-des",
+	.base.cra_priority	= 100,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= CFB8_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_tdes_ctx),
+	.base.cra_alignmask	= 0,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_tdes_init_tfm,
+	.min_keysize		= DES_KEY_SIZE,
+	.max_keysize		= DES_KEY_SIZE,
+	.ivsize			= DES_BLOCK_SIZE,
+	.setkey			= atmel_des_setkey,
+	.encrypt		= atmel_tdes_cfb8_encrypt,
+	.decrypt		= atmel_tdes_cfb8_decrypt,
 },
 {
-	.cra_name		= "cfb16(des)",
-	.cra_driver_name	= "atmel-cfb16-des",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CFB16_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
-	.cra_alignmask		= 0x1,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_tdes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= DES_KEY_SIZE,
-		.max_keysize	= DES_KEY_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= atmel_des_setkey,
-		.encrypt	= atmel_tdes_cfb16_encrypt,
-		.decrypt	= atmel_tdes_cfb16_decrypt,
-	}
+	.base.cra_name		= "cfb16(des)",
+	.base.cra_driver_name	= "atmel-cfb16-des",
+	.base.cra_priority	= 100,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= CFB16_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_tdes_ctx),
+	.base.cra_alignmask	= 0x1,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_tdes_init_tfm,
+	.min_keysize		= DES_KEY_SIZE,
+	.max_keysize		= DES_KEY_SIZE,
+	.ivsize			= DES_BLOCK_SIZE,
+	.setkey			= atmel_des_setkey,
+	.encrypt		= atmel_tdes_cfb16_encrypt,
+	.decrypt		= atmel_tdes_cfb16_decrypt,
 },
 {
-	.cra_name		= "cfb32(des)",
-	.cra_driver_name	= "atmel-cfb32-des",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CFB32_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
-	.cra_alignmask		= 0x3,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_tdes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= DES_KEY_SIZE,
-		.max_keysize	= DES_KEY_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= atmel_des_setkey,
-		.encrypt	= atmel_tdes_cfb32_encrypt,
-		.decrypt	= atmel_tdes_cfb32_decrypt,
-	}
+	.base.cra_name		= "cfb32(des)",
+	.base.cra_driver_name	= "atmel-cfb32-des",
+	.base.cra_priority	= 100,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= CFB32_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_tdes_ctx),
+	.base.cra_alignmask	= 0x3,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_tdes_init_tfm,
+	.min_keysize		= DES_KEY_SIZE,
+	.max_keysize		= DES_KEY_SIZE,
+	.ivsize			= DES_BLOCK_SIZE,
+	.setkey			= atmel_des_setkey,
+	.encrypt		= atmel_tdes_cfb32_encrypt,
+	.decrypt		= atmel_tdes_cfb32_decrypt,
 },
 {
-	.cra_name		= "ofb(des)",
-	.cra_driver_name	= "atmel-ofb-des",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
-	.cra_alignmask		= 0x7,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_tdes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= DES_KEY_SIZE,
-		.max_keysize	= DES_KEY_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= atmel_des_setkey,
-		.encrypt	= atmel_tdes_ofb_encrypt,
-		.decrypt	= atmel_tdes_ofb_decrypt,
-	}
+	.base.cra_name		= "ofb(des)",
+	.base.cra_driver_name	= "atmel-ofb-des",
+	.base.cra_priority	= 100,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= DES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_tdes_ctx),
+	.base.cra_alignmask	= 0x7,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_tdes_init_tfm,
+	.min_keysize		= DES_KEY_SIZE,
+	.max_keysize		= DES_KEY_SIZE,
+	.ivsize			= DES_BLOCK_SIZE,
+	.setkey			= atmel_des_setkey,
+	.encrypt		= atmel_tdes_ofb_encrypt,
+	.decrypt		= atmel_tdes_ofb_decrypt,
 },
 {
-	.cra_name		= "ecb(des3_ede)",
-	.cra_driver_name	= "atmel-ecb-tdes",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
-	.cra_alignmask		= 0x7,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_tdes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= 3 * DES_KEY_SIZE,
-		.max_keysize	= 3 * DES_KEY_SIZE,
-		.setkey		= atmel_tdes_setkey,
-		.encrypt	= atmel_tdes_ecb_encrypt,
-		.decrypt	= atmel_tdes_ecb_decrypt,
-	}
+	.base.cra_name		= "ecb(des3_ede)",
+	.base.cra_driver_name	= "atmel-ecb-tdes",
+	.base.cra_priority	= 100,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= DES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_tdes_ctx),
+	.base.cra_alignmask	= 0x7,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_tdes_init_tfm,
+	.min_keysize		= DES3_EDE_KEY_SIZE,
+	.max_keysize		= DES3_EDE_KEY_SIZE,
+	.setkey			= atmel_tdes_setkey,
+	.encrypt		= atmel_tdes_ecb_encrypt,
+	.decrypt		= atmel_tdes_ecb_decrypt,
 },
 {
-	.cra_name		= "cbc(des3_ede)",
-	.cra_driver_name	= "atmel-cbc-tdes",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
-	.cra_alignmask		= 0x7,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_tdes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= 3*DES_KEY_SIZE,
-		.max_keysize	= 3*DES_KEY_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= atmel_tdes_setkey,
-		.encrypt	= atmel_tdes_cbc_encrypt,
-		.decrypt	= atmel_tdes_cbc_decrypt,
-	}
+	.base.cra_name		= "cbc(des3_ede)",
+	.base.cra_driver_name	= "atmel-cbc-tdes",
+	.base.cra_priority	= 100,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= DES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_tdes_ctx),
+	.base.cra_alignmask	= 0x7,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_tdes_init_tfm,
+	.min_keysize		= DES3_EDE_KEY_SIZE,
+	.max_keysize		= DES3_EDE_KEY_SIZE,
+	.setkey			= atmel_tdes_setkey,
+	.encrypt		= atmel_tdes_cbc_encrypt,
+	.decrypt		= atmel_tdes_cbc_decrypt,
+	.ivsize			= DES_BLOCK_SIZE,
 },
 {
-	.cra_name		= "ofb(des3_ede)",
-	.cra_driver_name	= "atmel-ofb-tdes",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
-	.cra_alignmask		= 0x7,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_tdes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= 3*DES_KEY_SIZE,
-		.max_keysize	= 3*DES_KEY_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= atmel_tdes_setkey,
-		.encrypt	= atmel_tdes_ofb_encrypt,
-		.decrypt	= atmel_tdes_ofb_decrypt,
-	}
+	.base.cra_name		= "ofb(des3_ede)",
+	.base.cra_driver_name	= "atmel-ofb-tdes",
+	.base.cra_priority	= 100,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= DES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct atmel_tdes_ctx),
+	.base.cra_alignmask	= 0x7,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= atmel_tdes_init_tfm,
+	.min_keysize		= DES3_EDE_KEY_SIZE,
+	.max_keysize		= DES3_EDE_KEY_SIZE,
+	.setkey			= atmel_tdes_setkey,
+	.encrypt		= atmel_tdes_ofb_encrypt,
+	.decrypt		= atmel_tdes_ofb_decrypt,
+	.ivsize			= DES_BLOCK_SIZE,
 },
 };
 
@@ -1148,7 +1165,7 @@ static void atmel_tdes_unregister_algs(struct atmel_tdes_dev *dd)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(tdes_algs); i++)
-		crypto_unregister_alg(&tdes_algs[i]);
+		crypto_unregister_skcipher(&tdes_algs[i]);
 }
 
 static int atmel_tdes_register_algs(struct atmel_tdes_dev *dd)
@@ -1156,7 +1173,7 @@ static int atmel_tdes_register_algs(struct atmel_tdes_dev *dd)
 	int err, i, j;
 
 	for (i = 0; i < ARRAY_SIZE(tdes_algs); i++) {
-		err = crypto_register_alg(&tdes_algs[i]);
+		err = crypto_register_skcipher(&tdes_algs[i]);
 		if (err)
 			goto err_tdes_algs;
 	}
@@ -1165,7 +1182,7 @@ static int atmel_tdes_register_algs(struct atmel_tdes_dev *dd)
 
 err_tdes_algs:
 	for (j = 0; j < i; j++)
-		crypto_unregister_alg(&tdes_algs[j]);
+		crypto_unregister_skcipher(&tdes_algs[j]);
 
 	return err;
 }
diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c
index f85356a48e7e..1564a6f8c9cb 100644
--- a/drivers/crypto/bcm/cipher.c
+++ b/drivers/crypto/bcm/cipher.c
@@ -110,8 +110,8 @@ static u8 select_channel(void)
 }
 
 /**
- * spu_ablkcipher_rx_sg_create() - Build up the scatterlist of buffers used to
- * receive a SPU response message for an ablkcipher request. Includes buffers to
+ * spu_skcipher_rx_sg_create() - Build up the scatterlist of buffers used to
+ * receive a SPU response message for an skcipher request. Includes buffers to
  * catch SPU message headers and the response data.
  * @mssg:	mailbox message containing the receive sg
  * @rctx:	crypto request context
@@ -130,7 +130,7 @@ static u8 select_channel(void)
  *   < 0 if an error
  */
 static int
-spu_ablkcipher_rx_sg_create(struct brcm_message *mssg,
+spu_skcipher_rx_sg_create(struct brcm_message *mssg,
 			    struct iproc_reqctx_s *rctx,
 			    u8 rx_frag_num,
 			    unsigned int chunksize, u32 stat_pad_len)
@@ -179,8 +179,8 @@ spu_ablkcipher_rx_sg_create(struct brcm_message *mssg,
 }
 
 /**
- * spu_ablkcipher_tx_sg_create() - Build up the scatterlist of buffers used to
- * send a SPU request message for an ablkcipher request. Includes SPU message
+ * spu_skcipher_tx_sg_create() - Build up the scatterlist of buffers used to
+ * send a SPU request message for an skcipher request. Includes SPU message
  * headers and the request data.
  * @mssg:	mailbox message containing the transmit sg
  * @rctx:	crypto request context
@@ -198,7 +198,7 @@ spu_ablkcipher_rx_sg_create(struct brcm_message *mssg,
  *   < 0 if an error
  */
 static int
-spu_ablkcipher_tx_sg_create(struct brcm_message *mssg,
+spu_skcipher_tx_sg_create(struct brcm_message *mssg,
 			    struct iproc_reqctx_s *rctx,
 			    u8 tx_frag_num, unsigned int chunksize, u32 pad_len)
 {
@@ -283,7 +283,7 @@ static int mailbox_send_message(struct brcm_message *mssg, u32 flags,
 }
 
 /**
- * handle_ablkcipher_req() - Submit as much of a block cipher request as fits in
+ * handle_skcipher_req() - Submit as much of a block cipher request as fits in
  * a single SPU request message, starting at the current position in the request
  * data.
  * @rctx:	Crypto request context
@@ -300,12 +300,12 @@ static int mailbox_send_message(struct brcm_message *mssg, u32 flags,
  *			 asynchronously
  *         Any other value indicates an error
  */
-static int handle_ablkcipher_req(struct iproc_reqctx_s *rctx)
+static int handle_skcipher_req(struct iproc_reqctx_s *rctx)
 {
 	struct spu_hw *spu = &iproc_priv.spu;
 	struct crypto_async_request *areq = rctx->parent;
-	struct ablkcipher_request *req =
-	    container_of(areq, struct ablkcipher_request, base);
+	struct skcipher_request *req =
+	    container_of(areq, struct skcipher_request, base);
 	struct iproc_ctx_s *ctx = rctx->ctx;
 	struct spu_cipher_parms cipher_parms;
 	int err = 0;
@@ -468,7 +468,7 @@ static int handle_ablkcipher_req(struct iproc_reqctx_s *rctx)
 	    spu->spu_xts_tweak_in_payload())
 		rx_frag_num++;	/* extra sg to insert tweak */
 
-	err = spu_ablkcipher_rx_sg_create(mssg, rctx, rx_frag_num, chunksize,
+	err = spu_skcipher_rx_sg_create(mssg, rctx, rx_frag_num, chunksize,
 					  stat_pad_len);
 	if (err)
 		return err;
@@ -482,7 +482,7 @@ static int handle_ablkcipher_req(struct iproc_reqctx_s *rctx)
 	    spu->spu_xts_tweak_in_payload())
 		tx_frag_num++;	/* extra sg to insert tweak */
 
-	err = spu_ablkcipher_tx_sg_create(mssg, rctx, tx_frag_num, chunksize,
+	err = spu_skcipher_tx_sg_create(mssg, rctx, tx_frag_num, chunksize,
 					  pad_len);
 	if (err)
 		return err;
@@ -495,16 +495,16 @@ static int handle_ablkcipher_req(struct iproc_reqctx_s *rctx)
 }
 
 /**
- * handle_ablkcipher_resp() - Process a block cipher SPU response. Updates the
+ * handle_skcipher_resp() - Process a block cipher SPU response. Updates the
  * total received count for the request and updates global stats.
  * @rctx:	Crypto request context
  */
-static void handle_ablkcipher_resp(struct iproc_reqctx_s *rctx)
+static void handle_skcipher_resp(struct iproc_reqctx_s *rctx)
 {
 	struct spu_hw *spu = &iproc_priv.spu;
 #ifdef DEBUG
 	struct crypto_async_request *areq = rctx->parent;
-	struct ablkcipher_request *req = ablkcipher_request_cast(areq);
+	struct skcipher_request *req = skcipher_request_cast(areq);
 #endif
 	struct iproc_ctx_s *ctx = rctx->ctx;
 	u32 payload_len;
@@ -1685,8 +1685,8 @@ static void spu_rx_callback(struct mbox_client *cl, void *msg)
 
 	/* Process the SPU response message */
 	switch (rctx->ctx->alg->type) {
-	case CRYPTO_ALG_TYPE_ABLKCIPHER:
-		handle_ablkcipher_resp(rctx);
+	case CRYPTO_ALG_TYPE_SKCIPHER:
+		handle_skcipher_resp(rctx);
 		break;
 	case CRYPTO_ALG_TYPE_AHASH:
 		handle_ahash_resp(rctx);
@@ -1708,8 +1708,8 @@ static void spu_rx_callback(struct mbox_client *cl, void *msg)
 		spu_chunk_cleanup(rctx);
 
 		switch (rctx->ctx->alg->type) {
-		case CRYPTO_ALG_TYPE_ABLKCIPHER:
-			err = handle_ablkcipher_req(rctx);
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			err = handle_skcipher_req(rctx);
 			break;
 		case CRYPTO_ALG_TYPE_AHASH:
 			err = handle_ahash_req(rctx);
@@ -1739,7 +1739,7 @@ cb_finish:
 /* ==================== Kernel Cryptographic API ==================== */
 
 /**
- * ablkcipher_enqueue() - Handle ablkcipher encrypt or decrypt request.
+ * skcipher_enqueue() - Handle skcipher encrypt or decrypt request.
  * @req:	Crypto API request
  * @encrypt:	true if encrypting; false if decrypting
  *
@@ -1747,11 +1747,11 @@ cb_finish:
  *			asynchronously
  *	   < 0 if an error
  */
-static int ablkcipher_enqueue(struct ablkcipher_request *req, bool encrypt)
+static int skcipher_enqueue(struct skcipher_request *req, bool encrypt)
 {
-	struct iproc_reqctx_s *rctx = ablkcipher_request_ctx(req);
+	struct iproc_reqctx_s *rctx = skcipher_request_ctx(req);
 	struct iproc_ctx_s *ctx =
-	    crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
+	    crypto_skcipher_ctx(crypto_skcipher_reqtfm(req));
 	int err;
 
 	flow_log("%s() enc:%u\n", __func__, encrypt);
@@ -1761,7 +1761,7 @@ static int ablkcipher_enqueue(struct ablkcipher_request *req, bool encrypt)
 	rctx->parent = &req->base;
 	rctx->is_encrypt = encrypt;
 	rctx->bd_suppress = false;
-	rctx->total_todo = req->nbytes;
+	rctx->total_todo = req->cryptlen;
 	rctx->src_sent = 0;
 	rctx->total_sent = 0;
 	rctx->total_received = 0;
@@ -1782,15 +1782,15 @@ static int ablkcipher_enqueue(struct ablkcipher_request *req, bool encrypt)
 	    ctx->cipher.mode == CIPHER_MODE_GCM ||
 	    ctx->cipher.mode == CIPHER_MODE_CCM) {
 		rctx->iv_ctr_len =
-		    crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(req));
-		memcpy(rctx->msg_buf.iv_ctr, req->info, rctx->iv_ctr_len);
+		    crypto_skcipher_ivsize(crypto_skcipher_reqtfm(req));
+		memcpy(rctx->msg_buf.iv_ctr, req->iv, rctx->iv_ctr_len);
 	} else {
 		rctx->iv_ctr_len = 0;
 	}
 
 	/* Choose a SPU to process this request */
 	rctx->chan_idx = select_channel();
-	err = handle_ablkcipher_req(rctx);
+	err = handle_skcipher_req(rctx);
 	if (err != -EINPROGRESS)
 		/* synchronous result */
 		spu_chunk_cleanup(rctx);
@@ -1798,13 +1798,13 @@ static int ablkcipher_enqueue(struct ablkcipher_request *req, bool encrypt)
 	return err;
 }
 
-static int des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int des_setkey(struct crypto_skcipher *cipher, const u8 *key,
 		      unsigned int keylen)
 {
-	struct iproc_ctx_s *ctx = crypto_ablkcipher_ctx(cipher);
+	struct iproc_ctx_s *ctx = crypto_skcipher_ctx(cipher);
 	int err;
 
-	err = verify_ablkcipher_des_key(cipher, key);
+	err = verify_skcipher_des_key(cipher, key);
 	if (err)
 		return err;
 
@@ -1812,13 +1812,13 @@ static int des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	return 0;
 }
 
-static int threedes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int threedes_setkey(struct crypto_skcipher *cipher, const u8 *key,
 			   unsigned int keylen)
 {
-	struct iproc_ctx_s *ctx = crypto_ablkcipher_ctx(cipher);
+	struct iproc_ctx_s *ctx = crypto_skcipher_ctx(cipher);
 	int err;
 
-	err = verify_ablkcipher_des3_key(cipher, key);
+	err = verify_skcipher_des3_key(cipher, key);
 	if (err)
 		return err;
 
@@ -1826,10 +1826,10 @@ static int threedes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	return 0;
 }
 
-static int aes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int aes_setkey(struct crypto_skcipher *cipher, const u8 *key,
 		      unsigned int keylen)
 {
-	struct iproc_ctx_s *ctx = crypto_ablkcipher_ctx(cipher);
+	struct iproc_ctx_s *ctx = crypto_skcipher_ctx(cipher);
 
 	if (ctx->cipher.mode == CIPHER_MODE_XTS)
 		/* XTS includes two keys of equal length */
@@ -1846,7 +1846,7 @@ static int aes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 		ctx->cipher_type = CIPHER_TYPE_AES256;
 		break;
 	default:
-		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		crypto_skcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 	WARN_ON((ctx->max_payload != SPU_MAX_PAYLOAD_INF) &&
@@ -1854,10 +1854,10 @@ static int aes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	return 0;
 }
 
-static int rc4_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int rc4_setkey(struct crypto_skcipher *cipher, const u8 *key,
 		      unsigned int keylen)
 {
-	struct iproc_ctx_s *ctx = crypto_ablkcipher_ctx(cipher);
+	struct iproc_ctx_s *ctx = crypto_skcipher_ctx(cipher);
 	int i;
 
 	ctx->enckeylen = ARC4_MAX_KEY_SIZE + ARC4_STATE_SIZE;
@@ -1874,16 +1874,16 @@ static int rc4_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	return 0;
 }
 
-static int ablkcipher_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int skcipher_setkey(struct crypto_skcipher *cipher, const u8 *key,
 			     unsigned int keylen)
 {
 	struct spu_hw *spu = &iproc_priv.spu;
-	struct iproc_ctx_s *ctx = crypto_ablkcipher_ctx(cipher);
+	struct iproc_ctx_s *ctx = crypto_skcipher_ctx(cipher);
 	struct spu_cipher_parms cipher_parms;
 	u32 alloc_len = 0;
 	int err;
 
-	flow_log("ablkcipher_setkey() keylen: %d\n", keylen);
+	flow_log("skcipher_setkey() keylen: %d\n", keylen);
 	flow_dump("  key: ", key, keylen);
 
 	switch (ctx->cipher.alg) {
@@ -1926,7 +1926,7 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 		alloc_len = BCM_HDR_LEN + SPU2_HEADER_ALLOC_LEN;
 	memset(ctx->bcm_spu_req_hdr, 0, alloc_len);
 	cipher_parms.iv_buf = NULL;
-	cipher_parms.iv_len = crypto_ablkcipher_ivsize(cipher);
+	cipher_parms.iv_len = crypto_skcipher_ivsize(cipher);
 	flow_log("%s: iv_len %u\n", __func__, cipher_parms.iv_len);
 
 	cipher_parms.alg = ctx->cipher.alg;
@@ -1950,17 +1950,17 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	return 0;
 }
 
-static int ablkcipher_encrypt(struct ablkcipher_request *req)
+static int skcipher_encrypt(struct skcipher_request *req)
 {
-	flow_log("ablkcipher_encrypt() nbytes:%u\n", req->nbytes);
+	flow_log("skcipher_encrypt() nbytes:%u\n", req->cryptlen);
 
-	return ablkcipher_enqueue(req, true);
+	return skcipher_enqueue(req, true);
 }
 
-static int ablkcipher_decrypt(struct ablkcipher_request *req)
+static int skcipher_decrypt(struct skcipher_request *req)
 {
-	flow_log("ablkcipher_decrypt() nbytes:%u\n", req->nbytes);
-	return ablkcipher_enqueue(req, false);
+	flow_log("skcipher_decrypt() nbytes:%u\n", req->cryptlen);
+	return skcipher_enqueue(req, false);
 }
 
 static int ahash_enqueue(struct ahash_request *req)
@@ -3585,18 +3585,16 @@ static struct iproc_alg_s driver_algs[] = {
 	 .auth_first = 0,
 	 },
 
-/* ABLKCIPHER algorithms. */
+/* SKCIPHER algorithms. */
 	{
-	 .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-	 .alg.crypto = {
-			.cra_name = "ecb(arc4)",
-			.cra_driver_name = "ecb-arc4-iproc",
-			.cra_blocksize = ARC4_BLOCK_SIZE,
-			.cra_ablkcipher = {
-					   .min_keysize = ARC4_MIN_KEY_SIZE,
-					   .max_keysize = ARC4_MAX_KEY_SIZE,
-					   .ivsize = 0,
-					}
+	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
+	 .alg.skcipher = {
+			.base.cra_name = "ecb(arc4)",
+			.base.cra_driver_name = "ecb-arc4-iproc",
+			.base.cra_blocksize = ARC4_BLOCK_SIZE,
+			.min_keysize = ARC4_MIN_KEY_SIZE,
+			.max_keysize = ARC4_MAX_KEY_SIZE,
+			.ivsize = 0,
 			},
 	 .cipher_info = {
 			 .alg = CIPHER_ALG_RC4,
@@ -3608,16 +3606,14 @@ static struct iproc_alg_s driver_algs[] = {
 		       },
 	 },
 	{
-	 .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-	 .alg.crypto = {
-			.cra_name = "ofb(des)",
-			.cra_driver_name = "ofb-des-iproc",
-			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_ablkcipher = {
-					   .min_keysize = DES_KEY_SIZE,
-					   .max_keysize = DES_KEY_SIZE,
-					   .ivsize = DES_BLOCK_SIZE,
-					}
+	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
+	 .alg.skcipher = {
+			.base.cra_name = "ofb(des)",
+			.base.cra_driver_name = "ofb-des-iproc",
+			.base.cra_blocksize = DES_BLOCK_SIZE,
+			.min_keysize = DES_KEY_SIZE,
+			.max_keysize = DES_KEY_SIZE,
+			.ivsize = DES_BLOCK_SIZE,
 			},
 	 .cipher_info = {
 			 .alg = CIPHER_ALG_DES,
@@ -3629,16 +3625,14 @@ static struct iproc_alg_s driver_algs[] = {
 		       },
 	 },
 	{
-	 .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-	 .alg.crypto = {
-			.cra_name = "cbc(des)",
-			.cra_driver_name = "cbc-des-iproc",
-			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_ablkcipher = {
-					   .min_keysize = DES_KEY_SIZE,
-					   .max_keysize = DES_KEY_SIZE,
-					   .ivsize = DES_BLOCK_SIZE,
-					}
+	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
+	 .alg.skcipher = {
+			.base.cra_name = "cbc(des)",
+			.base.cra_driver_name = "cbc-des-iproc",
+			.base.cra_blocksize = DES_BLOCK_SIZE,
+			.min_keysize = DES_KEY_SIZE,
+			.max_keysize = DES_KEY_SIZE,
+			.ivsize = DES_BLOCK_SIZE,
 			},
 	 .cipher_info = {
 			 .alg = CIPHER_ALG_DES,
@@ -3650,16 +3644,14 @@ static struct iproc_alg_s driver_algs[] = {
 		       },
 	 },
 	{
-	 .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-	 .alg.crypto = {
-			.cra_name = "ecb(des)",
-			.cra_driver_name = "ecb-des-iproc",
-			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_ablkcipher = {
-					   .min_keysize = DES_KEY_SIZE,
-					   .max_keysize = DES_KEY_SIZE,
-					   .ivsize = 0,
-					}
+	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
+	 .alg.skcipher = {
+			.base.cra_name = "ecb(des)",
+			.base.cra_driver_name = "ecb-des-iproc",
+			.base.cra_blocksize = DES_BLOCK_SIZE,
+			.min_keysize = DES_KEY_SIZE,
+			.max_keysize = DES_KEY_SIZE,
+			.ivsize = 0,
 			},
 	 .cipher_info = {
 			 .alg = CIPHER_ALG_DES,
@@ -3671,16 +3663,14 @@ static struct iproc_alg_s driver_algs[] = {
 		       },
 	 },
 	{
-	 .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-	 .alg.crypto = {
-			.cra_name = "ofb(des3_ede)",
-			.cra_driver_name = "ofb-des3-iproc",
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_ablkcipher = {
-					   .min_keysize = DES3_EDE_KEY_SIZE,
-					   .max_keysize = DES3_EDE_KEY_SIZE,
-					   .ivsize = DES3_EDE_BLOCK_SIZE,
-					}
+	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
+	 .alg.skcipher = {
+			.base.cra_name = "ofb(des3_ede)",
+			.base.cra_driver_name = "ofb-des3-iproc",
+			.base.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.min_keysize = DES3_EDE_KEY_SIZE,
+			.max_keysize = DES3_EDE_KEY_SIZE,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
 			},
 	 .cipher_info = {
 			 .alg = CIPHER_ALG_3DES,
@@ -3692,16 +3682,14 @@ static struct iproc_alg_s driver_algs[] = {
 		       },
 	 },
 	{
-	 .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-	 .alg.crypto = {
-			.cra_name = "cbc(des3_ede)",
-			.cra_driver_name = "cbc-des3-iproc",
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_ablkcipher = {
-					   .min_keysize = DES3_EDE_KEY_SIZE,
-					   .max_keysize = DES3_EDE_KEY_SIZE,
-					   .ivsize = DES3_EDE_BLOCK_SIZE,
-					}
+	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
+	 .alg.skcipher = {
+			.base.cra_name = "cbc(des3_ede)",
+			.base.cra_driver_name = "cbc-des3-iproc",
+			.base.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.min_keysize = DES3_EDE_KEY_SIZE,
+			.max_keysize = DES3_EDE_KEY_SIZE,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
 			},
 	 .cipher_info = {
 			 .alg = CIPHER_ALG_3DES,
@@ -3713,16 +3701,14 @@ static struct iproc_alg_s driver_algs[] = {
 		       },
 	 },
 	{
-	 .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-	 .alg.crypto = {
-			.cra_name = "ecb(des3_ede)",
-			.cra_driver_name = "ecb-des3-iproc",
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_ablkcipher = {
-					   .min_keysize = DES3_EDE_KEY_SIZE,
-					   .max_keysize = DES3_EDE_KEY_SIZE,
-					   .ivsize = 0,
-					}
+	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
+	 .alg.skcipher = {
+			.base.cra_name = "ecb(des3_ede)",
+			.base.cra_driver_name = "ecb-des3-iproc",
+			.base.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.min_keysize = DES3_EDE_KEY_SIZE,
+			.max_keysize = DES3_EDE_KEY_SIZE,
+			.ivsize = 0,
 			},
 	 .cipher_info = {
 			 .alg = CIPHER_ALG_3DES,
@@ -3734,16 +3720,14 @@ static struct iproc_alg_s driver_algs[] = {
 		       },
 	 },
 	{
-	 .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-	 .alg.crypto = {
-			.cra_name = "ofb(aes)",
-			.cra_driver_name = "ofb-aes-iproc",
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_ablkcipher = {
-					   .min_keysize = AES_MIN_KEY_SIZE,
-					   .max_keysize = AES_MAX_KEY_SIZE,
-					   .ivsize = AES_BLOCK_SIZE,
-					}
+	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
+	 .alg.skcipher = {
+			.base.cra_name = "ofb(aes)",
+			.base.cra_driver_name = "ofb-aes-iproc",
+			.base.cra_blocksize = AES_BLOCK_SIZE,
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
 			},
 	 .cipher_info = {
 			 .alg = CIPHER_ALG_AES,
@@ -3755,16 +3739,14 @@ static struct iproc_alg_s driver_algs[] = {
 		       },
 	 },
 	{
-	 .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-	 .alg.crypto = {
-			.cra_name = "cbc(aes)",
-			.cra_driver_name = "cbc-aes-iproc",
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_ablkcipher = {
-					   .min_keysize = AES_MIN_KEY_SIZE,
-					   .max_keysize = AES_MAX_KEY_SIZE,
-					   .ivsize = AES_BLOCK_SIZE,
-					}
+	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
+	 .alg.skcipher = {
+			.base.cra_name = "cbc(aes)",
+			.base.cra_driver_name = "cbc-aes-iproc",
+			.base.cra_blocksize = AES_BLOCK_SIZE,
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
 			},
 	 .cipher_info = {
 			 .alg = CIPHER_ALG_AES,
@@ -3776,16 +3758,14 @@ static struct iproc_alg_s driver_algs[] = {
 		       },
 	 },
 	{
-	 .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-	 .alg.crypto = {
-			.cra_name = "ecb(aes)",
-			.cra_driver_name = "ecb-aes-iproc",
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_ablkcipher = {
-					   .min_keysize = AES_MIN_KEY_SIZE,
-					   .max_keysize = AES_MAX_KEY_SIZE,
-					   .ivsize = 0,
-					}
+	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
+	 .alg.skcipher = {
+			.base.cra_name = "ecb(aes)",
+			.base.cra_driver_name = "ecb-aes-iproc",
+			.base.cra_blocksize = AES_BLOCK_SIZE,
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = 0,
 			},
 	 .cipher_info = {
 			 .alg = CIPHER_ALG_AES,
@@ -3797,16 +3777,14 @@ static struct iproc_alg_s driver_algs[] = {
 		       },
 	 },
 	{
-	 .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-	 .alg.crypto = {
-			.cra_name = "ctr(aes)",
-			.cra_driver_name = "ctr-aes-iproc",
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_ablkcipher = {
-					   .min_keysize = AES_MIN_KEY_SIZE,
-					   .max_keysize = AES_MAX_KEY_SIZE,
-					   .ivsize = AES_BLOCK_SIZE,
-					}
+	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
+	 .alg.skcipher = {
+			.base.cra_name = "ctr(aes)",
+			.base.cra_driver_name = "ctr-aes-iproc",
+			.base.cra_blocksize = AES_BLOCK_SIZE,
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
 			},
 	 .cipher_info = {
 			 .alg = CIPHER_ALG_AES,
@@ -3818,16 +3796,14 @@ static struct iproc_alg_s driver_algs[] = {
 		       },
 	 },
 {
-	 .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-	 .alg.crypto = {
-			.cra_name = "xts(aes)",
-			.cra_driver_name = "xts-aes-iproc",
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_ablkcipher = {
-				.min_keysize = 2 * AES_MIN_KEY_SIZE,
-				.max_keysize = 2 * AES_MAX_KEY_SIZE,
-				.ivsize = AES_BLOCK_SIZE,
-				}
+	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
+	 .alg.skcipher = {
+			.base.cra_name = "xts(aes)",
+			.base.cra_driver_name = "xts-aes-iproc",
+			.base.cra_blocksize = AES_BLOCK_SIZE,
+			.min_keysize = 2 * AES_MIN_KEY_SIZE,
+			.max_keysize = 2 * AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
 			},
 	 .cipher_info = {
 			 .alg = CIPHER_ALG_AES,
@@ -4282,16 +4258,17 @@ static int generic_cra_init(struct crypto_tfm *tfm,
 	return 0;
 }
 
-static int ablkcipher_cra_init(struct crypto_tfm *tfm)
+static int skcipher_init_tfm(struct crypto_skcipher *skcipher)
 {
-	struct crypto_alg *alg = tfm->__crt_alg;
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher);
+	struct skcipher_alg *alg = crypto_skcipher_alg(skcipher);
 	struct iproc_alg_s *cipher_alg;
 
 	flow_log("%s()\n", __func__);
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct iproc_reqctx_s);
+	crypto_skcipher_set_reqsize(skcipher, sizeof(struct iproc_reqctx_s));
 
-	cipher_alg = container_of(alg, struct iproc_alg_s, alg.crypto);
+	cipher_alg = container_of(alg, struct iproc_alg_s, alg.skcipher);
 	return generic_cra_init(tfm, cipher_alg);
 }
 
@@ -4363,6 +4340,11 @@ static void generic_cra_exit(struct crypto_tfm *tfm)
 	atomic_dec(&iproc_priv.session_count);
 }
 
+static void skcipher_exit_tfm(struct crypto_skcipher *tfm)
+{
+	generic_cra_exit(crypto_skcipher_tfm(tfm));
+}
+
 static void aead_cra_exit(struct crypto_aead *aead)
 {
 	struct crypto_tfm *tfm = crypto_aead_tfm(aead);
@@ -4524,10 +4506,10 @@ static void spu_counters_init(void)
 	atomic_set(&iproc_priv.bad_icv, 0);
 }
 
-static int spu_register_ablkcipher(struct iproc_alg_s *driver_alg)
+static int spu_register_skcipher(struct iproc_alg_s *driver_alg)
 {
 	struct spu_hw *spu = &iproc_priv.spu;
-	struct crypto_alg *crypto = &driver_alg->alg.crypto;
+	struct skcipher_alg *crypto = &driver_alg->alg.skcipher;
 	int err;
 
 	/* SPU2 does not support RC4 */
@@ -4535,26 +4517,23 @@ static int spu_register_ablkcipher(struct iproc_alg_s *driver_alg)
 	    (spu->spu_type == SPU_TYPE_SPU2))
 		return 0;
 
-	crypto->cra_module = THIS_MODULE;
-	crypto->cra_priority = cipher_pri;
-	crypto->cra_alignmask = 0;
-	crypto->cra_ctxsize = sizeof(struct iproc_ctx_s);
-
-	crypto->cra_init = ablkcipher_cra_init;
-	crypto->cra_exit = generic_cra_exit;
-	crypto->cra_type = &crypto_ablkcipher_type;
-	crypto->cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC |
-				CRYPTO_ALG_KERN_DRIVER_ONLY;
+	crypto->base.cra_module = THIS_MODULE;
+	crypto->base.cra_priority = cipher_pri;
+	crypto->base.cra_alignmask = 0;
+	crypto->base.cra_ctxsize = sizeof(struct iproc_ctx_s);
+	crypto->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY;
 
-	crypto->cra_ablkcipher.setkey = ablkcipher_setkey;
-	crypto->cra_ablkcipher.encrypt = ablkcipher_encrypt;
-	crypto->cra_ablkcipher.decrypt = ablkcipher_decrypt;
+	crypto->init = skcipher_init_tfm;
+	crypto->exit = skcipher_exit_tfm;
+	crypto->setkey = skcipher_setkey;
+	crypto->encrypt = skcipher_encrypt;
+	crypto->decrypt = skcipher_decrypt;
 
-	err = crypto_register_alg(crypto);
+	err = crypto_register_skcipher(crypto);
 	/* Mark alg as having been registered, if successful */
 	if (err == 0)
 		driver_alg->registered = true;
-	pr_debug("  registered ablkcipher %s\n", crypto->cra_driver_name);
+	pr_debug("  registered skcipher %s\n", crypto->base.cra_driver_name);
 	return err;
 }
 
@@ -4649,8 +4628,8 @@ static int spu_algs_register(struct device *dev)
 
 	for (i = 0; i < ARRAY_SIZE(driver_algs); i++) {
 		switch (driver_algs[i].type) {
-		case CRYPTO_ALG_TYPE_ABLKCIPHER:
-			err = spu_register_ablkcipher(&driver_algs[i]);
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			err = spu_register_skcipher(&driver_algs[i]);
 			break;
 		case CRYPTO_ALG_TYPE_AHASH:
 			err = spu_register_ahash(&driver_algs[i]);
@@ -4680,8 +4659,8 @@ err_algs:
 		if (!driver_algs[j].registered)
 			continue;
 		switch (driver_algs[j].type) {
-		case CRYPTO_ALG_TYPE_ABLKCIPHER:
-			crypto_unregister_alg(&driver_algs[j].alg.crypto);
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			crypto_unregister_skcipher(&driver_algs[j].alg.skcipher);
 			driver_algs[j].registered = false;
 			break;
 		case CRYPTO_ALG_TYPE_AHASH:
@@ -4837,10 +4816,10 @@ static int bcm_spu_remove(struct platform_device *pdev)
 			continue;
 
 		switch (driver_algs[i].type) {
-		case CRYPTO_ALG_TYPE_ABLKCIPHER:
-			crypto_unregister_alg(&driver_algs[i].alg.crypto);
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			crypto_unregister_skcipher(&driver_algs[i].alg.skcipher);
 			dev_dbg(dev, "  unregistered cipher %s\n",
-				driver_algs[i].alg.crypto.cra_driver_name);
+				driver_algs[i].alg.skcipher.base.cra_driver_name);
 			driver_algs[i].registered = false;
 			break;
 		case CRYPTO_ALG_TYPE_AHASH:
diff --git a/drivers/crypto/bcm/cipher.h b/drivers/crypto/bcm/cipher.h
index 766452b24d0a..b6d83e3aa46c 100644
--- a/drivers/crypto/bcm/cipher.h
+++ b/drivers/crypto/bcm/cipher.h
@@ -1,3 +1,4 @@
+
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright 2016 Broadcom
@@ -11,6 +12,7 @@
 #include <linux/mailbox_client.h>
 #include <crypto/aes.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
 #include <crypto/aead.h>
 #include <crypto/arc4.h>
 #include <crypto/gcm.h>
@@ -102,7 +104,7 @@ struct auth_op {
 struct iproc_alg_s {
 	u32 type;
 	union {
-		struct crypto_alg crypto;
+		struct skcipher_alg skcipher;
 		struct ahash_alg hash;
 		struct aead_alg aead;
 	} alg;
@@ -149,7 +151,7 @@ struct spu_msg_buf {
 	u8 rx_stat[ALIGN(SPU_RX_STATUS_LEN, SPU_MSG_ALIGN)];
 
 	union {
-		/* Buffers only used for ablkcipher */
+		/* Buffers only used for skcipher */
 		struct {
 			/*
 			 * Field used for either SUPDT when RC4 is used
@@ -214,7 +216,7 @@ struct iproc_ctx_s {
 
 	/*
 	 * Buffer to hold SPU message header template. Template is created at
-	 * setkey time for ablkcipher requests, since most of the fields in the
+	 * setkey time for skcipher requests, since most of the fields in the
 	 * header are known at that time. At request time, just fill in a few
 	 * missing pieces related to length of data in the request and IVs, etc.
 	 */
@@ -256,7 +258,7 @@ struct iproc_reqctx_s {
 
 	/* total todo, rx'd, and sent for this request */
 	unsigned int total_todo;
-	unsigned int total_received;	/* only valid for ablkcipher */
+	unsigned int total_received;	/* only valid for skcipher */
 	unsigned int total_sent;
 
 	/*
diff --git a/drivers/crypto/bcm/spu2.c b/drivers/crypto/bcm/spu2.c
index 2add51024575..59abb5ecefa4 100644
--- a/drivers/crypto/bcm/spu2.c
+++ b/drivers/crypto/bcm/spu2.c
@@ -542,7 +542,7 @@ void spu2_dump_msg_hdr(u8 *buf, unsigned int buf_len)
 
 /**
  * spu2_fmd_init() - At setkey time, initialize the fixed meta data for
- * subsequent ablkcipher requests for this context.
+ * subsequent skcipher requests for this context.
  * @spu2_cipher_type:  Cipher algorithm
  * @spu2_mode:         Cipher mode
  * @cipher_key_len:    Length of cipher key, in bytes
@@ -1107,13 +1107,13 @@ u32 spu2_create_request(u8 *spu_hdr,
 }
 
 /**
- * spu_cipher_req_init() - Build an ablkcipher SPU2 request message header,
+ * spu_cipher_req_init() - Build an skcipher SPU2 request message header,
  * including FMD and OMD.
  * @spu_hdr:       Location of start of SPU request (FMD field)
  * @cipher_parms:  Parameters describing cipher request
  *
  * Called at setkey time to initialize a msg header that can be reused for all
- * subsequent ablkcipher requests. Construct the message starting at spu_hdr.
+ * subsequent skcipher requests. Construct the message starting at spu_hdr.
  * Caller should allocate this buffer in DMA-able memory at least
  * SPU_HEADER_ALLOC_LEN bytes long.
  *
diff --git a/drivers/crypto/caam/Kconfig b/drivers/crypto/caam/Kconfig
index 137ed3df0c74..87053e46c788 100644
--- a/drivers/crypto/caam/Kconfig
+++ b/drivers/crypto/caam/Kconfig
@@ -97,7 +97,7 @@ config CRYPTO_DEV_FSL_CAAM_CRYPTO_API
 	select CRYPTO_DEV_FSL_CAAM_CRYPTO_API_DESC
 	select CRYPTO_AEAD
 	select CRYPTO_AUTHENC
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_DES
 	help
 	  Selecting this will offload crypto for users of the
@@ -110,7 +110,7 @@ config CRYPTO_DEV_FSL_CAAM_CRYPTO_API_QI
 	default y
 	select CRYPTO_DEV_FSL_CAAM_CRYPTO_API_DESC
 	select CRYPTO_AUTHENC
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_DES
 	help
 	  Selecting this will use CAAM Queue Interface (QI) for sending
@@ -158,7 +158,7 @@ config CRYPTO_DEV_FSL_DPAA2_CAAM
 	select CRYPTO_DEV_FSL_CAAM_COMMON
 	select CRYPTO_DEV_FSL_CAAM_CRYPTO_API_DESC
 	select CRYPTO_DEV_FSL_CAAM_AHASH_API_DESC
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_AUTHENC
 	select CRYPTO_AEAD
 	select CRYPTO_HASH
diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c
index 83f96d4f86e0..6619c512ef1a 100644
--- a/drivers/crypto/caam/caampkc.c
+++ b/drivers/crypto/caam/caampkc.c
@@ -252,9 +252,9 @@ static struct rsa_edesc *rsa_edesc_alloc(struct akcipher_request *req,
 	gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
 		       GFP_KERNEL : GFP_ATOMIC;
 	int sg_flags = (flags == GFP_ATOMIC) ? SG_MITER_ATOMIC : 0;
-	int sgc;
 	int sec4_sg_index, sec4_sg_len = 0, sec4_sg_bytes;
 	int src_nents, dst_nents;
+	int mapped_src_nents, mapped_dst_nents;
 	unsigned int diff_size = 0;
 	int lzeros;
 
@@ -285,13 +285,27 @@ static struct rsa_edesc *rsa_edesc_alloc(struct akcipher_request *req,
 				     req_ctx->fixup_src_len);
 	dst_nents = sg_nents_for_len(req->dst, req->dst_len);
 
-	if (!diff_size && src_nents == 1)
+	mapped_src_nents = dma_map_sg(dev, req_ctx->fixup_src, src_nents,
+				      DMA_TO_DEVICE);
+	if (unlikely(!mapped_src_nents)) {
+		dev_err(dev, "unable to map source\n");
+		return ERR_PTR(-ENOMEM);
+	}
+	mapped_dst_nents = dma_map_sg(dev, req->dst, dst_nents,
+				      DMA_FROM_DEVICE);
+	if (unlikely(!mapped_dst_nents)) {
+		dev_err(dev, "unable to map destination\n");
+		goto src_fail;
+	}
+
+	if (!diff_size && mapped_src_nents == 1)
 		sec4_sg_len = 0; /* no need for an input hw s/g table */
 	else
-		sec4_sg_len = src_nents + !!diff_size;
+		sec4_sg_len = mapped_src_nents + !!diff_size;
 	sec4_sg_index = sec4_sg_len;
-	if (dst_nents > 1)
-		sec4_sg_len += pad_sg_nents(dst_nents);
+
+	if (mapped_dst_nents > 1)
+		sec4_sg_len += pad_sg_nents(mapped_dst_nents);
 	else
 		sec4_sg_len = pad_sg_nents(sec4_sg_len);
 
@@ -301,19 +315,7 @@ static struct rsa_edesc *rsa_edesc_alloc(struct akcipher_request *req,
 	edesc = kzalloc(sizeof(*edesc) + desclen + sec4_sg_bytes,
 			GFP_DMA | flags);
 	if (!edesc)
-		return ERR_PTR(-ENOMEM);
-
-	sgc = dma_map_sg(dev, req_ctx->fixup_src, src_nents, DMA_TO_DEVICE);
-	if (unlikely(!sgc)) {
-		dev_err(dev, "unable to map source\n");
-		goto src_fail;
-	}
-
-	sgc = dma_map_sg(dev, req->dst, dst_nents, DMA_FROM_DEVICE);
-	if (unlikely(!sgc)) {
-		dev_err(dev, "unable to map destination\n");
 		goto dst_fail;
-	}
 
 	edesc->sec4_sg = (void *)edesc + sizeof(*edesc) + desclen;
 	if (diff_size)
@@ -324,7 +326,7 @@ static struct rsa_edesc *rsa_edesc_alloc(struct akcipher_request *req,
 		sg_to_sec4_sg_last(req_ctx->fixup_src, req_ctx->fixup_src_len,
 				   edesc->sec4_sg + !!diff_size, 0);
 
-	if (dst_nents > 1)
+	if (mapped_dst_nents > 1)
 		sg_to_sec4_sg_last(req->dst, req->dst_len,
 				   edesc->sec4_sg + sec4_sg_index, 0);
 
@@ -335,6 +337,9 @@ static struct rsa_edesc *rsa_edesc_alloc(struct akcipher_request *req,
 	if (!sec4_sg_bytes)
 		return edesc;
 
+	edesc->mapped_src_nents = mapped_src_nents;
+	edesc->mapped_dst_nents = mapped_dst_nents;
+
 	edesc->sec4_sg_dma = dma_map_single(dev, edesc->sec4_sg,
 					    sec4_sg_bytes, DMA_TO_DEVICE);
 	if (dma_mapping_error(dev, edesc->sec4_sg_dma)) {
@@ -351,11 +356,11 @@ static struct rsa_edesc *rsa_edesc_alloc(struct akcipher_request *req,
 	return edesc;
 
 sec4_sg_fail:
-	dma_unmap_sg(dev, req->dst, dst_nents, DMA_FROM_DEVICE);
+	kfree(edesc);
 dst_fail:
-	dma_unmap_sg(dev, req_ctx->fixup_src, src_nents, DMA_TO_DEVICE);
+	dma_unmap_sg(dev, req->dst, dst_nents, DMA_FROM_DEVICE);
 src_fail:
-	kfree(edesc);
+	dma_unmap_sg(dev, req_ctx->fixup_src, src_nents, DMA_TO_DEVICE);
 	return ERR_PTR(-ENOMEM);
 }
 
@@ -383,15 +388,15 @@ static int set_rsa_pub_pdb(struct akcipher_request *req,
 		return -ENOMEM;
 	}
 
-	if (edesc->src_nents > 1) {
+	if (edesc->mapped_src_nents > 1) {
 		pdb->sgf |= RSA_PDB_SGF_F;
 		pdb->f_dma = edesc->sec4_sg_dma;
-		sec4_sg_index += edesc->src_nents;
+		sec4_sg_index += edesc->mapped_src_nents;
 	} else {
 		pdb->f_dma = sg_dma_address(req_ctx->fixup_src);
 	}
 
-	if (edesc->dst_nents > 1) {
+	if (edesc->mapped_dst_nents > 1) {
 		pdb->sgf |= RSA_PDB_SGF_G;
 		pdb->g_dma = edesc->sec4_sg_dma +
 			     sec4_sg_index * sizeof(struct sec4_sg_entry);
@@ -428,17 +433,18 @@ static int set_rsa_priv_f1_pdb(struct akcipher_request *req,
 		return -ENOMEM;
 	}
 
-	if (edesc->src_nents > 1) {
+	if (edesc->mapped_src_nents > 1) {
 		pdb->sgf |= RSA_PRIV_PDB_SGF_G;
 		pdb->g_dma = edesc->sec4_sg_dma;
-		sec4_sg_index += edesc->src_nents;
+		sec4_sg_index += edesc->mapped_src_nents;
+
 	} else {
 		struct caam_rsa_req_ctx *req_ctx = akcipher_request_ctx(req);
 
 		pdb->g_dma = sg_dma_address(req_ctx->fixup_src);
 	}
 
-	if (edesc->dst_nents > 1) {
+	if (edesc->mapped_dst_nents > 1) {
 		pdb->sgf |= RSA_PRIV_PDB_SGF_F;
 		pdb->f_dma = edesc->sec4_sg_dma +
 			     sec4_sg_index * sizeof(struct sec4_sg_entry);
@@ -493,17 +499,17 @@ static int set_rsa_priv_f2_pdb(struct akcipher_request *req,
 		goto unmap_tmp1;
 	}
 
-	if (edesc->src_nents > 1) {
+	if (edesc->mapped_src_nents > 1) {
 		pdb->sgf |= RSA_PRIV_PDB_SGF_G;
 		pdb->g_dma = edesc->sec4_sg_dma;
-		sec4_sg_index += edesc->src_nents;
+		sec4_sg_index += edesc->mapped_src_nents;
 	} else {
 		struct caam_rsa_req_ctx *req_ctx = akcipher_request_ctx(req);
 
 		pdb->g_dma = sg_dma_address(req_ctx->fixup_src);
 	}
 
-	if (edesc->dst_nents > 1) {
+	if (edesc->mapped_dst_nents > 1) {
 		pdb->sgf |= RSA_PRIV_PDB_SGF_F;
 		pdb->f_dma = edesc->sec4_sg_dma +
 			     sec4_sg_index * sizeof(struct sec4_sg_entry);
@@ -582,17 +588,17 @@ static int set_rsa_priv_f3_pdb(struct akcipher_request *req,
 		goto unmap_tmp1;
 	}
 
-	if (edesc->src_nents > 1) {
+	if (edesc->mapped_src_nents > 1) {
 		pdb->sgf |= RSA_PRIV_PDB_SGF_G;
 		pdb->g_dma = edesc->sec4_sg_dma;
-		sec4_sg_index += edesc->src_nents;
+		sec4_sg_index += edesc->mapped_src_nents;
 	} else {
 		struct caam_rsa_req_ctx *req_ctx = akcipher_request_ctx(req);
 
 		pdb->g_dma = sg_dma_address(req_ctx->fixup_src);
 	}
 
-	if (edesc->dst_nents > 1) {
+	if (edesc->mapped_dst_nents > 1) {
 		pdb->sgf |= RSA_PRIV_PDB_SGF_F;
 		pdb->f_dma = edesc->sec4_sg_dma +
 			     sec4_sg_index * sizeof(struct sec4_sg_entry);
diff --git a/drivers/crypto/caam/caampkc.h b/drivers/crypto/caam/caampkc.h
index 2c488c9a3812..c68fb4c03ee6 100644
--- a/drivers/crypto/caam/caampkc.h
+++ b/drivers/crypto/caam/caampkc.h
@@ -112,8 +112,10 @@ struct caam_rsa_req_ctx {
 
 /**
  * rsa_edesc - s/w-extended rsa descriptor
- * @src_nents     : number of segments in input scatterlist
- * @dst_nents     : number of segments in output scatterlist
+ * @src_nents     : number of segments in input s/w scatterlist
+ * @dst_nents     : number of segments in output s/w scatterlist
+ * @mapped_src_nents: number of segments in input h/w link table
+ * @mapped_dst_nents: number of segments in output h/w link table
  * @sec4_sg_bytes : length of h/w link table
  * @sec4_sg_dma   : dma address of h/w link table
  * @sec4_sg       : pointer to h/w link table
@@ -123,6 +125,8 @@ struct caam_rsa_req_ctx {
 struct rsa_edesc {
 	int src_nents;
 	int dst_nents;
+	int mapped_src_nents;
+	int mapped_dst_nents;
 	int sec4_sg_bytes;
 	dma_addr_t sec4_sg_dma;
 	struct sec4_sg_entry *sec4_sg;
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index db22777d59b4..d7c3c3805693 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -176,6 +176,73 @@ static inline int run_descriptor_deco0(struct device *ctrldev, u32 *desc,
 }
 
 /*
+ * deinstantiate_rng - builds and executes a descriptor on DECO0,
+ *		       which deinitializes the RNG block.
+ * @ctrldev - pointer to device
+ * @state_handle_mask - bitmask containing the instantiation status
+ *			for the RNG4 state handles which exist in
+ *			the RNG4 block: 1 if it's been instantiated
+ *
+ * Return: - 0 if no error occurred
+ *	   - -ENOMEM if there isn't enough memory to allocate the descriptor
+ *	   - -ENODEV if DECO0 couldn't be acquired
+ *	   - -EAGAIN if an error occurred when executing the descriptor
+ */
+static int deinstantiate_rng(struct device *ctrldev, int state_handle_mask)
+{
+	u32 *desc, status;
+	int sh_idx, ret = 0;
+
+	desc = kmalloc(CAAM_CMD_SZ * 3, GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	for (sh_idx = 0; sh_idx < RNG4_MAX_HANDLES; sh_idx++) {
+		/*
+		 * If the corresponding bit is set, then it means the state
+		 * handle was initialized by us, and thus it needs to be
+		 * deinitialized as well
+		 */
+		if ((1 << sh_idx) & state_handle_mask) {
+			/*
+			 * Create the descriptor for deinstantating this state
+			 * handle
+			 */
+			build_deinstantiation_desc(desc, sh_idx);
+
+			/* Try to run it through DECO0 */
+			ret = run_descriptor_deco0(ctrldev, desc, &status);
+
+			if (ret ||
+			    (status && status != JRSTA_SSRC_JUMP_HALT_CC)) {
+				dev_err(ctrldev,
+					"Failed to deinstantiate RNG4 SH%d\n",
+					sh_idx);
+				break;
+			}
+			dev_info(ctrldev, "Deinstantiated RNG4 SH%d\n", sh_idx);
+		}
+	}
+
+	kfree(desc);
+
+	return ret;
+}
+
+static void devm_deinstantiate_rng(void *data)
+{
+	struct device *ctrldev = data;
+	struct caam_drv_private *ctrlpriv = dev_get_drvdata(ctrldev);
+
+	/*
+	 * De-initialize RNG state handles initialized by this driver.
+	 * In case of SoCs with Management Complex, RNG is managed by MC f/w.
+	 */
+	if (ctrlpriv->rng4_sh_init)
+		deinstantiate_rng(ctrldev, ctrlpriv->rng4_sh_init);
+}
+
+/*
  * instantiate_rng - builds and executes a descriptor on DECO0,
  *		     which initializes the RNG block.
  * @ctrldev - pointer to device
@@ -247,99 +314,13 @@ static int instantiate_rng(struct device *ctrldev, int state_handle_mask,
 
 	kfree(desc);
 
-	return ret;
-}
-
-/*
- * deinstantiate_rng - builds and executes a descriptor on DECO0,
- *		       which deinitializes the RNG block.
- * @ctrldev - pointer to device
- * @state_handle_mask - bitmask containing the instantiation status
- *			for the RNG4 state handles which exist in
- *			the RNG4 block: 1 if it's been instantiated
- *
- * Return: - 0 if no error occurred
- *	   - -ENOMEM if there isn't enough memory to allocate the descriptor
- *	   - -ENODEV if DECO0 couldn't be acquired
- *	   - -EAGAIN if an error occurred when executing the descriptor
- */
-static int deinstantiate_rng(struct device *ctrldev, int state_handle_mask)
-{
-	u32 *desc, status;
-	int sh_idx, ret = 0;
-
-	desc = kmalloc(CAAM_CMD_SZ * 3, GFP_KERNEL);
-	if (!desc)
-		return -ENOMEM;
-
-	for (sh_idx = 0; sh_idx < RNG4_MAX_HANDLES; sh_idx++) {
-		/*
-		 * If the corresponding bit is set, then it means the state
-		 * handle was initialized by us, and thus it needs to be
-		 * deinitialized as well
-		 */
-		if ((1 << sh_idx) & state_handle_mask) {
-			/*
-			 * Create the descriptor for deinstantating this state
-			 * handle
-			 */
-			build_deinstantiation_desc(desc, sh_idx);
-
-			/* Try to run it through DECO0 */
-			ret = run_descriptor_deco0(ctrldev, desc, &status);
-
-			if (ret ||
-			    (status && status != JRSTA_SSRC_JUMP_HALT_CC)) {
-				dev_err(ctrldev,
-					"Failed to deinstantiate RNG4 SH%d\n",
-					sh_idx);
-				break;
-			}
-			dev_info(ctrldev, "Deinstantiated RNG4 SH%d\n", sh_idx);
-		}
-	}
-
-	kfree(desc);
+	if (!ret)
+		ret = devm_add_action_or_reset(ctrldev, devm_deinstantiate_rng,
+					       ctrldev);
 
 	return ret;
 }
 
-static int caam_remove(struct platform_device *pdev)
-{
-	struct device *ctrldev;
-	struct caam_drv_private *ctrlpriv;
-	struct caam_ctrl __iomem *ctrl;
-
-	ctrldev = &pdev->dev;
-	ctrlpriv = dev_get_drvdata(ctrldev);
-	ctrl = (struct caam_ctrl __iomem *)ctrlpriv->ctrl;
-
-	/* Remove platform devices under the crypto node */
-	of_platform_depopulate(ctrldev);
-
-#ifdef CONFIG_CAAM_QI
-	if (ctrlpriv->qi_init)
-		caam_qi_shutdown(ctrldev);
-#endif
-
-	/*
-	 * De-initialize RNG state handles initialized by this driver.
-	 * In case of SoCs with Management Complex, RNG is managed by MC f/w.
-	 */
-	if (!ctrlpriv->mc_en && ctrlpriv->rng4_sh_init)
-		deinstantiate_rng(ctrldev, ctrlpriv->rng4_sh_init);
-
-	/* Shut down debug views */
-#ifdef CONFIG_DEBUG_FS
-	debugfs_remove_recursive(ctrlpriv->dfs_root);
-#endif
-
-	/* Unmap controller region */
-	iounmap(ctrl);
-
-	return 0;
-}
-
 /*
  * kick_trng - sets the various parameters for enabling the initialization
  *	       of the RNG4 block in CAAM
@@ -568,6 +549,13 @@ static int init_clocks(struct device *dev, const struct caam_imx_data *data)
 	return devm_add_action_or_reset(dev, disable_clocks, ctrlpriv);
 }
 
+#ifdef CONFIG_DEBUG_FS
+static void caam_remove_debugfs(void *root)
+{
+	debugfs_remove_recursive(root);
+}
+#endif
+
 /* Probe routine for CAAM top (controller) level */
 static int caam_probe(struct platform_device *pdev)
 {
@@ -580,6 +568,7 @@ static int caam_probe(struct platform_device *pdev)
 	struct caam_drv_private *ctrlpriv;
 #ifdef CONFIG_DEBUG_FS
 	struct caam_perfmon *perfmon;
+	struct dentry *dfs_root;
 #endif
 	u32 scfgr, comp_params;
 	u8 rng_vid;
@@ -611,10 +600,11 @@ static int caam_probe(struct platform_device *pdev)
 
 	/* Get configuration properties from device tree */
 	/* First, get register page */
-	ctrl = of_iomap(nprop, 0);
-	if (!ctrl) {
+	ctrl = devm_of_iomap(dev, nprop, 0, NULL);
+	ret = PTR_ERR_OR_ZERO(ctrl);
+	if (ret) {
 		dev_err(dev, "caam: of_iomap() failed\n");
-		return -ENOMEM;
+		return ret;
 	}
 
 	caam_little_end = !(bool)(rd_reg32(&ctrl->perfmon.status) &
@@ -632,22 +622,18 @@ static int caam_probe(struct platform_device *pdev)
 	if (ctrlpriv->qi_present && !caam_dpaa2) {
 		ret = qman_is_probed();
 		if (!ret) {
-			ret = -EPROBE_DEFER;
-			goto iounmap_ctrl;
+			return -EPROBE_DEFER;
 		} else if (ret < 0) {
 			dev_err(dev, "failing probe due to qman probe error\n");
-			ret = -ENODEV;
-			goto iounmap_ctrl;
+			return -ENODEV;
 		}
 
 		ret = qman_portals_probed();
 		if (!ret) {
-			ret = -EPROBE_DEFER;
-			goto iounmap_ctrl;
+			return -EPROBE_DEFER;
 		} else if (ret < 0) {
 			dev_err(dev, "failing probe due to qman portals probe error\n");
-			ret = -ENODEV;
-			goto iounmap_ctrl;
+			return -ENODEV;
 		}
 	}
 #endif
@@ -722,7 +708,7 @@ static int caam_probe(struct platform_device *pdev)
 	ret = dma_set_mask_and_coherent(dev, caam_get_dma_mask(dev));
 	if (ret) {
 		dev_err(dev, "dma_set_mask_and_coherent failed (%d)\n", ret);
-		goto iounmap_ctrl;
+		return ret;
 	}
 
 	ctrlpriv->era = caam_get_era(ctrl);
@@ -736,8 +722,12 @@ static int caam_probe(struct platform_device *pdev)
 	 */
 	perfmon = (struct caam_perfmon __force *)&ctrl->perfmon;
 
-	ctrlpriv->dfs_root = debugfs_create_dir(dev_name(dev), NULL);
-	ctrlpriv->ctl = debugfs_create_dir("ctl", ctrlpriv->dfs_root);
+	dfs_root = debugfs_create_dir(dev_name(dev), NULL);
+	ret = devm_add_action_or_reset(dev, caam_remove_debugfs, dfs_root);
+	if (ret)
+		return ret;
+
+	ctrlpriv->ctl = debugfs_create_dir("ctl", dfs_root);
 #endif
 
 	/* Check to see if (DPAA 1.x) QI present. If so, enable */
@@ -757,12 +747,6 @@ static int caam_probe(struct platform_device *pdev)
 #endif
 	}
 
-	ret = of_platform_populate(nprop, caam_match, NULL, dev);
-	if (ret) {
-		dev_err(dev, "JR platform devices creation error\n");
-		goto shutdown_qi;
-	}
-
 	ring = 0;
 	for_each_available_child_of_node(nprop, np)
 		if (of_device_is_compatible(np, "fsl,sec-v4.0-job-ring") ||
@@ -779,8 +763,7 @@ static int caam_probe(struct platform_device *pdev)
 	/* If no QI and no rings specified, quit and go home */
 	if ((!ctrlpriv->qi_present) && (!ctrlpriv->total_jobrs)) {
 		dev_err(dev, "no queues configured, terminating\n");
-		ret = -ENOMEM;
-		goto caam_remove;
+		return -ENOMEM;
 	}
 
 	if (ctrlpriv->era < 10)
@@ -843,7 +826,7 @@ static int caam_probe(struct platform_device *pdev)
 		} while ((ret == -EAGAIN) && (ent_delay < RTSDCTL_ENT_DLY_MAX));
 		if (ret) {
 			dev_err(dev, "failed to instantiate RNG");
-			goto caam_remove;
+			return ret;
 		}
 		/*
 		 * Set handles init'ed by this module as the complement of the
@@ -916,19 +899,11 @@ static int caam_probe(struct platform_device *pdev)
 	debugfs_create_blob("tdsk", S_IRUSR | S_IRGRP | S_IROTH, ctrlpriv->ctl,
 			    &ctrlpriv->ctl_tdsk_wrap);
 #endif
-	return 0;
 
-caam_remove:
-	caam_remove(pdev);
-	return ret;
+	ret = devm_of_platform_populate(dev);
+	if (ret)
+		dev_err(dev, "JR platform devices creation error\n");
 
-shutdown_qi:
-#ifdef CONFIG_CAAM_QI
-	if (ctrlpriv->qi_init)
-		caam_qi_shutdown(dev);
-#endif
-iounmap_ctrl:
-	iounmap(ctrl);
 	return ret;
 }
 
@@ -938,7 +913,6 @@ static struct platform_driver caam_driver = {
 		.of_match_table = caam_match,
 	},
 	.probe       = caam_probe,
-	.remove      = caam_remove,
 };
 
 module_platform_driver(caam_driver);
diff --git a/drivers/crypto/caam/intern.h b/drivers/crypto/caam/intern.h
index 731b06becd9c..c7c10c90464b 100644
--- a/drivers/crypto/caam/intern.h
+++ b/drivers/crypto/caam/intern.h
@@ -81,9 +81,6 @@ struct caam_drv_private {
 	 */
 	u8 total_jobrs;		/* Total Job Rings in device */
 	u8 qi_present;		/* Nonzero if QI present in device */
-#ifdef CONFIG_CAAM_QI
-	u8 qi_init;		/* Nonzero if QI has been initialized */
-#endif
 	u8 mc_en;		/* Nonzero if MC f/w is active */
 	int secvio_irq;		/* Security violation interrupt number */
 	int virt_en;		/* Virtualization enabled in CAAM */
@@ -102,7 +99,6 @@ struct caam_drv_private {
 	 * variables at runtime.
 	 */
 #ifdef CONFIG_DEBUG_FS
-	struct dentry *dfs_root;
 	struct dentry *ctl; /* controller dir */
 	struct debugfs_blob_wrapper ctl_kek_wrap, ctl_tkek_wrap, ctl_tdsk_wrap;
 #endif
diff --git a/drivers/crypto/caam/qi.c b/drivers/crypto/caam/qi.c
index 378f627e1d64..dacf2fa4aa8e 100644
--- a/drivers/crypto/caam/qi.c
+++ b/drivers/crypto/caam/qi.c
@@ -500,9 +500,10 @@ void caam_drv_ctx_rel(struct caam_drv_ctx *drv_ctx)
 }
 EXPORT_SYMBOL(caam_drv_ctx_rel);
 
-void caam_qi_shutdown(struct device *qidev)
+static void caam_qi_shutdown(void *data)
 {
 	int i;
+	struct device *qidev = data;
 	struct caam_qi_priv *priv = &qipriv;
 	const cpumask_t *cpus = qman_affine_cpus();
 
@@ -761,7 +762,10 @@ int caam_qi_init(struct platform_device *caam_pdev)
 			    &times_congested, &caam_fops_u64_ro);
 #endif
 
-	ctrlpriv->qi_init = 1;
+	err = devm_add_action_or_reset(qidev, caam_qi_shutdown, ctrlpriv);
+	if (err)
+		return err;
+
 	dev_info(qidev, "Linux CAAM Queue I/F driver initialised\n");
 	return 0;
 }
diff --git a/drivers/crypto/caam/qi.h b/drivers/crypto/caam/qi.h
index db0549549e3b..848958951f68 100644
--- a/drivers/crypto/caam/qi.h
+++ b/drivers/crypto/caam/qi.h
@@ -147,7 +147,6 @@ int caam_drv_ctx_update(struct caam_drv_ctx *drv_ctx, u32 *sh_desc);
 void caam_drv_ctx_rel(struct caam_drv_ctx *drv_ctx);
 
 int caam_qi_init(struct platform_device *pdev);
-void caam_qi_shutdown(struct device *dev);
 
 /**
  * qi_cache_alloc - Allocate buffers from CAAM-QI cache
diff --git a/drivers/crypto/cavium/cpt/cptvf_algs.c b/drivers/crypto/cavium/cpt/cptvf_algs.c
index 596ce28b957d..1ad66677d88e 100644
--- a/drivers/crypto/cavium/cpt/cptvf_algs.c
+++ b/drivers/crypto/cavium/cpt/cptvf_algs.c
@@ -92,15 +92,15 @@ static inline void update_output_data(struct cpt_request_info *req_info,
 	}
 }
 
-static inline u32 create_ctx_hdr(struct ablkcipher_request *req, u32 enc,
+static inline u32 create_ctx_hdr(struct skcipher_request *req, u32 enc,
 				 u32 *argcnt)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct cvm_enc_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct cvm_req_ctx *rctx = ablkcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct cvm_enc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct cvm_req_ctx *rctx = skcipher_request_ctx(req);
 	struct fc_context *fctx = &rctx->fctx;
 	u64 *offset_control = &rctx->control_word;
-	u32 enc_iv_len = crypto_ablkcipher_ivsize(tfm);
+	u32 enc_iv_len = crypto_skcipher_ivsize(tfm);
 	struct cpt_request_info *req_info = &rctx->cpt_req;
 	u64 *ctrl_flags = NULL;
 
@@ -115,7 +115,7 @@ static inline u32 create_ctx_hdr(struct ablkcipher_request *req, u32 enc,
 	else
 		req_info->req.opcode.s.minor = 3;
 
-	req_info->req.param1 = req->nbytes; /* Encryption Data length */
+	req_info->req.param1 = req->cryptlen; /* Encryption Data length */
 	req_info->req.param2 = 0; /*Auth data length */
 
 	fctx->enc.enc_ctrl.e.enc_cipher = ctx->cipher_type;
@@ -147,32 +147,32 @@ static inline u32 create_ctx_hdr(struct ablkcipher_request *req, u32 enc,
 	return 0;
 }
 
-static inline u32 create_input_list(struct ablkcipher_request  *req, u32 enc,
+static inline u32 create_input_list(struct skcipher_request  *req, u32 enc,
 				    u32 enc_iv_len)
 {
-	struct cvm_req_ctx *rctx = ablkcipher_request_ctx(req);
+	struct cvm_req_ctx *rctx = skcipher_request_ctx(req);
 	struct cpt_request_info *req_info = &rctx->cpt_req;
 	u32 argcnt =  0;
 
 	create_ctx_hdr(req, enc, &argcnt);
-	update_input_iv(req_info, req->info, enc_iv_len, &argcnt);
-	update_input_data(req_info, req->src, req->nbytes, &argcnt);
+	update_input_iv(req_info, req->iv, enc_iv_len, &argcnt);
+	update_input_data(req_info, req->src, req->cryptlen, &argcnt);
 	req_info->incnt = argcnt;
 
 	return 0;
 }
 
-static inline void store_cb_info(struct ablkcipher_request *req,
+static inline void store_cb_info(struct skcipher_request *req,
 				 struct cpt_request_info *req_info)
 {
 	req_info->callback = (void *)cvm_callback;
 	req_info->callback_arg = (void *)&req->base;
 }
 
-static inline void create_output_list(struct ablkcipher_request *req,
+static inline void create_output_list(struct skcipher_request *req,
 				      u32 enc_iv_len)
 {
-	struct cvm_req_ctx *rctx = ablkcipher_request_ctx(req);
+	struct cvm_req_ctx *rctx = skcipher_request_ctx(req);
 	struct cpt_request_info *req_info = &rctx->cpt_req;
 	u32 argcnt = 0;
 
@@ -184,16 +184,16 @@ static inline void create_output_list(struct ablkcipher_request *req,
 	 * [ 16 Bytes/     [   Request Enc/Dec/ DATA Len AES CBC ]
 	 */
 	/* Reading IV information */
-	update_output_iv(req_info, req->info, enc_iv_len, &argcnt);
-	update_output_data(req_info, req->dst, req->nbytes, &argcnt);
+	update_output_iv(req_info, req->iv, enc_iv_len, &argcnt);
+	update_output_data(req_info, req->dst, req->cryptlen, &argcnt);
 	req_info->outcnt = argcnt;
 }
 
-static inline int cvm_enc_dec(struct ablkcipher_request *req, u32 enc)
+static inline int cvm_enc_dec(struct skcipher_request *req, u32 enc)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct cvm_req_ctx *rctx = ablkcipher_request_ctx(req);
-	u32 enc_iv_len = crypto_ablkcipher_ivsize(tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct cvm_req_ctx *rctx = skcipher_request_ctx(req);
+	u32 enc_iv_len = crypto_skcipher_ivsize(tfm);
 	struct fc_context *fctx = &rctx->fctx;
 	struct cpt_request_info *req_info = &rctx->cpt_req;
 	void *cdev = NULL;
@@ -217,20 +217,20 @@ static inline int cvm_enc_dec(struct ablkcipher_request *req, u32 enc)
 		return -EINPROGRESS;
 }
 
-static int cvm_encrypt(struct ablkcipher_request *req)
+static int cvm_encrypt(struct skcipher_request *req)
 {
 	return cvm_enc_dec(req, true);
 }
 
-static int cvm_decrypt(struct ablkcipher_request *req)
+static int cvm_decrypt(struct skcipher_request *req)
 {
 	return cvm_enc_dec(req, false);
 }
 
-static int cvm_xts_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int cvm_xts_setkey(struct crypto_skcipher *cipher, const u8 *key,
 		   u32 keylen)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(cipher);
 	struct cvm_enc_ctx *ctx = crypto_tfm_ctx(tfm);
 	int err;
 	const u8 *key1 = key;
@@ -284,10 +284,10 @@ static int cvm_validate_keylen(struct cvm_enc_ctx *ctx, u32 keylen)
 	return -EINVAL;
 }
 
-static int cvm_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int cvm_setkey(struct crypto_skcipher *cipher, const u8 *key,
 		      u32 keylen, u8 cipher_type)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(cipher);
 	struct cvm_enc_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	ctx->cipher_type = cipher_type;
@@ -295,183 +295,159 @@ static int cvm_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 		memcpy(ctx->enc_key, key, keylen);
 		return 0;
 	} else {
-		crypto_ablkcipher_set_flags(cipher,
+		crypto_skcipher_set_flags(cipher,
 					    CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 }
 
-static int cvm_cbc_aes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int cvm_cbc_aes_setkey(struct crypto_skcipher *cipher, const u8 *key,
 			      u32 keylen)
 {
 	return cvm_setkey(cipher, key, keylen, AES_CBC);
 }
 
-static int cvm_ecb_aes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int cvm_ecb_aes_setkey(struct crypto_skcipher *cipher, const u8 *key,
 			      u32 keylen)
 {
 	return cvm_setkey(cipher, key, keylen, AES_ECB);
 }
 
-static int cvm_cfb_aes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int cvm_cfb_aes_setkey(struct crypto_skcipher *cipher, const u8 *key,
 			      u32 keylen)
 {
 	return cvm_setkey(cipher, key, keylen, AES_CFB);
 }
 
-static int cvm_cbc_des3_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int cvm_cbc_des3_setkey(struct crypto_skcipher *cipher, const u8 *key,
 			       u32 keylen)
 {
-	return verify_ablkcipher_des3_key(cipher, key) ?:
+	return verify_skcipher_des3_key(cipher, key) ?:
 	       cvm_setkey(cipher, key, keylen, DES3_CBC);
 }
 
-static int cvm_ecb_des3_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int cvm_ecb_des3_setkey(struct crypto_skcipher *cipher, const u8 *key,
 			       u32 keylen)
 {
-	return verify_ablkcipher_des3_key(cipher, key) ?:
+	return verify_skcipher_des3_key(cipher, key) ?:
 	       cvm_setkey(cipher, key, keylen, DES3_ECB);
 }
 
-static int cvm_enc_dec_init(struct crypto_tfm *tfm)
+static int cvm_enc_dec_init(struct crypto_skcipher *tfm)
 {
-	tfm->crt_ablkcipher.reqsize = sizeof(struct cvm_req_ctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct cvm_req_ctx));
+
 	return 0;
 }
 
-static struct crypto_alg algs[] = { {
-	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize = AES_BLOCK_SIZE,
-	.cra_ctxsize = sizeof(struct cvm_enc_ctx),
-	.cra_alignmask = 7,
-	.cra_priority = 4001,
-	.cra_name = "xts(aes)",
-	.cra_driver_name = "cavium-xts-aes",
-	.cra_type = &crypto_ablkcipher_type,
-	.cra_u = {
-		.ablkcipher = {
-			.ivsize = AES_BLOCK_SIZE,
-			.min_keysize = 2 * AES_MIN_KEY_SIZE,
-			.max_keysize = 2 * AES_MAX_KEY_SIZE,
-			.setkey = cvm_xts_setkey,
-			.encrypt = cvm_encrypt,
-			.decrypt = cvm_decrypt,
-		},
-	},
-	.cra_init = cvm_enc_dec_init,
-	.cra_module = THIS_MODULE,
+static struct skcipher_alg algs[] = { {
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct cvm_enc_ctx),
+	.base.cra_alignmask	= 7,
+	.base.cra_priority	= 4001,
+	.base.cra_name		= "xts(aes)",
+	.base.cra_driver_name	= "cavium-xts-aes",
+	.base.cra_module	= THIS_MODULE,
+
+	.ivsize			= AES_BLOCK_SIZE,
+	.min_keysize		= 2 * AES_MIN_KEY_SIZE,
+	.max_keysize		= 2 * AES_MAX_KEY_SIZE,
+	.setkey			= cvm_xts_setkey,
+	.encrypt		= cvm_encrypt,
+	.decrypt		= cvm_decrypt,
+	.init			= cvm_enc_dec_init,
 }, {
-	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize = AES_BLOCK_SIZE,
-	.cra_ctxsize = sizeof(struct cvm_enc_ctx),
-	.cra_alignmask = 7,
-	.cra_priority = 4001,
-	.cra_name = "cbc(aes)",
-	.cra_driver_name = "cavium-cbc-aes",
-	.cra_type = &crypto_ablkcipher_type,
-	.cra_u = {
-		.ablkcipher = {
-			.ivsize = AES_BLOCK_SIZE,
-			.min_keysize = AES_MIN_KEY_SIZE,
-			.max_keysize = AES_MAX_KEY_SIZE,
-			.setkey = cvm_cbc_aes_setkey,
-			.encrypt = cvm_encrypt,
-			.decrypt = cvm_decrypt,
-		},
-	},
-	.cra_init = cvm_enc_dec_init,
-	.cra_module = THIS_MODULE,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct cvm_enc_ctx),
+	.base.cra_alignmask	= 7,
+	.base.cra_priority	= 4001,
+	.base.cra_name		= "cbc(aes)",
+	.base.cra_driver_name	= "cavium-cbc-aes",
+	.base.cra_module	= THIS_MODULE,
+
+	.ivsize			= AES_BLOCK_SIZE,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= cvm_cbc_aes_setkey,
+	.encrypt		= cvm_encrypt,
+	.decrypt		= cvm_decrypt,
+	.init			= cvm_enc_dec_init,
 }, {
-	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize = AES_BLOCK_SIZE,
-	.cra_ctxsize = sizeof(struct cvm_enc_ctx),
-	.cra_alignmask = 7,
-	.cra_priority = 4001,
-	.cra_name = "ecb(aes)",
-	.cra_driver_name = "cavium-ecb-aes",
-	.cra_type = &crypto_ablkcipher_type,
-	.cra_u = {
-		.ablkcipher = {
-			.ivsize = AES_BLOCK_SIZE,
-			.min_keysize = AES_MIN_KEY_SIZE,
-			.max_keysize = AES_MAX_KEY_SIZE,
-			.setkey = cvm_ecb_aes_setkey,
-			.encrypt = cvm_encrypt,
-			.decrypt = cvm_decrypt,
-		},
-	},
-	.cra_init = cvm_enc_dec_init,
-	.cra_module = THIS_MODULE,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct cvm_enc_ctx),
+	.base.cra_alignmask	= 7,
+	.base.cra_priority	= 4001,
+	.base.cra_name		= "ecb(aes)",
+	.base.cra_driver_name	= "cavium-ecb-aes",
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= cvm_ecb_aes_setkey,
+	.encrypt		= cvm_encrypt,
+	.decrypt		= cvm_decrypt,
+	.init			= cvm_enc_dec_init,
 }, {
-	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize = AES_BLOCK_SIZE,
-	.cra_ctxsize = sizeof(struct cvm_enc_ctx),
-	.cra_alignmask = 7,
-	.cra_priority = 4001,
-	.cra_name = "cfb(aes)",
-	.cra_driver_name = "cavium-cfb-aes",
-	.cra_type = &crypto_ablkcipher_type,
-	.cra_u = {
-		.ablkcipher = {
-			.ivsize = AES_BLOCK_SIZE,
-			.min_keysize = AES_MIN_KEY_SIZE,
-			.max_keysize = AES_MAX_KEY_SIZE,
-			.setkey = cvm_cfb_aes_setkey,
-			.encrypt = cvm_encrypt,
-			.decrypt = cvm_decrypt,
-		},
-	},
-	.cra_init = cvm_enc_dec_init,
-	.cra_module = THIS_MODULE,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct cvm_enc_ctx),
+	.base.cra_alignmask	= 7,
+	.base.cra_priority	= 4001,
+	.base.cra_name		= "cfb(aes)",
+	.base.cra_driver_name	= "cavium-cfb-aes",
+	.base.cra_module	= THIS_MODULE,
+
+	.ivsize			= AES_BLOCK_SIZE,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= cvm_cfb_aes_setkey,
+	.encrypt		= cvm_encrypt,
+	.decrypt		= cvm_decrypt,
+	.init			= cvm_enc_dec_init,
 }, {
-	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-	.cra_ctxsize = sizeof(struct cvm_des3_ctx),
-	.cra_alignmask = 7,
-	.cra_priority = 4001,
-	.cra_name = "cbc(des3_ede)",
-	.cra_driver_name = "cavium-cbc-des3_ede",
-	.cra_type = &crypto_ablkcipher_type,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize = DES3_EDE_KEY_SIZE,
-			.max_keysize = DES3_EDE_KEY_SIZE,
-			.ivsize = DES_BLOCK_SIZE,
-			.setkey = cvm_cbc_des3_setkey,
-			.encrypt = cvm_encrypt,
-			.decrypt = cvm_decrypt,
-		},
-	},
-	.cra_init = cvm_enc_dec_init,
-	.cra_module = THIS_MODULE,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct cvm_des3_ctx),
+	.base.cra_alignmask	= 7,
+	.base.cra_priority	= 4001,
+	.base.cra_name		= "cbc(des3_ede)",
+	.base.cra_driver_name	= "cavium-cbc-des3_ede",
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= DES3_EDE_KEY_SIZE,
+	.max_keysize		= DES3_EDE_KEY_SIZE,
+	.ivsize			= DES_BLOCK_SIZE,
+	.setkey			= cvm_cbc_des3_setkey,
+	.encrypt		= cvm_encrypt,
+	.decrypt		= cvm_decrypt,
+	.init			= cvm_enc_dec_init,
 }, {
-	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-	.cra_ctxsize = sizeof(struct cvm_des3_ctx),
-	.cra_alignmask = 7,
-	.cra_priority = 4001,
-	.cra_name = "ecb(des3_ede)",
-	.cra_driver_name = "cavium-ecb-des3_ede",
-	.cra_type = &crypto_ablkcipher_type,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize = DES3_EDE_KEY_SIZE,
-			.max_keysize = DES3_EDE_KEY_SIZE,
-			.ivsize = DES_BLOCK_SIZE,
-			.setkey = cvm_ecb_des3_setkey,
-			.encrypt = cvm_encrypt,
-			.decrypt = cvm_decrypt,
-		},
-	},
-	.cra_init = cvm_enc_dec_init,
-	.cra_module = THIS_MODULE,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct cvm_des3_ctx),
+	.base.cra_alignmask	= 7,
+	.base.cra_priority	= 4001,
+	.base.cra_name		= "ecb(des3_ede)",
+	.base.cra_driver_name	= "cavium-ecb-des3_ede",
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= DES3_EDE_KEY_SIZE,
+	.max_keysize		= DES3_EDE_KEY_SIZE,
+	.ivsize			= DES_BLOCK_SIZE,
+	.setkey			= cvm_ecb_des3_setkey,
+	.encrypt		= cvm_encrypt,
+	.decrypt		= cvm_decrypt,
+	.init			= cvm_enc_dec_init,
 } };
 
 static inline int cav_register_algs(void)
 {
 	int err = 0;
 
-	err = crypto_register_algs(algs, ARRAY_SIZE(algs));
+	err = crypto_register_skciphers(algs, ARRAY_SIZE(algs));
 	if (err)
 		return err;
 
@@ -480,7 +456,7 @@ static inline int cav_register_algs(void)
 
 static inline void cav_unregister_algs(void)
 {
-	crypto_unregister_algs(algs, ARRAY_SIZE(algs));
+	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
 }
 
 int cvm_crypto_init(struct cpt_vf *cptvf)
diff --git a/drivers/crypto/cavium/nitrox/Kconfig b/drivers/crypto/cavium/nitrox/Kconfig
index 7b1e751bb9cd..7dc008332a81 100644
--- a/drivers/crypto/cavium/nitrox/Kconfig
+++ b/drivers/crypto/cavium/nitrox/Kconfig
@@ -4,7 +4,7 @@
 #
 config CRYPTO_DEV_NITROX
 	tristate
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_AES
 	select CRYPTO_LIB_DES
 	select FW_LOADER
diff --git a/drivers/crypto/cavium/nitrox/nitrox_aead.c b/drivers/crypto/cavium/nitrox/nitrox_aead.c
index e4841eb2a09f..6f80cc3b5c84 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_aead.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_aead.c
@@ -74,6 +74,25 @@ static int nitrox_aead_setauthsize(struct crypto_aead *aead,
 	return 0;
 }
 
+static int nitrox_aes_gcm_setauthsize(struct crypto_aead *aead,
+				      unsigned int authsize)
+{
+	switch (authsize) {
+	case 4:
+	case 8:
+	case 12:
+	case 13:
+	case 14:
+	case 15:
+	case 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return nitrox_aead_setauthsize(aead, authsize);
+}
+
 static int alloc_src_sglist(struct nitrox_kcrypt_request *nkreq,
 			    struct scatterlist *src, char *iv, int ivsize,
 			    int buflen)
@@ -186,6 +205,14 @@ static void nitrox_aead_callback(void *arg, int err)
 	areq->base.complete(&areq->base, err);
 }
 
+static inline bool nitrox_aes_gcm_assoclen_supported(unsigned int assoclen)
+{
+	if (assoclen <= 512)
+		return true;
+
+	return false;
+}
+
 static int nitrox_aes_gcm_enc(struct aead_request *areq)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
@@ -195,6 +222,9 @@ static int nitrox_aes_gcm_enc(struct aead_request *areq)
 	struct flexi_crypto_context *fctx = nctx->u.fctx;
 	int ret;
 
+	if (!nitrox_aes_gcm_assoclen_supported(areq->assoclen))
+		return -EINVAL;
+
 	memcpy(fctx->crypto.iv, areq->iv, GCM_AES_SALT_SIZE);
 
 	rctx->cryptlen = areq->cryptlen;
@@ -226,6 +256,9 @@ static int nitrox_aes_gcm_dec(struct aead_request *areq)
 	struct flexi_crypto_context *fctx = nctx->u.fctx;
 	int ret;
 
+	if (!nitrox_aes_gcm_assoclen_supported(areq->assoclen))
+		return -EINVAL;
+
 	memcpy(fctx->crypto.iv, areq->iv, GCM_AES_SALT_SIZE);
 
 	rctx->cryptlen = areq->cryptlen - aead->authsize;
@@ -492,13 +525,13 @@ static struct aead_alg nitrox_aeads[] = { {
 		.cra_driver_name = "n5_aes_gcm",
 		.cra_priority = PRIO,
 		.cra_flags = CRYPTO_ALG_ASYNC,
-		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_blocksize = 1,
 		.cra_ctxsize = sizeof(struct nitrox_crypto_ctx),
 		.cra_alignmask = 0,
 		.cra_module = THIS_MODULE,
 	},
 	.setkey = nitrox_aes_gcm_setkey,
-	.setauthsize = nitrox_aead_setauthsize,
+	.setauthsize = nitrox_aes_gcm_setauthsize,
 	.encrypt = nitrox_aes_gcm_enc,
 	.decrypt = nitrox_aes_gcm_dec,
 	.init = nitrox_aes_gcm_init,
@@ -511,7 +544,7 @@ static struct aead_alg nitrox_aeads[] = { {
 		.cra_driver_name = "n5_rfc4106",
 		.cra_priority = PRIO,
 		.cra_flags = CRYPTO_ALG_ASYNC,
-		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_blocksize = 1,
 		.cra_ctxsize = sizeof(struct nitrox_crypto_ctx),
 		.cra_alignmask = 0,
 		.cra_module = THIS_MODULE,
diff --git a/drivers/crypto/cavium/nitrox/nitrox_dev.h b/drivers/crypto/cavium/nitrox/nitrox_dev.h
index 2217a2736c8e..c2d0c23fb81b 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_dev.h
+++ b/drivers/crypto/cavium/nitrox/nitrox_dev.h
@@ -109,6 +109,13 @@ struct nitrox_q_vector {
 	};
 };
 
+enum mcode_type {
+	MCODE_TYPE_INVALID,
+	MCODE_TYPE_AE,
+	MCODE_TYPE_SE_SSL,
+	MCODE_TYPE_SE_IPSEC,
+};
+
 /**
  * mbox_msg - Mailbox message data
  * @type: message type
@@ -128,6 +135,14 @@ union mbox_msg {
 		u64 chipid: 8;
 		u64 vfid: 8;
 	} id;
+	struct {
+		u64 type: 2;
+		u64 opcode: 6;
+		u64 count: 4;
+		u64 info: 40;
+		u64 next_se_grp: 3;
+		u64 next_ae_grp: 3;
+	} mcode_info;
 };
 
 /**
diff --git a/drivers/crypto/cavium/nitrox/nitrox_main.c b/drivers/crypto/cavium/nitrox/nitrox_main.c
index bc924980e10c..c4632d84c9a1 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_main.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_main.c
@@ -103,8 +103,7 @@ static void write_to_ucd_unit(struct nitrox_device *ndev, u32 ucode_size,
 	offset = UCD_UCODE_LOAD_BLOCK_NUM;
 	nitrox_write_csr(ndev, offset, block_num);
 
-	code_size = ucode_size;
-	code_size = roundup(code_size, 8);
+	code_size = roundup(ucode_size, 16);
 	while (code_size) {
 		data = ucode_data[i];
 		/* write 8 bytes at a time */
@@ -220,11 +219,11 @@ static int nitrox_load_fw(struct nitrox_device *ndev)
 
 	/* write block number and firmware length
 	 * bit:<2:0> block number
-	 * bit:3 is set SE uses 32KB microcode
-	 * bit:3 is clear SE uses 64KB microcode
+	 * bit:3 is set AE uses 32KB microcode
+	 * bit:3 is clear AE uses 64KB microcode
 	 */
 	core_2_eid_val.value = 0ULL;
-	core_2_eid_val.ucode_blk = 0;
+	core_2_eid_val.ucode_blk = 2;
 	if (ucode_size <= CNN55XX_UCD_BLOCK_SIZE)
 		core_2_eid_val.ucode_len = 1;
 	else
diff --git a/drivers/crypto/cavium/nitrox/nitrox_mbx.c b/drivers/crypto/cavium/nitrox/nitrox_mbx.c
index 02ee95064841..b51b0449b478 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_mbx.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_mbx.c
@@ -25,6 +25,7 @@ enum mbx_msg_opcode {
 	MSG_OP_VF_UP,
 	MSG_OP_VF_DOWN,
 	MSG_OP_CHIPID_VFID,
+	MSG_OP_MCODE_INFO = 11,
 };
 
 struct pf2vf_work {
@@ -73,6 +74,13 @@ static void pf2vf_send_response(struct nitrox_device *ndev,
 		vfdev->nr_queues = 0;
 		atomic_set(&vfdev->state, __NDEV_NOT_READY);
 		break;
+	case MSG_OP_MCODE_INFO:
+		msg.data = 0;
+		msg.mcode_info.count = 2;
+		msg.mcode_info.info = MCODE_TYPE_SE_SSL | (MCODE_TYPE_AE << 5);
+		msg.mcode_info.next_se_grp = 1;
+		msg.mcode_info.next_ae_grp = 1;
+		break;
 	default:
 		msg.type = MBX_MSG_TYPE_NOP;
 		break;
diff --git a/drivers/crypto/cavium/nitrox/nitrox_req.h b/drivers/crypto/cavium/nitrox/nitrox_req.h
index f69ba02c4d25..12282c1b14f5 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_req.h
+++ b/drivers/crypto/cavium/nitrox/nitrox_req.h
@@ -10,6 +10,8 @@
 #define PENDING_SIG	0xFFFFFFFFFFFFFFFFUL
 #define PRIO 4001
 
+typedef void (*sereq_completion_t)(void *req, int err);
+
 /**
  * struct gphdr - General purpose Header
  * @param0: first parameter.
@@ -203,12 +205,14 @@ struct nitrox_crypto_ctx {
 		struct flexi_crypto_context *fctx;
 	} u;
 	struct crypto_ctx_hdr *chdr;
+	sereq_completion_t callback;
 };
 
 struct nitrox_kcrypt_request {
 	struct se_crypto_request creq;
 	u8 *src;
 	u8 *dst;
+	u8 *iv_out;
 };
 
 /**
diff --git a/drivers/crypto/cavium/nitrox/nitrox_skcipher.c b/drivers/crypto/cavium/nitrox/nitrox_skcipher.c
index 3cdce1f0f257..97af4d50d003 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_skcipher.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_skcipher.c
@@ -6,6 +6,7 @@
 
 #include <crypto/aes.h>
 #include <crypto/skcipher.h>
+#include <crypto/scatterwalk.h>
 #include <crypto/ctr.h>
 #include <crypto/internal/des.h>
 #include <crypto/xts.h>
@@ -47,6 +48,63 @@ static enum flexi_cipher flexi_cipher_type(const char *name)
 	return cipher->value;
 }
 
+static void free_src_sglist(struct skcipher_request *skreq)
+{
+	struct nitrox_kcrypt_request *nkreq = skcipher_request_ctx(skreq);
+
+	kfree(nkreq->src);
+}
+
+static void free_dst_sglist(struct skcipher_request *skreq)
+{
+	struct nitrox_kcrypt_request *nkreq = skcipher_request_ctx(skreq);
+
+	kfree(nkreq->dst);
+}
+
+static void nitrox_skcipher_callback(void *arg, int err)
+{
+	struct skcipher_request *skreq = arg;
+
+	free_src_sglist(skreq);
+	free_dst_sglist(skreq);
+	if (err) {
+		pr_err_ratelimited("request failed status 0x%0x\n", err);
+		err = -EINVAL;
+	}
+
+	skcipher_request_complete(skreq, err);
+}
+
+static void nitrox_cbc_cipher_callback(void *arg, int err)
+{
+	struct skcipher_request *skreq = arg;
+	struct nitrox_kcrypt_request *nkreq = skcipher_request_ctx(skreq);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(skreq);
+	int ivsize = crypto_skcipher_ivsize(cipher);
+	unsigned int start = skreq->cryptlen - ivsize;
+
+	if (err) {
+		nitrox_skcipher_callback(arg, err);
+		return;
+	}
+
+	if (nkreq->creq.ctrl.s.arg == ENCRYPT) {
+		scatterwalk_map_and_copy(skreq->iv, skreq->dst, start, ivsize,
+					 0);
+	} else {
+		if (skreq->src != skreq->dst) {
+			scatterwalk_map_and_copy(skreq->iv, skreq->src, start,
+						 ivsize, 0);
+		} else {
+			memcpy(skreq->iv, nkreq->iv_out, ivsize);
+			kfree(nkreq->iv_out);
+		}
+	}
+
+	nitrox_skcipher_callback(arg, err);
+}
+
 static int nitrox_skcipher_init(struct crypto_skcipher *tfm)
 {
 	struct nitrox_crypto_ctx *nctx = crypto_skcipher_ctx(tfm);
@@ -63,6 +121,8 @@ static int nitrox_skcipher_init(struct crypto_skcipher *tfm)
 		nitrox_put_device(nctx->ndev);
 		return -ENOMEM;
 	}
+
+	nctx->callback = nitrox_skcipher_callback;
 	nctx->chdr = chdr;
 	nctx->u.ctx_handle = (uintptr_t)((u8 *)chdr->vaddr +
 					 sizeof(struct ctx_hdr));
@@ -71,6 +131,19 @@ static int nitrox_skcipher_init(struct crypto_skcipher *tfm)
 	return 0;
 }
 
+static int nitrox_cbc_init(struct crypto_skcipher *tfm)
+{
+	int err;
+	struct nitrox_crypto_ctx *nctx = crypto_skcipher_ctx(tfm);
+
+	err = nitrox_skcipher_init(tfm);
+	if (err)
+		return err;
+
+	nctx->callback = nitrox_cbc_cipher_callback;
+	return 0;
+}
+
 static void nitrox_skcipher_exit(struct crypto_skcipher *tfm)
 {
 	struct nitrox_crypto_ctx *nctx = crypto_skcipher_ctx(tfm);
@@ -173,34 +246,6 @@ static int alloc_dst_sglist(struct skcipher_request *skreq, int ivsize)
 	return 0;
 }
 
-static void free_src_sglist(struct skcipher_request *skreq)
-{
-	struct nitrox_kcrypt_request *nkreq = skcipher_request_ctx(skreq);
-
-	kfree(nkreq->src);
-}
-
-static void free_dst_sglist(struct skcipher_request *skreq)
-{
-	struct nitrox_kcrypt_request *nkreq = skcipher_request_ctx(skreq);
-
-	kfree(nkreq->dst);
-}
-
-static void nitrox_skcipher_callback(void *arg, int err)
-{
-	struct skcipher_request *skreq = arg;
-
-	free_src_sglist(skreq);
-	free_dst_sglist(skreq);
-	if (err) {
-		pr_err_ratelimited("request failed status 0x%0x\n", err);
-		err = -EINVAL;
-	}
-
-	skcipher_request_complete(skreq, err);
-}
-
 static int nitrox_skcipher_crypt(struct skcipher_request *skreq, bool enc)
 {
 	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(skreq);
@@ -240,8 +285,28 @@ static int nitrox_skcipher_crypt(struct skcipher_request *skreq, bool enc)
 	}
 
 	/* send the crypto request */
-	return nitrox_process_se_request(nctx->ndev, creq,
-					 nitrox_skcipher_callback, skreq);
+	return nitrox_process_se_request(nctx->ndev, creq, nctx->callback,
+					 skreq);
+}
+
+static int nitrox_cbc_decrypt(struct skcipher_request *skreq)
+{
+	struct nitrox_kcrypt_request *nkreq = skcipher_request_ctx(skreq);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(skreq);
+	int ivsize = crypto_skcipher_ivsize(cipher);
+	gfp_t flags = (skreq->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+			GFP_KERNEL : GFP_ATOMIC;
+	unsigned int start = skreq->cryptlen - ivsize;
+
+	if (skreq->src != skreq->dst)
+		return nitrox_skcipher_crypt(skreq, false);
+
+	nkreq->iv_out = kmalloc(ivsize, flags);
+	if (!nkreq->iv_out)
+		return -ENOMEM;
+
+	scatterwalk_map_and_copy(nkreq->iv_out, skreq->src, start, ivsize, 0);
+	return nitrox_skcipher_crypt(skreq, false);
 }
 
 static int nitrox_aes_encrypt(struct skcipher_request *skreq)
@@ -340,8 +405,8 @@ static struct skcipher_alg nitrox_skciphers[] = { {
 	.ivsize = AES_BLOCK_SIZE,
 	.setkey = nitrox_aes_setkey,
 	.encrypt = nitrox_aes_encrypt,
-	.decrypt = nitrox_aes_decrypt,
-	.init = nitrox_skcipher_init,
+	.decrypt = nitrox_cbc_decrypt,
+	.init = nitrox_cbc_init,
 	.exit = nitrox_skcipher_exit,
 }, {
 	.base = {
@@ -428,7 +493,6 @@ static struct skcipher_alg nitrox_skciphers[] = { {
 		.cra_blocksize = AES_BLOCK_SIZE,
 		.cra_ctxsize = sizeof(struct nitrox_crypto_ctx),
 		.cra_alignmask = 0,
-		.cra_type = &crypto_ablkcipher_type,
 		.cra_module = THIS_MODULE,
 	},
 	.min_keysize = AES_MIN_KEY_SIZE,
@@ -455,8 +519,8 @@ static struct skcipher_alg nitrox_skciphers[] = { {
 	.ivsize = DES3_EDE_BLOCK_SIZE,
 	.setkey = nitrox_3des_setkey,
 	.encrypt = nitrox_3des_encrypt,
-	.decrypt = nitrox_3des_decrypt,
-	.init = nitrox_skcipher_init,
+	.decrypt = nitrox_cbc_decrypt,
+	.init = nitrox_cbc_init,
 	.exit = nitrox_skcipher_exit,
 }, {
 	.base = {
diff --git a/drivers/crypto/ccp/Kconfig b/drivers/crypto/ccp/Kconfig
index 8fec733f567f..e0a8bd15aa74 100644
--- a/drivers/crypto/ccp/Kconfig
+++ b/drivers/crypto/ccp/Kconfig
@@ -27,7 +27,7 @@ config CRYPTO_DEV_CCP_CRYPTO
 	depends on CRYPTO_DEV_CCP_DD
 	depends on CRYPTO_DEV_SP_CCP
 	select CRYPTO_HASH
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_AUTHENC
 	select CRYPTO_RSA
 	select CRYPTO_LIB_AES
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-galois.c b/drivers/crypto/ccp/ccp-crypto-aes-galois.c
index 94c1ad7eeddf..ff50ee80d223 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes-galois.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes-galois.c
@@ -172,14 +172,12 @@ static struct aead_alg ccp_aes_gcm_defaults = {
 	.ivsize = GCM_AES_IV_SIZE,
 	.maxauthsize = AES_BLOCK_SIZE,
 	.base = {
-		.cra_flags	= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC |
+		.cra_flags	= CRYPTO_ALG_ASYNC |
 				  CRYPTO_ALG_KERN_DRIVER_ONLY |
 				  CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize	= AES_BLOCK_SIZE,
 		.cra_ctxsize	= sizeof(struct ccp_ctx),
 		.cra_priority	= CCP_CRA_PRIORITY,
-		.cra_type	= &crypto_ablkcipher_type,
 		.cra_exit	= ccp_aes_gcm_cra_exit,
 		.cra_module	= THIS_MODULE,
 	},
@@ -229,11 +227,10 @@ static int ccp_register_aes_aead(struct list_head *head,
 	snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 		 def->driver_name);
 	alg->base.cra_blocksize = def->blocksize;
-	alg->base.cra_ablkcipher.ivsize = def->ivsize;
 
 	ret = crypto_register_aead(alg);
 	if (ret) {
-		pr_err("%s ablkcipher algorithm registration error (%d)\n",
+		pr_err("%s aead algorithm registration error (%d)\n",
 		       alg->base.cra_name, ret);
 		kfree(ccp_aead);
 		return ret;
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-xts.c b/drivers/crypto/ccp/ccp-crypto-aes-xts.c
index 8e4a531f4f70..04b2517df955 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes-xts.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes-xts.c
@@ -24,7 +24,7 @@ struct ccp_aes_xts_def {
 	const char *drv_name;
 };
 
-static struct ccp_aes_xts_def aes_xts_algs[] = {
+static const struct ccp_aes_xts_def aes_xts_algs[] = {
 	{
 		.name		= "xts(aes)",
 		.drv_name	= "xts-aes-ccp",
@@ -61,26 +61,25 @@ static struct ccp_unit_size_map xts_unit_sizes[] = {
 
 static int ccp_aes_xts_complete(struct crypto_async_request *async_req, int ret)
 {
-	struct ablkcipher_request *req = ablkcipher_request_cast(async_req);
-	struct ccp_aes_req_ctx *rctx = ablkcipher_request_ctx(req);
+	struct skcipher_request *req = skcipher_request_cast(async_req);
+	struct ccp_aes_req_ctx *rctx = skcipher_request_ctx(req);
 
 	if (ret)
 		return ret;
 
-	memcpy(req->info, rctx->iv, AES_BLOCK_SIZE);
+	memcpy(req->iv, rctx->iv, AES_BLOCK_SIZE);
 
 	return 0;
 }
 
-static int ccp_aes_xts_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int ccp_aes_xts_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			      unsigned int key_len)
 {
-	struct crypto_tfm *xfm = crypto_ablkcipher_tfm(tfm);
-	struct ccp_ctx *ctx = crypto_tfm_ctx(xfm);
+	struct ccp_ctx *ctx = crypto_skcipher_ctx(tfm);
 	unsigned int ccpversion = ccp_version();
 	int ret;
 
-	ret = xts_check_key(xfm, key, key_len);
+	ret = xts_verify_key(tfm, key, key_len);
 	if (ret)
 		return ret;
 
@@ -102,11 +101,12 @@ static int ccp_aes_xts_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 	return crypto_sync_skcipher_setkey(ctx->u.aes.tfm_skcipher, key, key_len);
 }
 
-static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
+static int ccp_aes_xts_crypt(struct skcipher_request *req,
 			     unsigned int encrypt)
 {
-	struct ccp_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	struct ccp_aes_req_ctx *rctx = ablkcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct ccp_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct ccp_aes_req_ctx *rctx = skcipher_request_ctx(req);
 	unsigned int ccpversion = ccp_version();
 	unsigned int fallback = 0;
 	unsigned int unit;
@@ -116,7 +116,7 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
 	if (!ctx->u.aes.key_len)
 		return -EINVAL;
 
-	if (!req->info)
+	if (!req->iv)
 		return -EINVAL;
 
 	/* Check conditions under which the CCP can fulfill a request. The
@@ -127,7 +127,7 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
 	 */
 	unit_size = CCP_XTS_AES_UNIT_SIZE__LAST;
 	for (unit = 0; unit < ARRAY_SIZE(xts_unit_sizes); unit++) {
-		if (req->nbytes == xts_unit_sizes[unit].size) {
+		if (req->cryptlen == xts_unit_sizes[unit].size) {
 			unit_size = unit;
 			break;
 		}
@@ -155,14 +155,14 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
 		skcipher_request_set_callback(subreq, req->base.flags,
 					      NULL, NULL);
 		skcipher_request_set_crypt(subreq, req->src, req->dst,
-					   req->nbytes, req->info);
+					   req->cryptlen, req->iv);
 		ret = encrypt ? crypto_skcipher_encrypt(subreq) :
 				crypto_skcipher_decrypt(subreq);
 		skcipher_request_zero(subreq);
 		return ret;
 	}
 
-	memcpy(rctx->iv, req->info, AES_BLOCK_SIZE);
+	memcpy(rctx->iv, req->iv, AES_BLOCK_SIZE);
 	sg_init_one(&rctx->iv_sg, rctx->iv, AES_BLOCK_SIZE);
 
 	memset(&rctx->cmd, 0, sizeof(rctx->cmd));
@@ -177,7 +177,7 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
 	rctx->cmd.u.xts.iv = &rctx->iv_sg;
 	rctx->cmd.u.xts.iv_len = AES_BLOCK_SIZE;
 	rctx->cmd.u.xts.src = req->src;
-	rctx->cmd.u.xts.src_len = req->nbytes;
+	rctx->cmd.u.xts.src_len = req->cryptlen;
 	rctx->cmd.u.xts.dst = req->dst;
 
 	ret = ccp_crypto_enqueue_request(&req->base, &rctx->cmd);
@@ -185,19 +185,19 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
 	return ret;
 }
 
-static int ccp_aes_xts_encrypt(struct ablkcipher_request *req)
+static int ccp_aes_xts_encrypt(struct skcipher_request *req)
 {
 	return ccp_aes_xts_crypt(req, 1);
 }
 
-static int ccp_aes_xts_decrypt(struct ablkcipher_request *req)
+static int ccp_aes_xts_decrypt(struct skcipher_request *req)
 {
 	return ccp_aes_xts_crypt(req, 0);
 }
 
-static int ccp_aes_xts_cra_init(struct crypto_tfm *tfm)
+static int ccp_aes_xts_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct ccp_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct ccp_ctx *ctx = crypto_skcipher_ctx(tfm);
 	struct crypto_sync_skcipher *fallback_tfm;
 
 	ctx->complete = ccp_aes_xts_complete;
@@ -212,14 +212,14 @@ static int ccp_aes_xts_cra_init(struct crypto_tfm *tfm)
 	}
 	ctx->u.aes.tfm_skcipher = fallback_tfm;
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ccp_aes_req_ctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct ccp_aes_req_ctx));
 
 	return 0;
 }
 
-static void ccp_aes_xts_cra_exit(struct crypto_tfm *tfm)
+static void ccp_aes_xts_exit_tfm(struct crypto_skcipher *tfm)
 {
-	struct ccp_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct ccp_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	crypto_free_sync_skcipher(ctx->u.aes.tfm_skcipher);
 }
@@ -227,8 +227,8 @@ static void ccp_aes_xts_cra_exit(struct crypto_tfm *tfm)
 static int ccp_register_aes_xts_alg(struct list_head *head,
 				    const struct ccp_aes_xts_def *def)
 {
-	struct ccp_crypto_ablkcipher_alg *ccp_alg;
-	struct crypto_alg *alg;
+	struct ccp_crypto_skcipher_alg *ccp_alg;
+	struct skcipher_alg *alg;
 	int ret;
 
 	ccp_alg = kzalloc(sizeof(*ccp_alg), GFP_KERNEL);
@@ -239,30 +239,30 @@ static int ccp_register_aes_xts_alg(struct list_head *head,
 
 	alg = &ccp_alg->alg;
 
-	snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
-	snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+	snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
+	snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 		 def->drv_name);
-	alg->cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC |
-			 CRYPTO_ALG_KERN_DRIVER_ONLY |
-			 CRYPTO_ALG_NEED_FALLBACK;
-	alg->cra_blocksize = AES_BLOCK_SIZE;
-	alg->cra_ctxsize = sizeof(struct ccp_ctx);
-	alg->cra_priority = CCP_CRA_PRIORITY;
-	alg->cra_type = &crypto_ablkcipher_type;
-	alg->cra_ablkcipher.setkey = ccp_aes_xts_setkey;
-	alg->cra_ablkcipher.encrypt = ccp_aes_xts_encrypt;
-	alg->cra_ablkcipher.decrypt = ccp_aes_xts_decrypt;
-	alg->cra_ablkcipher.min_keysize = AES_MIN_KEY_SIZE * 2;
-	alg->cra_ablkcipher.max_keysize = AES_MAX_KEY_SIZE * 2;
-	alg->cra_ablkcipher.ivsize = AES_BLOCK_SIZE;
-	alg->cra_init = ccp_aes_xts_cra_init;
-	alg->cra_exit = ccp_aes_xts_cra_exit;
-	alg->cra_module = THIS_MODULE;
-
-	ret = crypto_register_alg(alg);
+	alg->base.cra_flags	= CRYPTO_ALG_ASYNC |
+				  CRYPTO_ALG_KERN_DRIVER_ONLY |
+				  CRYPTO_ALG_NEED_FALLBACK;
+	alg->base.cra_blocksize	= AES_BLOCK_SIZE;
+	alg->base.cra_ctxsize	= sizeof(struct ccp_ctx);
+	alg->base.cra_priority	= CCP_CRA_PRIORITY;
+	alg->base.cra_module	= THIS_MODULE;
+
+	alg->setkey		= ccp_aes_xts_setkey;
+	alg->encrypt		= ccp_aes_xts_encrypt;
+	alg->decrypt		= ccp_aes_xts_decrypt;
+	alg->min_keysize	= AES_MIN_KEY_SIZE * 2;
+	alg->max_keysize	= AES_MAX_KEY_SIZE * 2;
+	alg->ivsize		= AES_BLOCK_SIZE;
+	alg->init		= ccp_aes_xts_init_tfm;
+	alg->exit		= ccp_aes_xts_exit_tfm;
+
+	ret = crypto_register_skcipher(alg);
 	if (ret) {
-		pr_err("%s ablkcipher algorithm registration error (%d)\n",
-		       alg->cra_name, ret);
+		pr_err("%s skcipher algorithm registration error (%d)\n",
+		       alg->base.cra_name, ret);
 		kfree(ccp_alg);
 		return ret;
 	}
diff --git a/drivers/crypto/ccp/ccp-crypto-aes.c b/drivers/crypto/ccp/ccp-crypto-aes.c
index 58c6dddfc5e1..33328a153225 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes.c
@@ -21,25 +21,24 @@
 
 static int ccp_aes_complete(struct crypto_async_request *async_req, int ret)
 {
-	struct ablkcipher_request *req = ablkcipher_request_cast(async_req);
+	struct skcipher_request *req = skcipher_request_cast(async_req);
 	struct ccp_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	struct ccp_aes_req_ctx *rctx = ablkcipher_request_ctx(req);
+	struct ccp_aes_req_ctx *rctx = skcipher_request_ctx(req);
 
 	if (ret)
 		return ret;
 
 	if (ctx->u.aes.mode != CCP_AES_MODE_ECB)
-		memcpy(req->info, rctx->iv, AES_BLOCK_SIZE);
+		memcpy(req->iv, rctx->iv, AES_BLOCK_SIZE);
 
 	return 0;
 }
 
-static int ccp_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int ccp_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			  unsigned int key_len)
 {
-	struct ccp_ctx *ctx = crypto_tfm_ctx(crypto_ablkcipher_tfm(tfm));
-	struct ccp_crypto_ablkcipher_alg *alg =
-		ccp_crypto_ablkcipher_alg(crypto_ablkcipher_tfm(tfm));
+	struct ccp_crypto_skcipher_alg *alg = ccp_crypto_skcipher_alg(tfm);
+	struct ccp_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	switch (key_len) {
 	case AES_KEYSIZE_128:
@@ -52,7 +51,7 @@ static int ccp_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 		ctx->u.aes.type = CCP_AES_TYPE_256;
 		break;
 	default:
-		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 	ctx->u.aes.mode = alg->mode;
@@ -64,10 +63,11 @@ static int ccp_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 	return 0;
 }
 
-static int ccp_aes_crypt(struct ablkcipher_request *req, bool encrypt)
+static int ccp_aes_crypt(struct skcipher_request *req, bool encrypt)
 {
-	struct ccp_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	struct ccp_aes_req_ctx *rctx = ablkcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct ccp_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct ccp_aes_req_ctx *rctx = skcipher_request_ctx(req);
 	struct scatterlist *iv_sg = NULL;
 	unsigned int iv_len = 0;
 	int ret;
@@ -77,14 +77,14 @@ static int ccp_aes_crypt(struct ablkcipher_request *req, bool encrypt)
 
 	if (((ctx->u.aes.mode == CCP_AES_MODE_ECB) ||
 	     (ctx->u.aes.mode == CCP_AES_MODE_CBC)) &&
-	    (req->nbytes & (AES_BLOCK_SIZE - 1)))
+	    (req->cryptlen & (AES_BLOCK_SIZE - 1)))
 		return -EINVAL;
 
 	if (ctx->u.aes.mode != CCP_AES_MODE_ECB) {
-		if (!req->info)
+		if (!req->iv)
 			return -EINVAL;
 
-		memcpy(rctx->iv, req->info, AES_BLOCK_SIZE);
+		memcpy(rctx->iv, req->iv, AES_BLOCK_SIZE);
 		iv_sg = &rctx->iv_sg;
 		iv_len = AES_BLOCK_SIZE;
 		sg_init_one(iv_sg, rctx->iv, iv_len);
@@ -102,7 +102,7 @@ static int ccp_aes_crypt(struct ablkcipher_request *req, bool encrypt)
 	rctx->cmd.u.aes.iv = iv_sg;
 	rctx->cmd.u.aes.iv_len = iv_len;
 	rctx->cmd.u.aes.src = req->src;
-	rctx->cmd.u.aes.src_len = req->nbytes;
+	rctx->cmd.u.aes.src_len = req->cryptlen;
 	rctx->cmd.u.aes.dst = req->dst;
 
 	ret = ccp_crypto_enqueue_request(&req->base, &rctx->cmd);
@@ -110,48 +110,44 @@ static int ccp_aes_crypt(struct ablkcipher_request *req, bool encrypt)
 	return ret;
 }
 
-static int ccp_aes_encrypt(struct ablkcipher_request *req)
+static int ccp_aes_encrypt(struct skcipher_request *req)
 {
 	return ccp_aes_crypt(req, true);
 }
 
-static int ccp_aes_decrypt(struct ablkcipher_request *req)
+static int ccp_aes_decrypt(struct skcipher_request *req)
 {
 	return ccp_aes_crypt(req, false);
 }
 
-static int ccp_aes_cra_init(struct crypto_tfm *tfm)
+static int ccp_aes_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct ccp_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct ccp_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	ctx->complete = ccp_aes_complete;
 	ctx->u.aes.key_len = 0;
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ccp_aes_req_ctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct ccp_aes_req_ctx));
 
 	return 0;
 }
 
-static void ccp_aes_cra_exit(struct crypto_tfm *tfm)
-{
-}
-
 static int ccp_aes_rfc3686_complete(struct crypto_async_request *async_req,
 				    int ret)
 {
-	struct ablkcipher_request *req = ablkcipher_request_cast(async_req);
-	struct ccp_aes_req_ctx *rctx = ablkcipher_request_ctx(req);
+	struct skcipher_request *req = skcipher_request_cast(async_req);
+	struct ccp_aes_req_ctx *rctx = skcipher_request_ctx(req);
 
 	/* Restore the original pointer */
-	req->info = rctx->rfc3686_info;
+	req->iv = rctx->rfc3686_info;
 
 	return ccp_aes_complete(async_req, ret);
 }
 
-static int ccp_aes_rfc3686_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int ccp_aes_rfc3686_setkey(struct crypto_skcipher *tfm, const u8 *key,
 				  unsigned int key_len)
 {
-	struct ccp_ctx *ctx = crypto_tfm_ctx(crypto_ablkcipher_tfm(tfm));
+	struct ccp_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	if (key_len < CTR_RFC3686_NONCE_SIZE)
 		return -EINVAL;
@@ -162,10 +158,11 @@ static int ccp_aes_rfc3686_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 	return ccp_aes_setkey(tfm, key, key_len);
 }
 
-static int ccp_aes_rfc3686_crypt(struct ablkcipher_request *req, bool encrypt)
+static int ccp_aes_rfc3686_crypt(struct skcipher_request *req, bool encrypt)
 {
-	struct ccp_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	struct ccp_aes_req_ctx *rctx = ablkcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct ccp_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct ccp_aes_req_ctx *rctx = skcipher_request_ctx(req);
 	u8 *iv;
 
 	/* Initialize the CTR block */
@@ -173,84 +170,72 @@ static int ccp_aes_rfc3686_crypt(struct ablkcipher_request *req, bool encrypt)
 	memcpy(iv, ctx->u.aes.nonce, CTR_RFC3686_NONCE_SIZE);
 
 	iv += CTR_RFC3686_NONCE_SIZE;
-	memcpy(iv, req->info, CTR_RFC3686_IV_SIZE);
+	memcpy(iv, req->iv, CTR_RFC3686_IV_SIZE);
 
 	iv += CTR_RFC3686_IV_SIZE;
 	*(__be32 *)iv = cpu_to_be32(1);
 
 	/* Point to the new IV */
-	rctx->rfc3686_info = req->info;
-	req->info = rctx->rfc3686_iv;
+	rctx->rfc3686_info = req->iv;
+	req->iv = rctx->rfc3686_iv;
 
 	return ccp_aes_crypt(req, encrypt);
 }
 
-static int ccp_aes_rfc3686_encrypt(struct ablkcipher_request *req)
+static int ccp_aes_rfc3686_encrypt(struct skcipher_request *req)
 {
 	return ccp_aes_rfc3686_crypt(req, true);
 }
 
-static int ccp_aes_rfc3686_decrypt(struct ablkcipher_request *req)
+static int ccp_aes_rfc3686_decrypt(struct skcipher_request *req)
 {
 	return ccp_aes_rfc3686_crypt(req, false);
 }
 
-static int ccp_aes_rfc3686_cra_init(struct crypto_tfm *tfm)
+static int ccp_aes_rfc3686_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct ccp_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct ccp_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	ctx->complete = ccp_aes_rfc3686_complete;
 	ctx->u.aes.key_len = 0;
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ccp_aes_req_ctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct ccp_aes_req_ctx));
 
 	return 0;
 }
 
-static void ccp_aes_rfc3686_cra_exit(struct crypto_tfm *tfm)
-{
-}
-
-static struct crypto_alg ccp_aes_defaults = {
-	.cra_flags	= CRYPTO_ALG_TYPE_ABLKCIPHER |
-			  CRYPTO_ALG_ASYNC |
-			  CRYPTO_ALG_KERN_DRIVER_ONLY |
-			  CRYPTO_ALG_NEED_FALLBACK,
-	.cra_blocksize	= AES_BLOCK_SIZE,
-	.cra_ctxsize	= sizeof(struct ccp_ctx),
-	.cra_priority	= CCP_CRA_PRIORITY,
-	.cra_type	= &crypto_ablkcipher_type,
-	.cra_init	= ccp_aes_cra_init,
-	.cra_exit	= ccp_aes_cra_exit,
-	.cra_module	= THIS_MODULE,
-	.cra_ablkcipher	= {
-		.setkey		= ccp_aes_setkey,
-		.encrypt	= ccp_aes_encrypt,
-		.decrypt	= ccp_aes_decrypt,
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-	},
+static const struct skcipher_alg ccp_aes_defaults = {
+	.setkey			= ccp_aes_setkey,
+	.encrypt		= ccp_aes_encrypt,
+	.decrypt		= ccp_aes_decrypt,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.init			= ccp_aes_init_tfm,
+
+	.base.cra_flags		= CRYPTO_ALG_ASYNC |
+				  CRYPTO_ALG_KERN_DRIVER_ONLY |
+				  CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct ccp_ctx),
+	.base.cra_priority	= CCP_CRA_PRIORITY,
+	.base.cra_module	= THIS_MODULE,
 };
 
-static struct crypto_alg ccp_aes_rfc3686_defaults = {
-	.cra_flags	= CRYPTO_ALG_TYPE_ABLKCIPHER |
-			   CRYPTO_ALG_ASYNC |
-			   CRYPTO_ALG_KERN_DRIVER_ONLY |
-			   CRYPTO_ALG_NEED_FALLBACK,
-	.cra_blocksize	= CTR_RFC3686_BLOCK_SIZE,
-	.cra_ctxsize	= sizeof(struct ccp_ctx),
-	.cra_priority	= CCP_CRA_PRIORITY,
-	.cra_type	= &crypto_ablkcipher_type,
-	.cra_init	= ccp_aes_rfc3686_cra_init,
-	.cra_exit	= ccp_aes_rfc3686_cra_exit,
-	.cra_module	= THIS_MODULE,
-	.cra_ablkcipher	= {
-		.setkey		= ccp_aes_rfc3686_setkey,
-		.encrypt	= ccp_aes_rfc3686_encrypt,
-		.decrypt	= ccp_aes_rfc3686_decrypt,
-		.min_keysize	= AES_MIN_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
-	},
+static const struct skcipher_alg ccp_aes_rfc3686_defaults = {
+	.setkey			= ccp_aes_rfc3686_setkey,
+	.encrypt		= ccp_aes_rfc3686_encrypt,
+	.decrypt		= ccp_aes_rfc3686_decrypt,
+	.min_keysize		= AES_MIN_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
+	.init			= ccp_aes_rfc3686_init_tfm,
+
+	.base.cra_flags		= CRYPTO_ALG_ASYNC |
+				  CRYPTO_ALG_KERN_DRIVER_ONLY |
+				  CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize	= CTR_RFC3686_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct ccp_ctx),
+	.base.cra_priority	= CCP_CRA_PRIORITY,
+	.base.cra_module	= THIS_MODULE,
 };
 
 struct ccp_aes_def {
@@ -260,7 +245,7 @@ struct ccp_aes_def {
 	const char *driver_name;
 	unsigned int blocksize;
 	unsigned int ivsize;
-	struct crypto_alg *alg_defaults;
+	const struct skcipher_alg *alg_defaults;
 };
 
 static struct ccp_aes_def aes_algs[] = {
@@ -323,8 +308,8 @@ static struct ccp_aes_def aes_algs[] = {
 static int ccp_register_aes_alg(struct list_head *head,
 				const struct ccp_aes_def *def)
 {
-	struct ccp_crypto_ablkcipher_alg *ccp_alg;
-	struct crypto_alg *alg;
+	struct ccp_crypto_skcipher_alg *ccp_alg;
+	struct skcipher_alg *alg;
 	int ret;
 
 	ccp_alg = kzalloc(sizeof(*ccp_alg), GFP_KERNEL);
@@ -338,16 +323,16 @@ static int ccp_register_aes_alg(struct list_head *head,
 	/* Copy the defaults and override as necessary */
 	alg = &ccp_alg->alg;
 	*alg = *def->alg_defaults;
-	snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
-	snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+	snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
+	snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 		 def->driver_name);
-	alg->cra_blocksize = def->blocksize;
-	alg->cra_ablkcipher.ivsize = def->ivsize;
+	alg->base.cra_blocksize = def->blocksize;
+	alg->ivsize = def->ivsize;
 
-	ret = crypto_register_alg(alg);
+	ret = crypto_register_skcipher(alg);
 	if (ret) {
-		pr_err("%s ablkcipher algorithm registration error (%d)\n",
-		       alg->cra_name, ret);
+		pr_err("%s skcipher algorithm registration error (%d)\n",
+		       alg->base.cra_name, ret);
 		kfree(ccp_alg);
 		return ret;
 	}
diff --git a/drivers/crypto/ccp/ccp-crypto-des3.c b/drivers/crypto/ccp/ccp-crypto-des3.c
index d2c49b2f0323..9c129defdb50 100644
--- a/drivers/crypto/ccp/ccp-crypto-des3.c
+++ b/drivers/crypto/ccp/ccp-crypto-des3.c
@@ -20,28 +20,27 @@
 
 static int ccp_des3_complete(struct crypto_async_request *async_req, int ret)
 {
-	struct ablkcipher_request *req = ablkcipher_request_cast(async_req);
+	struct skcipher_request *req = skcipher_request_cast(async_req);
 	struct ccp_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	struct ccp_des3_req_ctx *rctx = ablkcipher_request_ctx(req);
+	struct ccp_des3_req_ctx *rctx = skcipher_request_ctx(req);
 
 	if (ret)
 		return ret;
 
 	if (ctx->u.des3.mode != CCP_DES3_MODE_ECB)
-		memcpy(req->info, rctx->iv, DES3_EDE_BLOCK_SIZE);
+		memcpy(req->iv, rctx->iv, DES3_EDE_BLOCK_SIZE);
 
 	return 0;
 }
 
-static int ccp_des3_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int ccp_des3_setkey(struct crypto_skcipher *tfm, const u8 *key,
 		unsigned int key_len)
 {
-	struct ccp_ctx *ctx = crypto_tfm_ctx(crypto_ablkcipher_tfm(tfm));
-	struct ccp_crypto_ablkcipher_alg *alg =
-		ccp_crypto_ablkcipher_alg(crypto_ablkcipher_tfm(tfm));
+	struct ccp_crypto_skcipher_alg *alg = ccp_crypto_skcipher_alg(tfm);
+	struct ccp_ctx *ctx = crypto_skcipher_ctx(tfm);
 	int err;
 
-	err = verify_ablkcipher_des3_key(tfm, key);
+	err = verify_skcipher_des3_key(tfm, key);
 	if (err)
 		return err;
 
@@ -58,10 +57,11 @@ static int ccp_des3_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 	return 0;
 }
 
-static int ccp_des3_crypt(struct ablkcipher_request *req, bool encrypt)
+static int ccp_des3_crypt(struct skcipher_request *req, bool encrypt)
 {
-	struct ccp_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	struct ccp_des3_req_ctx *rctx = ablkcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct ccp_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct ccp_des3_req_ctx *rctx = skcipher_request_ctx(req);
 	struct scatterlist *iv_sg = NULL;
 	unsigned int iv_len = 0;
 	int ret;
@@ -71,14 +71,14 @@ static int ccp_des3_crypt(struct ablkcipher_request *req, bool encrypt)
 
 	if (((ctx->u.des3.mode == CCP_DES3_MODE_ECB) ||
 	     (ctx->u.des3.mode == CCP_DES3_MODE_CBC)) &&
-	    (req->nbytes & (DES3_EDE_BLOCK_SIZE - 1)))
+	    (req->cryptlen & (DES3_EDE_BLOCK_SIZE - 1)))
 		return -EINVAL;
 
 	if (ctx->u.des3.mode != CCP_DES3_MODE_ECB) {
-		if (!req->info)
+		if (!req->iv)
 			return -EINVAL;
 
-		memcpy(rctx->iv, req->info, DES3_EDE_BLOCK_SIZE);
+		memcpy(rctx->iv, req->iv, DES3_EDE_BLOCK_SIZE);
 		iv_sg = &rctx->iv_sg;
 		iv_len = DES3_EDE_BLOCK_SIZE;
 		sg_init_one(iv_sg, rctx->iv, iv_len);
@@ -97,7 +97,7 @@ static int ccp_des3_crypt(struct ablkcipher_request *req, bool encrypt)
 	rctx->cmd.u.des3.iv = iv_sg;
 	rctx->cmd.u.des3.iv_len = iv_len;
 	rctx->cmd.u.des3.src = req->src;
-	rctx->cmd.u.des3.src_len = req->nbytes;
+	rctx->cmd.u.des3.src_len = req->cryptlen;
 	rctx->cmd.u.des3.dst = req->dst;
 
 	ret = ccp_crypto_enqueue_request(&req->base, &rctx->cmd);
@@ -105,51 +105,43 @@ static int ccp_des3_crypt(struct ablkcipher_request *req, bool encrypt)
 	return ret;
 }
 
-static int ccp_des3_encrypt(struct ablkcipher_request *req)
+static int ccp_des3_encrypt(struct skcipher_request *req)
 {
 	return ccp_des3_crypt(req, true);
 }
 
-static int ccp_des3_decrypt(struct ablkcipher_request *req)
+static int ccp_des3_decrypt(struct skcipher_request *req)
 {
 	return ccp_des3_crypt(req, false);
 }
 
-static int ccp_des3_cra_init(struct crypto_tfm *tfm)
+static int ccp_des3_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct ccp_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct ccp_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	ctx->complete = ccp_des3_complete;
 	ctx->u.des3.key_len = 0;
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ccp_des3_req_ctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct ccp_des3_req_ctx));
 
 	return 0;
 }
 
-static void ccp_des3_cra_exit(struct crypto_tfm *tfm)
-{
-}
-
-static struct crypto_alg ccp_des3_defaults = {
-	.cra_flags	= CRYPTO_ALG_TYPE_ABLKCIPHER |
-		CRYPTO_ALG_ASYNC |
-		CRYPTO_ALG_KERN_DRIVER_ONLY |
-		CRYPTO_ALG_NEED_FALLBACK,
-	.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
-	.cra_ctxsize	= sizeof(struct ccp_ctx),
-	.cra_priority	= CCP_CRA_PRIORITY,
-	.cra_type	= &crypto_ablkcipher_type,
-	.cra_init	= ccp_des3_cra_init,
-	.cra_exit	= ccp_des3_cra_exit,
-	.cra_module	= THIS_MODULE,
-	.cra_ablkcipher	= {
-		.setkey		= ccp_des3_setkey,
-		.encrypt	= ccp_des3_encrypt,
-		.decrypt	= ccp_des3_decrypt,
-		.min_keysize	= DES3_EDE_KEY_SIZE,
-		.max_keysize	= DES3_EDE_KEY_SIZE,
-	},
+static const struct skcipher_alg ccp_des3_defaults = {
+	.setkey			= ccp_des3_setkey,
+	.encrypt		= ccp_des3_encrypt,
+	.decrypt		= ccp_des3_decrypt,
+	.min_keysize		= DES3_EDE_KEY_SIZE,
+	.max_keysize		= DES3_EDE_KEY_SIZE,
+	.init			= ccp_des3_init_tfm,
+
+	.base.cra_flags		= CRYPTO_ALG_ASYNC |
+				  CRYPTO_ALG_KERN_DRIVER_ONLY |
+				  CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct ccp_ctx),
+	.base.cra_priority	= CCP_CRA_PRIORITY,
+	.base.cra_module	= THIS_MODULE,
 };
 
 struct ccp_des3_def {
@@ -159,10 +151,10 @@ struct ccp_des3_def {
 	const char *driver_name;
 	unsigned int blocksize;
 	unsigned int ivsize;
-	struct crypto_alg *alg_defaults;
+	const struct skcipher_alg *alg_defaults;
 };
 
-static struct ccp_des3_def des3_algs[] = {
+static const struct ccp_des3_def des3_algs[] = {
 	{
 		.mode		= CCP_DES3_MODE_ECB,
 		.version	= CCP_VERSION(5, 0),
@@ -186,8 +178,8 @@ static struct ccp_des3_def des3_algs[] = {
 static int ccp_register_des3_alg(struct list_head *head,
 				 const struct ccp_des3_def *def)
 {
-	struct ccp_crypto_ablkcipher_alg *ccp_alg;
-	struct crypto_alg *alg;
+	struct ccp_crypto_skcipher_alg *ccp_alg;
+	struct skcipher_alg *alg;
 	int ret;
 
 	ccp_alg = kzalloc(sizeof(*ccp_alg), GFP_KERNEL);
@@ -201,16 +193,16 @@ static int ccp_register_des3_alg(struct list_head *head,
 	/* Copy the defaults and override as necessary */
 	alg = &ccp_alg->alg;
 	*alg = *def->alg_defaults;
-	snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
-	snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+	snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
+	snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 			def->driver_name);
-	alg->cra_blocksize = def->blocksize;
-	alg->cra_ablkcipher.ivsize = def->ivsize;
+	alg->base.cra_blocksize = def->blocksize;
+	alg->ivsize = def->ivsize;
 
-	ret = crypto_register_alg(alg);
+	ret = crypto_register_skcipher(alg);
 	if (ret) {
-		pr_err("%s ablkcipher algorithm registration error (%d)\n",
-				alg->cra_name, ret);
+		pr_err("%s skcipher algorithm registration error (%d)\n",
+				alg->base.cra_name, ret);
 		kfree(ccp_alg);
 		return ret;
 	}
diff --git a/drivers/crypto/ccp/ccp-crypto-main.c b/drivers/crypto/ccp/ccp-crypto-main.c
index 8ee4cb45a3f3..88275b4867ea 100644
--- a/drivers/crypto/ccp/ccp-crypto-main.c
+++ b/drivers/crypto/ccp/ccp-crypto-main.c
@@ -41,7 +41,7 @@ MODULE_PARM_DESC(rsa_disable, "Disable use of RSA - any non-zero value");
 
 /* List heads for the supported algorithms */
 static LIST_HEAD(hash_algs);
-static LIST_HEAD(cipher_algs);
+static LIST_HEAD(skcipher_algs);
 static LIST_HEAD(aead_algs);
 static LIST_HEAD(akcipher_algs);
 
@@ -330,7 +330,7 @@ static int ccp_register_algs(void)
 	int ret;
 
 	if (!aes_disable) {
-		ret = ccp_register_aes_algs(&cipher_algs);
+		ret = ccp_register_aes_algs(&skcipher_algs);
 		if (ret)
 			return ret;
 
@@ -338,7 +338,7 @@ static int ccp_register_algs(void)
 		if (ret)
 			return ret;
 
-		ret = ccp_register_aes_xts_algs(&cipher_algs);
+		ret = ccp_register_aes_xts_algs(&skcipher_algs);
 		if (ret)
 			return ret;
 
@@ -348,7 +348,7 @@ static int ccp_register_algs(void)
 	}
 
 	if (!des3_disable) {
-		ret = ccp_register_des3_algs(&cipher_algs);
+		ret = ccp_register_des3_algs(&skcipher_algs);
 		if (ret)
 			return ret;
 	}
@@ -371,7 +371,7 @@ static int ccp_register_algs(void)
 static void ccp_unregister_algs(void)
 {
 	struct ccp_crypto_ahash_alg *ahash_alg, *ahash_tmp;
-	struct ccp_crypto_ablkcipher_alg *ablk_alg, *ablk_tmp;
+	struct ccp_crypto_skcipher_alg *ablk_alg, *ablk_tmp;
 	struct ccp_crypto_aead *aead_alg, *aead_tmp;
 	struct ccp_crypto_akcipher_alg *akc_alg, *akc_tmp;
 
@@ -381,8 +381,8 @@ static void ccp_unregister_algs(void)
 		kfree(ahash_alg);
 	}
 
-	list_for_each_entry_safe(ablk_alg, ablk_tmp, &cipher_algs, entry) {
-		crypto_unregister_alg(&ablk_alg->alg);
+	list_for_each_entry_safe(ablk_alg, ablk_tmp, &skcipher_algs, entry) {
+		crypto_unregister_skcipher(&ablk_alg->alg);
 		list_del(&ablk_alg->entry);
 		kfree(ablk_alg);
 	}
diff --git a/drivers/crypto/ccp/ccp-crypto.h b/drivers/crypto/ccp/ccp-crypto.h
index 9015b5da6ba3..90a009e6b5c1 100644
--- a/drivers/crypto/ccp/ccp-crypto.h
+++ b/drivers/crypto/ccp/ccp-crypto.h
@@ -21,6 +21,7 @@
 #include <crypto/hash.h>
 #include <crypto/sha.h>
 #include <crypto/akcipher.h>
+#include <crypto/skcipher.h>
 #include <crypto/internal/rsa.h>
 
 /* We want the module name in front of our messages */
@@ -31,12 +32,12 @@
 
 #define CCP_CRA_PRIORITY	300
 
-struct ccp_crypto_ablkcipher_alg {
+struct ccp_crypto_skcipher_alg {
 	struct list_head entry;
 
 	u32 mode;
 
-	struct crypto_alg alg;
+	struct skcipher_alg alg;
 };
 
 struct ccp_crypto_aead {
@@ -66,12 +67,12 @@ struct ccp_crypto_akcipher_alg {
 	struct akcipher_alg alg;
 };
 
-static inline struct ccp_crypto_ablkcipher_alg *
-	ccp_crypto_ablkcipher_alg(struct crypto_tfm *tfm)
+static inline struct ccp_crypto_skcipher_alg *
+	ccp_crypto_skcipher_alg(struct crypto_skcipher *tfm)
 {
-	struct crypto_alg *alg = tfm->__crt_alg;
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
 
-	return container_of(alg, struct ccp_crypto_ablkcipher_alg, alg);
+	return container_of(alg, struct ccp_crypto_skcipher_alg, alg);
 }
 
 static inline struct ccp_crypto_ahash_alg *
diff --git a/drivers/crypto/ccp/ccp-dev-v5.c b/drivers/crypto/ccp/ccp-dev-v5.c
index 57eb53b8ac21..82ac4c14c04c 100644
--- a/drivers/crypto/ccp/ccp-dev-v5.c
+++ b/drivers/crypto/ccp/ccp-dev-v5.c
@@ -789,6 +789,18 @@ static int ccp5_init(struct ccp_device *ccp)
 
 	/* Find available queues */
 	qmr = ioread32(ccp->io_regs + Q_MASK_REG);
+	/*
+	 * Check for a access to the registers.  If this read returns
+	 * 0xffffffff, it's likely that the system is running a broken
+	 * BIOS which disallows access to the device. Stop here and fail
+	 * the initialization (but not the load, as the PSP could get
+	 * properly initialized).
+	 */
+	if (qmr == 0xffffffff) {
+		dev_notice(dev, "ccp: unable to access the device: you might be running a broken BIOS.\n");
+		return 1;
+	}
+
 	for (i = 0; (i < MAX_HW_QUEUES) && (ccp->cmd_q_count < ccp->max_q_count); i++) {
 		if (!(qmr & (1 << i)))
 			continue;
@@ -854,7 +866,7 @@ static int ccp5_init(struct ccp_device *ccp)
 
 	if (ccp->cmd_q_count == 0) {
 		dev_notice(dev, "no command queues available\n");
-		ret = -EIO;
+		ret = 1;
 		goto e_pool;
 	}
 
diff --git a/drivers/crypto/ccp/ccp-dev.c b/drivers/crypto/ccp/ccp-dev.c
index 73acf0fdb793..19ac509ed76e 100644
--- a/drivers/crypto/ccp/ccp-dev.c
+++ b/drivers/crypto/ccp/ccp-dev.c
@@ -641,18 +641,27 @@ int ccp_dev_init(struct sp_device *sp)
 		ccp->vdata->setup(ccp);
 
 	ret = ccp->vdata->perform->init(ccp);
-	if (ret)
+	if (ret) {
+		/* A positive number means that the device cannot be initialized,
+		 * but no additional message is required.
+		 */
+		if (ret > 0)
+			goto e_quiet;
+
+		/* An unexpected problem occurred, and should be reported in the log */
 		goto e_err;
+	}
 
 	dev_notice(dev, "ccp enabled\n");
 
 	return 0;
 
 e_err:
-	sp->ccp_data = NULL;
-
 	dev_notice(dev, "ccp initialization failed\n");
 
+e_quiet:
+	sp->ccp_data = NULL;
+
 	return ret;
 }
 
diff --git a/drivers/crypto/ccp/ccp-dmaengine.c b/drivers/crypto/ccp/ccp-dmaengine.c
index a54f9367a580..0770a83bf1a5 100644
--- a/drivers/crypto/ccp/ccp-dmaengine.c
+++ b/drivers/crypto/ccp/ccp-dmaengine.c
@@ -342,6 +342,7 @@ static struct ccp_dma_desc *ccp_alloc_dma_desc(struct ccp_dma_chan *chan,
 	desc->tx_desc.flags = flags;
 	desc->tx_desc.tx_submit = ccp_tx_submit;
 	desc->ccp = chan->ccp;
+	INIT_LIST_HEAD(&desc->entry);
 	INIT_LIST_HEAD(&desc->pending);
 	INIT_LIST_HEAD(&desc->active);
 	desc->status = DMA_IN_PROGRESS;
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index c8da8eb160da..422193690fd4 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -1777,8 +1777,9 @@ ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 			       LSB_ITEM_SIZE);
 			break;
 		default:
+			kfree(hmac_buf);
 			ret = -EINVAL;
-			goto e_ctx;
+			goto e_data;
 		}
 
 		memset(&hmac_cmd, 0, sizeof(hmac_cmd));
diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c
index 6b17d179ef8a..7ca2d3408e7a 100644
--- a/drivers/crypto/ccp/psp-dev.c
+++ b/drivers/crypto/ccp/psp-dev.c
@@ -21,6 +21,8 @@
 #include <linux/ccp.h>
 #include <linux/firmware.h>
 
+#include <asm/smp.h>
+
 #include "sp-dev.h"
 #include "psp-dev.h"
 
@@ -235,6 +237,13 @@ static int __sev_platform_init_locked(int *error)
 		return rc;
 
 	psp->sev_state = SEV_STATE_INIT;
+
+	/* Prepare for first SEV guest launch after INIT */
+	wbinvd_on_all_cpus();
+	rc = __sev_do_cmd_locked(SEV_CMD_DF_FLUSH, NULL, error);
+	if (rc)
+		return rc;
+
 	dev_dbg(psp->dev, "SEV firmware initialized\n");
 
 	return rc;
@@ -294,6 +303,9 @@ static int sev_ioctl_do_reset(struct sev_issue_cmd *argp)
 {
 	int state, rc;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	/*
 	 * The SEV spec requires that FACTORY_RESET must be issued in
 	 * UNINIT state. Before we go further lets check if any guest is
@@ -338,6 +350,9 @@ static int sev_ioctl_do_pek_pdh_gen(int cmd, struct sev_issue_cmd *argp)
 {
 	int rc;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if (psp_master->sev_state == SEV_STATE_UNINIT) {
 		rc = __sev_platform_init_locked(&argp->error);
 		if (rc)
@@ -354,6 +369,9 @@ static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp)
 	void *blob = NULL;
 	int ret;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if (copy_from_user(&input, (void __user *)argp->data, sizeof(input)))
 		return -EFAULT;
 
@@ -540,6 +558,9 @@ static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp)
 	void *pek_blob, *oca_blob;
 	int ret;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if (copy_from_user(&input, (void __user *)argp->data, sizeof(input)))
 		return -EFAULT;
 
@@ -695,6 +716,16 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp)
 	struct sev_data_pdh_cert_export *data;
 	int ret;
 
+	/* If platform is not in INIT state then transition it to INIT. */
+	if (psp_master->sev_state != SEV_STATE_INIT) {
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		ret = __sev_platform_init_locked(&argp->error);
+		if (ret)
+			return ret;
+	}
+
 	if (copy_from_user(&input, (void __user *)argp->data, sizeof(input)))
 		return -EFAULT;
 
@@ -741,13 +772,6 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp)
 	data->cert_chain_len = input.cert_chain_len;
 
 cmd:
-	/* If platform is not in INIT state then transition it to INIT. */
-	if (psp_master->sev_state != SEV_STATE_INIT) {
-		ret = __sev_platform_init_locked(&argp->error);
-		if (ret)
-			goto e_free_cert;
-	}
-
 	ret = __sev_do_cmd_locked(SEV_CMD_PDH_CERT_EXPORT, data, &argp->error);
 
 	/* If we query the length, FW responded with expected data. */
@@ -929,8 +953,22 @@ static int sev_misc_init(struct psp_device *psp)
 
 static int psp_check_sev_support(struct psp_device *psp)
 {
-	/* Check if device supports SEV feature */
-	if (!(ioread32(psp->io_regs + psp->vdata->feature_reg) & 1)) {
+	unsigned int val = ioread32(psp->io_regs + psp->vdata->feature_reg);
+
+	/*
+	 * Check for a access to the registers.  If this read returns
+	 * 0xffffffff, it's likely that the system is running a broken
+	 * BIOS which disallows access to the device. Stop here and
+	 * fail the PSP initialization (but not the load, as the CCP
+	 * could get properly initialized).
+	 */
+	if (val == 0xffffffff) {
+		dev_notice(psp->dev, "psp: unable to access the device: you might be running a broken BIOS.\n");
+		return -ENODEV;
+	}
+
+	if (!(val & 1)) {
+		/* Device does not support the SEV feature */
 		dev_dbg(psp->dev, "psp does not support SEV\n");
 		return -ENODEV;
 	}
@@ -1064,6 +1102,18 @@ void psp_pci_init(void)
 
 	/* Initialize the platform */
 	rc = sev_platform_init(&error);
+	if (rc && (error == SEV_RET_SECURE_DATA_INVALID)) {
+		/*
+		 * INIT command returned an integrity check failure
+		 * status code, meaning that firmware load and
+		 * validation of SEV related persistent data has
+		 * failed and persistent state has been erased.
+		 * Retrying INIT command here should succeed.
+		 */
+		dev_dbg(sp->dev, "SEV: retrying INIT command");
+		rc = sev_platform_init(&error);
+	}
+
 	if (rc) {
 		dev_err(sp->dev, "SEV: failed to INIT error %#x\n", error);
 		return;
diff --git a/drivers/crypto/ccp/psp-dev.h b/drivers/crypto/ccp/psp-dev.h
index 82a084f02990..dd516b35ba86 100644
--- a/drivers/crypto/ccp/psp-dev.h
+++ b/drivers/crypto/ccp/psp-dev.h
@@ -23,6 +23,7 @@
 #include <linux/dmaengine.h>
 #include <linux/psp-sev.h>
 #include <linux/miscdevice.h>
+#include <linux/capability.h>
 
 #include "sp-dev.h"
 
diff --git a/drivers/crypto/ccree/cc_aead.c b/drivers/crypto/ccree/cc_aead.c
index d3e8faa03f15..64d318dc0d47 100644
--- a/drivers/crypto/ccree/cc_aead.c
+++ b/drivers/crypto/ccree/cc_aead.c
@@ -293,7 +293,8 @@ static unsigned int xcbc_setkey(struct cc_hw_desc *desc,
 	return 4;
 }
 
-static int hmac_setkey(struct cc_hw_desc *desc, struct cc_aead_ctx *ctx)
+static unsigned int hmac_setkey(struct cc_hw_desc *desc,
+				struct cc_aead_ctx *ctx)
 {
 	unsigned int hmac_pad_const[2] = { HMAC_IPAD_CONST, HMAC_OPAD_CONST };
 	unsigned int digest_ofs = 0;
diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index 254b48797799..3112b58d0bb1 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -16,7 +16,7 @@
 #include "cc_cipher.h"
 #include "cc_request_mgr.h"
 
-#define MAX_ABLKCIPHER_SEQ_LEN 6
+#define MAX_SKCIPHER_SEQ_LEN 6
 
 #define template_skcipher	template_u.skcipher
 
@@ -822,7 +822,7 @@ static int cc_cipher_process(struct skcipher_request *req,
 	void *iv = req->iv;
 	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
 	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
-	struct cc_hw_desc desc[MAX_ABLKCIPHER_SEQ_LEN];
+	struct cc_hw_desc desc[MAX_SKCIPHER_SEQ_LEN];
 	struct cc_crypto_req cc_req = {};
 	int rc;
 	unsigned int seq_len = 0;
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index 38ee38b37ae6..1b4a5664e604 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -93,7 +93,7 @@ static u32 round_constant[11] = {
 	0x1B000000, 0x36000000, 0x6C000000
 };
 
-static int chcr_handle_cipher_resp(struct ablkcipher_request *req,
+static int chcr_handle_cipher_resp(struct skcipher_request *req,
 				   unsigned char *input, int err);
 
 static inline  struct chcr_aead_ctx *AEAD_CTX(struct chcr_context *ctx)
@@ -568,11 +568,11 @@ static void  ulptx_walk_add_sg(struct ulptx_walk *walk,
 	}
 }
 
-static inline int get_cryptoalg_subtype(struct crypto_tfm *tfm)
+static inline int get_cryptoalg_subtype(struct crypto_skcipher *tfm)
 {
-	struct crypto_alg *alg = tfm->__crt_alg;
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
 	struct chcr_alg_template *chcr_crypto_alg =
-		container_of(alg, struct chcr_alg_template, alg.crypto);
+		container_of(alg, struct chcr_alg_template, alg.skcipher);
 
 	return chcr_crypto_alg->type & CRYPTO_ALG_SUB_TYPE_MASK;
 }
@@ -757,14 +757,14 @@ static inline void create_wreq(struct chcr_context *ctx,
  */
 static struct sk_buff *create_cipher_wr(struct cipher_wr_param *wrparam)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(wrparam->req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(wrparam->req);
 	struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(tfm));
 	struct sk_buff *skb = NULL;
 	struct chcr_wr *chcr_req;
 	struct cpl_rx_phys_dsgl *phys_cpl;
 	struct ulptx_sgl *ulptx;
-	struct chcr_blkcipher_req_ctx *reqctx =
-		ablkcipher_request_ctx(wrparam->req);
+	struct chcr_skcipher_req_ctx *reqctx =
+		skcipher_request_ctx(wrparam->req);
 	unsigned int temp = 0, transhdr_len, dst_size;
 	int error;
 	int nents;
@@ -807,9 +807,9 @@ static struct sk_buff *create_cipher_wr(struct cipher_wr_param *wrparam)
 
 	chcr_req->key_ctx.ctx_hdr = ablkctx->key_ctx_hdr;
 	if ((reqctx->op == CHCR_DECRYPT_OP) &&
-	    (!(get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm)) ==
+	    (!(get_cryptoalg_subtype(tfm) ==
 	       CRYPTO_ALG_SUB_TYPE_CTR)) &&
-	    (!(get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm)) ==
+	    (!(get_cryptoalg_subtype(tfm) ==
 	       CRYPTO_ALG_SUB_TYPE_CTR_RFC3686))) {
 		generate_copy_rrkey(ablkctx, &chcr_req->key_ctx);
 	} else {
@@ -843,7 +843,7 @@ static struct sk_buff *create_cipher_wr(struct cipher_wr_param *wrparam)
 	if (reqctx->op && (ablkctx->ciph_mode ==
 			   CHCR_SCMD_CIPHER_MODE_AES_CBC))
 		sg_pcopy_to_buffer(wrparam->req->src,
-			sg_nents(wrparam->req->src), wrparam->req->info, 16,
+			sg_nents(wrparam->req->src), wrparam->req->iv, 16,
 			reqctx->processed + wrparam->bytes - AES_BLOCK_SIZE);
 
 	return skb;
@@ -866,11 +866,11 @@ static inline int chcr_keyctx_ck_size(unsigned int keylen)
 
 	return ck_size;
 }
-static int chcr_cipher_fallback_setkey(struct crypto_ablkcipher *cipher,
+static int chcr_cipher_fallback_setkey(struct crypto_skcipher *cipher,
 				       const u8 *key,
 				       unsigned int keylen)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(cipher);
 	struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(cipher));
 	int err = 0;
 
@@ -886,7 +886,7 @@ static int chcr_cipher_fallback_setkey(struct crypto_ablkcipher *cipher,
 	return err;
 }
 
-static int chcr_aes_cbc_setkey(struct crypto_ablkcipher *cipher,
+static int chcr_aes_cbc_setkey(struct crypto_skcipher *cipher,
 			       const u8 *key,
 			       unsigned int keylen)
 {
@@ -912,13 +912,13 @@ static int chcr_aes_cbc_setkey(struct crypto_ablkcipher *cipher,
 	ablkctx->ciph_mode = CHCR_SCMD_CIPHER_MODE_AES_CBC;
 	return 0;
 badkey_err:
-	crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	crypto_skcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
 	ablkctx->enckey_len = 0;
 
 	return err;
 }
 
-static int chcr_aes_ctr_setkey(struct crypto_ablkcipher *cipher,
+static int chcr_aes_ctr_setkey(struct crypto_skcipher *cipher,
 				   const u8 *key,
 				   unsigned int keylen)
 {
@@ -943,13 +943,13 @@ static int chcr_aes_ctr_setkey(struct crypto_ablkcipher *cipher,
 
 	return 0;
 badkey_err:
-	crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	crypto_skcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
 	ablkctx->enckey_len = 0;
 
 	return err;
 }
 
-static int chcr_aes_rfc3686_setkey(struct crypto_ablkcipher *cipher,
+static int chcr_aes_rfc3686_setkey(struct crypto_skcipher *cipher,
 				   const u8 *key,
 				   unsigned int keylen)
 {
@@ -981,7 +981,7 @@ static int chcr_aes_rfc3686_setkey(struct crypto_ablkcipher *cipher,
 
 	return 0;
 badkey_err:
-	crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	crypto_skcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
 	ablkctx->enckey_len = 0;
 
 	return err;
@@ -1017,12 +1017,12 @@ static unsigned int adjust_ctr_overflow(u8 *iv, u32 bytes)
 	return bytes;
 }
 
-static int chcr_update_tweak(struct ablkcipher_request *req, u8 *iv,
+static int chcr_update_tweak(struct skcipher_request *req, u8 *iv,
 			     u32 isfinal)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(tfm));
-	struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
+	struct chcr_skcipher_req_ctx *reqctx = skcipher_request_ctx(req);
 	struct crypto_aes_ctx aes;
 	int ret, i;
 	u8 *key;
@@ -1051,16 +1051,16 @@ static int chcr_update_tweak(struct ablkcipher_request *req, u8 *iv,
 	return 0;
 }
 
-static int chcr_update_cipher_iv(struct ablkcipher_request *req,
+static int chcr_update_cipher_iv(struct skcipher_request *req,
 				   struct cpl_fw6_pld *fw6_pld, u8 *iv)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
-	int subtype = get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm));
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chcr_skcipher_req_ctx *reqctx = skcipher_request_ctx(req);
+	int subtype = get_cryptoalg_subtype(tfm);
 	int ret = 0;
 
 	if (subtype == CRYPTO_ALG_SUB_TYPE_CTR)
-		ctr_add_iv(iv, req->info, (reqctx->processed /
+		ctr_add_iv(iv, req->iv, (reqctx->processed /
 			   AES_BLOCK_SIZE));
 	else if (subtype == CRYPTO_ALG_SUB_TYPE_CTR_RFC3686)
 		*(__be32 *)(reqctx->iv + CTR_RFC3686_NONCE_SIZE +
@@ -1071,7 +1071,7 @@ static int chcr_update_cipher_iv(struct ablkcipher_request *req,
 	else if (subtype == CRYPTO_ALG_SUB_TYPE_CBC) {
 		if (reqctx->op)
 			/*Updated before sending last WR*/
-			memcpy(iv, req->info, AES_BLOCK_SIZE);
+			memcpy(iv, req->iv, AES_BLOCK_SIZE);
 		else
 			memcpy(iv, &fw6_pld->data[2], AES_BLOCK_SIZE);
 	}
@@ -1085,16 +1085,16 @@ static int chcr_update_cipher_iv(struct ablkcipher_request *req,
  * for subsequent update requests
  */
 
-static int chcr_final_cipher_iv(struct ablkcipher_request *req,
+static int chcr_final_cipher_iv(struct skcipher_request *req,
 				   struct cpl_fw6_pld *fw6_pld, u8 *iv)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
-	int subtype = get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm));
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chcr_skcipher_req_ctx *reqctx = skcipher_request_ctx(req);
+	int subtype = get_cryptoalg_subtype(tfm);
 	int ret = 0;
 
 	if (subtype == CRYPTO_ALG_SUB_TYPE_CTR)
-		ctr_add_iv(iv, req->info, DIV_ROUND_UP(reqctx->processed,
+		ctr_add_iv(iv, req->iv, DIV_ROUND_UP(reqctx->processed,
 						       AES_BLOCK_SIZE));
 	else if (subtype == CRYPTO_ALG_SUB_TYPE_XTS)
 		ret = chcr_update_tweak(req, iv, 1);
@@ -1108,25 +1108,25 @@ static int chcr_final_cipher_iv(struct ablkcipher_request *req,
 
 }
 
-static int chcr_handle_cipher_resp(struct ablkcipher_request *req,
+static int chcr_handle_cipher_resp(struct skcipher_request *req,
 				   unsigned char *input, int err)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct uld_ctx *u_ctx = ULD_CTX(c_ctx(tfm));
 	struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(tfm));
 	struct sk_buff *skb;
 	struct cpl_fw6_pld *fw6_pld = (struct cpl_fw6_pld *)input;
-	struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
+	struct chcr_skcipher_req_ctx *reqctx = skcipher_request_ctx(req);
 	struct  cipher_wr_param wrparam;
 	struct chcr_dev *dev = c_ctx(tfm)->dev;
 	int bytes;
 
 	if (err)
 		goto unmap;
-	if (req->nbytes == reqctx->processed) {
+	if (req->cryptlen == reqctx->processed) {
 		chcr_cipher_dma_unmap(&ULD_CTX(c_ctx(tfm))->lldi.pdev->dev,
 				      req);
-		err = chcr_final_cipher_iv(req, fw6_pld, req->info);
+		err = chcr_final_cipher_iv(req, fw6_pld, req->iv);
 		goto complete;
 	}
 
@@ -1134,13 +1134,13 @@ static int chcr_handle_cipher_resp(struct ablkcipher_request *req,
 		bytes = chcr_sg_ent_in_wr(reqctx->srcsg, reqctx->dstsg, 0,
 					  CIP_SPACE_LEFT(ablkctx->enckey_len),
 					  reqctx->src_ofst, reqctx->dst_ofst);
-		if ((bytes + reqctx->processed) >= req->nbytes)
-			bytes  = req->nbytes - reqctx->processed;
+		if ((bytes + reqctx->processed) >= req->cryptlen)
+			bytes  = req->cryptlen - reqctx->processed;
 		else
 			bytes = rounddown(bytes, 16);
 	} else {
 		/*CTR mode counter overfloa*/
-		bytes  = req->nbytes - reqctx->processed;
+		bytes  = req->cryptlen - reqctx->processed;
 	}
 	err = chcr_update_cipher_iv(req, fw6_pld, reqctx->iv);
 	if (err)
@@ -1153,13 +1153,13 @@ static int chcr_handle_cipher_resp(struct ablkcipher_request *req,
 				     req->base.flags,
 				     req->src,
 				     req->dst,
-				     req->nbytes,
-				     req->info,
+				     req->cryptlen,
+				     req->iv,
 				     reqctx->op);
 		goto complete;
 	}
 
-	if (get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm)) ==
+	if (get_cryptoalg_subtype(tfm) ==
 	    CRYPTO_ALG_SUB_TYPE_CTR)
 		bytes = adjust_ctr_overflow(reqctx->iv, bytes);
 	wrparam.qid = u_ctx->lldi.rxq_ids[c_ctx(tfm)->rx_qidx];
@@ -1185,33 +1185,33 @@ complete:
 	return err;
 }
 
-static int process_cipher(struct ablkcipher_request *req,
+static int process_cipher(struct skcipher_request *req,
 				  unsigned short qid,
 				  struct sk_buff **skb,
 				  unsigned short op_type)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	unsigned int ivsize = crypto_ablkcipher_ivsize(tfm);
-	struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	unsigned int ivsize = crypto_skcipher_ivsize(tfm);
+	struct chcr_skcipher_req_ctx *reqctx = skcipher_request_ctx(req);
 	struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(tfm));
 	struct	cipher_wr_param wrparam;
 	int bytes, err = -EINVAL;
 
 	reqctx->processed = 0;
-	if (!req->info)
+	if (!req->iv)
 		goto error;
 	if ((ablkctx->enckey_len == 0) || (ivsize > AES_BLOCK_SIZE) ||
-	    (req->nbytes == 0) ||
-	    (req->nbytes % crypto_ablkcipher_blocksize(tfm))) {
+	    (req->cryptlen == 0) ||
+	    (req->cryptlen % crypto_skcipher_blocksize(tfm))) {
 		pr_err("AES: Invalid value of Key Len %d nbytes %d IV Len %d\n",
-		       ablkctx->enckey_len, req->nbytes, ivsize);
+		       ablkctx->enckey_len, req->cryptlen, ivsize);
 		goto error;
 	}
 
 	err = chcr_cipher_dma_map(&ULD_CTX(c_ctx(tfm))->lldi.pdev->dev, req);
 	if (err)
 		goto error;
-	if (req->nbytes < (SGE_MAX_WR_LEN - (sizeof(struct chcr_wr) +
+	if (req->cryptlen < (SGE_MAX_WR_LEN - (sizeof(struct chcr_wr) +
 					    AES_MIN_KEY_SIZE +
 					    sizeof(struct cpl_rx_phys_dsgl) +
 					/*Min dsgl size*/
@@ -1219,14 +1219,14 @@ static int process_cipher(struct ablkcipher_request *req,
 		/* Can be sent as Imm*/
 		unsigned int dnents = 0, transhdr_len, phys_dsgl, kctx_len;
 
-		dnents = sg_nents_xlen(req->dst, req->nbytes,
+		dnents = sg_nents_xlen(req->dst, req->cryptlen,
 				       CHCR_DST_SG_SIZE, 0);
 		phys_dsgl = get_space_for_phys_dsgl(dnents);
 		kctx_len = roundup(ablkctx->enckey_len, 16);
 		transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, phys_dsgl);
-		reqctx->imm = (transhdr_len + IV + req->nbytes) <=
+		reqctx->imm = (transhdr_len + IV + req->cryptlen) <=
 			SGE_MAX_WR_LEN;
-		bytes = IV + req->nbytes;
+		bytes = IV + req->cryptlen;
 
 	} else {
 		reqctx->imm = 0;
@@ -1236,21 +1236,21 @@ static int process_cipher(struct ablkcipher_request *req,
 		bytes = chcr_sg_ent_in_wr(req->src, req->dst, 0,
 					  CIP_SPACE_LEFT(ablkctx->enckey_len),
 					  0, 0);
-		if ((bytes + reqctx->processed) >= req->nbytes)
-			bytes  = req->nbytes - reqctx->processed;
+		if ((bytes + reqctx->processed) >= req->cryptlen)
+			bytes  = req->cryptlen - reqctx->processed;
 		else
 			bytes = rounddown(bytes, 16);
 	} else {
-		bytes = req->nbytes;
+		bytes = req->cryptlen;
 	}
-	if (get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm)) ==
+	if (get_cryptoalg_subtype(tfm) ==
 	    CRYPTO_ALG_SUB_TYPE_CTR) {
-		bytes = adjust_ctr_overflow(req->info, bytes);
+		bytes = adjust_ctr_overflow(req->iv, bytes);
 	}
-	if (get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm)) ==
+	if (get_cryptoalg_subtype(tfm) ==
 	    CRYPTO_ALG_SUB_TYPE_CTR_RFC3686) {
 		memcpy(reqctx->iv, ablkctx->nonce, CTR_RFC3686_NONCE_SIZE);
-		memcpy(reqctx->iv + CTR_RFC3686_NONCE_SIZE, req->info,
+		memcpy(reqctx->iv + CTR_RFC3686_NONCE_SIZE, req->iv,
 				CTR_RFC3686_IV_SIZE);
 
 		/* initialize counter portion of counter block */
@@ -1259,7 +1259,7 @@ static int process_cipher(struct ablkcipher_request *req,
 
 	} else {
 
-		memcpy(reqctx->iv, req->info, IV);
+		memcpy(reqctx->iv, req->iv, IV);
 	}
 	if (unlikely(bytes == 0)) {
 		chcr_cipher_dma_unmap(&ULD_CTX(c_ctx(tfm))->lldi.pdev->dev,
@@ -1268,7 +1268,7 @@ static int process_cipher(struct ablkcipher_request *req,
 					   req->base.flags,
 					   req->src,
 					   req->dst,
-					   req->nbytes,
+					   req->cryptlen,
 					   reqctx->iv,
 					   op_type);
 		goto error;
@@ -1296,9 +1296,9 @@ error:
 	return err;
 }
 
-static int chcr_aes_encrypt(struct ablkcipher_request *req)
+static int chcr_aes_encrypt(struct skcipher_request *req)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chcr_dev *dev = c_ctx(tfm)->dev;
 	struct sk_buff *skb = NULL;
 	int err, isfull = 0;
@@ -1329,9 +1329,9 @@ error:
 	return err;
 }
 
-static int chcr_aes_decrypt(struct ablkcipher_request *req)
+static int chcr_aes_decrypt(struct skcipher_request *req)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct uld_ctx *u_ctx = ULD_CTX(c_ctx(tfm));
 	struct chcr_dev *dev = c_ctx(tfm)->dev;
 	struct sk_buff *skb = NULL;
@@ -1398,27 +1398,28 @@ out:
 	return err;
 }
 
-static int chcr_cra_init(struct crypto_tfm *tfm)
+static int chcr_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct crypto_alg *alg = tfm->__crt_alg;
-	struct chcr_context *ctx = crypto_tfm_ctx(tfm);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	struct chcr_context *ctx = crypto_skcipher_ctx(tfm);
 	struct ablk_ctx *ablkctx = ABLK_CTX(ctx);
 
-	ablkctx->sw_cipher = crypto_alloc_sync_skcipher(alg->cra_name, 0,
+	ablkctx->sw_cipher = crypto_alloc_sync_skcipher(alg->base.cra_name, 0,
 				CRYPTO_ALG_NEED_FALLBACK);
 	if (IS_ERR(ablkctx->sw_cipher)) {
-		pr_err("failed to allocate fallback for %s\n", alg->cra_name);
+		pr_err("failed to allocate fallback for %s\n", alg->base.cra_name);
 		return PTR_ERR(ablkctx->sw_cipher);
 	}
 
-	tfm->crt_ablkcipher.reqsize =  sizeof(struct chcr_blkcipher_req_ctx);
-	return chcr_device_init(crypto_tfm_ctx(tfm));
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct chcr_skcipher_req_ctx));
+
+	return chcr_device_init(ctx);
 }
 
-static int chcr_rfc3686_init(struct crypto_tfm *tfm)
+static int chcr_rfc3686_init(struct crypto_skcipher *tfm)
 {
-	struct crypto_alg *alg = tfm->__crt_alg;
-	struct chcr_context *ctx = crypto_tfm_ctx(tfm);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	struct chcr_context *ctx = crypto_skcipher_ctx(tfm);
 	struct ablk_ctx *ablkctx = ABLK_CTX(ctx);
 
 	/*RFC3686 initialises IV counter value to 1, rfc3686(ctr(aes))
@@ -1427,17 +1428,17 @@ static int chcr_rfc3686_init(struct crypto_tfm *tfm)
 	ablkctx->sw_cipher = crypto_alloc_sync_skcipher("ctr(aes)", 0,
 				CRYPTO_ALG_NEED_FALLBACK);
 	if (IS_ERR(ablkctx->sw_cipher)) {
-		pr_err("failed to allocate fallback for %s\n", alg->cra_name);
+		pr_err("failed to allocate fallback for %s\n", alg->base.cra_name);
 		return PTR_ERR(ablkctx->sw_cipher);
 	}
-	tfm->crt_ablkcipher.reqsize =  sizeof(struct chcr_blkcipher_req_ctx);
-	return chcr_device_init(crypto_tfm_ctx(tfm));
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct chcr_skcipher_req_ctx));
+	return chcr_device_init(ctx);
 }
 
 
-static void chcr_cra_exit(struct crypto_tfm *tfm)
+static void chcr_exit_tfm(struct crypto_skcipher *tfm)
 {
-	struct chcr_context *ctx = crypto_tfm_ctx(tfm);
+	struct chcr_context *ctx = crypto_skcipher_ctx(tfm);
 	struct ablk_ctx *ablkctx = ABLK_CTX(ctx);
 
 	crypto_free_sync_skcipher(ablkctx->sw_cipher);
@@ -2056,8 +2057,8 @@ int chcr_handle_resp(struct crypto_async_request *req, unsigned char *input,
 		err = chcr_handle_aead_resp(aead_request_cast(req), input, err);
 		break;
 
-	case CRYPTO_ALG_TYPE_ABLKCIPHER:
-		 chcr_handle_cipher_resp(ablkcipher_request_cast(req),
+	case CRYPTO_ALG_TYPE_SKCIPHER:
+		 chcr_handle_cipher_resp(skcipher_request_cast(req),
 					       input, err);
 		break;
 	case CRYPTO_ALG_TYPE_AHASH:
@@ -2148,7 +2149,7 @@ out:
 	return err;
 }
 
-static int chcr_aes_xts_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int chcr_aes_xts_setkey(struct crypto_skcipher *cipher, const u8 *key,
 			       unsigned int key_len)
 {
 	struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(cipher));
@@ -2172,7 +2173,7 @@ static int chcr_aes_xts_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	ablkctx->ciph_mode = CHCR_SCMD_CIPHER_MODE_AES_XTS;
 	return 0;
 badkey_err:
-	crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	crypto_skcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
 	ablkctx->enckey_len = 0;
 
 	return err;
@@ -2576,12 +2577,12 @@ void chcr_add_aead_dst_ent(struct aead_request *req,
 	dsgl_walk_end(&dsgl_walk, qid, ctx->pci_chan_id);
 }
 
-void chcr_add_cipher_src_ent(struct ablkcipher_request *req,
+void chcr_add_cipher_src_ent(struct skcipher_request *req,
 			     void *ulptx,
 			     struct  cipher_wr_param *wrparam)
 {
 	struct ulptx_walk ulp_walk;
-	struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
+	struct chcr_skcipher_req_ctx *reqctx = skcipher_request_ctx(req);
 	u8 *buf = ulptx;
 
 	memcpy(buf, reqctx->iv, IV);
@@ -2599,13 +2600,13 @@ void chcr_add_cipher_src_ent(struct ablkcipher_request *req,
 	}
 }
 
-void chcr_add_cipher_dst_ent(struct ablkcipher_request *req,
+void chcr_add_cipher_dst_ent(struct skcipher_request *req,
 			     struct cpl_rx_phys_dsgl *phys_cpl,
 			     struct  cipher_wr_param *wrparam,
 			     unsigned short qid)
 {
-	struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(wrparam->req);
+	struct chcr_skcipher_req_ctx *reqctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(wrparam->req);
 	struct chcr_context *ctx = c_ctx(tfm);
 	struct dsgl_walk dsgl_walk;
 
@@ -2680,7 +2681,7 @@ void chcr_hash_dma_unmap(struct device *dev,
 }
 
 int chcr_cipher_dma_map(struct device *dev,
-			struct ablkcipher_request *req)
+			struct skcipher_request *req)
 {
 	int error;
 
@@ -2709,7 +2710,7 @@ err:
 }
 
 void chcr_cipher_dma_unmap(struct device *dev,
-			   struct ablkcipher_request *req)
+			   struct skcipher_request *req)
 {
 	if (req->src == req->dst) {
 		dma_unmap_sg(dev, req->src, sg_nents(req->src),
@@ -3712,82 +3713,76 @@ static int chcr_aead_decrypt(struct aead_request *req)
 static struct chcr_alg_template driver_algs[] = {
 	/* AES-CBC */
 	{
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_SUB_TYPE_CBC,
+		.type = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_SUB_TYPE_CBC,
 		.is_registered = 0,
-		.alg.crypto = {
-			.cra_name		= "cbc(aes)",
-			.cra_driver_name	= "cbc-aes-chcr",
-			.cra_blocksize		= AES_BLOCK_SIZE,
-			.cra_init		= chcr_cra_init,
-			.cra_exit		= chcr_cra_exit,
-			.cra_u.ablkcipher	= {
-				.min_keysize	= AES_MIN_KEY_SIZE,
-				.max_keysize	= AES_MAX_KEY_SIZE,
-				.ivsize		= AES_BLOCK_SIZE,
-				.setkey			= chcr_aes_cbc_setkey,
-				.encrypt		= chcr_aes_encrypt,
-				.decrypt		= chcr_aes_decrypt,
+		.alg.skcipher = {
+			.base.cra_name		= "cbc(aes)",
+			.base.cra_driver_name	= "cbc-aes-chcr",
+			.base.cra_blocksize	= AES_BLOCK_SIZE,
+
+			.init			= chcr_init_tfm,
+			.exit			= chcr_exit_tfm,
+			.min_keysize		= AES_MIN_KEY_SIZE,
+			.max_keysize		= AES_MAX_KEY_SIZE,
+			.ivsize			= AES_BLOCK_SIZE,
+			.setkey			= chcr_aes_cbc_setkey,
+			.encrypt		= chcr_aes_encrypt,
+			.decrypt		= chcr_aes_decrypt,
 			}
-		}
 	},
 	{
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_SUB_TYPE_XTS,
+		.type = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_SUB_TYPE_XTS,
 		.is_registered = 0,
-		.alg.crypto =   {
-			.cra_name		= "xts(aes)",
-			.cra_driver_name	= "xts-aes-chcr",
-			.cra_blocksize		= AES_BLOCK_SIZE,
-			.cra_init		= chcr_cra_init,
-			.cra_exit		= NULL,
-			.cra_u .ablkcipher = {
-					.min_keysize	= 2 * AES_MIN_KEY_SIZE,
-					.max_keysize	= 2 * AES_MAX_KEY_SIZE,
-					.ivsize		= AES_BLOCK_SIZE,
-					.setkey		= chcr_aes_xts_setkey,
-					.encrypt	= chcr_aes_encrypt,
-					.decrypt	= chcr_aes_decrypt,
-				}
+		.alg.skcipher = {
+			.base.cra_name		= "xts(aes)",
+			.base.cra_driver_name	= "xts-aes-chcr",
+			.base.cra_blocksize	= AES_BLOCK_SIZE,
+
+			.init			= chcr_init_tfm,
+			.exit			= chcr_exit_tfm,
+			.min_keysize		= 2 * AES_MIN_KEY_SIZE,
+			.max_keysize		= 2 * AES_MAX_KEY_SIZE,
+			.ivsize			= AES_BLOCK_SIZE,
+			.setkey			= chcr_aes_xts_setkey,
+			.encrypt		= chcr_aes_encrypt,
+			.decrypt		= chcr_aes_decrypt,
 			}
 	},
 	{
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_SUB_TYPE_CTR,
+		.type = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_SUB_TYPE_CTR,
 		.is_registered = 0,
-		.alg.crypto = {
-			.cra_name		= "ctr(aes)",
-			.cra_driver_name	= "ctr-aes-chcr",
-			.cra_blocksize		= 1,
-			.cra_init		= chcr_cra_init,
-			.cra_exit		= chcr_cra_exit,
-			.cra_u.ablkcipher	= {
-				.min_keysize	= AES_MIN_KEY_SIZE,
-				.max_keysize	= AES_MAX_KEY_SIZE,
-				.ivsize		= AES_BLOCK_SIZE,
-				.setkey		= chcr_aes_ctr_setkey,
-				.encrypt	= chcr_aes_encrypt,
-				.decrypt	= chcr_aes_decrypt,
-			}
+		.alg.skcipher = {
+			.base.cra_name		= "ctr(aes)",
+			.base.cra_driver_name	= "ctr-aes-chcr",
+			.base.cra_blocksize	= 1,
+
+			.init			= chcr_init_tfm,
+			.exit			= chcr_exit_tfm,
+			.min_keysize		= AES_MIN_KEY_SIZE,
+			.max_keysize		= AES_MAX_KEY_SIZE,
+			.ivsize			= AES_BLOCK_SIZE,
+			.setkey			= chcr_aes_ctr_setkey,
+			.encrypt		= chcr_aes_encrypt,
+			.decrypt		= chcr_aes_decrypt,
 		}
 	},
 	{
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER |
+		.type = CRYPTO_ALG_TYPE_SKCIPHER |
 			CRYPTO_ALG_SUB_TYPE_CTR_RFC3686,
 		.is_registered = 0,
-		.alg.crypto = {
-			.cra_name		= "rfc3686(ctr(aes))",
-			.cra_driver_name	= "rfc3686-ctr-aes-chcr",
-			.cra_blocksize		= 1,
-			.cra_init		= chcr_rfc3686_init,
-			.cra_exit		= chcr_cra_exit,
-			.cra_u.ablkcipher	= {
-				.min_keysize	= AES_MIN_KEY_SIZE +
-					CTR_RFC3686_NONCE_SIZE,
-				.max_keysize	= AES_MAX_KEY_SIZE +
-					CTR_RFC3686_NONCE_SIZE,
-				.ivsize		= CTR_RFC3686_IV_SIZE,
-				.setkey		= chcr_aes_rfc3686_setkey,
-				.encrypt	= chcr_aes_encrypt,
-				.decrypt	= chcr_aes_decrypt,
-			}
+		.alg.skcipher = {
+			.base.cra_name		= "rfc3686(ctr(aes))",
+			.base.cra_driver_name	= "rfc3686-ctr-aes-chcr",
+			.base.cra_blocksize	= 1,
+
+			.init			= chcr_rfc3686_init,
+			.exit			= chcr_exit_tfm,
+			.min_keysize		= AES_MIN_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
+			.max_keysize		= AES_MAX_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
+			.ivsize			= CTR_RFC3686_IV_SIZE,
+			.setkey			= chcr_aes_rfc3686_setkey,
+			.encrypt		= chcr_aes_encrypt,
+			.decrypt		= chcr_aes_decrypt,
 		}
 	},
 	/* SHA */
@@ -4254,10 +4249,10 @@ static int chcr_unregister_alg(void)
 
 	for (i = 0; i < ARRAY_SIZE(driver_algs); i++) {
 		switch (driver_algs[i].type & CRYPTO_ALG_TYPE_MASK) {
-		case CRYPTO_ALG_TYPE_ABLKCIPHER:
+		case CRYPTO_ALG_TYPE_SKCIPHER:
 			if (driver_algs[i].is_registered)
-				crypto_unregister_alg(
-						&driver_algs[i].alg.crypto);
+				crypto_unregister_skcipher(
+						&driver_algs[i].alg.skcipher);
 			break;
 		case CRYPTO_ALG_TYPE_AEAD:
 			if (driver_algs[i].is_registered)
@@ -4293,21 +4288,20 @@ static int chcr_register_alg(void)
 		if (driver_algs[i].is_registered)
 			continue;
 		switch (driver_algs[i].type & CRYPTO_ALG_TYPE_MASK) {
-		case CRYPTO_ALG_TYPE_ABLKCIPHER:
-			driver_algs[i].alg.crypto.cra_priority =
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			driver_algs[i].alg.skcipher.base.cra_priority =
 				CHCR_CRA_PRIORITY;
-			driver_algs[i].alg.crypto.cra_module = THIS_MODULE;
-			driver_algs[i].alg.crypto.cra_flags =
-				CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC |
+			driver_algs[i].alg.skcipher.base.cra_module = THIS_MODULE;
+			driver_algs[i].alg.skcipher.base.cra_flags =
+				CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC |
 				CRYPTO_ALG_NEED_FALLBACK;
-			driver_algs[i].alg.crypto.cra_ctxsize =
+			driver_algs[i].alg.skcipher.base.cra_ctxsize =
 				sizeof(struct chcr_context) +
 				sizeof(struct ablk_ctx);
-			driver_algs[i].alg.crypto.cra_alignmask = 0;
-			driver_algs[i].alg.crypto.cra_type =
-				&crypto_ablkcipher_type;
-			err = crypto_register_alg(&driver_algs[i].alg.crypto);
-			name = driver_algs[i].alg.crypto.cra_driver_name;
+			driver_algs[i].alg.skcipher.base.cra_alignmask = 0;
+
+			err = crypto_register_skcipher(&driver_algs[i].alg.skcipher);
+			name = driver_algs[i].alg.skcipher.base.cra_driver_name;
 			break;
 		case CRYPTO_ALG_TYPE_AEAD:
 			driver_algs[i].alg.aead.base.cra_flags =
diff --git a/drivers/crypto/chelsio/chcr_algo.h b/drivers/crypto/chelsio/chcr_algo.h
index d1e6b51df0ce..f58c2b5c7fc5 100644
--- a/drivers/crypto/chelsio/chcr_algo.h
+++ b/drivers/crypto/chelsio/chcr_algo.h
@@ -287,7 +287,7 @@ struct hash_wr_param {
 };
 
 struct cipher_wr_param {
-	struct ablkcipher_request *req;
+	struct skcipher_request *req;
 	char *iv;
 	int bytes;
 	unsigned short qid;
diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h
index 993c97e70565..6db2df8c8a05 100644
--- a/drivers/crypto/chelsio/chcr_crypto.h
+++ b/drivers/crypto/chelsio/chcr_crypto.h
@@ -160,9 +160,9 @@ static inline struct chcr_context *a_ctx(struct crypto_aead *tfm)
 	return crypto_aead_ctx(tfm);
 }
 
-static inline struct chcr_context *c_ctx(struct crypto_ablkcipher *tfm)
+static inline struct chcr_context *c_ctx(struct crypto_skcipher *tfm)
 {
-	return crypto_ablkcipher_ctx(tfm);
+	return crypto_skcipher_ctx(tfm);
 }
 
 static inline struct chcr_context *h_ctx(struct crypto_ahash *tfm)
@@ -285,7 +285,7 @@ struct chcr_ahash_req_ctx {
 	u8 bfr2[CHCR_HASH_MAX_BLOCK_SIZE_128];
 };
 
-struct chcr_blkcipher_req_ctx {
+struct chcr_skcipher_req_ctx {
 	struct sk_buff *skb;
 	struct scatterlist *dstsg;
 	unsigned int processed;
@@ -302,7 +302,7 @@ struct chcr_alg_template {
 	u32 type;
 	u32 is_registered;
 	union {
-		struct crypto_alg crypto;
+		struct skcipher_alg skcipher;
 		struct ahash_alg hash;
 		struct aead_alg aead;
 	} alg;
@@ -321,12 +321,12 @@ void chcr_add_aead_dst_ent(struct aead_request *req,
 			   struct cpl_rx_phys_dsgl *phys_cpl,
 			   unsigned short qid);
 void chcr_add_aead_src_ent(struct aead_request *req, struct ulptx_sgl *ulptx);
-void chcr_add_cipher_src_ent(struct ablkcipher_request *req,
+void chcr_add_cipher_src_ent(struct skcipher_request *req,
 			     void *ulptx,
 			     struct  cipher_wr_param *wrparam);
-int chcr_cipher_dma_map(struct device *dev, struct ablkcipher_request *req);
-void chcr_cipher_dma_unmap(struct device *dev, struct ablkcipher_request *req);
-void chcr_add_cipher_dst_ent(struct ablkcipher_request *req,
+int chcr_cipher_dma_map(struct device *dev, struct skcipher_request *req);
+void chcr_cipher_dma_unmap(struct device *dev, struct skcipher_request *req);
+void chcr_add_cipher_dst_ent(struct skcipher_request *req,
 			     struct cpl_rx_phys_dsgl *phys_cpl,
 			     struct  cipher_wr_param *wrparam,
 			     unsigned short qid);
diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
index 599dec59c6cc..5cf9b021220b 100644
--- a/drivers/crypto/chelsio/chtls/chtls_io.c
+++ b/drivers/crypto/chelsio/chtls/chtls_io.c
@@ -97,7 +97,7 @@ static struct sk_buff *create_flowc_wr_skb(struct sock *sk,
 	if (!skb)
 		return NULL;
 
-	memcpy(__skb_put(skb, flowclen), flowc, flowclen);
+	__skb_put_data(skb, flowc, flowclen);
 	skb_set_queue_mapping(skb, (csk->txq_idx << 1) | CPL_PRIORITY_DATA);
 
 	return skb;
@@ -1841,8 +1841,7 @@ skip_copy:
 			tp->urg_data = 0;
 
 		if (avail + offset >= skb->len) {
-			if (likely(skb))
-				chtls_free_skb(sk, skb);
+			chtls_free_skb(sk, skb);
 			buffers_freed++;
 
 			if  (copied >= target &&
diff --git a/drivers/crypto/geode-aes.c b/drivers/crypto/geode-aes.c
index d81a1297cb9e..73a899e6f837 100644
--- a/drivers/crypto/geode-aes.c
+++ b/drivers/crypto/geode-aes.c
@@ -10,6 +10,7 @@
 #include <linux/spinlock.h>
 #include <crypto/algapi.h>
 #include <crypto/aes.h>
+#include <crypto/internal/skcipher.h>
 
 #include <linux/io.h>
 #include <linux/delay.h>
@@ -23,12 +24,12 @@ static spinlock_t lock;
 
 /* Write a 128 bit field (either a writable key or IV) */
 static inline void
-_writefield(u32 offset, void *value)
+_writefield(u32 offset, const void *value)
 {
 	int i;
 
 	for (i = 0; i < 4; i++)
-		iowrite32(((u32 *) value)[i], _iobase + offset + (i * 4));
+		iowrite32(((const u32 *) value)[i], _iobase + offset + (i * 4));
 }
 
 /* Read a 128 bit field (either a writable key or IV) */
@@ -42,12 +43,12 @@ _readfield(u32 offset, void *value)
 }
 
 static int
-do_crypt(void *src, void *dst, int len, u32 flags)
+do_crypt(const void *src, void *dst, u32 len, u32 flags)
 {
 	u32 status;
 	u32 counter = AES_OP_TIMEOUT;
 
-	iowrite32(virt_to_phys(src), _iobase + AES_SOURCEA_REG);
+	iowrite32(virt_to_phys((void *)src), _iobase + AES_SOURCEA_REG);
 	iowrite32(virt_to_phys(dst), _iobase + AES_DSTA_REG);
 	iowrite32(len,  _iobase + AES_LENA_REG);
 
@@ -64,16 +65,14 @@ do_crypt(void *src, void *dst, int len, u32 flags)
 	return counter ? 0 : 1;
 }
 
-static unsigned int
-geode_aes_crypt(struct geode_aes_op *op)
+static void
+geode_aes_crypt(const struct geode_aes_tfm_ctx *tctx, const void *src,
+		void *dst, u32 len, u8 *iv, int mode, int dir)
 {
 	u32 flags = 0;
 	unsigned long iflags;
 	int ret;
 
-	if (op->len == 0)
-		return 0;
-
 	/* If the source and destination is the same, then
 	 * we need to turn on the coherent flags, otherwise
 	 * we don't need to worry
@@ -81,32 +80,28 @@ geode_aes_crypt(struct geode_aes_op *op)
 
 	flags |= (AES_CTRL_DCA | AES_CTRL_SCA);
 
-	if (op->dir == AES_DIR_ENCRYPT)
+	if (dir == AES_DIR_ENCRYPT)
 		flags |= AES_CTRL_ENCRYPT;
 
 	/* Start the critical section */
 
 	spin_lock_irqsave(&lock, iflags);
 
-	if (op->mode == AES_MODE_CBC) {
+	if (mode == AES_MODE_CBC) {
 		flags |= AES_CTRL_CBC;
-		_writefield(AES_WRITEIV0_REG, op->iv);
+		_writefield(AES_WRITEIV0_REG, iv);
 	}
 
-	if (!(op->flags & AES_FLAGS_HIDDENKEY)) {
-		flags |= AES_CTRL_WRKEY;
-		_writefield(AES_WRITEKEY0_REG, op->key);
-	}
+	flags |= AES_CTRL_WRKEY;
+	_writefield(AES_WRITEKEY0_REG, tctx->key);
 
-	ret = do_crypt(op->src, op->dst, op->len, flags);
+	ret = do_crypt(src, dst, len, flags);
 	BUG_ON(ret);
 
-	if (op->mode == AES_MODE_CBC)
-		_readfield(AES_WRITEIV0_REG, op->iv);
+	if (mode == AES_MODE_CBC)
+		_readfield(AES_WRITEIV0_REG, iv);
 
 	spin_unlock_irqrestore(&lock, iflags);
-
-	return op->len;
 }
 
 /* CRYPTO-API Functions */
@@ -114,13 +109,13 @@ geode_aes_crypt(struct geode_aes_op *op)
 static int geode_setkey_cip(struct crypto_tfm *tfm, const u8 *key,
 		unsigned int len)
 {
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
+	struct geode_aes_tfm_ctx *tctx = crypto_tfm_ctx(tfm);
 	unsigned int ret;
 
-	op->keylen = len;
+	tctx->keylen = len;
 
 	if (len == AES_KEYSIZE_128) {
-		memcpy(op->key, key, len);
+		memcpy(tctx->key, key, len);
 		return 0;
 	}
 
@@ -133,135 +128,93 @@ static int geode_setkey_cip(struct crypto_tfm *tfm, const u8 *key,
 	/*
 	 * The requested key size is not supported by HW, do a fallback
 	 */
-	op->fallback.cip->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-	op->fallback.cip->base.crt_flags |= (tfm->crt_flags & CRYPTO_TFM_REQ_MASK);
+	tctx->fallback.cip->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
+	tctx->fallback.cip->base.crt_flags |=
+		(tfm->crt_flags & CRYPTO_TFM_REQ_MASK);
 
-	ret = crypto_cipher_setkey(op->fallback.cip, key, len);
+	ret = crypto_cipher_setkey(tctx->fallback.cip, key, len);
 	if (ret) {
 		tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-		tfm->crt_flags |= (op->fallback.cip->base.crt_flags & CRYPTO_TFM_RES_MASK);
+		tfm->crt_flags |= (tctx->fallback.cip->base.crt_flags &
+				   CRYPTO_TFM_RES_MASK);
 	}
 	return ret;
 }
 
-static int geode_setkey_blk(struct crypto_tfm *tfm, const u8 *key,
-		unsigned int len)
+static int geode_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key,
+				 unsigned int len)
 {
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
+	struct geode_aes_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
 	unsigned int ret;
 
-	op->keylen = len;
+	tctx->keylen = len;
 
 	if (len == AES_KEYSIZE_128) {
-		memcpy(op->key, key, len);
+		memcpy(tctx->key, key, len);
 		return 0;
 	}
 
 	if (len != AES_KEYSIZE_192 && len != AES_KEYSIZE_256) {
 		/* not supported at all */
-		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
 	/*
 	 * The requested key size is not supported by HW, do a fallback
 	 */
-	op->fallback.blk->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-	op->fallback.blk->base.crt_flags |= (tfm->crt_flags & CRYPTO_TFM_REQ_MASK);
-
-	ret = crypto_blkcipher_setkey(op->fallback.blk, key, len);
-	if (ret) {
-		tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-		tfm->crt_flags |= (op->fallback.blk->base.crt_flags & CRYPTO_TFM_RES_MASK);
-	}
-	return ret;
-}
-
-static int fallback_blk_dec(struct blkcipher_desc *desc,
-		struct scatterlist *dst, struct scatterlist *src,
-		unsigned int nbytes)
-{
-	unsigned int ret;
-	struct crypto_blkcipher *tfm;
-	struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm);
-
-	tfm = desc->tfm;
-	desc->tfm = op->fallback.blk;
-
-	ret = crypto_blkcipher_decrypt_iv(desc, dst, src, nbytes);
-
-	desc->tfm = tfm;
-	return ret;
-}
-static int fallback_blk_enc(struct blkcipher_desc *desc,
-		struct scatterlist *dst, struct scatterlist *src,
-		unsigned int nbytes)
-{
-	unsigned int ret;
-	struct crypto_blkcipher *tfm;
-	struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm);
-
-	tfm = desc->tfm;
-	desc->tfm = op->fallback.blk;
-
-	ret = crypto_blkcipher_encrypt_iv(desc, dst, src, nbytes);
-
-	desc->tfm = tfm;
+	crypto_skcipher_clear_flags(tctx->fallback.skcipher,
+				    CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(tctx->fallback.skcipher,
+				  crypto_skcipher_get_flags(tfm) &
+				  CRYPTO_TFM_REQ_MASK);
+	ret = crypto_skcipher_setkey(tctx->fallback.skcipher, key, len);
+	crypto_skcipher_set_flags(tfm,
+				  crypto_skcipher_get_flags(tctx->fallback.skcipher) &
+				  CRYPTO_TFM_RES_MASK);
 	return ret;
 }
 
 static void
 geode_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
+	const struct geode_aes_tfm_ctx *tctx = crypto_tfm_ctx(tfm);
 
-	if (unlikely(op->keylen != AES_KEYSIZE_128)) {
-		crypto_cipher_encrypt_one(op->fallback.cip, out, in);
+	if (unlikely(tctx->keylen != AES_KEYSIZE_128)) {
+		crypto_cipher_encrypt_one(tctx->fallback.cip, out, in);
 		return;
 	}
 
-	op->src = (void *) in;
-	op->dst = (void *) out;
-	op->mode = AES_MODE_ECB;
-	op->flags = 0;
-	op->len = AES_BLOCK_SIZE;
-	op->dir = AES_DIR_ENCRYPT;
-
-	geode_aes_crypt(op);
+	geode_aes_crypt(tctx, in, out, AES_BLOCK_SIZE, NULL,
+			AES_MODE_ECB, AES_DIR_ENCRYPT);
 }
 
 
 static void
 geode_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
+	const struct geode_aes_tfm_ctx *tctx = crypto_tfm_ctx(tfm);
 
-	if (unlikely(op->keylen != AES_KEYSIZE_128)) {
-		crypto_cipher_decrypt_one(op->fallback.cip, out, in);
+	if (unlikely(tctx->keylen != AES_KEYSIZE_128)) {
+		crypto_cipher_decrypt_one(tctx->fallback.cip, out, in);
 		return;
 	}
 
-	op->src = (void *) in;
-	op->dst = (void *) out;
-	op->mode = AES_MODE_ECB;
-	op->flags = 0;
-	op->len = AES_BLOCK_SIZE;
-	op->dir = AES_DIR_DECRYPT;
-
-	geode_aes_crypt(op);
+	geode_aes_crypt(tctx, in, out, AES_BLOCK_SIZE, NULL,
+			AES_MODE_ECB, AES_DIR_DECRYPT);
 }
 
 static int fallback_init_cip(struct crypto_tfm *tfm)
 {
 	const char *name = crypto_tfm_alg_name(tfm);
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
+	struct geode_aes_tfm_ctx *tctx = crypto_tfm_ctx(tfm);
 
-	op->fallback.cip = crypto_alloc_cipher(name, 0,
-					       CRYPTO_ALG_NEED_FALLBACK);
+	tctx->fallback.cip = crypto_alloc_cipher(name, 0,
+						 CRYPTO_ALG_NEED_FALLBACK);
 
-	if (IS_ERR(op->fallback.cip)) {
+	if (IS_ERR(tctx->fallback.cip)) {
 		printk(KERN_ERR "Error allocating fallback algo %s\n", name);
-		return PTR_ERR(op->fallback.cip);
+		return PTR_ERR(tctx->fallback.cip);
 	}
 
 	return 0;
@@ -269,10 +222,9 @@ static int fallback_init_cip(struct crypto_tfm *tfm)
 
 static void fallback_exit_cip(struct crypto_tfm *tfm)
 {
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
+	struct geode_aes_tfm_ctx *tctx = crypto_tfm_ctx(tfm);
 
-	crypto_free_cipher(op->fallback.cip);
-	op->fallback.cip = NULL;
+	crypto_free_cipher(tctx->fallback.cip);
 }
 
 static struct crypto_alg geode_alg = {
@@ -285,7 +237,7 @@ static struct crypto_alg geode_alg = {
 	.cra_init			=	fallback_init_cip,
 	.cra_exit			=	fallback_exit_cip,
 	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct geode_aes_op),
+	.cra_ctxsize		=	sizeof(struct geode_aes_tfm_ctx),
 	.cra_module			=	THIS_MODULE,
 	.cra_u				=	{
 		.cipher	=	{
@@ -298,209 +250,126 @@ static struct crypto_alg geode_alg = {
 	}
 };
 
-static int
-geode_cbc_decrypt(struct blkcipher_desc *desc,
-		  struct scatterlist *dst, struct scatterlist *src,
-		  unsigned int nbytes)
+static int geode_init_skcipher(struct crypto_skcipher *tfm)
 {
-	struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	int err, ret;
-
-	if (unlikely(op->keylen != AES_KEYSIZE_128))
-		return fallback_blk_dec(desc, dst, src, nbytes);
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	op->iv = walk.iv;
-
-	while ((nbytes = walk.nbytes)) {
-		op->src = walk.src.virt.addr,
-		op->dst = walk.dst.virt.addr;
-		op->mode = AES_MODE_CBC;
-		op->len = nbytes - (nbytes % AES_BLOCK_SIZE);
-		op->dir = AES_DIR_DECRYPT;
+	const char *name = crypto_tfm_alg_name(&tfm->base);
+	struct geode_aes_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
 
-		ret = geode_aes_crypt(op);
-
-		nbytes -= ret;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+	tctx->fallback.skcipher =
+		crypto_alloc_skcipher(name, 0, CRYPTO_ALG_NEED_FALLBACK |
+				      CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tctx->fallback.skcipher)) {
+		printk(KERN_ERR "Error allocating fallback algo %s\n", name);
+		return PTR_ERR(tctx->fallback.skcipher);
 	}
 
-	return err;
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct skcipher_request) +
+				    crypto_skcipher_reqsize(tctx->fallback.skcipher));
+	return 0;
 }
 
-static int
-geode_cbc_encrypt(struct blkcipher_desc *desc,
-		  struct scatterlist *dst, struct scatterlist *src,
-		  unsigned int nbytes)
+static void geode_exit_skcipher(struct crypto_skcipher *tfm)
 {
-	struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	int err, ret;
-
-	if (unlikely(op->keylen != AES_KEYSIZE_128))
-		return fallback_blk_enc(desc, dst, src, nbytes);
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	op->iv = walk.iv;
-
-	while ((nbytes = walk.nbytes)) {
-		op->src = walk.src.virt.addr,
-		op->dst = walk.dst.virt.addr;
-		op->mode = AES_MODE_CBC;
-		op->len = nbytes - (nbytes % AES_BLOCK_SIZE);
-		op->dir = AES_DIR_ENCRYPT;
-
-		ret = geode_aes_crypt(op);
-		nbytes -= ret;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
+	struct geode_aes_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
 
-	return err;
+	crypto_free_skcipher(tctx->fallback.skcipher);
 }
 
-static int fallback_init_blk(struct crypto_tfm *tfm)
+static int geode_skcipher_crypt(struct skcipher_request *req, int mode, int dir)
 {
-	const char *name = crypto_tfm_alg_name(tfm);
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct geode_aes_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	int err;
+
+	if (unlikely(tctx->keylen != AES_KEYSIZE_128)) {
+		struct skcipher_request *subreq = skcipher_request_ctx(req);
+
+		*subreq = *req;
+		skcipher_request_set_tfm(subreq, tctx->fallback.skcipher);
+		if (dir == AES_DIR_DECRYPT)
+			return crypto_skcipher_decrypt(subreq);
+		else
+			return crypto_skcipher_encrypt(subreq);
+	}
 
-	op->fallback.blk = crypto_alloc_blkcipher(name, 0,
-			CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	if (IS_ERR(op->fallback.blk)) {
-		printk(KERN_ERR "Error allocating fallback algo %s\n", name);
-		return PTR_ERR(op->fallback.blk);
+	while ((nbytes = walk.nbytes) != 0) {
+		geode_aes_crypt(tctx, walk.src.virt.addr, walk.dst.virt.addr,
+				round_down(nbytes, AES_BLOCK_SIZE),
+				walk.iv, mode, dir);
+		err = skcipher_walk_done(&walk, nbytes % AES_BLOCK_SIZE);
 	}
 
-	return 0;
+	return err;
 }
 
-static void fallback_exit_blk(struct crypto_tfm *tfm)
+static int geode_cbc_encrypt(struct skcipher_request *req)
 {
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
-
-	crypto_free_blkcipher(op->fallback.blk);
-	op->fallback.blk = NULL;
+	return geode_skcipher_crypt(req, AES_MODE_CBC, AES_DIR_ENCRYPT);
 }
 
-static struct crypto_alg geode_cbc_alg = {
-	.cra_name		=	"cbc(aes)",
-	.cra_driver_name	=	"cbc-aes-geode",
-	.cra_priority		=	400,
-	.cra_flags			=	CRYPTO_ALG_TYPE_BLKCIPHER |
-						CRYPTO_ALG_KERN_DRIVER_ONLY |
-						CRYPTO_ALG_NEED_FALLBACK,
-	.cra_init			=	fallback_init_blk,
-	.cra_exit			=	fallback_exit_blk,
-	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct geode_aes_op),
-	.cra_alignmask		=	15,
-	.cra_type			=	&crypto_blkcipher_type,
-	.cra_module			=	THIS_MODULE,
-	.cra_u				=	{
-		.blkcipher	=	{
-			.min_keysize	=	AES_MIN_KEY_SIZE,
-			.max_keysize	=	AES_MAX_KEY_SIZE,
-			.setkey			=	geode_setkey_blk,
-			.encrypt		=	geode_cbc_encrypt,
-			.decrypt		=	geode_cbc_decrypt,
-			.ivsize			=	AES_BLOCK_SIZE,
-		}
-	}
-};
-
-static int
-geode_ecb_decrypt(struct blkcipher_desc *desc,
-		  struct scatterlist *dst, struct scatterlist *src,
-		  unsigned int nbytes)
+static int geode_cbc_decrypt(struct skcipher_request *req)
 {
-	struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	int err, ret;
-
-	if (unlikely(op->keylen != AES_KEYSIZE_128))
-		return fallback_blk_dec(desc, dst, src, nbytes);
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-
-	while ((nbytes = walk.nbytes)) {
-		op->src = walk.src.virt.addr,
-		op->dst = walk.dst.virt.addr;
-		op->mode = AES_MODE_ECB;
-		op->len = nbytes - (nbytes % AES_BLOCK_SIZE);
-		op->dir = AES_DIR_DECRYPT;
-
-		ret = geode_aes_crypt(op);
-		nbytes -= ret;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
-
-	return err;
+	return geode_skcipher_crypt(req, AES_MODE_CBC, AES_DIR_DECRYPT);
 }
 
-static int
-geode_ecb_encrypt(struct blkcipher_desc *desc,
-		  struct scatterlist *dst, struct scatterlist *src,
-		  unsigned int nbytes)
+static int geode_ecb_encrypt(struct skcipher_request *req)
 {
-	struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	int err, ret;
-
-	if (unlikely(op->keylen != AES_KEYSIZE_128))
-		return fallback_blk_enc(desc, dst, src, nbytes);
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-
-	while ((nbytes = walk.nbytes)) {
-		op->src = walk.src.virt.addr,
-		op->dst = walk.dst.virt.addr;
-		op->mode = AES_MODE_ECB;
-		op->len = nbytes - (nbytes % AES_BLOCK_SIZE);
-		op->dir = AES_DIR_ENCRYPT;
-
-		ret = geode_aes_crypt(op);
-		nbytes -= ret;
-		ret =  blkcipher_walk_done(desc, &walk, nbytes);
-	}
+	return geode_skcipher_crypt(req, AES_MODE_ECB, AES_DIR_ENCRYPT);
+}
 
-	return err;
+static int geode_ecb_decrypt(struct skcipher_request *req)
+{
+	return geode_skcipher_crypt(req, AES_MODE_ECB, AES_DIR_DECRYPT);
 }
 
-static struct crypto_alg geode_ecb_alg = {
-	.cra_name			=	"ecb(aes)",
-	.cra_driver_name	=	"ecb-aes-geode",
-	.cra_priority		=	400,
-	.cra_flags			=	CRYPTO_ALG_TYPE_BLKCIPHER |
-						CRYPTO_ALG_KERN_DRIVER_ONLY |
-						CRYPTO_ALG_NEED_FALLBACK,
-	.cra_init			=	fallback_init_blk,
-	.cra_exit			=	fallback_exit_blk,
-	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct geode_aes_op),
-	.cra_alignmask		=	15,
-	.cra_type			=	&crypto_blkcipher_type,
-	.cra_module			=	THIS_MODULE,
-	.cra_u				=	{
-		.blkcipher	=	{
-			.min_keysize	=	AES_MIN_KEY_SIZE,
-			.max_keysize	=	AES_MAX_KEY_SIZE,
-			.setkey			=	geode_setkey_blk,
-			.encrypt		=	geode_ecb_encrypt,
-			.decrypt		=	geode_ecb_decrypt,
-		}
-	}
+static struct skcipher_alg geode_skcipher_algs[] = {
+	{
+		.base.cra_name		= "cbc(aes)",
+		.base.cra_driver_name	= "cbc-aes-geode",
+		.base.cra_priority	= 400,
+		.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
+					  CRYPTO_ALG_NEED_FALLBACK,
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct geode_aes_tfm_ctx),
+		.base.cra_alignmask	= 15,
+		.base.cra_module	= THIS_MODULE,
+		.init			= geode_init_skcipher,
+		.exit			= geode_exit_skcipher,
+		.setkey			= geode_setkey_skcipher,
+		.encrypt		= geode_cbc_encrypt,
+		.decrypt		= geode_cbc_decrypt,
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.ivsize			= AES_BLOCK_SIZE,
+	}, {
+		.base.cra_name		= "ecb(aes)",
+		.base.cra_driver_name	= "ecb-aes-geode",
+		.base.cra_priority	= 400,
+		.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
+					  CRYPTO_ALG_NEED_FALLBACK,
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct geode_aes_tfm_ctx),
+		.base.cra_alignmask	= 15,
+		.base.cra_module	= THIS_MODULE,
+		.init			= geode_init_skcipher,
+		.exit			= geode_exit_skcipher,
+		.setkey			= geode_setkey_skcipher,
+		.encrypt		= geode_ecb_encrypt,
+		.decrypt		= geode_ecb_decrypt,
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+	},
 };
 
 static void geode_aes_remove(struct pci_dev *dev)
 {
 	crypto_unregister_alg(&geode_alg);
-	crypto_unregister_alg(&geode_ecb_alg);
-	crypto_unregister_alg(&geode_cbc_alg);
+	crypto_unregister_skciphers(geode_skcipher_algs,
+				    ARRAY_SIZE(geode_skcipher_algs));
 
 	pci_iounmap(dev, _iobase);
 	_iobase = NULL;
@@ -538,20 +407,14 @@ static int geode_aes_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	if (ret)
 		goto eiomap;
 
-	ret = crypto_register_alg(&geode_ecb_alg);
+	ret = crypto_register_skciphers(geode_skcipher_algs,
+					ARRAY_SIZE(geode_skcipher_algs));
 	if (ret)
 		goto ealg;
 
-	ret = crypto_register_alg(&geode_cbc_alg);
-	if (ret)
-		goto eecb;
-
 	dev_notice(&dev->dev, "GEODE AES engine enabled.\n");
 	return 0;
 
- eecb:
-	crypto_unregister_alg(&geode_ecb_alg);
-
  ealg:
 	crypto_unregister_alg(&geode_alg);
 
diff --git a/drivers/crypto/geode-aes.h b/drivers/crypto/geode-aes.h
index 5c6e131a8f9d..6d0a0cdc7647 100644
--- a/drivers/crypto/geode-aes.h
+++ b/drivers/crypto/geode-aes.h
@@ -46,21 +46,10 @@
 
 #define AES_OP_TIMEOUT    0x50000
 
-struct geode_aes_op {
-
-	void *src;
-	void *dst;
-
-	u32 mode;
-	u32 dir;
-	u32 flags;
-	int len;
-
+struct geode_aes_tfm_ctx {
 	u8 key[AES_KEYSIZE_128];
-	u8 *iv;
-
 	union {
-		struct crypto_blkcipher *blk;
+		struct crypto_skcipher *skcipher;
 		struct crypto_cipher *cip;
 	} fallback;
 	u32 keylen;
diff --git a/drivers/crypto/hifn_795x.c b/drivers/crypto/hifn_795x.c
index a18e62df68d9..4e7323884ae3 100644
--- a/drivers/crypto/hifn_795x.c
+++ b/drivers/crypto/hifn_795x.c
@@ -22,6 +22,7 @@
 
 #include <crypto/algapi.h>
 #include <crypto/internal/des.h>
+#include <crypto/internal/skcipher.h>
 
 static char hifn_pll_ref[sizeof("extNNN")] = "ext";
 module_param_string(hifn_pll_ref, hifn_pll_ref, sizeof(hifn_pll_ref), 0444);
@@ -596,7 +597,7 @@ struct hifn_crypt_result {
 
 struct hifn_crypto_alg {
 	struct list_head	entry;
-	struct crypto_alg	alg;
+	struct skcipher_alg	alg;
 	struct hifn_device	*dev;
 };
 
@@ -1404,7 +1405,7 @@ static void hifn_cipher_walk_exit(struct hifn_cipher_walk *w)
 	w->num = 0;
 }
 
-static int ablkcipher_add(unsigned int *drestp, struct scatterlist *dst,
+static int skcipher_add(unsigned int *drestp, struct scatterlist *dst,
 		unsigned int size, unsigned int *nbytesp)
 {
 	unsigned int copy, drest = *drestp, nbytes = *nbytesp;
@@ -1433,11 +1434,11 @@ static int ablkcipher_add(unsigned int *drestp, struct scatterlist *dst,
 	return idx;
 }
 
-static int hifn_cipher_walk(struct ablkcipher_request *req,
+static int hifn_cipher_walk(struct skcipher_request *req,
 		struct hifn_cipher_walk *w)
 {
 	struct scatterlist *dst, *t;
-	unsigned int nbytes = req->nbytes, offset, copy, diff;
+	unsigned int nbytes = req->cryptlen, offset, copy, diff;
 	int idx, tidx, err;
 
 	tidx = idx = 0;
@@ -1459,7 +1460,7 @@ static int hifn_cipher_walk(struct ablkcipher_request *req,
 
 			t = &w->cache[idx];
 
-			err = ablkcipher_add(&dlen, dst, slen, &nbytes);
+			err = skcipher_add(&dlen, dst, slen, &nbytes);
 			if (err < 0)
 				return err;
 
@@ -1498,7 +1499,7 @@ static int hifn_cipher_walk(struct ablkcipher_request *req,
 
 				dst = &req->dst[idx];
 
-				err = ablkcipher_add(&dlen, dst, nbytes, &nbytes);
+				err = skcipher_add(&dlen, dst, nbytes, &nbytes);
 				if (err < 0)
 					return err;
 
@@ -1518,13 +1519,13 @@ static int hifn_cipher_walk(struct ablkcipher_request *req,
 	return tidx;
 }
 
-static int hifn_setup_session(struct ablkcipher_request *req)
+static int hifn_setup_session(struct skcipher_request *req)
 {
 	struct hifn_context *ctx = crypto_tfm_ctx(req->base.tfm);
-	struct hifn_request_context *rctx = ablkcipher_request_ctx(req);
+	struct hifn_request_context *rctx = skcipher_request_ctx(req);
 	struct hifn_device *dev = ctx->dev;
 	unsigned long dlen, flags;
-	unsigned int nbytes = req->nbytes, idx = 0;
+	unsigned int nbytes = req->cryptlen, idx = 0;
 	int err = -EINVAL, sg_num;
 	struct scatterlist *dst;
 
@@ -1563,7 +1564,7 @@ static int hifn_setup_session(struct ablkcipher_request *req)
 		goto err_out;
 	}
 
-	err = hifn_setup_dma(dev, ctx, rctx, req->src, req->dst, req->nbytes, req);
+	err = hifn_setup_dma(dev, ctx, rctx, req->src, req->dst, req->cryptlen, req);
 	if (err)
 		goto err_out;
 
@@ -1610,7 +1611,7 @@ static int hifn_start_device(struct hifn_device *dev)
 	return 0;
 }
 
-static int ablkcipher_get(void *saddr, unsigned int *srestp, unsigned int offset,
+static int skcipher_get(void *saddr, unsigned int *srestp, unsigned int offset,
 		struct scatterlist *dst, unsigned int size, unsigned int *nbytesp)
 {
 	unsigned int srest = *srestp, nbytes = *nbytesp, copy;
@@ -1660,12 +1661,12 @@ static inline void hifn_complete_sa(struct hifn_device *dev, int i)
 	BUG_ON(dev->started < 0);
 }
 
-static void hifn_process_ready(struct ablkcipher_request *req, int error)
+static void hifn_process_ready(struct skcipher_request *req, int error)
 {
-	struct hifn_request_context *rctx = ablkcipher_request_ctx(req);
+	struct hifn_request_context *rctx = skcipher_request_ctx(req);
 
 	if (rctx->walk.flags & ASYNC_FLAGS_MISALIGNED) {
-		unsigned int nbytes = req->nbytes;
+		unsigned int nbytes = req->cryptlen;
 		int idx = 0, err;
 		struct scatterlist *dst, *t;
 		void *saddr;
@@ -1688,7 +1689,7 @@ static void hifn_process_ready(struct ablkcipher_request *req, int error)
 
 			saddr = kmap_atomic(sg_page(t));
 
-			err = ablkcipher_get(saddr, &t->length, t->offset,
+			err = skcipher_get(saddr, &t->length, t->offset,
 					dst, nbytes, &nbytes);
 			if (err < 0) {
 				kunmap_atomic(saddr);
@@ -1910,7 +1911,7 @@ static void hifn_flush(struct hifn_device *dev)
 {
 	unsigned long flags;
 	struct crypto_async_request *async_req;
-	struct ablkcipher_request *req;
+	struct skcipher_request *req;
 	struct hifn_dma *dma = (struct hifn_dma *)dev->desc_virt;
 	int i;
 
@@ -1926,7 +1927,7 @@ static void hifn_flush(struct hifn_device *dev)
 
 	spin_lock_irqsave(&dev->lock, flags);
 	while ((async_req = crypto_dequeue_request(&dev->queue))) {
-		req = ablkcipher_request_cast(async_req);
+		req = skcipher_request_cast(async_req);
 		spin_unlock_irqrestore(&dev->lock, flags);
 
 		hifn_process_ready(req, -ENODEV);
@@ -1936,14 +1937,14 @@ static void hifn_flush(struct hifn_device *dev)
 	spin_unlock_irqrestore(&dev->lock, flags);
 }
 
-static int hifn_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int hifn_setkey(struct crypto_skcipher *cipher, const u8 *key,
 		unsigned int len)
 {
-	struct hifn_context *ctx = crypto_ablkcipher_ctx(cipher);
+	struct hifn_context *ctx = crypto_skcipher_ctx(cipher);
 	struct hifn_device *dev = ctx->dev;
 	int err;
 
-	err = verify_ablkcipher_des_key(cipher, key);
+	err = verify_skcipher_des_key(cipher, key);
 	if (err)
 		return err;
 
@@ -1955,14 +1956,14 @@ static int hifn_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	return 0;
 }
 
-static int hifn_des3_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int hifn_des3_setkey(struct crypto_skcipher *cipher, const u8 *key,
 			    unsigned int len)
 {
-	struct hifn_context *ctx = crypto_ablkcipher_ctx(cipher);
+	struct hifn_context *ctx = crypto_skcipher_ctx(cipher);
 	struct hifn_device *dev = ctx->dev;
 	int err;
 
-	err = verify_ablkcipher_des3_key(cipher, key);
+	err = verify_skcipher_des3_key(cipher, key);
 	if (err)
 		return err;
 
@@ -1974,36 +1975,36 @@ static int hifn_des3_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	return 0;
 }
 
-static int hifn_handle_req(struct ablkcipher_request *req)
+static int hifn_handle_req(struct skcipher_request *req)
 {
 	struct hifn_context *ctx = crypto_tfm_ctx(req->base.tfm);
 	struct hifn_device *dev = ctx->dev;
 	int err = -EAGAIN;
 
-	if (dev->started + DIV_ROUND_UP(req->nbytes, PAGE_SIZE) <= HIFN_QUEUE_LENGTH)
+	if (dev->started + DIV_ROUND_UP(req->cryptlen, PAGE_SIZE) <= HIFN_QUEUE_LENGTH)
 		err = hifn_setup_session(req);
 
 	if (err == -EAGAIN) {
 		unsigned long flags;
 
 		spin_lock_irqsave(&dev->lock, flags);
-		err = ablkcipher_enqueue_request(&dev->queue, req);
+		err = crypto_enqueue_request(&dev->queue, &req->base);
 		spin_unlock_irqrestore(&dev->lock, flags);
 	}
 
 	return err;
 }
 
-static int hifn_setup_crypto_req(struct ablkcipher_request *req, u8 op,
+static int hifn_setup_crypto_req(struct skcipher_request *req, u8 op,
 		u8 type, u8 mode)
 {
 	struct hifn_context *ctx = crypto_tfm_ctx(req->base.tfm);
-	struct hifn_request_context *rctx = ablkcipher_request_ctx(req);
+	struct hifn_request_context *rctx = skcipher_request_ctx(req);
 	unsigned ivsize;
 
-	ivsize = crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(req));
+	ivsize = crypto_skcipher_ivsize(crypto_skcipher_reqtfm(req));
 
-	if (req->info && mode != ACRYPTO_MODE_ECB) {
+	if (req->iv && mode != ACRYPTO_MODE_ECB) {
 		if (type == ACRYPTO_TYPE_AES_128)
 			ivsize = HIFN_AES_IV_LENGTH;
 		else if (type == ACRYPTO_TYPE_DES)
@@ -2022,7 +2023,7 @@ static int hifn_setup_crypto_req(struct ablkcipher_request *req, u8 op,
 	rctx->op = op;
 	rctx->mode = mode;
 	rctx->type = type;
-	rctx->iv = req->info;
+	rctx->iv = req->iv;
 	rctx->ivsize = ivsize;
 
 	/*
@@ -2037,7 +2038,7 @@ static int hifn_setup_crypto_req(struct ablkcipher_request *req, u8 op,
 static int hifn_process_queue(struct hifn_device *dev)
 {
 	struct crypto_async_request *async_req, *backlog;
-	struct ablkcipher_request *req;
+	struct skcipher_request *req;
 	unsigned long flags;
 	int err = 0;
 
@@ -2053,7 +2054,7 @@ static int hifn_process_queue(struct hifn_device *dev)
 		if (backlog)
 			backlog->complete(backlog, -EINPROGRESS);
 
-		req = ablkcipher_request_cast(async_req);
+		req = skcipher_request_cast(async_req);
 
 		err = hifn_handle_req(req);
 		if (err)
@@ -2063,7 +2064,7 @@ static int hifn_process_queue(struct hifn_device *dev)
 	return err;
 }
 
-static int hifn_setup_crypto(struct ablkcipher_request *req, u8 op,
+static int hifn_setup_crypto(struct skcipher_request *req, u8 op,
 		u8 type, u8 mode)
 {
 	int err;
@@ -2083,22 +2084,22 @@ static int hifn_setup_crypto(struct ablkcipher_request *req, u8 op,
 /*
  * AES ecryption functions.
  */
-static inline int hifn_encrypt_aes_ecb(struct ablkcipher_request *req)
+static inline int hifn_encrypt_aes_ecb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
 			ACRYPTO_TYPE_AES_128, ACRYPTO_MODE_ECB);
 }
-static inline int hifn_encrypt_aes_cbc(struct ablkcipher_request *req)
+static inline int hifn_encrypt_aes_cbc(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
 			ACRYPTO_TYPE_AES_128, ACRYPTO_MODE_CBC);
 }
-static inline int hifn_encrypt_aes_cfb(struct ablkcipher_request *req)
+static inline int hifn_encrypt_aes_cfb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
 			ACRYPTO_TYPE_AES_128, ACRYPTO_MODE_CFB);
 }
-static inline int hifn_encrypt_aes_ofb(struct ablkcipher_request *req)
+static inline int hifn_encrypt_aes_ofb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
 			ACRYPTO_TYPE_AES_128, ACRYPTO_MODE_OFB);
@@ -2107,22 +2108,22 @@ static inline int hifn_encrypt_aes_ofb(struct ablkcipher_request *req)
 /*
  * AES decryption functions.
  */
-static inline int hifn_decrypt_aes_ecb(struct ablkcipher_request *req)
+static inline int hifn_decrypt_aes_ecb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
 			ACRYPTO_TYPE_AES_128, ACRYPTO_MODE_ECB);
 }
-static inline int hifn_decrypt_aes_cbc(struct ablkcipher_request *req)
+static inline int hifn_decrypt_aes_cbc(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
 			ACRYPTO_TYPE_AES_128, ACRYPTO_MODE_CBC);
 }
-static inline int hifn_decrypt_aes_cfb(struct ablkcipher_request *req)
+static inline int hifn_decrypt_aes_cfb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
 			ACRYPTO_TYPE_AES_128, ACRYPTO_MODE_CFB);
 }
-static inline int hifn_decrypt_aes_ofb(struct ablkcipher_request *req)
+static inline int hifn_decrypt_aes_ofb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
 			ACRYPTO_TYPE_AES_128, ACRYPTO_MODE_OFB);
@@ -2131,22 +2132,22 @@ static inline int hifn_decrypt_aes_ofb(struct ablkcipher_request *req)
 /*
  * DES ecryption functions.
  */
-static inline int hifn_encrypt_des_ecb(struct ablkcipher_request *req)
+static inline int hifn_encrypt_des_ecb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
 			ACRYPTO_TYPE_DES, ACRYPTO_MODE_ECB);
 }
-static inline int hifn_encrypt_des_cbc(struct ablkcipher_request *req)
+static inline int hifn_encrypt_des_cbc(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
 			ACRYPTO_TYPE_DES, ACRYPTO_MODE_CBC);
 }
-static inline int hifn_encrypt_des_cfb(struct ablkcipher_request *req)
+static inline int hifn_encrypt_des_cfb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
 			ACRYPTO_TYPE_DES, ACRYPTO_MODE_CFB);
 }
-static inline int hifn_encrypt_des_ofb(struct ablkcipher_request *req)
+static inline int hifn_encrypt_des_ofb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
 			ACRYPTO_TYPE_DES, ACRYPTO_MODE_OFB);
@@ -2155,22 +2156,22 @@ static inline int hifn_encrypt_des_ofb(struct ablkcipher_request *req)
 /*
  * DES decryption functions.
  */
-static inline int hifn_decrypt_des_ecb(struct ablkcipher_request *req)
+static inline int hifn_decrypt_des_ecb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
 			ACRYPTO_TYPE_DES, ACRYPTO_MODE_ECB);
 }
-static inline int hifn_decrypt_des_cbc(struct ablkcipher_request *req)
+static inline int hifn_decrypt_des_cbc(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
 			ACRYPTO_TYPE_DES, ACRYPTO_MODE_CBC);
 }
-static inline int hifn_decrypt_des_cfb(struct ablkcipher_request *req)
+static inline int hifn_decrypt_des_cfb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
 			ACRYPTO_TYPE_DES, ACRYPTO_MODE_CFB);
 }
-static inline int hifn_decrypt_des_ofb(struct ablkcipher_request *req)
+static inline int hifn_decrypt_des_ofb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
 			ACRYPTO_TYPE_DES, ACRYPTO_MODE_OFB);
@@ -2179,44 +2180,44 @@ static inline int hifn_decrypt_des_ofb(struct ablkcipher_request *req)
 /*
  * 3DES ecryption functions.
  */
-static inline int hifn_encrypt_3des_ecb(struct ablkcipher_request *req)
+static inline int hifn_encrypt_3des_ecb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
 			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_ECB);
 }
-static inline int hifn_encrypt_3des_cbc(struct ablkcipher_request *req)
+static inline int hifn_encrypt_3des_cbc(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
 			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_CBC);
 }
-static inline int hifn_encrypt_3des_cfb(struct ablkcipher_request *req)
+static inline int hifn_encrypt_3des_cfb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
 			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_CFB);
 }
-static inline int hifn_encrypt_3des_ofb(struct ablkcipher_request *req)
+static inline int hifn_encrypt_3des_ofb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
 			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_OFB);
 }
 
 /* 3DES decryption functions. */
-static inline int hifn_decrypt_3des_ecb(struct ablkcipher_request *req)
+static inline int hifn_decrypt_3des_ecb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
 			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_ECB);
 }
-static inline int hifn_decrypt_3des_cbc(struct ablkcipher_request *req)
+static inline int hifn_decrypt_3des_cbc(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
 			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_CBC);
 }
-static inline int hifn_decrypt_3des_cfb(struct ablkcipher_request *req)
+static inline int hifn_decrypt_3des_cfb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
 			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_CFB);
 }
-static inline int hifn_decrypt_3des_ofb(struct ablkcipher_request *req)
+static inline int hifn_decrypt_3des_ofb(struct skcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
 			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_OFB);
@@ -2226,16 +2227,16 @@ struct hifn_alg_template {
 	char name[CRYPTO_MAX_ALG_NAME];
 	char drv_name[CRYPTO_MAX_ALG_NAME];
 	unsigned int bsize;
-	struct ablkcipher_alg ablkcipher;
+	struct skcipher_alg skcipher;
 };
 
-static struct hifn_alg_template hifn_alg_templates[] = {
+static const struct hifn_alg_template hifn_alg_templates[] = {
 	/*
 	 * 3DES ECB, CBC, CFB and OFB modes.
 	 */
 	{
 		.name = "cfb(des3_ede)", .drv_name = "cfb-3des", .bsize = 8,
-		.ablkcipher = {
+		.skcipher = {
 			.min_keysize	=	HIFN_3DES_KEY_LENGTH,
 			.max_keysize	=	HIFN_3DES_KEY_LENGTH,
 			.setkey		=	hifn_des3_setkey,
@@ -2245,7 +2246,7 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 	},
 	{
 		.name = "ofb(des3_ede)", .drv_name = "ofb-3des", .bsize = 8,
-		.ablkcipher = {
+		.skcipher = {
 			.min_keysize	=	HIFN_3DES_KEY_LENGTH,
 			.max_keysize	=	HIFN_3DES_KEY_LENGTH,
 			.setkey		=	hifn_des3_setkey,
@@ -2255,7 +2256,7 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 	},
 	{
 		.name = "cbc(des3_ede)", .drv_name = "cbc-3des", .bsize = 8,
-		.ablkcipher = {
+		.skcipher = {
 			.ivsize		=	HIFN_IV_LENGTH,
 			.min_keysize	=	HIFN_3DES_KEY_LENGTH,
 			.max_keysize	=	HIFN_3DES_KEY_LENGTH,
@@ -2266,7 +2267,7 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 	},
 	{
 		.name = "ecb(des3_ede)", .drv_name = "ecb-3des", .bsize = 8,
-		.ablkcipher = {
+		.skcipher = {
 			.min_keysize	=	HIFN_3DES_KEY_LENGTH,
 			.max_keysize	=	HIFN_3DES_KEY_LENGTH,
 			.setkey		=	hifn_des3_setkey,
@@ -2280,7 +2281,7 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 	 */
 	{
 		.name = "cfb(des)", .drv_name = "cfb-des", .bsize = 8,
-		.ablkcipher = {
+		.skcipher = {
 			.min_keysize	=	HIFN_DES_KEY_LENGTH,
 			.max_keysize	=	HIFN_DES_KEY_LENGTH,
 			.setkey		=	hifn_setkey,
@@ -2290,7 +2291,7 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 	},
 	{
 		.name = "ofb(des)", .drv_name = "ofb-des", .bsize = 8,
-		.ablkcipher = {
+		.skcipher = {
 			.min_keysize	=	HIFN_DES_KEY_LENGTH,
 			.max_keysize	=	HIFN_DES_KEY_LENGTH,
 			.setkey		=	hifn_setkey,
@@ -2300,7 +2301,7 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 	},
 	{
 		.name = "cbc(des)", .drv_name = "cbc-des", .bsize = 8,
-		.ablkcipher = {
+		.skcipher = {
 			.ivsize		=	HIFN_IV_LENGTH,
 			.min_keysize	=	HIFN_DES_KEY_LENGTH,
 			.max_keysize	=	HIFN_DES_KEY_LENGTH,
@@ -2311,7 +2312,7 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 	},
 	{
 		.name = "ecb(des)", .drv_name = "ecb-des", .bsize = 8,
-		.ablkcipher = {
+		.skcipher = {
 			.min_keysize	=	HIFN_DES_KEY_LENGTH,
 			.max_keysize	=	HIFN_DES_KEY_LENGTH,
 			.setkey		=	hifn_setkey,
@@ -2325,7 +2326,7 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 	 */
 	{
 		.name = "ecb(aes)", .drv_name = "ecb-aes", .bsize = 16,
-		.ablkcipher = {
+		.skcipher = {
 			.min_keysize	=	AES_MIN_KEY_SIZE,
 			.max_keysize	=	AES_MAX_KEY_SIZE,
 			.setkey		=	hifn_setkey,
@@ -2335,7 +2336,7 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 	},
 	{
 		.name = "cbc(aes)", .drv_name = "cbc-aes", .bsize = 16,
-		.ablkcipher = {
+		.skcipher = {
 			.ivsize		=	HIFN_AES_IV_LENGTH,
 			.min_keysize	=	AES_MIN_KEY_SIZE,
 			.max_keysize	=	AES_MAX_KEY_SIZE,
@@ -2346,7 +2347,7 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 	},
 	{
 		.name = "cfb(aes)", .drv_name = "cfb-aes", .bsize = 16,
-		.ablkcipher = {
+		.skcipher = {
 			.min_keysize	=	AES_MIN_KEY_SIZE,
 			.max_keysize	=	AES_MAX_KEY_SIZE,
 			.setkey		=	hifn_setkey,
@@ -2356,7 +2357,7 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 	},
 	{
 		.name = "ofb(aes)", .drv_name = "ofb-aes", .bsize = 16,
-		.ablkcipher = {
+		.skcipher = {
 			.min_keysize	=	AES_MIN_KEY_SIZE,
 			.max_keysize	=	AES_MAX_KEY_SIZE,
 			.setkey		=	hifn_setkey,
@@ -2366,18 +2367,19 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 	},
 };
 
-static int hifn_cra_init(struct crypto_tfm *tfm)
+static int hifn_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct crypto_alg *alg = tfm->__crt_alg;
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
 	struct hifn_crypto_alg *ha = crypto_alg_to_hifn(alg);
-	struct hifn_context *ctx = crypto_tfm_ctx(tfm);
+	struct hifn_context *ctx = crypto_skcipher_ctx(tfm);
 
 	ctx->dev = ha->dev;
-	tfm->crt_ablkcipher.reqsize = sizeof(struct hifn_request_context);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct hifn_request_context));
+
 	return 0;
 }
 
-static int hifn_alg_alloc(struct hifn_device *dev, struct hifn_alg_template *t)
+static int hifn_alg_alloc(struct hifn_device *dev, const struct hifn_alg_template *t)
 {
 	struct hifn_crypto_alg *alg;
 	int err;
@@ -2386,26 +2388,25 @@ static int hifn_alg_alloc(struct hifn_device *dev, struct hifn_alg_template *t)
 	if (!alg)
 		return -ENOMEM;
 
-	snprintf(alg->alg.cra_name, CRYPTO_MAX_ALG_NAME, "%s", t->name);
-	snprintf(alg->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s-%s",
+	alg->alg = t->skcipher;
+	alg->alg.init = hifn_init_tfm;
+
+	snprintf(alg->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, "%s", t->name);
+	snprintf(alg->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s-%s",
 		 t->drv_name, dev->name);
 
-	alg->alg.cra_priority = 300;
-	alg->alg.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-				CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC;
-	alg->alg.cra_blocksize = t->bsize;
-	alg->alg.cra_ctxsize = sizeof(struct hifn_context);
-	alg->alg.cra_alignmask = 0;
-	alg->alg.cra_type = &crypto_ablkcipher_type;
-	alg->alg.cra_module = THIS_MODULE;
-	alg->alg.cra_u.ablkcipher = t->ablkcipher;
-	alg->alg.cra_init = hifn_cra_init;
+	alg->alg.base.cra_priority = 300;
+	alg->alg.base.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC;
+	alg->alg.base.cra_blocksize = t->bsize;
+	alg->alg.base.cra_ctxsize = sizeof(struct hifn_context);
+	alg->alg.base.cra_alignmask = 0;
+	alg->alg.base.cra_module = THIS_MODULE;
 
 	alg->dev = dev;
 
 	list_add_tail(&alg->entry, &dev->alg_list);
 
-	err = crypto_register_alg(&alg->alg);
+	err = crypto_register_skcipher(&alg->alg);
 	if (err) {
 		list_del(&alg->entry);
 		kfree(alg);
@@ -2420,7 +2421,7 @@ static void hifn_unregister_alg(struct hifn_device *dev)
 
 	list_for_each_entry_safe(a, n, &dev->alg_list, entry) {
 		list_del(&a->entry);
-		crypto_unregister_alg(&a->alg);
+		crypto_unregister_skcipher(&a->alg);
 		kfree(a);
 	}
 }
diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig
index ebaf91e0146d..c0e7a85fe129 100644
--- a/drivers/crypto/hisilicon/Kconfig
+++ b/drivers/crypto/hisilicon/Kconfig
@@ -2,7 +2,7 @@
 
 config CRYPTO_DEV_HISI_SEC
 	tristate "Support for Hisilicon SEC crypto block cipher accelerator"
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_ALGAPI
 	select CRYPTO_LIB_DES
 	select SG_SPLIT
@@ -14,26 +14,47 @@ config CRYPTO_DEV_HISI_SEC
 	  To compile this as a module, choose M here: the module
 	  will be called hisi_sec.
 
+config CRYPTO_DEV_HISI_SEC2
+	tristate "Support for HiSilicon SEC2 crypto block cipher accelerator"
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_ALGAPI
+	select CRYPTO_LIB_DES
+	select CRYPTO_DEV_HISI_QM
+	depends on PCI && PCI_MSI
+	depends on ARM64 || (COMPILE_TEST && 64BIT)
+	help
+	  Support for HiSilicon SEC Engine of version 2 in crypto subsystem.
+	  It provides AES, SM4, and 3DES algorithms with ECB
+	  CBC, and XTS cipher mode.
+
+	  To compile this as a module, choose M here: the module
+          will be called hisi_sec2.
+
 config CRYPTO_DEV_HISI_QM
 	tristate
-	depends on ARM64 && PCI && PCI_MSI
+	depends on ARM64 || COMPILE_TEST
+	depends on PCI && PCI_MSI
 	help
 	  HiSilicon accelerator engines use a common queue management
 	  interface. Specific engine driver may use this module.
 
-config CRYPTO_HISI_SGL
-	tristate
-	depends on ARM64
-	help
-	  HiSilicon accelerator engines use a common hardware scatterlist
-	  interface for data format. Specific engine driver may use this
-	  module.
-
 config CRYPTO_DEV_HISI_ZIP
 	tristate "Support for HiSilicon ZIP accelerator"
-	depends on ARM64 && PCI && PCI_MSI
+	depends on PCI && PCI_MSI
+	depends on ARM64 || (COMPILE_TEST && 64BIT)
+	depends on !CPU_BIG_ENDIAN || COMPILE_TEST
 	select CRYPTO_DEV_HISI_QM
-	select CRYPTO_HISI_SGL
 	select SG_SPLIT
 	help
 	  Support for HiSilicon ZIP Driver
+
+config CRYPTO_DEV_HISI_HPRE
+	tristate "Support for HISI HPRE accelerator"
+	depends on PCI && PCI_MSI
+	depends on ARM64 || (COMPILE_TEST && 64BIT)
+	select CRYPTO_DEV_HISI_QM
+	select CRYPTO_DH
+	select CRYPTO_RSA
+	help
+	  Support for HiSilicon HPRE(High Performance RSA Engine)
+	  accelerator, which can accelerate RSA and DH algorithms.
diff --git a/drivers/crypto/hisilicon/Makefile b/drivers/crypto/hisilicon/Makefile
index 45a279741126..7f5f74c72baa 100644
--- a/drivers/crypto/hisilicon/Makefile
+++ b/drivers/crypto/hisilicon/Makefile
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_CRYPTO_DEV_HISI_HPRE) += hpre/
 obj-$(CONFIG_CRYPTO_DEV_HISI_SEC) += sec/
-obj-$(CONFIG_CRYPTO_DEV_HISI_QM) += qm.o
-obj-$(CONFIG_CRYPTO_HISI_SGL) += sgl.o
+obj-$(CONFIG_CRYPTO_DEV_HISI_SEC2) += sec2/
+obj-$(CONFIG_CRYPTO_DEV_HISI_QM) += hisi_qm.o
+hisi_qm-objs = qm.o sgl.o
 obj-$(CONFIG_CRYPTO_DEV_HISI_ZIP) += zip/
diff --git a/drivers/crypto/hisilicon/hpre/Makefile b/drivers/crypto/hisilicon/hpre/Makefile
new file mode 100644
index 000000000000..4fd32b789e1e
--- /dev/null
+++ b/drivers/crypto/hisilicon/hpre/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_CRYPTO_DEV_HISI_HPRE) += hisi_hpre.o
+hisi_hpre-objs = hpre_main.o hpre_crypto.o
diff --git a/drivers/crypto/hisilicon/hpre/hpre.h b/drivers/crypto/hisilicon/hpre/hpre.h
new file mode 100644
index 000000000000..ddf13ea9862a
--- /dev/null
+++ b/drivers/crypto/hisilicon/hpre/hpre.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 HiSilicon Limited. */
+#ifndef __HISI_HPRE_H
+#define __HISI_HPRE_H
+
+#include <linux/list.h>
+#include "../qm.h"
+
+#define HPRE_SQE_SIZE			sizeof(struct hpre_sqe)
+#define HPRE_PF_DEF_Q_NUM		64
+#define HPRE_PF_DEF_Q_BASE		0
+
+enum {
+	HPRE_CLUSTER0,
+	HPRE_CLUSTER1,
+	HPRE_CLUSTER2,
+	HPRE_CLUSTER3,
+	HPRE_CLUSTERS_NUM,
+};
+
+enum hpre_ctrl_dbgfs_file {
+	HPRE_CURRENT_QM,
+	HPRE_CLEAR_ENABLE,
+	HPRE_CLUSTER_CTRL,
+	HPRE_DEBUG_FILE_NUM,
+};
+
+#define HPRE_DEBUGFS_FILE_NUM    (HPRE_DEBUG_FILE_NUM + HPRE_CLUSTERS_NUM - 1)
+
+struct hpre_debugfs_file {
+	int index;
+	enum hpre_ctrl_dbgfs_file type;
+	spinlock_t lock;
+	struct hpre_debug *debug;
+};
+
+/*
+ * One HPRE controller has one PF and multiple VFs, some global configurations
+ * which PF has need this structure.
+ * Just relevant for PF.
+ */
+struct hpre_debug {
+	struct dentry *debug_root;
+	struct hpre_debugfs_file files[HPRE_DEBUGFS_FILE_NUM];
+};
+
+struct hpre {
+	struct hisi_qm qm;
+	struct list_head list;
+	struct hpre_debug debug;
+	u32 num_vfs;
+	unsigned long status;
+};
+
+enum hpre_alg_type {
+	HPRE_ALG_NC_NCRT = 0x0,
+	HPRE_ALG_NC_CRT = 0x1,
+	HPRE_ALG_KG_STD = 0x2,
+	HPRE_ALG_KG_CRT = 0x3,
+	HPRE_ALG_DH_G2 = 0x4,
+	HPRE_ALG_DH = 0x5,
+};
+
+struct hpre_sqe {
+	__le32 dw0;
+	__u8 task_len1;
+	__u8 task_len2;
+	__u8 mrttest_num;
+	__u8 resv1;
+	__le64 key;
+	__le64 in;
+	__le64 out;
+	__le16 tag;
+	__le16 resv2;
+#define _HPRE_SQE_ALIGN_EXT	7
+	__le32 rsvd1[_HPRE_SQE_ALIGN_EXT];
+};
+
+struct hpre *hpre_find_device(int node);
+int hpre_algs_register(void);
+void hpre_algs_unregister(void);
+
+#endif
diff --git a/drivers/crypto/hisilicon/hpre/hpre_crypto.c b/drivers/crypto/hisilicon/hpre/hpre_crypto.c
new file mode 100644
index 000000000000..98f037e6ea3e
--- /dev/null
+++ b/drivers/crypto/hisilicon/hpre/hpre_crypto.c
@@ -0,0 +1,1137 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 HiSilicon Limited. */
+#include <crypto/akcipher.h>
+#include <crypto/dh.h>
+#include <crypto/internal/akcipher.h>
+#include <crypto/internal/kpp.h>
+#include <crypto/internal/rsa.h>
+#include <crypto/kpp.h>
+#include <crypto/scatterwalk.h>
+#include <linux/dma-mapping.h>
+#include <linux/fips.h>
+#include <linux/module.h>
+#include "hpre.h"
+
+struct hpre_ctx;
+
+#define HPRE_CRYPTO_ALG_PRI	1000
+#define HPRE_ALIGN_SZ		64
+#define HPRE_BITS_2_BYTES_SHIFT	3
+#define HPRE_RSA_512BITS_KSZ	64
+#define HPRE_RSA_1536BITS_KSZ	192
+#define HPRE_CRT_PRMS		5
+#define HPRE_CRT_Q		2
+#define HPRE_CRT_P		3
+#define HPRE_CRT_INV		4
+#define HPRE_DH_G_FLAG		0x02
+#define HPRE_TRY_SEND_TIMES	100
+#define HPRE_INVLD_REQ_ID		(-1)
+#define HPRE_DEV(ctx)		(&((ctx)->qp->qm->pdev->dev))
+
+#define HPRE_SQE_ALG_BITS	5
+#define HPRE_SQE_DONE_SHIFT	30
+#define HPRE_DH_MAX_P_SZ	512
+
+typedef void (*hpre_cb)(struct hpre_ctx *ctx, void *sqe);
+
+struct hpre_rsa_ctx {
+	/* low address: e--->n */
+	char *pubkey;
+	dma_addr_t dma_pubkey;
+
+	/* low address: d--->n */
+	char *prikey;
+	dma_addr_t dma_prikey;
+
+	/* low address: dq->dp->q->p->qinv */
+	char *crt_prikey;
+	dma_addr_t dma_crt_prikey;
+
+	struct crypto_akcipher *soft_tfm;
+};
+
+struct hpre_dh_ctx {
+	/*
+	 * If base is g we compute the public key
+	 *	ya = g^xa mod p; [RFC2631 sec 2.1.1]
+	 * else if base if the counterpart public key we
+	 * compute the shared secret
+	 *	ZZ = yb^xa mod p; [RFC2631 sec 2.1.1]
+	 */
+	char *xa_p; /* low address: d--->n, please refer to Hisilicon HPRE UM */
+	dma_addr_t dma_xa_p;
+
+	char *g; /* m */
+	dma_addr_t dma_g;
+};
+
+struct hpre_ctx {
+	struct hisi_qp *qp;
+	struct hpre_asym_request **req_list;
+	spinlock_t req_lock;
+	unsigned int key_sz;
+	bool crt_g2_mode;
+	struct idr req_idr;
+	union {
+		struct hpre_rsa_ctx rsa;
+		struct hpre_dh_ctx dh;
+	};
+};
+
+struct hpre_asym_request {
+	char *src;
+	char *dst;
+	struct hpre_sqe req;
+	struct hpre_ctx *ctx;
+	union {
+		struct akcipher_request *rsa;
+		struct kpp_request *dh;
+	} areq;
+	int err;
+	int req_id;
+	hpre_cb cb;
+};
+
+static DEFINE_MUTEX(hpre_alg_lock);
+static unsigned int hpre_active_devs;
+
+static int hpre_alloc_req_id(struct hpre_ctx *ctx)
+{
+	unsigned long flags;
+	int id;
+
+	spin_lock_irqsave(&ctx->req_lock, flags);
+	id = idr_alloc(&ctx->req_idr, NULL, 0, QM_Q_DEPTH, GFP_ATOMIC);
+	spin_unlock_irqrestore(&ctx->req_lock, flags);
+
+	return id;
+}
+
+static void hpre_free_req_id(struct hpre_ctx *ctx, int req_id)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctx->req_lock, flags);
+	idr_remove(&ctx->req_idr, req_id);
+	spin_unlock_irqrestore(&ctx->req_lock, flags);
+}
+
+static int hpre_add_req_to_ctx(struct hpre_asym_request *hpre_req)
+{
+	struct hpre_ctx *ctx;
+	int id;
+
+	ctx = hpre_req->ctx;
+	id = hpre_alloc_req_id(ctx);
+	if (id < 0)
+		return -EINVAL;
+
+	ctx->req_list[id] = hpre_req;
+	hpre_req->req_id = id;
+
+	return id;
+}
+
+static void hpre_rm_req_from_ctx(struct hpre_asym_request *hpre_req)
+{
+	struct hpre_ctx *ctx = hpre_req->ctx;
+	int id = hpre_req->req_id;
+
+	if (hpre_req->req_id >= 0) {
+		hpre_req->req_id = HPRE_INVLD_REQ_ID;
+		ctx->req_list[id] = NULL;
+		hpre_free_req_id(ctx, id);
+	}
+}
+
+static struct hisi_qp *hpre_get_qp_and_start(void)
+{
+	struct hisi_qp *qp;
+	struct hpre *hpre;
+	int ret;
+
+	/* find the proper hpre device, which is near the current CPU core */
+	hpre = hpre_find_device(cpu_to_node(smp_processor_id()));
+	if (!hpre) {
+		pr_err("Can not find proper hpre device!\n");
+		return ERR_PTR(-ENODEV);
+	}
+
+	qp = hisi_qm_create_qp(&hpre->qm, 0);
+	if (IS_ERR(qp)) {
+		pci_err(hpre->qm.pdev, "Can not create qp!\n");
+		return ERR_PTR(-ENODEV);
+	}
+
+	ret = hisi_qm_start_qp(qp, 0);
+	if (ret < 0) {
+		hisi_qm_release_qp(qp);
+		pci_err(hpre->qm.pdev, "Can not start qp!\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	return qp;
+}
+
+static int hpre_get_data_dma_addr(struct hpre_asym_request *hpre_req,
+			      struct scatterlist *data, unsigned int len,
+			      int is_src, dma_addr_t *tmp)
+{
+	struct hpre_ctx *ctx = hpre_req->ctx;
+	struct device *dev = HPRE_DEV(ctx);
+	enum dma_data_direction dma_dir;
+
+	if (is_src) {
+		hpre_req->src = NULL;
+		dma_dir = DMA_TO_DEVICE;
+	} else {
+		hpre_req->dst = NULL;
+		dma_dir = DMA_FROM_DEVICE;
+	}
+	*tmp = dma_map_single(dev, sg_virt(data),
+			      len, dma_dir);
+	if (dma_mapping_error(dev, *tmp)) {
+		dev_err(dev, "dma map data err!\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int hpre_prepare_dma_buf(struct hpre_asym_request *hpre_req,
+			       struct scatterlist *data, unsigned int len,
+			       int is_src, dma_addr_t *tmp)
+{
+	struct hpre_ctx *ctx = hpre_req->ctx;
+	struct device *dev = HPRE_DEV(ctx);
+	void *ptr;
+	int shift;
+
+	shift = ctx->key_sz - len;
+	if (shift < 0)
+		return -EINVAL;
+
+	ptr = dma_alloc_coherent(dev, ctx->key_sz, tmp, GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	if (is_src) {
+		scatterwalk_map_and_copy(ptr + shift, data, 0, len, 0);
+		hpre_req->src = ptr;
+	} else {
+		hpre_req->dst = ptr;
+	}
+
+	return 0;
+}
+
+static int hpre_hw_data_init(struct hpre_asym_request *hpre_req,
+			 struct scatterlist *data, unsigned int len,
+			 int is_src, int is_dh)
+{
+	struct hpre_sqe *msg = &hpre_req->req;
+	struct hpre_ctx *ctx = hpre_req->ctx;
+	dma_addr_t tmp;
+	int ret;
+
+	/* when the data is dh's source, we should format it */
+	if ((sg_is_last(data) && len == ctx->key_sz) &&
+	    ((is_dh && !is_src) || !is_dh))
+		ret = hpre_get_data_dma_addr(hpre_req, data, len, is_src, &tmp);
+	else
+		ret = hpre_prepare_dma_buf(hpre_req, data, len,
+					  is_src, &tmp);
+	if (ret)
+		return ret;
+
+	if (is_src)
+		msg->in = cpu_to_le64(tmp);
+	else
+		msg->out = cpu_to_le64(tmp);
+
+	return 0;
+}
+
+static void hpre_hw_data_clr_all(struct hpre_ctx *ctx,
+			     struct hpre_asym_request *req,
+			     struct scatterlist *dst, struct scatterlist *src)
+{
+	struct device *dev = HPRE_DEV(ctx);
+	struct hpre_sqe *sqe = &req->req;
+	dma_addr_t tmp;
+
+	tmp = le64_to_cpu(sqe->in);
+	if (!tmp)
+		return;
+
+	if (src) {
+		if (req->src)
+			dma_free_coherent(dev, ctx->key_sz,
+					  req->src, tmp);
+		else
+			dma_unmap_single(dev, tmp,
+					 ctx->key_sz, DMA_TO_DEVICE);
+	}
+
+	tmp = le64_to_cpu(sqe->out);
+	if (!tmp)
+		return;
+
+	if (req->dst) {
+		if (dst)
+			scatterwalk_map_and_copy(req->dst, dst, 0,
+						 ctx->key_sz, 1);
+		dma_free_coherent(dev, ctx->key_sz, req->dst, tmp);
+	} else {
+		dma_unmap_single(dev, tmp, ctx->key_sz, DMA_FROM_DEVICE);
+	}
+}
+
+static int hpre_alg_res_post_hf(struct hpre_ctx *ctx, struct hpre_sqe *sqe,
+			    void **kreq)
+{
+	struct hpre_asym_request *req;
+	int err, id, done;
+
+#define HPRE_NO_HW_ERR		0
+#define HPRE_HW_TASK_DONE	3
+#define HREE_HW_ERR_MASK	0x7ff
+#define HREE_SQE_DONE_MASK	0x3
+	id = (int)le16_to_cpu(sqe->tag);
+	req = ctx->req_list[id];
+	hpre_rm_req_from_ctx(req);
+	*kreq = req;
+
+	err = (le32_to_cpu(sqe->dw0) >> HPRE_SQE_ALG_BITS) &
+		HREE_HW_ERR_MASK;
+
+	done = (le32_to_cpu(sqe->dw0) >> HPRE_SQE_DONE_SHIFT) &
+		HREE_SQE_DONE_MASK;
+
+	if (err == HPRE_NO_HW_ERR &&  done == HPRE_HW_TASK_DONE)
+		return  0;
+
+	return -EINVAL;
+}
+
+static int hpre_ctx_set(struct hpre_ctx *ctx, struct hisi_qp *qp, int qlen)
+{
+	if (!ctx || !qp || qlen < 0)
+		return -EINVAL;
+
+	spin_lock_init(&ctx->req_lock);
+	ctx->qp = qp;
+
+	ctx->req_list = kcalloc(qlen, sizeof(void *), GFP_KERNEL);
+	if (!ctx->req_list)
+		return -ENOMEM;
+	ctx->key_sz = 0;
+	ctx->crt_g2_mode = false;
+	idr_init(&ctx->req_idr);
+
+	return 0;
+}
+
+static void hpre_ctx_clear(struct hpre_ctx *ctx, bool is_clear_all)
+{
+	if (is_clear_all) {
+		idr_destroy(&ctx->req_idr);
+		kfree(ctx->req_list);
+		hisi_qm_release_qp(ctx->qp);
+	}
+
+	ctx->crt_g2_mode = false;
+	ctx->key_sz = 0;
+}
+
+static void hpre_dh_cb(struct hpre_ctx *ctx, void *resp)
+{
+	struct hpre_asym_request *req;
+	struct kpp_request *areq;
+	int ret;
+
+	ret = hpre_alg_res_post_hf(ctx, resp, (void **)&req);
+	areq = req->areq.dh;
+	areq->dst_len = ctx->key_sz;
+	hpre_hw_data_clr_all(ctx, req, areq->dst, areq->src);
+	kpp_request_complete(areq, ret);
+}
+
+static void hpre_rsa_cb(struct hpre_ctx *ctx, void *resp)
+{
+	struct hpre_asym_request *req;
+	struct akcipher_request *areq;
+	int ret;
+
+	ret = hpre_alg_res_post_hf(ctx, resp, (void **)&req);
+	areq = req->areq.rsa;
+	areq->dst_len = ctx->key_sz;
+	hpre_hw_data_clr_all(ctx, req, areq->dst, areq->src);
+	akcipher_request_complete(areq, ret);
+}
+
+static void hpre_alg_cb(struct hisi_qp *qp, void *resp)
+{
+	struct hpre_ctx *ctx = qp->qp_ctx;
+	struct hpre_sqe *sqe = resp;
+
+	ctx->req_list[sqe->tag]->cb(ctx, resp);
+}
+
+static int hpre_ctx_init(struct hpre_ctx *ctx)
+{
+	struct hisi_qp *qp;
+
+	qp = hpre_get_qp_and_start();
+	if (IS_ERR(qp))
+		return PTR_ERR(qp);
+
+	qp->qp_ctx = ctx;
+	qp->req_cb = hpre_alg_cb;
+
+	return hpre_ctx_set(ctx, qp, QM_Q_DEPTH);
+}
+
+static int hpre_msg_request_set(struct hpre_ctx *ctx, void *req, bool is_rsa)
+{
+	struct hpre_asym_request *h_req;
+	struct hpre_sqe *msg;
+	int req_id;
+	void *tmp;
+
+	if (is_rsa) {
+		struct akcipher_request *akreq = req;
+
+		if (akreq->dst_len < ctx->key_sz) {
+			akreq->dst_len = ctx->key_sz;
+			return -EOVERFLOW;
+		}
+
+		tmp = akcipher_request_ctx(akreq);
+		h_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ);
+		h_req->cb = hpre_rsa_cb;
+		h_req->areq.rsa = akreq;
+		msg = &h_req->req;
+		memset(msg, 0, sizeof(*msg));
+	} else {
+		struct kpp_request *kreq = req;
+
+		if (kreq->dst_len < ctx->key_sz) {
+			kreq->dst_len = ctx->key_sz;
+			return -EOVERFLOW;
+		}
+
+		tmp = kpp_request_ctx(kreq);
+		h_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ);
+		h_req->cb = hpre_dh_cb;
+		h_req->areq.dh = kreq;
+		msg = &h_req->req;
+		memset(msg, 0, sizeof(*msg));
+		msg->key = cpu_to_le64((u64)ctx->dh.dma_xa_p);
+	}
+
+	msg->dw0 |= cpu_to_le32(0x1 << HPRE_SQE_DONE_SHIFT);
+	msg->task_len1 = (ctx->key_sz >> HPRE_BITS_2_BYTES_SHIFT) - 1;
+	h_req->ctx = ctx;
+
+	req_id = hpre_add_req_to_ctx(h_req);
+	if (req_id < 0)
+		return -EBUSY;
+
+	msg->tag = cpu_to_le16((u16)req_id);
+
+	return 0;
+}
+
+#ifdef CONFIG_CRYPTO_DH
+static int hpre_dh_compute_value(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+	void *tmp = kpp_request_ctx(req);
+	struct hpre_asym_request *hpre_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ);
+	struct hpre_sqe *msg = &hpre_req->req;
+	int ctr = 0;
+	int ret;
+
+	if (!ctx)
+		return -EINVAL;
+
+	ret = hpre_msg_request_set(ctx, req, false);
+	if (ret)
+		return ret;
+
+	if (req->src) {
+		ret = hpre_hw_data_init(hpre_req, req->src, req->src_len, 1, 1);
+		if (ret)
+			goto clear_all;
+	}
+
+	ret = hpre_hw_data_init(hpre_req, req->dst, req->dst_len, 0, 1);
+	if (ret)
+		goto clear_all;
+
+	if (ctx->crt_g2_mode && !req->src)
+		msg->dw0 |= HPRE_ALG_DH_G2;
+	else
+		msg->dw0 |= HPRE_ALG_DH;
+	do {
+		ret = hisi_qp_send(ctx->qp, msg);
+	} while (ret == -EBUSY && ctr++ < HPRE_TRY_SEND_TIMES);
+
+	/* success */
+	if (!ret)
+		return -EINPROGRESS;
+
+clear_all:
+	hpre_rm_req_from_ctx(hpre_req);
+	hpre_hw_data_clr_all(ctx, hpre_req, req->dst, req->src);
+
+	return ret;
+}
+
+static int hpre_is_dh_params_length_valid(unsigned int key_sz)
+{
+#define _HPRE_DH_GRP1		768
+#define _HPRE_DH_GRP2		1024
+#define _HPRE_DH_GRP5		1536
+#define _HPRE_DH_GRP14		2048
+#define _HPRE_DH_GRP15		3072
+#define _HPRE_DH_GRP16		4096
+	switch (key_sz) {
+	case _HPRE_DH_GRP1:
+	case _HPRE_DH_GRP2:
+	case _HPRE_DH_GRP5:
+	case _HPRE_DH_GRP14:
+	case _HPRE_DH_GRP15:
+	case _HPRE_DH_GRP16:
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int hpre_dh_set_params(struct hpre_ctx *ctx, struct dh *params)
+{
+	struct device *dev = HPRE_DEV(ctx);
+	unsigned int sz;
+
+	if (params->p_size > HPRE_DH_MAX_P_SZ)
+		return -EINVAL;
+
+	if (hpre_is_dh_params_length_valid(params->p_size <<
+		HPRE_BITS_2_BYTES_SHIFT))
+		return -EINVAL;
+
+	sz = ctx->key_sz = params->p_size;
+	ctx->dh.xa_p = dma_alloc_coherent(dev, sz << 1,
+				&ctx->dh.dma_xa_p, GFP_KERNEL);
+	if (!ctx->dh.xa_p)
+		return -ENOMEM;
+
+	memcpy(ctx->dh.xa_p + sz, params->p, sz);
+
+	/* If g equals 2 don't copy it */
+	if (params->g_size == 1 && *(char *)params->g == HPRE_DH_G_FLAG) {
+		ctx->crt_g2_mode = true;
+		return 0;
+	}
+
+	ctx->dh.g = dma_alloc_coherent(dev, sz, &ctx->dh.dma_g, GFP_KERNEL);
+	if (!ctx->dh.g) {
+		dma_free_coherent(dev, sz << 1, ctx->dh.xa_p,
+				  ctx->dh.dma_xa_p);
+		ctx->dh.xa_p = NULL;
+		return -ENOMEM;
+	}
+
+	memcpy(ctx->dh.g + (sz - params->g_size), params->g, params->g_size);
+
+	return 0;
+}
+
+static void hpre_dh_clear_ctx(struct hpre_ctx *ctx, bool is_clear_all)
+{
+	struct device *dev = HPRE_DEV(ctx);
+	unsigned int sz = ctx->key_sz;
+
+	if (is_clear_all)
+		hisi_qm_stop_qp(ctx->qp);
+
+	if (ctx->dh.g) {
+		memset(ctx->dh.g, 0, sz);
+		dma_free_coherent(dev, sz, ctx->dh.g, ctx->dh.dma_g);
+		ctx->dh.g = NULL;
+	}
+
+	if (ctx->dh.xa_p) {
+		memset(ctx->dh.xa_p, 0, sz);
+		dma_free_coherent(dev, sz << 1, ctx->dh.xa_p,
+				  ctx->dh.dma_xa_p);
+		ctx->dh.xa_p = NULL;
+	}
+
+	hpre_ctx_clear(ctx, is_clear_all);
+}
+
+static int hpre_dh_set_secret(struct crypto_kpp *tfm, const void *buf,
+			      unsigned int len)
+{
+	struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+	struct dh params;
+	int ret;
+
+	if (crypto_dh_decode_key(buf, len, &params) < 0)
+		return -EINVAL;
+
+	/* Free old secret if any */
+	hpre_dh_clear_ctx(ctx, false);
+
+	ret = hpre_dh_set_params(ctx, &params);
+	if (ret < 0)
+		goto err_clear_ctx;
+
+	memcpy(ctx->dh.xa_p + (ctx->key_sz - params.key_size), params.key,
+	       params.key_size);
+
+	return 0;
+
+err_clear_ctx:
+	hpre_dh_clear_ctx(ctx, false);
+	return ret;
+}
+
+static unsigned int hpre_dh_max_size(struct crypto_kpp *tfm)
+{
+	struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+
+	return ctx->key_sz;
+}
+
+static int hpre_dh_init_tfm(struct crypto_kpp *tfm)
+{
+	struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+
+	return hpre_ctx_init(ctx);
+}
+
+static void hpre_dh_exit_tfm(struct crypto_kpp *tfm)
+{
+	struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+
+	hpre_dh_clear_ctx(ctx, true);
+}
+#endif
+
+static void hpre_rsa_drop_leading_zeros(const char **ptr, size_t *len)
+{
+	while (!**ptr && *len) {
+		(*ptr)++;
+		(*len)--;
+	}
+}
+
+static bool hpre_rsa_key_size_is_support(unsigned int len)
+{
+	unsigned int bits = len << HPRE_BITS_2_BYTES_SHIFT;
+
+#define _RSA_1024BITS_KEY_WDTH		1024
+#define _RSA_2048BITS_KEY_WDTH		2048
+#define _RSA_3072BITS_KEY_WDTH		3072
+#define _RSA_4096BITS_KEY_WDTH		4096
+
+	switch (bits) {
+	case _RSA_1024BITS_KEY_WDTH:
+	case _RSA_2048BITS_KEY_WDTH:
+	case _RSA_3072BITS_KEY_WDTH:
+	case _RSA_4096BITS_KEY_WDTH:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static int hpre_rsa_enc(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct hpre_ctx *ctx = akcipher_tfm_ctx(tfm);
+	void *tmp = akcipher_request_ctx(req);
+	struct hpre_asym_request *hpre_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ);
+	struct hpre_sqe *msg = &hpre_req->req;
+	int ctr = 0;
+	int ret;
+
+	if (!ctx)
+		return -EINVAL;
+
+	/* For 512 and 1536 bits key size, use soft tfm instead */
+	if (ctx->key_sz == HPRE_RSA_512BITS_KSZ ||
+	    ctx->key_sz == HPRE_RSA_1536BITS_KSZ) {
+		akcipher_request_set_tfm(req, ctx->rsa.soft_tfm);
+		ret = crypto_akcipher_encrypt(req);
+		akcipher_request_set_tfm(req, tfm);
+		return ret;
+	}
+
+	if (!ctx->rsa.pubkey)
+		return -EINVAL;
+
+	ret = hpre_msg_request_set(ctx, req, true);
+	if (ret)
+		return ret;
+
+	msg->dw0 |= HPRE_ALG_NC_NCRT;
+	msg->key = cpu_to_le64((u64)ctx->rsa.dma_pubkey);
+
+	ret = hpre_hw_data_init(hpre_req, req->src, req->src_len, 1, 0);
+	if (ret)
+		goto clear_all;
+
+	ret = hpre_hw_data_init(hpre_req, req->dst, req->dst_len, 0, 0);
+	if (ret)
+		goto clear_all;
+
+	do {
+		ret = hisi_qp_send(ctx->qp, msg);
+	} while (ret == -EBUSY && ctr++ < HPRE_TRY_SEND_TIMES);
+
+	/* success */
+	if (!ret)
+		return -EINPROGRESS;
+
+clear_all:
+	hpre_rm_req_from_ctx(hpre_req);
+	hpre_hw_data_clr_all(ctx, hpre_req, req->dst, req->src);
+
+	return ret;
+}
+
+static int hpre_rsa_dec(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct hpre_ctx *ctx = akcipher_tfm_ctx(tfm);
+	void *tmp = akcipher_request_ctx(req);
+	struct hpre_asym_request *hpre_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ);
+	struct hpre_sqe *msg = &hpre_req->req;
+	int ctr = 0;
+	int ret;
+
+	if (!ctx)
+		return -EINVAL;
+
+	/* For 512 and 1536 bits key size, use soft tfm instead */
+	if (ctx->key_sz == HPRE_RSA_512BITS_KSZ ||
+	    ctx->key_sz == HPRE_RSA_1536BITS_KSZ) {
+		akcipher_request_set_tfm(req, ctx->rsa.soft_tfm);
+		ret = crypto_akcipher_decrypt(req);
+		akcipher_request_set_tfm(req, tfm);
+		return ret;
+	}
+
+	if (!ctx->rsa.prikey)
+		return -EINVAL;
+
+	ret = hpre_msg_request_set(ctx, req, true);
+	if (ret)
+		return ret;
+
+	if (ctx->crt_g2_mode) {
+		msg->key = cpu_to_le64((u64)ctx->rsa.dma_crt_prikey);
+		msg->dw0 |= HPRE_ALG_NC_CRT;
+	} else {
+		msg->key = cpu_to_le64((u64)ctx->rsa.dma_prikey);
+		msg->dw0 |= HPRE_ALG_NC_NCRT;
+	}
+
+	ret = hpre_hw_data_init(hpre_req, req->src, req->src_len, 1, 0);
+	if (ret)
+		goto clear_all;
+
+	ret = hpre_hw_data_init(hpre_req, req->dst, req->dst_len, 0, 0);
+	if (ret)
+		goto clear_all;
+
+	do {
+		ret = hisi_qp_send(ctx->qp, msg);
+	} while (ret == -EBUSY && ctr++ < HPRE_TRY_SEND_TIMES);
+
+	/* success */
+	if (!ret)
+		return -EINPROGRESS;
+
+clear_all:
+	hpre_rm_req_from_ctx(hpre_req);
+	hpre_hw_data_clr_all(ctx, hpre_req, req->dst, req->src);
+
+	return ret;
+}
+
+static int hpre_rsa_set_n(struct hpre_ctx *ctx, const char *value,
+			  size_t vlen, bool private)
+{
+	const char *ptr = value;
+
+	hpre_rsa_drop_leading_zeros(&ptr, &vlen);
+
+	ctx->key_sz = vlen;
+
+	/* if invalid key size provided, we use software tfm */
+	if (!hpre_rsa_key_size_is_support(ctx->key_sz))
+		return 0;
+
+	ctx->rsa.pubkey = dma_alloc_coherent(HPRE_DEV(ctx), vlen << 1,
+					     &ctx->rsa.dma_pubkey,
+					     GFP_KERNEL);
+	if (!ctx->rsa.pubkey)
+		return -ENOMEM;
+
+	if (private) {
+		ctx->rsa.prikey = dma_alloc_coherent(HPRE_DEV(ctx), vlen << 1,
+						     &ctx->rsa.dma_prikey,
+						     GFP_KERNEL);
+		if (!ctx->rsa.prikey) {
+			dma_free_coherent(HPRE_DEV(ctx), vlen << 1,
+					  ctx->rsa.pubkey,
+					  ctx->rsa.dma_pubkey);
+			ctx->rsa.pubkey = NULL;
+			return -ENOMEM;
+		}
+		memcpy(ctx->rsa.prikey + vlen, ptr, vlen);
+	}
+	memcpy(ctx->rsa.pubkey + vlen, ptr, vlen);
+
+	/* Using hardware HPRE to do RSA */
+	return 1;
+}
+
+static int hpre_rsa_set_e(struct hpre_ctx *ctx, const char *value,
+			  size_t vlen)
+{
+	const char *ptr = value;
+
+	hpre_rsa_drop_leading_zeros(&ptr, &vlen);
+
+	if (!ctx->key_sz || !vlen || vlen > ctx->key_sz) {
+		ctx->rsa.pubkey = NULL;
+		return -EINVAL;
+	}
+
+	memcpy(ctx->rsa.pubkey + ctx->key_sz - vlen, ptr, vlen);
+
+	return 0;
+}
+
+static int hpre_rsa_set_d(struct hpre_ctx *ctx, const char *value,
+			  size_t vlen)
+{
+	const char *ptr = value;
+
+	hpre_rsa_drop_leading_zeros(&ptr, &vlen);
+
+	if (!ctx->key_sz || !vlen || vlen > ctx->key_sz)
+		return -EINVAL;
+
+	memcpy(ctx->rsa.prikey + ctx->key_sz - vlen, ptr, vlen);
+
+	return 0;
+}
+
+static int hpre_crt_para_get(char *para, const char *raw,
+			     unsigned int raw_sz, unsigned int para_size)
+{
+	const char *ptr = raw;
+	size_t len = raw_sz;
+
+	hpre_rsa_drop_leading_zeros(&ptr, &len);
+	if (!len || len > para_size)
+		return -EINVAL;
+
+	memcpy(para + para_size - len, ptr, len);
+
+	return 0;
+}
+
+static int hpre_rsa_setkey_crt(struct hpre_ctx *ctx, struct rsa_key *rsa_key)
+{
+	unsigned int hlf_ksz = ctx->key_sz >> 1;
+	struct device *dev = HPRE_DEV(ctx);
+	u64 offset;
+	int ret;
+
+	ctx->rsa.crt_prikey = dma_alloc_coherent(dev, hlf_ksz * HPRE_CRT_PRMS,
+					&ctx->rsa.dma_crt_prikey,
+					GFP_KERNEL);
+	if (!ctx->rsa.crt_prikey)
+		return -ENOMEM;
+
+	ret = hpre_crt_para_get(ctx->rsa.crt_prikey, rsa_key->dq,
+				rsa_key->dq_sz, hlf_ksz);
+	if (ret)
+		goto free_key;
+
+	offset = hlf_ksz;
+	ret = hpre_crt_para_get(ctx->rsa.crt_prikey + offset, rsa_key->dp,
+				rsa_key->dp_sz, hlf_ksz);
+	if (ret)
+		goto free_key;
+
+	offset = hlf_ksz * HPRE_CRT_Q;
+	ret = hpre_crt_para_get(ctx->rsa.crt_prikey + offset,
+				rsa_key->q, rsa_key->q_sz, hlf_ksz);
+	if (ret)
+		goto free_key;
+
+	offset = hlf_ksz * HPRE_CRT_P;
+	ret = hpre_crt_para_get(ctx->rsa.crt_prikey + offset,
+				rsa_key->p, rsa_key->p_sz, hlf_ksz);
+	if (ret)
+		goto free_key;
+
+	offset = hlf_ksz * HPRE_CRT_INV;
+	ret = hpre_crt_para_get(ctx->rsa.crt_prikey + offset,
+				rsa_key->qinv, rsa_key->qinv_sz, hlf_ksz);
+	if (ret)
+		goto free_key;
+
+	ctx->crt_g2_mode = true;
+
+	return 0;
+
+free_key:
+	offset = hlf_ksz * HPRE_CRT_PRMS;
+	memset(ctx->rsa.crt_prikey, 0, offset);
+	dma_free_coherent(dev, hlf_ksz * HPRE_CRT_PRMS, ctx->rsa.crt_prikey,
+			  ctx->rsa.dma_crt_prikey);
+	ctx->rsa.crt_prikey = NULL;
+	ctx->crt_g2_mode = false;
+
+	return ret;
+}
+
+/* If it is clear all, all the resources of the QP will be cleaned. */
+static void hpre_rsa_clear_ctx(struct hpre_ctx *ctx, bool is_clear_all)
+{
+	unsigned int half_key_sz = ctx->key_sz >> 1;
+	struct device *dev = HPRE_DEV(ctx);
+
+	if (is_clear_all)
+		hisi_qm_stop_qp(ctx->qp);
+
+	if (ctx->rsa.pubkey) {
+		dma_free_coherent(dev, ctx->key_sz << 1,
+				  ctx->rsa.pubkey, ctx->rsa.dma_pubkey);
+		ctx->rsa.pubkey = NULL;
+	}
+
+	if (ctx->rsa.crt_prikey) {
+		memset(ctx->rsa.crt_prikey, 0, half_key_sz * HPRE_CRT_PRMS);
+		dma_free_coherent(dev, half_key_sz * HPRE_CRT_PRMS,
+				  ctx->rsa.crt_prikey, ctx->rsa.dma_crt_prikey);
+		ctx->rsa.crt_prikey = NULL;
+	}
+
+	if (ctx->rsa.prikey) {
+		memset(ctx->rsa.prikey, 0, ctx->key_sz);
+		dma_free_coherent(dev, ctx->key_sz << 1, ctx->rsa.prikey,
+				  ctx->rsa.dma_prikey);
+		ctx->rsa.prikey = NULL;
+	}
+
+	hpre_ctx_clear(ctx, is_clear_all);
+}
+
+/*
+ * we should judge if it is CRT or not,
+ * CRT: return true,  N-CRT: return false .
+ */
+static bool hpre_is_crt_key(struct rsa_key *key)
+{
+	u16 len = key->p_sz + key->q_sz + key->dp_sz + key->dq_sz +
+		  key->qinv_sz;
+
+#define LEN_OF_NCRT_PARA	5
+
+	/* N-CRT less than 5 parameters */
+	return len > LEN_OF_NCRT_PARA;
+}
+
+static int hpre_rsa_setkey(struct hpre_ctx *ctx, const void *key,
+			   unsigned int keylen, bool private)
+{
+	struct rsa_key rsa_key;
+	int ret;
+
+	hpre_rsa_clear_ctx(ctx, false);
+
+	if (private)
+		ret = rsa_parse_priv_key(&rsa_key, key, keylen);
+	else
+		ret = rsa_parse_pub_key(&rsa_key, key, keylen);
+	if (ret < 0)
+		return ret;
+
+	ret = hpre_rsa_set_n(ctx, rsa_key.n, rsa_key.n_sz, private);
+	if (ret <= 0)
+		return ret;
+
+	if (private) {
+		ret = hpre_rsa_set_d(ctx, rsa_key.d, rsa_key.d_sz);
+		if (ret < 0)
+			goto free;
+
+		if (hpre_is_crt_key(&rsa_key)) {
+			ret = hpre_rsa_setkey_crt(ctx, &rsa_key);
+			if (ret < 0)
+				goto free;
+		}
+	}
+
+	ret = hpre_rsa_set_e(ctx, rsa_key.e, rsa_key.e_sz);
+	if (ret < 0)
+		goto free;
+
+	if ((private && !ctx->rsa.prikey) || !ctx->rsa.pubkey) {
+		ret = -EINVAL;
+		goto free;
+	}
+
+	return 0;
+
+free:
+	hpre_rsa_clear_ctx(ctx, false);
+	return ret;
+}
+
+static int hpre_rsa_setpubkey(struct crypto_akcipher *tfm, const void *key,
+			      unsigned int keylen)
+{
+	struct hpre_ctx *ctx = akcipher_tfm_ctx(tfm);
+	int ret;
+
+	ret = crypto_akcipher_set_pub_key(ctx->rsa.soft_tfm, key, keylen);
+	if (ret)
+		return ret;
+
+	return hpre_rsa_setkey(ctx, key, keylen, false);
+}
+
+static int hpre_rsa_setprivkey(struct crypto_akcipher *tfm, const void *key,
+			       unsigned int keylen)
+{
+	struct hpre_ctx *ctx = akcipher_tfm_ctx(tfm);
+	int ret;
+
+	ret = crypto_akcipher_set_priv_key(ctx->rsa.soft_tfm, key, keylen);
+	if (ret)
+		return ret;
+
+	return hpre_rsa_setkey(ctx, key, keylen, true);
+}
+
+static unsigned int hpre_rsa_max_size(struct crypto_akcipher *tfm)
+{
+	struct hpre_ctx *ctx = akcipher_tfm_ctx(tfm);
+
+	/* For 512 and 1536 bits key size, use soft tfm instead */
+	if (ctx->key_sz == HPRE_RSA_512BITS_KSZ ||
+	    ctx->key_sz == HPRE_RSA_1536BITS_KSZ)
+		return crypto_akcipher_maxsize(ctx->rsa.soft_tfm);
+
+	return ctx->key_sz;
+}
+
+static int hpre_rsa_init_tfm(struct crypto_akcipher *tfm)
+{
+	struct hpre_ctx *ctx = akcipher_tfm_ctx(tfm);
+
+	ctx->rsa.soft_tfm = crypto_alloc_akcipher("rsa-generic", 0, 0);
+	if (IS_ERR(ctx->rsa.soft_tfm)) {
+		pr_err("Can not alloc_akcipher!\n");
+		return PTR_ERR(ctx->rsa.soft_tfm);
+	}
+
+	return hpre_ctx_init(ctx);
+}
+
+static void hpre_rsa_exit_tfm(struct crypto_akcipher *tfm)
+{
+	struct hpre_ctx *ctx = akcipher_tfm_ctx(tfm);
+
+	hpre_rsa_clear_ctx(ctx, true);
+	crypto_free_akcipher(ctx->rsa.soft_tfm);
+}
+
+static struct akcipher_alg rsa = {
+	.sign = hpre_rsa_dec,
+	.verify = hpre_rsa_enc,
+	.encrypt = hpre_rsa_enc,
+	.decrypt = hpre_rsa_dec,
+	.set_pub_key = hpre_rsa_setpubkey,
+	.set_priv_key = hpre_rsa_setprivkey,
+	.max_size = hpre_rsa_max_size,
+	.init = hpre_rsa_init_tfm,
+	.exit = hpre_rsa_exit_tfm,
+	.reqsize = sizeof(struct hpre_asym_request) + HPRE_ALIGN_SZ,
+	.base = {
+		.cra_ctxsize = sizeof(struct hpre_ctx),
+		.cra_priority = HPRE_CRYPTO_ALG_PRI,
+		.cra_name = "rsa",
+		.cra_driver_name = "hpre-rsa",
+		.cra_module = THIS_MODULE,
+	},
+};
+
+#ifdef CONFIG_CRYPTO_DH
+static struct kpp_alg dh = {
+	.set_secret = hpre_dh_set_secret,
+	.generate_public_key = hpre_dh_compute_value,
+	.compute_shared_secret = hpre_dh_compute_value,
+	.max_size = hpre_dh_max_size,
+	.init = hpre_dh_init_tfm,
+	.exit = hpre_dh_exit_tfm,
+	.reqsize = sizeof(struct hpre_asym_request) + HPRE_ALIGN_SZ,
+	.base = {
+		.cra_ctxsize = sizeof(struct hpre_ctx),
+		.cra_priority = HPRE_CRYPTO_ALG_PRI,
+		.cra_name = "dh",
+		.cra_driver_name = "hpre-dh",
+		.cra_module = THIS_MODULE,
+	},
+};
+#endif
+
+int hpre_algs_register(void)
+{
+	int ret = 0;
+
+	mutex_lock(&hpre_alg_lock);
+	if (++hpre_active_devs == 1) {
+		rsa.base.cra_flags = 0;
+		ret = crypto_register_akcipher(&rsa);
+		if (ret)
+			goto unlock;
+#ifdef CONFIG_CRYPTO_DH
+		ret = crypto_register_kpp(&dh);
+		if (ret) {
+			crypto_unregister_akcipher(&rsa);
+			goto unlock;
+		}
+#endif
+	}
+
+unlock:
+	mutex_unlock(&hpre_alg_lock);
+	return ret;
+}
+
+void hpre_algs_unregister(void)
+{
+	mutex_lock(&hpre_alg_lock);
+	if (--hpre_active_devs == 0) {
+		crypto_unregister_akcipher(&rsa);
+#ifdef CONFIG_CRYPTO_DH
+		crypto_unregister_kpp(&dh);
+#endif
+	}
+	mutex_unlock(&hpre_alg_lock);
+}
diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c
new file mode 100644
index 000000000000..34e0424410bf
--- /dev/null
+++ b/drivers/crypto/hisilicon/hpre/hpre_main.c
@@ -0,0 +1,1052 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018-2019 HiSilicon Limited. */
+#include <linux/acpi.h>
+#include <linux/aer.h>
+#include <linux/bitops.h>
+#include <linux/debugfs.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/topology.h>
+#include "hpre.h"
+
+#define HPRE_VF_NUM			63
+#define HPRE_QUEUE_NUM_V2		1024
+#define HPRE_QM_ABNML_INT_MASK		0x100004
+#define HPRE_CTRL_CNT_CLR_CE_BIT	BIT(0)
+#define HPRE_COMM_CNT_CLR_CE		0x0
+#define HPRE_CTRL_CNT_CLR_CE		0x301000
+#define HPRE_FSM_MAX_CNT		0x301008
+#define HPRE_VFG_AXQOS			0x30100c
+#define HPRE_VFG_AXCACHE		0x301010
+#define HPRE_RDCHN_INI_CFG		0x301014
+#define HPRE_AWUSR_FP_CFG		0x301018
+#define HPRE_BD_ENDIAN			0x301020
+#define HPRE_ECC_BYPASS			0x301024
+#define HPRE_RAS_WIDTH_CFG		0x301028
+#define HPRE_POISON_BYPASS		0x30102c
+#define HPRE_BD_ARUSR_CFG		0x301030
+#define HPRE_BD_AWUSR_CFG		0x301034
+#define HPRE_TYPES_ENB			0x301038
+#define HPRE_DATA_RUSER_CFG		0x30103c
+#define HPRE_DATA_WUSER_CFG		0x301040
+#define HPRE_INT_MASK			0x301400
+#define HPRE_INT_STATUS			0x301800
+#define HPRE_CORE_INT_ENABLE		0
+#define HPRE_CORE_INT_DISABLE		0x003fffff
+#define HPRE_RAS_ECC_1BIT_TH		0x30140c
+#define HPRE_RDCHN_INI_ST		0x301a00
+#define HPRE_CLSTR_BASE			0x302000
+#define HPRE_CORE_EN_OFFSET		0x04
+#define HPRE_CORE_INI_CFG_OFFSET	0x20
+#define HPRE_CORE_INI_STATUS_OFFSET	0x80
+#define HPRE_CORE_HTBT_WARN_OFFSET	0x8c
+#define HPRE_CORE_IS_SCHD_OFFSET	0x90
+
+#define HPRE_RAS_CE_ENB			0x301410
+#define HPRE_HAC_RAS_CE_ENABLE		0x3f
+#define HPRE_RAS_NFE_ENB		0x301414
+#define HPRE_HAC_RAS_NFE_ENABLE		0x3fffc0
+#define HPRE_RAS_FE_ENB			0x301418
+#define HPRE_HAC_RAS_FE_ENABLE		0
+
+#define HPRE_CORE_ENB		(HPRE_CLSTR_BASE + HPRE_CORE_EN_OFFSET)
+#define HPRE_CORE_INI_CFG	(HPRE_CLSTR_BASE + HPRE_CORE_INI_CFG_OFFSET)
+#define HPRE_CORE_INI_STATUS (HPRE_CLSTR_BASE + HPRE_CORE_INI_STATUS_OFFSET)
+#define HPRE_HAC_ECC1_CNT		0x301a04
+#define HPRE_HAC_ECC2_CNT		0x301a08
+#define HPRE_HAC_INT_STATUS		0x301800
+#define HPRE_HAC_SOURCE_INT		0x301600
+#define MASTER_GLOBAL_CTRL_SHUTDOWN	1
+#define MASTER_TRANS_RETURN_RW		3
+#define HPRE_MASTER_TRANS_RETURN	0x300150
+#define HPRE_MASTER_GLOBAL_CTRL		0x300000
+#define HPRE_CLSTR_ADDR_INTRVL		0x1000
+#define HPRE_CLUSTER_INQURY		0x100
+#define HPRE_CLSTR_ADDR_INQRY_RSLT	0x104
+#define HPRE_TIMEOUT_ABNML_BIT		6
+#define HPRE_PASID_EN_BIT		9
+#define HPRE_REG_RD_INTVRL_US		10
+#define HPRE_REG_RD_TMOUT_US		1000
+#define HPRE_DBGFS_VAL_MAX_LEN		20
+#define HPRE_PCI_DEVICE_ID		0xa258
+#define HPRE_PCI_VF_DEVICE_ID		0xa259
+#define HPRE_ADDR(qm, offset)		(qm->io_base + (offset))
+#define HPRE_QM_USR_CFG_MASK		0xfffffffe
+#define HPRE_QM_AXI_CFG_MASK		0xffff
+#define HPRE_QM_VFG_AX_MASK		0xff
+#define HPRE_BD_USR_MASK		0x3
+#define HPRE_CLUSTER_CORE_MASK		0xf
+
+#define HPRE_VIA_MSI_DSM		1
+
+static LIST_HEAD(hpre_list);
+static DEFINE_MUTEX(hpre_list_lock);
+static const char hpre_name[] = "hisi_hpre";
+static struct dentry *hpre_debugfs_root;
+static const struct pci_device_id hpre_dev_ids[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, HPRE_PCI_DEVICE_ID) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, HPRE_PCI_VF_DEVICE_ID) },
+	{ 0, }
+};
+
+MODULE_DEVICE_TABLE(pci, hpre_dev_ids);
+
+struct hpre_hw_error {
+	u32 int_msk;
+	const char *msg;
+};
+
+static const char * const hpre_debug_file_name[] = {
+	[HPRE_CURRENT_QM]   = "current_qm",
+	[HPRE_CLEAR_ENABLE] = "rdclr_en",
+	[HPRE_CLUSTER_CTRL] = "cluster_ctrl",
+};
+
+static const struct hpre_hw_error hpre_hw_errors[] = {
+	{ .int_msk = BIT(0), .msg = "hpre_ecc_1bitt_err" },
+	{ .int_msk = BIT(1), .msg = "hpre_ecc_2bit_err" },
+	{ .int_msk = BIT(2), .msg = "hpre_data_wr_err" },
+	{ .int_msk = BIT(3), .msg = "hpre_data_rd_err" },
+	{ .int_msk = BIT(4), .msg = "hpre_bd_rd_err" },
+	{ .int_msk = BIT(5), .msg = "hpre_ooo_2bit_ecc_err" },
+	{ .int_msk = BIT(6), .msg = "hpre_cltr1_htbt_tm_out_err" },
+	{ .int_msk = BIT(7), .msg = "hpre_cltr2_htbt_tm_out_err" },
+	{ .int_msk = BIT(8), .msg = "hpre_cltr3_htbt_tm_out_err" },
+	{ .int_msk = BIT(9), .msg = "hpre_cltr4_htbt_tm_out_err" },
+	{ .int_msk = GENMASK(15, 10), .msg = "hpre_ooo_rdrsp_err" },
+	{ .int_msk = GENMASK(21, 16), .msg = "hpre_ooo_wrrsp_err" },
+	{ /* sentinel */ }
+};
+
+static const u64 hpre_cluster_offsets[] = {
+	[HPRE_CLUSTER0] =
+		HPRE_CLSTR_BASE + HPRE_CLUSTER0 * HPRE_CLSTR_ADDR_INTRVL,
+	[HPRE_CLUSTER1] =
+		HPRE_CLSTR_BASE + HPRE_CLUSTER1 * HPRE_CLSTR_ADDR_INTRVL,
+	[HPRE_CLUSTER2] =
+		HPRE_CLSTR_BASE + HPRE_CLUSTER2 * HPRE_CLSTR_ADDR_INTRVL,
+	[HPRE_CLUSTER3] =
+		HPRE_CLSTR_BASE + HPRE_CLUSTER3 * HPRE_CLSTR_ADDR_INTRVL,
+};
+
+static struct debugfs_reg32 hpre_cluster_dfx_regs[] = {
+	{"CORES_EN_STATUS          ",  HPRE_CORE_EN_OFFSET},
+	{"CORES_INI_CFG              ",  HPRE_CORE_INI_CFG_OFFSET},
+	{"CORES_INI_STATUS         ",  HPRE_CORE_INI_STATUS_OFFSET},
+	{"CORES_HTBT_WARN         ",  HPRE_CORE_HTBT_WARN_OFFSET},
+	{"CORES_IS_SCHD               ",  HPRE_CORE_IS_SCHD_OFFSET},
+};
+
+static struct debugfs_reg32 hpre_com_dfx_regs[] = {
+	{"READ_CLR_EN          ",  HPRE_CTRL_CNT_CLR_CE},
+	{"AXQOS                   ",  HPRE_VFG_AXQOS},
+	{"AWUSR_CFG              ",  HPRE_AWUSR_FP_CFG},
+	{"QM_ARUSR_MCFG1           ",  QM_ARUSER_M_CFG_1},
+	{"QM_AWUSR_MCFG1           ",  QM_AWUSER_M_CFG_1},
+	{"BD_ENDIAN               ",  HPRE_BD_ENDIAN},
+	{"ECC_CHECK_CTRL       ",  HPRE_ECC_BYPASS},
+	{"RAS_INT_WIDTH       ",  HPRE_RAS_WIDTH_CFG},
+	{"POISON_BYPASS       ",  HPRE_POISON_BYPASS},
+	{"BD_ARUSER               ",  HPRE_BD_ARUSR_CFG},
+	{"BD_AWUSER               ",  HPRE_BD_AWUSR_CFG},
+	{"DATA_ARUSER            ",  HPRE_DATA_RUSER_CFG},
+	{"DATA_AWUSER           ",  HPRE_DATA_WUSER_CFG},
+	{"INT_STATUS               ",  HPRE_INT_STATUS},
+};
+
+static int hpre_pf_q_num_set(const char *val, const struct kernel_param *kp)
+{
+	struct pci_dev *pdev;
+	u32 n, q_num;
+	u8 rev_id;
+	int ret;
+
+	if (!val)
+		return -EINVAL;
+
+	pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI, HPRE_PCI_DEVICE_ID, NULL);
+	if (!pdev) {
+		q_num = HPRE_QUEUE_NUM_V2;
+		pr_info("No device found currently, suppose queue number is %d\n",
+			q_num);
+	} else {
+		rev_id = pdev->revision;
+		if (rev_id != QM_HW_V2)
+			return -EINVAL;
+
+		q_num = HPRE_QUEUE_NUM_V2;
+	}
+
+	ret = kstrtou32(val, 10, &n);
+	if (ret != 0 || n == 0 || n > q_num)
+		return -EINVAL;
+
+	return param_set_int(val, kp);
+}
+
+static const struct kernel_param_ops hpre_pf_q_num_ops = {
+	.set = hpre_pf_q_num_set,
+	.get = param_get_int,
+};
+
+static u32 hpre_pf_q_num = HPRE_PF_DEF_Q_NUM;
+module_param_cb(hpre_pf_q_num, &hpre_pf_q_num_ops, &hpre_pf_q_num, 0444);
+MODULE_PARM_DESC(hpre_pf_q_num, "Number of queues in PF of CS(1-1024)");
+
+static inline void hpre_add_to_list(struct hpre *hpre)
+{
+	mutex_lock(&hpre_list_lock);
+	list_add_tail(&hpre->list, &hpre_list);
+	mutex_unlock(&hpre_list_lock);
+}
+
+static inline void hpre_remove_from_list(struct hpre *hpre)
+{
+	mutex_lock(&hpre_list_lock);
+	list_del(&hpre->list);
+	mutex_unlock(&hpre_list_lock);
+}
+
+struct hpre *hpre_find_device(int node)
+{
+	struct hpre *hpre, *ret = NULL;
+	int min_distance = INT_MAX;
+	struct device *dev;
+	int dev_node = 0;
+
+	mutex_lock(&hpre_list_lock);
+	list_for_each_entry(hpre, &hpre_list, list) {
+		dev = &hpre->qm.pdev->dev;
+#ifdef CONFIG_NUMA
+		dev_node = dev->numa_node;
+		if (dev_node < 0)
+			dev_node = 0;
+#endif
+		if (node_distance(dev_node, node) < min_distance) {
+			ret = hpre;
+			min_distance = node_distance(dev_node, node);
+		}
+	}
+	mutex_unlock(&hpre_list_lock);
+
+	return ret;
+}
+
+static int hpre_cfg_by_dsm(struct hisi_qm *qm)
+{
+	struct device *dev = &qm->pdev->dev;
+	union acpi_object *obj;
+	guid_t guid;
+
+	if (guid_parse("b06b81ab-0134-4a45-9b0c-483447b95fa7", &guid)) {
+		dev_err(dev, "Hpre GUID failed\n");
+		return -EINVAL;
+	}
+
+	/* Switch over to MSI handling due to non-standard PCI implementation */
+	obj = acpi_evaluate_dsm(ACPI_HANDLE(dev), &guid,
+				0, HPRE_VIA_MSI_DSM, NULL);
+	if (!obj) {
+		dev_err(dev, "ACPI handle failed!\n");
+		return -EIO;
+	}
+
+	ACPI_FREE(obj);
+
+	return 0;
+}
+
+static int hpre_set_user_domain_and_cache(struct hpre *hpre)
+{
+	struct hisi_qm *qm = &hpre->qm;
+	struct device *dev = &qm->pdev->dev;
+	unsigned long offset;
+	int ret, i;
+	u32 val;
+
+	writel(HPRE_QM_USR_CFG_MASK, HPRE_ADDR(qm, QM_ARUSER_M_CFG_ENABLE));
+	writel(HPRE_QM_USR_CFG_MASK, HPRE_ADDR(qm, QM_AWUSER_M_CFG_ENABLE));
+	writel_relaxed(HPRE_QM_AXI_CFG_MASK, HPRE_ADDR(qm, QM_AXI_M_CFG));
+
+	/* disable FLR triggered by BME(bus master enable) */
+	writel(PEH_AXUSER_CFG, HPRE_ADDR(qm, QM_PEH_AXUSER_CFG));
+	writel(PEH_AXUSER_CFG_ENABLE, HPRE_ADDR(qm, QM_PEH_AXUSER_CFG_ENABLE));
+
+	/* HPRE need more time, we close this interrupt */
+	val = readl_relaxed(HPRE_ADDR(qm, HPRE_QM_ABNML_INT_MASK));
+	val |= BIT(HPRE_TIMEOUT_ABNML_BIT);
+	writel_relaxed(val, HPRE_ADDR(qm, HPRE_QM_ABNML_INT_MASK));
+
+	writel(0x1, HPRE_ADDR(qm, HPRE_TYPES_ENB));
+	writel(HPRE_QM_VFG_AX_MASK, HPRE_ADDR(qm, HPRE_VFG_AXCACHE));
+	writel(0x0, HPRE_ADDR(qm, HPRE_BD_ENDIAN));
+	writel(0x0, HPRE_ADDR(qm, HPRE_INT_MASK));
+	writel(0x0, HPRE_ADDR(qm, HPRE_RAS_ECC_1BIT_TH));
+	writel(0x0, HPRE_ADDR(qm, HPRE_POISON_BYPASS));
+	writel(0x0, HPRE_ADDR(qm, HPRE_COMM_CNT_CLR_CE));
+	writel(0x0, HPRE_ADDR(qm, HPRE_ECC_BYPASS));
+
+	writel(HPRE_BD_USR_MASK, HPRE_ADDR(qm, HPRE_BD_ARUSR_CFG));
+	writel(HPRE_BD_USR_MASK, HPRE_ADDR(qm, HPRE_BD_AWUSR_CFG));
+	writel(0x1, HPRE_ADDR(qm, HPRE_RDCHN_INI_CFG));
+	ret = readl_relaxed_poll_timeout(HPRE_ADDR(qm, HPRE_RDCHN_INI_ST), val,
+			val & BIT(0),
+			HPRE_REG_RD_INTVRL_US,
+			HPRE_REG_RD_TMOUT_US);
+	if (ret) {
+		dev_err(dev, "read rd channel timeout fail!\n");
+		return -ETIMEDOUT;
+	}
+
+	for (i = 0; i < HPRE_CLUSTERS_NUM; i++) {
+		offset = i * HPRE_CLSTR_ADDR_INTRVL;
+
+		/* clusters initiating */
+		writel(HPRE_CLUSTER_CORE_MASK,
+		       HPRE_ADDR(qm, offset + HPRE_CORE_ENB));
+		writel(0x1, HPRE_ADDR(qm, offset + HPRE_CORE_INI_CFG));
+		ret = readl_relaxed_poll_timeout(HPRE_ADDR(qm, offset +
+					HPRE_CORE_INI_STATUS), val,
+					((val & HPRE_CLUSTER_CORE_MASK) ==
+					HPRE_CLUSTER_CORE_MASK),
+					HPRE_REG_RD_INTVRL_US,
+					HPRE_REG_RD_TMOUT_US);
+		if (ret) {
+			dev_err(dev,
+				"cluster %d int st status timeout!\n", i);
+			return -ETIMEDOUT;
+		}
+	}
+
+	ret = hpre_cfg_by_dsm(qm);
+	if (ret)
+		dev_err(dev, "acpi_evaluate_dsm err.\n");
+
+	return ret;
+}
+
+static void hpre_cnt_regs_clear(struct hisi_qm *qm)
+{
+	unsigned long offset;
+	int i;
+
+	/* clear current_qm */
+	writel(0x0, qm->io_base + QM_DFX_MB_CNT_VF);
+	writel(0x0, qm->io_base + QM_DFX_DB_CNT_VF);
+
+	/* clear clusterX/cluster_ctrl */
+	for (i = 0; i < HPRE_CLUSTERS_NUM; i++) {
+		offset = HPRE_CLSTR_BASE + i * HPRE_CLSTR_ADDR_INTRVL;
+		writel(0x0, qm->io_base + offset + HPRE_CLUSTER_INQURY);
+	}
+
+	/* clear rdclr_en */
+	writel(0x0, qm->io_base + HPRE_CTRL_CNT_CLR_CE);
+
+	hisi_qm_debug_regs_clear(qm);
+}
+
+static void hpre_hw_error_disable(struct hpre *hpre)
+{
+	struct hisi_qm *qm = &hpre->qm;
+
+	/* disable hpre hw error interrupts */
+	writel(HPRE_CORE_INT_DISABLE, qm->io_base + HPRE_INT_MASK);
+}
+
+static void hpre_hw_error_enable(struct hpre *hpre)
+{
+	struct hisi_qm *qm = &hpre->qm;
+
+	/* enable hpre hw error interrupts */
+	writel(HPRE_CORE_INT_ENABLE, qm->io_base + HPRE_INT_MASK);
+	writel(HPRE_HAC_RAS_CE_ENABLE, qm->io_base + HPRE_RAS_CE_ENB);
+	writel(HPRE_HAC_RAS_NFE_ENABLE, qm->io_base + HPRE_RAS_NFE_ENB);
+	writel(HPRE_HAC_RAS_FE_ENABLE, qm->io_base + HPRE_RAS_FE_ENB);
+}
+
+static inline struct hisi_qm *hpre_file_to_qm(struct hpre_debugfs_file *file)
+{
+	struct hpre *hpre = container_of(file->debug, struct hpre, debug);
+
+	return &hpre->qm;
+}
+
+static u32 hpre_current_qm_read(struct hpre_debugfs_file *file)
+{
+	struct hisi_qm *qm = hpre_file_to_qm(file);
+
+	return readl(qm->io_base + QM_DFX_MB_CNT_VF);
+}
+
+static int hpre_current_qm_write(struct hpre_debugfs_file *file, u32 val)
+{
+	struct hisi_qm *qm = hpre_file_to_qm(file);
+	struct hpre_debug *debug = file->debug;
+	struct hpre *hpre = container_of(debug, struct hpre, debug);
+	u32 num_vfs = hpre->num_vfs;
+	u32 vfq_num, tmp;
+
+
+	if (val > num_vfs)
+		return -EINVAL;
+
+	/* According PF or VF Dev ID to calculation curr_qm_qp_num and store */
+	if (val == 0) {
+		qm->debug.curr_qm_qp_num = qm->qp_num;
+	} else {
+		vfq_num = (qm->ctrl_qp_num - qm->qp_num) / num_vfs;
+		if (val == num_vfs) {
+			qm->debug.curr_qm_qp_num =
+			qm->ctrl_qp_num - qm->qp_num - (num_vfs - 1) * vfq_num;
+		} else {
+			qm->debug.curr_qm_qp_num = vfq_num;
+		}
+	}
+
+	writel(val, qm->io_base + QM_DFX_MB_CNT_VF);
+	writel(val, qm->io_base + QM_DFX_DB_CNT_VF);
+
+	tmp = val |
+	      (readl(qm->io_base + QM_DFX_SQE_CNT_VF_SQN) & CURRENT_Q_MASK);
+	writel(tmp, qm->io_base + QM_DFX_SQE_CNT_VF_SQN);
+
+	tmp = val |
+	      (readl(qm->io_base + QM_DFX_CQE_CNT_VF_CQN) & CURRENT_Q_MASK);
+	writel(tmp, qm->io_base + QM_DFX_CQE_CNT_VF_CQN);
+
+	return  0;
+}
+
+static u32 hpre_clear_enable_read(struct hpre_debugfs_file *file)
+{
+	struct hisi_qm *qm = hpre_file_to_qm(file);
+
+	return readl(qm->io_base + HPRE_CTRL_CNT_CLR_CE) &
+	       HPRE_CTRL_CNT_CLR_CE_BIT;
+}
+
+static int hpre_clear_enable_write(struct hpre_debugfs_file *file, u32 val)
+{
+	struct hisi_qm *qm = hpre_file_to_qm(file);
+	u32 tmp;
+
+	if (val != 1 && val != 0)
+		return -EINVAL;
+
+	tmp = (readl(qm->io_base + HPRE_CTRL_CNT_CLR_CE) &
+	       ~HPRE_CTRL_CNT_CLR_CE_BIT) | val;
+	writel(tmp, qm->io_base + HPRE_CTRL_CNT_CLR_CE);
+
+	return  0;
+}
+
+static u32 hpre_cluster_inqry_read(struct hpre_debugfs_file *file)
+{
+	struct hisi_qm *qm = hpre_file_to_qm(file);
+	int cluster_index = file->index - HPRE_CLUSTER_CTRL;
+	unsigned long offset = HPRE_CLSTR_BASE +
+			       cluster_index * HPRE_CLSTR_ADDR_INTRVL;
+
+	return readl(qm->io_base + offset + HPRE_CLSTR_ADDR_INQRY_RSLT);
+}
+
+static int hpre_cluster_inqry_write(struct hpre_debugfs_file *file, u32 val)
+{
+	struct hisi_qm *qm = hpre_file_to_qm(file);
+	int cluster_index = file->index - HPRE_CLUSTER_CTRL;
+	unsigned long offset = HPRE_CLSTR_BASE + cluster_index *
+			       HPRE_CLSTR_ADDR_INTRVL;
+
+	writel(val, qm->io_base + offset + HPRE_CLUSTER_INQURY);
+
+	return  0;
+}
+
+static ssize_t hpre_ctrl_debug_read(struct file *filp, char __user *buf,
+			       size_t count, loff_t *pos)
+{
+	struct hpre_debugfs_file *file = filp->private_data;
+	char tbuf[HPRE_DBGFS_VAL_MAX_LEN];
+	u32 val;
+	int ret;
+
+	spin_lock_irq(&file->lock);
+	switch (file->type) {
+	case HPRE_CURRENT_QM:
+		val = hpre_current_qm_read(file);
+		break;
+	case HPRE_CLEAR_ENABLE:
+		val = hpre_clear_enable_read(file);
+		break;
+	case HPRE_CLUSTER_CTRL:
+		val = hpre_cluster_inqry_read(file);
+		break;
+	default:
+		spin_unlock_irq(&file->lock);
+		return -EINVAL;
+	}
+	spin_unlock_irq(&file->lock);
+	ret = sprintf(tbuf, "%u\n", val);
+	return simple_read_from_buffer(buf, count, pos, tbuf, ret);
+}
+
+static ssize_t hpre_ctrl_debug_write(struct file *filp, const char __user *buf,
+				size_t count, loff_t *pos)
+{
+	struct hpre_debugfs_file *file = filp->private_data;
+	char tbuf[HPRE_DBGFS_VAL_MAX_LEN];
+	unsigned long val;
+	int len, ret;
+
+	if (*pos != 0)
+		return 0;
+
+	if (count >= HPRE_DBGFS_VAL_MAX_LEN)
+		return -ENOSPC;
+
+	len = simple_write_to_buffer(tbuf, HPRE_DBGFS_VAL_MAX_LEN - 1,
+				     pos, buf, count);
+	if (len < 0)
+		return len;
+
+	tbuf[len] = '\0';
+	if (kstrtoul(tbuf, 0, &val))
+		return -EFAULT;
+
+	spin_lock_irq(&file->lock);
+	switch (file->type) {
+	case HPRE_CURRENT_QM:
+		ret = hpre_current_qm_write(file, val);
+		if (ret)
+			goto err_input;
+		break;
+	case HPRE_CLEAR_ENABLE:
+		ret = hpre_clear_enable_write(file, val);
+		if (ret)
+			goto err_input;
+		break;
+	case HPRE_CLUSTER_CTRL:
+		ret = hpre_cluster_inqry_write(file, val);
+		if (ret)
+			goto err_input;
+		break;
+	default:
+		ret = -EINVAL;
+		goto err_input;
+	}
+	spin_unlock_irq(&file->lock);
+
+	return count;
+
+err_input:
+	spin_unlock_irq(&file->lock);
+	return ret;
+}
+
+static const struct file_operations hpre_ctrl_debug_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read = hpre_ctrl_debug_read,
+	.write = hpre_ctrl_debug_write,
+};
+
+static int hpre_create_debugfs_file(struct hpre_debug *dbg, struct dentry *dir,
+				    enum hpre_ctrl_dbgfs_file type, int indx)
+{
+	struct dentry *tmp, *file_dir;
+
+	if (dir)
+		file_dir = dir;
+	else
+		file_dir = dbg->debug_root;
+
+	if (type >= HPRE_DEBUG_FILE_NUM)
+		return -EINVAL;
+
+	spin_lock_init(&dbg->files[indx].lock);
+	dbg->files[indx].debug = dbg;
+	dbg->files[indx].type = type;
+	dbg->files[indx].index = indx;
+	tmp = debugfs_create_file(hpre_debug_file_name[type], 0600, file_dir,
+				  dbg->files + indx, &hpre_ctrl_debug_fops);
+	if (!tmp)
+		return -ENOENT;
+
+	return 0;
+}
+
+static int hpre_pf_comm_regs_debugfs_init(struct hpre_debug *debug)
+{
+	struct hpre *hpre = container_of(debug, struct hpre, debug);
+	struct hisi_qm *qm = &hpre->qm;
+	struct device *dev = &qm->pdev->dev;
+	struct debugfs_regset32 *regset;
+	struct dentry *tmp;
+
+	regset = devm_kzalloc(dev, sizeof(*regset), GFP_KERNEL);
+	if (!regset)
+		return -ENOMEM;
+
+	regset->regs = hpre_com_dfx_regs;
+	regset->nregs = ARRAY_SIZE(hpre_com_dfx_regs);
+	regset->base = qm->io_base;
+
+	tmp = debugfs_create_regset32("regs", 0444,  debug->debug_root, regset);
+	if (!tmp)
+		return -ENOENT;
+
+	return 0;
+}
+
+static int hpre_cluster_debugfs_init(struct hpre_debug *debug)
+{
+	struct hpre *hpre = container_of(debug, struct hpre, debug);
+	struct hisi_qm *qm = &hpre->qm;
+	struct device *dev = &qm->pdev->dev;
+	char buf[HPRE_DBGFS_VAL_MAX_LEN];
+	struct debugfs_regset32 *regset;
+	struct dentry *tmp_d, *tmp;
+	int i, ret;
+
+	for (i = 0; i < HPRE_CLUSTERS_NUM; i++) {
+		sprintf(buf, "cluster%d", i);
+
+		tmp_d = debugfs_create_dir(buf, debug->debug_root);
+		if (!tmp_d)
+			return -ENOENT;
+
+		regset = devm_kzalloc(dev, sizeof(*regset), GFP_KERNEL);
+		if (!regset)
+			return -ENOMEM;
+
+		regset->regs = hpre_cluster_dfx_regs;
+		regset->nregs = ARRAY_SIZE(hpre_cluster_dfx_regs);
+		regset->base = qm->io_base + hpre_cluster_offsets[i];
+
+		tmp = debugfs_create_regset32("regs", 0444, tmp_d, regset);
+		if (!tmp)
+			return -ENOENT;
+		ret = hpre_create_debugfs_file(debug, tmp_d, HPRE_CLUSTER_CTRL,
+					       i + HPRE_CLUSTER_CTRL);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int hpre_ctrl_debug_init(struct hpre_debug *debug)
+{
+	int ret;
+
+	ret = hpre_create_debugfs_file(debug, NULL, HPRE_CURRENT_QM,
+				       HPRE_CURRENT_QM);
+	if (ret)
+		return ret;
+
+	ret = hpre_create_debugfs_file(debug, NULL, HPRE_CLEAR_ENABLE,
+				       HPRE_CLEAR_ENABLE);
+	if (ret)
+		return ret;
+
+	ret = hpre_pf_comm_regs_debugfs_init(debug);
+	if (ret)
+		return ret;
+
+	return hpre_cluster_debugfs_init(debug);
+}
+
+static int hpre_debugfs_init(struct hpre *hpre)
+{
+	struct hisi_qm *qm = &hpre->qm;
+	struct device *dev = &qm->pdev->dev;
+	struct dentry *dir;
+	int ret;
+
+	dir = debugfs_create_dir(dev_name(dev), hpre_debugfs_root);
+	if (!dir)
+		return -ENOENT;
+
+	qm->debug.debug_root = dir;
+
+	ret = hisi_qm_debug_init(qm);
+	if (ret)
+		goto failed_to_create;
+
+	if (qm->pdev->device == HPRE_PCI_DEVICE_ID) {
+		hpre->debug.debug_root = dir;
+		ret = hpre_ctrl_debug_init(&hpre->debug);
+		if (ret)
+			goto failed_to_create;
+	}
+	return 0;
+
+failed_to_create:
+	debugfs_remove_recursive(qm->debug.debug_root);
+	return ret;
+}
+
+static void hpre_debugfs_exit(struct hpre *hpre)
+{
+	struct hisi_qm *qm = &hpre->qm;
+
+	debugfs_remove_recursive(qm->debug.debug_root);
+}
+
+static int hpre_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev)
+{
+	enum qm_hw_ver rev_id;
+
+	rev_id = hisi_qm_get_hw_version(pdev);
+	if (rev_id < 0)
+		return -ENODEV;
+
+	if (rev_id == QM_HW_V1) {
+		pci_warn(pdev, "HPRE version 1 is not supported!\n");
+		return -EINVAL;
+	}
+
+	qm->pdev = pdev;
+	qm->ver = rev_id;
+	qm->sqe_size = HPRE_SQE_SIZE;
+	qm->dev_name = hpre_name;
+	qm->fun_type = (pdev->device == HPRE_PCI_DEVICE_ID) ?
+		       QM_HW_PF : QM_HW_VF;
+	if (pdev->is_physfn) {
+		qm->qp_base = HPRE_PF_DEF_Q_BASE;
+		qm->qp_num = hpre_pf_q_num;
+	}
+	qm->use_dma_api = true;
+
+	return 0;
+}
+
+static void hpre_hw_err_init(struct hpre *hpre)
+{
+	hisi_qm_hw_error_init(&hpre->qm, QM_BASE_CE, QM_BASE_NFE,
+			      0, QM_DB_RANDOM_INVALID);
+	hpre_hw_error_enable(hpre);
+}
+
+static int hpre_pf_probe_init(struct hpre *hpre)
+{
+	struct hisi_qm *qm = &hpre->qm;
+	int ret;
+
+	qm->ctrl_qp_num = HPRE_QUEUE_NUM_V2;
+
+	ret = hpre_set_user_domain_and_cache(hpre);
+	if (ret)
+		return ret;
+
+	hpre_hw_err_init(hpre);
+
+	return 0;
+}
+
+static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct hisi_qm *qm;
+	struct hpre *hpre;
+	int ret;
+
+	hpre = devm_kzalloc(&pdev->dev, sizeof(*hpre), GFP_KERNEL);
+	if (!hpre)
+		return -ENOMEM;
+
+	pci_set_drvdata(pdev, hpre);
+
+	qm = &hpre->qm;
+	ret = hpre_qm_pre_init(qm, pdev);
+	if (ret)
+		return ret;
+
+	ret = hisi_qm_init(qm);
+	if (ret)
+		return ret;
+
+	if (pdev->is_physfn) {
+		ret = hpre_pf_probe_init(hpre);
+		if (ret)
+			goto err_with_qm_init;
+	} else if (qm->fun_type == QM_HW_VF && qm->ver == QM_HW_V2) {
+		/* v2 starts to support get vft by mailbox */
+		ret = hisi_qm_get_vft(qm, &qm->qp_base, &qm->qp_num);
+		if (ret)
+			goto err_with_qm_init;
+	}
+
+	ret = hisi_qm_start(qm);
+	if (ret)
+		goto err_with_err_init;
+
+	ret = hpre_debugfs_init(hpre);
+	if (ret)
+		dev_warn(&pdev->dev, "init debugfs fail!\n");
+
+	hpre_add_to_list(hpre);
+
+	ret = hpre_algs_register();
+	if (ret < 0) {
+		hpre_remove_from_list(hpre);
+		pci_err(pdev, "fail to register algs to crypto!\n");
+		goto err_with_qm_start;
+	}
+	return 0;
+
+err_with_qm_start:
+	hisi_qm_stop(qm);
+
+err_with_err_init:
+	if (pdev->is_physfn)
+		hpre_hw_error_disable(hpre);
+
+err_with_qm_init:
+	hisi_qm_uninit(qm);
+
+	return ret;
+}
+
+static int hpre_vf_q_assign(struct hpre *hpre, int num_vfs)
+{
+	struct hisi_qm *qm = &hpre->qm;
+	u32 qp_num = qm->qp_num;
+	int q_num, remain_q_num, i;
+	u32 q_base = qp_num;
+	int ret;
+
+	if (!num_vfs)
+		return -EINVAL;
+
+	remain_q_num = qm->ctrl_qp_num - qp_num;
+
+	/* If remaining queues are not enough, return error. */
+	if (remain_q_num < num_vfs)
+		return -EINVAL;
+
+	q_num = remain_q_num / num_vfs;
+	for (i = 1; i <= num_vfs; i++) {
+		if (i == num_vfs)
+			q_num += remain_q_num % num_vfs;
+		ret = hisi_qm_set_vft(qm, i, q_base, (u32)q_num);
+		if (ret)
+			return ret;
+		q_base += q_num;
+	}
+
+	return 0;
+}
+
+static int hpre_clear_vft_config(struct hpre *hpre)
+{
+	struct hisi_qm *qm = &hpre->qm;
+	u32 num_vfs = hpre->num_vfs;
+	int ret;
+	u32 i;
+
+	for (i = 1; i <= num_vfs; i++) {
+		ret = hisi_qm_set_vft(qm, i, 0, 0);
+		if (ret)
+			return ret;
+	}
+	hpre->num_vfs = 0;
+
+	return 0;
+}
+
+static int hpre_sriov_enable(struct pci_dev *pdev, int max_vfs)
+{
+	struct hpre *hpre = pci_get_drvdata(pdev);
+	int pre_existing_vfs, num_vfs, ret;
+
+	pre_existing_vfs = pci_num_vf(pdev);
+	if (pre_existing_vfs) {
+		pci_err(pdev,
+			"Can't enable VF. Please disable pre-enabled VFs!\n");
+		return 0;
+	}
+
+	num_vfs = min_t(int, max_vfs, HPRE_VF_NUM);
+	ret = hpre_vf_q_assign(hpre, num_vfs);
+	if (ret) {
+		pci_err(pdev, "Can't assign queues for VF!\n");
+		return ret;
+	}
+
+	hpre->num_vfs = num_vfs;
+
+	ret = pci_enable_sriov(pdev, num_vfs);
+	if (ret) {
+		pci_err(pdev, "Can't enable VF!\n");
+		hpre_clear_vft_config(hpre);
+		return ret;
+	}
+
+	return num_vfs;
+}
+
+static int hpre_sriov_disable(struct pci_dev *pdev)
+{
+	struct hpre *hpre = pci_get_drvdata(pdev);
+
+	if (pci_vfs_assigned(pdev)) {
+		pci_err(pdev, "Failed to disable VFs while VFs are assigned!\n");
+		return -EPERM;
+	}
+
+	/* remove in hpre_pci_driver will be called to free VF resources */
+	pci_disable_sriov(pdev);
+
+	return hpre_clear_vft_config(hpre);
+}
+
+static int hpre_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+	if (num_vfs)
+		return hpre_sriov_enable(pdev, num_vfs);
+	else
+		return hpre_sriov_disable(pdev);
+}
+
+static void hpre_remove(struct pci_dev *pdev)
+{
+	struct hpre *hpre = pci_get_drvdata(pdev);
+	struct hisi_qm *qm = &hpre->qm;
+	int ret;
+
+	hpre_algs_unregister();
+	hpre_remove_from_list(hpre);
+	if (qm->fun_type == QM_HW_PF && hpre->num_vfs != 0) {
+		ret = hpre_sriov_disable(pdev);
+		if (ret) {
+			pci_err(pdev, "Disable SRIOV fail!\n");
+			return;
+		}
+	}
+	if (qm->fun_type == QM_HW_PF) {
+		hpre_cnt_regs_clear(qm);
+		qm->debug.curr_qm_qp_num = 0;
+	}
+
+	hpre_debugfs_exit(hpre);
+	hisi_qm_stop(qm);
+	if (qm->fun_type == QM_HW_PF)
+		hpre_hw_error_disable(hpre);
+	hisi_qm_uninit(qm);
+}
+
+static void hpre_log_hw_error(struct hpre *hpre, u32 err_sts)
+{
+	const struct hpre_hw_error *err = hpre_hw_errors;
+	struct device *dev = &hpre->qm.pdev->dev;
+
+	while (err->msg) {
+		if (err->int_msk & err_sts)
+			dev_warn(dev, "%s [error status=0x%x] found\n",
+				 err->msg, err->int_msk);
+		err++;
+	}
+}
+
+static pci_ers_result_t hpre_hw_error_handle(struct hpre *hpre)
+{
+	u32 err_sts;
+
+	/* read err sts */
+	err_sts = readl(hpre->qm.io_base + HPRE_HAC_INT_STATUS);
+	if (err_sts) {
+		hpre_log_hw_error(hpre, err_sts);
+
+		/* clear error interrupts */
+		writel(err_sts, hpre->qm.io_base + HPRE_HAC_SOURCE_INT);
+		return PCI_ERS_RESULT_NEED_RESET;
+	}
+
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
+static pci_ers_result_t hpre_process_hw_error(struct pci_dev *pdev)
+{
+	struct hpre *hpre = pci_get_drvdata(pdev);
+	pci_ers_result_t qm_ret, hpre_ret;
+
+	/* log qm error */
+	qm_ret = hisi_qm_hw_error_handle(&hpre->qm);
+
+	/* log hpre error */
+	hpre_ret = hpre_hw_error_handle(hpre);
+
+	return (qm_ret == PCI_ERS_RESULT_NEED_RESET ||
+		hpre_ret == PCI_ERS_RESULT_NEED_RESET) ?
+		PCI_ERS_RESULT_NEED_RESET : PCI_ERS_RESULT_RECOVERED;
+}
+
+static pci_ers_result_t hpre_error_detected(struct pci_dev *pdev,
+					    pci_channel_state_t state)
+{
+	pci_info(pdev, "PCI error detected, state(=%d)!!\n", state);
+	if (state == pci_channel_io_perm_failure)
+		return PCI_ERS_RESULT_DISCONNECT;
+
+	return hpre_process_hw_error(pdev);
+}
+
+static const struct pci_error_handlers hpre_err_handler = {
+	.error_detected		= hpre_error_detected,
+};
+
+static struct pci_driver hpre_pci_driver = {
+	.name			= hpre_name,
+	.id_table		= hpre_dev_ids,
+	.probe			= hpre_probe,
+	.remove			= hpre_remove,
+	.sriov_configure	= hpre_sriov_configure,
+	.err_handler		= &hpre_err_handler,
+};
+
+static void hpre_register_debugfs(void)
+{
+	if (!debugfs_initialized())
+		return;
+
+	hpre_debugfs_root = debugfs_create_dir(hpre_name, NULL);
+	if (IS_ERR_OR_NULL(hpre_debugfs_root))
+		hpre_debugfs_root = NULL;
+}
+
+static void hpre_unregister_debugfs(void)
+{
+	debugfs_remove_recursive(hpre_debugfs_root);
+}
+
+static int __init hpre_init(void)
+{
+	int ret;
+
+	hpre_register_debugfs();
+
+	ret = pci_register_driver(&hpre_pci_driver);
+	if (ret) {
+		hpre_unregister_debugfs();
+		pr_err("hpre: can't register hisi hpre driver.\n");
+	}
+
+	return ret;
+}
+
+static void __exit hpre_exit(void)
+{
+	pci_unregister_driver(&hpre_pci_driver);
+	hpre_unregister_debugfs();
+}
+
+module_init(hpre_init);
+module_exit(hpre_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Zaibo Xu <xuzaibo@huawei.com>");
+MODULE_DESCRIPTION("Driver for HiSilicon HPRE accelerator");
diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
index f975c393a603..b57da5ef8b5b 100644
--- a/drivers/crypto/hisilicon/qm.c
+++ b/drivers/crypto/hisilicon/qm.c
@@ -59,17 +59,17 @@
 #define QM_CQ_PHASE_SHIFT		0
 #define QM_CQ_FLAG_SHIFT		1
 
-#define QM_CQE_PHASE(cqe)		((cqe)->w7 & 0x1)
+#define QM_CQE_PHASE(cqe)		(le16_to_cpu((cqe)->w7) & 0x1)
 #define QM_QC_CQE_SIZE			4
 
 /* eqc shift */
 #define QM_EQE_AEQE_SIZE		(2UL << 12)
 #define QM_EQC_PHASE_SHIFT		16
 
-#define QM_EQE_PHASE(eqe)		(((eqe)->dw0 >> 16) & 0x1)
+#define QM_EQE_PHASE(eqe)		((le32_to_cpu((eqe)->dw0) >> 16) & 0x1)
 #define QM_EQE_CQN_MASK			GENMASK(15, 0)
 
-#define QM_AEQE_PHASE(aeqe)		(((aeqe)->dw0 >> 16) & 0x1)
+#define QM_AEQE_PHASE(aeqe)		((le32_to_cpu((aeqe)->dw0) >> 16) & 0x1)
 #define QM_AEQE_TYPE_SHIFT		17
 
 #define QM_DOORBELL_CMD_SQ		0
@@ -169,17 +169,17 @@
 #define QM_MK_SQC_DW3_V2(sqe_sz) \
 	((QM_Q_DEPTH - 1) | ((u32)ilog2(sqe_sz) << QM_SQ_SQE_SIZE_SHIFT))
 
-#define INIT_QC_COMMON(qc, base, pasid) do {	\
-	(qc)->head = 0;				\
-	(qc)->tail = 0;				\
-	(qc)->base_l = lower_32_bits(base);	\
-	(qc)->base_h = upper_32_bits(base);	\
-	(qc)->dw3 = 0;				\
-	(qc)->w8 = 0;				\
-	(qc)->rsvd0 = 0;			\
-	(qc)->pasid = pasid;			\
-	(qc)->w11 = 0;				\
-	(qc)->rsvd1 = 0;			\
+#define INIT_QC_COMMON(qc, base, pasid) do {			\
+	(qc)->head = 0;						\
+	(qc)->tail = 0;						\
+	(qc)->base_l = cpu_to_le32(lower_32_bits(base));	\
+	(qc)->base_h = cpu_to_le32(upper_32_bits(base));	\
+	(qc)->dw3 = 0;						\
+	(qc)->w8 = 0;						\
+	(qc)->rsvd0 = 0;					\
+	(qc)->pasid = cpu_to_le16(pasid);			\
+	(qc)->w11 = 0;						\
+	(qc)->rsvd1 = 0;					\
 } while (0)
 
 enum vft_type {
@@ -331,12 +331,18 @@ static void qm_mb_write(struct hisi_qm *qm, const void *src)
 	void __iomem *fun_base = qm->io_base + QM_MB_CMD_SEND_BASE;
 	unsigned long tmp0 = 0, tmp1 = 0;
 
+	if (!IS_ENABLED(CONFIG_ARM64)) {
+		memcpy_toio(fun_base, src, 16);
+		wmb();
+		return;
+	}
+
 	asm volatile("ldp %0, %1, %3\n"
 		     "stp %0, %1, %2\n"
 		     "dsb sy\n"
 		     : "=&r" (tmp0),
 		       "=&r" (tmp1),
-		       "+Q" (*((char *)fun_base))
+		       "+Q" (*((char __iomem *)fun_base))
 		     : "Q" (*((char *)src))
 		     : "memory");
 }
@@ -350,12 +356,12 @@ static int qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue,
 	dev_dbg(&qm->pdev->dev, "QM mailbox request to q%u: %u-%llx\n",
 		queue, cmd, (unsigned long long)dma_addr);
 
-	mailbox.w0 = cmd |
+	mailbox.w0 = cpu_to_le16(cmd |
 		     (op ? 0x1 << QM_MB_OP_SHIFT : 0) |
-		     (0x1 << QM_MB_BUSY_SHIFT);
-	mailbox.queue_num = queue;
-	mailbox.base_l = lower_32_bits(dma_addr);
-	mailbox.base_h = upper_32_bits(dma_addr);
+		     (0x1 << QM_MB_BUSY_SHIFT));
+	mailbox.queue_num = cpu_to_le16(queue);
+	mailbox.base_l = cpu_to_le32(lower_32_bits(dma_addr));
+	mailbox.base_h = cpu_to_le32(upper_32_bits(dma_addr));
 	mailbox.rsvd = 0;
 
 	mutex_lock(&qm->mailbox_lock);
@@ -442,7 +448,7 @@ static u32 qm_get_irq_num_v2(struct hisi_qm *qm)
 
 static struct hisi_qp *qm_to_hisi_qp(struct hisi_qm *qm, struct qm_eqe *eqe)
 {
-	u16 cqn = eqe->dw0 & QM_EQE_CQN_MASK;
+	u16 cqn = le32_to_cpu(eqe->dw0) & QM_EQE_CQN_MASK;
 
 	return qm->qp_array[cqn];
 }
@@ -464,7 +470,8 @@ static void qm_poll_qp(struct hisi_qp *qp, struct hisi_qm *qm)
 	if (qp->req_cb) {
 		while (QM_CQE_PHASE(cqe) == qp->qp_status.cqc_phase) {
 			dma_rmb();
-			qp->req_cb(qp, qp->sqe + qm->sqe_size * cqe->sq_head);
+			qp->req_cb(qp, qp->sqe + qm->sqe_size *
+				   le16_to_cpu(cqe->sq_head));
 			qm_cq_head_update(qp);
 			cqe = qp->cqe + qp->qp_status.cq_head;
 			qm_db(qm, qp->qp_id, QM_DOORBELL_CMD_CQ,
@@ -542,7 +549,7 @@ static irqreturn_t qm_aeq_irq(int irq, void *data)
 		return IRQ_NONE;
 
 	while (QM_AEQE_PHASE(aeqe) == qm->status.aeqc_phase) {
-		type = aeqe->dw0 >> QM_AEQE_TYPE_SHIFT;
+		type = le32_to_cpu(aeqe->dw0) >> QM_AEQE_TYPE_SHIFT;
 		if (type < ARRAY_SIZE(qm_fifo_overflow))
 			dev_err(&qm->pdev->dev, "%s overflow\n",
 				qm_fifo_overflow[type]);
@@ -646,7 +653,7 @@ static void qm_init_qp_status(struct hisi_qp *qp)
 
 	qp_status->sq_tail = 0;
 	qp_status->cq_head = 0;
-	qp_status->cqc_phase = 1;
+	qp_status->cqc_phase = true;
 	qp_status->flags = 0;
 }
 
@@ -963,13 +970,11 @@ static const struct file_operations qm_regs_fops = {
 
 static int qm_create_debugfs_file(struct hisi_qm *qm, enum qm_debug_file index)
 {
-	struct dentry *qm_d = qm->debug.qm_d, *tmp;
+	struct dentry *qm_d = qm->debug.qm_d;
 	struct debugfs_file *file = qm->debug.files + index;
 
-	tmp = debugfs_create_file(qm_debug_file_name[index], 0600, qm_d, file,
-				  &qm_debug_fops);
-	if (IS_ERR(tmp))
-		return -ENOENT;
+	debugfs_create_file(qm_debug_file_name[index], 0600, qm_d, file,
+			    &qm_debug_fops);
 
 	file->index = index;
 	mutex_init(&file->lock);
@@ -981,9 +986,6 @@ static int qm_create_debugfs_file(struct hisi_qm *qm, enum qm_debug_file index)
 static void qm_hw_error_init_v1(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe,
 				u32 msi)
 {
-	dev_info(&qm->pdev->dev,
-		 "QM v%d does not support hw error handle\n", qm->ver);
-
 	writel(QM_ABNORMAL_INT_MASK_VALUE, qm->io_base + QM_ABNORMAL_INT_MASK);
 }
 
@@ -1123,6 +1125,7 @@ struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type)
 	}
 	set_bit(qp_id, qm->qp_bitmap);
 	qm->qp_array[qp_id] = qp;
+	qm->qp_in_used++;
 
 	write_unlock(&qm->qps_lock);
 
@@ -1187,6 +1190,7 @@ void hisi_qm_release_qp(struct hisi_qp *qp)
 	write_lock(&qm->qps_lock);
 	qm->qp_array[qp->qp_id] = NULL;
 	clear_bit(qp->qp_id, qm->qp_bitmap);
+	qm->qp_in_used--;
 	write_unlock(&qm->qps_lock);
 
 	kfree(qp);
@@ -1218,14 +1222,14 @@ static int qm_qp_ctx_cfg(struct hisi_qp *qp, int qp_id, int pasid)
 
 	INIT_QC_COMMON(sqc, qp->sqe_dma, pasid);
 	if (ver == QM_HW_V1) {
-		sqc->dw3 = QM_MK_SQC_DW3_V1(0, 0, 0, qm->sqe_size);
-		sqc->w8 = QM_Q_DEPTH - 1;
+		sqc->dw3 = cpu_to_le32(QM_MK_SQC_DW3_V1(0, 0, 0, qm->sqe_size));
+		sqc->w8 = cpu_to_le16(QM_Q_DEPTH - 1);
 	} else if (ver == QM_HW_V2) {
-		sqc->dw3 = QM_MK_SQC_DW3_V2(qm->sqe_size);
+		sqc->dw3 = cpu_to_le32(QM_MK_SQC_DW3_V2(qm->sqe_size));
 		sqc->w8 = 0; /* rand_qc */
 	}
-	sqc->cq_num = qp_id;
-	sqc->w13 = QM_MK_SQC_W13(0, 1, qp->alg_type);
+	sqc->cq_num = cpu_to_le16(qp_id);
+	sqc->w13 = cpu_to_le16(QM_MK_SQC_W13(0, 1, qp->alg_type));
 
 	ret = qm_mb(qm, QM_MB_CMD_SQC, sqc_dma, qp_id, 0);
 	dma_unmap_single(dev, sqc_dma, sizeof(struct qm_sqc), DMA_TO_DEVICE);
@@ -1245,13 +1249,13 @@ static int qm_qp_ctx_cfg(struct hisi_qp *qp, int qp_id, int pasid)
 
 	INIT_QC_COMMON(cqc, qp->cqe_dma, pasid);
 	if (ver == QM_HW_V1) {
-		cqc->dw3 = QM_MK_CQC_DW3_V1(0, 0, 0, 4);
-		cqc->w8 = QM_Q_DEPTH - 1;
+		cqc->dw3 = cpu_to_le32(QM_MK_CQC_DW3_V1(0, 0, 0, 4));
+		cqc->w8 = cpu_to_le16(QM_Q_DEPTH - 1);
 	} else if (ver == QM_HW_V2) {
-		cqc->dw3 = QM_MK_CQC_DW3_V2(4);
+		cqc->dw3 = cpu_to_le32(QM_MK_CQC_DW3_V2(4));
 		cqc->w8 = 0;
 	}
-	cqc->dw6 = 1 << QM_CQ_PHASE_SHIFT | 1 << QM_CQ_FLAG_SHIFT;
+	cqc->dw6 = cpu_to_le32(1 << QM_CQ_PHASE_SHIFT | 1 << QM_CQ_FLAG_SHIFT);
 
 	ret = qm_mb(qm, QM_MB_CMD_CQC, cqc_dma, qp_id, 0);
 	dma_unmap_single(dev, cqc_dma, sizeof(struct qm_cqc), DMA_TO_DEVICE);
@@ -1392,6 +1396,24 @@ static void hisi_qm_cache_wb(struct hisi_qm *qm)
 }
 
 /**
+ * hisi_qm_get_free_qp_num() - Get free number of qp in qm.
+ * @qm: The qm which want to get free qp.
+ *
+ * This function return free number of qp in qm.
+ */
+int hisi_qm_get_free_qp_num(struct hisi_qm *qm)
+{
+	int ret;
+
+	read_lock(&qm->qps_lock);
+	ret = qm->qp_num - qm->qp_in_used;
+	read_unlock(&qm->qps_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hisi_qm_get_free_qp_num);
+
+/**
  * hisi_qm_init() - Initialize configures about qm.
  * @qm: The qm needing init.
  *
@@ -1454,6 +1476,7 @@ int hisi_qm_init(struct hisi_qm *qm)
 	if (ret)
 		goto err_free_irq_vectors;
 
+	qm->qp_in_used = 0;
 	mutex_init(&qm->mailbox_lock);
 	rwlock_init(&qm->qps_lock);
 
@@ -1560,8 +1583,8 @@ static void qm_init_eq_aeq_status(struct hisi_qm *qm)
 
 	status->eq_head = 0;
 	status->aeq_head = 0;
-	status->eqc_phase = 1;
-	status->aeqc_phase = 1;
+	status->eqc_phase = true;
+	status->aeqc_phase = true;
 }
 
 static int qm_eq_ctx_cfg(struct hisi_qm *qm)
@@ -1585,11 +1608,11 @@ static int qm_eq_ctx_cfg(struct hisi_qm *qm)
 		return -ENOMEM;
 	}
 
-	eqc->base_l = lower_32_bits(qm->eqe_dma);
-	eqc->base_h = upper_32_bits(qm->eqe_dma);
+	eqc->base_l = cpu_to_le32(lower_32_bits(qm->eqe_dma));
+	eqc->base_h = cpu_to_le32(upper_32_bits(qm->eqe_dma));
 	if (qm->ver == QM_HW_V1)
-		eqc->dw3 = QM_EQE_AEQE_SIZE;
-	eqc->dw6 = (QM_Q_DEPTH - 1) | (1 << QM_EQC_PHASE_SHIFT);
+		eqc->dw3 = cpu_to_le32(QM_EQE_AEQE_SIZE);
+	eqc->dw6 = cpu_to_le32((QM_Q_DEPTH - 1) | (1 << QM_EQC_PHASE_SHIFT));
 	ret = qm_mb(qm, QM_MB_CMD_EQC, eqc_dma, 0, 0);
 	dma_unmap_single(dev, eqc_dma, sizeof(struct qm_eqc), DMA_TO_DEVICE);
 	kfree(eqc);
@@ -1606,9 +1629,9 @@ static int qm_eq_ctx_cfg(struct hisi_qm *qm)
 		return -ENOMEM;
 	}
 
-	aeqc->base_l = lower_32_bits(qm->aeqe_dma);
-	aeqc->base_h = upper_32_bits(qm->aeqe_dma);
-	aeqc->dw6 = (QM_Q_DEPTH - 1) | (1 << QM_EQC_PHASE_SHIFT);
+	aeqc->base_l = cpu_to_le32(lower_32_bits(qm->aeqe_dma));
+	aeqc->base_h = cpu_to_le32(upper_32_bits(qm->aeqe_dma));
+	aeqc->dw6 = cpu_to_le32((QM_Q_DEPTH - 1) | (1 << QM_EQC_PHASE_SHIFT));
 
 	ret = qm_mb(qm, QM_MB_CMD_AEQC, aeqc_dma, 0, 0);
 	dma_unmap_single(dev, aeqc_dma, sizeof(struct qm_aeqc), DMA_TO_DEVICE);
@@ -1780,12 +1803,10 @@ EXPORT_SYMBOL_GPL(hisi_qm_stop);
  */
 int hisi_qm_debug_init(struct hisi_qm *qm)
 {
-	struct dentry *qm_d, *qm_regs;
+	struct dentry *qm_d;
 	int i, ret;
 
 	qm_d = debugfs_create_dir("qm", qm->debug.debug_root);
-	if (IS_ERR(qm_d))
-		return -ENOENT;
 	qm->debug.qm_d = qm_d;
 
 	/* only show this in PF */
@@ -1796,12 +1817,7 @@ int hisi_qm_debug_init(struct hisi_qm *qm)
 				goto failed_to_create;
 			}
 
-	qm_regs = debugfs_create_file("qm_regs", 0444, qm->debug.qm_d, qm,
-				      &qm_regs_fops);
-	if (IS_ERR(qm_regs)) {
-		ret = -ENOENT;
-		goto failed_to_create;
-	}
+	debugfs_create_file("qm_regs", 0444, qm->debug.qm_d, qm, &qm_regs_fops);
 
 	return 0;
 
@@ -1862,8 +1878,7 @@ void hisi_qm_hw_error_init(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe,
 			   u32 msi)
 {
 	if (!qm->ops->hw_error_init) {
-		dev_err(&qm->pdev->dev, "QM version %d doesn't support hw error handling!\n",
-			qm->ver);
+		dev_err(&qm->pdev->dev, "QM doesn't support hw error handling!\n");
 		return;
 	}
 
@@ -1877,11 +1892,10 @@ EXPORT_SYMBOL_GPL(hisi_qm_hw_error_init);
  *
  * Accelerators use this function to handle qm non-fatal hardware errors.
  */
-int hisi_qm_hw_error_handle(struct hisi_qm *qm)
+pci_ers_result_t hisi_qm_hw_error_handle(struct hisi_qm *qm)
 {
 	if (!qm->ops->hw_error_handle) {
-		dev_err(&qm->pdev->dev, "QM version %d doesn't support hw error report!\n",
-			qm->ver);
+		dev_err(&qm->pdev->dev, "QM doesn't support hw error report!\n");
 		return PCI_ERS_RESULT_NONE;
 	}
 
diff --git a/drivers/crypto/hisilicon/qm.h b/drivers/crypto/hisilicon/qm.h
index 70e672ae86bf..078b8f1f1b77 100644
--- a/drivers/crypto/hisilicon/qm.h
+++ b/drivers/crypto/hisilicon/qm.h
@@ -75,6 +75,8 @@
 
 #define QM_Q_DEPTH			1024
 
+#define HISI_ACC_SGL_SGE_NR_MAX		255
+
 enum qp_state {
 	QP_STOP,
 };
@@ -132,6 +134,7 @@ struct hisi_qm {
 	u32 sqe_size;
 	u32 qp_base;
 	u32 qp_num;
+	u32 qp_in_used;
 	u32 ctrl_qp_num;
 
 	struct qm_dma qdma;
@@ -204,12 +207,24 @@ int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg);
 int hisi_qm_stop_qp(struct hisi_qp *qp);
 void hisi_qm_release_qp(struct hisi_qp *qp);
 int hisi_qp_send(struct hisi_qp *qp, const void *msg);
+int hisi_qm_get_free_qp_num(struct hisi_qm *qm);
 int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number);
 int hisi_qm_set_vft(struct hisi_qm *qm, u32 fun_num, u32 base, u32 number);
 int hisi_qm_debug_init(struct hisi_qm *qm);
 void hisi_qm_hw_error_init(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe,
 			   u32 msi);
-int hisi_qm_hw_error_handle(struct hisi_qm *qm);
+pci_ers_result_t hisi_qm_hw_error_handle(struct hisi_qm *qm);
 enum qm_hw_ver hisi_qm_get_hw_version(struct pci_dev *pdev);
 void hisi_qm_debug_regs_clear(struct hisi_qm *qm);
+
+struct hisi_acc_sgl_pool;
+struct hisi_acc_hw_sgl *hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev,
+	struct scatterlist *sgl, struct hisi_acc_sgl_pool *pool,
+	u32 index, dma_addr_t *hw_sgl_dma);
+void hisi_acc_sg_buf_unmap(struct device *dev, struct scatterlist *sgl,
+			   struct hisi_acc_hw_sgl *hw_sgl);
+struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev,
+						   u32 count, u32 sge_nr);
+void hisi_acc_free_sgl_pool(struct device *dev,
+			    struct hisi_acc_sgl_pool *pool);
 #endif
diff --git a/drivers/crypto/hisilicon/sec2/Makefile b/drivers/crypto/hisilicon/sec2/Makefile
new file mode 100644
index 000000000000..b4f6cf14be3a
--- /dev/null
+++ b/drivers/crypto/hisilicon/sec2/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_CRYPTO_DEV_HISI_SEC2) += hisi_sec2.o
+hisi_sec2-objs = sec_main.o sec_crypto.o
diff --git a/drivers/crypto/hisilicon/sec2/sec.h b/drivers/crypto/hisilicon/sec2/sec.h
new file mode 100644
index 000000000000..26754d0570ba
--- /dev/null
+++ b/drivers/crypto/hisilicon/sec2/sec.h
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 HiSilicon Limited. */
+
+#ifndef __HISI_SEC_V2_H
+#define __HISI_SEC_V2_H
+
+#include <linux/list.h>
+
+#include "../qm.h"
+#include "sec_crypto.h"
+
+/* Cipher resource per hardware SEC queue */
+struct sec_cipher_res {
+	u8 *c_ivin;
+	dma_addr_t c_ivin_dma;
+};
+
+/* Cipher request of SEC private */
+struct sec_cipher_req {
+	struct hisi_acc_hw_sgl *c_in;
+	dma_addr_t c_in_dma;
+	struct hisi_acc_hw_sgl *c_out;
+	dma_addr_t c_out_dma;
+	u8 *c_ivin;
+	dma_addr_t c_ivin_dma;
+	struct skcipher_request *sk_req;
+	u32 c_len;
+	bool encrypt;
+};
+
+/* SEC request of Crypto */
+struct sec_req {
+	struct sec_sqe sec_sqe;
+	struct sec_ctx *ctx;
+	struct sec_qp_ctx *qp_ctx;
+
+	/* Cipher supported only at present */
+	struct sec_cipher_req c_req;
+	int err_type;
+	int req_id;
+
+	/* Status of the SEC request */
+	int fake_busy;
+};
+
+/**
+ * struct sec_req_op - Operations for SEC request
+ * @get_res: Get resources for TFM on the SEC device
+ * @resource_alloc: Allocate resources for queue context on the SEC device
+ * @resource_free: Free resources for queue context on the SEC device
+ * @buf_map: DMA map the SGL buffers of the request
+ * @buf_unmap: DMA unmap the SGL buffers of the request
+ * @bd_fill: Fill the SEC queue BD
+ * @bd_send: Send the SEC BD into the hardware queue
+ * @callback: Call back for the request
+ * @process: Main processing logic of Skcipher
+ */
+struct sec_req_op {
+	int (*get_res)(struct sec_ctx *ctx, struct sec_req *req);
+	int (*resource_alloc)(struct sec_ctx *ctx, struct sec_qp_ctx *qp_ctx);
+	void (*resource_free)(struct sec_ctx *ctx, struct sec_qp_ctx *qp_ctx);
+	int (*buf_map)(struct sec_ctx *ctx, struct sec_req *req);
+	void (*buf_unmap)(struct sec_ctx *ctx, struct sec_req *req);
+	void (*do_transfer)(struct sec_ctx *ctx, struct sec_req *req);
+	int (*bd_fill)(struct sec_ctx *ctx, struct sec_req *req);
+	int (*bd_send)(struct sec_ctx *ctx, struct sec_req *req);
+	void (*callback)(struct sec_ctx *ctx, struct sec_req *req);
+	int (*process)(struct sec_ctx *ctx, struct sec_req *req);
+};
+
+/* SEC cipher context which cipher's relatives */
+struct sec_cipher_ctx {
+	u8 *c_key;
+	dma_addr_t c_key_dma;
+	sector_t iv_offset;
+	u32 c_gran_size;
+	u32 ivsize;
+	u8 c_mode;
+	u8 c_alg;
+	u8 c_key_len;
+};
+
+/* SEC queue context which defines queue's relatives */
+struct sec_qp_ctx {
+	struct hisi_qp *qp;
+	struct sec_req **req_list;
+	struct idr req_idr;
+	void *alg_meta_data;
+	struct sec_ctx *ctx;
+	struct mutex req_lock;
+	struct hisi_acc_sgl_pool *c_in_pool;
+	struct hisi_acc_sgl_pool *c_out_pool;
+	atomic_t pending_reqs;
+};
+
+/* SEC Crypto TFM context which defines queue and cipher .etc relatives */
+struct sec_ctx {
+	struct sec_qp_ctx *qp_ctx;
+	struct sec_dev *sec;
+	const struct sec_req_op *req_op;
+
+	/* Half queues for encipher, and half for decipher */
+	u32 hlf_q_num;
+
+	/* Threshold for fake busy, trigger to return -EBUSY to user */
+	u32 fake_req_limit;
+
+	/* Currrent cyclic index to select a queue for encipher */
+	atomic_t enc_qcyclic;
+
+	 /* Currrent cyclic index to select a queue for decipher */
+	atomic_t dec_qcyclic;
+	struct sec_cipher_ctx c_ctx;
+};
+
+enum sec_endian {
+	SEC_LE = 0,
+	SEC_32BE,
+	SEC_64BE
+};
+
+enum sec_debug_file_index {
+	SEC_CURRENT_QM,
+	SEC_CLEAR_ENABLE,
+	SEC_DEBUG_FILE_NUM,
+};
+
+struct sec_debug_file {
+	enum sec_debug_file_index index;
+	spinlock_t lock;
+	struct hisi_qm *qm;
+};
+
+struct sec_dfx {
+	u64 send_cnt;
+	u64 recv_cnt;
+};
+
+struct sec_debug {
+	struct sec_dfx dfx;
+	struct sec_debug_file files[SEC_DEBUG_FILE_NUM];
+};
+
+struct sec_dev {
+	struct hisi_qm qm;
+	struct list_head list;
+	struct sec_debug debug;
+	u32 ctx_q_num;
+	u32 num_vfs;
+	unsigned long status;
+};
+
+struct sec_dev *sec_find_device(int node);
+int sec_register_to_crypto(void);
+void sec_unregister_from_crypto(void);
+#endif
diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c
new file mode 100644
index 000000000000..dc1eb97d57f7
--- /dev/null
+++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c
@@ -0,0 +1,889 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 HiSilicon Limited. */
+
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/des.h>
+#include <crypto/skcipher.h>
+#include <crypto/xts.h>
+#include <linux/crypto.h>
+#include <linux/dma-mapping.h>
+#include <linux/idr.h>
+
+#include "sec.h"
+#include "sec_crypto.h"
+
+#define SEC_PRIORITY		4001
+#define SEC_XTS_MIN_KEY_SIZE	(2 * AES_MIN_KEY_SIZE)
+#define SEC_XTS_MAX_KEY_SIZE	(2 * AES_MAX_KEY_SIZE)
+#define SEC_DES3_2KEY_SIZE	(2 * DES_KEY_SIZE)
+#define SEC_DES3_3KEY_SIZE	(3 * DES_KEY_SIZE)
+
+/* SEC sqe(bd) bit operational relative MACRO */
+#define SEC_DE_OFFSET		1
+#define SEC_CIPHER_OFFSET	4
+#define SEC_SCENE_OFFSET	3
+#define SEC_DST_SGL_OFFSET	2
+#define SEC_SRC_SGL_OFFSET	7
+#define SEC_CKEY_OFFSET		9
+#define SEC_CMODE_OFFSET	12
+#define SEC_FLAG_OFFSET		7
+#define SEC_FLAG_MASK		0x0780
+#define SEC_TYPE_MASK		0x0F
+#define SEC_DONE_MASK		0x0001
+
+#define SEC_TOTAL_IV_SZ		(SEC_IV_SIZE * QM_Q_DEPTH)
+#define SEC_SGL_SGE_NR		128
+#define SEC_CTX_DEV(ctx)	(&(ctx)->sec->qm.pdev->dev)
+
+static DEFINE_MUTEX(sec_algs_lock);
+static unsigned int sec_active_devs;
+
+/* Get an en/de-cipher queue cyclically to balance load over queues of TFM */
+static inline int sec_get_queue_id(struct sec_ctx *ctx, struct sec_req *req)
+{
+	if (req->c_req.encrypt)
+		return (u32)atomic_inc_return(&ctx->enc_qcyclic) %
+				 ctx->hlf_q_num;
+
+	return (u32)atomic_inc_return(&ctx->dec_qcyclic) % ctx->hlf_q_num +
+				 ctx->hlf_q_num;
+}
+
+static inline void sec_put_queue_id(struct sec_ctx *ctx, struct sec_req *req)
+{
+	if (req->c_req.encrypt)
+		atomic_dec(&ctx->enc_qcyclic);
+	else
+		atomic_dec(&ctx->dec_qcyclic);
+}
+
+static int sec_alloc_req_id(struct sec_req *req, struct sec_qp_ctx *qp_ctx)
+{
+	int req_id;
+
+	mutex_lock(&qp_ctx->req_lock);
+
+	req_id = idr_alloc_cyclic(&qp_ctx->req_idr, NULL,
+				  0, QM_Q_DEPTH, GFP_ATOMIC);
+	mutex_unlock(&qp_ctx->req_lock);
+	if (req_id < 0) {
+		dev_err(SEC_CTX_DEV(req->ctx), "alloc req id fail!\n");
+		return req_id;
+	}
+
+	req->qp_ctx = qp_ctx;
+	qp_ctx->req_list[req_id] = req;
+	return req_id;
+}
+
+static void sec_free_req_id(struct sec_req *req)
+{
+	struct sec_qp_ctx *qp_ctx = req->qp_ctx;
+	int req_id = req->req_id;
+
+	if (req_id < 0 || req_id >= QM_Q_DEPTH) {
+		dev_err(SEC_CTX_DEV(req->ctx), "free request id invalid!\n");
+		return;
+	}
+
+	qp_ctx->req_list[req_id] = NULL;
+	req->qp_ctx = NULL;
+
+	mutex_lock(&qp_ctx->req_lock);
+	idr_remove(&qp_ctx->req_idr, req_id);
+	mutex_unlock(&qp_ctx->req_lock);
+}
+
+static void sec_req_cb(struct hisi_qp *qp, void *resp)
+{
+	struct sec_qp_ctx *qp_ctx = qp->qp_ctx;
+	struct sec_sqe *bd = resp;
+	u16 done, flag;
+	u8 type;
+	struct sec_req *req;
+
+	type = bd->type_cipher_auth & SEC_TYPE_MASK;
+	if (type == SEC_BD_TYPE2) {
+		req = qp_ctx->req_list[le16_to_cpu(bd->type2.tag)];
+		req->err_type = bd->type2.error_type;
+
+		done = le16_to_cpu(bd->type2.done_flag) & SEC_DONE_MASK;
+		flag = (le16_to_cpu(bd->type2.done_flag) &
+				   SEC_FLAG_MASK) >> SEC_FLAG_OFFSET;
+		if (req->err_type || done != 0x1 || flag != 0x2)
+			dev_err(SEC_CTX_DEV(req->ctx),
+				"err_type[%d],done[%d],flag[%d]\n",
+				req->err_type, done, flag);
+	} else {
+		pr_err("err bd type [%d]\n", type);
+		return;
+	}
+
+	__sync_add_and_fetch(&req->ctx->sec->debug.dfx.recv_cnt, 1);
+
+	req->ctx->req_op->buf_unmap(req->ctx, req);
+
+	req->ctx->req_op->callback(req->ctx, req);
+}
+
+static int sec_bd_send(struct sec_ctx *ctx, struct sec_req *req)
+{
+	struct sec_qp_ctx *qp_ctx = req->qp_ctx;
+	int ret;
+
+	mutex_lock(&qp_ctx->req_lock);
+	ret = hisi_qp_send(qp_ctx->qp, &req->sec_sqe);
+	mutex_unlock(&qp_ctx->req_lock);
+	__sync_add_and_fetch(&ctx->sec->debug.dfx.send_cnt, 1);
+
+	if (ret == -EBUSY)
+		return -ENOBUFS;
+
+	if (!ret) {
+		if (req->fake_busy)
+			ret = -EBUSY;
+		else
+			ret = -EINPROGRESS;
+	}
+
+	return ret;
+}
+
+static int sec_create_qp_ctx(struct hisi_qm *qm, struct sec_ctx *ctx,
+			     int qp_ctx_id, int alg_type)
+{
+	struct device *dev = SEC_CTX_DEV(ctx);
+	struct sec_qp_ctx *qp_ctx;
+	struct hisi_qp *qp;
+	int ret = -ENOMEM;
+
+	qp = hisi_qm_create_qp(qm, alg_type);
+	if (IS_ERR(qp))
+		return PTR_ERR(qp);
+
+	qp_ctx = &ctx->qp_ctx[qp_ctx_id];
+	qp->req_type = 0;
+	qp->qp_ctx = qp_ctx;
+	qp->req_cb = sec_req_cb;
+	qp_ctx->qp = qp;
+	qp_ctx->ctx = ctx;
+
+	mutex_init(&qp_ctx->req_lock);
+	atomic_set(&qp_ctx->pending_reqs, 0);
+	idr_init(&qp_ctx->req_idr);
+
+	qp_ctx->req_list = kcalloc(QM_Q_DEPTH, sizeof(void *), GFP_ATOMIC);
+	if (!qp_ctx->req_list)
+		goto err_destroy_idr;
+
+	qp_ctx->c_in_pool = hisi_acc_create_sgl_pool(dev, QM_Q_DEPTH,
+						     SEC_SGL_SGE_NR);
+	if (!qp_ctx->c_in_pool) {
+		dev_err(dev, "fail to create sgl pool for input!\n");
+		goto err_free_req_list;
+	}
+
+	qp_ctx->c_out_pool = hisi_acc_create_sgl_pool(dev, QM_Q_DEPTH,
+						      SEC_SGL_SGE_NR);
+	if (!qp_ctx->c_out_pool) {
+		dev_err(dev, "fail to create sgl pool for output!\n");
+		goto err_free_c_in_pool;
+	}
+
+	ret = ctx->req_op->resource_alloc(ctx, qp_ctx);
+	if (ret)
+		goto err_free_c_out_pool;
+
+	ret = hisi_qm_start_qp(qp, 0);
+	if (ret < 0)
+		goto err_queue_free;
+
+	return 0;
+
+err_queue_free:
+	ctx->req_op->resource_free(ctx, qp_ctx);
+err_free_c_out_pool:
+	hisi_acc_free_sgl_pool(dev, qp_ctx->c_out_pool);
+err_free_c_in_pool:
+	hisi_acc_free_sgl_pool(dev, qp_ctx->c_in_pool);
+err_free_req_list:
+	kfree(qp_ctx->req_list);
+err_destroy_idr:
+	idr_destroy(&qp_ctx->req_idr);
+	hisi_qm_release_qp(qp);
+
+	return ret;
+}
+
+static void sec_release_qp_ctx(struct sec_ctx *ctx,
+			       struct sec_qp_ctx *qp_ctx)
+{
+	struct device *dev = SEC_CTX_DEV(ctx);
+
+	hisi_qm_stop_qp(qp_ctx->qp);
+	ctx->req_op->resource_free(ctx, qp_ctx);
+
+	hisi_acc_free_sgl_pool(dev, qp_ctx->c_out_pool);
+	hisi_acc_free_sgl_pool(dev, qp_ctx->c_in_pool);
+
+	idr_destroy(&qp_ctx->req_idr);
+	kfree(qp_ctx->req_list);
+	hisi_qm_release_qp(qp_ctx->qp);
+}
+
+static int sec_skcipher_init(struct crypto_skcipher *tfm)
+{
+	struct sec_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct sec_cipher_ctx *c_ctx;
+	struct sec_dev *sec;
+	struct device *dev;
+	struct hisi_qm *qm;
+	int i, ret;
+
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct sec_req));
+
+	sec = sec_find_device(cpu_to_node(smp_processor_id()));
+	if (!sec) {
+		pr_err("find no Hisilicon SEC device!\n");
+		return -ENODEV;
+	}
+	ctx->sec = sec;
+	qm = &sec->qm;
+	dev = &qm->pdev->dev;
+	ctx->hlf_q_num = sec->ctx_q_num >> 0x1;
+
+	/* Half of queue depth is taken as fake requests limit in the queue. */
+	ctx->fake_req_limit = QM_Q_DEPTH >> 0x1;
+	ctx->qp_ctx = kcalloc(sec->ctx_q_num, sizeof(struct sec_qp_ctx),
+			      GFP_KERNEL);
+	if (!ctx->qp_ctx)
+		return -ENOMEM;
+
+	for (i = 0; i < sec->ctx_q_num; i++) {
+		ret = sec_create_qp_ctx(qm, ctx, i, 0);
+		if (ret)
+			goto err_sec_release_qp_ctx;
+	}
+
+	c_ctx = &ctx->c_ctx;
+	c_ctx->ivsize = crypto_skcipher_ivsize(tfm);
+	if (c_ctx->ivsize > SEC_IV_SIZE) {
+		dev_err(dev, "get error iv size!\n");
+		ret = -EINVAL;
+		goto err_sec_release_qp_ctx;
+	}
+	c_ctx->c_key = dma_alloc_coherent(dev, SEC_MAX_KEY_SIZE,
+					  &c_ctx->c_key_dma, GFP_KERNEL);
+	if (!c_ctx->c_key) {
+		ret = -ENOMEM;
+		goto err_sec_release_qp_ctx;
+	}
+
+	return 0;
+
+err_sec_release_qp_ctx:
+	for (i = i - 1; i >= 0; i--)
+		sec_release_qp_ctx(ctx, &ctx->qp_ctx[i]);
+
+	kfree(ctx->qp_ctx);
+	return ret;
+}
+
+static void sec_skcipher_exit(struct crypto_skcipher *tfm)
+{
+	struct sec_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct sec_cipher_ctx *c_ctx = &ctx->c_ctx;
+	int i = 0;
+
+	if (c_ctx->c_key) {
+		dma_free_coherent(SEC_CTX_DEV(ctx), SEC_MAX_KEY_SIZE,
+				  c_ctx->c_key, c_ctx->c_key_dma);
+		c_ctx->c_key = NULL;
+	}
+
+	for (i = 0; i < ctx->sec->ctx_q_num; i++)
+		sec_release_qp_ctx(ctx, &ctx->qp_ctx[i]);
+
+	kfree(ctx->qp_ctx);
+}
+
+static int sec_skcipher_3des_setkey(struct sec_cipher_ctx *c_ctx,
+				    const u32 keylen,
+				    const enum sec_cmode c_mode)
+{
+	switch (keylen) {
+	case SEC_DES3_2KEY_SIZE:
+		c_ctx->c_key_len = SEC_CKEY_3DES_2KEY;
+		break;
+	case SEC_DES3_3KEY_SIZE:
+		c_ctx->c_key_len = SEC_CKEY_3DES_3KEY;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int sec_skcipher_aes_sm4_setkey(struct sec_cipher_ctx *c_ctx,
+				       const u32 keylen,
+				       const enum sec_cmode c_mode)
+{
+	if (c_mode == SEC_CMODE_XTS) {
+		switch (keylen) {
+		case SEC_XTS_MIN_KEY_SIZE:
+			c_ctx->c_key_len = SEC_CKEY_128BIT;
+			break;
+		case SEC_XTS_MAX_KEY_SIZE:
+			c_ctx->c_key_len = SEC_CKEY_256BIT;
+			break;
+		default:
+			pr_err("hisi_sec2: xts mode key error!\n");
+			return -EINVAL;
+		}
+	} else {
+		switch (keylen) {
+		case AES_KEYSIZE_128:
+			c_ctx->c_key_len = SEC_CKEY_128BIT;
+			break;
+		case AES_KEYSIZE_192:
+			c_ctx->c_key_len = SEC_CKEY_192BIT;
+			break;
+		case AES_KEYSIZE_256:
+			c_ctx->c_key_len = SEC_CKEY_256BIT;
+			break;
+		default:
+			pr_err("hisi_sec2: aes key error!\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int sec_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			       const u32 keylen, const enum sec_calg c_alg,
+			       const enum sec_cmode c_mode)
+{
+	struct sec_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct sec_cipher_ctx *c_ctx = &ctx->c_ctx;
+	int ret;
+
+	if (c_mode == SEC_CMODE_XTS) {
+		ret = xts_verify_key(tfm, key, keylen);
+		if (ret) {
+			dev_err(SEC_CTX_DEV(ctx), "xts mode key err!\n");
+			return ret;
+		}
+	}
+
+	c_ctx->c_alg  = c_alg;
+	c_ctx->c_mode = c_mode;
+
+	switch (c_alg) {
+	case SEC_CALG_3DES:
+		ret = sec_skcipher_3des_setkey(c_ctx, keylen, c_mode);
+		break;
+	case SEC_CALG_AES:
+	case SEC_CALG_SM4:
+		ret = sec_skcipher_aes_sm4_setkey(c_ctx, keylen, c_mode);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (ret) {
+		dev_err(SEC_CTX_DEV(ctx), "set sec key err!\n");
+		return ret;
+	}
+
+	memcpy(c_ctx->c_key, key, keylen);
+
+	return 0;
+}
+
+#define GEN_SEC_SETKEY_FUNC(name, c_alg, c_mode)			\
+static int sec_setkey_##name(struct crypto_skcipher *tfm, const u8 *key,\
+	u32 keylen)							\
+{									\
+	return sec_skcipher_setkey(tfm, key, keylen, c_alg, c_mode);	\
+}
+
+GEN_SEC_SETKEY_FUNC(aes_ecb, SEC_CALG_AES, SEC_CMODE_ECB)
+GEN_SEC_SETKEY_FUNC(aes_cbc, SEC_CALG_AES, SEC_CMODE_CBC)
+GEN_SEC_SETKEY_FUNC(aes_xts, SEC_CALG_AES, SEC_CMODE_XTS)
+
+GEN_SEC_SETKEY_FUNC(3des_ecb, SEC_CALG_3DES, SEC_CMODE_ECB)
+GEN_SEC_SETKEY_FUNC(3des_cbc, SEC_CALG_3DES, SEC_CMODE_CBC)
+
+GEN_SEC_SETKEY_FUNC(sm4_xts, SEC_CALG_SM4, SEC_CMODE_XTS)
+GEN_SEC_SETKEY_FUNC(sm4_cbc, SEC_CALG_SM4, SEC_CMODE_CBC)
+
+static int sec_skcipher_get_res(struct sec_ctx *ctx,
+				struct sec_req *req)
+{
+	struct sec_qp_ctx *qp_ctx = req->qp_ctx;
+	struct sec_cipher_res *c_res = qp_ctx->alg_meta_data;
+	struct sec_cipher_req *c_req = &req->c_req;
+	int req_id = req->req_id;
+
+	c_req->c_ivin = c_res[req_id].c_ivin;
+	c_req->c_ivin_dma = c_res[req_id].c_ivin_dma;
+
+	return 0;
+}
+
+static int sec_skcipher_resource_alloc(struct sec_ctx *ctx,
+				       struct sec_qp_ctx *qp_ctx)
+{
+	struct device *dev = SEC_CTX_DEV(ctx);
+	struct sec_cipher_res *res;
+	int i;
+
+	res = kcalloc(QM_Q_DEPTH, sizeof(struct sec_cipher_res), GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
+
+	res->c_ivin = dma_alloc_coherent(dev, SEC_TOTAL_IV_SZ,
+					   &res->c_ivin_dma, GFP_KERNEL);
+	if (!res->c_ivin) {
+		kfree(res);
+		return -ENOMEM;
+	}
+
+	for (i = 1; i < QM_Q_DEPTH; i++) {
+		res[i].c_ivin_dma = res->c_ivin_dma + i * SEC_IV_SIZE;
+		res[i].c_ivin = res->c_ivin + i * SEC_IV_SIZE;
+	}
+	qp_ctx->alg_meta_data = res;
+
+	return 0;
+}
+
+static void sec_skcipher_resource_free(struct sec_ctx *ctx,
+				      struct sec_qp_ctx *qp_ctx)
+{
+	struct sec_cipher_res *res = qp_ctx->alg_meta_data;
+	struct device *dev = SEC_CTX_DEV(ctx);
+
+	if (!res)
+		return;
+
+	dma_free_coherent(dev, SEC_TOTAL_IV_SZ, res->c_ivin, res->c_ivin_dma);
+	kfree(res);
+}
+
+static int sec_skcipher_map(struct device *dev, struct sec_req *req,
+			    struct scatterlist *src, struct scatterlist *dst)
+{
+	struct sec_cipher_req *c_req = &req->c_req;
+	struct sec_qp_ctx *qp_ctx = req->qp_ctx;
+
+	c_req->c_in = hisi_acc_sg_buf_map_to_hw_sgl(dev, src,
+						    qp_ctx->c_in_pool,
+						    req->req_id,
+						    &c_req->c_in_dma);
+
+	if (IS_ERR(c_req->c_in)) {
+		dev_err(dev, "fail to dma map input sgl buffers!\n");
+		return PTR_ERR(c_req->c_in);
+	}
+
+	if (dst == src) {
+		c_req->c_out = c_req->c_in;
+		c_req->c_out_dma = c_req->c_in_dma;
+	} else {
+		c_req->c_out = hisi_acc_sg_buf_map_to_hw_sgl(dev, dst,
+							     qp_ctx->c_out_pool,
+							     req->req_id,
+							     &c_req->c_out_dma);
+
+		if (IS_ERR(c_req->c_out)) {
+			dev_err(dev, "fail to dma map output sgl buffers!\n");
+			hisi_acc_sg_buf_unmap(dev, src, c_req->c_in);
+			return PTR_ERR(c_req->c_out);
+		}
+	}
+
+	return 0;
+}
+
+static int sec_skcipher_sgl_map(struct sec_ctx *ctx, struct sec_req *req)
+{
+	struct sec_cipher_req *c_req = &req->c_req;
+
+	return sec_skcipher_map(SEC_CTX_DEV(ctx), req,
+				c_req->sk_req->src, c_req->sk_req->dst);
+}
+
+static void sec_skcipher_sgl_unmap(struct sec_ctx *ctx, struct sec_req *req)
+{
+	struct device *dev = SEC_CTX_DEV(ctx);
+	struct sec_cipher_req *c_req = &req->c_req;
+	struct skcipher_request *sk_req = c_req->sk_req;
+
+	if (sk_req->dst != sk_req->src)
+		hisi_acc_sg_buf_unmap(dev, sk_req->src, c_req->c_in);
+
+	hisi_acc_sg_buf_unmap(dev, sk_req->dst, c_req->c_out);
+}
+
+static int sec_request_transfer(struct sec_ctx *ctx, struct sec_req *req)
+{
+	int ret;
+
+	ret = ctx->req_op->buf_map(ctx, req);
+	if (ret)
+		return ret;
+
+	ctx->req_op->do_transfer(ctx, req);
+
+	ret = ctx->req_op->bd_fill(ctx, req);
+	if (ret)
+		goto unmap_req_buf;
+
+	return ret;
+
+unmap_req_buf:
+	ctx->req_op->buf_unmap(ctx, req);
+
+	return ret;
+}
+
+static void sec_request_untransfer(struct sec_ctx *ctx, struct sec_req *req)
+{
+	ctx->req_op->buf_unmap(ctx, req);
+}
+
+static void sec_skcipher_copy_iv(struct sec_ctx *ctx, struct sec_req *req)
+{
+	struct skcipher_request *sk_req = req->c_req.sk_req;
+	struct sec_cipher_req *c_req = &req->c_req;
+
+	c_req->c_len = sk_req->cryptlen;
+	memcpy(c_req->c_ivin, sk_req->iv, ctx->c_ctx.ivsize);
+}
+
+static int sec_skcipher_bd_fill(struct sec_ctx *ctx, struct sec_req *req)
+{
+	struct sec_cipher_ctx *c_ctx = &ctx->c_ctx;
+	struct sec_cipher_req *c_req = &req->c_req;
+	struct sec_sqe *sec_sqe = &req->sec_sqe;
+	u8 de = 0;
+	u8 scene, sa_type, da_type;
+	u8 bd_type, cipher;
+
+	memset(sec_sqe, 0, sizeof(struct sec_sqe));
+
+	sec_sqe->type2.c_key_addr = cpu_to_le64(c_ctx->c_key_dma);
+	sec_sqe->type2.c_ivin_addr = cpu_to_le64(c_req->c_ivin_dma);
+	sec_sqe->type2.data_src_addr = cpu_to_le64(c_req->c_in_dma);
+	sec_sqe->type2.data_dst_addr = cpu_to_le64(c_req->c_out_dma);
+
+	sec_sqe->type2.icvw_kmode |= cpu_to_le16(((u16)c_ctx->c_mode) <<
+						SEC_CMODE_OFFSET);
+	sec_sqe->type2.c_alg = c_ctx->c_alg;
+	sec_sqe->type2.icvw_kmode |= cpu_to_le16(((u16)c_ctx->c_key_len) <<
+						SEC_CKEY_OFFSET);
+
+	bd_type = SEC_BD_TYPE2;
+	if (c_req->encrypt)
+		cipher = SEC_CIPHER_ENC << SEC_CIPHER_OFFSET;
+	else
+		cipher = SEC_CIPHER_DEC << SEC_CIPHER_OFFSET;
+	sec_sqe->type_cipher_auth = bd_type | cipher;
+
+	sa_type = SEC_SGL << SEC_SRC_SGL_OFFSET;
+	scene = SEC_COMM_SCENE << SEC_SCENE_OFFSET;
+	if (c_req->c_in_dma != c_req->c_out_dma)
+		de = 0x1 << SEC_DE_OFFSET;
+
+	sec_sqe->sds_sa_type = (de | scene | sa_type);
+
+	/* Just set DST address type */
+	da_type = SEC_SGL << SEC_DST_SGL_OFFSET;
+	sec_sqe->sdm_addr_type |= da_type;
+
+	sec_sqe->type2.clen_ivhlen |= cpu_to_le32(c_req->c_len);
+	sec_sqe->type2.tag = cpu_to_le16((u16)req->req_id);
+
+	return 0;
+}
+
+static void sec_update_iv(struct sec_req *req)
+{
+	struct skcipher_request *sk_req = req->c_req.sk_req;
+	u32 iv_size = req->ctx->c_ctx.ivsize;
+	struct scatterlist *sgl;
+	size_t sz;
+
+	if (req->c_req.encrypt)
+		sgl = sk_req->dst;
+	else
+		sgl = sk_req->src;
+
+	sz = sg_pcopy_to_buffer(sgl, sg_nents(sgl), sk_req->iv,
+				iv_size, sk_req->cryptlen - iv_size);
+	if (sz != iv_size)
+		dev_err(SEC_CTX_DEV(req->ctx), "copy output iv error!\n");
+}
+
+static void sec_skcipher_callback(struct sec_ctx *ctx, struct sec_req *req)
+{
+	struct skcipher_request *sk_req = req->c_req.sk_req;
+	struct sec_qp_ctx *qp_ctx = req->qp_ctx;
+
+	atomic_dec(&qp_ctx->pending_reqs);
+	sec_free_req_id(req);
+
+	/* IV output at encrypto of CBC mode */
+	if (ctx->c_ctx.c_mode == SEC_CMODE_CBC && req->c_req.encrypt)
+		sec_update_iv(req);
+
+	if (__sync_bool_compare_and_swap(&req->fake_busy, 1, 0))
+		sk_req->base.complete(&sk_req->base, -EINPROGRESS);
+
+	sk_req->base.complete(&sk_req->base, req->err_type);
+}
+
+static void sec_request_uninit(struct sec_ctx *ctx, struct sec_req *req)
+{
+	struct sec_qp_ctx *qp_ctx = req->qp_ctx;
+
+	atomic_dec(&qp_ctx->pending_reqs);
+	sec_free_req_id(req);
+	sec_put_queue_id(ctx, req);
+}
+
+static int sec_request_init(struct sec_ctx *ctx, struct sec_req *req)
+{
+	struct sec_qp_ctx *qp_ctx;
+	int issue_id, ret;
+
+	/* To load balance */
+	issue_id = sec_get_queue_id(ctx, req);
+	qp_ctx = &ctx->qp_ctx[issue_id];
+
+	req->req_id = sec_alloc_req_id(req, qp_ctx);
+	if (req->req_id < 0) {
+		sec_put_queue_id(ctx, req);
+		return req->req_id;
+	}
+
+	if (ctx->fake_req_limit <= atomic_inc_return(&qp_ctx->pending_reqs))
+		req->fake_busy = 1;
+	else
+		req->fake_busy = 0;
+
+	ret = ctx->req_op->get_res(ctx, req);
+	if (ret) {
+		atomic_dec(&qp_ctx->pending_reqs);
+		sec_request_uninit(ctx, req);
+		dev_err(SEC_CTX_DEV(ctx), "get resources failed!\n");
+	}
+
+	return ret;
+}
+
+static int sec_process(struct sec_ctx *ctx, struct sec_req *req)
+{
+	int ret;
+
+	ret = sec_request_init(ctx, req);
+	if (ret)
+		return ret;
+
+	ret = sec_request_transfer(ctx, req);
+	if (ret)
+		goto err_uninit_req;
+
+	/* Output IV as decrypto */
+	if (ctx->c_ctx.c_mode == SEC_CMODE_CBC && !req->c_req.encrypt)
+		sec_update_iv(req);
+
+	ret = ctx->req_op->bd_send(ctx, req);
+	if (ret != -EBUSY && ret != -EINPROGRESS) {
+		dev_err(SEC_CTX_DEV(ctx), "send sec request failed!\n");
+		goto err_send_req;
+	}
+
+	return ret;
+
+err_send_req:
+	/* As failing, restore the IV from user */
+	if (ctx->c_ctx.c_mode == SEC_CMODE_CBC && !req->c_req.encrypt)
+		memcpy(req->c_req.sk_req->iv, req->c_req.c_ivin,
+		       ctx->c_ctx.ivsize);
+
+	sec_request_untransfer(ctx, req);
+err_uninit_req:
+	sec_request_uninit(ctx, req);
+
+	return ret;
+}
+
+static struct sec_req_op sec_req_ops_tbl = {
+	.get_res	= sec_skcipher_get_res,
+	.resource_alloc	= sec_skcipher_resource_alloc,
+	.resource_free	= sec_skcipher_resource_free,
+	.buf_map	= sec_skcipher_sgl_map,
+	.buf_unmap	= sec_skcipher_sgl_unmap,
+	.do_transfer	= sec_skcipher_copy_iv,
+	.bd_fill	= sec_skcipher_bd_fill,
+	.bd_send	= sec_bd_send,
+	.callback	= sec_skcipher_callback,
+	.process	= sec_process,
+};
+
+static int sec_skcipher_ctx_init(struct crypto_skcipher *tfm)
+{
+	struct sec_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	ctx->req_op = &sec_req_ops_tbl;
+
+	return sec_skcipher_init(tfm);
+}
+
+static void sec_skcipher_ctx_exit(struct crypto_skcipher *tfm)
+{
+	sec_skcipher_exit(tfm);
+}
+
+static int sec_skcipher_param_check(struct sec_ctx *ctx,
+				    struct skcipher_request *sk_req)
+{
+	u8 c_alg = ctx->c_ctx.c_alg;
+	struct device *dev = SEC_CTX_DEV(ctx);
+
+	if (!sk_req->src || !sk_req->dst) {
+		dev_err(dev, "skcipher input param error!\n");
+		return -EINVAL;
+	}
+
+	if (c_alg == SEC_CALG_3DES) {
+		if (sk_req->cryptlen & (DES3_EDE_BLOCK_SIZE - 1)) {
+			dev_err(dev, "skcipher 3des input length error!\n");
+			return -EINVAL;
+		}
+		return 0;
+	} else if (c_alg == SEC_CALG_AES || c_alg == SEC_CALG_SM4) {
+		if (sk_req->cryptlen & (AES_BLOCK_SIZE - 1)) {
+			dev_err(dev, "skcipher aes input length error!\n");
+			return -EINVAL;
+		}
+		return 0;
+	}
+
+	dev_err(dev, "skcipher algorithm error!\n");
+	return -EINVAL;
+}
+
+static int sec_skcipher_crypto(struct skcipher_request *sk_req, bool encrypt)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(sk_req);
+	struct sec_req *req = skcipher_request_ctx(sk_req);
+	struct sec_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int ret;
+
+	if (!sk_req->cryptlen)
+		return 0;
+
+	ret = sec_skcipher_param_check(ctx, sk_req);
+	if (ret)
+		return ret;
+
+	req->c_req.sk_req = sk_req;
+	req->c_req.encrypt = encrypt;
+	req->ctx = ctx;
+
+	return ctx->req_op->process(ctx, req);
+}
+
+static int sec_skcipher_encrypt(struct skcipher_request *sk_req)
+{
+	return sec_skcipher_crypto(sk_req, true);
+}
+
+static int sec_skcipher_decrypt(struct skcipher_request *sk_req)
+{
+	return sec_skcipher_crypto(sk_req, false);
+}
+
+#define SEC_SKCIPHER_GEN_ALG(sec_cra_name, sec_set_key, sec_min_key_size, \
+	sec_max_key_size, ctx_init, ctx_exit, blk_size, iv_size)\
+{\
+	.base = {\
+		.cra_name = sec_cra_name,\
+		.cra_driver_name = "hisi_sec_"sec_cra_name,\
+		.cra_priority = SEC_PRIORITY,\
+		.cra_flags = CRYPTO_ALG_ASYNC,\
+		.cra_blocksize = blk_size,\
+		.cra_ctxsize = sizeof(struct sec_ctx),\
+		.cra_module = THIS_MODULE,\
+	},\
+	.init = ctx_init,\
+	.exit = ctx_exit,\
+	.setkey = sec_set_key,\
+	.decrypt = sec_skcipher_decrypt,\
+	.encrypt = sec_skcipher_encrypt,\
+	.min_keysize = sec_min_key_size,\
+	.max_keysize = sec_max_key_size,\
+	.ivsize = iv_size,\
+},
+
+#define SEC_SKCIPHER_ALG(name, key_func, min_key_size, \
+	max_key_size, blk_size, iv_size) \
+	SEC_SKCIPHER_GEN_ALG(name, key_func, min_key_size, max_key_size, \
+	sec_skcipher_ctx_init, sec_skcipher_ctx_exit, blk_size, iv_size)
+
+static struct skcipher_alg sec_algs[] = {
+	SEC_SKCIPHER_ALG("ecb(aes)", sec_setkey_aes_ecb,
+			 AES_MIN_KEY_SIZE, AES_MAX_KEY_SIZE,
+			 AES_BLOCK_SIZE, 0)
+
+	SEC_SKCIPHER_ALG("cbc(aes)", sec_setkey_aes_cbc,
+			 AES_MIN_KEY_SIZE, AES_MAX_KEY_SIZE,
+			 AES_BLOCK_SIZE, AES_BLOCK_SIZE)
+
+	SEC_SKCIPHER_ALG("xts(aes)", sec_setkey_aes_xts,
+			 SEC_XTS_MIN_KEY_SIZE, SEC_XTS_MAX_KEY_SIZE,
+			 AES_BLOCK_SIZE, AES_BLOCK_SIZE)
+
+	SEC_SKCIPHER_ALG("ecb(des3_ede)", sec_setkey_3des_ecb,
+			 SEC_DES3_2KEY_SIZE, SEC_DES3_3KEY_SIZE,
+			 DES3_EDE_BLOCK_SIZE, 0)
+
+	SEC_SKCIPHER_ALG("cbc(des3_ede)", sec_setkey_3des_cbc,
+			 SEC_DES3_2KEY_SIZE, SEC_DES3_3KEY_SIZE,
+			 DES3_EDE_BLOCK_SIZE, DES3_EDE_BLOCK_SIZE)
+
+	SEC_SKCIPHER_ALG("xts(sm4)", sec_setkey_sm4_xts,
+			 SEC_XTS_MIN_KEY_SIZE, SEC_XTS_MIN_KEY_SIZE,
+			 AES_BLOCK_SIZE, AES_BLOCK_SIZE)
+
+	SEC_SKCIPHER_ALG("cbc(sm4)", sec_setkey_sm4_cbc,
+			 AES_MIN_KEY_SIZE, AES_MIN_KEY_SIZE,
+			 AES_BLOCK_SIZE, AES_BLOCK_SIZE)
+};
+
+int sec_register_to_crypto(void)
+{
+	int ret = 0;
+
+	/* To avoid repeat register */
+	mutex_lock(&sec_algs_lock);
+	if (++sec_active_devs == 1)
+		ret = crypto_register_skciphers(sec_algs, ARRAY_SIZE(sec_algs));
+	mutex_unlock(&sec_algs_lock);
+
+	return ret;
+}
+
+void sec_unregister_from_crypto(void)
+{
+	mutex_lock(&sec_algs_lock);
+	if (--sec_active_devs == 0)
+		crypto_unregister_skciphers(sec_algs, ARRAY_SIZE(sec_algs));
+	mutex_unlock(&sec_algs_lock);
+}
diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.h b/drivers/crypto/hisilicon/sec2/sec_crypto.h
new file mode 100644
index 000000000000..097dce828340
--- /dev/null
+++ b/drivers/crypto/hisilicon/sec2/sec_crypto.h
@@ -0,0 +1,198 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 HiSilicon Limited. */
+
+#ifndef __HISI_SEC_V2_CRYPTO_H
+#define __HISI_SEC_V2_CRYPTO_H
+
+#define SEC_IV_SIZE		24
+#define SEC_MAX_KEY_SIZE	64
+#define SEC_COMM_SCENE		0
+
+enum sec_calg {
+	SEC_CALG_3DES = 0x1,
+	SEC_CALG_AES  = 0x2,
+	SEC_CALG_SM4  = 0x3,
+};
+
+enum sec_cmode {
+	SEC_CMODE_ECB    = 0x0,
+	SEC_CMODE_CBC    = 0x1,
+	SEC_CMODE_CTR    = 0x4,
+	SEC_CMODE_XTS    = 0x7,
+};
+
+enum sec_ckey_type {
+	SEC_CKEY_128BIT = 0x0,
+	SEC_CKEY_192BIT = 0x1,
+	SEC_CKEY_256BIT = 0x2,
+	SEC_CKEY_3DES_3KEY = 0x1,
+	SEC_CKEY_3DES_2KEY = 0x3,
+};
+
+enum sec_bd_type {
+	SEC_BD_TYPE1 = 0x1,
+	SEC_BD_TYPE2 = 0x2,
+};
+
+enum sec_cipher_dir {
+	SEC_CIPHER_ENC = 0x1,
+	SEC_CIPHER_DEC = 0x2,
+};
+
+enum sec_addr_type {
+	SEC_PBUF = 0x0,
+	SEC_SGL  = 0x1,
+	SEC_PRP  = 0x2,
+};
+
+struct sec_sqe_type2 {
+
+	/*
+	 * mac_len: 0~5 bits
+	 * a_key_len: 6~10 bits
+	 * a_alg: 11~16 bits
+	 */
+	__le32 mac_key_alg;
+
+	/*
+	 * c_icv_len: 0~5 bits
+	 * c_width: 6~8 bits
+	 * c_key_len: 9~11 bits
+	 * c_mode: 12~15 bits
+	 */
+	__le16 icvw_kmode;
+
+	/* c_alg: 0~3 bits */
+	__u8 c_alg;
+	__u8 rsvd4;
+
+	/*
+	 * a_len: 0~23 bits
+	 * iv_offset_l: 24~31 bits
+	 */
+	__le32 alen_ivllen;
+
+	/*
+	 * c_len: 0~23 bits
+	 * iv_offset_h: 24~31 bits
+	 */
+	__le32 clen_ivhlen;
+
+	__le16 auth_src_offset;
+	__le16 cipher_src_offset;
+	__le16 cs_ip_header_offset;
+	__le16 cs_udp_header_offset;
+	__le16 pass_word_len;
+	__le16 dk_len;
+	__u8 salt3;
+	__u8 salt2;
+	__u8 salt1;
+	__u8 salt0;
+
+	__le16 tag;
+	__le16 rsvd5;
+
+	/*
+	 * c_pad_type: 0~3 bits
+	 * c_pad_len: 4~11 bits
+	 * c_pad_data_type: 12~15 bits
+	 */
+	__le16 cph_pad;
+
+	/* c_pad_len_field: 0~1 bits */
+	__le16 c_pad_len_field;
+
+
+	__le64 long_a_data_len;
+	__le64 a_ivin_addr;
+	__le64 a_key_addr;
+	__le64 mac_addr;
+	__le64 c_ivin_addr;
+	__le64 c_key_addr;
+
+	__le64 data_src_addr;
+	__le64 data_dst_addr;
+
+	/*
+	 * done: 0 bit
+	 * icv: 1~3 bits
+	 * csc: 4~6 bits
+	 * flag: 7-10 bits
+	 * dif_check: 11~13 bits
+	 */
+	__le16 done_flag;
+
+	__u8 error_type;
+	__u8 warning_type;
+	__u8 mac_i3;
+	__u8 mac_i2;
+	__u8 mac_i1;
+	__u8 mac_i0;
+	__le16 check_sum_i;
+	__u8 tls_pad_len_i;
+	__u8 rsvd12;
+	__le32 counter;
+};
+
+struct sec_sqe {
+	/*
+	 * type:	0~3 bits
+	 * cipher:	4~5 bits
+	 * auth:	6~7 bit s
+	 */
+	__u8 type_cipher_auth;
+
+	/*
+	 * seq:	0 bit
+	 * de:	1~2 bits
+	 * scene:	3~6 bits
+	 * src_addr_type: ~7 bit, with sdm_addr_type 0-1 bits
+	 */
+	__u8 sds_sa_type;
+
+	/*
+	 * src_addr_type: 0~1 bits, not used now,
+	 * if support PRP, set this field, or set zero.
+	 * dst_addr_type: 2~4 bits
+	 * mac_addr_type: 5~7 bits
+	 */
+	__u8 sdm_addr_type;
+	__u8 rsvd0;
+
+	/*
+	 * nonce_len(type2): 0~3 bits
+	 * huk(type2): 4 bit
+	 * key_s(type2): 5 bit
+	 * ci_gen: 6~7 bits
+	 */
+	__u8 huk_key_ci;
+
+	/*
+	 * ai_gen: 0~1 bits
+	 * a_pad(type2): 2~3 bits
+	 * c_s(type2): 4~5 bits
+	 */
+	__u8 ai_apd_cs;
+
+	/*
+	 * rhf(type2): 0 bit
+	 * c_key_type: 1~2 bits
+	 * a_key_type: 3~4 bits
+	 * write_frame_len(type2): 5~7 bits
+	 */
+	__u8 rca_key_frm;
+
+	/*
+	 * cal_iv_addr_en(type2): 0 bit
+	 * tls_up(type2): 1 bit
+	 * inveld: 7 bit
+	 */
+	__u8 iv_tls_ld;
+
+	/* Just using type2 BD now */
+	struct sec_sqe_type2 type2;
+};
+
+int sec_register_to_crypto(void);
+void sec_unregister_from_crypto(void);
+#endif
diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c
new file mode 100644
index 000000000000..74f0654028c9
--- /dev/null
+++ b/drivers/crypto/hisilicon/sec2/sec_main.c
@@ -0,0 +1,1095 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 HiSilicon Limited. */
+
+#include <linux/acpi.h>
+#include <linux/aer.h>
+#include <linux/bitops.h>
+#include <linux/debugfs.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/seq_file.h>
+#include <linux/topology.h>
+
+#include "sec.h"
+
+#define SEC_VF_NUM			63
+#define SEC_QUEUE_NUM_V1		4096
+#define SEC_QUEUE_NUM_V2		1024
+#define SEC_PF_PCI_DEVICE_ID		0xa255
+#define SEC_VF_PCI_DEVICE_ID		0xa256
+
+#define SEC_XTS_MIV_ENABLE_REG		0x301384
+#define SEC_XTS_MIV_ENABLE_MSK		0x7FFFFFFF
+#define SEC_XTS_MIV_DISABLE_MSK		0xFFFFFFFF
+#define SEC_BD_ERR_CHK_EN1		0xfffff7fd
+#define SEC_BD_ERR_CHK_EN2		0xffffbfff
+
+#define SEC_SQE_SIZE			128
+#define SEC_SQ_SIZE			(SEC_SQE_SIZE * QM_Q_DEPTH)
+#define SEC_PF_DEF_Q_NUM		64
+#define SEC_PF_DEF_Q_BASE		0
+#define SEC_CTX_Q_NUM_DEF		24
+
+#define SEC_CTRL_CNT_CLR_CE		0x301120
+#define SEC_CTRL_CNT_CLR_CE_BIT		BIT(0)
+#define SEC_ENGINE_PF_CFG_OFF		0x300000
+#define SEC_ACC_COMMON_REG_OFF		0x1000
+#define SEC_CORE_INT_SOURCE		0x301010
+#define SEC_CORE_INT_MASK		0x301000
+#define SEC_CORE_INT_STATUS		0x301008
+#define SEC_CORE_SRAM_ECC_ERR_INFO	0x301C14
+#define SEC_ECC_NUM(err)			(((err) >> 16) & 0xFF)
+#define SEC_ECC_ADDR(err)			((err) >> 0)
+#define SEC_CORE_INT_DISABLE		0x0
+#define SEC_CORE_INT_ENABLE		0x1ff
+
+#define SEC_RAS_CE_REG			0x50
+#define SEC_RAS_FE_REG			0x54
+#define SEC_RAS_NFE_REG			0x58
+#define SEC_RAS_CE_ENB_MSK		0x88
+#define SEC_RAS_FE_ENB_MSK		0x0
+#define SEC_RAS_NFE_ENB_MSK		0x177
+#define SEC_RAS_DISABLE			0x0
+#define SEC_MEM_START_INIT_REG		0x0100
+#define SEC_MEM_INIT_DONE_REG		0x0104
+#define SEC_QM_ABNORMAL_INT_MASK	0x100004
+
+#define SEC_CONTROL_REG			0x0200
+#define SEC_TRNG_EN_SHIFT		8
+#define SEC_CLK_GATE_ENABLE		BIT(3)
+#define SEC_CLK_GATE_DISABLE		(~BIT(3))
+#define SEC_AXI_SHUTDOWN_ENABLE	BIT(12)
+#define SEC_AXI_SHUTDOWN_DISABLE	0xFFFFEFFF
+
+#define SEC_INTERFACE_USER_CTRL0_REG	0x0220
+#define SEC_INTERFACE_USER_CTRL1_REG	0x0224
+#define SEC_BD_ERR_CHK_EN_REG1		0x0384
+#define SEC_BD_ERR_CHK_EN_REG2		0x038c
+
+#define SEC_USER0_SMMU_NORMAL		(BIT(23) | BIT(15))
+#define SEC_USER1_SMMU_NORMAL		(BIT(31) | BIT(23) | BIT(15) | BIT(7))
+#define SEC_CORE_INT_STATUS_M_ECC	BIT(2)
+
+#define SEC_DELAY_10_US			10
+#define SEC_POLL_TIMEOUT_US		1000
+#define SEC_VF_CNT_MASK			0xffffffc0
+#define SEC_DBGFS_VAL_MAX_LEN		20
+
+#define SEC_ADDR(qm, offset) ((qm)->io_base + (offset) + \
+			     SEC_ENGINE_PF_CFG_OFF + SEC_ACC_COMMON_REG_OFF)
+
+struct sec_hw_error {
+	u32 int_msk;
+	const char *msg;
+};
+
+static const char sec_name[] = "hisi_sec2";
+static struct dentry *sec_debugfs_root;
+static LIST_HEAD(sec_list);
+static DEFINE_MUTEX(sec_list_lock);
+
+static const struct sec_hw_error sec_hw_errors[] = {
+	{.int_msk = BIT(0), .msg = "sec_axi_rresp_err_rint"},
+	{.int_msk = BIT(1), .msg = "sec_axi_bresp_err_rint"},
+	{.int_msk = BIT(2), .msg = "sec_ecc_2bit_err_rint"},
+	{.int_msk = BIT(3), .msg = "sec_ecc_1bit_err_rint"},
+	{.int_msk = BIT(4), .msg = "sec_req_trng_timeout_rint"},
+	{.int_msk = BIT(5), .msg = "sec_fsm_hbeat_rint"},
+	{.int_msk = BIT(6), .msg = "sec_channel_req_rng_timeout_rint"},
+	{.int_msk = BIT(7), .msg = "sec_bd_err_rint"},
+	{.int_msk = BIT(8), .msg = "sec_chain_buff_err_rint"},
+	{ /* sentinel */ }
+};
+
+struct sec_dev *sec_find_device(int node)
+{
+#define SEC_NUMA_MAX_DISTANCE	100
+	int min_distance = SEC_NUMA_MAX_DISTANCE;
+	int dev_node = 0, free_qp_num = 0;
+	struct sec_dev *sec, *ret = NULL;
+	struct hisi_qm *qm;
+	struct device *dev;
+
+	mutex_lock(&sec_list_lock);
+	list_for_each_entry(sec, &sec_list, list) {
+		qm = &sec->qm;
+		dev = &qm->pdev->dev;
+#ifdef CONFIG_NUMA
+		dev_node = dev->numa_node;
+		if (dev_node < 0)
+			dev_node = 0;
+#endif
+		if (node_distance(dev_node, node) < min_distance) {
+			free_qp_num = hisi_qm_get_free_qp_num(qm);
+			if (free_qp_num >= sec->ctx_q_num) {
+				ret = sec;
+				min_distance = node_distance(dev_node, node);
+			}
+		}
+	}
+	mutex_unlock(&sec_list_lock);
+
+	return ret;
+}
+
+static const char * const sec_dbg_file_name[] = {
+	[SEC_CURRENT_QM] = "current_qm",
+	[SEC_CLEAR_ENABLE] = "clear_enable",
+};
+
+static struct debugfs_reg32 sec_dfx_regs[] = {
+	{"SEC_PF_ABNORMAL_INT_SOURCE    ",  0x301010},
+	{"SEC_SAA_EN                    ",  0x301270},
+	{"SEC_BD_LATENCY_MIN            ",  0x301600},
+	{"SEC_BD_LATENCY_MAX            ",  0x301608},
+	{"SEC_BD_LATENCY_AVG            ",  0x30160C},
+	{"SEC_BD_NUM_IN_SAA0            ",  0x301670},
+	{"SEC_BD_NUM_IN_SAA1            ",  0x301674},
+	{"SEC_BD_NUM_IN_SEC             ",  0x301680},
+	{"SEC_ECC_1BIT_CNT              ",  0x301C00},
+	{"SEC_ECC_1BIT_INFO             ",  0x301C04},
+	{"SEC_ECC_2BIT_CNT              ",  0x301C10},
+	{"SEC_ECC_2BIT_INFO             ",  0x301C14},
+	{"SEC_BD_SAA0                   ",  0x301C20},
+	{"SEC_BD_SAA1                   ",  0x301C24},
+	{"SEC_BD_SAA2                   ",  0x301C28},
+	{"SEC_BD_SAA3                   ",  0x301C2C},
+	{"SEC_BD_SAA4                   ",  0x301C30},
+	{"SEC_BD_SAA5                   ",  0x301C34},
+	{"SEC_BD_SAA6                   ",  0x301C38},
+	{"SEC_BD_SAA7                   ",  0x301C3C},
+	{"SEC_BD_SAA8                   ",  0x301C40},
+};
+
+static int sec_pf_q_num_set(const char *val, const struct kernel_param *kp)
+{
+	struct pci_dev *pdev;
+	u32 n, q_num;
+	u8 rev_id;
+	int ret;
+
+	if (!val)
+		return -EINVAL;
+
+	pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI,
+			      SEC_PF_PCI_DEVICE_ID, NULL);
+	if (!pdev) {
+		q_num = min_t(u32, SEC_QUEUE_NUM_V1, SEC_QUEUE_NUM_V2);
+		pr_info("No device, suppose queue number is %d!\n", q_num);
+	} else {
+		rev_id = pdev->revision;
+
+		switch (rev_id) {
+		case QM_HW_V1:
+			q_num = SEC_QUEUE_NUM_V1;
+			break;
+		case QM_HW_V2:
+			q_num = SEC_QUEUE_NUM_V2;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	ret = kstrtou32(val, 10, &n);
+	if (ret || !n || n > q_num)
+		return -EINVAL;
+
+	return param_set_int(val, kp);
+}
+
+static const struct kernel_param_ops sec_pf_q_num_ops = {
+	.set = sec_pf_q_num_set,
+	.get = param_get_int,
+};
+static u32 pf_q_num = SEC_PF_DEF_Q_NUM;
+module_param_cb(pf_q_num, &sec_pf_q_num_ops, &pf_q_num, 0444);
+MODULE_PARM_DESC(pf_q_num, "Number of queues in PF(v1 0-4096, v2 0-1024)");
+
+static int sec_ctx_q_num_set(const char *val, const struct kernel_param *kp)
+{
+	u32 ctx_q_num;
+	int ret;
+
+	if (!val)
+		return -EINVAL;
+
+	ret = kstrtou32(val, 10, &ctx_q_num);
+	if (ret)
+		return -EINVAL;
+
+	if (!ctx_q_num || ctx_q_num > QM_Q_DEPTH || ctx_q_num & 0x1) {
+		pr_err("ctx queue num[%u] is invalid!\n", ctx_q_num);
+		return -EINVAL;
+	}
+
+	return param_set_int(val, kp);
+}
+
+static const struct kernel_param_ops sec_ctx_q_num_ops = {
+	.set = sec_ctx_q_num_set,
+	.get = param_get_int,
+};
+static u32 ctx_q_num = SEC_CTX_Q_NUM_DEF;
+module_param_cb(ctx_q_num, &sec_ctx_q_num_ops, &ctx_q_num, 0444);
+MODULE_PARM_DESC(ctx_q_num, "Number of queue in ctx (2, 4, 6, ..., 1024)");
+
+static const struct pci_device_id sec_dev_ids[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, SEC_PF_PCI_DEVICE_ID) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, SEC_VF_PCI_DEVICE_ID) },
+	{ 0, }
+};
+MODULE_DEVICE_TABLE(pci, sec_dev_ids);
+
+static inline void sec_add_to_list(struct sec_dev *sec)
+{
+	mutex_lock(&sec_list_lock);
+	list_add_tail(&sec->list, &sec_list);
+	mutex_unlock(&sec_list_lock);
+}
+
+static inline void sec_remove_from_list(struct sec_dev *sec)
+{
+	mutex_lock(&sec_list_lock);
+	list_del(&sec->list);
+	mutex_unlock(&sec_list_lock);
+}
+
+static u8 sec_get_endian(struct sec_dev *sec)
+{
+	struct hisi_qm *qm = &sec->qm;
+	u32 reg;
+
+	/*
+	 * As for VF, it is a wrong way to get endian setting by
+	 * reading a register of the engine
+	 */
+	if (qm->pdev->is_virtfn) {
+		dev_err_ratelimited(&qm->pdev->dev,
+				    "cannot access a register in VF!\n");
+		return SEC_LE;
+	}
+	reg = readl_relaxed(qm->io_base + SEC_ENGINE_PF_CFG_OFF +
+			    SEC_ACC_COMMON_REG_OFF + SEC_CONTROL_REG);
+
+	/* BD little endian mode */
+	if (!(reg & BIT(0)))
+		return SEC_LE;
+
+	/* BD 32-bits big endian mode */
+	else if (!(reg & BIT(1)))
+		return SEC_32BE;
+
+	/* BD 64-bits big endian mode */
+	else
+		return SEC_64BE;
+}
+
+static int sec_engine_init(struct sec_dev *sec)
+{
+	struct hisi_qm *qm = &sec->qm;
+	int ret;
+	u32 reg;
+
+	/* disable clock gate control */
+	reg = readl_relaxed(SEC_ADDR(qm, SEC_CONTROL_REG));
+	reg &= SEC_CLK_GATE_DISABLE;
+	writel_relaxed(reg, SEC_ADDR(qm, SEC_CONTROL_REG));
+
+	writel_relaxed(0x1, SEC_ADDR(qm, SEC_MEM_START_INIT_REG));
+
+	ret = readl_relaxed_poll_timeout(SEC_ADDR(qm, SEC_MEM_INIT_DONE_REG),
+					 reg, reg & 0x1, SEC_DELAY_10_US,
+					 SEC_POLL_TIMEOUT_US);
+	if (ret) {
+		dev_err(&qm->pdev->dev, "fail to init sec mem\n");
+		return ret;
+	}
+
+	reg = readl_relaxed(SEC_ADDR(qm, SEC_CONTROL_REG));
+	reg |= (0x1 << SEC_TRNG_EN_SHIFT);
+	writel_relaxed(reg, SEC_ADDR(qm, SEC_CONTROL_REG));
+
+	reg = readl_relaxed(SEC_ADDR(qm, SEC_INTERFACE_USER_CTRL0_REG));
+	reg |= SEC_USER0_SMMU_NORMAL;
+	writel_relaxed(reg, SEC_ADDR(qm, SEC_INTERFACE_USER_CTRL0_REG));
+
+	reg = readl_relaxed(SEC_ADDR(qm, SEC_INTERFACE_USER_CTRL1_REG));
+	reg |= SEC_USER1_SMMU_NORMAL;
+	writel_relaxed(reg, SEC_ADDR(qm, SEC_INTERFACE_USER_CTRL1_REG));
+
+	writel_relaxed(SEC_BD_ERR_CHK_EN1,
+		       SEC_ADDR(qm, SEC_BD_ERR_CHK_EN_REG1));
+	writel_relaxed(SEC_BD_ERR_CHK_EN2,
+		       SEC_ADDR(qm, SEC_BD_ERR_CHK_EN_REG2));
+
+	/* enable clock gate control */
+	reg = readl_relaxed(SEC_ADDR(qm, SEC_CONTROL_REG));
+	reg |= SEC_CLK_GATE_ENABLE;
+	writel_relaxed(reg, SEC_ADDR(qm, SEC_CONTROL_REG));
+
+	/* config endian */
+	reg = readl_relaxed(SEC_ADDR(qm, SEC_CONTROL_REG));
+	reg |= sec_get_endian(sec);
+	writel_relaxed(reg, SEC_ADDR(qm, SEC_CONTROL_REG));
+
+	/* Enable sm4 xts mode multiple iv */
+	writel_relaxed(SEC_XTS_MIV_ENABLE_MSK,
+		       qm->io_base + SEC_XTS_MIV_ENABLE_REG);
+
+	return 0;
+}
+
+static int sec_set_user_domain_and_cache(struct sec_dev *sec)
+{
+	struct hisi_qm *qm = &sec->qm;
+
+	/* qm user domain */
+	writel(AXUSER_BASE, qm->io_base + QM_ARUSER_M_CFG_1);
+	writel(ARUSER_M_CFG_ENABLE, qm->io_base + QM_ARUSER_M_CFG_ENABLE);
+	writel(AXUSER_BASE, qm->io_base + QM_AWUSER_M_CFG_1);
+	writel(AWUSER_M_CFG_ENABLE, qm->io_base + QM_AWUSER_M_CFG_ENABLE);
+	writel(WUSER_M_CFG_ENABLE, qm->io_base + QM_WUSER_M_CFG_ENABLE);
+
+	/* qm cache */
+	writel(AXI_M_CFG, qm->io_base + QM_AXI_M_CFG);
+	writel(AXI_M_CFG_ENABLE, qm->io_base + QM_AXI_M_CFG_ENABLE);
+
+	/* disable FLR triggered by BME(bus master enable) */
+	writel(PEH_AXUSER_CFG, qm->io_base + QM_PEH_AXUSER_CFG);
+	writel(PEH_AXUSER_CFG_ENABLE, qm->io_base + QM_PEH_AXUSER_CFG_ENABLE);
+
+	/* enable sqc,cqc writeback */
+	writel(SQC_CACHE_ENABLE | CQC_CACHE_ENABLE | SQC_CACHE_WB_ENABLE |
+	       CQC_CACHE_WB_ENABLE | FIELD_PREP(SQC_CACHE_WB_THRD, 1) |
+	       FIELD_PREP(CQC_CACHE_WB_THRD, 1), qm->io_base + QM_CACHE_CTL);
+
+	return sec_engine_init(sec);
+}
+
+/* sec_debug_regs_clear() - clear the sec debug regs */
+static void sec_debug_regs_clear(struct hisi_qm *qm)
+{
+	/* clear current_qm */
+	writel(0x0, qm->io_base + QM_DFX_MB_CNT_VF);
+	writel(0x0, qm->io_base + QM_DFX_DB_CNT_VF);
+
+	/* clear rdclr_en */
+	writel(0x0, qm->io_base + SEC_CTRL_CNT_CLR_CE);
+
+	hisi_qm_debug_regs_clear(qm);
+}
+
+static void sec_hw_error_enable(struct sec_dev *sec)
+{
+	struct hisi_qm *qm = &sec->qm;
+	u32 val;
+
+	if (qm->ver == QM_HW_V1) {
+		writel(SEC_CORE_INT_DISABLE, qm->io_base + SEC_CORE_INT_MASK);
+		dev_info(&qm->pdev->dev, "V1 not support hw error handle\n");
+		return;
+	}
+
+	val = readl(qm->io_base + SEC_CONTROL_REG);
+
+	/* clear SEC hw error source if having */
+	writel(SEC_CORE_INT_DISABLE, qm->io_base + SEC_CORE_INT_SOURCE);
+
+	/* enable SEC hw error interrupts */
+	writel(SEC_CORE_INT_ENABLE, qm->io_base + SEC_CORE_INT_MASK);
+
+	/* enable RAS int */
+	writel(SEC_RAS_CE_ENB_MSK, qm->io_base + SEC_RAS_CE_REG);
+	writel(SEC_RAS_FE_ENB_MSK, qm->io_base + SEC_RAS_FE_REG);
+	writel(SEC_RAS_NFE_ENB_MSK, qm->io_base + SEC_RAS_NFE_REG);
+
+	/* enable SEC block master OOO when m-bit error occur */
+	val = val | SEC_AXI_SHUTDOWN_ENABLE;
+
+	writel(val, qm->io_base + SEC_CONTROL_REG);
+}
+
+static void sec_hw_error_disable(struct sec_dev *sec)
+{
+	struct hisi_qm *qm = &sec->qm;
+	u32 val;
+
+	val = readl(qm->io_base + SEC_CONTROL_REG);
+
+	/* disable RAS int */
+	writel(SEC_RAS_DISABLE, qm->io_base + SEC_RAS_CE_REG);
+	writel(SEC_RAS_DISABLE, qm->io_base + SEC_RAS_FE_REG);
+	writel(SEC_RAS_DISABLE, qm->io_base + SEC_RAS_NFE_REG);
+
+	/* disable SEC hw error interrupts */
+	writel(SEC_CORE_INT_DISABLE, qm->io_base + SEC_CORE_INT_MASK);
+
+	/* disable SEC block master OOO when m-bit error occur */
+	val = val & SEC_AXI_SHUTDOWN_DISABLE;
+
+	writel(val, qm->io_base + SEC_CONTROL_REG);
+}
+
+static void sec_hw_error_init(struct sec_dev *sec)
+{
+	if (sec->qm.fun_type == QM_HW_VF)
+		return;
+
+	hisi_qm_hw_error_init(&sec->qm, QM_BASE_CE,
+			      QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT
+			      | QM_ACC_WB_NOT_READY_TIMEOUT, 0,
+			      QM_DB_RANDOM_INVALID);
+	sec_hw_error_enable(sec);
+}
+
+static void sec_hw_error_uninit(struct sec_dev *sec)
+{
+	if (sec->qm.fun_type == QM_HW_VF)
+		return;
+
+	sec_hw_error_disable(sec);
+	writel(GENMASK(12, 0), sec->qm.io_base + SEC_QM_ABNORMAL_INT_MASK);
+}
+
+static u32 sec_current_qm_read(struct sec_debug_file *file)
+{
+	struct hisi_qm *qm = file->qm;
+
+	return readl(qm->io_base + QM_DFX_MB_CNT_VF);
+}
+
+static int sec_current_qm_write(struct sec_debug_file *file, u32 val)
+{
+	struct hisi_qm *qm = file->qm;
+	struct sec_dev *sec = container_of(qm, struct sec_dev, qm);
+	u32 vfq_num;
+	u32 tmp;
+
+	if (val > sec->num_vfs)
+		return -EINVAL;
+
+	/* According PF or VF Dev ID to calculation curr_qm_qp_num and store */
+	if (!val) {
+		qm->debug.curr_qm_qp_num = qm->qp_num;
+	} else {
+		vfq_num = (qm->ctrl_qp_num - qm->qp_num) / sec->num_vfs;
+
+		if (val == sec->num_vfs)
+			qm->debug.curr_qm_qp_num =
+				qm->ctrl_qp_num - qm->qp_num -
+				(sec->num_vfs - 1) * vfq_num;
+		else
+			qm->debug.curr_qm_qp_num = vfq_num;
+	}
+
+	writel(val, qm->io_base + QM_DFX_MB_CNT_VF);
+	writel(val, qm->io_base + QM_DFX_DB_CNT_VF);
+
+	tmp = val |
+	      (readl(qm->io_base + QM_DFX_SQE_CNT_VF_SQN) & CURRENT_Q_MASK);
+	writel(tmp, qm->io_base + QM_DFX_SQE_CNT_VF_SQN);
+
+	tmp = val |
+	      (readl(qm->io_base + QM_DFX_CQE_CNT_VF_CQN) & CURRENT_Q_MASK);
+	writel(tmp, qm->io_base + QM_DFX_CQE_CNT_VF_CQN);
+
+	return 0;
+}
+
+static u32 sec_clear_enable_read(struct sec_debug_file *file)
+{
+	struct hisi_qm *qm = file->qm;
+
+	return readl(qm->io_base + SEC_CTRL_CNT_CLR_CE) &
+			SEC_CTRL_CNT_CLR_CE_BIT;
+}
+
+static int sec_clear_enable_write(struct sec_debug_file *file, u32 val)
+{
+	struct hisi_qm *qm = file->qm;
+	u32 tmp;
+
+	if (val != 1 && val)
+		return -EINVAL;
+
+	tmp = (readl(qm->io_base + SEC_CTRL_CNT_CLR_CE) &
+	       ~SEC_CTRL_CNT_CLR_CE_BIT) | val;
+	writel(tmp, qm->io_base + SEC_CTRL_CNT_CLR_CE);
+
+	return 0;
+}
+
+static ssize_t sec_debug_read(struct file *filp, char __user *buf,
+			       size_t count, loff_t *pos)
+{
+	struct sec_debug_file *file = filp->private_data;
+	char tbuf[SEC_DBGFS_VAL_MAX_LEN];
+	u32 val;
+	int ret;
+
+	spin_lock_irq(&file->lock);
+
+	switch (file->index) {
+	case SEC_CURRENT_QM:
+		val = sec_current_qm_read(file);
+		break;
+	case SEC_CLEAR_ENABLE:
+		val = sec_clear_enable_read(file);
+		break;
+	default:
+		spin_unlock_irq(&file->lock);
+		return -EINVAL;
+	}
+
+	spin_unlock_irq(&file->lock);
+	ret = snprintf(tbuf, SEC_DBGFS_VAL_MAX_LEN, "%u\n", val);
+
+	return simple_read_from_buffer(buf, count, pos, tbuf, ret);
+}
+
+static ssize_t sec_debug_write(struct file *filp, const char __user *buf,
+			       size_t count, loff_t *pos)
+{
+	struct sec_debug_file *file = filp->private_data;
+	char tbuf[SEC_DBGFS_VAL_MAX_LEN];
+	unsigned long val;
+	int len, ret;
+
+	if (*pos != 0)
+		return 0;
+
+	if (count >= SEC_DBGFS_VAL_MAX_LEN)
+		return -ENOSPC;
+
+	len = simple_write_to_buffer(tbuf, SEC_DBGFS_VAL_MAX_LEN - 1,
+				     pos, buf, count);
+	if (len < 0)
+		return len;
+
+	tbuf[len] = '\0';
+	if (kstrtoul(tbuf, 0, &val))
+		return -EFAULT;
+
+	spin_lock_irq(&file->lock);
+
+	switch (file->index) {
+	case SEC_CURRENT_QM:
+		ret = sec_current_qm_write(file, val);
+		if (ret)
+			goto err_input;
+		break;
+	case SEC_CLEAR_ENABLE:
+		ret = sec_clear_enable_write(file, val);
+		if (ret)
+			goto err_input;
+		break;
+	default:
+		ret = -EINVAL;
+		goto err_input;
+	}
+
+	spin_unlock_irq(&file->lock);
+
+	return count;
+
+ err_input:
+	spin_unlock_irq(&file->lock);
+	return ret;
+}
+
+static const struct file_operations sec_dbg_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read = sec_debug_read,
+	.write = sec_debug_write,
+};
+
+static int sec_core_debug_init(struct sec_dev *sec)
+{
+	struct hisi_qm *qm = &sec->qm;
+	struct device *dev = &qm->pdev->dev;
+	struct sec_dfx *dfx = &sec->debug.dfx;
+	struct debugfs_regset32 *regset;
+	struct dentry *tmp_d;
+
+	tmp_d = debugfs_create_dir("sec_dfx", sec->qm.debug.debug_root);
+
+	regset = devm_kzalloc(dev, sizeof(*regset), GFP_KERNEL);
+	if (!regset)
+		return -ENOENT;
+
+	regset->regs = sec_dfx_regs;
+	regset->nregs = ARRAY_SIZE(sec_dfx_regs);
+	regset->base = qm->io_base;
+
+	debugfs_create_regset32("regs", 0444, tmp_d, regset);
+
+	debugfs_create_u64("send_cnt", 0444, tmp_d, &dfx->send_cnt);
+
+	debugfs_create_u64("recv_cnt", 0444, tmp_d, &dfx->recv_cnt);
+
+	return 0;
+}
+
+static int sec_debug_init(struct sec_dev *sec)
+{
+	int i;
+
+	for (i = SEC_CURRENT_QM; i < SEC_DEBUG_FILE_NUM; i++) {
+		spin_lock_init(&sec->debug.files[i].lock);
+		sec->debug.files[i].index = i;
+		sec->debug.files[i].qm = &sec->qm;
+
+		debugfs_create_file(sec_dbg_file_name[i], 0600,
+				    sec->qm.debug.debug_root,
+				    sec->debug.files + i,
+				    &sec_dbg_fops);
+	}
+
+	return sec_core_debug_init(sec);
+}
+
+static int sec_debugfs_init(struct sec_dev *sec)
+{
+	struct hisi_qm *qm = &sec->qm;
+	struct device *dev = &qm->pdev->dev;
+	int ret;
+
+	qm->debug.debug_root = debugfs_create_dir(dev_name(dev),
+						  sec_debugfs_root);
+	ret = hisi_qm_debug_init(qm);
+	if (ret)
+		goto failed_to_create;
+
+	if (qm->pdev->device == SEC_PF_PCI_DEVICE_ID) {
+		ret = sec_debug_init(sec);
+		if (ret)
+			goto failed_to_create;
+	}
+
+	return 0;
+
+failed_to_create:
+	debugfs_remove_recursive(sec_debugfs_root);
+
+	return ret;
+}
+
+static void sec_debugfs_exit(struct sec_dev *sec)
+{
+	debugfs_remove_recursive(sec->qm.debug.debug_root);
+}
+
+static int sec_pf_probe_init(struct sec_dev *sec)
+{
+	struct hisi_qm *qm = &sec->qm;
+	int ret;
+
+	switch (qm->ver) {
+	case QM_HW_V1:
+		qm->ctrl_qp_num = SEC_QUEUE_NUM_V1;
+		break;
+
+	case QM_HW_V2:
+		qm->ctrl_qp_num = SEC_QUEUE_NUM_V2;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	ret = sec_set_user_domain_and_cache(sec);
+	if (ret)
+		return ret;
+
+	sec_hw_error_init(sec);
+	sec_debug_regs_clear(qm);
+
+	return 0;
+}
+
+static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
+{
+	enum qm_hw_ver rev_id;
+
+	rev_id = hisi_qm_get_hw_version(pdev);
+	if (rev_id == QM_HW_UNKNOWN)
+		return -ENODEV;
+
+	qm->pdev = pdev;
+	qm->ver = rev_id;
+
+	qm->sqe_size = SEC_SQE_SIZE;
+	qm->dev_name = sec_name;
+	qm->fun_type = (pdev->device == SEC_PF_PCI_DEVICE_ID) ?
+			QM_HW_PF : QM_HW_VF;
+	qm->use_dma_api = true;
+
+	return hisi_qm_init(qm);
+}
+
+static void sec_qm_uninit(struct hisi_qm *qm)
+{
+	hisi_qm_uninit(qm);
+}
+
+static int sec_probe_init(struct hisi_qm *qm, struct sec_dev *sec)
+{
+	if (qm->fun_type == QM_HW_PF) {
+		qm->qp_base = SEC_PF_DEF_Q_BASE;
+		qm->qp_num = pf_q_num;
+		qm->debug.curr_qm_qp_num = pf_q_num;
+
+		return sec_pf_probe_init(sec);
+	} else if (qm->fun_type == QM_HW_VF) {
+		/*
+		 * have no way to get qm configure in VM in v1 hardware,
+		 * so currently force PF to uses SEC_PF_DEF_Q_NUM, and force
+		 * to trigger only one VF in v1 hardware.
+		 * v2 hardware has no such problem.
+		 */
+		if (qm->ver == QM_HW_V1) {
+			qm->qp_base = SEC_PF_DEF_Q_NUM;
+			qm->qp_num = SEC_QUEUE_NUM_V1 - SEC_PF_DEF_Q_NUM;
+		} else if (qm->ver == QM_HW_V2) {
+			/* v2 starts to support get vft by mailbox */
+			return hisi_qm_get_vft(qm, &qm->qp_base, &qm->qp_num);
+		}
+	} else {
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static void sec_probe_uninit(struct sec_dev *sec)
+{
+	sec_hw_error_uninit(sec);
+}
+
+static int sec_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct sec_dev *sec;
+	struct hisi_qm *qm;
+	int ret;
+
+	sec = devm_kzalloc(&pdev->dev, sizeof(*sec), GFP_KERNEL);
+	if (!sec)
+		return -ENOMEM;
+
+	pci_set_drvdata(pdev, sec);
+
+	sec->ctx_q_num = ctx_q_num;
+
+	qm = &sec->qm;
+
+	ret = sec_qm_init(qm, pdev);
+	if (ret) {
+		pci_err(pdev, "Failed to pre init qm!\n");
+		return ret;
+	}
+
+	ret = sec_probe_init(qm, sec);
+	if (ret) {
+		pci_err(pdev, "Failed to probe!\n");
+		goto err_qm_uninit;
+	}
+
+	ret = hisi_qm_start(qm);
+	if (ret) {
+		pci_err(pdev, "Failed to start sec qm!\n");
+		goto err_probe_uninit;
+	}
+
+	ret = sec_debugfs_init(sec);
+	if (ret)
+		pci_warn(pdev, "Failed to init debugfs!\n");
+
+	sec_add_to_list(sec);
+
+	ret = sec_register_to_crypto();
+	if (ret < 0) {
+		pr_err("Failed to register driver to crypto.\n");
+		goto err_remove_from_list;
+	}
+
+	return 0;
+
+err_remove_from_list:
+	sec_remove_from_list(sec);
+	sec_debugfs_exit(sec);
+	hisi_qm_stop(qm);
+
+err_probe_uninit:
+	sec_probe_uninit(sec);
+
+err_qm_uninit:
+	sec_qm_uninit(qm);
+
+	return ret;
+}
+
+/* now we only support equal assignment */
+static int sec_vf_q_assign(struct sec_dev *sec, u32 num_vfs)
+{
+	struct hisi_qm *qm = &sec->qm;
+	u32 qp_num = qm->qp_num;
+	u32 q_base = qp_num;
+	u32 q_num, remain_q_num;
+	int i, j, ret;
+
+	if (!num_vfs)
+		return -EINVAL;
+
+	remain_q_num = qm->ctrl_qp_num - qp_num;
+	q_num = remain_q_num / num_vfs;
+
+	for (i = 1; i <= num_vfs; i++) {
+		if (i == num_vfs)
+			q_num += remain_q_num % num_vfs;
+		ret = hisi_qm_set_vft(qm, i, q_base, q_num);
+		if (ret) {
+			for (j = i; j > 0; j--)
+				hisi_qm_set_vft(qm, j, 0, 0);
+			return ret;
+		}
+		q_base += q_num;
+	}
+
+	return 0;
+}
+
+static int sec_clear_vft_config(struct sec_dev *sec)
+{
+	struct hisi_qm *qm = &sec->qm;
+	u32 num_vfs = sec->num_vfs;
+	int ret;
+	u32 i;
+
+	for (i = 1; i <= num_vfs; i++) {
+		ret = hisi_qm_set_vft(qm, i, 0, 0);
+		if (ret)
+			return ret;
+	}
+
+	sec->num_vfs = 0;
+
+	return 0;
+}
+
+static int sec_sriov_enable(struct pci_dev *pdev, int max_vfs)
+{
+	struct sec_dev *sec = pci_get_drvdata(pdev);
+	int pre_existing_vfs, ret;
+	u32 num_vfs;
+
+	pre_existing_vfs = pci_num_vf(pdev);
+
+	if (pre_existing_vfs) {
+		pci_err(pdev, "Can't enable VF. Please disable at first!\n");
+		return 0;
+	}
+
+	num_vfs = min_t(u32, max_vfs, SEC_VF_NUM);
+
+	ret = sec_vf_q_assign(sec, num_vfs);
+	if (ret) {
+		pci_err(pdev, "Can't assign queues for VF!\n");
+		return ret;
+	}
+
+	sec->num_vfs = num_vfs;
+
+	ret = pci_enable_sriov(pdev, num_vfs);
+	if (ret) {
+		pci_err(pdev, "Can't enable VF!\n");
+		sec_clear_vft_config(sec);
+		return ret;
+	}
+
+	return num_vfs;
+}
+
+static int sec_sriov_disable(struct pci_dev *pdev)
+{
+	struct sec_dev *sec = pci_get_drvdata(pdev);
+
+	if (pci_vfs_assigned(pdev)) {
+		pci_err(pdev, "Can't disable VFs while VFs are assigned!\n");
+		return -EPERM;
+	}
+
+	/* remove in sec_pci_driver will be called to free VF resources */
+	pci_disable_sriov(pdev);
+
+	return sec_clear_vft_config(sec);
+}
+
+static int sec_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+	if (num_vfs)
+		return sec_sriov_enable(pdev, num_vfs);
+	else
+		return sec_sriov_disable(pdev);
+}
+
+static void sec_remove(struct pci_dev *pdev)
+{
+	struct sec_dev *sec = pci_get_drvdata(pdev);
+	struct hisi_qm *qm = &sec->qm;
+
+	sec_unregister_from_crypto();
+
+	sec_remove_from_list(sec);
+
+	if (qm->fun_type == QM_HW_PF && sec->num_vfs)
+		(void)sec_sriov_disable(pdev);
+
+	sec_debugfs_exit(sec);
+
+	(void)hisi_qm_stop(qm);
+
+	if (qm->fun_type == QM_HW_PF)
+		sec_debug_regs_clear(qm);
+
+	sec_probe_uninit(sec);
+
+	sec_qm_uninit(qm);
+}
+
+static void sec_log_hw_error(struct sec_dev *sec, u32 err_sts)
+{
+	const struct sec_hw_error *errs = sec_hw_errors;
+	struct device *dev = &sec->qm.pdev->dev;
+	u32 err_val;
+
+	while (errs->msg) {
+		if (errs->int_msk & err_sts) {
+			dev_err(dev, "%s [error status=0x%x] found\n",
+				errs->msg, errs->int_msk);
+
+			if (SEC_CORE_INT_STATUS_M_ECC & err_sts) {
+				err_val = readl(sec->qm.io_base +
+						SEC_CORE_SRAM_ECC_ERR_INFO);
+				dev_err(dev, "multi ecc sram num=0x%x\n",
+					SEC_ECC_NUM(err_val));
+				dev_err(dev, "multi ecc sram addr=0x%x\n",
+					SEC_ECC_ADDR(err_val));
+			}
+		}
+		errs++;
+	}
+}
+
+static pci_ers_result_t sec_hw_error_handle(struct sec_dev *sec)
+{
+	u32 err_sts;
+
+	/* read err sts */
+	err_sts = readl(sec->qm.io_base + SEC_CORE_INT_STATUS);
+	if (err_sts) {
+		sec_log_hw_error(sec, err_sts);
+
+		/* clear error interrupts */
+		writel(err_sts, sec->qm.io_base + SEC_CORE_INT_SOURCE);
+
+		return PCI_ERS_RESULT_NEED_RESET;
+	}
+
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
+static pci_ers_result_t sec_process_hw_error(struct pci_dev *pdev)
+{
+	struct sec_dev *sec = pci_get_drvdata(pdev);
+	pci_ers_result_t qm_ret, sec_ret;
+
+	if (!sec) {
+		pci_err(pdev, "Can't recover error during device init\n");
+		return PCI_ERS_RESULT_NONE;
+	}
+
+	/* log qm error */
+	qm_ret = hisi_qm_hw_error_handle(&sec->qm);
+
+	/* log sec error */
+	sec_ret = sec_hw_error_handle(sec);
+
+	return (qm_ret == PCI_ERS_RESULT_NEED_RESET ||
+		sec_ret == PCI_ERS_RESULT_NEED_RESET) ?
+		PCI_ERS_RESULT_NEED_RESET : PCI_ERS_RESULT_RECOVERED;
+}
+
+static pci_ers_result_t sec_error_detected(struct pci_dev *pdev,
+					   pci_channel_state_t state)
+{
+	if (pdev->is_virtfn)
+		return PCI_ERS_RESULT_NONE;
+
+	pci_info(pdev, "PCI error detected, state(=%d)!!\n", state);
+	if (state == pci_channel_io_perm_failure)
+		return PCI_ERS_RESULT_DISCONNECT;
+
+	return sec_process_hw_error(pdev);
+}
+
+static const struct pci_error_handlers sec_err_handler = {
+	.error_detected = sec_error_detected,
+};
+
+static struct pci_driver sec_pci_driver = {
+	.name = "hisi_sec2",
+	.id_table = sec_dev_ids,
+	.probe = sec_probe,
+	.remove = sec_remove,
+	.err_handler = &sec_err_handler,
+	.sriov_configure = sec_sriov_configure,
+};
+
+static void sec_register_debugfs(void)
+{
+	if (!debugfs_initialized())
+		return;
+
+	sec_debugfs_root = debugfs_create_dir("hisi_sec2", NULL);
+}
+
+static void sec_unregister_debugfs(void)
+{
+	debugfs_remove_recursive(sec_debugfs_root);
+}
+
+static int __init sec_init(void)
+{
+	int ret;
+
+	sec_register_debugfs();
+
+	ret = pci_register_driver(&sec_pci_driver);
+	if (ret < 0) {
+		sec_unregister_debugfs();
+		pr_err("Failed to register pci driver.\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static void __exit sec_exit(void)
+{
+	pci_unregister_driver(&sec_pci_driver);
+	sec_unregister_debugfs();
+}
+
+module_init(sec_init);
+module_exit(sec_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Zaibo Xu <xuzaibo@huawei.com>");
+MODULE_AUTHOR("Longfang Liu <liulongfang@huawei.com>");
+MODULE_AUTHOR("Wei Zhang <zhangwei375@huawei.com>");
+MODULE_DESCRIPTION("Driver for HiSilicon SEC accelerator");
diff --git a/drivers/crypto/hisilicon/sgl.c b/drivers/crypto/hisilicon/sgl.c
index e083d172b618..012023c347b1 100644
--- a/drivers/crypto/hisilicon/sgl.c
+++ b/drivers/crypto/hisilicon/sgl.c
@@ -2,37 +2,13 @@
 /* Copyright (c) 2019 HiSilicon Limited. */
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
-#include "./sgl.h"
+#include <linux/slab.h>
+#include "qm.h"
 
 #define HISI_ACC_SGL_SGE_NR_MIN		1
-#define HISI_ACC_SGL_SGE_NR_MAX		255
-#define HISI_ACC_SGL_SGE_NR_DEF		10
 #define HISI_ACC_SGL_NR_MAX		256
 #define HISI_ACC_SGL_ALIGN_SIZE		64
-
-static int acc_sgl_sge_set(const char *val, const struct kernel_param *kp)
-{
-	int ret;
-	u32 n;
-
-	if (!val)
-		return -EINVAL;
-
-	ret = kstrtou32(val, 10, &n);
-	if (ret != 0 || n > HISI_ACC_SGL_SGE_NR_MAX || n == 0)
-		return -EINVAL;
-
-	return param_set_int(val, kp);
-}
-
-static const struct kernel_param_ops acc_sgl_sge_ops = {
-	.set = acc_sgl_sge_set,
-	.get = param_get_int,
-};
-
-static u32 acc_sgl_sge_nr = HISI_ACC_SGL_SGE_NR_DEF;
-module_param_cb(acc_sgl_sge_nr, &acc_sgl_sge_ops, &acc_sgl_sge_nr, 0444);
-MODULE_PARM_DESC(acc_sgl_sge_nr, "Number of sge in sgl(1-255)");
+#define HISI_ACC_MEM_BLOCK_NR		5
 
 struct acc_hw_sge {
 	dma_addr_t buf;
@@ -55,37 +31,91 @@ struct hisi_acc_hw_sgl {
 	struct acc_hw_sge sge_entries[];
 } __aligned(1);
 
+struct hisi_acc_sgl_pool {
+	struct mem_block {
+		struct hisi_acc_hw_sgl *sgl;
+		dma_addr_t sgl_dma;
+		size_t size;
+	} mem_block[HISI_ACC_MEM_BLOCK_NR];
+	u32 sgl_num_per_block;
+	u32 block_num;
+	u32 count;
+	u32 sge_nr;
+	size_t sgl_size;
+};
+
 /**
  * hisi_acc_create_sgl_pool() - Create a hw sgl pool.
  * @dev: The device which hw sgl pool belongs to.
- * @pool: Pointer of pool.
  * @count: Count of hisi_acc_hw_sgl in pool.
+ * @sge_nr: The count of sge in hw_sgl
  *
  * This function creates a hw sgl pool, after this user can get hw sgl memory
  * from it.
  */
-int hisi_acc_create_sgl_pool(struct device *dev,
-			     struct hisi_acc_sgl_pool *pool, u32 count)
+struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev,
+						   u32 count, u32 sge_nr)
 {
-	u32 sgl_size;
-	u32 size;
+	u32 sgl_size, block_size, sgl_num_per_block, block_num, remain_sgl = 0;
+	struct hisi_acc_sgl_pool *pool;
+	struct mem_block *block;
+	u32 i, j;
 
-	if (!dev || !pool || !count)
-		return -EINVAL;
+	if (!dev || !count || !sge_nr || sge_nr > HISI_ACC_SGL_SGE_NR_MAX)
+		return ERR_PTR(-EINVAL);
 
-	sgl_size = sizeof(struct acc_hw_sge) * acc_sgl_sge_nr +
+	sgl_size = sizeof(struct acc_hw_sge) * sge_nr +
 		   sizeof(struct hisi_acc_hw_sgl);
-	size = sgl_size * count;
+	block_size = PAGE_SIZE * (1 << (MAX_ORDER - 1));
+	sgl_num_per_block = block_size / sgl_size;
+	block_num = count / sgl_num_per_block;
+	remain_sgl = count % sgl_num_per_block;
+
+	if ((!remain_sgl && block_num > HISI_ACC_MEM_BLOCK_NR) ||
+	    (remain_sgl > 0 && block_num > HISI_ACC_MEM_BLOCK_NR - 1))
+		return ERR_PTR(-EINVAL);
+
+	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+	if (!pool)
+		return ERR_PTR(-ENOMEM);
+	block = pool->mem_block;
+
+	for (i = 0; i < block_num; i++) {
+		block[i].sgl = dma_alloc_coherent(dev, block_size,
+						  &block[i].sgl_dma,
+						  GFP_KERNEL);
+		if (!block[i].sgl)
+			goto err_free_mem;
+
+		block[i].size = block_size;
+	}
+
+	if (remain_sgl > 0) {
+		block[i].sgl = dma_alloc_coherent(dev, remain_sgl * sgl_size,
+						  &block[i].sgl_dma,
+						  GFP_KERNEL);
+		if (!block[i].sgl)
+			goto err_free_mem;
 
-	pool->sgl = dma_alloc_coherent(dev, size, &pool->sgl_dma, GFP_KERNEL);
-	if (!pool->sgl)
-		return -ENOMEM;
+		block[i].size = remain_sgl * sgl_size;
+	}
 
-	pool->size = size;
+	pool->sgl_num_per_block = sgl_num_per_block;
+	pool->block_num = remain_sgl ? block_num + 1 : block_num;
 	pool->count = count;
 	pool->sgl_size = sgl_size;
+	pool->sge_nr = sge_nr;
 
-	return 0;
+	return pool;
+
+err_free_mem:
+	for (j = 0; j < i; j++) {
+		dma_free_coherent(dev, block_size, block[j].sgl,
+				  block[j].sgl_dma);
+		memset(block + j, 0, sizeof(*block));
+	}
+	kfree(pool);
+	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL_GPL(hisi_acc_create_sgl_pool);
 
@@ -98,38 +128,57 @@ EXPORT_SYMBOL_GPL(hisi_acc_create_sgl_pool);
  */
 void hisi_acc_free_sgl_pool(struct device *dev, struct hisi_acc_sgl_pool *pool)
 {
-	dma_free_coherent(dev, pool->size, pool->sgl, pool->sgl_dma);
-	memset(pool, 0, sizeof(struct hisi_acc_sgl_pool));
+	struct mem_block *block;
+	int i;
+
+	if (!dev || !pool)
+		return;
+
+	block = pool->mem_block;
+
+	for (i = 0; i < pool->block_num; i++)
+		dma_free_coherent(dev, block[i].size, block[i].sgl,
+				  block[i].sgl_dma);
+
+	kfree(pool);
 }
 EXPORT_SYMBOL_GPL(hisi_acc_free_sgl_pool);
 
-struct hisi_acc_hw_sgl *acc_get_sgl(struct hisi_acc_sgl_pool *pool, u32 index,
-				    dma_addr_t *hw_sgl_dma)
+static struct hisi_acc_hw_sgl *acc_get_sgl(struct hisi_acc_sgl_pool *pool,
+					   u32 index, dma_addr_t *hw_sgl_dma)
 {
-	if (!pool || !hw_sgl_dma || index >= pool->count || !pool->sgl)
+	struct mem_block *block;
+	u32 block_index, offset;
+
+	if (!pool || !hw_sgl_dma || index >= pool->count)
 		return ERR_PTR(-EINVAL);
 
-	*hw_sgl_dma = pool->sgl_dma + pool->sgl_size * index;
-	return (void *)pool->sgl + pool->sgl_size * index;
-}
+	block = pool->mem_block;
+	block_index = index / pool->sgl_num_per_block;
+	offset = index % pool->sgl_num_per_block;
 
-void acc_put_sgl(struct hisi_acc_sgl_pool *pool, u32 index) {}
+	*hw_sgl_dma = block[block_index].sgl_dma + pool->sgl_size * offset;
+	return (void *)block[block_index].sgl + pool->sgl_size * offset;
+}
 
 static void sg_map_to_hw_sg(struct scatterlist *sgl,
 			    struct acc_hw_sge *hw_sge)
 {
-	hw_sge->buf = sgl->dma_address;
-	hw_sge->len = sgl->dma_length;
+	hw_sge->buf = sg_dma_address(sgl);
+	hw_sge->len = cpu_to_le32(sg_dma_len(sgl));
 }
 
 static void inc_hw_sgl_sge(struct hisi_acc_hw_sgl *hw_sgl)
 {
-	hw_sgl->entry_sum_in_sgl++;
+	u16 var = le16_to_cpu(hw_sgl->entry_sum_in_sgl);
+
+	var++;
+	hw_sgl->entry_sum_in_sgl = cpu_to_le16(var);
 }
 
 static void update_hw_sgl_sum_sge(struct hisi_acc_hw_sgl *hw_sgl, u16 sum)
 {
-	hw_sgl->entry_sum_in_chain = sum;
+	hw_sgl->entry_sum_in_chain = cpu_to_le16(sum);
 }
 
 /**
@@ -153,10 +202,13 @@ hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev,
 	dma_addr_t curr_sgl_dma = 0;
 	struct acc_hw_sge *curr_hw_sge;
 	struct scatterlist *sg;
-	int sg_n = sg_nents(sgl);
-	int i, ret;
+	int i, ret, sg_n;
 
-	if (!dev || !sgl || !pool || !hw_sgl_dma || sg_n > acc_sgl_sge_nr)
+	if (!dev || !sgl || !pool || !hw_sgl_dma)
+		return ERR_PTR(-EINVAL);
+
+	sg_n = sg_nents(sgl);
+	if (sg_n > pool->sge_nr)
 		return ERR_PTR(-EINVAL);
 
 	ret = dma_map_sg(dev, sgl, sg_n, DMA_BIDIRECTIONAL);
@@ -164,11 +216,12 @@ hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev,
 		return ERR_PTR(-EINVAL);
 
 	curr_hw_sgl = acc_get_sgl(pool, index, &curr_sgl_dma);
-	if (!curr_hw_sgl) {
-		ret = -ENOMEM;
-		goto err_unmap_sg;
+	if (IS_ERR(curr_hw_sgl)) {
+		dma_unmap_sg(dev, sgl, sg_n, DMA_BIDIRECTIONAL);
+		return ERR_PTR(-ENOMEM);
+
 	}
-	curr_hw_sgl->entry_length_in_sgl = acc_sgl_sge_nr;
+	curr_hw_sgl->entry_length_in_sgl = cpu_to_le16(pool->sge_nr);
 	curr_hw_sge = curr_hw_sgl->sge_entries;
 
 	for_each_sg(sgl, sg, sg_n, i) {
@@ -177,14 +230,10 @@ hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev,
 		curr_hw_sge++;
 	}
 
-	update_hw_sgl_sum_sge(curr_hw_sgl, acc_sgl_sge_nr);
+	update_hw_sgl_sum_sge(curr_hw_sgl, pool->sge_nr);
 	*hw_sgl_dma = curr_sgl_dma;
 
 	return curr_hw_sgl;
-
-err_unmap_sg:
-	dma_unmap_sg(dev, sgl, sg_n, DMA_BIDIRECTIONAL);
-	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(hisi_acc_sg_buf_map_to_hw_sgl);
 
@@ -201,6 +250,9 @@ EXPORT_SYMBOL_GPL(hisi_acc_sg_buf_map_to_hw_sgl);
 void hisi_acc_sg_buf_unmap(struct device *dev, struct scatterlist *sgl,
 			   struct hisi_acc_hw_sgl *hw_sgl)
 {
+	if (!dev || !sgl || !hw_sgl)
+		return;
+
 	dma_unmap_sg(dev, sgl, sg_nents(sgl), DMA_BIDIRECTIONAL);
 
 	hw_sgl->entry_sum_in_chain = 0;
diff --git a/drivers/crypto/hisilicon/sgl.h b/drivers/crypto/hisilicon/sgl.h
deleted file mode 100644
index 3ac8871c7acf..000000000000
--- a/drivers/crypto/hisilicon/sgl.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (c) 2019 HiSilicon Limited. */
-#ifndef HISI_ACC_SGL_H
-#define HISI_ACC_SGL_H
-
-struct hisi_acc_sgl_pool {
-	struct hisi_acc_hw_sgl *sgl;
-	dma_addr_t sgl_dma;
-	size_t size;
-	u32 count;
-	size_t sgl_size;
-};
-
-struct hisi_acc_hw_sgl *
-hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev,
-			      struct scatterlist *sgl,
-			      struct hisi_acc_sgl_pool *pool,
-			      u32 index, dma_addr_t *hw_sgl_dma);
-void hisi_acc_sg_buf_unmap(struct device *dev, struct scatterlist *sgl,
-			   struct hisi_acc_hw_sgl *hw_sgl);
-int hisi_acc_create_sgl_pool(struct device *dev, struct hisi_acc_sgl_pool *pool,
-			     u32 count);
-void hisi_acc_free_sgl_pool(struct device *dev, struct hisi_acc_sgl_pool *pool);
-#endif
diff --git a/drivers/crypto/hisilicon/zip/zip.h b/drivers/crypto/hisilicon/zip/zip.h
index ffb00d987d02..79fc4dd3fe00 100644
--- a/drivers/crypto/hisilicon/zip/zip.h
+++ b/drivers/crypto/hisilicon/zip/zip.h
@@ -8,7 +8,6 @@
 
 #include <linux/list.h>
 #include "../qm.h"
-#include "../sgl.h"
 
 /* hisi_zip_sqe dw3 */
 #define HZIP_BD_STATUS_M			GENMASK(7, 0)
diff --git a/drivers/crypto/hisilicon/zip/zip_crypto.c b/drivers/crypto/hisilicon/zip/zip_crypto.c
index 59023545a1c4..795428c1d07e 100644
--- a/drivers/crypto/hisilicon/zip/zip_crypto.c
+++ b/drivers/crypto/hisilicon/zip/zip_crypto.c
@@ -22,6 +22,7 @@
 #define HZIP_CTX_Q_NUM				2
 #define HZIP_GZIP_HEAD_BUF			256
 #define HZIP_ALG_PRIORITY			300
+#define HZIP_SGL_SGE_NR				10
 
 static const u8 zlib_head[HZIP_ZLIB_HEAD_SIZE] = {0x78, 0x9c};
 static const u8 gzip_head[HZIP_GZIP_HEAD_SIZE] = {0x1f, 0x8b, 0x08, 0x0, 0x0,
@@ -41,7 +42,7 @@ enum hisi_zip_alg_type {
 
 #define TO_HEAD(req_type)						\
 	(((req_type) == HZIP_ALG_TYPE_ZLIB) ? zlib_head :		\
-	 ((req_type) == HZIP_ALG_TYPE_GZIP) ? gzip_head : 0)		\
+	 ((req_type) == HZIP_ALG_TYPE_GZIP) ? gzip_head : NULL)		\
 
 struct hisi_zip_req {
 	struct acomp_req *req;
@@ -67,7 +68,7 @@ struct hisi_zip_qp_ctx {
 	struct hisi_qp *qp;
 	struct hisi_zip_sqe zip_sqe;
 	struct hisi_zip_req_q req_q;
-	struct hisi_acc_sgl_pool sgl_pool;
+	struct hisi_acc_sgl_pool *sgl_pool;
 	struct hisi_zip *zip_dev;
 	struct hisi_zip_ctx *ctx;
 };
@@ -78,6 +79,30 @@ struct hisi_zip_ctx {
 	struct hisi_zip_qp_ctx qp_ctx[HZIP_CTX_Q_NUM];
 };
 
+static int sgl_sge_nr_set(const char *val, const struct kernel_param *kp)
+{
+	int ret;
+	u16 n;
+
+	if (!val)
+		return -EINVAL;
+
+	ret = kstrtou16(val, 10, &n);
+	if (ret || n == 0 || n > HISI_ACC_SGL_SGE_NR_MAX)
+		return -EINVAL;
+
+	return param_set_int(val, kp);
+}
+
+static const struct kernel_param_ops sgl_sge_nr_ops = {
+	.set = sgl_sge_nr_set,
+	.get = param_get_int,
+};
+
+static u16 sgl_sge_nr = HZIP_SGL_SGE_NR;
+module_param_cb(sgl_sge_nr, &sgl_sge_nr_ops, &sgl_sge_nr, 0444);
+MODULE_PARM_DESC(sgl_sge_nr, "Number of sge in sgl(1-255)");
+
 static void hisi_zip_config_buf_type(struct hisi_zip_sqe *sqe, u8 buf_type)
 {
 	u32 val;
@@ -265,14 +290,15 @@ static void hisi_zip_release_req_q(struct hisi_zip_ctx *ctx)
 static int hisi_zip_create_sgl_pool(struct hisi_zip_ctx *ctx)
 {
 	struct hisi_zip_qp_ctx *tmp;
-	int i, ret;
+	struct device *dev;
+	int i;
 
 	for (i = 0; i < HZIP_CTX_Q_NUM; i++) {
 		tmp = &ctx->qp_ctx[i];
-		ret = hisi_acc_create_sgl_pool(&tmp->qp->qm->pdev->dev,
-					       &tmp->sgl_pool,
-					       QM_Q_DEPTH << 1);
-		if (ret < 0) {
+		dev = &tmp->qp->qm->pdev->dev;
+		tmp->sgl_pool = hisi_acc_create_sgl_pool(dev, QM_Q_DEPTH << 1,
+							 sgl_sge_nr);
+		if (IS_ERR(tmp->sgl_pool)) {
 			if (i == 1)
 				goto err_free_sgl_pool0;
 			return -ENOMEM;
@@ -283,7 +309,7 @@ static int hisi_zip_create_sgl_pool(struct hisi_zip_ctx *ctx)
 
 err_free_sgl_pool0:
 	hisi_acc_free_sgl_pool(&ctx->qp_ctx[QPC_COMP].qp->qm->pdev->dev,
-			       &ctx->qp_ctx[QPC_COMP].sgl_pool);
+			       ctx->qp_ctx[QPC_COMP].sgl_pool);
 	return -ENOMEM;
 }
 
@@ -293,7 +319,7 @@ static void hisi_zip_release_sgl_pool(struct hisi_zip_ctx *ctx)
 
 	for (i = 0; i < HZIP_CTX_Q_NUM; i++)
 		hisi_acc_free_sgl_pool(&ctx->qp_ctx[i].qp->qm->pdev->dev,
-				       &ctx->qp_ctx[i].sgl_pool);
+				       ctx->qp_ctx[i].sgl_pool);
 }
 
 static void hisi_zip_remove_req(struct hisi_zip_qp_ctx *qp_ctx,
@@ -512,7 +538,7 @@ static int hisi_zip_do_work(struct hisi_zip_req *req,
 	struct hisi_zip_sqe *zip_sqe = &qp_ctx->zip_sqe;
 	struct hisi_qp *qp = qp_ctx->qp;
 	struct device *dev = &qp->qm->pdev->dev;
-	struct hisi_acc_sgl_pool *pool = &qp_ctx->sgl_pool;
+	struct hisi_acc_sgl_pool *pool = qp_ctx->sgl_pool;
 	dma_addr_t input;
 	dma_addr_t output;
 	int ret;
diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c
index 1b2ee96c888d..e1bab1a91333 100644
--- a/drivers/crypto/hisilicon/zip/zip_main.c
+++ b/drivers/crypto/hisilicon/zip/zip_main.c
@@ -79,47 +79,80 @@
 #define HZIP_SOFT_CTRL_CNT_CLR_CE	0x301000
 #define SOFT_CTRL_CNT_CLR_CE_BIT	BIT(0)
 
-#define HZIP_NUMA_DISTANCE		100
 #define HZIP_BUF_SIZE			22
 
 static const char hisi_zip_name[] = "hisi_zip";
 static struct dentry *hzip_debugfs_root;
-LIST_HEAD(hisi_zip_list);
-DEFINE_MUTEX(hisi_zip_list_lock);
+static LIST_HEAD(hisi_zip_list);
+static DEFINE_MUTEX(hisi_zip_list_lock);
 
-#ifdef CONFIG_NUMA
-static struct hisi_zip *find_zip_device_numa(int node)
+struct hisi_zip_resource {
+	struct hisi_zip *hzip;
+	int distance;
+	struct list_head list;
+};
+
+static void free_list(struct list_head *head)
 {
-	struct hisi_zip *zip = NULL;
-	struct hisi_zip *hisi_zip;
-	int min_distance = HZIP_NUMA_DISTANCE;
-	struct device *dev;
+	struct hisi_zip_resource *res, *tmp;
 
-	list_for_each_entry(hisi_zip, &hisi_zip_list, list) {
-		dev = &hisi_zip->qm.pdev->dev;
-		if (node_distance(dev->numa_node, node) < min_distance) {
-			zip = hisi_zip;
-			min_distance = node_distance(dev->numa_node, node);
-		}
+	list_for_each_entry_safe(res, tmp, head, list) {
+		list_del(&res->list);
+		kfree(res);
 	}
-
-	return zip;
 }
-#endif
 
 struct hisi_zip *find_zip_device(int node)
 {
-	struct hisi_zip *zip = NULL;
+	struct hisi_zip_resource *res, *tmp;
+	struct hisi_zip *ret = NULL;
+	struct hisi_zip *hisi_zip;
+	struct list_head *n;
+	struct device *dev;
+	LIST_HEAD(head);
 
 	mutex_lock(&hisi_zip_list_lock);
-#ifdef CONFIG_NUMA
-	zip = find_zip_device_numa(node);
-#else
-	zip = list_first_entry(&hisi_zip_list, struct hisi_zip, list);
-#endif
+
+	if (IS_ENABLED(CONFIG_NUMA)) {
+		list_for_each_entry(hisi_zip, &hisi_zip_list, list) {
+			res = kzalloc(sizeof(*res), GFP_KERNEL);
+			if (!res)
+				goto err;
+
+			dev = &hisi_zip->qm.pdev->dev;
+			res->hzip = hisi_zip;
+			res->distance = node_distance(dev_to_node(dev), node);
+
+			n = &head;
+			list_for_each_entry(tmp, &head, list) {
+				if (res->distance < tmp->distance) {
+					n = &tmp->list;
+					break;
+				}
+			}
+			list_add_tail(&res->list, n);
+		}
+
+		list_for_each_entry(tmp, &head, list) {
+			if (hisi_qm_get_free_qp_num(&tmp->hzip->qm)) {
+				ret = tmp->hzip;
+				break;
+			}
+		}
+
+		free_list(&head);
+	} else {
+		ret = list_first_entry(&hisi_zip_list, struct hisi_zip, list);
+	}
+
 	mutex_unlock(&hisi_zip_list_lock);
 
-	return zip;
+	return ret;
+
+err:
+	free_list(&head);
+	mutex_unlock(&hisi_zip_list_lock);
+	return NULL;
 }
 
 struct hisi_zip_hw_error {
@@ -267,6 +300,10 @@ MODULE_PARM_DESC(pf_q_num, "Number of queues in PF(v1 1-4096, v2 1-1024)");
 static int uacce_mode;
 module_param(uacce_mode, int, 0);
 
+static u32 vfs_num;
+module_param(vfs_num, uint, 0444);
+MODULE_PARM_DESC(vfs_num, "Number of VFs to enable(1-63)");
+
 static const struct pci_device_id hisi_zip_dev_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_ZIP_PF) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_ZIP_VF) },
@@ -335,8 +372,7 @@ static void hisi_zip_hw_error_set_state(struct hisi_zip *hisi_zip, bool state)
 
 	if (qm->ver == QM_HW_V1) {
 		writel(HZIP_CORE_INT_DISABLE, qm->io_base + HZIP_CORE_INT_MASK);
-		dev_info(&qm->pdev->dev, "ZIP v%d does not support hw error handle\n",
-			 qm->ver);
+		dev_info(&qm->pdev->dev, "Does not support hw error handle\n");
 		return;
 	}
 
@@ -511,7 +547,7 @@ static int hisi_zip_core_debug_init(struct hisi_zip_ctrl *ctrl)
 	struct hisi_qm *qm = &hisi_zip->qm;
 	struct device *dev = &qm->pdev->dev;
 	struct debugfs_regset32 *regset;
-	struct dentry *tmp_d, *tmp;
+	struct dentry *tmp_d;
 	char buf[HZIP_BUF_SIZE];
 	int i;
 
@@ -521,10 +557,6 @@ static int hisi_zip_core_debug_init(struct hisi_zip_ctrl *ctrl)
 		else
 			sprintf(buf, "decomp_core%d", i - HZIP_COMP_CORE_NUM);
 
-		tmp_d = debugfs_create_dir(buf, ctrl->debug_root);
-		if (!tmp_d)
-			return -ENOENT;
-
 		regset = devm_kzalloc(dev, sizeof(*regset), GFP_KERNEL);
 		if (!regset)
 			return -ENOENT;
@@ -533,9 +565,8 @@ static int hisi_zip_core_debug_init(struct hisi_zip_ctrl *ctrl)
 		regset->nregs = ARRAY_SIZE(hzip_dfx_regs);
 		regset->base = qm->io_base + core_offsets[i];
 
-		tmp = debugfs_create_regset32("regs", 0444, tmp_d, regset);
-		if (!tmp)
-			return -ENOENT;
+		tmp_d = debugfs_create_dir(buf, ctrl->debug_root);
+		debugfs_create_regset32("regs", 0444, tmp_d, regset);
 	}
 
 	return 0;
@@ -543,7 +574,6 @@ static int hisi_zip_core_debug_init(struct hisi_zip_ctrl *ctrl)
 
 static int hisi_zip_ctrl_debug_init(struct hisi_zip_ctrl *ctrl)
 {
-	struct dentry *tmp;
 	int i;
 
 	for (i = HZIP_CURRENT_QM; i < HZIP_DEBUG_FILE_NUM; i++) {
@@ -551,11 +581,9 @@ static int hisi_zip_ctrl_debug_init(struct hisi_zip_ctrl *ctrl)
 		ctrl->files[i].ctrl = ctrl;
 		ctrl->files[i].index = i;
 
-		tmp = debugfs_create_file(ctrl_debug_file_name[i], 0600,
-					  ctrl->debug_root, ctrl->files + i,
-					  &ctrl_debug_fops);
-		if (!tmp)
-			return -ENOENT;
+		debugfs_create_file(ctrl_debug_file_name[i], 0600,
+				    ctrl->debug_root, ctrl->files + i,
+				    &ctrl_debug_fops);
 	}
 
 	return hisi_zip_core_debug_init(ctrl);
@@ -569,8 +597,6 @@ static int hisi_zip_debugfs_init(struct hisi_zip *hisi_zip)
 	int ret;
 
 	dev_d = debugfs_create_dir(dev_name(dev), hzip_debugfs_root);
-	if (!dev_d)
-		return -ENOENT;
 
 	qm->debug.debug_root = dev_d;
 	ret = hisi_qm_debug_init(qm);
@@ -652,90 +678,6 @@ static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip)
 	return 0;
 }
 
-static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id)
-{
-	struct hisi_zip *hisi_zip;
-	enum qm_hw_ver rev_id;
-	struct hisi_qm *qm;
-	int ret;
-
-	rev_id = hisi_qm_get_hw_version(pdev);
-	if (rev_id == QM_HW_UNKNOWN)
-		return -EINVAL;
-
-	hisi_zip = devm_kzalloc(&pdev->dev, sizeof(*hisi_zip), GFP_KERNEL);
-	if (!hisi_zip)
-		return -ENOMEM;
-	pci_set_drvdata(pdev, hisi_zip);
-
-	qm = &hisi_zip->qm;
-	qm->pdev = pdev;
-	qm->ver = rev_id;
-
-	qm->sqe_size = HZIP_SQE_SIZE;
-	qm->dev_name = hisi_zip_name;
-	qm->fun_type = (pdev->device == PCI_DEVICE_ID_ZIP_PF) ? QM_HW_PF :
-								QM_HW_VF;
-	switch (uacce_mode) {
-	case 0:
-		qm->use_dma_api = true;
-		break;
-	case 1:
-		qm->use_dma_api = false;
-		break;
-	case 2:
-		qm->use_dma_api = true;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	ret = hisi_qm_init(qm);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to init qm!\n");
-		return ret;
-	}
-
-	if (qm->fun_type == QM_HW_PF) {
-		ret = hisi_zip_pf_probe_init(hisi_zip);
-		if (ret)
-			return ret;
-
-		qm->qp_base = HZIP_PF_DEF_Q_BASE;
-		qm->qp_num = pf_q_num;
-	} else if (qm->fun_type == QM_HW_VF) {
-		/*
-		 * have no way to get qm configure in VM in v1 hardware,
-		 * so currently force PF to uses HZIP_PF_DEF_Q_NUM, and force
-		 * to trigger only one VF in v1 hardware.
-		 *
-		 * v2 hardware has no such problem.
-		 */
-		if (qm->ver == QM_HW_V1) {
-			qm->qp_base = HZIP_PF_DEF_Q_NUM;
-			qm->qp_num = HZIP_QUEUE_NUM_V1 - HZIP_PF_DEF_Q_NUM;
-		} else if (qm->ver == QM_HW_V2)
-			/* v2 starts to support get vft by mailbox */
-			hisi_qm_get_vft(qm, &qm->qp_base, &qm->qp_num);
-	}
-
-	ret = hisi_qm_start(qm);
-	if (ret)
-		goto err_qm_uninit;
-
-	ret = hisi_zip_debugfs_init(hisi_zip);
-	if (ret)
-		dev_err(&pdev->dev, "Failed to init debugfs (%d)!\n", ret);
-
-	hisi_zip_add_to_list(hisi_zip);
-
-	return 0;
-
-err_qm_uninit:
-	hisi_qm_uninit(qm);
-	return ret;
-}
-
 /* Currently we only support equal assignment */
 static int hisi_zip_vf_q_assign(struct hisi_zip *hisi_zip, int num_vfs)
 {
@@ -832,6 +774,100 @@ static int hisi_zip_sriov_disable(struct pci_dev *pdev)
 	return hisi_zip_clear_vft_config(hisi_zip);
 }
 
+static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct hisi_zip *hisi_zip;
+	enum qm_hw_ver rev_id;
+	struct hisi_qm *qm;
+	int ret;
+
+	rev_id = hisi_qm_get_hw_version(pdev);
+	if (rev_id == QM_HW_UNKNOWN)
+		return -EINVAL;
+
+	hisi_zip = devm_kzalloc(&pdev->dev, sizeof(*hisi_zip), GFP_KERNEL);
+	if (!hisi_zip)
+		return -ENOMEM;
+	pci_set_drvdata(pdev, hisi_zip);
+
+	qm = &hisi_zip->qm;
+	qm->pdev = pdev;
+	qm->ver = rev_id;
+
+	qm->sqe_size = HZIP_SQE_SIZE;
+	qm->dev_name = hisi_zip_name;
+	qm->fun_type = (pdev->device == PCI_DEVICE_ID_ZIP_PF) ? QM_HW_PF :
+								QM_HW_VF;
+	switch (uacce_mode) {
+	case 0:
+		qm->use_dma_api = true;
+		break;
+	case 1:
+		qm->use_dma_api = false;
+		break;
+	case 2:
+		qm->use_dma_api = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = hisi_qm_init(qm);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to init qm!\n");
+		return ret;
+	}
+
+	if (qm->fun_type == QM_HW_PF) {
+		ret = hisi_zip_pf_probe_init(hisi_zip);
+		if (ret)
+			return ret;
+
+		qm->qp_base = HZIP_PF_DEF_Q_BASE;
+		qm->qp_num = pf_q_num;
+	} else if (qm->fun_type == QM_HW_VF) {
+		/*
+		 * have no way to get qm configure in VM in v1 hardware,
+		 * so currently force PF to uses HZIP_PF_DEF_Q_NUM, and force
+		 * to trigger only one VF in v1 hardware.
+		 *
+		 * v2 hardware has no such problem.
+		 */
+		if (qm->ver == QM_HW_V1) {
+			qm->qp_base = HZIP_PF_DEF_Q_NUM;
+			qm->qp_num = HZIP_QUEUE_NUM_V1 - HZIP_PF_DEF_Q_NUM;
+		} else if (qm->ver == QM_HW_V2)
+			/* v2 starts to support get vft by mailbox */
+			hisi_qm_get_vft(qm, &qm->qp_base, &qm->qp_num);
+	}
+
+	ret = hisi_qm_start(qm);
+	if (ret)
+		goto err_qm_uninit;
+
+	ret = hisi_zip_debugfs_init(hisi_zip);
+	if (ret)
+		dev_err(&pdev->dev, "Failed to init debugfs (%d)!\n", ret);
+
+	hisi_zip_add_to_list(hisi_zip);
+
+	if (qm->fun_type == QM_HW_PF && vfs_num > 0) {
+		ret = hisi_zip_sriov_enable(pdev, vfs_num);
+		if (ret < 0)
+			goto err_remove_from_list;
+	}
+
+	return 0;
+
+err_remove_from_list:
+	hisi_zip_remove_from_list(hisi_zip);
+	hisi_zip_debugfs_exit(hisi_zip);
+	hisi_qm_stop(qm);
+err_qm_uninit:
+	hisi_qm_uninit(qm);
+	return ret;
+}
+
 static int hisi_zip_sriov_configure(struct pci_dev *pdev, int num_vfs)
 {
 	if (num_vfs == 0)
@@ -945,7 +981,7 @@ static struct pci_driver hisi_zip_pci_driver = {
 	.probe			= hisi_zip_probe,
 	.remove			= hisi_zip_remove,
 	.sriov_configure	= IS_ENABLED(CONFIG_PCI_IOV) ?
-					hisi_zip_sriov_configure : 0,
+					hisi_zip_sriov_configure : NULL,
 	.err_handler		= &hisi_zip_err_handler,
 };
 
@@ -955,8 +991,6 @@ static void hisi_zip_register_debugfs(void)
 		return;
 
 	hzip_debugfs_root = debugfs_create_dir("hisi_zip", NULL);
-	if (IS_ERR_OR_NULL(hzip_debugfs_root))
-		hzip_debugfs_root = NULL;
 }
 
 static void hisi_zip_unregister_debugfs(void)
diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 4ab1bde8dd9b..64894d8b442a 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -75,9 +75,9 @@ static void eip197_trc_cache_banksel(struct safexcel_crypto_priv *priv,
 }
 
 static u32 eip197_trc_cache_probe(struct safexcel_crypto_priv *priv,
-				  int maxbanks, u32 probemask)
+				  int maxbanks, u32 probemask, u32 stride)
 {
-	u32 val, addrhi, addrlo, addrmid;
+	u32 val, addrhi, addrlo, addrmid, addralias, delta, marker;
 	int actbank;
 
 	/*
@@ -87,32 +87,37 @@ static u32 eip197_trc_cache_probe(struct safexcel_crypto_priv *priv,
 	addrhi = 1 << (16 + maxbanks);
 	addrlo = 0;
 	actbank = min(maxbanks - 1, 0);
-	while ((addrhi - addrlo) > 32) {
+	while ((addrhi - addrlo) > stride) {
 		/* write marker to lowest address in top half */
 		addrmid = (addrhi + addrlo) >> 1;
+		marker = (addrmid ^ 0xabadbabe) & probemask; /* Unique */
 		eip197_trc_cache_banksel(priv, addrmid, &actbank);
-		writel((addrmid | (addrlo << 16)) & probemask,
+		writel(marker,
 			priv->base + EIP197_CLASSIFICATION_RAMS +
 			(addrmid & 0xffff));
 
-		/* write marker to lowest address in bottom half */
-		eip197_trc_cache_banksel(priv, addrlo, &actbank);
-		writel((addrlo | (addrhi << 16)) & probemask,
-			priv->base + EIP197_CLASSIFICATION_RAMS +
-			(addrlo & 0xffff));
+		/* write invalid markers to possible aliases */
+		delta = 1 << __fls(addrmid);
+		while (delta >= stride) {
+			addralias = addrmid - delta;
+			eip197_trc_cache_banksel(priv, addralias, &actbank);
+			writel(~marker,
+			       priv->base + EIP197_CLASSIFICATION_RAMS +
+			       (addralias & 0xffff));
+			delta >>= 1;
+		}
 
 		/* read back marker from top half */
 		eip197_trc_cache_banksel(priv, addrmid, &actbank);
 		val = readl(priv->base + EIP197_CLASSIFICATION_RAMS +
 			    (addrmid & 0xffff));
 
-		if (val == ((addrmid | (addrlo << 16)) & probemask)) {
+		if ((val & probemask) == marker)
 			/* read back correct, continue with top half */
 			addrlo = addrmid;
-		} else {
+		else
 			/* not read back correct, continue with bottom half */
 			addrhi = addrmid;
-		}
 	}
 	return addrhi;
 }
@@ -150,7 +155,7 @@ static void eip197_trc_cache_clear(struct safexcel_crypto_priv *priv,
 		       htable_offset + i * sizeof(u32));
 }
 
-static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
+static int eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
 {
 	u32 val, dsize, asize;
 	int cs_rc_max, cs_ht_wc, cs_trc_rec_wc, cs_trc_lg_rec_wc;
@@ -183,7 +188,7 @@ static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
 	writel(val, priv->base + EIP197_TRC_PARAMS);
 
 	/* Probed data RAM size in bytes */
-	dsize = eip197_trc_cache_probe(priv, maxbanks, 0xffffffff);
+	dsize = eip197_trc_cache_probe(priv, maxbanks, 0xffffffff, 32);
 
 	/*
 	 * Now probe the administration RAM size pretty much the same way
@@ -196,11 +201,18 @@ static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
 	writel(val, priv->base + EIP197_TRC_PARAMS);
 
 	/* Probed admin RAM size in admin words */
-	asize = eip197_trc_cache_probe(priv, 0, 0xbfffffff) >> 4;
+	asize = eip197_trc_cache_probe(priv, 0, 0x3fffffff, 16) >> 4;
 
 	/* Clear any ECC errors detected while probing! */
 	writel(0, priv->base + EIP197_TRC_ECCCTRL);
 
+	/* Sanity check probing results */
+	if (dsize < EIP197_MIN_DSIZE || asize < EIP197_MIN_ASIZE) {
+		dev_err(priv->dev, "Record cache probing failed (%d,%d).",
+			dsize, asize);
+		return -ENODEV;
+	}
+
 	/*
 	 * Determine optimal configuration from RAM sizes
 	 * Note that we assume that the physical RAM configuration is sane
@@ -221,9 +233,9 @@ static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
 	/* Step #3: Determine log2 of hash table size */
 	cs_ht_sz = __fls(asize - cs_rc_max) - 2;
 	/* Step #4: determine current size of hash table in dwords */
-	cs_ht_wc = 16<<cs_ht_sz; /* dwords, not admin words */
+	cs_ht_wc = 16 << cs_ht_sz; /* dwords, not admin words */
 	/* Step #5: add back excess words and see if we can fit more records */
-	cs_rc_max = min_t(uint, cs_rc_abs_max, asize - (cs_ht_wc >> 4));
+	cs_rc_max = min_t(uint, cs_rc_abs_max, asize - (cs_ht_wc >> 2));
 
 	/* Clear the cache RAMs */
 	eip197_trc_cache_clear(priv, cs_rc_max, cs_ht_wc);
@@ -251,6 +263,7 @@ static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
 
 	dev_info(priv->dev, "TRC init: %dd,%da (%dr,%dh)\n",
 		 dsize, asize, cs_rc_max, cs_ht_wc + cs_ht_wc);
+	return 0;
 }
 
 static void eip197_init_firmware(struct safexcel_crypto_priv *priv)
@@ -298,13 +311,14 @@ static void eip197_init_firmware(struct safexcel_crypto_priv *priv)
 static int eip197_write_firmware(struct safexcel_crypto_priv *priv,
 				  const struct firmware *fw)
 {
-	const u32 *data = (const u32 *)fw->data;
+	const __be32 *data = (const __be32 *)fw->data;
 	int i;
 
 	/* Write the firmware */
 	for (i = 0; i < fw->size / sizeof(u32); i++)
 		writel(be32_to_cpu(data[i]),
-		       priv->base + EIP197_CLASSIFICATION_RAMS + i * sizeof(u32));
+		       priv->base + EIP197_CLASSIFICATION_RAMS +
+		       i * sizeof(__be32));
 
 	/* Exclude final 2 NOPs from size */
 	return i - EIP197_FW_TERMINAL_NOPS;
@@ -471,6 +485,14 @@ static int safexcel_hw_setup_cdesc_rings(struct safexcel_crypto_priv *priv)
 		cd_fetch_cnt = ((1 << priv->hwconfig.hwcfsize) /
 				cd_size_rnd) - 1;
 	}
+	/*
+	 * Since we're using command desc's way larger than formally specified,
+	 * we need to check whether we can fit even 1 for low-end EIP196's!
+	 */
+	if (!cd_fetch_cnt) {
+		dev_err(priv->dev, "Unable to fit even 1 command desc!\n");
+		return -ENODEV;
+	}
 
 	for (i = 0; i < priv->config.rings; i++) {
 		/* ring base address */
@@ -479,12 +501,12 @@ static int safexcel_hw_setup_cdesc_rings(struct safexcel_crypto_priv *priv)
 		writel(upper_32_bits(priv->ring[i].cdr.base_dma),
 		       EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_RING_BASE_ADDR_HI);
 
-		writel(EIP197_xDR_DESC_MODE_64BIT | (priv->config.cd_offset << 16) |
+		writel(EIP197_xDR_DESC_MODE_64BIT | (priv->config.cd_offset << 14) |
 		       priv->config.cd_size,
 		       EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_DESC_SIZE);
 		writel(((cd_fetch_cnt *
 			 (cd_size_rnd << priv->hwconfig.hwdataw)) << 16) |
-		       (cd_fetch_cnt * priv->config.cd_offset),
+		       (cd_fetch_cnt * (priv->config.cd_offset / sizeof(u32))),
 		       EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_CFG);
 
 		/* Configure DMA tx control */
@@ -527,13 +549,13 @@ static int safexcel_hw_setup_rdesc_rings(struct safexcel_crypto_priv *priv)
 		writel(upper_32_bits(priv->ring[i].rdr.base_dma),
 		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_RING_BASE_ADDR_HI);
 
-		writel(EIP197_xDR_DESC_MODE_64BIT | (priv->config.rd_offset << 16) |
+		writel(EIP197_xDR_DESC_MODE_64BIT | (priv->config.rd_offset << 14) |
 		       priv->config.rd_size,
 		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_DESC_SIZE);
 
 		writel(((rd_fetch_cnt *
 			 (rd_size_rnd << priv->hwconfig.hwdataw)) << 16) |
-		       (rd_fetch_cnt * priv->config.rd_offset),
+		       (rd_fetch_cnt * (priv->config.rd_offset / sizeof(u32))),
 		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_CFG);
 
 		/* Configure DMA tx control */
@@ -559,7 +581,7 @@ static int safexcel_hw_setup_rdesc_rings(struct safexcel_crypto_priv *priv)
 static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 {
 	u32 val;
-	int i, ret, pe;
+	int i, ret, pe, opbuflo, opbufhi;
 
 	dev_dbg(priv->dev, "HW init: using %d pipe(s) and %d ring(s)\n",
 		priv->config.pes, priv->config.rings);
@@ -595,8 +617,8 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 		writel(EIP197_DxE_THR_CTRL_RESET_PE,
 		       EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL(pe));
 
-		if (priv->flags & SAFEXCEL_HW_EIP197)
-			/* Reset HIA input interface arbiter (EIP197 only) */
+		if (priv->flags & EIP197_PE_ARB)
+			/* Reset HIA input interface arbiter (if present) */
 			writel(EIP197_HIA_RA_PE_CTRL_RESET,
 			       EIP197_HIA_AIC(priv) + EIP197_HIA_RA_PE_CTRL(pe));
 
@@ -639,9 +661,16 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 			;
 
 		/* DMA transfer size to use */
+		if (priv->hwconfig.hwnumpes > 4) {
+			opbuflo = 9;
+			opbufhi = 10;
+		} else {
+			opbuflo = 7;
+			opbufhi = 8;
+		}
 		val = EIP197_HIA_DSE_CFG_DIS_DEBUG;
-		val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(7) |
-		       EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(8);
+		val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(opbuflo) |
+		       EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(opbufhi);
 		val |= EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(WR_CACHE_3BITS);
 		val |= EIP197_HIA_DSE_CFG_ALWAYS_BUFFERABLE;
 		/* FIXME: instability issues can occur for EIP97 but disabling
@@ -655,8 +684,8 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 		writel(0, EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL(pe));
 
 		/* Configure the procesing engine thresholds */
-		writel(EIP197_PE_OUT_DBUF_THRES_MIN(7) |
-		       EIP197_PE_OUT_DBUF_THRES_MAX(8),
+		writel(EIP197_PE_OUT_DBUF_THRES_MIN(opbuflo) |
+		       EIP197_PE_OUT_DBUF_THRES_MAX(opbufhi),
 		       EIP197_PE(priv) + EIP197_PE_OUT_DBUF_THRES(pe));
 
 		/* Processing Engine configuration */
@@ -696,7 +725,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 		writel(0,
 		       EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_PROC_PNTR);
 
-		writel((EIP197_DEFAULT_RING_SIZE * priv->config.cd_offset) << 2,
+		writel((EIP197_DEFAULT_RING_SIZE * priv->config.cd_offset),
 		       EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_RING_SIZE);
 	}
 
@@ -719,7 +748,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_PROC_PNTR);
 
 		/* Ring size */
-		writel((EIP197_DEFAULT_RING_SIZE * priv->config.rd_offset) << 2,
+		writel((EIP197_DEFAULT_RING_SIZE * priv->config.rd_offset),
 		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_RING_SIZE);
 	}
 
@@ -736,19 +765,28 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	/* Clear any HIA interrupt */
 	writel(GENMASK(30, 20), EIP197_HIA_AIC_G(priv) + EIP197_HIA_AIC_G_ACK);
 
-	if (priv->flags & SAFEXCEL_HW_EIP197) {
-		eip197_trc_cache_init(priv);
-		priv->flags |= EIP197_TRC_CACHE;
+	if (priv->flags & EIP197_SIMPLE_TRC) {
+		writel(EIP197_STRC_CONFIG_INIT |
+		       EIP197_STRC_CONFIG_LARGE_REC(EIP197_CS_TRC_REC_WC) |
+		       EIP197_STRC_CONFIG_SMALL_REC(EIP197_CS_TRC_REC_WC),
+		       priv->base + EIP197_STRC_CONFIG);
+		writel(EIP197_PE_EIP96_TOKEN_CTRL2_CTX_DONE,
+		       EIP197_PE(priv) + EIP197_PE_EIP96_TOKEN_CTRL2(0));
+	} else if (priv->flags & SAFEXCEL_HW_EIP197) {
+		ret = eip197_trc_cache_init(priv);
+		if (ret)
+			return ret;
+	}
 
+	if (priv->flags & EIP197_ICE) {
 		ret = eip197_load_firmwares(priv);
 		if (ret)
 			return ret;
 	}
 
-	safexcel_hw_setup_cdesc_rings(priv);
-	safexcel_hw_setup_rdesc_rings(priv);
-
-	return 0;
+	return safexcel_hw_setup_cdesc_rings(priv) ?:
+	       safexcel_hw_setup_rdesc_rings(priv) ?:
+	       0;
 }
 
 /* Called with ring's lock taken */
@@ -836,20 +874,24 @@ finalize:
 	spin_unlock_bh(&priv->ring[ring].lock);
 
 	/* let the RDR know we have pending descriptors */
-	writel((rdesc * priv->config.rd_offset) << 2,
+	writel((rdesc * priv->config.rd_offset),
 	       EIP197_HIA_RDR(priv, ring) + EIP197_HIA_xDR_PREP_COUNT);
 
 	/* let the CDR know we have pending descriptors */
-	writel((cdesc * priv->config.cd_offset) << 2,
+	writel((cdesc * priv->config.cd_offset),
 	       EIP197_HIA_CDR(priv, ring) + EIP197_HIA_xDR_PREP_COUNT);
 }
 
 inline int safexcel_rdesc_check_errors(struct safexcel_crypto_priv *priv,
-				       struct safexcel_result_desc *rdesc)
+				       void *rdp)
 {
-	if (likely((!rdesc->descriptor_overflow) &&
-		   (!rdesc->buffer_overflow) &&
-		   (!rdesc->result_data.error_code)))
+	struct safexcel_result_desc *rdesc = rdp;
+	struct result_data_desc *result_data = rdp + priv->config.res_offset;
+
+	if (likely((!rdesc->last_seg) || /* Rest only valid if last seg! */
+		   ((!rdesc->descriptor_overflow) &&
+		    (!rdesc->buffer_overflow) &&
+		    (!result_data->error_code))))
 		return 0;
 
 	if (rdesc->descriptor_overflow)
@@ -858,13 +900,14 @@ inline int safexcel_rdesc_check_errors(struct safexcel_crypto_priv *priv,
 	if (rdesc->buffer_overflow)
 		dev_err(priv->dev, "Buffer overflow detected");
 
-	if (rdesc->result_data.error_code & 0x4066) {
+	if (result_data->error_code & 0x4066) {
 		/* Fatal error (bits 1,2,5,6 & 14) */
 		dev_err(priv->dev,
 			"result descriptor error (%x)",
-			rdesc->result_data.error_code);
+			result_data->error_code);
+
 		return -EIO;
-	} else if (rdesc->result_data.error_code &
+	} else if (result_data->error_code &
 		   (BIT(7) | BIT(4) | BIT(3) | BIT(0))) {
 		/*
 		 * Give priority over authentication fails:
@@ -872,7 +915,7 @@ inline int safexcel_rdesc_check_errors(struct safexcel_crypto_priv *priv,
 		 * something wrong with the input!
 		 */
 		return -EINVAL;
-	} else if (rdesc->result_data.error_code & BIT(9)) {
+	} else if (result_data->error_code & BIT(9)) {
 		/* Authentication failed */
 		return -EBADMSG;
 	}
@@ -1003,7 +1046,7 @@ handle_results:
 acknowledge:
 	if (i)
 		writel(EIP197_xDR_PROC_xD_PKT(i) |
-		       EIP197_xDR_PROC_xD_COUNT(tot_descs * priv->config.rd_offset),
+		       (tot_descs * priv->config.rd_offset),
 		       EIP197_HIA_RDR(priv, ring) + EIP197_HIA_xDR_PROC_COUNT);
 
 	/* If the number of requests overflowed the counter, try to proceed more
@@ -1120,6 +1163,8 @@ static int safexcel_request_ring_irq(void *pdev, int irqid,
 				irq_name, irq);
 			return irq;
 		}
+	} else {
+		return -ENXIO;
 	}
 
 	ret = devm_request_threaded_irq(dev, irq, handler,
@@ -1169,6 +1214,44 @@ static struct safexcel_alg_template *safexcel_algs[] = {
 	&safexcel_alg_xts_aes,
 	&safexcel_alg_gcm,
 	&safexcel_alg_ccm,
+	&safexcel_alg_crc32,
+	&safexcel_alg_cbcmac,
+	&safexcel_alg_xcbcmac,
+	&safexcel_alg_cmac,
+	&safexcel_alg_chacha20,
+	&safexcel_alg_chachapoly,
+	&safexcel_alg_chachapoly_esp,
+	&safexcel_alg_sm3,
+	&safexcel_alg_hmac_sm3,
+	&safexcel_alg_ecb_sm4,
+	&safexcel_alg_cbc_sm4,
+	&safexcel_alg_ofb_sm4,
+	&safexcel_alg_cfb_sm4,
+	&safexcel_alg_ctr_sm4,
+	&safexcel_alg_authenc_hmac_sha1_cbc_sm4,
+	&safexcel_alg_authenc_hmac_sm3_cbc_sm4,
+	&safexcel_alg_authenc_hmac_sha1_ctr_sm4,
+	&safexcel_alg_authenc_hmac_sm3_ctr_sm4,
+	&safexcel_alg_sha3_224,
+	&safexcel_alg_sha3_256,
+	&safexcel_alg_sha3_384,
+	&safexcel_alg_sha3_512,
+	&safexcel_alg_hmac_sha3_224,
+	&safexcel_alg_hmac_sha3_256,
+	&safexcel_alg_hmac_sha3_384,
+	&safexcel_alg_hmac_sha3_512,
+	&safexcel_alg_authenc_hmac_sha1_cbc_des,
+	&safexcel_alg_authenc_hmac_sha256_cbc_des3_ede,
+	&safexcel_alg_authenc_hmac_sha224_cbc_des3_ede,
+	&safexcel_alg_authenc_hmac_sha512_cbc_des3_ede,
+	&safexcel_alg_authenc_hmac_sha384_cbc_des3_ede,
+	&safexcel_alg_authenc_hmac_sha256_cbc_des,
+	&safexcel_alg_authenc_hmac_sha224_cbc_des,
+	&safexcel_alg_authenc_hmac_sha512_cbc_des,
+	&safexcel_alg_authenc_hmac_sha384_cbc_des,
+	&safexcel_alg_rfc4106_gcm,
+	&safexcel_alg_rfc4543_gcm,
+	&safexcel_alg_rfc4309_ccm,
 };
 
 static int safexcel_register_algorithms(struct safexcel_crypto_priv *priv)
@@ -1238,30 +1321,28 @@ static void safexcel_unregister_algorithms(struct safexcel_crypto_priv *priv)
 
 static void safexcel_configure(struct safexcel_crypto_priv *priv)
 {
-	u32 val, mask = 0;
-
-	val = readl(EIP197_HIA_AIC_G(priv) + EIP197_HIA_OPTIONS);
-
-	/* Read number of PEs from the engine */
-	if (priv->flags & SAFEXCEL_HW_EIP197)
-		/* Wider field width for all EIP197 type engines */
-		mask = EIP197_N_PES_MASK;
-	else
-		/* Narrow field width for EIP97 type engine */
-		mask = EIP97_N_PES_MASK;
+	u32 mask = BIT(priv->hwconfig.hwdataw) - 1;
 
-	priv->config.pes = (val >> EIP197_N_PES_OFFSET) & mask;
+	priv->config.pes = priv->hwconfig.hwnumpes;
+	priv->config.rings = min_t(u32, priv->hwconfig.hwnumrings, max_rings);
+	/* Cannot currently support more rings than we have ring AICs! */
+	priv->config.rings = min_t(u32, priv->config.rings,
+					priv->hwconfig.hwnumraic);
 
-	priv->config.rings = min_t(u32, val & GENMASK(3, 0), max_rings);
-
-	val = (val & GENMASK(27, 25)) >> 25;
-	mask = BIT(val) - 1;
-
-	priv->config.cd_size = (sizeof(struct safexcel_command_desc) / sizeof(u32));
+	priv->config.cd_size = EIP197_CD64_FETCH_SIZE;
 	priv->config.cd_offset = (priv->config.cd_size + mask) & ~mask;
 
-	priv->config.rd_size = (sizeof(struct safexcel_result_desc) / sizeof(u32));
+	/* res token is behind the descr, but ofs must be rounded to buswdth */
+	priv->config.res_offset = (EIP197_RD64_FETCH_SIZE + mask) & ~mask;
+	/* now the size of the descr is this 1st part plus the result struct */
+	priv->config.rd_size    = priv->config.res_offset +
+				  EIP197_RD64_RESULT_SIZE;
 	priv->config.rd_offset = (priv->config.rd_size + mask) & ~mask;
+
+	/* convert dwords to bytes */
+	priv->config.cd_offset *= sizeof(u32);
+	priv->config.rd_offset *= sizeof(u32);
+	priv->config.res_offset *= sizeof(u32);
 }
 
 static void safexcel_init_register_offsets(struct safexcel_crypto_priv *priv)
@@ -1307,7 +1388,7 @@ static int safexcel_probe_generic(void *pdev,
 				  int is_pci_dev)
 {
 	struct device *dev = priv->dev;
-	u32 peid, version, mask, val, hiaopt;
+	u32 peid, version, mask, val, hiaopt, hwopt, peopt;
 	int i, ret, hwctg;
 
 	priv->context_pool = dmam_pool_create("safexcel-context", dev,
@@ -1369,13 +1450,16 @@ static int safexcel_probe_generic(void *pdev,
 	 */
 	version = readl(EIP197_GLOBAL(priv) + EIP197_VERSION);
 	if (((priv->flags & SAFEXCEL_HW_EIP197) &&
-	     (EIP197_REG_LO16(version) != EIP197_VERSION_LE)) ||
+	     (EIP197_REG_LO16(version) != EIP197_VERSION_LE) &&
+	     (EIP197_REG_LO16(version) != EIP196_VERSION_LE)) ||
 	    ((!(priv->flags & SAFEXCEL_HW_EIP197) &&
 	     (EIP197_REG_LO16(version) != EIP97_VERSION_LE)))) {
 		/*
 		 * We did not find the device that matched our initial probing
 		 * (or our initial probing failed) Report appropriate error.
 		 */
+		dev_err(priv->dev, "Probing for EIP97/EIP19x failed - no such device (read %08x)\n",
+			version);
 		return -ENODEV;
 	}
 
@@ -1383,6 +1467,14 @@ static int safexcel_probe_generic(void *pdev,
 	hwctg = version >> 28;
 	peid = version & 255;
 
+	/* Detect EIP206 processing pipe */
+	version = readl(EIP197_PE(priv) + + EIP197_PE_VERSION(0));
+	if (EIP197_REG_LO16(version) != EIP206_VERSION_LE) {
+		dev_err(priv->dev, "EIP%d: EIP206 not detected\n", peid);
+		return -ENODEV;
+	}
+	priv->hwconfig.ppver = EIP197_VERSION_MASK(version);
+
 	/* Detect EIP96 packet engine and version */
 	version = readl(EIP197_PE(priv) + EIP197_PE_EIP96_VERSION(0));
 	if (EIP197_REG_LO16(version) != EIP96_VERSION_LE) {
@@ -1391,10 +1483,13 @@ static int safexcel_probe_generic(void *pdev,
 	}
 	priv->hwconfig.pever = EIP197_VERSION_MASK(version);
 
+	hwopt = readl(EIP197_GLOBAL(priv) + EIP197_OPTIONS);
 	hiaopt = readl(EIP197_HIA_AIC(priv) + EIP197_HIA_OPTIONS);
 
 	if (priv->flags & SAFEXCEL_HW_EIP197) {
 		/* EIP197 */
+		peopt = readl(EIP197_PE(priv) + EIP197_PE_OPTIONS(0));
+
 		priv->hwconfig.hwdataw  = (hiaopt >> EIP197_HWDATAW_OFFSET) &
 					  EIP197_HWDATAW_MASK;
 		priv->hwconfig.hwcfsize = ((hiaopt >> EIP197_CFSIZE_OFFSET) &
@@ -1403,6 +1498,19 @@ static int safexcel_probe_generic(void *pdev,
 		priv->hwconfig.hwrfsize = ((hiaopt >> EIP197_RFSIZE_OFFSET) &
 					   EIP197_RFSIZE_MASK) +
 					  EIP197_RFSIZE_ADJUST;
+		priv->hwconfig.hwnumpes	= (hiaopt >> EIP197_N_PES_OFFSET) &
+					  EIP197_N_PES_MASK;
+		priv->hwconfig.hwnumrings = (hiaopt >> EIP197_N_RINGS_OFFSET) &
+					    EIP197_N_RINGS_MASK;
+		if (hiaopt & EIP197_HIA_OPT_HAS_PE_ARB)
+			priv->flags |= EIP197_PE_ARB;
+		if (EIP206_OPT_ICE_TYPE(peopt) == 1)
+			priv->flags |= EIP197_ICE;
+		/* If not a full TRC, then assume simple TRC */
+		if (!(hwopt & EIP197_OPT_HAS_TRC))
+			priv->flags |= EIP197_SIMPLE_TRC;
+		/* EIP197 always has SOME form of TRC */
+		priv->flags |= EIP197_TRC_CACHE;
 	} else {
 		/* EIP97 */
 		priv->hwconfig.hwdataw  = (hiaopt >> EIP197_HWDATAW_OFFSET) &
@@ -1411,6 +1519,23 @@ static int safexcel_probe_generic(void *pdev,
 					  EIP97_CFSIZE_MASK;
 		priv->hwconfig.hwrfsize = (hiaopt >> EIP97_RFSIZE_OFFSET) &
 					  EIP97_RFSIZE_MASK;
+		priv->hwconfig.hwnumpes	= 1; /* by definition */
+		priv->hwconfig.hwnumrings = (hiaopt >> EIP197_N_RINGS_OFFSET) &
+					    EIP197_N_RINGS_MASK;
+	}
+
+	/* Scan for ring AIC's */
+	for (i = 0; i < EIP197_MAX_RING_AIC; i++) {
+		version = readl(EIP197_HIA_AIC_R(priv) +
+				EIP197_HIA_AIC_R_VERSION(i));
+		if (EIP197_REG_LO16(version) != EIP201_VERSION_LE)
+			break;
+	}
+	priv->hwconfig.hwnumraic = i;
+	/* Low-end EIP196 may not have any ring AIC's ... */
+	if (!priv->hwconfig.hwnumraic) {
+		dev_err(priv->dev, "No ring interrupt controller present!\n");
+		return -ENODEV;
 	}
 
 	/* Get supported algorithms from EIP96 transform engine */
@@ -1418,10 +1543,12 @@ static int safexcel_probe_generic(void *pdev,
 				    EIP197_PE_EIP96_OPTIONS(0));
 
 	/* Print single info line describing what we just detected */
-	dev_info(priv->dev, "EIP%d:%x(%d)-HIA:%x(%d,%d,%d),PE:%x,alg:%08x\n",
-		 peid, priv->hwconfig.hwver, hwctg, priv->hwconfig.hiaver,
-		 priv->hwconfig.hwdataw, priv->hwconfig.hwcfsize,
-		 priv->hwconfig.hwrfsize, priv->hwconfig.pever,
+	dev_info(priv->dev, "EIP%d:%x(%d,%d,%d,%d)-HIA:%x(%d,%d,%d),PE:%x/%x,alg:%08x\n",
+		 peid, priv->hwconfig.hwver, hwctg, priv->hwconfig.hwnumpes,
+		 priv->hwconfig.hwnumrings, priv->hwconfig.hwnumraic,
+		 priv->hwconfig.hiaver, priv->hwconfig.hwdataw,
+		 priv->hwconfig.hwcfsize, priv->hwconfig.hwrfsize,
+		 priv->hwconfig.ppver, priv->hwconfig.pever,
 		 priv->hwconfig.algo_flags);
 
 	safexcel_configure(priv);
@@ -1545,7 +1672,6 @@ static void safexcel_hw_reset_rings(struct safexcel_crypto_priv *priv)
 	}
 }
 
-#if IS_ENABLED(CONFIG_OF)
 /* for Device Tree platform driver */
 
 static int safexcel_probe(struct platform_device *pdev)
@@ -1623,6 +1749,7 @@ static int safexcel_remove(struct platform_device *pdev)
 	safexcel_unregister_algorithms(priv);
 	safexcel_hw_reset_rings(priv);
 
+	clk_disable_unprepare(priv->reg_clk);
 	clk_disable_unprepare(priv->clk);
 
 	for (i = 0; i < priv->config.rings; i++)
@@ -1664,9 +1791,7 @@ static struct platform_driver  crypto_safexcel = {
 		.of_match_table = safexcel_of_match_table,
 	},
 };
-#endif
 
-#if IS_ENABLED(CONFIG_PCI)
 /* PCIE devices - i.e. Inside Secure development boards */
 
 static int safexcel_pci_probe(struct pci_dev *pdev,
@@ -1757,7 +1882,7 @@ static int safexcel_pci_probe(struct pci_dev *pdev,
 	return rc;
 }
 
-void safexcel_pci_remove(struct pci_dev *pdev)
+static void safexcel_pci_remove(struct pci_dev *pdev)
 {
 	struct safexcel_crypto_priv *priv = pci_get_drvdata(pdev);
 	int i;
@@ -1787,54 +1912,32 @@ static struct pci_driver safexcel_pci_driver = {
 	.probe         = safexcel_pci_probe,
 	.remove        = safexcel_pci_remove,
 };
-#endif
-
-/* Unfortunately, we have to resort to global variables here */
-#if IS_ENABLED(CONFIG_PCI)
-int pcireg_rc = -EINVAL; /* Default safe value */
-#endif
-#if IS_ENABLED(CONFIG_OF)
-int ofreg_rc = -EINVAL; /* Default safe value */
-#endif
 
 static int __init safexcel_init(void)
 {
-#if IS_ENABLED(CONFIG_PCI)
+	int ret;
+
 	/* Register PCI driver */
-	pcireg_rc = pci_register_driver(&safexcel_pci_driver);
-#endif
+	ret = pci_register_driver(&safexcel_pci_driver);
 
-#if IS_ENABLED(CONFIG_OF)
 	/* Register platform driver */
-	ofreg_rc = platform_driver_register(&crypto_safexcel);
- #if IS_ENABLED(CONFIG_PCI)
-	/* Return success if either PCI or OF registered OK */
-	return pcireg_rc ? ofreg_rc : 0;
- #else
-	return ofreg_rc;
- #endif
-#else
- #if IS_ENABLED(CONFIG_PCI)
-	return pcireg_rc;
- #else
-	return -EINVAL;
- #endif
-#endif
+	if (IS_ENABLED(CONFIG_OF) && !ret) {
+		ret = platform_driver_register(&crypto_safexcel);
+		if (ret)
+			pci_unregister_driver(&safexcel_pci_driver);
+	}
+
+	return ret;
 }
 
 static void __exit safexcel_exit(void)
 {
-#if IS_ENABLED(CONFIG_OF)
 	/* Unregister platform driver */
-	if (!ofreg_rc)
+	if (IS_ENABLED(CONFIG_OF))
 		platform_driver_unregister(&crypto_safexcel);
-#endif
 
-#if IS_ENABLED(CONFIG_PCI)
 	/* Unregister PCI driver if successfully registered before */
-	if (!pcireg_rc)
-		pci_unregister_driver(&safexcel_pci_driver);
-#endif
+	pci_unregister_driver(&safexcel_pci_driver);
 }
 
 module_init(safexcel_init);
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 930cc48a6f85..b4624b5687ce 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -17,8 +17,11 @@
 #define EIP197_HIA_VERSION_BE			0xca35
 #define EIP197_HIA_VERSION_LE			0x35ca
 #define EIP97_VERSION_LE			0x9e61
+#define EIP196_VERSION_LE			0x3bc4
 #define EIP197_VERSION_LE			0x3ac5
 #define EIP96_VERSION_LE			0x9f60
+#define EIP201_VERSION_LE			0x36c9
+#define EIP206_VERSION_LE			0x31ce
 #define EIP197_REG_LO16(reg)			(reg & 0xffff)
 #define EIP197_REG_HI16(reg)			((reg >> 16) & 0xffff)
 #define EIP197_VERSION_MASK(reg)		((reg >> 16) & 0xfff)
@@ -26,12 +29,22 @@
 						((reg >> 4) & 0xf0) | \
 						((reg >> 12) & 0xf))
 
+/* EIP197 HIA OPTIONS ENCODING */
+#define EIP197_HIA_OPT_HAS_PE_ARB		BIT(29)
+
+/* EIP206 OPTIONS ENCODING */
+#define EIP206_OPT_ICE_TYPE(n)			((n>>8)&3)
+
+/* EIP197 OPTIONS ENCODING */
+#define EIP197_OPT_HAS_TRC			BIT(31)
+
 /* Static configuration */
 #define EIP197_DEFAULT_RING_SIZE		400
-#define EIP197_MAX_TOKENS			18
+#define EIP197_MAX_TOKENS			19
 #define EIP197_MAX_RINGS			4
 #define EIP197_FETCH_DEPTH			2
 #define EIP197_MAX_BATCH_SZ			64
+#define EIP197_MAX_RING_AIC			14
 
 #define EIP197_GFP_FLAGS(base)	((base).flags & CRYPTO_TFM_REQ_MAY_SLEEP ? \
 				 GFP_KERNEL : GFP_ATOMIC)
@@ -138,6 +151,7 @@
 #define EIP197_HIA_AIC_R_ENABLED_STAT(r)	(0xe010 - EIP197_HIA_AIC_R_OFF(r))
 #define EIP197_HIA_AIC_R_ACK(r)			(0xe010 - EIP197_HIA_AIC_R_OFF(r))
 #define EIP197_HIA_AIC_R_ENABLE_CLR(r)		(0xe014 - EIP197_HIA_AIC_R_OFF(r))
+#define EIP197_HIA_AIC_R_VERSION(r)		(0xe01c - EIP197_HIA_AIC_R_OFF(r))
 #define EIP197_HIA_AIC_G_ENABLE_CTRL		0xf808
 #define EIP197_HIA_AIC_G_ENABLED_STAT		0xf810
 #define EIP197_HIA_AIC_G_ACK			0xf810
@@ -157,12 +171,16 @@
 #define EIP197_PE_EIP96_FUNCTION_EN(n)		(0x1004 + (0x2000 * (n)))
 #define EIP197_PE_EIP96_CONTEXT_CTRL(n)		(0x1008 + (0x2000 * (n)))
 #define EIP197_PE_EIP96_CONTEXT_STAT(n)		(0x100c + (0x2000 * (n)))
+#define EIP197_PE_EIP96_TOKEN_CTRL2(n)		(0x102c + (0x2000 * (n)))
 #define EIP197_PE_EIP96_FUNCTION2_EN(n)		(0x1030 + (0x2000 * (n)))
 #define EIP197_PE_EIP96_OPTIONS(n)		(0x13f8 + (0x2000 * (n)))
 #define EIP197_PE_EIP96_VERSION(n)		(0x13fc + (0x2000 * (n)))
 #define EIP197_PE_OUT_DBUF_THRES(n)		(0x1c00 + (0x2000 * (n)))
 #define EIP197_PE_OUT_TBUF_THRES(n)		(0x1d00 + (0x2000 * (n)))
+#define EIP197_PE_OPTIONS(n)			(0x1ff8 + (0x2000 * (n)))
+#define EIP197_PE_VERSION(n)			(0x1ffc + (0x2000 * (n)))
 #define EIP197_MST_CTRL				0xfff4
+#define EIP197_OPTIONS				0xfff8
 #define EIP197_VERSION				0xfffc
 
 /* EIP197-specific registers, no indirection */
@@ -178,6 +196,7 @@
 #define EIP197_TRC_ECCADMINSTAT			0xf0838
 #define EIP197_TRC_ECCDATASTAT			0xf083c
 #define EIP197_TRC_ECCDATA			0xf0840
+#define EIP197_STRC_CONFIG			0xf43f0
 #define EIP197_FLUE_CACHEBASE_LO(n)		(0xf6000 + (32 * (n)))
 #define EIP197_FLUE_CACHEBASE_HI(n)		(0xf6004 + (32 * (n)))
 #define EIP197_FLUE_CONFIG(n)			(0xf6010 + (32 * (n)))
@@ -213,7 +232,6 @@
 /* EIP197_HIA_xDR_PROC_COUNT */
 #define EIP197_xDR_PROC_xD_PKT_OFFSET		24
 #define EIP197_xDR_PROC_xD_PKT_MASK		GENMASK(6, 0)
-#define EIP197_xDR_PROC_xD_COUNT(n)		((n) << 2)
 #define EIP197_xDR_PROC_xD_PKT(n)		((n) << 24)
 #define EIP197_xDR_PROC_CLR_COUNT		BIT(31)
 
@@ -228,6 +246,8 @@
 #define EIP197_HIA_RA_PE_CTRL_EN		BIT(30)
 
 /* EIP197_HIA_OPTIONS */
+#define EIP197_N_RINGS_OFFSET			0
+#define EIP197_N_RINGS_MASK			GENMASK(3, 0)
 #define EIP197_N_PES_OFFSET			4
 #define EIP197_N_PES_MASK			GENMASK(4, 0)
 #define EIP97_N_PES_MASK			GENMASK(2, 0)
@@ -237,13 +257,13 @@
 #define EIP197_CFSIZE_OFFSET			9
 #define EIP197_CFSIZE_ADJUST			4
 #define EIP97_CFSIZE_OFFSET			8
-#define EIP197_CFSIZE_MASK			GENMASK(3, 0)
-#define EIP97_CFSIZE_MASK			GENMASK(4, 0)
+#define EIP197_CFSIZE_MASK			GENMASK(2, 0)
+#define EIP97_CFSIZE_MASK			GENMASK(3, 0)
 #define EIP197_RFSIZE_OFFSET			12
 #define EIP197_RFSIZE_ADJUST			4
 #define EIP97_RFSIZE_OFFSET			12
-#define EIP197_RFSIZE_MASK			GENMASK(3, 0)
-#define EIP97_RFSIZE_MASK			GENMASK(4, 0)
+#define EIP197_RFSIZE_MASK			GENMASK(2, 0)
+#define EIP97_RFSIZE_MASK			GENMASK(3, 0)
 
 /* EIP197_HIA_AIC_R_ENABLE_CTRL */
 #define EIP197_CDR_IRQ(n)			BIT((n) * 2)
@@ -327,13 +347,21 @@
 #define EIP197_ADDRESS_MODE			BIT(8)
 #define EIP197_CONTROL_MODE			BIT(9)
 
+/* EIP197_PE_EIP96_TOKEN_CTRL2 */
+#define EIP197_PE_EIP96_TOKEN_CTRL2_CTX_DONE	BIT(3)
+
+/* EIP197_STRC_CONFIG */
+#define EIP197_STRC_CONFIG_INIT			BIT(31)
+#define EIP197_STRC_CONFIG_LARGE_REC(s)		(s<<8)
+#define EIP197_STRC_CONFIG_SMALL_REC(s)		(s<<0)
+
 /* EIP197_FLUE_CONFIG */
 #define EIP197_FLUE_CONFIG_MAGIC		0xc7000004
 
 /* Context Control */
 struct safexcel_context_record {
-	u32 control0;
-	u32 control1;
+	__le32 control0;
+	__le32 control1;
 
 	__le32 data[40];
 } __packed;
@@ -358,10 +386,14 @@ struct safexcel_context_record {
 #define CONTEXT_CONTROL_CRYPTO_ALG_AES128	(0x5 << 17)
 #define CONTEXT_CONTROL_CRYPTO_ALG_AES192	(0x6 << 17)
 #define CONTEXT_CONTROL_CRYPTO_ALG_AES256	(0x7 << 17)
+#define CONTEXT_CONTROL_CRYPTO_ALG_CHACHA20	(0x8 << 17)
+#define CONTEXT_CONTROL_CRYPTO_ALG_SM4		(0xd << 17)
+#define CONTEXT_CONTROL_DIGEST_INITIAL		(0x0 << 21)
 #define CONTEXT_CONTROL_DIGEST_PRECOMPUTED	(0x1 << 21)
 #define CONTEXT_CONTROL_DIGEST_XCM		(0x2 << 21)
 #define CONTEXT_CONTROL_DIGEST_HMAC		(0x3 << 21)
 #define CONTEXT_CONTROL_CRYPTO_ALG_MD5		(0x0 << 23)
+#define CONTEXT_CONTROL_CRYPTO_ALG_CRC32	(0x0 << 23)
 #define CONTEXT_CONTROL_CRYPTO_ALG_SHA1		(0x2 << 23)
 #define CONTEXT_CONTROL_CRYPTO_ALG_SHA224	(0x4 << 23)
 #define CONTEXT_CONTROL_CRYPTO_ALG_SHA256	(0x3 << 23)
@@ -371,17 +403,25 @@ struct safexcel_context_record {
 #define CONTEXT_CONTROL_CRYPTO_ALG_XCBC128	(0x1 << 23)
 #define CONTEXT_CONTROL_CRYPTO_ALG_XCBC192	(0x2 << 23)
 #define CONTEXT_CONTROL_CRYPTO_ALG_XCBC256	(0x3 << 23)
+#define CONTEXT_CONTROL_CRYPTO_ALG_SM3		(0x7 << 23)
+#define CONTEXT_CONTROL_CRYPTO_ALG_SHA3_256	(0xb << 23)
+#define CONTEXT_CONTROL_CRYPTO_ALG_SHA3_224	(0xc << 23)
+#define CONTEXT_CONTROL_CRYPTO_ALG_SHA3_512	(0xd << 23)
+#define CONTEXT_CONTROL_CRYPTO_ALG_SHA3_384	(0xe << 23)
+#define CONTEXT_CONTROL_CRYPTO_ALG_POLY1305	(0xf << 23)
 #define CONTEXT_CONTROL_INV_FR			(0x5 << 24)
 #define CONTEXT_CONTROL_INV_TR			(0x6 << 24)
 
 /* control1 */
 #define CONTEXT_CONTROL_CRYPTO_MODE_ECB		(0 << 0)
 #define CONTEXT_CONTROL_CRYPTO_MODE_CBC		(1 << 0)
+#define CONTEXT_CONTROL_CHACHA20_MODE_256_32	(2 << 0)
 #define CONTEXT_CONTROL_CRYPTO_MODE_OFB		(4 << 0)
 #define CONTEXT_CONTROL_CRYPTO_MODE_CFB		(5 << 0)
 #define CONTEXT_CONTROL_CRYPTO_MODE_CTR_LOAD	(6 << 0)
 #define CONTEXT_CONTROL_CRYPTO_MODE_XTS		(7 << 0)
 #define CONTEXT_CONTROL_CRYPTO_MODE_XCM		((6 << 0) | BIT(17))
+#define CONTEXT_CONTROL_CHACHA20_MODE_CALC_OTK	(12 << 0)
 #define CONTEXT_CONTROL_IV0			BIT(5)
 #define CONTEXT_CONTROL_IV1			BIT(6)
 #define CONTEXT_CONTROL_IV2			BIT(7)
@@ -394,6 +434,13 @@ struct safexcel_context_record {
 #define EIP197_XCM_MODE_GCM			1
 #define EIP197_XCM_MODE_CCM			2
 
+#define EIP197_AEAD_TYPE_IPSEC_ESP		2
+#define EIP197_AEAD_TYPE_IPSEC_ESP_GMAC		3
+#define EIP197_AEAD_IPSEC_IV_SIZE		8
+#define EIP197_AEAD_IPSEC_NONCE_SIZE		4
+#define EIP197_AEAD_IPSEC_COUNTER_SIZE		4
+#define EIP197_AEAD_IPSEC_CCM_NONCE_SIZE	3
+
 /* The hash counter given to the engine in the context has a granularity of
  * 64 bits.
  */
@@ -423,6 +470,8 @@ struct safexcel_context_record {
 #define EIP197_TRC_PARAMS2_RC_SZ_SMALL(n)	((n) << 18)
 
 /* Cache helpers */
+#define EIP197_MIN_DSIZE			1024
+#define EIP197_MIN_ASIZE			8
 #define EIP197_CS_TRC_REC_WC			64
 #define EIP197_CS_RC_SIZE			(4 * sizeof(u32))
 #define EIP197_CS_RC_NEXT(x)			(x)
@@ -447,7 +496,7 @@ struct result_data_desc {
 	u16 application_id;
 	u16 rsvd1;
 
-	u32 rsvd2;
+	u32 rsvd2[5];
 } __packed;
 
 
@@ -465,16 +514,15 @@ struct safexcel_result_desc {
 
 	u32 data_lo;
 	u32 data_hi;
-
-	struct result_data_desc result_data;
 } __packed;
 
 /*
  * The EIP(1)97 only needs to fetch the descriptor part of
  * the result descriptor, not the result token part!
  */
-#define EIP197_RD64_FETCH_SIZE		((sizeof(struct safexcel_result_desc) -\
-					  sizeof(struct result_data_desc)) /\
+#define EIP197_RD64_FETCH_SIZE		(sizeof(struct safexcel_result_desc) /\
+					 sizeof(u32))
+#define EIP197_RD64_RESULT_SIZE		(sizeof(struct result_data_desc) /\
 					 sizeof(u32))
 
 struct safexcel_token {
@@ -561,6 +609,9 @@ struct safexcel_command_desc {
 	struct safexcel_control_data_desc control_data;
 } __packed;
 
+#define EIP197_CD64_FETCH_SIZE		(sizeof(struct safexcel_command_desc) /\
+					sizeof(u32))
+
 /*
  * Internal structures & functions
  */
@@ -604,6 +655,7 @@ struct safexcel_config {
 
 	u32 rd_size;
 	u32 rd_offset;
+	u32 res_offset;
 };
 
 struct safexcel_work_data {
@@ -654,6 +706,12 @@ enum safexcel_eip_version {
 /* Priority we use for advertising our algorithms */
 #define SAFEXCEL_CRA_PRIORITY		300
 
+/* SM3 digest result for zero length message */
+#define EIP197_SM3_ZEROM_HASH	"\x1A\xB2\x1D\x83\x55\xCF\xA1\x7F" \
+				"\x8E\x61\x19\x48\x31\xE8\x1A\x8F" \
+				"\x22\xBE\xC8\xC7\x28\xFE\xFB\x74" \
+				"\x7E\xD0\x35\xEB\x50\x82\xAA\x2B"
+
 /* EIP algorithm presence flags */
 enum safexcel_eip_algorithms {
 	SAFEXCEL_ALG_BC0      = BIT(5),
@@ -697,16 +755,23 @@ struct safexcel_register_offsets {
 enum safexcel_flags {
 	EIP197_TRC_CACHE	= BIT(0),
 	SAFEXCEL_HW_EIP197	= BIT(1),
+	EIP197_PE_ARB		= BIT(2),
+	EIP197_ICE		= BIT(3),
+	EIP197_SIMPLE_TRC	= BIT(4),
 };
 
 struct safexcel_hwconfig {
 	enum safexcel_eip_algorithms algo_flags;
 	int hwver;
 	int hiaver;
+	int ppver;
 	int pever;
 	int hwdataw;
 	int hwcfsize;
 	int hwrfsize;
+	int hwnumpes;
+	int hwnumrings;
+	int hwnumraic;
 };
 
 struct safexcel_crypto_priv {
@@ -778,7 +843,7 @@ struct safexcel_inv_result {
 
 void safexcel_dequeue(struct safexcel_crypto_priv *priv, int ring);
 int safexcel_rdesc_check_errors(struct safexcel_crypto_priv *priv,
-				struct safexcel_result_desc *rdesc);
+				void *rdp);
 void safexcel_complete(struct safexcel_crypto_priv *priv, int ring);
 int safexcel_invalidate_cache(struct crypto_async_request *async,
 			      struct safexcel_crypto_priv *priv,
@@ -853,5 +918,43 @@ extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha512_ctr_aes;
 extern struct safexcel_alg_template safexcel_alg_xts_aes;
 extern struct safexcel_alg_template safexcel_alg_gcm;
 extern struct safexcel_alg_template safexcel_alg_ccm;
+extern struct safexcel_alg_template safexcel_alg_crc32;
+extern struct safexcel_alg_template safexcel_alg_cbcmac;
+extern struct safexcel_alg_template safexcel_alg_xcbcmac;
+extern struct safexcel_alg_template safexcel_alg_cmac;
+extern struct safexcel_alg_template safexcel_alg_chacha20;
+extern struct safexcel_alg_template safexcel_alg_chachapoly;
+extern struct safexcel_alg_template safexcel_alg_chachapoly_esp;
+extern struct safexcel_alg_template safexcel_alg_sm3;
+extern struct safexcel_alg_template safexcel_alg_hmac_sm3;
+extern struct safexcel_alg_template safexcel_alg_ecb_sm4;
+extern struct safexcel_alg_template safexcel_alg_cbc_sm4;
+extern struct safexcel_alg_template safexcel_alg_ofb_sm4;
+extern struct safexcel_alg_template safexcel_alg_cfb_sm4;
+extern struct safexcel_alg_template safexcel_alg_ctr_sm4;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_sm4;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sm3_cbc_sm4;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_ctr_sm4;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sm3_ctr_sm4;
+extern struct safexcel_alg_template safexcel_alg_sha3_224;
+extern struct safexcel_alg_template safexcel_alg_sha3_256;
+extern struct safexcel_alg_template safexcel_alg_sha3_384;
+extern struct safexcel_alg_template safexcel_alg_sha3_512;
+extern struct safexcel_alg_template safexcel_alg_hmac_sha3_224;
+extern struct safexcel_alg_template safexcel_alg_hmac_sha3_256;
+extern struct safexcel_alg_template safexcel_alg_hmac_sha3_384;
+extern struct safexcel_alg_template safexcel_alg_hmac_sha3_512;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_des;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha256_cbc_des3_ede;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_des3_ede;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha512_cbc_des3_ede;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha384_cbc_des3_ede;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha256_cbc_des;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_des;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha512_cbc_des;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha384_cbc_des;
+extern struct safexcel_alg_template safexcel_alg_rfc4106_gcm;
+extern struct safexcel_alg_template safexcel_alg_rfc4543_gcm;
+extern struct safexcel_alg_template safexcel_alg_rfc4309_ccm;
 
 #endif
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index ef51f8c2b473..c02995694b41 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -5,18 +5,22 @@
  * Antoine Tenart <antoine.tenart@free-electrons.com>
  */
 
+#include <asm/unaligned.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmapool.h>
-
 #include <crypto/aead.h>
 #include <crypto/aes.h>
 #include <crypto/authenc.h>
+#include <crypto/chacha.h>
 #include <crypto/ctr.h>
 #include <crypto/internal/des.h>
 #include <crypto/gcm.h>
 #include <crypto/ghash.h>
+#include <crypto/poly1305.h>
 #include <crypto/sha.h>
+#include <crypto/sm3.h>
+#include <crypto/sm4.h>
 #include <crypto/xts.h>
 #include <crypto/skcipher.h>
 #include <crypto/internal/aead.h>
@@ -33,6 +37,8 @@ enum safexcel_cipher_alg {
 	SAFEXCEL_DES,
 	SAFEXCEL_3DES,
 	SAFEXCEL_AES,
+	SAFEXCEL_CHACHA20,
+	SAFEXCEL_SM4,
 };
 
 struct safexcel_cipher_ctx {
@@ -41,8 +47,8 @@ struct safexcel_cipher_ctx {
 
 	u32 mode;
 	enum safexcel_cipher_alg alg;
-	bool aead;
-	int  xcm; /* 0=authenc, 1=GCM, 2 reserved for CCM */
+	char aead; /* !=0=AEAD, 2=IPSec ESP AEAD, 3=IPsec ESP GMAC */
+	char xcm;  /* 0=authenc, 1=GCM, 2 reserved for CCM */
 
 	__le32 key[16];
 	u32 nonce;
@@ -51,10 +57,11 @@ struct safexcel_cipher_ctx {
 	/* All the below is AEAD specific */
 	u32 hash_alg;
 	u32 state_sz;
-	u32 ipad[SHA512_DIGEST_SIZE / sizeof(u32)];
-	u32 opad[SHA512_DIGEST_SIZE / sizeof(u32)];
+	__be32 ipad[SHA512_DIGEST_SIZE / sizeof(u32)];
+	__be32 opad[SHA512_DIGEST_SIZE / sizeof(u32)];
 
 	struct crypto_cipher *hkaes;
+	struct crypto_aead *fback;
 };
 
 struct safexcel_cipher_req {
@@ -70,24 +77,50 @@ static void safexcel_cipher_token(struct safexcel_cipher_ctx *ctx, u8 *iv,
 {
 	u32 block_sz = 0;
 
-	if (ctx->mode == CONTEXT_CONTROL_CRYPTO_MODE_CTR_LOAD) {
+	if (ctx->mode == CONTEXT_CONTROL_CRYPTO_MODE_CTR_LOAD ||
+	    ctx->aead & EIP197_AEAD_TYPE_IPSEC_ESP) { /* _ESP and _ESP_GMAC */
 		cdesc->control_data.options |= EIP197_OPTION_4_TOKEN_IV_CMD;
 
 		/* 32 bit nonce */
 		cdesc->control_data.token[0] = ctx->nonce;
 		/* 64 bit IV part */
 		memcpy(&cdesc->control_data.token[1], iv, 8);
-		/* 32 bit counter, start at 1 (big endian!) */
-		cdesc->control_data.token[3] = cpu_to_be32(1);
+
+		if (ctx->alg == SAFEXCEL_CHACHA20 ||
+		    ctx->xcm == EIP197_XCM_MODE_CCM) {
+			/* 32 bit counter, starting at 0 */
+			cdesc->control_data.token[3] = 0;
+		} else {
+			/* 32 bit counter, start at 1 (big endian!) */
+			cdesc->control_data.token[3] =
+				(__force u32)cpu_to_be32(1);
+		}
 
 		return;
-	} else if (ctx->xcm == EIP197_XCM_MODE_GCM) {
+	} else if (ctx->xcm == EIP197_XCM_MODE_GCM ||
+		   (ctx->aead && ctx->alg == SAFEXCEL_CHACHA20)) {
 		cdesc->control_data.options |= EIP197_OPTION_4_TOKEN_IV_CMD;
 
 		/* 96 bit IV part */
 		memcpy(&cdesc->control_data.token[0], iv, 12);
-		/* 32 bit counter, start at 1 (big endian!) */
-		cdesc->control_data.token[3] = cpu_to_be32(1);
+
+		if (ctx->alg == SAFEXCEL_CHACHA20) {
+			/* 32 bit counter, starting at 0 */
+			cdesc->control_data.token[3] = 0;
+		} else {
+			/* 32 bit counter, start at 1 (big endian!) */
+			*(__be32 *)&cdesc->control_data.token[3] =
+				cpu_to_be32(1);
+		}
+
+		return;
+	} else if (ctx->alg == SAFEXCEL_CHACHA20) {
+		cdesc->control_data.options |= EIP197_OPTION_4_TOKEN_IV_CMD;
+
+		/* 96 bit nonce part */
+		memcpy(&cdesc->control_data.token[0], &iv[4], 12);
+		/* 32 bit counter */
+		cdesc->control_data.token[3] = *(u32 *)iv;
 
 		return;
 	} else if (ctx->xcm == EIP197_XCM_MODE_CCM) {
@@ -112,10 +145,16 @@ static void safexcel_cipher_token(struct safexcel_cipher_ctx *ctx, u8 *iv,
 			block_sz = DES3_EDE_BLOCK_SIZE;
 			cdesc->control_data.options |= EIP197_OPTION_2_TOKEN_IV_CMD;
 			break;
+		case SAFEXCEL_SM4:
+			block_sz = SM4_BLOCK_SIZE;
+			cdesc->control_data.options |= EIP197_OPTION_4_TOKEN_IV_CMD;
+			break;
 		case SAFEXCEL_AES:
 			block_sz = AES_BLOCK_SIZE;
 			cdesc->control_data.options |= EIP197_OPTION_4_TOKEN_IV_CMD;
 			break;
+		default:
+			break;
 		}
 		memcpy(cdesc->control_data.token, iv, block_sz);
 	}
@@ -153,72 +192,84 @@ static void safexcel_aead_token(struct safexcel_cipher_ctx *ctx, u8 *iv,
 	if (direction == SAFEXCEL_ENCRYPT) {
 		/* align end of instruction sequence to end of token */
 		token = (struct safexcel_token *)(cdesc->control_data.token +
-			 EIP197_MAX_TOKENS - 13);
+			 EIP197_MAX_TOKENS - 14);
 
-		token[12].opcode = EIP197_TOKEN_OPCODE_INSERT;
-		token[12].packet_length = digestsize;
-		token[12].stat = EIP197_TOKEN_STAT_LAST_HASH |
+		token[13].opcode = EIP197_TOKEN_OPCODE_INSERT;
+		token[13].packet_length = digestsize;
+		token[13].stat = EIP197_TOKEN_STAT_LAST_HASH |
 				 EIP197_TOKEN_STAT_LAST_PACKET;
-		token[12].instructions = EIP197_TOKEN_INS_TYPE_OUTPUT |
+		token[13].instructions = EIP197_TOKEN_INS_TYPE_OUTPUT |
 					 EIP197_TOKEN_INS_INSERT_HASH_DIGEST;
 	} else {
 		cryptlen -= digestsize;
 
 		/* align end of instruction sequence to end of token */
 		token = (struct safexcel_token *)(cdesc->control_data.token +
-			 EIP197_MAX_TOKENS - 14);
+			 EIP197_MAX_TOKENS - 15);
 
-		token[12].opcode = EIP197_TOKEN_OPCODE_RETRIEVE;
-		token[12].packet_length = digestsize;
-		token[12].stat = EIP197_TOKEN_STAT_LAST_HASH |
+		token[13].opcode = EIP197_TOKEN_OPCODE_RETRIEVE;
+		token[13].packet_length = digestsize;
+		token[13].stat = EIP197_TOKEN_STAT_LAST_HASH |
 				 EIP197_TOKEN_STAT_LAST_PACKET;
-		token[12].instructions = EIP197_TOKEN_INS_INSERT_HASH_DIGEST;
+		token[13].instructions = EIP197_TOKEN_INS_INSERT_HASH_DIGEST;
 
-		token[13].opcode = EIP197_TOKEN_OPCODE_VERIFY;
-		token[13].packet_length = digestsize |
+		token[14].opcode = EIP197_TOKEN_OPCODE_VERIFY;
+		token[14].packet_length = digestsize |
 					  EIP197_TOKEN_HASH_RESULT_VERIFY;
-		token[13].stat = EIP197_TOKEN_STAT_LAST_HASH |
+		token[14].stat = EIP197_TOKEN_STAT_LAST_HASH |
 				 EIP197_TOKEN_STAT_LAST_PACKET;
-		token[13].instructions = EIP197_TOKEN_INS_TYPE_OUTPUT;
+		token[14].instructions = EIP197_TOKEN_INS_TYPE_OUTPUT;
 	}
 
-	token[6].opcode = EIP197_TOKEN_OPCODE_DIRECTION;
-	token[6].packet_length = assoclen;
+	if (ctx->aead == EIP197_AEAD_TYPE_IPSEC_ESP) {
+		/* For ESP mode (and not GMAC), skip over the IV */
+		token[8].opcode = EIP197_TOKEN_OPCODE_DIRECTION;
+		token[8].packet_length = EIP197_AEAD_IPSEC_IV_SIZE;
 
-	if (likely(cryptlen)) {
-		token[6].instructions = EIP197_TOKEN_INS_TYPE_HASH;
+		assoclen -= EIP197_AEAD_IPSEC_IV_SIZE;
+	}
 
-		token[10].opcode = EIP197_TOKEN_OPCODE_DIRECTION;
-		token[10].packet_length = cryptlen;
-		token[10].stat = EIP197_TOKEN_STAT_LAST_HASH;
-		token[10].instructions = EIP197_TOKEN_INS_LAST |
-					 EIP197_TOKEN_INS_TYPE_CRYPTO |
-					 EIP197_TOKEN_INS_TYPE_HASH |
-					 EIP197_TOKEN_INS_TYPE_OUTPUT;
+	token[6].opcode = EIP197_TOKEN_OPCODE_DIRECTION;
+	token[6].packet_length = assoclen;
+	token[6].instructions = EIP197_TOKEN_INS_LAST |
+				EIP197_TOKEN_INS_TYPE_HASH;
+
+	if (likely(cryptlen || ctx->alg == SAFEXCEL_CHACHA20)) {
+		token[11].opcode = EIP197_TOKEN_OPCODE_DIRECTION;
+		token[11].packet_length = cryptlen;
+		token[11].stat = EIP197_TOKEN_STAT_LAST_HASH;
+		if (unlikely(ctx->aead == EIP197_AEAD_TYPE_IPSEC_ESP_GMAC)) {
+			token[6].instructions = EIP197_TOKEN_INS_TYPE_HASH;
+			/* Do not send to crypt engine in case of GMAC */
+			token[11].instructions = EIP197_TOKEN_INS_LAST |
+						 EIP197_TOKEN_INS_TYPE_HASH |
+						 EIP197_TOKEN_INS_TYPE_OUTPUT;
+		} else {
+			token[11].instructions = EIP197_TOKEN_INS_LAST |
+						 EIP197_TOKEN_INS_TYPE_CRYPTO |
+						 EIP197_TOKEN_INS_TYPE_HASH |
+						 EIP197_TOKEN_INS_TYPE_OUTPUT;
+		}
 	} else if (ctx->xcm != EIP197_XCM_MODE_CCM) {
 		token[6].stat = EIP197_TOKEN_STAT_LAST_HASH;
-		token[6].instructions = EIP197_TOKEN_INS_LAST |
-					EIP197_TOKEN_INS_TYPE_HASH;
 	}
 
 	if (!ctx->xcm)
 		return;
 
-	token[8].opcode = EIP197_TOKEN_OPCODE_INSERT_REMRES;
-	token[8].packet_length = 0;
-	token[8].instructions = AES_BLOCK_SIZE;
+	token[9].opcode = EIP197_TOKEN_OPCODE_INSERT_REMRES;
+	token[9].packet_length = 0;
+	token[9].instructions = AES_BLOCK_SIZE;
 
-	token[9].opcode = EIP197_TOKEN_OPCODE_INSERT;
-	token[9].packet_length = AES_BLOCK_SIZE;
-	token[9].instructions = EIP197_TOKEN_INS_TYPE_OUTPUT |
-				EIP197_TOKEN_INS_TYPE_CRYPTO;
+	token[10].opcode = EIP197_TOKEN_OPCODE_INSERT;
+	token[10].packet_length = AES_BLOCK_SIZE;
+	token[10].instructions = EIP197_TOKEN_INS_TYPE_OUTPUT |
+				 EIP197_TOKEN_INS_TYPE_CRYPTO;
 
-	if (ctx->xcm == EIP197_XCM_MODE_GCM) {
-		token[6].instructions = EIP197_TOKEN_INS_LAST |
-					EIP197_TOKEN_INS_TYPE_HASH;
-	} else {
+	if (ctx->xcm != EIP197_XCM_MODE_GCM) {
+		u8 *final_iv = (u8 *)cdesc->control_data.token;
 		u8 *cbcmaciv = (u8 *)&token[1];
-		u32 *aadlen = (u32 *)&token[5];
+		__le32 *aadlen = (__le32 *)&token[5];
 
 		/* Construct IV block B0 for the CBC-MAC */
 		token[0].opcode = EIP197_TOKEN_OPCODE_INSERT;
@@ -227,17 +278,18 @@ static void safexcel_aead_token(struct safexcel_cipher_ctx *ctx, u8 *iv,
 		token[0].instructions = EIP197_TOKEN_INS_ORIGIN_TOKEN |
 					EIP197_TOKEN_INS_TYPE_HASH;
 		/* Variable length IV part */
-		memcpy(cbcmaciv, iv, 15 - iv[0]);
+		memcpy(cbcmaciv, final_iv, 15 - final_iv[0]);
 		/* fixup flags byte */
 		cbcmaciv[0] |= ((assoclen > 0) << 6) | ((digestsize - 2) << 2);
 		/* Clear upper bytes of variable message length to 0 */
-		memset(cbcmaciv + 15 - iv[0], 0, iv[0] - 1);
+		memset(cbcmaciv + 15 - final_iv[0], 0, final_iv[0] - 1);
 		/* insert lower 2 bytes of message length */
 		cbcmaciv[14] = cryptlen >> 8;
 		cbcmaciv[15] = cryptlen & 255;
 
 		if (assoclen) {
-			*aadlen = cpu_to_le32(cpu_to_be16(assoclen));
+			*aadlen = cpu_to_le32((assoclen >> 8) |
+					      ((assoclen & 0xff) << 8));
 			assoclen += 2;
 		}
 
@@ -252,13 +304,13 @@ static void safexcel_aead_token(struct safexcel_cipher_ctx *ctx, u8 *iv,
 			token[7].instructions = EIP197_TOKEN_INS_TYPE_HASH;
 
 			/* Align crypto data towards hash engine */
-			token[10].stat = 0;
+			token[11].stat = 0;
 
-			token[11].opcode = EIP197_TOKEN_OPCODE_INSERT;
+			token[12].opcode = EIP197_TOKEN_OPCODE_INSERT;
 			cryptlen &= 15;
-			token[11].packet_length = cryptlen ? 16 - cryptlen : 0;
-			token[11].stat = EIP197_TOKEN_STAT_LAST_HASH;
-			token[11].instructions = EIP197_TOKEN_INS_TYPE_HASH;
+			token[12].packet_length = cryptlen ? 16 - cryptlen : 0;
+			token[12].stat = EIP197_TOKEN_STAT_LAST_HASH;
+			token[12].instructions = EIP197_TOKEN_INS_TYPE_HASH;
 		} else {
 			token[7].stat = EIP197_TOKEN_STAT_LAST_HASH;
 			token[7].instructions = EIP197_TOKEN_INS_LAST |
@@ -284,7 +336,7 @@ static int safexcel_skcipher_aes_setkey(struct crypto_skcipher *ctfm,
 
 	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma) {
 		for (i = 0; i < len / sizeof(u32); i++) {
-			if (ctx->key[i] != cpu_to_le32(aes.key_enc[i])) {
+			if (le32_to_cpu(ctx->key[i]) != aes.key_enc[i]) {
 				ctx->base.needs_inv = true;
 				break;
 			}
@@ -309,25 +361,29 @@ static int safexcel_aead_setkey(struct crypto_aead *ctfm, const u8 *key,
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	struct crypto_authenc_keys keys;
 	struct crypto_aes_ctx aes;
-	int err = -EINVAL;
+	int err = -EINVAL, i;
 
-	if (crypto_authenc_extractkeys(&keys, key, len) != 0)
+	if (unlikely(crypto_authenc_extractkeys(&keys, key, len)))
 		goto badkey;
 
 	if (ctx->mode == CONTEXT_CONTROL_CRYPTO_MODE_CTR_LOAD) {
-		/* Minimum keysize is minimum AES key size + nonce size */
-		if (keys.enckeylen < (AES_MIN_KEY_SIZE +
-				      CTR_RFC3686_NONCE_SIZE))
+		/* Must have at least space for the nonce here */
+		if (unlikely(keys.enckeylen < CTR_RFC3686_NONCE_SIZE))
 			goto badkey;
 		/* last 4 bytes of key are the nonce! */
 		ctx->nonce = *(u32 *)(keys.enckey + keys.enckeylen -
 				      CTR_RFC3686_NONCE_SIZE);
 		/* exclude the nonce here */
-		keys.enckeylen -= CONTEXT_CONTROL_CRYPTO_MODE_CTR_LOAD;
+		keys.enckeylen -= CTR_RFC3686_NONCE_SIZE;
 	}
 
 	/* Encryption key */
 	switch (ctx->alg) {
+	case SAFEXCEL_DES:
+		err = verify_aead_des_key(ctfm, keys.enckey, keys.enckeylen);
+		if (unlikely(err))
+			goto badkey_expflags;
+		break;
 	case SAFEXCEL_3DES:
 		err = verify_aead_des3_key(ctfm, keys.enckey, keys.enckeylen);
 		if (unlikely(err))
@@ -338,14 +394,24 @@ static int safexcel_aead_setkey(struct crypto_aead *ctfm, const u8 *key,
 		if (unlikely(err))
 			goto badkey;
 		break;
+	case SAFEXCEL_SM4:
+		if (unlikely(keys.enckeylen != SM4_KEY_SIZE))
+			goto badkey;
+		break;
 	default:
 		dev_err(priv->dev, "aead: unsupported cipher algorithm\n");
 		goto badkey;
 	}
 
-	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma &&
-	    memcmp(ctx->key, keys.enckey, keys.enckeylen))
-		ctx->base.needs_inv = true;
+	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma) {
+		for (i = 0; i < keys.enckeylen / sizeof(u32); i++) {
+			if (le32_to_cpu(ctx->key[i]) !=
+			    ((u32 *)keys.enckey)[i]) {
+				ctx->base.needs_inv = true;
+				break;
+			}
+		}
+	}
 
 	/* Auth key */
 	switch (ctx->hash_alg) {
@@ -374,6 +440,11 @@ static int safexcel_aead_setkey(struct crypto_aead *ctfm, const u8 *key,
 					 keys.authkeylen, &istate, &ostate))
 			goto badkey;
 		break;
+	case CONTEXT_CONTROL_CRYPTO_ALG_SM3:
+		if (safexcel_hmac_setkey("safexcel-sm3", keys.authkey,
+					 keys.authkeylen, &istate, &ostate))
+			goto badkey;
+		break;
 	default:
 		dev_err(priv->dev, "aead: unsupported hash algorithm\n");
 		goto badkey;
@@ -388,7 +459,8 @@ static int safexcel_aead_setkey(struct crypto_aead *ctfm, const u8 *key,
 		ctx->base.needs_inv = true;
 
 	/* Now copy the keys into the context */
-	memcpy(ctx->key, keys.enckey, keys.enckeylen);
+	for (i = 0; i < keys.enckeylen / sizeof(u32); i++)
+		ctx->key[i] = cpu_to_le32(((u32 *)keys.enckey)[i]);
 	ctx->key_len = keys.enckeylen;
 
 	memcpy(ctx->ipad, &istate.state, ctx->state_sz);
@@ -423,6 +495,17 @@ static int safexcel_context_control(struct safexcel_cipher_ctx *ctx,
 				CONTEXT_CONTROL_DIGEST_XCM |
 				ctx->hash_alg |
 				CONTEXT_CONTROL_SIZE(ctrl_size);
+		} else if (ctx->alg == SAFEXCEL_CHACHA20) {
+			/* Chacha20-Poly1305 */
+			cdesc->control_data.control0 =
+				CONTEXT_CONTROL_KEY_EN |
+				CONTEXT_CONTROL_CRYPTO_ALG_CHACHA20 |
+				(sreq->direction == SAFEXCEL_ENCRYPT ?
+					CONTEXT_CONTROL_TYPE_ENCRYPT_HASH_OUT :
+					CONTEXT_CONTROL_TYPE_HASH_DECRYPT_IN) |
+				ctx->hash_alg |
+				CONTEXT_CONTROL_SIZE(ctrl_size);
+			return 0;
 		} else {
 			ctrl_size += ctx->state_sz / sizeof(u32) * 2;
 			cdesc->control_data.control0 =
@@ -431,17 +514,21 @@ static int safexcel_context_control(struct safexcel_cipher_ctx *ctx,
 				ctx->hash_alg |
 				CONTEXT_CONTROL_SIZE(ctrl_size);
 		}
-		if (sreq->direction == SAFEXCEL_ENCRYPT)
-			cdesc->control_data.control0 |=
-				(ctx->xcm == EIP197_XCM_MODE_CCM) ?
-					CONTEXT_CONTROL_TYPE_HASH_ENCRYPT_OUT :
-					CONTEXT_CONTROL_TYPE_ENCRYPT_HASH_OUT;
 
+		if (sreq->direction == SAFEXCEL_ENCRYPT &&
+		    (ctx->xcm == EIP197_XCM_MODE_CCM ||
+		     ctx->aead == EIP197_AEAD_TYPE_IPSEC_ESP_GMAC))
+			cdesc->control_data.control0 |=
+				CONTEXT_CONTROL_TYPE_HASH_ENCRYPT_OUT;
+		else if (sreq->direction == SAFEXCEL_ENCRYPT)
+			cdesc->control_data.control0 |=
+				CONTEXT_CONTROL_TYPE_ENCRYPT_HASH_OUT;
+		else if (ctx->xcm == EIP197_XCM_MODE_CCM)
+			cdesc->control_data.control0 |=
+				CONTEXT_CONTROL_TYPE_DECRYPT_HASH_IN;
 		else
 			cdesc->control_data.control0 |=
-				(ctx->xcm == EIP197_XCM_MODE_CCM) ?
-					CONTEXT_CONTROL_TYPE_DECRYPT_HASH_IN :
-					CONTEXT_CONTROL_TYPE_HASH_DECRYPT_IN;
+				CONTEXT_CONTROL_TYPE_HASH_DECRYPT_IN;
 	} else {
 		if (sreq->direction == SAFEXCEL_ENCRYPT)
 			cdesc->control_data.control0 =
@@ -480,6 +567,12 @@ static int safexcel_context_control(struct safexcel_cipher_ctx *ctx,
 				ctx->key_len >> ctx->xts);
 			return -EINVAL;
 		}
+	} else if (ctx->alg == SAFEXCEL_CHACHA20) {
+		cdesc->control_data.control0 |=
+			CONTEXT_CONTROL_CRYPTO_ALG_CHACHA20;
+	} else if (ctx->alg == SAFEXCEL_SM4) {
+		cdesc->control_data.control0 |=
+			CONTEXT_CONTROL_CRYPTO_ALG_SM4;
 	}
 
 	return 0;
@@ -1295,7 +1388,7 @@ static int safexcel_skcipher_aesctr_setkey(struct crypto_skcipher *ctfm,
 
 	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma) {
 		for (i = 0; i < keylen / sizeof(u32); i++) {
-			if (ctx->key[i] != cpu_to_le32(aes.key_enc[i])) {
+			if (le32_to_cpu(ctx->key[i]) != aes.key_enc[i]) {
 				ctx->base.needs_inv = true;
 				break;
 			}
@@ -1451,13 +1544,11 @@ static int safexcel_des3_ede_setkey(struct crypto_skcipher *ctfm,
 		return err;
 
 	/* if context exits and key changed, need to invalidate it */
-	if (ctx->base.ctxr_dma) {
+	if (ctx->base.ctxr_dma)
 		if (memcmp(ctx->key, key, len))
 			ctx->base.needs_inv = true;
-	}
 
 	memcpy(ctx->key, key, len);
-
 	ctx->key_len = len;
 
 	return 0;
@@ -1777,6 +1868,312 @@ struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_des3_ede = {
 	},
 };
 
+static int safexcel_aead_sha256_des3_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_sha256_cra_init(tfm);
+	ctx->alg = SAFEXCEL_3DES; /* override default */
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha256_cbc_des3_ede = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_DES | SAFEXCEL_ALG_SHA2_256,
+	.alg.aead = {
+		.setkey = safexcel_aead_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = DES3_EDE_BLOCK_SIZE,
+		.maxauthsize = SHA256_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha256),cbc(des3_ede))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha256-cbc-des3_ede",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha256_des3_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_sha224_des3_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_sha224_cra_init(tfm);
+	ctx->alg = SAFEXCEL_3DES; /* override default */
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_des3_ede = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_DES | SAFEXCEL_ALG_SHA2_256,
+	.alg.aead = {
+		.setkey = safexcel_aead_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = DES3_EDE_BLOCK_SIZE,
+		.maxauthsize = SHA224_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha224),cbc(des3_ede))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha224-cbc-des3_ede",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha224_des3_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_sha512_des3_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_sha512_cra_init(tfm);
+	ctx->alg = SAFEXCEL_3DES; /* override default */
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha512_cbc_des3_ede = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_DES | SAFEXCEL_ALG_SHA2_512,
+	.alg.aead = {
+		.setkey = safexcel_aead_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = DES3_EDE_BLOCK_SIZE,
+		.maxauthsize = SHA512_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha512),cbc(des3_ede))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha512-cbc-des3_ede",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha512_des3_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_sha384_des3_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_sha384_cra_init(tfm);
+	ctx->alg = SAFEXCEL_3DES; /* override default */
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha384_cbc_des3_ede = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_DES | SAFEXCEL_ALG_SHA2_512,
+	.alg.aead = {
+		.setkey = safexcel_aead_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = DES3_EDE_BLOCK_SIZE,
+		.maxauthsize = SHA384_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha384),cbc(des3_ede))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha384-cbc-des3_ede",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha384_des3_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_sha1_des_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_sha1_cra_init(tfm);
+	ctx->alg = SAFEXCEL_DES; /* override default */
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_des = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_DES | SAFEXCEL_ALG_SHA1,
+	.alg.aead = {
+		.setkey = safexcel_aead_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = DES_BLOCK_SIZE,
+		.maxauthsize = SHA1_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha1),cbc(des))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha1-cbc-des",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha1_des_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_sha256_des_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_sha256_cra_init(tfm);
+	ctx->alg = SAFEXCEL_DES; /* override default */
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha256_cbc_des = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_DES | SAFEXCEL_ALG_SHA2_256,
+	.alg.aead = {
+		.setkey = safexcel_aead_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = DES_BLOCK_SIZE,
+		.maxauthsize = SHA256_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha256),cbc(des))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha256-cbc-des",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha256_des_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_sha224_des_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_sha224_cra_init(tfm);
+	ctx->alg = SAFEXCEL_DES; /* override default */
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_des = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_DES | SAFEXCEL_ALG_SHA2_256,
+	.alg.aead = {
+		.setkey = safexcel_aead_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = DES_BLOCK_SIZE,
+		.maxauthsize = SHA224_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha224),cbc(des))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha224-cbc-des",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha224_des_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_sha512_des_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_sha512_cra_init(tfm);
+	ctx->alg = SAFEXCEL_DES; /* override default */
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha512_cbc_des = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_DES | SAFEXCEL_ALG_SHA2_512,
+	.alg.aead = {
+		.setkey = safexcel_aead_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = DES_BLOCK_SIZE,
+		.maxauthsize = SHA512_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha512),cbc(des))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha512-cbc-des",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha512_des_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_sha384_des_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_sha384_cra_init(tfm);
+	ctx->alg = SAFEXCEL_DES; /* override default */
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha384_cbc_des = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_DES | SAFEXCEL_ALG_SHA2_512,
+	.alg.aead = {
+		.setkey = safexcel_aead_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = DES_BLOCK_SIZE,
+		.maxauthsize = SHA384_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha384),cbc(des))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha384-cbc-des",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha384_des_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
 static int safexcel_aead_sha1_ctr_cra_init(struct crypto_tfm *tfm)
 {
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
@@ -1972,7 +2369,7 @@ static int safexcel_skcipher_aesxts_setkey(struct crypto_skcipher *ctfm,
 
 	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma) {
 		for (i = 0; i < keylen / sizeof(u32); i++) {
-			if (ctx->key[i] != cpu_to_le32(aes.key_enc[i])) {
+			if (le32_to_cpu(ctx->key[i]) != aes.key_enc[i]) {
 				ctx->base.needs_inv = true;
 				break;
 			}
@@ -1991,8 +2388,8 @@ static int safexcel_skcipher_aesxts_setkey(struct crypto_skcipher *ctfm,
 
 	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma) {
 		for (i = 0; i < keylen / sizeof(u32); i++) {
-			if (ctx->key[i + keylen / sizeof(u32)] !=
-			    cpu_to_le32(aes.key_enc[i])) {
+			if (le32_to_cpu(ctx->key[i + keylen / sizeof(u32)]) !=
+			    aes.key_enc[i]) {
 				ctx->base.needs_inv = true;
 				break;
 			}
@@ -2082,7 +2479,7 @@ static int safexcel_aead_gcm_setkey(struct crypto_aead *ctfm, const u8 *key,
 
 	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma) {
 		for (i = 0; i < len / sizeof(u32); i++) {
-			if (ctx->key[i] != cpu_to_le32(aes.key_enc[i])) {
+			if (le32_to_cpu(ctx->key[i]) != aes.key_enc[i]) {
 				ctx->base.needs_inv = true;
 				break;
 			}
@@ -2109,7 +2506,7 @@ static int safexcel_aead_gcm_setkey(struct crypto_aead *ctfm, const u8 *key,
 
 	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma) {
 		for (i = 0; i < AES_BLOCK_SIZE / sizeof(u32); i++) {
-			if (ctx->ipad[i] != cpu_to_be32(hashkey[i])) {
+			if (be32_to_cpu(ctx->ipad[i]) != hashkey[i]) {
 				ctx->base.needs_inv = true;
 				break;
 			}
@@ -2199,7 +2596,7 @@ static int safexcel_aead_ccm_setkey(struct crypto_aead *ctfm, const u8 *key,
 
 	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma) {
 		for (i = 0; i < len / sizeof(u32); i++) {
-			if (ctx->key[i] != cpu_to_le32(aes.key_enc[i])) {
+			if (le32_to_cpu(ctx->key[i]) != aes.key_enc[i]) {
 				ctx->base.needs_inv = true;
 				break;
 			}
@@ -2303,3 +2700,938 @@ struct safexcel_alg_template safexcel_alg_ccm = {
 		},
 	},
 };
+
+static void safexcel_chacha20_setkey(struct safexcel_cipher_ctx *ctx,
+				     const u8 *key)
+{
+	struct safexcel_crypto_priv *priv = ctx->priv;
+
+	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma)
+		if (memcmp(ctx->key, key, CHACHA_KEY_SIZE))
+			ctx->base.needs_inv = true;
+
+	memcpy(ctx->key, key, CHACHA_KEY_SIZE);
+	ctx->key_len = CHACHA_KEY_SIZE;
+}
+
+static int safexcel_skcipher_chacha20_setkey(struct crypto_skcipher *ctfm,
+					     const u8 *key, unsigned int len)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_skcipher_ctx(ctfm);
+
+	if (len != CHACHA_KEY_SIZE) {
+		crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	safexcel_chacha20_setkey(ctx, key);
+
+	return 0;
+}
+
+static int safexcel_skcipher_chacha20_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_skcipher_cra_init(tfm);
+	ctx->alg  = SAFEXCEL_CHACHA20;
+	ctx->mode = CONTEXT_CONTROL_CHACHA20_MODE_256_32;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_chacha20 = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.algo_mask = SAFEXCEL_ALG_CHACHA20,
+	.alg.skcipher = {
+		.setkey = safexcel_skcipher_chacha20_setkey,
+		.encrypt = safexcel_encrypt,
+		.decrypt = safexcel_decrypt,
+		.min_keysize = CHACHA_KEY_SIZE,
+		.max_keysize = CHACHA_KEY_SIZE,
+		.ivsize = CHACHA_IV_SIZE,
+		.base = {
+			.cra_name = "chacha20",
+			.cra_driver_name = "safexcel-chacha20",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_chacha20_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_chachapoly_setkey(struct crypto_aead *ctfm,
+				    const u8 *key, unsigned int len)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_aead_ctx(ctfm);
+
+	if (ctx->aead  == EIP197_AEAD_TYPE_IPSEC_ESP &&
+	    len > EIP197_AEAD_IPSEC_NONCE_SIZE) {
+		/* ESP variant has nonce appended to key */
+		len -= EIP197_AEAD_IPSEC_NONCE_SIZE;
+		ctx->nonce = *(u32 *)(key + len);
+	}
+	if (len != CHACHA_KEY_SIZE) {
+		crypto_aead_set_flags(ctfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	safexcel_chacha20_setkey(ctx, key);
+
+	return 0;
+}
+
+static int safexcel_aead_chachapoly_setauthsize(struct crypto_aead *tfm,
+					 unsigned int authsize)
+{
+	if (authsize != POLY1305_DIGEST_SIZE)
+		return -EINVAL;
+	return 0;
+}
+
+static int safexcel_aead_chachapoly_crypt(struct aead_request *req,
+					  enum safexcel_cipher_direction dir)
+{
+	struct safexcel_cipher_req *creq = aead_request_ctx(req);
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_tfm *tfm = crypto_aead_tfm(aead);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aead_request *subreq = aead_request_ctx(req);
+	u32 key[CHACHA_KEY_SIZE / sizeof(u32) + 1];
+	int ret = 0;
+
+	/*
+	 * Instead of wasting time detecting umpteen silly corner cases,
+	 * just dump all "small" requests to the fallback implementation.
+	 * HW would not be faster on such small requests anyway.
+	 */
+	if (likely((ctx->aead != EIP197_AEAD_TYPE_IPSEC_ESP ||
+		    req->assoclen >= EIP197_AEAD_IPSEC_IV_SIZE) &&
+		   req->cryptlen > POLY1305_DIGEST_SIZE)) {
+		return safexcel_queue_req(&req->base, creq, dir);
+	}
+
+	/* HW cannot do full (AAD+payload) zero length, use fallback */
+	memcpy(key, ctx->key, CHACHA_KEY_SIZE);
+	if (ctx->aead == EIP197_AEAD_TYPE_IPSEC_ESP) {
+		/* ESP variant has nonce appended to the key */
+		key[CHACHA_KEY_SIZE / sizeof(u32)] = ctx->nonce;
+		ret = crypto_aead_setkey(ctx->fback, (u8 *)key,
+					 CHACHA_KEY_SIZE +
+					 EIP197_AEAD_IPSEC_NONCE_SIZE);
+	} else {
+		ret = crypto_aead_setkey(ctx->fback, (u8 *)key,
+					 CHACHA_KEY_SIZE);
+	}
+	if (ret) {
+		crypto_aead_clear_flags(aead, CRYPTO_TFM_REQ_MASK);
+		crypto_aead_set_flags(aead, crypto_aead_get_flags(ctx->fback) &
+					    CRYPTO_TFM_REQ_MASK);
+		return ret;
+	}
+
+	aead_request_set_tfm(subreq, ctx->fback);
+	aead_request_set_callback(subreq, req->base.flags, req->base.complete,
+				  req->base.data);
+	aead_request_set_crypt(subreq, req->src, req->dst, req->cryptlen,
+			       req->iv);
+	aead_request_set_ad(subreq, req->assoclen);
+
+	return (dir ==  SAFEXCEL_ENCRYPT) ?
+		crypto_aead_encrypt(subreq) :
+		crypto_aead_decrypt(subreq);
+}
+
+static int safexcel_aead_chachapoly_encrypt(struct aead_request *req)
+{
+	return safexcel_aead_chachapoly_crypt(req, SAFEXCEL_ENCRYPT);
+}
+
+static int safexcel_aead_chachapoly_decrypt(struct aead_request *req)
+{
+	return safexcel_aead_chachapoly_crypt(req, SAFEXCEL_DECRYPT);
+}
+
+static int safexcel_aead_fallback_cra_init(struct crypto_tfm *tfm)
+{
+	struct crypto_aead *aead = __crypto_aead_cast(tfm);
+	struct aead_alg *alg = crypto_aead_alg(aead);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_cra_init(tfm);
+
+	/* Allocate fallback implementation */
+	ctx->fback = crypto_alloc_aead(alg->base.cra_name, 0,
+				       CRYPTO_ALG_ASYNC |
+				       CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(ctx->fback))
+		return PTR_ERR(ctx->fback);
+
+	crypto_aead_set_reqsize(aead, max(sizeof(struct safexcel_cipher_req),
+					  sizeof(struct aead_request) +
+					  crypto_aead_reqsize(ctx->fback)));
+
+	return 0;
+}
+
+static int safexcel_aead_chachapoly_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_fallback_cra_init(tfm);
+	ctx->alg  = SAFEXCEL_CHACHA20;
+	ctx->mode = CONTEXT_CONTROL_CHACHA20_MODE_256_32 |
+		    CONTEXT_CONTROL_CHACHA20_MODE_CALC_OTK;
+	ctx->hash_alg = CONTEXT_CONTROL_CRYPTO_ALG_POLY1305;
+	ctx->state_sz = 0; /* Precomputed by HW */
+	return 0;
+}
+
+static void safexcel_aead_fallback_cra_exit(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_aead(ctx->fback);
+	safexcel_aead_cra_exit(tfm);
+}
+
+struct safexcel_alg_template safexcel_alg_chachapoly = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_CHACHA20 | SAFEXCEL_ALG_POLY1305,
+	.alg.aead = {
+		.setkey = safexcel_aead_chachapoly_setkey,
+		.setauthsize = safexcel_aead_chachapoly_setauthsize,
+		.encrypt = safexcel_aead_chachapoly_encrypt,
+		.decrypt = safexcel_aead_chachapoly_decrypt,
+		.ivsize = CHACHAPOLY_IV_SIZE,
+		.maxauthsize = POLY1305_DIGEST_SIZE,
+		.base = {
+			.cra_name = "rfc7539(chacha20,poly1305)",
+			.cra_driver_name = "safexcel-chacha20-poly1305",
+			/* +1 to put it above HW chacha + SW poly */
+			.cra_priority = SAFEXCEL_CRA_PRIORITY + 1,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY |
+				     CRYPTO_ALG_NEED_FALLBACK,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_chachapoly_cra_init,
+			.cra_exit = safexcel_aead_fallback_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_chachapolyesp_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret;
+
+	ret = safexcel_aead_chachapoly_cra_init(tfm);
+	ctx->aead  = EIP197_AEAD_TYPE_IPSEC_ESP;
+	return ret;
+}
+
+struct safexcel_alg_template safexcel_alg_chachapoly_esp = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_CHACHA20 | SAFEXCEL_ALG_POLY1305,
+	.alg.aead = {
+		.setkey = safexcel_aead_chachapoly_setkey,
+		.setauthsize = safexcel_aead_chachapoly_setauthsize,
+		.encrypt = safexcel_aead_chachapoly_encrypt,
+		.decrypt = safexcel_aead_chachapoly_decrypt,
+		.ivsize = CHACHAPOLY_IV_SIZE - EIP197_AEAD_IPSEC_NONCE_SIZE,
+		.maxauthsize = POLY1305_DIGEST_SIZE,
+		.base = {
+			.cra_name = "rfc7539esp(chacha20,poly1305)",
+			.cra_driver_name = "safexcel-chacha20-poly1305-esp",
+			/* +1 to put it above HW chacha + SW poly */
+			.cra_priority = SAFEXCEL_CRA_PRIORITY + 1,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY |
+				     CRYPTO_ALG_NEED_FALLBACK,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_chachapolyesp_cra_init,
+			.cra_exit = safexcel_aead_fallback_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_skcipher_sm4_setkey(struct crypto_skcipher *ctfm,
+					const u8 *key, unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(ctfm);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct safexcel_crypto_priv *priv = ctx->priv;
+
+	if (len != SM4_KEY_SIZE) {
+		crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma)
+		if (memcmp(ctx->key, key, SM4_KEY_SIZE))
+			ctx->base.needs_inv = true;
+
+	memcpy(ctx->key, key, SM4_KEY_SIZE);
+	ctx->key_len = SM4_KEY_SIZE;
+
+	return 0;
+}
+
+static int safexcel_sm4_blk_encrypt(struct skcipher_request *req)
+{
+	/* Workaround for HW bug: EIP96 4.3 does not report blocksize error */
+	if (req->cryptlen & (SM4_BLOCK_SIZE - 1))
+		return -EINVAL;
+	else
+		return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+					  SAFEXCEL_ENCRYPT);
+}
+
+static int safexcel_sm4_blk_decrypt(struct skcipher_request *req)
+{
+	/* Workaround for HW bug: EIP96 4.3 does not report blocksize error */
+	if (req->cryptlen & (SM4_BLOCK_SIZE - 1))
+		return -EINVAL;
+	else
+		return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+					  SAFEXCEL_DECRYPT);
+}
+
+static int safexcel_skcipher_sm4_ecb_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_skcipher_cra_init(tfm);
+	ctx->alg  = SAFEXCEL_SM4;
+	ctx->mode = CONTEXT_CONTROL_CRYPTO_MODE_ECB;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_ecb_sm4 = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.algo_mask = SAFEXCEL_ALG_SM4,
+	.alg.skcipher = {
+		.setkey = safexcel_skcipher_sm4_setkey,
+		.encrypt = safexcel_sm4_blk_encrypt,
+		.decrypt = safexcel_sm4_blk_decrypt,
+		.min_keysize = SM4_KEY_SIZE,
+		.max_keysize = SM4_KEY_SIZE,
+		.base = {
+			.cra_name = "ecb(sm4)",
+			.cra_driver_name = "safexcel-ecb-sm4",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = SM4_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_sm4_ecb_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_skcipher_sm4_cbc_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_skcipher_cra_init(tfm);
+	ctx->alg  = SAFEXCEL_SM4;
+	ctx->mode = CONTEXT_CONTROL_CRYPTO_MODE_CBC;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_cbc_sm4 = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.algo_mask = SAFEXCEL_ALG_SM4,
+	.alg.skcipher = {
+		.setkey = safexcel_skcipher_sm4_setkey,
+		.encrypt = safexcel_sm4_blk_encrypt,
+		.decrypt = safexcel_sm4_blk_decrypt,
+		.min_keysize = SM4_KEY_SIZE,
+		.max_keysize = SM4_KEY_SIZE,
+		.ivsize = SM4_BLOCK_SIZE,
+		.base = {
+			.cra_name = "cbc(sm4)",
+			.cra_driver_name = "safexcel-cbc-sm4",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = SM4_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_sm4_cbc_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_skcipher_sm4_ofb_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_skcipher_cra_init(tfm);
+	ctx->alg  = SAFEXCEL_SM4;
+	ctx->mode = CONTEXT_CONTROL_CRYPTO_MODE_OFB;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_ofb_sm4 = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.algo_mask = SAFEXCEL_ALG_SM4 | SAFEXCEL_ALG_AES_XFB,
+	.alg.skcipher = {
+		.setkey = safexcel_skcipher_sm4_setkey,
+		.encrypt = safexcel_encrypt,
+		.decrypt = safexcel_decrypt,
+		.min_keysize = SM4_KEY_SIZE,
+		.max_keysize = SM4_KEY_SIZE,
+		.ivsize = SM4_BLOCK_SIZE,
+		.base = {
+			.cra_name = "ofb(sm4)",
+			.cra_driver_name = "safexcel-ofb-sm4",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_sm4_ofb_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_skcipher_sm4_cfb_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_skcipher_cra_init(tfm);
+	ctx->alg  = SAFEXCEL_SM4;
+	ctx->mode = CONTEXT_CONTROL_CRYPTO_MODE_CFB;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_cfb_sm4 = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.algo_mask = SAFEXCEL_ALG_SM4 | SAFEXCEL_ALG_AES_XFB,
+	.alg.skcipher = {
+		.setkey = safexcel_skcipher_sm4_setkey,
+		.encrypt = safexcel_encrypt,
+		.decrypt = safexcel_decrypt,
+		.min_keysize = SM4_KEY_SIZE,
+		.max_keysize = SM4_KEY_SIZE,
+		.ivsize = SM4_BLOCK_SIZE,
+		.base = {
+			.cra_name = "cfb(sm4)",
+			.cra_driver_name = "safexcel-cfb-sm4",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_sm4_cfb_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_skcipher_sm4ctr_setkey(struct crypto_skcipher *ctfm,
+					   const u8 *key, unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(ctfm);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	/* last 4 bytes of key are the nonce! */
+	ctx->nonce = *(u32 *)(key + len - CTR_RFC3686_NONCE_SIZE);
+	/* exclude the nonce here */
+	len -= CTR_RFC3686_NONCE_SIZE;
+
+	return safexcel_skcipher_sm4_setkey(ctfm, key, len);
+}
+
+static int safexcel_skcipher_sm4_ctr_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_skcipher_cra_init(tfm);
+	ctx->alg  = SAFEXCEL_SM4;
+	ctx->mode = CONTEXT_CONTROL_CRYPTO_MODE_CTR_LOAD;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_ctr_sm4 = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.algo_mask = SAFEXCEL_ALG_SM4,
+	.alg.skcipher = {
+		.setkey = safexcel_skcipher_sm4ctr_setkey,
+		.encrypt = safexcel_encrypt,
+		.decrypt = safexcel_decrypt,
+		/* Add nonce size */
+		.min_keysize = SM4_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
+		.max_keysize = SM4_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
+		.ivsize = CTR_RFC3686_IV_SIZE,
+		.base = {
+			.cra_name = "rfc3686(ctr(sm4))",
+			.cra_driver_name = "safexcel-ctr-sm4",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_sm4_ctr_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_sm4_blk_encrypt(struct aead_request *req)
+{
+	/* Workaround for HW bug: EIP96 4.3 does not report blocksize error */
+	if (req->cryptlen & (SM4_BLOCK_SIZE - 1))
+		return -EINVAL;
+
+	return safexcel_queue_req(&req->base, aead_request_ctx(req),
+				  SAFEXCEL_ENCRYPT);
+}
+
+static int safexcel_aead_sm4_blk_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+
+	/* Workaround for HW bug: EIP96 4.3 does not report blocksize error */
+	if ((req->cryptlen - crypto_aead_authsize(tfm)) & (SM4_BLOCK_SIZE - 1))
+		return -EINVAL;
+
+	return safexcel_queue_req(&req->base, aead_request_ctx(req),
+				  SAFEXCEL_DECRYPT);
+}
+
+static int safexcel_aead_sm4cbc_sha1_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_cra_init(tfm);
+	ctx->alg = SAFEXCEL_SM4;
+	ctx->hash_alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA1;
+	ctx->state_sz = SHA1_DIGEST_SIZE;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_sm4 = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_SM4 | SAFEXCEL_ALG_SHA1,
+	.alg.aead = {
+		.setkey = safexcel_aead_setkey,
+		.encrypt = safexcel_aead_sm4_blk_encrypt,
+		.decrypt = safexcel_aead_sm4_blk_decrypt,
+		.ivsize = SM4_BLOCK_SIZE,
+		.maxauthsize = SHA1_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha1),cbc(sm4))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha1-cbc-sm4",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = SM4_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sm4cbc_sha1_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_fallback_setkey(struct crypto_aead *ctfm,
+					 const u8 *key, unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_aead_tfm(ctfm);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	/* Keep fallback cipher synchronized */
+	return crypto_aead_setkey(ctx->fback, (u8 *)key, len) ?:
+	       safexcel_aead_setkey(ctfm, key, len);
+}
+
+static int safexcel_aead_fallback_setauthsize(struct crypto_aead *ctfm,
+					      unsigned int authsize)
+{
+	struct crypto_tfm *tfm = crypto_aead_tfm(ctfm);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	/* Keep fallback cipher synchronized */
+	return crypto_aead_setauthsize(ctx->fback, authsize);
+}
+
+static int safexcel_aead_fallback_crypt(struct aead_request *req,
+					enum safexcel_cipher_direction dir)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_tfm *tfm = crypto_aead_tfm(aead);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aead_request *subreq = aead_request_ctx(req);
+
+	aead_request_set_tfm(subreq, ctx->fback);
+	aead_request_set_callback(subreq, req->base.flags, req->base.complete,
+				  req->base.data);
+	aead_request_set_crypt(subreq, req->src, req->dst, req->cryptlen,
+			       req->iv);
+	aead_request_set_ad(subreq, req->assoclen);
+
+	return (dir ==  SAFEXCEL_ENCRYPT) ?
+		crypto_aead_encrypt(subreq) :
+		crypto_aead_decrypt(subreq);
+}
+
+static int safexcel_aead_sm4cbc_sm3_encrypt(struct aead_request *req)
+{
+	struct safexcel_cipher_req *creq = aead_request_ctx(req);
+
+	/* Workaround for HW bug: EIP96 4.3 does not report blocksize error */
+	if (req->cryptlen & (SM4_BLOCK_SIZE - 1))
+		return -EINVAL;
+	else if (req->cryptlen || req->assoclen) /* If input length > 0 only */
+		return safexcel_queue_req(&req->base, creq, SAFEXCEL_ENCRYPT);
+
+	/* HW cannot do full (AAD+payload) zero length, use fallback */
+	return safexcel_aead_fallback_crypt(req, SAFEXCEL_ENCRYPT);
+}
+
+static int safexcel_aead_sm4cbc_sm3_decrypt(struct aead_request *req)
+{
+	struct safexcel_cipher_req *creq = aead_request_ctx(req);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+
+	/* Workaround for HW bug: EIP96 4.3 does not report blocksize error */
+	if ((req->cryptlen - crypto_aead_authsize(tfm)) & (SM4_BLOCK_SIZE - 1))
+		return -EINVAL;
+	else if (req->cryptlen > crypto_aead_authsize(tfm) || req->assoclen)
+		/* If input length > 0 only */
+		return safexcel_queue_req(&req->base, creq, SAFEXCEL_DECRYPT);
+
+	/* HW cannot do full (AAD+payload) zero length, use fallback */
+	return safexcel_aead_fallback_crypt(req, SAFEXCEL_DECRYPT);
+}
+
+static int safexcel_aead_sm4cbc_sm3_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_fallback_cra_init(tfm);
+	ctx->alg = SAFEXCEL_SM4;
+	ctx->hash_alg = CONTEXT_CONTROL_CRYPTO_ALG_SM3;
+	ctx->state_sz = SM3_DIGEST_SIZE;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sm3_cbc_sm4 = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_SM4 | SAFEXCEL_ALG_SM3,
+	.alg.aead = {
+		.setkey = safexcel_aead_fallback_setkey,
+		.setauthsize = safexcel_aead_fallback_setauthsize,
+		.encrypt = safexcel_aead_sm4cbc_sm3_encrypt,
+		.decrypt = safexcel_aead_sm4cbc_sm3_decrypt,
+		.ivsize = SM4_BLOCK_SIZE,
+		.maxauthsize = SM3_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sm3),cbc(sm4))",
+			.cra_driver_name = "safexcel-authenc-hmac-sm3-cbc-sm4",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY |
+				     CRYPTO_ALG_NEED_FALLBACK,
+			.cra_blocksize = SM4_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sm4cbc_sm3_cra_init,
+			.cra_exit = safexcel_aead_fallback_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_sm4ctr_sha1_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_sm4cbc_sha1_cra_init(tfm);
+	ctx->mode = CONTEXT_CONTROL_CRYPTO_MODE_CTR_LOAD;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_ctr_sm4 = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_SM4 | SAFEXCEL_ALG_SHA1,
+	.alg.aead = {
+		.setkey = safexcel_aead_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = CTR_RFC3686_IV_SIZE,
+		.maxauthsize = SHA1_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha1),rfc3686(ctr(sm4)))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha1-ctr-sm4",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sm4ctr_sha1_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_sm4ctr_sm3_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_sm4cbc_sm3_cra_init(tfm);
+	ctx->mode = CONTEXT_CONTROL_CRYPTO_MODE_CTR_LOAD;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sm3_ctr_sm4 = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_SM4 | SAFEXCEL_ALG_SM3,
+	.alg.aead = {
+		.setkey = safexcel_aead_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = CTR_RFC3686_IV_SIZE,
+		.maxauthsize = SM3_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sm3),rfc3686(ctr(sm4)))",
+			.cra_driver_name = "safexcel-authenc-hmac-sm3-ctr-sm4",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sm4ctr_sm3_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_rfc4106_gcm_setkey(struct crypto_aead *ctfm, const u8 *key,
+				       unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_aead_tfm(ctfm);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	/* last 4 bytes of key are the nonce! */
+	ctx->nonce = *(u32 *)(key + len - CTR_RFC3686_NONCE_SIZE);
+
+	len -= CTR_RFC3686_NONCE_SIZE;
+	return safexcel_aead_gcm_setkey(ctfm, key, len);
+}
+
+static int safexcel_rfc4106_gcm_setauthsize(struct crypto_aead *tfm,
+					    unsigned int authsize)
+{
+	return crypto_rfc4106_check_authsize(authsize);
+}
+
+static int safexcel_rfc4106_encrypt(struct aead_request *req)
+{
+	return crypto_ipsec_check_assoclen(req->assoclen) ?:
+	       safexcel_aead_encrypt(req);
+}
+
+static int safexcel_rfc4106_decrypt(struct aead_request *req)
+{
+	return crypto_ipsec_check_assoclen(req->assoclen) ?:
+	       safexcel_aead_decrypt(req);
+}
+
+static int safexcel_rfc4106_gcm_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret;
+
+	ret = safexcel_aead_gcm_cra_init(tfm);
+	ctx->aead  = EIP197_AEAD_TYPE_IPSEC_ESP;
+	return ret;
+}
+
+struct safexcel_alg_template safexcel_alg_rfc4106_gcm = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_AES | SAFEXCEL_ALG_GHASH,
+	.alg.aead = {
+		.setkey = safexcel_rfc4106_gcm_setkey,
+		.setauthsize = safexcel_rfc4106_gcm_setauthsize,
+		.encrypt = safexcel_rfc4106_encrypt,
+		.decrypt = safexcel_rfc4106_decrypt,
+		.ivsize = GCM_RFC4106_IV_SIZE,
+		.maxauthsize = GHASH_DIGEST_SIZE,
+		.base = {
+			.cra_name = "rfc4106(gcm(aes))",
+			.cra_driver_name = "safexcel-rfc4106-gcm-aes",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_rfc4106_gcm_cra_init,
+			.cra_exit = safexcel_aead_gcm_cra_exit,
+		},
+	},
+};
+
+static int safexcel_rfc4543_gcm_setauthsize(struct crypto_aead *tfm,
+					    unsigned int authsize)
+{
+	if (authsize != GHASH_DIGEST_SIZE)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int safexcel_rfc4543_gcm_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret;
+
+	ret = safexcel_aead_gcm_cra_init(tfm);
+	ctx->aead  = EIP197_AEAD_TYPE_IPSEC_ESP_GMAC;
+	return ret;
+}
+
+struct safexcel_alg_template safexcel_alg_rfc4543_gcm = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_AES | SAFEXCEL_ALG_GHASH,
+	.alg.aead = {
+		.setkey = safexcel_rfc4106_gcm_setkey,
+		.setauthsize = safexcel_rfc4543_gcm_setauthsize,
+		.encrypt = safexcel_rfc4106_encrypt,
+		.decrypt = safexcel_rfc4106_decrypt,
+		.ivsize = GCM_RFC4543_IV_SIZE,
+		.maxauthsize = GHASH_DIGEST_SIZE,
+		.base = {
+			.cra_name = "rfc4543(gcm(aes))",
+			.cra_driver_name = "safexcel-rfc4543-gcm-aes",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_rfc4543_gcm_cra_init,
+			.cra_exit = safexcel_aead_gcm_cra_exit,
+		},
+	},
+};
+
+static int safexcel_rfc4309_ccm_setkey(struct crypto_aead *ctfm, const u8 *key,
+				       unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_aead_tfm(ctfm);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	/* First byte of the nonce = L = always 3 for RFC4309 (4 byte ctr) */
+	*(u8 *)&ctx->nonce = EIP197_AEAD_IPSEC_COUNTER_SIZE - 1;
+	/* last 3 bytes of key are the nonce! */
+	memcpy((u8 *)&ctx->nonce + 1, key + len -
+	       EIP197_AEAD_IPSEC_CCM_NONCE_SIZE,
+	       EIP197_AEAD_IPSEC_CCM_NONCE_SIZE);
+
+	len -= EIP197_AEAD_IPSEC_CCM_NONCE_SIZE;
+	return safexcel_aead_ccm_setkey(ctfm, key, len);
+}
+
+static int safexcel_rfc4309_ccm_setauthsize(struct crypto_aead *tfm,
+					    unsigned int authsize)
+{
+	/* Borrowed from crypto/ccm.c */
+	switch (authsize) {
+	case 8:
+	case 12:
+	case 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int safexcel_rfc4309_ccm_encrypt(struct aead_request *req)
+{
+	struct safexcel_cipher_req *creq = aead_request_ctx(req);
+
+	/* Borrowed from crypto/ccm.c */
+	if (req->assoclen != 16 && req->assoclen != 20)
+		return -EINVAL;
+
+	return safexcel_queue_req(&req->base, creq, SAFEXCEL_ENCRYPT);
+}
+
+static int safexcel_rfc4309_ccm_decrypt(struct aead_request *req)
+{
+	struct safexcel_cipher_req *creq = aead_request_ctx(req);
+
+	/* Borrowed from crypto/ccm.c */
+	if (req->assoclen != 16 && req->assoclen != 20)
+		return -EINVAL;
+
+	return safexcel_queue_req(&req->base, creq, SAFEXCEL_DECRYPT);
+}
+
+static int safexcel_rfc4309_ccm_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret;
+
+	ret = safexcel_aead_ccm_cra_init(tfm);
+	ctx->aead  = EIP197_AEAD_TYPE_IPSEC_ESP;
+	return ret;
+}
+
+struct safexcel_alg_template safexcel_alg_rfc4309_ccm = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.algo_mask = SAFEXCEL_ALG_AES | SAFEXCEL_ALG_CBC_MAC_ALL,
+	.alg.aead = {
+		.setkey = safexcel_rfc4309_ccm_setkey,
+		.setauthsize = safexcel_rfc4309_ccm_setauthsize,
+		.encrypt = safexcel_rfc4309_ccm_encrypt,
+		.decrypt = safexcel_rfc4309_ccm_decrypt,
+		.ivsize = EIP197_AEAD_IPSEC_IV_SIZE,
+		.maxauthsize = AES_BLOCK_SIZE,
+		.base = {
+			.cra_name = "rfc4309(ccm(aes))",
+			.cra_driver_name = "safexcel-rfc4309-ccm-aes",
+			.cra_priority = SAFEXCEL_CRA_PRIORITY,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_rfc4309_ccm_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 2effb6d21e8b..2134daef24f6 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -5,9 +5,13 @@
  * Antoine Tenart <antoine.tenart@free-electrons.com>
  */
 
+#include <crypto/aes.h>
 #include <crypto/hmac.h>
 #include <crypto/md5.h>
 #include <crypto/sha.h>
+#include <crypto/sha3.h>
+#include <crypto/skcipher.h>
+#include <crypto/sm3.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmapool.h>
@@ -19,9 +23,19 @@ struct safexcel_ahash_ctx {
 	struct safexcel_crypto_priv *priv;
 
 	u32 alg;
-
-	u32 ipad[SHA512_DIGEST_SIZE / sizeof(u32)];
-	u32 opad[SHA512_DIGEST_SIZE / sizeof(u32)];
+	u8  key_sz;
+	bool cbcmac;
+	bool do_fallback;
+	bool fb_init_done;
+	bool fb_do_setkey;
+
+	__le32 ipad[SHA3_512_BLOCK_SIZE / sizeof(__le32)];
+	__le32 opad[SHA3_512_BLOCK_SIZE / sizeof(__le32)];
+
+	struct crypto_cipher *kaes;
+	struct crypto_ahash *fback;
+	struct crypto_shash *shpre;
+	struct shash_desc *shdesc;
 };
 
 struct safexcel_ahash_req {
@@ -31,6 +45,8 @@ struct safexcel_ahash_req {
 	bool needs_inv;
 	bool hmac_zlen;
 	bool len_is_le;
+	bool not_first;
+	bool xcbcmac;
 
 	int nents;
 	dma_addr_t result_dma;
@@ -39,7 +55,9 @@ struct safexcel_ahash_req {
 
 	u8 state_sz;    /* expected state size, only set once */
 	u8 block_sz;    /* block size, only set once */
-	u32 state[SHA512_DIGEST_SIZE / sizeof(u32)] __aligned(sizeof(u32));
+	u8 digest_sz;   /* output digest size, only set once */
+	__le32 state[SHA3_512_BLOCK_SIZE /
+		     sizeof(__le32)] __aligned(sizeof(__le32));
 
 	u64 len;
 	u64 processed;
@@ -57,21 +75,31 @@ static inline u64 safexcel_queued_len(struct safexcel_ahash_req *req)
 }
 
 static void safexcel_hash_token(struct safexcel_command_desc *cdesc,
-				u32 input_length, u32 result_length)
+				u32 input_length, u32 result_length,
+				bool cbcmac)
 {
 	struct safexcel_token *token =
 		(struct safexcel_token *)cdesc->control_data.token;
 
 	token[0].opcode = EIP197_TOKEN_OPCODE_DIRECTION;
 	token[0].packet_length = input_length;
-	token[0].stat = EIP197_TOKEN_STAT_LAST_HASH;
 	token[0].instructions = EIP197_TOKEN_INS_TYPE_HASH;
 
-	token[1].opcode = EIP197_TOKEN_OPCODE_INSERT;
-	token[1].packet_length = result_length;
-	token[1].stat = EIP197_TOKEN_STAT_LAST_HASH |
+	input_length &= 15;
+	if (unlikely(cbcmac && input_length)) {
+		token[1].opcode = EIP197_TOKEN_OPCODE_INSERT;
+		token[1].packet_length = 16 - input_length;
+		token[1].stat = EIP197_TOKEN_STAT_LAST_HASH;
+		token[1].instructions = EIP197_TOKEN_INS_TYPE_HASH;
+	} else {
+		token[0].stat = EIP197_TOKEN_STAT_LAST_HASH;
+	}
+
+	token[2].opcode = EIP197_TOKEN_OPCODE_INSERT;
+	token[2].stat = EIP197_TOKEN_STAT_LAST_HASH |
 			EIP197_TOKEN_STAT_LAST_PACKET;
-	token[1].instructions = EIP197_TOKEN_INS_TYPE_OUTPUT |
+	token[2].packet_length = result_length;
+	token[2].instructions = EIP197_TOKEN_INS_TYPE_OUTPUT |
 				EIP197_TOKEN_INS_INSERT_HASH_DIGEST;
 }
 
@@ -82,29 +110,48 @@ static void safexcel_context_control(struct safexcel_ahash_ctx *ctx,
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	u64 count = 0;
 
-	cdesc->control_data.control0 |= ctx->alg;
+	cdesc->control_data.control0 = ctx->alg;
 
 	/*
 	 * Copy the input digest if needed, and setup the context
 	 * fields. Do this now as we need it to setup the first command
 	 * descriptor.
 	 */
-	if (!req->processed) {
-		/* First - and possibly only - block of basic hash only */
-		if (req->finish) {
+	if (unlikely(req->digest == CONTEXT_CONTROL_DIGEST_XCM)) {
+		if (req->xcbcmac)
+			memcpy(ctx->base.ctxr->data, ctx->ipad, ctx->key_sz);
+		else
+			memcpy(ctx->base.ctxr->data, req->state, req->state_sz);
+
+		if (!req->finish && req->xcbcmac)
 			cdesc->control_data.control0 |=
+				CONTEXT_CONTROL_DIGEST_XCM |
+				CONTEXT_CONTROL_TYPE_HASH_OUT  |
+				CONTEXT_CONTROL_NO_FINISH_HASH |
+				CONTEXT_CONTROL_SIZE(req->state_sz /
+						     sizeof(u32));
+		else
+			cdesc->control_data.control0 |=
+				CONTEXT_CONTROL_DIGEST_XCM |
+				CONTEXT_CONTROL_TYPE_HASH_OUT  |
+				CONTEXT_CONTROL_SIZE(req->state_sz /
+						     sizeof(u32));
+		return;
+	} else if (!req->processed) {
+		/* First - and possibly only - block of basic hash only */
+		if (req->finish)
+			cdesc->control_data.control0 |= req->digest |
 				CONTEXT_CONTROL_TYPE_HASH_OUT |
 				CONTEXT_CONTROL_RESTART_HASH  |
 				/* ensure its not 0! */
 				CONTEXT_CONTROL_SIZE(1);
-		} else {
-			cdesc->control_data.control0 |=
+		else
+			cdesc->control_data.control0 |= req->digest |
 				CONTEXT_CONTROL_TYPE_HASH_OUT  |
 				CONTEXT_CONTROL_RESTART_HASH   |
 				CONTEXT_CONTROL_NO_FINISH_HASH |
 				/* ensure its not 0! */
 				CONTEXT_CONTROL_SIZE(1);
-		}
 		return;
 	}
 
@@ -204,7 +251,7 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv,
 	}
 
 	if (sreq->result_dma) {
-		dma_unmap_single(priv->dev, sreq->result_dma, sreq->state_sz,
+		dma_unmap_single(priv->dev, sreq->result_dma, sreq->digest_sz,
 				 DMA_FROM_DEVICE);
 		sreq->result_dma = 0;
 	}
@@ -223,7 +270,7 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv,
 			memcpy(sreq->cache, sreq->state,
 			       crypto_ahash_digestsize(ahash));
 
-			memcpy(sreq->state, ctx->opad, sreq->state_sz);
+			memcpy(sreq->state, ctx->opad, sreq->digest_sz);
 
 			sreq->len = sreq->block_sz +
 				    crypto_ahash_digestsize(ahash);
@@ -238,8 +285,14 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv,
 			return 1;
 		}
 
-		memcpy(areq->result, sreq->state,
-		       crypto_ahash_digestsize(ahash));
+		if (unlikely(sreq->digest == CONTEXT_CONTROL_DIGEST_XCM &&
+			     ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_CRC32)) {
+			/* Undo final XOR with 0xffffffff ...*/
+			*(__le32 *)areq->result = ~sreq->state[0];
+		} else {
+			memcpy(areq->result, sreq->state,
+			       crypto_ahash_digestsize(ahash));
+		}
 	}
 
 	cache_len = safexcel_queued_len(sreq);
@@ -261,10 +314,10 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 	struct safexcel_command_desc *cdesc, *first_cdesc = NULL;
 	struct safexcel_result_desc *rdesc;
 	struct scatterlist *sg;
-	int i, extra = 0, n_cdesc = 0, ret = 0;
-	u64 queued, len, cache_len;
+	int i, extra = 0, n_cdesc = 0, ret = 0, cache_len, skip = 0;
+	u64 queued, len;
 
-	queued = len = safexcel_queued_len(req);
+	queued = safexcel_queued_len(req);
 	if (queued <= HASH_CACHE_SIZE)
 		cache_len = queued;
 	else
@@ -287,15 +340,52 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 				   areq->nbytes - extra);
 
 		queued -= extra;
-		len -= extra;
 
 		if (!queued) {
 			*commands = 0;
 			*results = 0;
 			return 0;
 		}
+
+		extra = 0;
 	}
 
+	if (unlikely(req->xcbcmac && req->processed > AES_BLOCK_SIZE)) {
+		if (unlikely(cache_len < AES_BLOCK_SIZE)) {
+			/*
+			 * Cache contains less than 1 full block, complete.
+			 */
+			extra = AES_BLOCK_SIZE - cache_len;
+			if (queued > cache_len) {
+				/* More data follows: borrow bytes */
+				u64 tmp = queued - cache_len;
+
+				skip = min_t(u64, tmp, extra);
+				sg_pcopy_to_buffer(areq->src,
+					sg_nents(areq->src),
+					req->cache + cache_len,
+					skip, 0);
+			}
+			extra -= skip;
+			memset(req->cache + cache_len + skip, 0, extra);
+			if (!ctx->cbcmac && extra) {
+				// 10- padding for XCBCMAC & CMAC
+				req->cache[cache_len + skip] = 0x80;
+				// HW will use K2 iso K3 - compensate!
+				for (i = 0; i < AES_BLOCK_SIZE / sizeof(u32); i++)
+					((__be32 *)req->cache)[i] ^=
+					  cpu_to_be32(le32_to_cpu(
+					    ctx->ipad[i] ^ ctx->ipad[i + 4]));
+			}
+			cache_len = AES_BLOCK_SIZE;
+			queued = queued + extra;
+		}
+
+		/* XCBC continue: XOR previous result into 1st word */
+		crypto_xor(req->cache, (const u8 *)req->state, AES_BLOCK_SIZE);
+	}
+
+	len = queued;
 	/* Add a command descriptor for the cached data, if any */
 	if (cache_len) {
 		req->cache_dma = dma_map_single(priv->dev, req->cache,
@@ -306,8 +396,8 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 		req->cache_sz = cache_len;
 		first_cdesc = safexcel_add_cdesc(priv, ring, 1,
 						 (cache_len == len),
-						 req->cache_dma, cache_len, len,
-						 ctx->base.ctxr_dma);
+						 req->cache_dma, cache_len,
+						 len, ctx->base.ctxr_dma);
 		if (IS_ERR(first_cdesc)) {
 			ret = PTR_ERR(first_cdesc);
 			goto unmap_cache;
@@ -319,10 +409,6 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 			goto send_command;
 	}
 
-	/* Skip descriptor generation for zero-length requests */
-	if (!areq->nbytes)
-		goto send_command;
-
 	/* Now handle the current ahash request buffer(s) */
 	req->nents = dma_map_sg(priv->dev, areq->src,
 				sg_nents_for_len(areq->src,
@@ -336,26 +422,34 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 	for_each_sg(areq->src, sg, req->nents, i) {
 		int sglen = sg_dma_len(sg);
 
+		if (unlikely(sglen <= skip)) {
+			skip -= sglen;
+			continue;
+		}
+
 		/* Do not overflow the request */
-		if (queued < sglen)
+		if ((queued + skip) <= sglen)
 			sglen = queued;
+		else
+			sglen -= skip;
 
 		cdesc = safexcel_add_cdesc(priv, ring, !n_cdesc,
 					   !(queued - sglen),
-					   sg_dma_address(sg),
-					   sglen, len, ctx->base.ctxr_dma);
+					   sg_dma_address(sg) + skip, sglen,
+					   len, ctx->base.ctxr_dma);
 		if (IS_ERR(cdesc)) {
 			ret = PTR_ERR(cdesc);
 			goto unmap_sg;
 		}
-		n_cdesc++;
 
-		if (n_cdesc == 1)
+		if (!n_cdesc)
 			first_cdesc = cdesc;
+		n_cdesc++;
 
 		queued -= sglen;
 		if (!queued)
 			break;
+		skip = 0;
 	}
 
 send_command:
@@ -363,9 +457,9 @@ send_command:
 	safexcel_context_control(ctx, req, first_cdesc);
 
 	/* Add the token */
-	safexcel_hash_token(first_cdesc, len, req->state_sz);
+	safexcel_hash_token(first_cdesc, len, req->digest_sz, ctx->cbcmac);
 
-	req->result_dma = dma_map_single(priv->dev, req->state, req->state_sz,
+	req->result_dma = dma_map_single(priv->dev, req->state, req->digest_sz,
 					 DMA_FROM_DEVICE);
 	if (dma_mapping_error(priv->dev, req->result_dma)) {
 		ret = -EINVAL;
@@ -374,7 +468,7 @@ send_command:
 
 	/* Add a result descriptor */
 	rdesc = safexcel_add_rdesc(priv, ring, 1, 1, req->result_dma,
-				   req->state_sz);
+				   req->digest_sz);
 	if (IS_ERR(rdesc)) {
 		ret = PTR_ERR(rdesc);
 		goto unmap_result;
@@ -382,17 +476,20 @@ send_command:
 
 	safexcel_rdr_req_set(priv, ring, rdesc, &areq->base);
 
-	req->processed += len;
+	req->processed += len - extra;
 
 	*commands = n_cdesc;
 	*results = 1;
 	return 0;
 
 unmap_result:
-	dma_unmap_single(priv->dev, req->result_dma, req->state_sz,
+	dma_unmap_single(priv->dev, req->result_dma, req->digest_sz,
 			 DMA_FROM_DEVICE);
 unmap_sg:
-	dma_unmap_sg(priv->dev, areq->src, req->nents, DMA_TO_DEVICE);
+	if (req->nents) {
+		dma_unmap_sg(priv->dev, areq->src, req->nents, DMA_TO_DEVICE);
+		req->nents = 0;
+	}
 cdesc_rollback:
 	for (i = 0; i < n_cdesc; i++)
 		safexcel_ring_rollback_wptr(priv, &priv->ring[ring].cdr);
@@ -590,16 +687,12 @@ static int safexcel_ahash_enqueue(struct ahash_request *areq)
 
 	if (ctx->base.ctxr) {
 		if (priv->flags & EIP197_TRC_CACHE && !ctx->base.needs_inv &&
-		    req->processed &&
-		    (/* invalidate for basic hash continuation finish */
-		     (req->finish &&
-		      (req->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED)) ||
+		     /* invalidate for *any* non-XCBC continuation */
+		   ((req->not_first && !req->xcbcmac) ||
 		     /* invalidate if (i)digest changed */
 		     memcmp(ctx->base.ctxr->data, req->state, req->state_sz) ||
-		     /* invalidate for HMAC continuation finish */
-		     (req->finish && (req->processed != req->block_sz)) ||
 		     /* invalidate for HMAC finish with odigest changed */
-		     (req->finish &&
+		     (req->finish && req->hmac &&
 		      memcmp(ctx->base.ctxr->data + (req->state_sz>>2),
 			     ctx->opad, req->state_sz))))
 			/*
@@ -622,6 +715,7 @@ static int safexcel_ahash_enqueue(struct ahash_request *areq)
 		if (!ctx->base.ctxr)
 			return -ENOMEM;
 	}
+	req->not_first = true;
 
 	ring = ctx->base.ring;
 
@@ -691,8 +785,34 @@ static int safexcel_ahash_final(struct ahash_request *areq)
 		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA512)
 			memcpy(areq->result, sha512_zero_message_hash,
 			       SHA512_DIGEST_SIZE);
+		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SM3) {
+			memcpy(areq->result,
+			       EIP197_SM3_ZEROM_HASH, SM3_DIGEST_SIZE);
+		}
 
 		return 0;
+	} else if (unlikely(req->digest == CONTEXT_CONTROL_DIGEST_XCM &&
+			    ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_MD5 &&
+			    req->len == sizeof(u32) && !areq->nbytes)) {
+		/* Zero length CRC32 */
+		memcpy(areq->result, ctx->ipad, sizeof(u32));
+		return 0;
+	} else if (unlikely(ctx->cbcmac && req->len == AES_BLOCK_SIZE &&
+			    !areq->nbytes)) {
+		/* Zero length CBC MAC */
+		memset(areq->result, 0, AES_BLOCK_SIZE);
+		return 0;
+	} else if (unlikely(req->xcbcmac && req->len == AES_BLOCK_SIZE &&
+			    !areq->nbytes)) {
+		/* Zero length (X)CBC/CMAC */
+		int i;
+
+		for (i = 0; i < AES_BLOCK_SIZE / sizeof(u32); i++)
+			((__be32 *)areq->result)[i] =
+				cpu_to_be32(le32_to_cpu(ctx->ipad[i + 4]));//K3
+		areq->result[0] ^= 0x80;			// 10- padding
+		crypto_cipher_encrypt_one(ctx->kaes, areq->result, areq->result);
+		return 0;
 	} else if (unlikely(req->hmac &&
 			    (req->len == req->block_sz) &&
 			    !areq->nbytes)) {
@@ -792,6 +912,7 @@ static int safexcel_ahash_cra_init(struct crypto_tfm *tfm)
 	ctx->priv = tmpl->priv;
 	ctx->base.send = safexcel_ahash_send;
 	ctx->base.handle_result = safexcel_handle_result;
+	ctx->fb_do_setkey = false;
 
 	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
 				 sizeof(struct safexcel_ahash_req));
@@ -808,6 +929,7 @@ static int safexcel_sha1_init(struct ahash_request *areq)
 	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA1;
 	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
 	req->state_sz = SHA1_DIGEST_SIZE;
+	req->digest_sz = SHA1_DIGEST_SIZE;
 	req->block_sz = SHA1_BLOCK_SIZE;
 
 	return 0;
@@ -889,6 +1011,7 @@ static int safexcel_hmac_sha1_init(struct ahash_request *areq)
 	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA1;
 	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
 	req->state_sz = SHA1_DIGEST_SIZE;
+	req->digest_sz = SHA1_DIGEST_SIZE;
 	req->block_sz = SHA1_BLOCK_SIZE;
 	req->hmac = true;
 
@@ -1125,6 +1248,7 @@ static int safexcel_sha256_init(struct ahash_request *areq)
 	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA256;
 	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
 	req->state_sz = SHA256_DIGEST_SIZE;
+	req->digest_sz = SHA256_DIGEST_SIZE;
 	req->block_sz = SHA256_BLOCK_SIZE;
 
 	return 0;
@@ -1180,6 +1304,7 @@ static int safexcel_sha224_init(struct ahash_request *areq)
 	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA224;
 	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
 	req->state_sz = SHA256_DIGEST_SIZE;
+	req->digest_sz = SHA256_DIGEST_SIZE;
 	req->block_sz = SHA256_BLOCK_SIZE;
 
 	return 0;
@@ -1248,6 +1373,7 @@ static int safexcel_hmac_sha224_init(struct ahash_request *areq)
 	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA224;
 	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
 	req->state_sz = SHA256_DIGEST_SIZE;
+	req->digest_sz = SHA256_DIGEST_SIZE;
 	req->block_sz = SHA256_BLOCK_SIZE;
 	req->hmac = true;
 
@@ -1318,6 +1444,7 @@ static int safexcel_hmac_sha256_init(struct ahash_request *areq)
 	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA256;
 	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
 	req->state_sz = SHA256_DIGEST_SIZE;
+	req->digest_sz = SHA256_DIGEST_SIZE;
 	req->block_sz = SHA256_BLOCK_SIZE;
 	req->hmac = true;
 
@@ -1375,6 +1502,7 @@ static int safexcel_sha512_init(struct ahash_request *areq)
 	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA512;
 	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
 	req->state_sz = SHA512_DIGEST_SIZE;
+	req->digest_sz = SHA512_DIGEST_SIZE;
 	req->block_sz = SHA512_BLOCK_SIZE;
 
 	return 0;
@@ -1430,6 +1558,7 @@ static int safexcel_sha384_init(struct ahash_request *areq)
 	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA384;
 	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
 	req->state_sz = SHA512_DIGEST_SIZE;
+	req->digest_sz = SHA512_DIGEST_SIZE;
 	req->block_sz = SHA512_BLOCK_SIZE;
 
 	return 0;
@@ -1498,6 +1627,7 @@ static int safexcel_hmac_sha512_init(struct ahash_request *areq)
 	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA512;
 	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
 	req->state_sz = SHA512_DIGEST_SIZE;
+	req->digest_sz = SHA512_DIGEST_SIZE;
 	req->block_sz = SHA512_BLOCK_SIZE;
 	req->hmac = true;
 
@@ -1568,6 +1698,7 @@ static int safexcel_hmac_sha384_init(struct ahash_request *areq)
 	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA384;
 	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
 	req->state_sz = SHA512_DIGEST_SIZE;
+	req->digest_sz = SHA512_DIGEST_SIZE;
 	req->block_sz = SHA512_BLOCK_SIZE;
 	req->hmac = true;
 
@@ -1625,6 +1756,7 @@ static int safexcel_md5_init(struct ahash_request *areq)
 	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_MD5;
 	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
 	req->state_sz = MD5_DIGEST_SIZE;
+	req->digest_sz = MD5_DIGEST_SIZE;
 	req->block_sz = MD5_HMAC_BLOCK_SIZE;
 
 	return 0;
@@ -1686,6 +1818,7 @@ static int safexcel_hmac_md5_init(struct ahash_request *areq)
 	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_MD5;
 	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
 	req->state_sz = MD5_DIGEST_SIZE;
+	req->digest_sz = MD5_DIGEST_SIZE;
 	req->block_sz = MD5_HMAC_BLOCK_SIZE;
 	req->len_is_le = true; /* MD5 is little endian! ... */
 	req->hmac = true;
@@ -1740,3 +1873,1247 @@ struct safexcel_alg_template safexcel_alg_hmac_md5 = {
 		},
 	},
 };
+
+static int safexcel_crc32_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret = safexcel_ahash_cra_init(tfm);
+
+	/* Default 'key' is all zeroes */
+	memset(ctx->ipad, 0, sizeof(u32));
+	return ret;
+}
+
+static int safexcel_crc32_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	/* Start from loaded key */
+	req->state[0]	= (__force __le32)le32_to_cpu(~ctx->ipad[0]);
+	/* Set processed to non-zero to enable invalidation detection */
+	req->len	= sizeof(u32);
+	req->processed	= sizeof(u32);
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_CRC32;
+	req->digest = CONTEXT_CONTROL_DIGEST_XCM;
+	req->state_sz = sizeof(u32);
+	req->digest_sz = sizeof(u32);
+	req->block_sz = sizeof(u32);
+
+	return 0;
+}
+
+static int safexcel_crc32_setkey(struct crypto_ahash *tfm, const u8 *key,
+				 unsigned int keylen)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
+
+	if (keylen != sizeof(u32)) {
+		crypto_ahash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(ctx->ipad, key, sizeof(u32));
+	return 0;
+}
+
+static int safexcel_crc32_digest(struct ahash_request *areq)
+{
+	return safexcel_crc32_init(areq) ?: safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_crc32 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.algo_mask = 0,
+	.alg.ahash = {
+		.init = safexcel_crc32_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_crc32_digest,
+		.setkey = safexcel_crc32_setkey,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = sizeof(u32),
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "crc32",
+				.cra_driver_name = "safexcel-crc32",
+				.cra_priority = SAFEXCEL_CRA_PRIORITY,
+				.cra_flags = CRYPTO_ALG_OPTIONAL_KEY |
+					     CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = 1,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_crc32_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_cbcmac_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	/* Start from loaded keys */
+	memcpy(req->state, ctx->ipad, ctx->key_sz);
+	/* Set processed to non-zero to enable invalidation detection */
+	req->len	= AES_BLOCK_SIZE;
+	req->processed	= AES_BLOCK_SIZE;
+
+	req->digest   = CONTEXT_CONTROL_DIGEST_XCM;
+	req->state_sz = ctx->key_sz;
+	req->digest_sz = AES_BLOCK_SIZE;
+	req->block_sz = AES_BLOCK_SIZE;
+	req->xcbcmac  = true;
+
+	return 0;
+}
+
+static int safexcel_cbcmac_setkey(struct crypto_ahash *tfm, const u8 *key,
+				 unsigned int len)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
+	struct crypto_aes_ctx aes;
+	int ret, i;
+
+	ret = aes_expandkey(&aes, key, len);
+	if (ret) {
+		crypto_ahash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return ret;
+	}
+
+	memset(ctx->ipad, 0, 2 * AES_BLOCK_SIZE);
+	for (i = 0; i < len / sizeof(u32); i++)
+		ctx->ipad[i + 8] = (__force __le32)cpu_to_be32(aes.key_enc[i]);
+
+	if (len == AES_KEYSIZE_192) {
+		ctx->alg    = CONTEXT_CONTROL_CRYPTO_ALG_XCBC192;
+		ctx->key_sz = AES_MAX_KEY_SIZE + 2 * AES_BLOCK_SIZE;
+	} else if (len == AES_KEYSIZE_256) {
+		ctx->alg    = CONTEXT_CONTROL_CRYPTO_ALG_XCBC256;
+		ctx->key_sz = AES_MAX_KEY_SIZE + 2 * AES_BLOCK_SIZE;
+	} else {
+		ctx->alg    = CONTEXT_CONTROL_CRYPTO_ALG_XCBC128;
+		ctx->key_sz = AES_MIN_KEY_SIZE + 2 * AES_BLOCK_SIZE;
+	}
+	ctx->cbcmac  = true;
+
+	memzero_explicit(&aes, sizeof(aes));
+	return 0;
+}
+
+static int safexcel_cbcmac_digest(struct ahash_request *areq)
+{
+	return safexcel_cbcmac_init(areq) ?: safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_cbcmac = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.algo_mask = 0,
+	.alg.ahash = {
+		.init = safexcel_cbcmac_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_cbcmac_digest,
+		.setkey = safexcel_cbcmac_setkey,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = AES_BLOCK_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "cbcmac(aes)",
+				.cra_driver_name = "safexcel-cbcmac-aes",
+				.cra_priority = SAFEXCEL_CRA_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = 1,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_xcbcmac_setkey(struct crypto_ahash *tfm, const u8 *key,
+				 unsigned int len)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
+	struct crypto_aes_ctx aes;
+	u32 key_tmp[3 * AES_BLOCK_SIZE / sizeof(u32)];
+	int ret, i;
+
+	ret = aes_expandkey(&aes, key, len);
+	if (ret) {
+		crypto_ahash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return ret;
+	}
+
+	/* precompute the XCBC key material */
+	crypto_cipher_clear_flags(ctx->kaes, CRYPTO_TFM_REQ_MASK);
+	crypto_cipher_set_flags(ctx->kaes, crypto_ahash_get_flags(tfm) &
+				CRYPTO_TFM_REQ_MASK);
+	ret = crypto_cipher_setkey(ctx->kaes, key, len);
+	crypto_ahash_set_flags(tfm, crypto_cipher_get_flags(ctx->kaes) &
+			       CRYPTO_TFM_RES_MASK);
+	if (ret)
+		return ret;
+
+	crypto_cipher_encrypt_one(ctx->kaes, (u8 *)key_tmp + 2 * AES_BLOCK_SIZE,
+		"\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1");
+	crypto_cipher_encrypt_one(ctx->kaes, (u8 *)key_tmp,
+		"\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2");
+	crypto_cipher_encrypt_one(ctx->kaes, (u8 *)key_tmp + AES_BLOCK_SIZE,
+		"\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3");
+	for (i = 0; i < 3 * AES_BLOCK_SIZE / sizeof(u32); i++)
+		ctx->ipad[i] =
+			cpu_to_le32((__force u32)cpu_to_be32(key_tmp[i]));
+
+	crypto_cipher_clear_flags(ctx->kaes, CRYPTO_TFM_REQ_MASK);
+	crypto_cipher_set_flags(ctx->kaes, crypto_ahash_get_flags(tfm) &
+				CRYPTO_TFM_REQ_MASK);
+	ret = crypto_cipher_setkey(ctx->kaes,
+				   (u8 *)key_tmp + 2 * AES_BLOCK_SIZE,
+				   AES_MIN_KEY_SIZE);
+	crypto_ahash_set_flags(tfm, crypto_cipher_get_flags(ctx->kaes) &
+			       CRYPTO_TFM_RES_MASK);
+	if (ret)
+		return ret;
+
+	ctx->alg    = CONTEXT_CONTROL_CRYPTO_ALG_XCBC128;
+	ctx->key_sz = AES_MIN_KEY_SIZE + 2 * AES_BLOCK_SIZE;
+	ctx->cbcmac = false;
+
+	memzero_explicit(&aes, sizeof(aes));
+	return 0;
+}
+
+static int safexcel_xcbcmac_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_ahash_cra_init(tfm);
+	ctx->kaes = crypto_alloc_cipher("aes", 0, 0);
+	return PTR_ERR_OR_ZERO(ctx->kaes);
+}
+
+static void safexcel_xcbcmac_cra_exit(struct crypto_tfm *tfm)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_cipher(ctx->kaes);
+	safexcel_ahash_cra_exit(tfm);
+}
+
+struct safexcel_alg_template safexcel_alg_xcbcmac = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.algo_mask = 0,
+	.alg.ahash = {
+		.init = safexcel_cbcmac_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_cbcmac_digest,
+		.setkey = safexcel_xcbcmac_setkey,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = AES_BLOCK_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "xcbc(aes)",
+				.cra_driver_name = "safexcel-xcbc-aes",
+				.cra_priority = SAFEXCEL_CRA_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_xcbcmac_cra_init,
+				.cra_exit = safexcel_xcbcmac_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_cmac_setkey(struct crypto_ahash *tfm, const u8 *key,
+				unsigned int len)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
+	struct crypto_aes_ctx aes;
+	__be64 consts[4];
+	u64 _const[2];
+	u8 msb_mask, gfmask;
+	int ret, i;
+
+	ret = aes_expandkey(&aes, key, len);
+	if (ret) {
+		crypto_ahash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return ret;
+	}
+
+	for (i = 0; i < len / sizeof(u32); i++)
+		ctx->ipad[i + 8] =
+			cpu_to_le32((__force u32)cpu_to_be32(aes.key_enc[i]));
+
+	/* precompute the CMAC key material */
+	crypto_cipher_clear_flags(ctx->kaes, CRYPTO_TFM_REQ_MASK);
+	crypto_cipher_set_flags(ctx->kaes, crypto_ahash_get_flags(tfm) &
+				CRYPTO_TFM_REQ_MASK);
+	ret = crypto_cipher_setkey(ctx->kaes, key, len);
+	crypto_ahash_set_flags(tfm, crypto_cipher_get_flags(ctx->kaes) &
+			       CRYPTO_TFM_RES_MASK);
+	if (ret)
+		return ret;
+
+	/* code below borrowed from crypto/cmac.c */
+	/* encrypt the zero block */
+	memset(consts, 0, AES_BLOCK_SIZE);
+	crypto_cipher_encrypt_one(ctx->kaes, (u8 *)consts, (u8 *)consts);
+
+	gfmask = 0x87;
+	_const[0] = be64_to_cpu(consts[1]);
+	_const[1] = be64_to_cpu(consts[0]);
+
+	/* gf(2^128) multiply zero-ciphertext with u and u^2 */
+	for (i = 0; i < 4; i += 2) {
+		msb_mask = ((s64)_const[1] >> 63) & gfmask;
+		_const[1] = (_const[1] << 1) | (_const[0] >> 63);
+		_const[0] = (_const[0] << 1) ^ msb_mask;
+
+		consts[i + 0] = cpu_to_be64(_const[1]);
+		consts[i + 1] = cpu_to_be64(_const[0]);
+	}
+	/* end of code borrowed from crypto/cmac.c */
+
+	for (i = 0; i < 2 * AES_BLOCK_SIZE / sizeof(u32); i++)
+		ctx->ipad[i] = (__force __le32)cpu_to_be32(((u32 *)consts)[i]);
+
+	if (len == AES_KEYSIZE_192) {
+		ctx->alg    = CONTEXT_CONTROL_CRYPTO_ALG_XCBC192;
+		ctx->key_sz = AES_MAX_KEY_SIZE + 2 * AES_BLOCK_SIZE;
+	} else if (len == AES_KEYSIZE_256) {
+		ctx->alg    = CONTEXT_CONTROL_CRYPTO_ALG_XCBC256;
+		ctx->key_sz = AES_MAX_KEY_SIZE + 2 * AES_BLOCK_SIZE;
+	} else {
+		ctx->alg    = CONTEXT_CONTROL_CRYPTO_ALG_XCBC128;
+		ctx->key_sz = AES_MIN_KEY_SIZE + 2 * AES_BLOCK_SIZE;
+	}
+	ctx->cbcmac = false;
+
+	memzero_explicit(&aes, sizeof(aes));
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_cmac = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.algo_mask = 0,
+	.alg.ahash = {
+		.init = safexcel_cbcmac_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_cbcmac_digest,
+		.setkey = safexcel_cmac_setkey,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = AES_BLOCK_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "cmac(aes)",
+				.cra_driver_name = "safexcel-cmac-aes",
+				.cra_priority = SAFEXCEL_CRA_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_xcbcmac_cra_init,
+				.cra_exit = safexcel_xcbcmac_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_sm3_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SM3;
+	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
+	req->state_sz = SM3_DIGEST_SIZE;
+	req->digest_sz = SM3_DIGEST_SIZE;
+	req->block_sz = SM3_BLOCK_SIZE;
+
+	return 0;
+}
+
+static int safexcel_sm3_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_sm3_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_sm3 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.algo_mask = SAFEXCEL_ALG_SM3,
+	.alg.ahash = {
+		.init = safexcel_sm3_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_sm3_digest,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SM3_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "sm3",
+				.cra_driver_name = "safexcel-sm3",
+				.cra_priority = SAFEXCEL_CRA_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SM3_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_hmac_sm3_setkey(struct crypto_ahash *tfm, const u8 *key,
+				    unsigned int keylen)
+{
+	return safexcel_hmac_alg_setkey(tfm, key, keylen, "safexcel-sm3",
+					SM3_DIGEST_SIZE);
+}
+
+static int safexcel_hmac_sm3_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	/* Start from ipad precompute */
+	memcpy(req->state, ctx->ipad, SM3_DIGEST_SIZE);
+	/* Already processed the key^ipad part now! */
+	req->len	= SM3_BLOCK_SIZE;
+	req->processed	= SM3_BLOCK_SIZE;
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SM3;
+	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
+	req->state_sz = SM3_DIGEST_SIZE;
+	req->digest_sz = SM3_DIGEST_SIZE;
+	req->block_sz = SM3_BLOCK_SIZE;
+	req->hmac = true;
+
+	return 0;
+}
+
+static int safexcel_hmac_sm3_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_hmac_sm3_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_hmac_sm3 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.algo_mask = SAFEXCEL_ALG_SM3,
+	.alg.ahash = {
+		.init = safexcel_hmac_sm3_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_hmac_sm3_digest,
+		.setkey = safexcel_hmac_sm3_setkey,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SM3_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "hmac(sm3)",
+				.cra_driver_name = "safexcel-hmac-sm3",
+				.cra_priority = SAFEXCEL_CRA_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SM3_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_sha3_224_init(struct ahash_request *areq)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA3_224;
+	req->digest = CONTEXT_CONTROL_DIGEST_INITIAL;
+	req->state_sz = SHA3_224_DIGEST_SIZE;
+	req->digest_sz = SHA3_224_DIGEST_SIZE;
+	req->block_sz = SHA3_224_BLOCK_SIZE;
+	ctx->do_fallback = false;
+	ctx->fb_init_done = false;
+	return 0;
+}
+
+static int safexcel_sha3_fbcheck(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *subreq = ahash_request_ctx(req);
+	int ret = 0;
+
+	if (ctx->do_fallback) {
+		ahash_request_set_tfm(subreq, ctx->fback);
+		ahash_request_set_callback(subreq, req->base.flags,
+					   req->base.complete, req->base.data);
+		ahash_request_set_crypt(subreq, req->src, req->result,
+					req->nbytes);
+		if (!ctx->fb_init_done) {
+			if (ctx->fb_do_setkey) {
+				/* Set fallback cipher HMAC key */
+				u8 key[SHA3_224_BLOCK_SIZE];
+
+				memcpy(key, ctx->ipad,
+				       crypto_ahash_blocksize(ctx->fback) / 2);
+				memcpy(key +
+				       crypto_ahash_blocksize(ctx->fback) / 2,
+				       ctx->opad,
+				       crypto_ahash_blocksize(ctx->fback) / 2);
+				ret = crypto_ahash_setkey(ctx->fback, key,
+					crypto_ahash_blocksize(ctx->fback));
+				memzero_explicit(key,
+					crypto_ahash_blocksize(ctx->fback));
+				ctx->fb_do_setkey = false;
+			}
+			ret = ret ?: crypto_ahash_init(subreq);
+			ctx->fb_init_done = true;
+		}
+	}
+	return ret;
+}
+
+static int safexcel_sha3_update(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *subreq = ahash_request_ctx(req);
+
+	ctx->do_fallback = true;
+	return safexcel_sha3_fbcheck(req) ?: crypto_ahash_update(subreq);
+}
+
+static int safexcel_sha3_final(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *subreq = ahash_request_ctx(req);
+
+	ctx->do_fallback = true;
+	return safexcel_sha3_fbcheck(req) ?: crypto_ahash_final(subreq);
+}
+
+static int safexcel_sha3_finup(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *subreq = ahash_request_ctx(req);
+
+	ctx->do_fallback |= !req->nbytes;
+	if (ctx->do_fallback)
+		/* Update or ex/import happened or len 0, cannot use the HW */
+		return safexcel_sha3_fbcheck(req) ?:
+		       crypto_ahash_finup(subreq);
+	else
+		return safexcel_ahash_finup(req);
+}
+
+static int safexcel_sha3_digest_fallback(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *subreq = ahash_request_ctx(req);
+
+	ctx->do_fallback = true;
+	ctx->fb_init_done = false;
+	return safexcel_sha3_fbcheck(req) ?: crypto_ahash_finup(subreq);
+}
+
+static int safexcel_sha3_224_digest(struct ahash_request *req)
+{
+	if (req->nbytes)
+		return safexcel_sha3_224_init(req) ?: safexcel_ahash_finup(req);
+
+	/* HW cannot do zero length hash, use fallback instead */
+	return safexcel_sha3_digest_fallback(req);
+}
+
+static int safexcel_sha3_export(struct ahash_request *req, void *out)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *subreq = ahash_request_ctx(req);
+
+	ctx->do_fallback = true;
+	return safexcel_sha3_fbcheck(req) ?: crypto_ahash_export(subreq, out);
+}
+
+static int safexcel_sha3_import(struct ahash_request *req, const void *in)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *subreq = ahash_request_ctx(req);
+
+	ctx->do_fallback = true;
+	return safexcel_sha3_fbcheck(req) ?: crypto_ahash_import(subreq, in);
+	// return safexcel_ahash_import(req, in);
+}
+
+static int safexcel_sha3_cra_init(struct crypto_tfm *tfm)
+{
+	struct crypto_ahash *ahash = __crypto_ahash_cast(tfm);
+	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_ahash_cra_init(tfm);
+
+	/* Allocate fallback implementation */
+	ctx->fback = crypto_alloc_ahash(crypto_tfm_alg_name(tfm), 0,
+					CRYPTO_ALG_ASYNC |
+					CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(ctx->fback))
+		return PTR_ERR(ctx->fback);
+
+	/* Update statesize from fallback algorithm! */
+	crypto_hash_alg_common(ahash)->statesize =
+		crypto_ahash_statesize(ctx->fback);
+	crypto_ahash_set_reqsize(ahash, max(sizeof(struct safexcel_ahash_req),
+					    sizeof(struct ahash_request) +
+					    crypto_ahash_reqsize(ctx->fback)));
+	return 0;
+}
+
+static void safexcel_sha3_cra_exit(struct crypto_tfm *tfm)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_ahash(ctx->fback);
+	safexcel_ahash_cra_exit(tfm);
+}
+
+struct safexcel_alg_template safexcel_alg_sha3_224 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.algo_mask = SAFEXCEL_ALG_SHA3,
+	.alg.ahash = {
+		.init = safexcel_sha3_224_init,
+		.update = safexcel_sha3_update,
+		.final = safexcel_sha3_final,
+		.finup = safexcel_sha3_finup,
+		.digest = safexcel_sha3_224_digest,
+		.export = safexcel_sha3_export,
+		.import = safexcel_sha3_import,
+		.halg = {
+			.digestsize = SHA3_224_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "sha3-224",
+				.cra_driver_name = "safexcel-sha3-224",
+				.cra_priority = SAFEXCEL_CRA_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY |
+					     CRYPTO_ALG_NEED_FALLBACK,
+				.cra_blocksize = SHA3_224_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_sha3_cra_init,
+				.cra_exit = safexcel_sha3_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_sha3_256_init(struct ahash_request *areq)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA3_256;
+	req->digest = CONTEXT_CONTROL_DIGEST_INITIAL;
+	req->state_sz = SHA3_256_DIGEST_SIZE;
+	req->digest_sz = SHA3_256_DIGEST_SIZE;
+	req->block_sz = SHA3_256_BLOCK_SIZE;
+	ctx->do_fallback = false;
+	ctx->fb_init_done = false;
+	return 0;
+}
+
+static int safexcel_sha3_256_digest(struct ahash_request *req)
+{
+	if (req->nbytes)
+		return safexcel_sha3_256_init(req) ?: safexcel_ahash_finup(req);
+
+	/* HW cannot do zero length hash, use fallback instead */
+	return safexcel_sha3_digest_fallback(req);
+}
+
+struct safexcel_alg_template safexcel_alg_sha3_256 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.algo_mask = SAFEXCEL_ALG_SHA3,
+	.alg.ahash = {
+		.init = safexcel_sha3_256_init,
+		.update = safexcel_sha3_update,
+		.final = safexcel_sha3_final,
+		.finup = safexcel_sha3_finup,
+		.digest = safexcel_sha3_256_digest,
+		.export = safexcel_sha3_export,
+		.import = safexcel_sha3_import,
+		.halg = {
+			.digestsize = SHA3_256_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "sha3-256",
+				.cra_driver_name = "safexcel-sha3-256",
+				.cra_priority = SAFEXCEL_CRA_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY |
+					     CRYPTO_ALG_NEED_FALLBACK,
+				.cra_blocksize = SHA3_256_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_sha3_cra_init,
+				.cra_exit = safexcel_sha3_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_sha3_384_init(struct ahash_request *areq)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA3_384;
+	req->digest = CONTEXT_CONTROL_DIGEST_INITIAL;
+	req->state_sz = SHA3_384_DIGEST_SIZE;
+	req->digest_sz = SHA3_384_DIGEST_SIZE;
+	req->block_sz = SHA3_384_BLOCK_SIZE;
+	ctx->do_fallback = false;
+	ctx->fb_init_done = false;
+	return 0;
+}
+
+static int safexcel_sha3_384_digest(struct ahash_request *req)
+{
+	if (req->nbytes)
+		return safexcel_sha3_384_init(req) ?: safexcel_ahash_finup(req);
+
+	/* HW cannot do zero length hash, use fallback instead */
+	return safexcel_sha3_digest_fallback(req);
+}
+
+struct safexcel_alg_template safexcel_alg_sha3_384 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.algo_mask = SAFEXCEL_ALG_SHA3,
+	.alg.ahash = {
+		.init = safexcel_sha3_384_init,
+		.update = safexcel_sha3_update,
+		.final = safexcel_sha3_final,
+		.finup = safexcel_sha3_finup,
+		.digest = safexcel_sha3_384_digest,
+		.export = safexcel_sha3_export,
+		.import = safexcel_sha3_import,
+		.halg = {
+			.digestsize = SHA3_384_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "sha3-384",
+				.cra_driver_name = "safexcel-sha3-384",
+				.cra_priority = SAFEXCEL_CRA_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY |
+					     CRYPTO_ALG_NEED_FALLBACK,
+				.cra_blocksize = SHA3_384_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_sha3_cra_init,
+				.cra_exit = safexcel_sha3_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_sha3_512_init(struct ahash_request *areq)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA3_512;
+	req->digest = CONTEXT_CONTROL_DIGEST_INITIAL;
+	req->state_sz = SHA3_512_DIGEST_SIZE;
+	req->digest_sz = SHA3_512_DIGEST_SIZE;
+	req->block_sz = SHA3_512_BLOCK_SIZE;
+	ctx->do_fallback = false;
+	ctx->fb_init_done = false;
+	return 0;
+}
+
+static int safexcel_sha3_512_digest(struct ahash_request *req)
+{
+	if (req->nbytes)
+		return safexcel_sha3_512_init(req) ?: safexcel_ahash_finup(req);
+
+	/* HW cannot do zero length hash, use fallback instead */
+	return safexcel_sha3_digest_fallback(req);
+}
+
+struct safexcel_alg_template safexcel_alg_sha3_512 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.algo_mask = SAFEXCEL_ALG_SHA3,
+	.alg.ahash = {
+		.init = safexcel_sha3_512_init,
+		.update = safexcel_sha3_update,
+		.final = safexcel_sha3_final,
+		.finup = safexcel_sha3_finup,
+		.digest = safexcel_sha3_512_digest,
+		.export = safexcel_sha3_export,
+		.import = safexcel_sha3_import,
+		.halg = {
+			.digestsize = SHA3_512_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "sha3-512",
+				.cra_driver_name = "safexcel-sha3-512",
+				.cra_priority = SAFEXCEL_CRA_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY |
+					     CRYPTO_ALG_NEED_FALLBACK,
+				.cra_blocksize = SHA3_512_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_sha3_cra_init,
+				.cra_exit = safexcel_sha3_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_hmac_sha3_cra_init(struct crypto_tfm *tfm, const char *alg)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret;
+
+	ret = safexcel_sha3_cra_init(tfm);
+	if (ret)
+		return ret;
+
+	/* Allocate precalc basic digest implementation */
+	ctx->shpre = crypto_alloc_shash(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(ctx->shpre))
+		return PTR_ERR(ctx->shpre);
+
+	ctx->shdesc = kmalloc(sizeof(*ctx->shdesc) +
+			      crypto_shash_descsize(ctx->shpre), GFP_KERNEL);
+	if (!ctx->shdesc) {
+		crypto_free_shash(ctx->shpre);
+		return -ENOMEM;
+	}
+	ctx->shdesc->tfm = ctx->shpre;
+	return 0;
+}
+
+static void safexcel_hmac_sha3_cra_exit(struct crypto_tfm *tfm)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_ahash(ctx->fback);
+	crypto_free_shash(ctx->shpre);
+	kfree(ctx->shdesc);
+	safexcel_ahash_cra_exit(tfm);
+}
+
+static int safexcel_hmac_sha3_setkey(struct crypto_ahash *tfm, const u8 *key,
+				     unsigned int keylen)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	int ret = 0;
+
+	if (keylen > crypto_ahash_blocksize(tfm)) {
+		/*
+		 * If the key is larger than the blocksize, then hash it
+		 * first using our fallback cipher
+		 */
+		ret = crypto_shash_digest(ctx->shdesc, key, keylen,
+					  (u8 *)ctx->ipad);
+		keylen = crypto_shash_digestsize(ctx->shpre);
+
+		/*
+		 * If the digest is larger than half the blocksize, we need to
+		 * move the rest to opad due to the way our HMAC infra works.
+		 */
+		if (keylen > crypto_ahash_blocksize(tfm) / 2)
+			/* Buffers overlap, need to use memmove iso memcpy! */
+			memmove(ctx->opad,
+				(u8 *)ctx->ipad +
+					crypto_ahash_blocksize(tfm) / 2,
+				keylen - crypto_ahash_blocksize(tfm) / 2);
+	} else {
+		/*
+		 * Copy the key to our ipad & opad buffers
+		 * Note that ipad and opad each contain one half of the key,
+		 * to match the existing HMAC driver infrastructure.
+		 */
+		if (keylen <= crypto_ahash_blocksize(tfm) / 2) {
+			memcpy(ctx->ipad, key, keylen);
+		} else {
+			memcpy(ctx->ipad, key,
+			       crypto_ahash_blocksize(tfm) / 2);
+			memcpy(ctx->opad,
+			       key + crypto_ahash_blocksize(tfm) / 2,
+			       keylen - crypto_ahash_blocksize(tfm) / 2);
+		}
+	}
+
+	/* Pad key with zeroes */
+	if (keylen <= crypto_ahash_blocksize(tfm) / 2) {
+		memset((u8 *)ctx->ipad + keylen, 0,
+		       crypto_ahash_blocksize(tfm) / 2 - keylen);
+		memset(ctx->opad, 0, crypto_ahash_blocksize(tfm) / 2);
+	} else {
+		memset((u8 *)ctx->opad + keylen -
+		       crypto_ahash_blocksize(tfm) / 2, 0,
+		       crypto_ahash_blocksize(tfm) - keylen);
+	}
+
+	/* If doing fallback, still need to set the new key! */
+	ctx->fb_do_setkey = true;
+	return ret;
+}
+
+static int safexcel_hmac_sha3_224_init(struct ahash_request *areq)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	/* Copy (half of) the key */
+	memcpy(req->state, ctx->ipad, SHA3_224_BLOCK_SIZE / 2);
+	/* Start of HMAC should have len == processed == blocksize */
+	req->len	= SHA3_224_BLOCK_SIZE;
+	req->processed	= SHA3_224_BLOCK_SIZE;
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA3_224;
+	req->digest = CONTEXT_CONTROL_DIGEST_HMAC;
+	req->state_sz = SHA3_224_BLOCK_SIZE / 2;
+	req->digest_sz = SHA3_224_DIGEST_SIZE;
+	req->block_sz = SHA3_224_BLOCK_SIZE;
+	req->hmac = true;
+	ctx->do_fallback = false;
+	ctx->fb_init_done = false;
+	return 0;
+}
+
+static int safexcel_hmac_sha3_224_digest(struct ahash_request *req)
+{
+	if (req->nbytes)
+		return safexcel_hmac_sha3_224_init(req) ?:
+		       safexcel_ahash_finup(req);
+
+	/* HW cannot do zero length HMAC, use fallback instead */
+	return safexcel_sha3_digest_fallback(req);
+}
+
+static int safexcel_hmac_sha3_224_cra_init(struct crypto_tfm *tfm)
+{
+	return safexcel_hmac_sha3_cra_init(tfm, "sha3-224");
+}
+
+struct safexcel_alg_template safexcel_alg_hmac_sha3_224 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.algo_mask = SAFEXCEL_ALG_SHA3,
+	.alg.ahash = {
+		.init = safexcel_hmac_sha3_224_init,
+		.update = safexcel_sha3_update,
+		.final = safexcel_sha3_final,
+		.finup = safexcel_sha3_finup,
+		.digest = safexcel_hmac_sha3_224_digest,
+		.setkey = safexcel_hmac_sha3_setkey,
+		.export = safexcel_sha3_export,
+		.import = safexcel_sha3_import,
+		.halg = {
+			.digestsize = SHA3_224_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "hmac(sha3-224)",
+				.cra_driver_name = "safexcel-hmac-sha3-224",
+				.cra_priority = SAFEXCEL_CRA_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY |
+					     CRYPTO_ALG_NEED_FALLBACK,
+				.cra_blocksize = SHA3_224_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_hmac_sha3_224_cra_init,
+				.cra_exit = safexcel_hmac_sha3_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_hmac_sha3_256_init(struct ahash_request *areq)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	/* Copy (half of) the key */
+	memcpy(req->state, ctx->ipad, SHA3_256_BLOCK_SIZE / 2);
+	/* Start of HMAC should have len == processed == blocksize */
+	req->len	= SHA3_256_BLOCK_SIZE;
+	req->processed	= SHA3_256_BLOCK_SIZE;
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA3_256;
+	req->digest = CONTEXT_CONTROL_DIGEST_HMAC;
+	req->state_sz = SHA3_256_BLOCK_SIZE / 2;
+	req->digest_sz = SHA3_256_DIGEST_SIZE;
+	req->block_sz = SHA3_256_BLOCK_SIZE;
+	req->hmac = true;
+	ctx->do_fallback = false;
+	ctx->fb_init_done = false;
+	return 0;
+}
+
+static int safexcel_hmac_sha3_256_digest(struct ahash_request *req)
+{
+	if (req->nbytes)
+		return safexcel_hmac_sha3_256_init(req) ?:
+		       safexcel_ahash_finup(req);
+
+	/* HW cannot do zero length HMAC, use fallback instead */
+	return safexcel_sha3_digest_fallback(req);
+}
+
+static int safexcel_hmac_sha3_256_cra_init(struct crypto_tfm *tfm)
+{
+	return safexcel_hmac_sha3_cra_init(tfm, "sha3-256");
+}
+
+struct safexcel_alg_template safexcel_alg_hmac_sha3_256 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.algo_mask = SAFEXCEL_ALG_SHA3,
+	.alg.ahash = {
+		.init = safexcel_hmac_sha3_256_init,
+		.update = safexcel_sha3_update,
+		.final = safexcel_sha3_final,
+		.finup = safexcel_sha3_finup,
+		.digest = safexcel_hmac_sha3_256_digest,
+		.setkey = safexcel_hmac_sha3_setkey,
+		.export = safexcel_sha3_export,
+		.import = safexcel_sha3_import,
+		.halg = {
+			.digestsize = SHA3_256_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "hmac(sha3-256)",
+				.cra_driver_name = "safexcel-hmac-sha3-256",
+				.cra_priority = SAFEXCEL_CRA_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY |
+					     CRYPTO_ALG_NEED_FALLBACK,
+				.cra_blocksize = SHA3_256_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_hmac_sha3_256_cra_init,
+				.cra_exit = safexcel_hmac_sha3_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_hmac_sha3_384_init(struct ahash_request *areq)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	/* Copy (half of) the key */
+	memcpy(req->state, ctx->ipad, SHA3_384_BLOCK_SIZE / 2);
+	/* Start of HMAC should have len == processed == blocksize */
+	req->len	= SHA3_384_BLOCK_SIZE;
+	req->processed	= SHA3_384_BLOCK_SIZE;
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA3_384;
+	req->digest = CONTEXT_CONTROL_DIGEST_HMAC;
+	req->state_sz = SHA3_384_BLOCK_SIZE / 2;
+	req->digest_sz = SHA3_384_DIGEST_SIZE;
+	req->block_sz = SHA3_384_BLOCK_SIZE;
+	req->hmac = true;
+	ctx->do_fallback = false;
+	ctx->fb_init_done = false;
+	return 0;
+}
+
+static int safexcel_hmac_sha3_384_digest(struct ahash_request *req)
+{
+	if (req->nbytes)
+		return safexcel_hmac_sha3_384_init(req) ?:
+		       safexcel_ahash_finup(req);
+
+	/* HW cannot do zero length HMAC, use fallback instead */
+	return safexcel_sha3_digest_fallback(req);
+}
+
+static int safexcel_hmac_sha3_384_cra_init(struct crypto_tfm *tfm)
+{
+	return safexcel_hmac_sha3_cra_init(tfm, "sha3-384");
+}
+
+struct safexcel_alg_template safexcel_alg_hmac_sha3_384 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.algo_mask = SAFEXCEL_ALG_SHA3,
+	.alg.ahash = {
+		.init = safexcel_hmac_sha3_384_init,
+		.update = safexcel_sha3_update,
+		.final = safexcel_sha3_final,
+		.finup = safexcel_sha3_finup,
+		.digest = safexcel_hmac_sha3_384_digest,
+		.setkey = safexcel_hmac_sha3_setkey,
+		.export = safexcel_sha3_export,
+		.import = safexcel_sha3_import,
+		.halg = {
+			.digestsize = SHA3_384_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "hmac(sha3-384)",
+				.cra_driver_name = "safexcel-hmac-sha3-384",
+				.cra_priority = SAFEXCEL_CRA_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY |
+					     CRYPTO_ALG_NEED_FALLBACK,
+				.cra_blocksize = SHA3_384_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_hmac_sha3_384_cra_init,
+				.cra_exit = safexcel_hmac_sha3_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_hmac_sha3_512_init(struct ahash_request *areq)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	/* Copy (half of) the key */
+	memcpy(req->state, ctx->ipad, SHA3_512_BLOCK_SIZE / 2);
+	/* Start of HMAC should have len == processed == blocksize */
+	req->len	= SHA3_512_BLOCK_SIZE;
+	req->processed	= SHA3_512_BLOCK_SIZE;
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA3_512;
+	req->digest = CONTEXT_CONTROL_DIGEST_HMAC;
+	req->state_sz = SHA3_512_BLOCK_SIZE / 2;
+	req->digest_sz = SHA3_512_DIGEST_SIZE;
+	req->block_sz = SHA3_512_BLOCK_SIZE;
+	req->hmac = true;
+	ctx->do_fallback = false;
+	ctx->fb_init_done = false;
+	return 0;
+}
+
+static int safexcel_hmac_sha3_512_digest(struct ahash_request *req)
+{
+	if (req->nbytes)
+		return safexcel_hmac_sha3_512_init(req) ?:
+		       safexcel_ahash_finup(req);
+
+	/* HW cannot do zero length HMAC, use fallback instead */
+	return safexcel_sha3_digest_fallback(req);
+}
+
+static int safexcel_hmac_sha3_512_cra_init(struct crypto_tfm *tfm)
+{
+	return safexcel_hmac_sha3_cra_init(tfm, "sha3-512");
+}
+struct safexcel_alg_template safexcel_alg_hmac_sha3_512 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.algo_mask = SAFEXCEL_ALG_SHA3,
+	.alg.ahash = {
+		.init = safexcel_hmac_sha3_512_init,
+		.update = safexcel_sha3_update,
+		.final = safexcel_sha3_final,
+		.finup = safexcel_sha3_finup,
+		.digest = safexcel_hmac_sha3_512_digest,
+		.setkey = safexcel_hmac_sha3_setkey,
+		.export = safexcel_sha3_export,
+		.import = safexcel_sha3_import,
+		.halg = {
+			.digestsize = SHA3_512_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "hmac(sha3-512)",
+				.cra_driver_name = "safexcel-hmac-sha3-512",
+				.cra_priority = SAFEXCEL_CRA_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY |
+					     CRYPTO_ALG_NEED_FALLBACK,
+				.cra_blocksize = SHA3_512_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_hmac_sha3_512_cra_init,
+				.cra_exit = safexcel_hmac_sha3_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
diff --git a/drivers/crypto/inside-secure/safexcel_ring.c b/drivers/crypto/inside-secure/safexcel_ring.c
index 0f269b89cfd4..9237ba745c2f 100644
--- a/drivers/crypto/inside-secure/safexcel_ring.c
+++ b/drivers/crypto/inside-secure/safexcel_ring.c
@@ -14,7 +14,7 @@ int safexcel_init_ring_descriptors(struct safexcel_crypto_priv *priv,
 				   struct safexcel_desc_ring *cdr,
 				   struct safexcel_desc_ring *rdr)
 {
-	cdr->offset = sizeof(u32) * priv->config.cd_offset;
+	cdr->offset = priv->config.cd_offset;
 	cdr->base = dmam_alloc_coherent(priv->dev,
 					cdr->offset * EIP197_DEFAULT_RING_SIZE,
 					&cdr->base_dma, GFP_KERNEL);
@@ -24,7 +24,7 @@ int safexcel_init_ring_descriptors(struct safexcel_crypto_priv *priv,
 	cdr->base_end = cdr->base + cdr->offset * (EIP197_DEFAULT_RING_SIZE - 1);
 	cdr->read = cdr->base;
 
-	rdr->offset = sizeof(u32) * priv->config.rd_offset;
+	rdr->offset = priv->config.rd_offset;
 	rdr->base = dmam_alloc_coherent(priv->dev,
 					rdr->offset * EIP197_DEFAULT_RING_SIZE,
 					&rdr->base_dma, GFP_KERNEL);
@@ -180,6 +180,7 @@ struct safexcel_result_desc *safexcel_add_rdesc(struct safexcel_crypto_priv *pri
 
 	rdesc->first_seg = first;
 	rdesc->last_seg = last;
+	rdesc->result_size = EIP197_RD64_RESULT_SIZE;
 	rdesc->particle_size = len;
 	rdesc->data_lo = lower_32_bits(data);
 	rdesc->data_hi = upper_32_bits(data);
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 9181523ba760..391e3b4df364 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -23,6 +23,7 @@
 #include <crypto/sha.h>
 #include <crypto/algapi.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
 #include <crypto/authenc.h>
 #include <crypto/scatterwalk.h>
 
@@ -137,7 +138,7 @@ struct crypt_ctl {
 	/* Used by Host: 4*4 bytes*/
 	unsigned ctl_flags;
 	union {
-		struct ablkcipher_request *ablk_req;
+		struct skcipher_request *ablk_req;
 		struct aead_request *aead_req;
 		struct crypto_tfm *tfm;
 	} data;
@@ -186,7 +187,7 @@ struct ixp_ctx {
 };
 
 struct ixp_alg {
-	struct crypto_alg crypto;
+	struct skcipher_alg crypto;
 	const struct ix_hash_algo *hash;
 	u32 cfg_enc;
 	u32 cfg_dec;
@@ -239,17 +240,17 @@ static inline struct crypt_ctl *crypt_phys2virt(dma_addr_t phys)
 
 static inline u32 cipher_cfg_enc(struct crypto_tfm *tfm)
 {
-	return container_of(tfm->__crt_alg, struct ixp_alg,crypto)->cfg_enc;
+	return container_of(tfm->__crt_alg, struct ixp_alg,crypto.base)->cfg_enc;
 }
 
 static inline u32 cipher_cfg_dec(struct crypto_tfm *tfm)
 {
-	return container_of(tfm->__crt_alg, struct ixp_alg,crypto)->cfg_dec;
+	return container_of(tfm->__crt_alg, struct ixp_alg,crypto.base)->cfg_dec;
 }
 
 static inline const struct ix_hash_algo *ix_hash(struct crypto_tfm *tfm)
 {
-	return container_of(tfm->__crt_alg, struct ixp_alg, crypto)->hash;
+	return container_of(tfm->__crt_alg, struct ixp_alg, crypto.base)->hash;
 }
 
 static int setup_crypt_desc(void)
@@ -378,8 +379,8 @@ static void one_packet(dma_addr_t phys)
 		break;
 	}
 	case CTL_FLAG_PERFORM_ABLK: {
-		struct ablkcipher_request *req = crypt->data.ablk_req;
-		struct ablk_ctx *req_ctx = ablkcipher_request_ctx(req);
+		struct skcipher_request *req = crypt->data.ablk_req;
+		struct ablk_ctx *req_ctx = skcipher_request_ctx(req);
 
 		if (req_ctx->dst) {
 			free_buf_chain(dev, req_ctx->dst, crypt->dst_buf);
@@ -571,10 +572,10 @@ static int init_tfm(struct crypto_tfm *tfm)
 	return ret;
 }
 
-static int init_tfm_ablk(struct crypto_tfm *tfm)
+static int init_tfm_ablk(struct crypto_skcipher *tfm)
 {
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ablk_ctx);
-	return init_tfm(tfm);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct ablk_ctx));
+	return init_tfm(crypto_skcipher_tfm(tfm));
 }
 
 static int init_tfm_aead(struct crypto_aead *tfm)
@@ -590,6 +591,11 @@ static void exit_tfm(struct crypto_tfm *tfm)
 	free_sa_dir(&ctx->decrypt);
 }
 
+static void exit_tfm_ablk(struct crypto_skcipher *tfm)
+{
+	exit_tfm(crypto_skcipher_tfm(tfm));
+}
+
 static void exit_tfm_aead(struct crypto_aead *tfm)
 {
 	exit_tfm(crypto_aead_tfm(tfm));
@@ -809,10 +815,10 @@ static struct buffer_desc *chainup_buffers(struct device *dev,
 	return buf;
 }
 
-static int ablk_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int ablk_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			unsigned int key_len)
 {
-	struct ixp_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct ixp_ctx *ctx = crypto_skcipher_ctx(tfm);
 	u32 *flags = &tfm->base.crt_flags;
 	int ret;
 
@@ -845,17 +851,17 @@ out:
 	return ret;
 }
 
-static int ablk_des3_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int ablk_des3_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			    unsigned int key_len)
 {
-	return verify_ablkcipher_des3_key(tfm, key) ?:
+	return verify_skcipher_des3_key(tfm, key) ?:
 	       ablk_setkey(tfm, key, key_len);
 }
 
-static int ablk_rfc3686_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int ablk_rfc3686_setkey(struct crypto_skcipher *tfm, const u8 *key,
 		unsigned int key_len)
 {
-	struct ixp_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct ixp_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	/* the nonce is stored in bytes at end of key */
 	if (key_len < CTR_RFC3686_NONCE_SIZE)
@@ -868,16 +874,16 @@ static int ablk_rfc3686_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 	return ablk_setkey(tfm, key, key_len);
 }
 
-static int ablk_perform(struct ablkcipher_request *req, int encrypt)
+static int ablk_perform(struct skcipher_request *req, int encrypt)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct ixp_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	unsigned ivsize = crypto_ablkcipher_ivsize(tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct ixp_ctx *ctx = crypto_skcipher_ctx(tfm);
+	unsigned ivsize = crypto_skcipher_ivsize(tfm);
 	struct ix_sa_dir *dir;
 	struct crypt_ctl *crypt;
-	unsigned int nbytes = req->nbytes;
+	unsigned int nbytes = req->cryptlen;
 	enum dma_data_direction src_direction = DMA_BIDIRECTIONAL;
-	struct ablk_ctx *req_ctx = ablkcipher_request_ctx(req);
+	struct ablk_ctx *req_ctx = skcipher_request_ctx(req);
 	struct buffer_desc src_hook;
 	struct device *dev = &pdev->dev;
 	gfp_t flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ?
@@ -902,8 +908,8 @@ static int ablk_perform(struct ablkcipher_request *req, int encrypt)
 	crypt->crypt_offs = 0;
 	crypt->crypt_len = nbytes;
 
-	BUG_ON(ivsize && !req->info);
-	memcpy(crypt->iv, req->info, ivsize);
+	BUG_ON(ivsize && !req->iv);
+	memcpy(crypt->iv, req->iv, ivsize);
 	if (req->src != req->dst) {
 		struct buffer_desc dst_hook;
 		crypt->mode |= NPE_OP_NOT_IN_PLACE;
@@ -941,22 +947,22 @@ free_buf_dest:
 	return -ENOMEM;
 }
 
-static int ablk_encrypt(struct ablkcipher_request *req)
+static int ablk_encrypt(struct skcipher_request *req)
 {
 	return ablk_perform(req, 1);
 }
 
-static int ablk_decrypt(struct ablkcipher_request *req)
+static int ablk_decrypt(struct skcipher_request *req)
 {
 	return ablk_perform(req, 0);
 }
 
-static int ablk_rfc3686_crypt(struct ablkcipher_request *req)
+static int ablk_rfc3686_crypt(struct skcipher_request *req)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct ixp_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct ixp_ctx *ctx = crypto_skcipher_ctx(tfm);
 	u8 iv[CTR_RFC3686_BLOCK_SIZE];
-	u8 *info = req->info;
+	u8 *info = req->iv;
 	int ret;
 
 	/* set up counter block */
@@ -967,9 +973,9 @@ static int ablk_rfc3686_crypt(struct ablkcipher_request *req)
 	*(__be32 *)(iv + CTR_RFC3686_NONCE_SIZE + CTR_RFC3686_IV_SIZE) =
 		cpu_to_be32(1);
 
-	req->info = iv;
+	req->iv = iv;
 	ret = ablk_perform(req, 1);
-	req->info = info;
+	req->iv = info;
 	return ret;
 }
 
@@ -1212,107 +1218,91 @@ static int aead_decrypt(struct aead_request *req)
 static struct ixp_alg ixp4xx_algos[] = {
 {
 	.crypto	= {
-		.cra_name	= "cbc(des)",
-		.cra_blocksize	= DES_BLOCK_SIZE,
-		.cra_u		= { .ablkcipher = {
-			.min_keysize	= DES_KEY_SIZE,
-			.max_keysize	= DES_KEY_SIZE,
-			.ivsize		= DES_BLOCK_SIZE,
-			}
-		}
+		.base.cra_name		= "cbc(des)",
+		.base.cra_blocksize	= DES_BLOCK_SIZE,
+
+		.min_keysize		= DES_KEY_SIZE,
+		.max_keysize		= DES_KEY_SIZE,
+		.ivsize			= DES_BLOCK_SIZE,
 	},
 	.cfg_enc = CIPH_ENCR | MOD_DES | MOD_CBC_ENC | KEYLEN_192,
 	.cfg_dec = CIPH_DECR | MOD_DES | MOD_CBC_DEC | KEYLEN_192,
 
 }, {
 	.crypto	= {
-		.cra_name	= "ecb(des)",
-		.cra_blocksize	= DES_BLOCK_SIZE,
-		.cra_u		= { .ablkcipher = {
-			.min_keysize	= DES_KEY_SIZE,
-			.max_keysize	= DES_KEY_SIZE,
-			}
-		}
+		.base.cra_name		= "ecb(des)",
+		.base.cra_blocksize	= DES_BLOCK_SIZE,
+		.min_keysize		= DES_KEY_SIZE,
+		.max_keysize		= DES_KEY_SIZE,
 	},
 	.cfg_enc = CIPH_ENCR | MOD_DES | MOD_ECB | KEYLEN_192,
 	.cfg_dec = CIPH_DECR | MOD_DES | MOD_ECB | KEYLEN_192,
 }, {
 	.crypto	= {
-		.cra_name	= "cbc(des3_ede)",
-		.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
-		.cra_u		= { .ablkcipher = {
-			.min_keysize	= DES3_EDE_KEY_SIZE,
-			.max_keysize	= DES3_EDE_KEY_SIZE,
-			.ivsize		= DES3_EDE_BLOCK_SIZE,
-			.setkey		= ablk_des3_setkey,
-			}
-		}
+		.base.cra_name		= "cbc(des3_ede)",
+		.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+
+		.min_keysize		= DES3_EDE_KEY_SIZE,
+		.max_keysize		= DES3_EDE_KEY_SIZE,
+		.ivsize			= DES3_EDE_BLOCK_SIZE,
+		.setkey			= ablk_des3_setkey,
 	},
 	.cfg_enc = CIPH_ENCR | MOD_3DES | MOD_CBC_ENC | KEYLEN_192,
 	.cfg_dec = CIPH_DECR | MOD_3DES | MOD_CBC_DEC | KEYLEN_192,
 }, {
 	.crypto	= {
-		.cra_name	= "ecb(des3_ede)",
-		.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
-		.cra_u		= { .ablkcipher = {
-			.min_keysize	= DES3_EDE_KEY_SIZE,
-			.max_keysize	= DES3_EDE_KEY_SIZE,
-			.setkey		= ablk_des3_setkey,
-			}
-		}
+		.base.cra_name		= "ecb(des3_ede)",
+		.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+
+		.min_keysize		= DES3_EDE_KEY_SIZE,
+		.max_keysize		= DES3_EDE_KEY_SIZE,
+		.setkey			= ablk_des3_setkey,
 	},
 	.cfg_enc = CIPH_ENCR | MOD_3DES | MOD_ECB | KEYLEN_192,
 	.cfg_dec = CIPH_DECR | MOD_3DES | MOD_ECB | KEYLEN_192,
 }, {
 	.crypto	= {
-		.cra_name	= "cbc(aes)",
-		.cra_blocksize	= AES_BLOCK_SIZE,
-		.cra_u		= { .ablkcipher = {
-			.min_keysize	= AES_MIN_KEY_SIZE,
-			.max_keysize	= AES_MAX_KEY_SIZE,
-			.ivsize		= AES_BLOCK_SIZE,
-			}
-		}
+		.base.cra_name		= "cbc(aes)",
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.ivsize			= AES_BLOCK_SIZE,
 	},
 	.cfg_enc = CIPH_ENCR | MOD_AES | MOD_CBC_ENC,
 	.cfg_dec = CIPH_DECR | MOD_AES | MOD_CBC_DEC,
 }, {
 	.crypto	= {
-		.cra_name	= "ecb(aes)",
-		.cra_blocksize	= AES_BLOCK_SIZE,
-		.cra_u		= { .ablkcipher = {
-			.min_keysize	= AES_MIN_KEY_SIZE,
-			.max_keysize	= AES_MAX_KEY_SIZE,
-			}
-		}
+		.base.cra_name		= "ecb(aes)",
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
 	},
 	.cfg_enc = CIPH_ENCR | MOD_AES | MOD_ECB,
 	.cfg_dec = CIPH_DECR | MOD_AES | MOD_ECB,
 }, {
 	.crypto	= {
-		.cra_name	= "ctr(aes)",
-		.cra_blocksize	= AES_BLOCK_SIZE,
-		.cra_u		= { .ablkcipher = {
-			.min_keysize	= AES_MIN_KEY_SIZE,
-			.max_keysize	= AES_MAX_KEY_SIZE,
-			.ivsize		= AES_BLOCK_SIZE,
-			}
-		}
+		.base.cra_name		= "ctr(aes)",
+		.base.cra_blocksize	= 1,
+
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.ivsize			= AES_BLOCK_SIZE,
 	},
 	.cfg_enc = CIPH_ENCR | MOD_AES | MOD_CTR,
 	.cfg_dec = CIPH_ENCR | MOD_AES | MOD_CTR,
 }, {
 	.crypto	= {
-		.cra_name	= "rfc3686(ctr(aes))",
-		.cra_blocksize	= AES_BLOCK_SIZE,
-		.cra_u		= { .ablkcipher = {
-			.min_keysize	= AES_MIN_KEY_SIZE,
-			.max_keysize	= AES_MAX_KEY_SIZE,
-			.ivsize		= AES_BLOCK_SIZE,
-			.setkey		= ablk_rfc3686_setkey,
-			.encrypt	= ablk_rfc3686_crypt,
-			.decrypt	= ablk_rfc3686_crypt }
-		}
+		.base.cra_name		= "rfc3686(ctr(aes))",
+		.base.cra_blocksize	= 1,
+
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.ivsize			= AES_BLOCK_SIZE,
+		.setkey			= ablk_rfc3686_setkey,
+		.encrypt		= ablk_rfc3686_crypt,
+		.decrypt		= ablk_rfc3686_crypt,
 	},
 	.cfg_enc = CIPH_ENCR | MOD_AES | MOD_CTR,
 	.cfg_dec = CIPH_ENCR | MOD_AES | MOD_CTR,
@@ -1421,10 +1411,10 @@ static int __init ixp_module_init(void)
 		return err;
 	}
 	for (i=0; i< num; i++) {
-		struct crypto_alg *cra = &ixp4xx_algos[i].crypto;
+		struct skcipher_alg *cra = &ixp4xx_algos[i].crypto;
 
-		if (snprintf(cra->cra_driver_name, CRYPTO_MAX_ALG_NAME,
-			"%s"IXP_POSTFIX, cra->cra_name) >=
+		if (snprintf(cra->base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+			"%s"IXP_POSTFIX, cra->base.cra_name) >=
 			CRYPTO_MAX_ALG_NAME)
 		{
 			continue;
@@ -1434,26 +1424,24 @@ static int __init ixp_module_init(void)
 		}
 
 		/* block ciphers */
-		cra->cra_type = &crypto_ablkcipher_type;
-		cra->cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-				 CRYPTO_ALG_KERN_DRIVER_ONLY |
-				 CRYPTO_ALG_ASYNC;
-		if (!cra->cra_ablkcipher.setkey)
-			cra->cra_ablkcipher.setkey = ablk_setkey;
-		if (!cra->cra_ablkcipher.encrypt)
-			cra->cra_ablkcipher.encrypt = ablk_encrypt;
-		if (!cra->cra_ablkcipher.decrypt)
-			cra->cra_ablkcipher.decrypt = ablk_decrypt;
-		cra->cra_init = init_tfm_ablk;
-
-		cra->cra_ctxsize = sizeof(struct ixp_ctx);
-		cra->cra_module = THIS_MODULE;
-		cra->cra_alignmask = 3;
-		cra->cra_priority = 300;
-		cra->cra_exit = exit_tfm;
-		if (crypto_register_alg(cra))
+		cra->base.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY |
+				      CRYPTO_ALG_ASYNC;
+		if (!cra->setkey)
+			cra->setkey = ablk_setkey;
+		if (!cra->encrypt)
+			cra->encrypt = ablk_encrypt;
+		if (!cra->decrypt)
+			cra->decrypt = ablk_decrypt;
+		cra->init = init_tfm_ablk;
+		cra->exit = exit_tfm_ablk;
+
+		cra->base.cra_ctxsize = sizeof(struct ixp_ctx);
+		cra->base.cra_module = THIS_MODULE;
+		cra->base.cra_alignmask = 3;
+		cra->base.cra_priority = 300;
+		if (crypto_register_skcipher(cra))
 			printk(KERN_ERR "Failed to register '%s'\n",
-				cra->cra_name);
+				cra->base.cra_name);
 		else
 			ixp4xx_algos[i].registered = 1;
 	}
@@ -1504,7 +1492,7 @@ static void __exit ixp_module_exit(void)
 
 	for (i=0; i< num; i++) {
 		if (ixp4xx_algos[i].registered)
-			crypto_unregister_alg(&ixp4xx_algos[i].crypto);
+			crypto_unregister_skcipher(&ixp4xx_algos[i].crypto);
 	}
 	release_ixp_crypto(&pdev->dev);
 	platform_device_unregister(pdev);
diff --git a/drivers/crypto/marvell/cesa.h b/drivers/crypto/marvell/cesa.h
index d63a6ee905c9..f1ed3b85c0d2 100644
--- a/drivers/crypto/marvell/cesa.h
+++ b/drivers/crypto/marvell/cesa.h
@@ -232,13 +232,13 @@ struct mv_cesa_sec_accel_desc {
 };
 
 /**
- * struct mv_cesa_blkcipher_op_ctx - cipher operation context
+ * struct mv_cesa_skcipher_op_ctx - cipher operation context
  * @key:	cipher key
  * @iv:		cipher IV
  *
  * Context associated to a cipher operation.
  */
-struct mv_cesa_blkcipher_op_ctx {
+struct mv_cesa_skcipher_op_ctx {
 	u32 key[8];
 	u32 iv[4];
 };
@@ -265,7 +265,7 @@ struct mv_cesa_hash_op_ctx {
 struct mv_cesa_op_ctx {
 	struct mv_cesa_sec_accel_desc desc;
 	union {
-		struct mv_cesa_blkcipher_op_ctx blkcipher;
+		struct mv_cesa_skcipher_op_ctx skcipher;
 		struct mv_cesa_hash_op_ctx hash;
 	} ctx;
 };
diff --git a/drivers/crypto/marvell/cipher.c b/drivers/crypto/marvell/cipher.c
index 84ceddfee76b..d8e8c857770c 100644
--- a/drivers/crypto/marvell/cipher.c
+++ b/drivers/crypto/marvell/cipher.c
@@ -209,7 +209,7 @@ mv_cesa_skcipher_complete(struct crypto_async_request *req)
 		struct mv_cesa_req *basereq;
 
 		basereq = &creq->base;
-		memcpy(skreq->iv, basereq->chain.last->op->ctx.blkcipher.iv,
+		memcpy(skreq->iv, basereq->chain.last->op->ctx.skcipher.iv,
 		       ivsize);
 	} else {
 		memcpy_fromio(skreq->iv,
@@ -470,7 +470,7 @@ static int mv_cesa_des_op(struct skcipher_request *req,
 	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTM_DES,
 			      CESA_SA_DESC_CFG_CRYPTM_MSK);
 
-	memcpy(tmpl->ctx.blkcipher.key, ctx->key, DES_KEY_SIZE);
+	memcpy(tmpl->ctx.skcipher.key, ctx->key, DES_KEY_SIZE);
 
 	return mv_cesa_skcipher_queue_req(req, tmpl);
 }
@@ -523,7 +523,7 @@ static int mv_cesa_cbc_des_op(struct skcipher_request *req,
 	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTCM_CBC,
 			      CESA_SA_DESC_CFG_CRYPTCM_MSK);
 
-	memcpy(tmpl->ctx.blkcipher.iv, req->iv, DES_BLOCK_SIZE);
+	memcpy(tmpl->ctx.skcipher.iv, req->iv, DES_BLOCK_SIZE);
 
 	return mv_cesa_des_op(req, tmpl);
 }
@@ -575,7 +575,7 @@ static int mv_cesa_des3_op(struct skcipher_request *req,
 	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTM_3DES,
 			      CESA_SA_DESC_CFG_CRYPTM_MSK);
 
-	memcpy(tmpl->ctx.blkcipher.key, ctx->key, DES3_EDE_KEY_SIZE);
+	memcpy(tmpl->ctx.skcipher.key, ctx->key, DES3_EDE_KEY_SIZE);
 
 	return mv_cesa_skcipher_queue_req(req, tmpl);
 }
@@ -628,7 +628,7 @@ struct skcipher_alg mv_cesa_ecb_des3_ede_alg = {
 static int mv_cesa_cbc_des3_op(struct skcipher_request *req,
 			       struct mv_cesa_op_ctx *tmpl)
 {
-	memcpy(tmpl->ctx.blkcipher.iv, req->iv, DES3_EDE_BLOCK_SIZE);
+	memcpy(tmpl->ctx.skcipher.iv, req->iv, DES3_EDE_BLOCK_SIZE);
 
 	return mv_cesa_des3_op(req, tmpl);
 }
@@ -694,7 +694,7 @@ static int mv_cesa_aes_op(struct skcipher_request *req,
 		key = ctx->aes.key_enc;
 
 	for (i = 0; i < ctx->aes.key_length / sizeof(u32); i++)
-		tmpl->ctx.blkcipher.key[i] = cpu_to_le32(key[i]);
+		tmpl->ctx.skcipher.key[i] = cpu_to_le32(key[i]);
 
 	if (ctx->aes.key_length == 24)
 		cfg |= CESA_SA_DESC_CFG_AES_LEN_192;
@@ -755,7 +755,7 @@ static int mv_cesa_cbc_aes_op(struct skcipher_request *req,
 {
 	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTCM_CBC,
 			      CESA_SA_DESC_CFG_CRYPTCM_MSK);
-	memcpy(tmpl->ctx.blkcipher.iv, req->iv, AES_BLOCK_SIZE);
+	memcpy(tmpl->ctx.skcipher.iv, req->iv, AES_BLOCK_SIZE);
 
 	return mv_cesa_aes_op(req, tmpl);
 }
diff --git a/drivers/crypto/mediatek/mtk-aes.c b/drivers/crypto/mediatek/mtk-aes.c
index 90c9644fb8a8..90880a81c534 100644
--- a/drivers/crypto/mediatek/mtk-aes.c
+++ b/drivers/crypto/mediatek/mtk-aes.c
@@ -11,6 +11,7 @@
 
 #include <crypto/aes.h>
 #include <crypto/gcm.h>
+#include <crypto/internal/skcipher.h>
 #include "mtk-platform.h"
 
 #define AES_QUEUE_SIZE		512
@@ -414,7 +415,7 @@ exit:
 static void mtk_aes_info_init(struct mtk_cryp *cryp, struct mtk_aes_rec *aes,
 			      size_t len)
 {
-	struct ablkcipher_request *req = ablkcipher_request_cast(aes->areq);
+	struct skcipher_request *req = skcipher_request_cast(aes->areq);
 	struct mtk_aes_base_ctx *ctx = aes->ctx;
 	struct mtk_aes_info *info = &ctx->info;
 	u32 cnt = 0;
@@ -450,7 +451,7 @@ static void mtk_aes_info_init(struct mtk_cryp *cryp, struct mtk_aes_rec *aes,
 		return;
 	}
 
-	mtk_aes_write_state_le(info->state + ctx->keylen, req->info,
+	mtk_aes_write_state_le(info->state + ctx->keylen, (void *)req->iv,
 			       AES_BLOCK_SIZE);
 ctr:
 	info->tfm[0] += AES_TFM_SIZE(SIZE_IN_WORDS(AES_BLOCK_SIZE));
@@ -552,13 +553,13 @@ static int mtk_aes_transfer_complete(struct mtk_cryp *cryp,
 
 static int mtk_aes_start(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 {
-	struct ablkcipher_request *req = ablkcipher_request_cast(aes->areq);
-	struct mtk_aes_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct skcipher_request *req = skcipher_request_cast(aes->areq);
+	struct mtk_aes_reqctx *rctx = skcipher_request_ctx(req);
 
 	mtk_aes_set_mode(aes, rctx);
 	aes->resume = mtk_aes_transfer_complete;
 
-	return mtk_aes_dma(cryp, aes, req->src, req->dst, req->nbytes);
+	return mtk_aes_dma(cryp, aes, req->src, req->dst, req->cryptlen);
 }
 
 static inline struct mtk_aes_ctr_ctx *
@@ -571,7 +572,7 @@ static int mtk_aes_ctr_transfer(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 {
 	struct mtk_aes_base_ctx *ctx = aes->ctx;
 	struct mtk_aes_ctr_ctx *cctx = mtk_aes_ctr_ctx_cast(ctx);
-	struct ablkcipher_request *req = ablkcipher_request_cast(aes->areq);
+	struct skcipher_request *req = skcipher_request_cast(aes->areq);
 	struct scatterlist *src, *dst;
 	u32 start, end, ctr, blocks;
 	size_t datalen;
@@ -579,11 +580,11 @@ static int mtk_aes_ctr_transfer(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 
 	/* Check for transfer completion. */
 	cctx->offset += aes->total;
-	if (cctx->offset >= req->nbytes)
+	if (cctx->offset >= req->cryptlen)
 		return mtk_aes_transfer_complete(cryp, aes);
 
 	/* Compute data length. */
-	datalen = req->nbytes - cctx->offset;
+	datalen = req->cryptlen - cctx->offset;
 	blocks = DIV_ROUND_UP(datalen, AES_BLOCK_SIZE);
 	ctr = be32_to_cpu(cctx->iv[3]);
 
@@ -591,7 +592,7 @@ static int mtk_aes_ctr_transfer(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 	start = ctr;
 	end = start + blocks - 1;
 	if (end < start) {
-		ctr |= 0xffffffff;
+		ctr = 0xffffffff;
 		datalen = AES_BLOCK_SIZE * -start;
 		fragmented = true;
 	}
@@ -620,12 +621,12 @@ static int mtk_aes_ctr_transfer(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 static int mtk_aes_ctr_start(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 {
 	struct mtk_aes_ctr_ctx *cctx = mtk_aes_ctr_ctx_cast(aes->ctx);
-	struct ablkcipher_request *req = ablkcipher_request_cast(aes->areq);
-	struct mtk_aes_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct skcipher_request *req = skcipher_request_cast(aes->areq);
+	struct mtk_aes_reqctx *rctx = skcipher_request_ctx(req);
 
 	mtk_aes_set_mode(aes, rctx);
 
-	memcpy(cctx->iv, req->info, AES_BLOCK_SIZE);
+	memcpy(cctx->iv, req->iv, AES_BLOCK_SIZE);
 	cctx->offset = 0;
 	aes->total = 0;
 	aes->resume = mtk_aes_ctr_transfer;
@@ -634,10 +635,10 @@ static int mtk_aes_ctr_start(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 }
 
 /* Check and set the AES key to transform state buffer */
-static int mtk_aes_setkey(struct crypto_ablkcipher *tfm,
+static int mtk_aes_setkey(struct crypto_skcipher *tfm,
 			  const u8 *key, u32 keylen)
 {
-	struct mtk_aes_base_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct mtk_aes_base_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	switch (keylen) {
 	case AES_KEYSIZE_128:
@@ -651,7 +652,7 @@ static int mtk_aes_setkey(struct crypto_ablkcipher *tfm,
 		break;
 
 	default:
-		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
@@ -661,10 +662,10 @@ static int mtk_aes_setkey(struct crypto_ablkcipher *tfm,
 	return 0;
 }
 
-static int mtk_aes_crypt(struct ablkcipher_request *req, u64 mode)
+static int mtk_aes_crypt(struct skcipher_request *req, u64 mode)
 {
-	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
-	struct mtk_aes_base_ctx *ctx = crypto_ablkcipher_ctx(ablkcipher);
+	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
+	struct mtk_aes_base_ctx *ctx = crypto_skcipher_ctx(skcipher);
 	struct mtk_aes_reqctx *rctx;
 	struct mtk_cryp *cryp;
 
@@ -672,185 +673,168 @@ static int mtk_aes_crypt(struct ablkcipher_request *req, u64 mode)
 	if (!cryp)
 		return -ENODEV;
 
-	rctx = ablkcipher_request_ctx(req);
+	rctx = skcipher_request_ctx(req);
 	rctx->mode = mode;
 
 	return mtk_aes_handle_queue(cryp, !(mode & AES_FLAGS_ENCRYPT),
 				    &req->base);
 }
 
-static int mtk_aes_ecb_encrypt(struct ablkcipher_request *req)
+static int mtk_aes_ecb_encrypt(struct skcipher_request *req)
 {
 	return mtk_aes_crypt(req, AES_FLAGS_ENCRYPT | AES_FLAGS_ECB);
 }
 
-static int mtk_aes_ecb_decrypt(struct ablkcipher_request *req)
+static int mtk_aes_ecb_decrypt(struct skcipher_request *req)
 {
 	return mtk_aes_crypt(req, AES_FLAGS_ECB);
 }
 
-static int mtk_aes_cbc_encrypt(struct ablkcipher_request *req)
+static int mtk_aes_cbc_encrypt(struct skcipher_request *req)
 {
 	return mtk_aes_crypt(req, AES_FLAGS_ENCRYPT | AES_FLAGS_CBC);
 }
 
-static int mtk_aes_cbc_decrypt(struct ablkcipher_request *req)
+static int mtk_aes_cbc_decrypt(struct skcipher_request *req)
 {
 	return mtk_aes_crypt(req, AES_FLAGS_CBC);
 }
 
-static int mtk_aes_ctr_encrypt(struct ablkcipher_request *req)
+static int mtk_aes_ctr_encrypt(struct skcipher_request *req)
 {
 	return mtk_aes_crypt(req, AES_FLAGS_ENCRYPT | AES_FLAGS_CTR);
 }
 
-static int mtk_aes_ctr_decrypt(struct ablkcipher_request *req)
+static int mtk_aes_ctr_decrypt(struct skcipher_request *req)
 {
 	return mtk_aes_crypt(req, AES_FLAGS_CTR);
 }
 
-static int mtk_aes_ofb_encrypt(struct ablkcipher_request *req)
+static int mtk_aes_ofb_encrypt(struct skcipher_request *req)
 {
 	return mtk_aes_crypt(req, AES_FLAGS_ENCRYPT | AES_FLAGS_OFB);
 }
 
-static int mtk_aes_ofb_decrypt(struct ablkcipher_request *req)
+static int mtk_aes_ofb_decrypt(struct skcipher_request *req)
 {
 	return mtk_aes_crypt(req, AES_FLAGS_OFB);
 }
 
-static int mtk_aes_cfb_encrypt(struct ablkcipher_request *req)
+static int mtk_aes_cfb_encrypt(struct skcipher_request *req)
 {
 	return mtk_aes_crypt(req, AES_FLAGS_ENCRYPT | AES_FLAGS_CFB128);
 }
 
-static int mtk_aes_cfb_decrypt(struct ablkcipher_request *req)
+static int mtk_aes_cfb_decrypt(struct skcipher_request *req)
 {
 	return mtk_aes_crypt(req, AES_FLAGS_CFB128);
 }
 
-static int mtk_aes_cra_init(struct crypto_tfm *tfm)
+static int mtk_aes_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct mtk_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct mtk_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct mtk_aes_reqctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct mtk_aes_reqctx));
 	ctx->base.start = mtk_aes_start;
 	return 0;
 }
 
-static int mtk_aes_ctr_cra_init(struct crypto_tfm *tfm)
+static int mtk_aes_ctr_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct mtk_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct mtk_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct mtk_aes_reqctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct mtk_aes_reqctx));
 	ctx->base.start = mtk_aes_ctr_start;
 	return 0;
 }
 
-static struct crypto_alg aes_algs[] = {
+static struct skcipher_alg aes_algs[] = {
 {
-	.cra_name		= "cbc(aes)",
-	.cra_driver_name	= "cbc-aes-mtk",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC,
-	.cra_init		= mtk_aes_cra_init,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct mtk_aes_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.setkey		= mtk_aes_setkey,
-		.encrypt	= mtk_aes_cbc_encrypt,
-		.decrypt	= mtk_aes_cbc_decrypt,
-		.ivsize		= AES_BLOCK_SIZE,
-	}
+	.base.cra_name		= "cbc(aes)",
+	.base.cra_driver_name	= "cbc-aes-mtk",
+	.base.cra_priority	= 400,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct mtk_aes_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= mtk_aes_setkey,
+	.encrypt		= mtk_aes_cbc_encrypt,
+	.decrypt		= mtk_aes_cbc_decrypt,
+	.ivsize			= AES_BLOCK_SIZE,
+	.init			= mtk_aes_init_tfm,
 },
 {
-	.cra_name		= "ecb(aes)",
-	.cra_driver_name	= "ecb-aes-mtk",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC,
-	.cra_init		= mtk_aes_cra_init,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct mtk_aes_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.setkey		= mtk_aes_setkey,
-		.encrypt	= mtk_aes_ecb_encrypt,
-		.decrypt	= mtk_aes_ecb_decrypt,
-	}
+	.base.cra_name		= "ecb(aes)",
+	.base.cra_driver_name	= "ecb-aes-mtk",
+	.base.cra_priority	= 400,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct mtk_aes_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= mtk_aes_setkey,
+	.encrypt		= mtk_aes_ecb_encrypt,
+	.decrypt		= mtk_aes_ecb_decrypt,
+	.init			= mtk_aes_init_tfm,
 },
 {
-	.cra_name		= "ctr(aes)",
-	.cra_driver_name	= "ctr-aes-mtk",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC,
-	.cra_init		= mtk_aes_ctr_cra_init,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct mtk_aes_ctr_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= mtk_aes_setkey,
-		.encrypt	= mtk_aes_ctr_encrypt,
-		.decrypt	= mtk_aes_ctr_decrypt,
-	}
+	.base.cra_name		= "ctr(aes)",
+	.base.cra_driver_name	= "ctr-aes-mtk",
+	.base.cra_priority	= 400,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct mtk_aes_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= mtk_aes_setkey,
+	.encrypt		= mtk_aes_ctr_encrypt,
+	.decrypt		= mtk_aes_ctr_decrypt,
+	.init			= mtk_aes_ctr_init_tfm,
 },
 {
-	.cra_name		= "ofb(aes)",
-	.cra_driver_name	= "ofb-aes-mtk",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC,
-	.cra_init		= mtk_aes_cra_init,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct mtk_aes_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= mtk_aes_setkey,
-		.encrypt	= mtk_aes_ofb_encrypt,
-		.decrypt	= mtk_aes_ofb_decrypt,
-	}
+	.base.cra_name		= "ofb(aes)",
+	.base.cra_driver_name	= "ofb-aes-mtk",
+	.base.cra_priority	= 400,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct mtk_aes_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= mtk_aes_setkey,
+	.encrypt		= mtk_aes_ofb_encrypt,
+	.decrypt		= mtk_aes_ofb_decrypt,
 },
 {
-	.cra_name		= "cfb(aes)",
-	.cra_driver_name	= "cfb-aes-mtk",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC,
-	.cra_init		= mtk_aes_cra_init,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct mtk_aes_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= mtk_aes_setkey,
-		.encrypt	= mtk_aes_cfb_encrypt,
-		.decrypt	= mtk_aes_cfb_decrypt,
-	}
+	.base.cra_name		= "cfb(aes)",
+	.base.cra_driver_name	= "cfb-aes-mtk",
+	.base.cra_priority	= 400,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct mtk_aes_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= mtk_aes_setkey,
+	.encrypt		= mtk_aes_cfb_encrypt,
+	.decrypt		= mtk_aes_cfb_decrypt,
 },
 };
 
@@ -1259,7 +1243,7 @@ static void mtk_aes_unregister_algs(void)
 	crypto_unregister_aead(&aes_gcm_alg);
 
 	for (i = 0; i < ARRAY_SIZE(aes_algs); i++)
-		crypto_unregister_alg(&aes_algs[i]);
+		crypto_unregister_skcipher(&aes_algs[i]);
 }
 
 static int mtk_aes_register_algs(void)
@@ -1267,7 +1251,7 @@ static int mtk_aes_register_algs(void)
 	int err, i;
 
 	for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
-		err = crypto_register_alg(&aes_algs[i]);
+		err = crypto_register_skcipher(&aes_algs[i]);
 		if (err)
 			goto err_aes_algs;
 	}
@@ -1280,7 +1264,7 @@ static int mtk_aes_register_algs(void)
 
 err_aes_algs:
 	for (; i--; )
-		crypto_unregister_alg(&aes_algs[i]);
+		crypto_unregister_skcipher(&aes_algs[i]);
 
 	return err;
 }
diff --git a/drivers/crypto/mxs-dcp.c b/drivers/crypto/mxs-dcp.c
index bf8d2197bc11..f438b425c655 100644
--- a/drivers/crypto/mxs-dcp.c
+++ b/drivers/crypto/mxs-dcp.c
@@ -211,11 +211,11 @@ static int mxs_dcp_start_dma(struct dcp_async_ctx *actx)
  * Encryption (AES128)
  */
 static int mxs_dcp_run_aes(struct dcp_async_ctx *actx,
-			   struct ablkcipher_request *req, int init)
+			   struct skcipher_request *req, int init)
 {
 	struct dcp *sdcp = global_sdcp;
 	struct dcp_dma_desc *desc = &sdcp->coh->desc[actx->chan];
-	struct dcp_aes_req_ctx *rctx = ablkcipher_request_ctx(req);
+	struct dcp_aes_req_ctx *rctx = skcipher_request_ctx(req);
 	int ret;
 
 	dma_addr_t key_phys = dma_map_single(sdcp->dev, sdcp->coh->aes_key,
@@ -274,9 +274,9 @@ static int mxs_dcp_aes_block_crypt(struct crypto_async_request *arq)
 {
 	struct dcp *sdcp = global_sdcp;
 
-	struct ablkcipher_request *req = ablkcipher_request_cast(arq);
+	struct skcipher_request *req = skcipher_request_cast(arq);
 	struct dcp_async_ctx *actx = crypto_tfm_ctx(arq->tfm);
-	struct dcp_aes_req_ctx *rctx = ablkcipher_request_ctx(req);
+	struct dcp_aes_req_ctx *rctx = skcipher_request_ctx(req);
 
 	struct scatterlist *dst = req->dst;
 	struct scatterlist *src = req->src;
@@ -305,7 +305,7 @@ static int mxs_dcp_aes_block_crypt(struct crypto_async_request *arq)
 
 	if (!rctx->ecb) {
 		/* Copy the CBC IV just past the key. */
-		memcpy(key + AES_KEYSIZE_128, req->info, AES_KEYSIZE_128);
+		memcpy(key + AES_KEYSIZE_128, req->iv, AES_KEYSIZE_128);
 		/* CBC needs the INIT set. */
 		init = 1;
 	} else {
@@ -316,10 +316,10 @@ static int mxs_dcp_aes_block_crypt(struct crypto_async_request *arq)
 		src_buf = sg_virt(src);
 		len = sg_dma_len(src);
 		tlen += len;
-		limit_hit = tlen > req->nbytes;
+		limit_hit = tlen > req->cryptlen;
 
 		if (limit_hit)
-			len = req->nbytes - (tlen - len);
+			len = req->cryptlen - (tlen - len);
 
 		do {
 			if (actx->fill + len > out_off)
@@ -375,10 +375,10 @@ static int mxs_dcp_aes_block_crypt(struct crypto_async_request *arq)
 	/* Copy the IV for CBC for chaining */
 	if (!rctx->ecb) {
 		if (rctx->enc)
-			memcpy(req->info, out_buf+(last_out_len-AES_BLOCK_SIZE),
+			memcpy(req->iv, out_buf+(last_out_len-AES_BLOCK_SIZE),
 				AES_BLOCK_SIZE);
 		else
-			memcpy(req->info, in_buf+(last_out_len-AES_BLOCK_SIZE),
+			memcpy(req->iv, in_buf+(last_out_len-AES_BLOCK_SIZE),
 				AES_BLOCK_SIZE);
 	}
 
@@ -422,17 +422,17 @@ static int dcp_chan_thread_aes(void *data)
 	return 0;
 }
 
-static int mxs_dcp_block_fallback(struct ablkcipher_request *req, int enc)
+static int mxs_dcp_block_fallback(struct skcipher_request *req, int enc)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct dcp_async_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct dcp_async_ctx *ctx = crypto_skcipher_ctx(tfm);
 	SYNC_SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
 	int ret;
 
 	skcipher_request_set_sync_tfm(subreq, ctx->fallback);
 	skcipher_request_set_callback(subreq, req->base.flags, NULL, NULL);
 	skcipher_request_set_crypt(subreq, req->src, req->dst,
-				   req->nbytes, req->info);
+				   req->cryptlen, req->iv);
 
 	if (enc)
 		ret = crypto_skcipher_encrypt(subreq);
@@ -444,12 +444,12 @@ static int mxs_dcp_block_fallback(struct ablkcipher_request *req, int enc)
 	return ret;
 }
 
-static int mxs_dcp_aes_enqueue(struct ablkcipher_request *req, int enc, int ecb)
+static int mxs_dcp_aes_enqueue(struct skcipher_request *req, int enc, int ecb)
 {
 	struct dcp *sdcp = global_sdcp;
 	struct crypto_async_request *arq = &req->base;
 	struct dcp_async_ctx *actx = crypto_tfm_ctx(arq->tfm);
-	struct dcp_aes_req_ctx *rctx = ablkcipher_request_ctx(req);
+	struct dcp_aes_req_ctx *rctx = skcipher_request_ctx(req);
 	int ret;
 
 	if (unlikely(actx->key_len != AES_KEYSIZE_128))
@@ -468,30 +468,30 @@ static int mxs_dcp_aes_enqueue(struct ablkcipher_request *req, int enc, int ecb)
 	return ret;
 }
 
-static int mxs_dcp_aes_ecb_decrypt(struct ablkcipher_request *req)
+static int mxs_dcp_aes_ecb_decrypt(struct skcipher_request *req)
 {
 	return mxs_dcp_aes_enqueue(req, 0, 1);
 }
 
-static int mxs_dcp_aes_ecb_encrypt(struct ablkcipher_request *req)
+static int mxs_dcp_aes_ecb_encrypt(struct skcipher_request *req)
 {
 	return mxs_dcp_aes_enqueue(req, 1, 1);
 }
 
-static int mxs_dcp_aes_cbc_decrypt(struct ablkcipher_request *req)
+static int mxs_dcp_aes_cbc_decrypt(struct skcipher_request *req)
 {
 	return mxs_dcp_aes_enqueue(req, 0, 0);
 }
 
-static int mxs_dcp_aes_cbc_encrypt(struct ablkcipher_request *req)
+static int mxs_dcp_aes_cbc_encrypt(struct skcipher_request *req)
 {
 	return mxs_dcp_aes_enqueue(req, 1, 0);
 }
 
-static int mxs_dcp_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int mxs_dcp_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			      unsigned int len)
 {
-	struct dcp_async_ctx *actx = crypto_ablkcipher_ctx(tfm);
+	struct dcp_async_ctx *actx = crypto_skcipher_ctx(tfm);
 	unsigned int ret;
 
 	/*
@@ -525,10 +525,10 @@ static int mxs_dcp_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 	return ret;
 }
 
-static int mxs_dcp_aes_fallback_init(struct crypto_tfm *tfm)
+static int mxs_dcp_aes_fallback_init_tfm(struct crypto_skcipher *tfm)
 {
-	const char *name = crypto_tfm_alg_name(tfm);
-	struct dcp_async_ctx *actx = crypto_tfm_ctx(tfm);
+	const char *name = crypto_tfm_alg_name(crypto_skcipher_tfm(tfm));
+	struct dcp_async_ctx *actx = crypto_skcipher_ctx(tfm);
 	struct crypto_sync_skcipher *blk;
 
 	blk = crypto_alloc_sync_skcipher(name, 0, CRYPTO_ALG_NEED_FALLBACK);
@@ -536,13 +536,13 @@ static int mxs_dcp_aes_fallback_init(struct crypto_tfm *tfm)
 		return PTR_ERR(blk);
 
 	actx->fallback = blk;
-	tfm->crt_ablkcipher.reqsize = sizeof(struct dcp_aes_req_ctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct dcp_aes_req_ctx));
 	return 0;
 }
 
-static void mxs_dcp_aes_fallback_exit(struct crypto_tfm *tfm)
+static void mxs_dcp_aes_fallback_exit_tfm(struct crypto_skcipher *tfm)
 {
-	struct dcp_async_ctx *actx = crypto_tfm_ctx(tfm);
+	struct dcp_async_ctx *actx = crypto_skcipher_ctx(tfm);
 
 	crypto_free_sync_skcipher(actx->fallback);
 }
@@ -854,54 +854,44 @@ static void dcp_sha_cra_exit(struct crypto_tfm *tfm)
 }
 
 /* AES 128 ECB and AES 128 CBC */
-static struct crypto_alg dcp_aes_algs[] = {
+static struct skcipher_alg dcp_aes_algs[] = {
 	{
-		.cra_name		= "ecb(aes)",
-		.cra_driver_name	= "ecb-aes-dcp",
-		.cra_priority		= 400,
-		.cra_alignmask		= 15,
-		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-					  CRYPTO_ALG_ASYNC |
+		.base.cra_name		= "ecb(aes)",
+		.base.cra_driver_name	= "ecb-aes-dcp",
+		.base.cra_priority	= 400,
+		.base.cra_alignmask	= 15,
+		.base.cra_flags		= CRYPTO_ALG_ASYNC |
 					  CRYPTO_ALG_NEED_FALLBACK,
-		.cra_init		= mxs_dcp_aes_fallback_init,
-		.cra_exit		= mxs_dcp_aes_fallback_exit,
-		.cra_blocksize		= AES_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct dcp_async_ctx),
-		.cra_type		= &crypto_ablkcipher_type,
-		.cra_module		= THIS_MODULE,
-		.cra_u	= {
-			.ablkcipher = {
-				.min_keysize	= AES_MIN_KEY_SIZE,
-				.max_keysize	= AES_MAX_KEY_SIZE,
-				.setkey		= mxs_dcp_aes_setkey,
-				.encrypt	= mxs_dcp_aes_ecb_encrypt,
-				.decrypt	= mxs_dcp_aes_ecb_decrypt
-			},
-		},
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct dcp_async_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.setkey			= mxs_dcp_aes_setkey,
+		.encrypt		= mxs_dcp_aes_ecb_encrypt,
+		.decrypt		= mxs_dcp_aes_ecb_decrypt,
+		.init			= mxs_dcp_aes_fallback_init_tfm,
+		.exit			= mxs_dcp_aes_fallback_exit_tfm,
 	}, {
-		.cra_name		= "cbc(aes)",
-		.cra_driver_name	= "cbc-aes-dcp",
-		.cra_priority		= 400,
-		.cra_alignmask		= 15,
-		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-					  CRYPTO_ALG_ASYNC |
+		.base.cra_name		= "cbc(aes)",
+		.base.cra_driver_name	= "cbc-aes-dcp",
+		.base.cra_priority	= 400,
+		.base.cra_alignmask	= 15,
+		.base.cra_flags		= CRYPTO_ALG_ASYNC |
 					  CRYPTO_ALG_NEED_FALLBACK,
-		.cra_init		= mxs_dcp_aes_fallback_init,
-		.cra_exit		= mxs_dcp_aes_fallback_exit,
-		.cra_blocksize		= AES_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct dcp_async_ctx),
-		.cra_type		= &crypto_ablkcipher_type,
-		.cra_module		= THIS_MODULE,
-		.cra_u = {
-			.ablkcipher = {
-				.min_keysize	= AES_MIN_KEY_SIZE,
-				.max_keysize	= AES_MAX_KEY_SIZE,
-				.setkey		= mxs_dcp_aes_setkey,
-				.encrypt	= mxs_dcp_aes_cbc_encrypt,
-				.decrypt	= mxs_dcp_aes_cbc_decrypt,
-				.ivsize		= AES_BLOCK_SIZE,
-			},
-		},
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct dcp_async_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.setkey			= mxs_dcp_aes_setkey,
+		.encrypt		= mxs_dcp_aes_cbc_encrypt,
+		.decrypt		= mxs_dcp_aes_cbc_decrypt,
+		.ivsize			= AES_BLOCK_SIZE,
+		.init			= mxs_dcp_aes_fallback_init_tfm,
+		.exit			= mxs_dcp_aes_fallback_exit_tfm,
 	},
 };
 
@@ -1104,8 +1094,8 @@ static int mxs_dcp_probe(struct platform_device *pdev)
 	sdcp->caps = readl(sdcp->base + MXS_DCP_CAPABILITY1);
 
 	if (sdcp->caps & MXS_DCP_CAPABILITY1_AES128) {
-		ret = crypto_register_algs(dcp_aes_algs,
-					   ARRAY_SIZE(dcp_aes_algs));
+		ret = crypto_register_skciphers(dcp_aes_algs,
+						ARRAY_SIZE(dcp_aes_algs));
 		if (ret) {
 			/* Failed to register algorithm. */
 			dev_err(dev, "Failed to register AES crypto!\n");
@@ -1139,7 +1129,7 @@ err_unregister_sha1:
 
 err_unregister_aes:
 	if (sdcp->caps & MXS_DCP_CAPABILITY1_AES128)
-		crypto_unregister_algs(dcp_aes_algs, ARRAY_SIZE(dcp_aes_algs));
+		crypto_unregister_skciphers(dcp_aes_algs, ARRAY_SIZE(dcp_aes_algs));
 
 err_destroy_aes_thread:
 	kthread_stop(sdcp->thread[DCP_CHAN_CRYPTO]);
@@ -1164,7 +1154,7 @@ static int mxs_dcp_remove(struct platform_device *pdev)
 		crypto_unregister_ahash(&dcp_sha1_alg);
 
 	if (sdcp->caps & MXS_DCP_CAPABILITY1_AES128)
-		crypto_unregister_algs(dcp_aes_algs, ARRAY_SIZE(dcp_aes_algs));
+		crypto_unregister_skciphers(dcp_aes_algs, ARRAY_SIZE(dcp_aes_algs));
 
 	kthread_stop(sdcp->thread[DCP_CHAN_HASH_SHA]);
 	kthread_stop(sdcp->thread[DCP_CHAN_CRYPTO]);
diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
index dc15b06e96ab..63bd565048f4 100644
--- a/drivers/crypto/n2_core.c
+++ b/drivers/crypto/n2_core.c
@@ -23,6 +23,7 @@
 #include <linux/sched.h>
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/algapi.h>
 
@@ -381,8 +382,8 @@ static int n2_hash_cra_init(struct crypto_tfm *tfm)
 	fallback_tfm = crypto_alloc_ahash(fallback_driver_name, 0,
 					  CRYPTO_ALG_NEED_FALLBACK);
 	if (IS_ERR(fallback_tfm)) {
-		pr_warning("Fallback driver '%s' could not be loaded!\n",
-			   fallback_driver_name);
+		pr_warn("Fallback driver '%s' could not be loaded!\n",
+			fallback_driver_name);
 		err = PTR_ERR(fallback_tfm);
 		goto out;
 	}
@@ -418,16 +419,16 @@ static int n2_hmac_cra_init(struct crypto_tfm *tfm)
 	fallback_tfm = crypto_alloc_ahash(fallback_driver_name, 0,
 					  CRYPTO_ALG_NEED_FALLBACK);
 	if (IS_ERR(fallback_tfm)) {
-		pr_warning("Fallback driver '%s' could not be loaded!\n",
-			   fallback_driver_name);
+		pr_warn("Fallback driver '%s' could not be loaded!\n",
+			fallback_driver_name);
 		err = PTR_ERR(fallback_tfm);
 		goto out;
 	}
 
 	child_shash = crypto_alloc_shash(n2alg->child_alg, 0, 0);
 	if (IS_ERR(child_shash)) {
-		pr_warning("Child shash '%s' could not be loaded!\n",
-			   n2alg->child_alg);
+		pr_warn("Child shash '%s' could not be loaded!\n",
+			n2alg->child_alg);
 		err = PTR_ERR(child_shash);
 		goto out_free_fallback;
 	}
@@ -657,7 +658,7 @@ static int n2_hmac_async_digest(struct ahash_request *req)
 				  ctx->hash_key_len);
 }
 
-struct n2_cipher_context {
+struct n2_skcipher_context {
 	int			key_len;
 	int			enc_type;
 	union {
@@ -683,7 +684,7 @@ struct n2_crypto_chunk {
 };
 
 struct n2_request_context {
-	struct ablkcipher_walk	walk;
+	struct skcipher_walk	walk;
 	struct list_head	chunk_list;
 	struct n2_crypto_chunk	chunk;
 	u8			temp_iv[16];
@@ -708,29 +709,29 @@ struct n2_request_context {
  * is not a valid sequence.
  */
 
-struct n2_cipher_alg {
+struct n2_skcipher_alg {
 	struct list_head	entry;
 	u8			enc_type;
-	struct crypto_alg	alg;
+	struct skcipher_alg	skcipher;
 };
 
-static inline struct n2_cipher_alg *n2_cipher_alg(struct crypto_tfm *tfm)
+static inline struct n2_skcipher_alg *n2_skcipher_alg(struct crypto_skcipher *tfm)
 {
-	struct crypto_alg *alg = tfm->__crt_alg;
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
 
-	return container_of(alg, struct n2_cipher_alg, alg);
+	return container_of(alg, struct n2_skcipher_alg, skcipher);
 }
 
-struct n2_cipher_request_context {
-	struct ablkcipher_walk	walk;
+struct n2_skcipher_request_context {
+	struct skcipher_walk	walk;
 };
 
-static int n2_aes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int n2_aes_setkey(struct crypto_skcipher *skcipher, const u8 *key,
 			 unsigned int keylen)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
-	struct n2_cipher_context *ctx = crypto_tfm_ctx(tfm);
-	struct n2_cipher_alg *n2alg = n2_cipher_alg(tfm);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher);
+	struct n2_skcipher_context *ctx = crypto_tfm_ctx(tfm);
+	struct n2_skcipher_alg *n2alg = n2_skcipher_alg(skcipher);
 
 	ctx->enc_type = (n2alg->enc_type & ENC_TYPE_CHAINING_MASK);
 
@@ -745,7 +746,7 @@ static int n2_aes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 		ctx->enc_type |= ENC_TYPE_ALG_AES256;
 		break;
 	default:
-		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		crypto_skcipher_set_flags(skcipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
@@ -754,15 +755,15 @@ static int n2_aes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	return 0;
 }
 
-static int n2_des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int n2_des_setkey(struct crypto_skcipher *skcipher, const u8 *key,
 			 unsigned int keylen)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
-	struct n2_cipher_context *ctx = crypto_tfm_ctx(tfm);
-	struct n2_cipher_alg *n2alg = n2_cipher_alg(tfm);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher);
+	struct n2_skcipher_context *ctx = crypto_tfm_ctx(tfm);
+	struct n2_skcipher_alg *n2alg = n2_skcipher_alg(skcipher);
 	int err;
 
-	err = verify_ablkcipher_des_key(cipher, key);
+	err = verify_skcipher_des_key(skcipher, key);
 	if (err)
 		return err;
 
@@ -773,15 +774,15 @@ static int n2_des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	return 0;
 }
 
-static int n2_3des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int n2_3des_setkey(struct crypto_skcipher *skcipher, const u8 *key,
 			  unsigned int keylen)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
-	struct n2_cipher_context *ctx = crypto_tfm_ctx(tfm);
-	struct n2_cipher_alg *n2alg = n2_cipher_alg(tfm);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher);
+	struct n2_skcipher_context *ctx = crypto_tfm_ctx(tfm);
+	struct n2_skcipher_alg *n2alg = n2_skcipher_alg(skcipher);
 	int err;
 
-	err = verify_ablkcipher_des3_key(cipher, key);
+	err = verify_skcipher_des3_key(skcipher, key);
 	if (err)
 		return err;
 
@@ -792,12 +793,12 @@ static int n2_3des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	return 0;
 }
 
-static int n2_arc4_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int n2_arc4_setkey(struct crypto_skcipher *skcipher, const u8 *key,
 			  unsigned int keylen)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
-	struct n2_cipher_context *ctx = crypto_tfm_ctx(tfm);
-	struct n2_cipher_alg *n2alg = n2_cipher_alg(tfm);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher);
+	struct n2_skcipher_context *ctx = crypto_tfm_ctx(tfm);
+	struct n2_skcipher_alg *n2alg = n2_skcipher_alg(skcipher);
 	u8 *s = ctx->key.arc4;
 	u8 *x = s + 256;
 	u8 *y = x + 1;
@@ -822,7 +823,7 @@ static int n2_arc4_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	return 0;
 }
 
-static inline int cipher_descriptor_len(int nbytes, unsigned int block_size)
+static inline int skcipher_descriptor_len(int nbytes, unsigned int block_size)
 {
 	int this_len = nbytes;
 
@@ -830,10 +831,11 @@ static inline int cipher_descriptor_len(int nbytes, unsigned int block_size)
 	return this_len > (1 << 16) ? (1 << 16) : this_len;
 }
 
-static int __n2_crypt_chunk(struct crypto_tfm *tfm, struct n2_crypto_chunk *cp,
+static int __n2_crypt_chunk(struct crypto_skcipher *skcipher,
+			    struct n2_crypto_chunk *cp,
 			    struct spu_queue *qp, bool encrypt)
 {
-	struct n2_cipher_context *ctx = crypto_tfm_ctx(tfm);
+	struct n2_skcipher_context *ctx = crypto_skcipher_ctx(skcipher);
 	struct cwq_initial_entry *ent;
 	bool in_place;
 	int i;
@@ -877,18 +879,17 @@ static int __n2_crypt_chunk(struct crypto_tfm *tfm, struct n2_crypto_chunk *cp,
 	return (spu_queue_submit(qp, ent) != HV_EOK) ? -EINVAL : 0;
 }
 
-static int n2_compute_chunks(struct ablkcipher_request *req)
+static int n2_compute_chunks(struct skcipher_request *req)
 {
-	struct n2_request_context *rctx = ablkcipher_request_ctx(req);
-	struct ablkcipher_walk *walk = &rctx->walk;
+	struct n2_request_context *rctx = skcipher_request_ctx(req);
+	struct skcipher_walk *walk = &rctx->walk;
 	struct n2_crypto_chunk *chunk;
 	unsigned long dest_prev;
 	unsigned int tot_len;
 	bool prev_in_place;
 	int err, nbytes;
 
-	ablkcipher_walk_init(walk, req->dst, req->src, req->nbytes);
-	err = ablkcipher_walk_phys(req, walk);
+	err = skcipher_walk_async(walk, req);
 	if (err)
 		return err;
 
@@ -910,12 +911,12 @@ static int n2_compute_chunks(struct ablkcipher_request *req)
 		bool in_place;
 		int this_len;
 
-		src_paddr = (page_to_phys(walk->src.page) +
-			     walk->src.offset);
-		dest_paddr = (page_to_phys(walk->dst.page) +
-			      walk->dst.offset);
+		src_paddr = (page_to_phys(walk->src.phys.page) +
+			     walk->src.phys.offset);
+		dest_paddr = (page_to_phys(walk->dst.phys.page) +
+			      walk->dst.phys.offset);
 		in_place = (src_paddr == dest_paddr);
-		this_len = cipher_descriptor_len(nbytes, walk->blocksize);
+		this_len = skcipher_descriptor_len(nbytes, walk->blocksize);
 
 		if (chunk->arr_len != 0) {
 			if (in_place != prev_in_place ||
@@ -946,7 +947,7 @@ static int n2_compute_chunks(struct ablkcipher_request *req)
 		prev_in_place = in_place;
 		tot_len += this_len;
 
-		err = ablkcipher_walk_done(req, walk, nbytes - this_len);
+		err = skcipher_walk_done(walk, nbytes - this_len);
 		if (err)
 			break;
 	}
@@ -958,15 +959,14 @@ static int n2_compute_chunks(struct ablkcipher_request *req)
 	return err;
 }
 
-static void n2_chunk_complete(struct ablkcipher_request *req, void *final_iv)
+static void n2_chunk_complete(struct skcipher_request *req, void *final_iv)
 {
-	struct n2_request_context *rctx = ablkcipher_request_ctx(req);
+	struct n2_request_context *rctx = skcipher_request_ctx(req);
 	struct n2_crypto_chunk *c, *tmp;
 
 	if (final_iv)
 		memcpy(rctx->walk.iv, final_iv, rctx->walk.blocksize);
 
-	ablkcipher_walk_complete(&rctx->walk);
 	list_for_each_entry_safe(c, tmp, &rctx->chunk_list, entry) {
 		list_del(&c->entry);
 		if (unlikely(c != &rctx->chunk))
@@ -975,10 +975,10 @@ static void n2_chunk_complete(struct ablkcipher_request *req, void *final_iv)
 
 }
 
-static int n2_do_ecb(struct ablkcipher_request *req, bool encrypt)
+static int n2_do_ecb(struct skcipher_request *req, bool encrypt)
 {
-	struct n2_request_context *rctx = ablkcipher_request_ctx(req);
-	struct crypto_tfm *tfm = req->base.tfm;
+	struct n2_request_context *rctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	int err = n2_compute_chunks(req);
 	struct n2_crypto_chunk *c, *tmp;
 	unsigned long flags, hv_ret;
@@ -1017,20 +1017,20 @@ out:
 	return err;
 }
 
-static int n2_encrypt_ecb(struct ablkcipher_request *req)
+static int n2_encrypt_ecb(struct skcipher_request *req)
 {
 	return n2_do_ecb(req, true);
 }
 
-static int n2_decrypt_ecb(struct ablkcipher_request *req)
+static int n2_decrypt_ecb(struct skcipher_request *req)
 {
 	return n2_do_ecb(req, false);
 }
 
-static int n2_do_chaining(struct ablkcipher_request *req, bool encrypt)
+static int n2_do_chaining(struct skcipher_request *req, bool encrypt)
 {
-	struct n2_request_context *rctx = ablkcipher_request_ctx(req);
-	struct crypto_tfm *tfm = req->base.tfm;
+	struct n2_request_context *rctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	unsigned long flags, hv_ret, iv_paddr;
 	int err = n2_compute_chunks(req);
 	struct n2_crypto_chunk *c, *tmp;
@@ -1107,32 +1107,32 @@ out:
 	return err;
 }
 
-static int n2_encrypt_chaining(struct ablkcipher_request *req)
+static int n2_encrypt_chaining(struct skcipher_request *req)
 {
 	return n2_do_chaining(req, true);
 }
 
-static int n2_decrypt_chaining(struct ablkcipher_request *req)
+static int n2_decrypt_chaining(struct skcipher_request *req)
 {
 	return n2_do_chaining(req, false);
 }
 
-struct n2_cipher_tmpl {
+struct n2_skcipher_tmpl {
 	const char		*name;
 	const char		*drv_name;
 	u8			block_size;
 	u8			enc_type;
-	struct ablkcipher_alg	ablkcipher;
+	struct skcipher_alg	skcipher;
 };
 
-static const struct n2_cipher_tmpl cipher_tmpls[] = {
+static const struct n2_skcipher_tmpl skcipher_tmpls[] = {
 	/* ARC4: only ECB is supported (chaining bits ignored) */
 	{	.name		= "ecb(arc4)",
 		.drv_name	= "ecb-arc4",
 		.block_size	= 1,
 		.enc_type	= (ENC_TYPE_ALG_RC4_STREAM |
 				   ENC_TYPE_CHAINING_ECB),
-		.ablkcipher	= {
+		.skcipher	= {
 			.min_keysize	= 1,
 			.max_keysize	= 256,
 			.setkey		= n2_arc4_setkey,
@@ -1147,7 +1147,7 @@ static const struct n2_cipher_tmpl cipher_tmpls[] = {
 		.block_size	= DES_BLOCK_SIZE,
 		.enc_type	= (ENC_TYPE_ALG_DES |
 				   ENC_TYPE_CHAINING_ECB),
-		.ablkcipher	= {
+		.skcipher	= {
 			.min_keysize	= DES_KEY_SIZE,
 			.max_keysize	= DES_KEY_SIZE,
 			.setkey		= n2_des_setkey,
@@ -1160,7 +1160,7 @@ static const struct n2_cipher_tmpl cipher_tmpls[] = {
 		.block_size	= DES_BLOCK_SIZE,
 		.enc_type	= (ENC_TYPE_ALG_DES |
 				   ENC_TYPE_CHAINING_CBC),
-		.ablkcipher	= {
+		.skcipher	= {
 			.ivsize		= DES_BLOCK_SIZE,
 			.min_keysize	= DES_KEY_SIZE,
 			.max_keysize	= DES_KEY_SIZE,
@@ -1174,7 +1174,7 @@ static const struct n2_cipher_tmpl cipher_tmpls[] = {
 		.block_size	= DES_BLOCK_SIZE,
 		.enc_type	= (ENC_TYPE_ALG_DES |
 				   ENC_TYPE_CHAINING_CFB),
-		.ablkcipher	= {
+		.skcipher	= {
 			.min_keysize	= DES_KEY_SIZE,
 			.max_keysize	= DES_KEY_SIZE,
 			.setkey		= n2_des_setkey,
@@ -1189,7 +1189,7 @@ static const struct n2_cipher_tmpl cipher_tmpls[] = {
 		.block_size	= DES_BLOCK_SIZE,
 		.enc_type	= (ENC_TYPE_ALG_3DES |
 				   ENC_TYPE_CHAINING_ECB),
-		.ablkcipher	= {
+		.skcipher	= {
 			.min_keysize	= 3 * DES_KEY_SIZE,
 			.max_keysize	= 3 * DES_KEY_SIZE,
 			.setkey		= n2_3des_setkey,
@@ -1202,7 +1202,7 @@ static const struct n2_cipher_tmpl cipher_tmpls[] = {
 		.block_size	= DES_BLOCK_SIZE,
 		.enc_type	= (ENC_TYPE_ALG_3DES |
 				   ENC_TYPE_CHAINING_CBC),
-		.ablkcipher	= {
+		.skcipher	= {
 			.ivsize		= DES_BLOCK_SIZE,
 			.min_keysize	= 3 * DES_KEY_SIZE,
 			.max_keysize	= 3 * DES_KEY_SIZE,
@@ -1216,7 +1216,7 @@ static const struct n2_cipher_tmpl cipher_tmpls[] = {
 		.block_size	= DES_BLOCK_SIZE,
 		.enc_type	= (ENC_TYPE_ALG_3DES |
 				   ENC_TYPE_CHAINING_CFB),
-		.ablkcipher	= {
+		.skcipher	= {
 			.min_keysize	= 3 * DES_KEY_SIZE,
 			.max_keysize	= 3 * DES_KEY_SIZE,
 			.setkey		= n2_3des_setkey,
@@ -1230,7 +1230,7 @@ static const struct n2_cipher_tmpl cipher_tmpls[] = {
 		.block_size	= AES_BLOCK_SIZE,
 		.enc_type	= (ENC_TYPE_ALG_AES128 |
 				   ENC_TYPE_CHAINING_ECB),
-		.ablkcipher	= {
+		.skcipher	= {
 			.min_keysize	= AES_MIN_KEY_SIZE,
 			.max_keysize	= AES_MAX_KEY_SIZE,
 			.setkey		= n2_aes_setkey,
@@ -1243,7 +1243,7 @@ static const struct n2_cipher_tmpl cipher_tmpls[] = {
 		.block_size	= AES_BLOCK_SIZE,
 		.enc_type	= (ENC_TYPE_ALG_AES128 |
 				   ENC_TYPE_CHAINING_CBC),
-		.ablkcipher	= {
+		.skcipher	= {
 			.ivsize		= AES_BLOCK_SIZE,
 			.min_keysize	= AES_MIN_KEY_SIZE,
 			.max_keysize	= AES_MAX_KEY_SIZE,
@@ -1257,7 +1257,7 @@ static const struct n2_cipher_tmpl cipher_tmpls[] = {
 		.block_size	= AES_BLOCK_SIZE,
 		.enc_type	= (ENC_TYPE_ALG_AES128 |
 				   ENC_TYPE_CHAINING_COUNTER),
-		.ablkcipher	= {
+		.skcipher	= {
 			.ivsize		= AES_BLOCK_SIZE,
 			.min_keysize	= AES_MIN_KEY_SIZE,
 			.max_keysize	= AES_MAX_KEY_SIZE,
@@ -1268,9 +1268,9 @@ static const struct n2_cipher_tmpl cipher_tmpls[] = {
 	},
 
 };
-#define NUM_CIPHER_TMPLS ARRAY_SIZE(cipher_tmpls)
+#define NUM_CIPHER_TMPLS ARRAY_SIZE(skcipher_tmpls)
 
-static LIST_HEAD(cipher_algs);
+static LIST_HEAD(skcipher_algs);
 
 struct n2_hash_tmpl {
 	const char	*name;
@@ -1344,14 +1344,14 @@ static int algs_registered;
 
 static void __n2_unregister_algs(void)
 {
-	struct n2_cipher_alg *cipher, *cipher_tmp;
+	struct n2_skcipher_alg *skcipher, *skcipher_tmp;
 	struct n2_ahash_alg *alg, *alg_tmp;
 	struct n2_hmac_alg *hmac, *hmac_tmp;
 
-	list_for_each_entry_safe(cipher, cipher_tmp, &cipher_algs, entry) {
-		crypto_unregister_alg(&cipher->alg);
-		list_del(&cipher->entry);
-		kfree(cipher);
+	list_for_each_entry_safe(skcipher, skcipher_tmp, &skcipher_algs, entry) {
+		crypto_unregister_skcipher(&skcipher->skcipher);
+		list_del(&skcipher->entry);
+		kfree(skcipher);
 	}
 	list_for_each_entry_safe(hmac, hmac_tmp, &hmac_algs, derived.entry) {
 		crypto_unregister_ahash(&hmac->derived.alg);
@@ -1365,44 +1365,42 @@ static void __n2_unregister_algs(void)
 	}
 }
 
-static int n2_cipher_cra_init(struct crypto_tfm *tfm)
+static int n2_skcipher_init_tfm(struct crypto_skcipher *tfm)
 {
-	tfm->crt_ablkcipher.reqsize = sizeof(struct n2_request_context);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct n2_request_context));
 	return 0;
 }
 
-static int __n2_register_one_cipher(const struct n2_cipher_tmpl *tmpl)
+static int __n2_register_one_skcipher(const struct n2_skcipher_tmpl *tmpl)
 {
-	struct n2_cipher_alg *p = kzalloc(sizeof(*p), GFP_KERNEL);
-	struct crypto_alg *alg;
+	struct n2_skcipher_alg *p = kzalloc(sizeof(*p), GFP_KERNEL);
+	struct skcipher_alg *alg;
 	int err;
 
 	if (!p)
 		return -ENOMEM;
 
-	alg = &p->alg;
+	alg = &p->skcipher;
+	*alg = tmpl->skcipher;
 
-	snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s", tmpl->name);
-	snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s-n2", tmpl->drv_name);
-	alg->cra_priority = N2_CRA_PRIORITY;
-	alg->cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-			 CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC;
-	alg->cra_blocksize = tmpl->block_size;
+	snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s", tmpl->name);
+	snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s-n2", tmpl->drv_name);
+	alg->base.cra_priority = N2_CRA_PRIORITY;
+	alg->base.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC;
+	alg->base.cra_blocksize = tmpl->block_size;
 	p->enc_type = tmpl->enc_type;
-	alg->cra_ctxsize = sizeof(struct n2_cipher_context);
-	alg->cra_type = &crypto_ablkcipher_type;
-	alg->cra_u.ablkcipher = tmpl->ablkcipher;
-	alg->cra_init = n2_cipher_cra_init;
-	alg->cra_module = THIS_MODULE;
-
-	list_add(&p->entry, &cipher_algs);
-	err = crypto_register_alg(alg);
+	alg->base.cra_ctxsize = sizeof(struct n2_skcipher_context);
+	alg->base.cra_module = THIS_MODULE;
+	alg->init = n2_skcipher_init_tfm;
+
+	list_add(&p->entry, &skcipher_algs);
+	err = crypto_register_skcipher(alg);
 	if (err) {
-		pr_err("%s alg registration failed\n", alg->cra_name);
+		pr_err("%s alg registration failed\n", alg->base.cra_name);
 		list_del(&p->entry);
 		kfree(p);
 	} else {
-		pr_info("%s alg registered\n", alg->cra_name);
+		pr_info("%s alg registered\n", alg->base.cra_name);
 	}
 	return err;
 }
@@ -1517,7 +1515,7 @@ static int n2_register_algs(void)
 		}
 	}
 	for (i = 0; i < NUM_CIPHER_TMPLS; i++) {
-		err = __n2_register_one_cipher(&cipher_tmpls[i]);
+		err = __n2_register_one_skcipher(&skcipher_tmpls[i]);
 		if (err) {
 			__n2_unregister_algs();
 			goto out;
diff --git a/drivers/crypto/nx/nx-aes-cbc.c b/drivers/crypto/nx/nx-aes-cbc.c
index e631f9979127..92e921eceed7 100644
--- a/drivers/crypto/nx/nx-aes-cbc.c
+++ b/drivers/crypto/nx/nx-aes-cbc.c
@@ -18,11 +18,11 @@
 #include "nx.h"
 
 
-static int cbc_aes_nx_set_key(struct crypto_tfm *tfm,
-			      const u8          *in_key,
-			      unsigned int       key_len)
+static int cbc_aes_nx_set_key(struct crypto_skcipher *tfm,
+			      const u8               *in_key,
+			      unsigned int            key_len)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
+	struct nx_crypto_ctx *nx_ctx = crypto_skcipher_ctx(tfm);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 
 	nx_ctx_init(nx_ctx, HCOP_FC_AES);
@@ -50,13 +50,11 @@ static int cbc_aes_nx_set_key(struct crypto_tfm *tfm,
 	return 0;
 }
 
-static int cbc_aes_nx_crypt(struct blkcipher_desc *desc,
-			    struct scatterlist    *dst,
-			    struct scatterlist    *src,
-			    unsigned int           nbytes,
-			    int                    enc)
+static int cbc_aes_nx_crypt(struct skcipher_request *req,
+			    int                      enc)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct nx_crypto_ctx *nx_ctx = crypto_skcipher_ctx(tfm);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	unsigned long irq_flags;
 	unsigned int processed = 0, to_process;
@@ -70,10 +68,11 @@ static int cbc_aes_nx_crypt(struct blkcipher_desc *desc,
 		NX_CPB_FDM(csbcpb) &= ~NX_FDM_ENDE_ENCRYPT;
 
 	do {
-		to_process = nbytes - processed;
+		to_process = req->cryptlen - processed;
 
-		rc = nx_build_sg_lists(nx_ctx, desc, dst, src, &to_process,
-				       processed, csbcpb->cpb.aes_cbc.iv);
+		rc = nx_build_sg_lists(nx_ctx, req->iv, req->dst, req->src,
+				       &to_process, processed,
+				       csbcpb->cpb.aes_cbc.iv);
 		if (rc)
 			goto out;
 
@@ -83,56 +82,46 @@ static int cbc_aes_nx_crypt(struct blkcipher_desc *desc,
 		}
 
 		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-				   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+				   req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP);
 		if (rc)
 			goto out;
 
-		memcpy(desc->info, csbcpb->cpb.aes_cbc.cv, AES_BLOCK_SIZE);
+		memcpy(req->iv, csbcpb->cpb.aes_cbc.cv, AES_BLOCK_SIZE);
 		atomic_inc(&(nx_ctx->stats->aes_ops));
 		atomic64_add(csbcpb->csb.processed_byte_count,
 			     &(nx_ctx->stats->aes_bytes));
 
 		processed += to_process;
-	} while (processed < nbytes);
+	} while (processed < req->cryptlen);
 out:
 	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return rc;
 }
 
-static int cbc_aes_nx_encrypt(struct blkcipher_desc *desc,
-			      struct scatterlist    *dst,
-			      struct scatterlist    *src,
-			      unsigned int           nbytes)
+static int cbc_aes_nx_encrypt(struct skcipher_request *req)
 {
-	return cbc_aes_nx_crypt(desc, dst, src, nbytes, 1);
+	return cbc_aes_nx_crypt(req, 1);
 }
 
-static int cbc_aes_nx_decrypt(struct blkcipher_desc *desc,
-			      struct scatterlist    *dst,
-			      struct scatterlist    *src,
-			      unsigned int           nbytes)
+static int cbc_aes_nx_decrypt(struct skcipher_request *req)
 {
-	return cbc_aes_nx_crypt(desc, dst, src, nbytes, 0);
+	return cbc_aes_nx_crypt(req, 0);
 }
 
-struct crypto_alg nx_cbc_aes_alg = {
-	.cra_name        = "cbc(aes)",
-	.cra_driver_name = "cbc-aes-nx",
-	.cra_priority    = 300,
-	.cra_flags       = CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize   = AES_BLOCK_SIZE,
-	.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-	.cra_type        = &crypto_blkcipher_type,
-	.cra_alignmask   = 0xf,
-	.cra_module      = THIS_MODULE,
-	.cra_init        = nx_crypto_ctx_aes_cbc_init,
-	.cra_exit        = nx_crypto_ctx_exit,
-	.cra_blkcipher = {
-		.min_keysize = AES_MIN_KEY_SIZE,
-		.max_keysize = AES_MAX_KEY_SIZE,
-		.ivsize      = AES_BLOCK_SIZE,
-		.setkey      = cbc_aes_nx_set_key,
-		.encrypt     = cbc_aes_nx_encrypt,
-		.decrypt     = cbc_aes_nx_decrypt,
-	}
+struct skcipher_alg nx_cbc_aes_alg = {
+	.base.cra_name		= "cbc(aes)",
+	.base.cra_driver_name	= "cbc-aes-nx",
+	.base.cra_priority	= 300,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct nx_crypto_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+	.init			= nx_crypto_ctx_aes_cbc_init,
+	.exit			= nx_crypto_ctx_skcipher_exit,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= cbc_aes_nx_set_key,
+	.encrypt		= cbc_aes_nx_encrypt,
+	.decrypt		= cbc_aes_nx_decrypt,
 };
diff --git a/drivers/crypto/nx/nx-aes-ccm.c b/drivers/crypto/nx/nx-aes-ccm.c
index 5be8f01c5da8..4c9362eebefd 100644
--- a/drivers/crypto/nx/nx-aes-ccm.c
+++ b/drivers/crypto/nx/nx-aes-ccm.c
@@ -327,7 +327,7 @@ static int generate_pat(u8                   *iv,
 }
 
 static int ccm_nx_decrypt(struct aead_request   *req,
-			  struct blkcipher_desc *desc,
+			  u8                    *iv,
 			  unsigned int assoclen)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
@@ -348,7 +348,7 @@ static int ccm_nx_decrypt(struct aead_request   *req,
 				 req->src, nbytes + req->assoclen, authsize,
 				 SCATTERWALK_FROM_SG);
 
-	rc = generate_pat(desc->info, req, nx_ctx, authsize, nbytes, assoclen,
+	rc = generate_pat(iv, req, nx_ctx, authsize, nbytes, assoclen,
 			  csbcpb->cpb.aes_ccm.in_pat_or_b0);
 	if (rc)
 		goto out;
@@ -367,7 +367,7 @@ static int ccm_nx_decrypt(struct aead_request   *req,
 
 		NX_CPB_FDM(nx_ctx->csbcpb) &= ~NX_FDM_ENDE_ENCRYPT;
 
-		rc = nx_build_sg_lists(nx_ctx, desc, req->dst, req->src,
+		rc = nx_build_sg_lists(nx_ctx, iv, req->dst, req->src,
 				       &to_process, processed + req->assoclen,
 				       csbcpb->cpb.aes_ccm.iv_or_ctr);
 		if (rc)
@@ -381,7 +381,7 @@ static int ccm_nx_decrypt(struct aead_request   *req,
 		/* for partial completion, copy following for next
 		 * entry into loop...
 		 */
-		memcpy(desc->info, csbcpb->cpb.aes_ccm.out_ctr, AES_BLOCK_SIZE);
+		memcpy(iv, csbcpb->cpb.aes_ccm.out_ctr, AES_BLOCK_SIZE);
 		memcpy(csbcpb->cpb.aes_ccm.in_pat_or_b0,
 			csbcpb->cpb.aes_ccm.out_pat_or_mac, AES_BLOCK_SIZE);
 		memcpy(csbcpb->cpb.aes_ccm.in_s0,
@@ -405,7 +405,7 @@ out:
 }
 
 static int ccm_nx_encrypt(struct aead_request   *req,
-			  struct blkcipher_desc *desc,
+			  u8                    *iv,
 			  unsigned int assoclen)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
@@ -418,7 +418,7 @@ static int ccm_nx_encrypt(struct aead_request   *req,
 
 	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
-	rc = generate_pat(desc->info, req, nx_ctx, authsize, nbytes, assoclen,
+	rc = generate_pat(iv, req, nx_ctx, authsize, nbytes, assoclen,
 			  csbcpb->cpb.aes_ccm.in_pat_or_b0);
 	if (rc)
 		goto out;
@@ -436,7 +436,7 @@ static int ccm_nx_encrypt(struct aead_request   *req,
 
 		NX_CPB_FDM(csbcpb) |= NX_FDM_ENDE_ENCRYPT;
 
-		rc = nx_build_sg_lists(nx_ctx, desc, req->dst, req->src,
+		rc = nx_build_sg_lists(nx_ctx, iv, req->dst, req->src,
 				       &to_process, processed + req->assoclen,
 				       csbcpb->cpb.aes_ccm.iv_or_ctr);
 		if (rc)
@@ -450,7 +450,7 @@ static int ccm_nx_encrypt(struct aead_request   *req,
 		/* for partial completion, copy following for next
 		 * entry into loop...
 		 */
-		memcpy(desc->info, csbcpb->cpb.aes_ccm.out_ctr, AES_BLOCK_SIZE);
+		memcpy(iv, csbcpb->cpb.aes_ccm.out_ctr, AES_BLOCK_SIZE);
 		memcpy(csbcpb->cpb.aes_ccm.in_pat_or_b0,
 			csbcpb->cpb.aes_ccm.out_pat_or_mac, AES_BLOCK_SIZE);
 		memcpy(csbcpb->cpb.aes_ccm.in_s0,
@@ -481,67 +481,50 @@ static int ccm4309_aes_nx_encrypt(struct aead_request *req)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
 	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
-	struct blkcipher_desc desc;
 	u8 *iv = rctx->iv;
 
 	iv[0] = 3;
 	memcpy(iv + 1, nx_ctx->priv.ccm.nonce, 3);
 	memcpy(iv + 4, req->iv, 8);
 
-	desc.info = iv;
-
-	return ccm_nx_encrypt(req, &desc, req->assoclen - 8);
+	return ccm_nx_encrypt(req, iv, req->assoclen - 8);
 }
 
 static int ccm_aes_nx_encrypt(struct aead_request *req)
 {
-	struct blkcipher_desc desc;
 	int rc;
 
-	desc.info = req->iv;
-
-	rc = crypto_ccm_check_iv(desc.info);
+	rc = crypto_ccm_check_iv(req->iv);
 	if (rc)
 		return rc;
 
-	return ccm_nx_encrypt(req, &desc, req->assoclen);
+	return ccm_nx_encrypt(req, req->iv, req->assoclen);
 }
 
 static int ccm4309_aes_nx_decrypt(struct aead_request *req)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
 	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
-	struct blkcipher_desc desc;
 	u8 *iv = rctx->iv;
 
 	iv[0] = 3;
 	memcpy(iv + 1, nx_ctx->priv.ccm.nonce, 3);
 	memcpy(iv + 4, req->iv, 8);
 
-	desc.info = iv;
-
-	return ccm_nx_decrypt(req, &desc, req->assoclen - 8);
+	return ccm_nx_decrypt(req, iv, req->assoclen - 8);
 }
 
 static int ccm_aes_nx_decrypt(struct aead_request *req)
 {
-	struct blkcipher_desc desc;
 	int rc;
 
-	desc.info = req->iv;
-
-	rc = crypto_ccm_check_iv(desc.info);
+	rc = crypto_ccm_check_iv(req->iv);
 	if (rc)
 		return rc;
 
-	return ccm_nx_decrypt(req, &desc, req->assoclen);
+	return ccm_nx_decrypt(req, req->iv, req->assoclen);
 }
 
-/* tell the block cipher walk routines that this is a stream cipher by
- * setting cra_blocksize to 1. Even using blkcipher_walk_virt_block
- * during encrypt/decrypt doesn't solve this problem, because it calls
- * blkcipher_walk_done under the covers, which doesn't use walk->blocksize,
- * but instead uses this tfm->blocksize. */
 struct aead_alg nx_ccm_aes_alg = {
 	.base = {
 		.cra_name        = "ccm(aes)",
diff --git a/drivers/crypto/nx/nx-aes-ctr.c b/drivers/crypto/nx/nx-aes-ctr.c
index 191e226a11a1..6d5ce1a66f1e 100644
--- a/drivers/crypto/nx/nx-aes-ctr.c
+++ b/drivers/crypto/nx/nx-aes-ctr.c
@@ -19,11 +19,11 @@
 #include "nx.h"
 
 
-static int ctr_aes_nx_set_key(struct crypto_tfm *tfm,
-			      const u8          *in_key,
-			      unsigned int       key_len)
+static int ctr_aes_nx_set_key(struct crypto_skcipher *tfm,
+			      const u8               *in_key,
+			      unsigned int            key_len)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
+	struct nx_crypto_ctx *nx_ctx = crypto_skcipher_ctx(tfm);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 
 	nx_ctx_init(nx_ctx, HCOP_FC_AES);
@@ -51,11 +51,11 @@ static int ctr_aes_nx_set_key(struct crypto_tfm *tfm,
 	return 0;
 }
 
-static int ctr3686_aes_nx_set_key(struct crypto_tfm *tfm,
-				  const u8          *in_key,
-				  unsigned int       key_len)
+static int ctr3686_aes_nx_set_key(struct crypto_skcipher *tfm,
+				  const u8               *in_key,
+				  unsigned int            key_len)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
+	struct nx_crypto_ctx *nx_ctx = crypto_skcipher_ctx(tfm);
 
 	if (key_len < CTR_RFC3686_NONCE_SIZE)
 		return -EINVAL;
@@ -69,12 +69,10 @@ static int ctr3686_aes_nx_set_key(struct crypto_tfm *tfm,
 	return ctr_aes_nx_set_key(tfm, in_key, key_len);
 }
 
-static int ctr_aes_nx_crypt(struct blkcipher_desc *desc,
-			    struct scatterlist    *dst,
-			    struct scatterlist    *src,
-			    unsigned int           nbytes)
+static int ctr_aes_nx_crypt(struct skcipher_request *req, u8 *iv)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct nx_crypto_ctx *nx_ctx = crypto_skcipher_ctx(tfm);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	unsigned long irq_flags;
 	unsigned int processed = 0, to_process;
@@ -83,10 +81,11 @@ static int ctr_aes_nx_crypt(struct blkcipher_desc *desc,
 	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
 	do {
-		to_process = nbytes - processed;
+		to_process = req->cryptlen - processed;
 
-		rc = nx_build_sg_lists(nx_ctx, desc, dst, src, &to_process,
-				       processed, csbcpb->cpb.aes_ctr.iv);
+		rc = nx_build_sg_lists(nx_ctx, iv, req->dst, req->src,
+				       &to_process, processed,
+				       csbcpb->cpb.aes_ctr.iv);
 		if (rc)
 			goto out;
 
@@ -96,59 +95,51 @@ static int ctr_aes_nx_crypt(struct blkcipher_desc *desc,
 		}
 
 		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-				   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+				   req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP);
 		if (rc)
 			goto out;
 
-		memcpy(desc->info, csbcpb->cpb.aes_cbc.cv, AES_BLOCK_SIZE);
+		memcpy(iv, csbcpb->cpb.aes_cbc.cv, AES_BLOCK_SIZE);
 
 		atomic_inc(&(nx_ctx->stats->aes_ops));
 		atomic64_add(csbcpb->csb.processed_byte_count,
 			     &(nx_ctx->stats->aes_bytes));
 
 		processed += to_process;
-	} while (processed < nbytes);
+	} while (processed < req->cryptlen);
 out:
 	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return rc;
 }
 
-static int ctr3686_aes_nx_crypt(struct blkcipher_desc *desc,
-				struct scatterlist    *dst,
-				struct scatterlist    *src,
-				unsigned int           nbytes)
+static int ctr3686_aes_nx_crypt(struct skcipher_request *req)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct nx_crypto_ctx *nx_ctx = crypto_skcipher_ctx(tfm);
 	u8 iv[16];
 
 	memcpy(iv, nx_ctx->priv.ctr.nonce, CTR_RFC3686_IV_SIZE);
-	memcpy(iv + CTR_RFC3686_NONCE_SIZE,
-	       desc->info, CTR_RFC3686_IV_SIZE);
+	memcpy(iv + CTR_RFC3686_NONCE_SIZE, req->iv, CTR_RFC3686_IV_SIZE);
 	iv[12] = iv[13] = iv[14] = 0;
 	iv[15] = 1;
 
-	desc->info = iv;
-
-	return ctr_aes_nx_crypt(desc, dst, src, nbytes);
+	return ctr_aes_nx_crypt(req, iv);
 }
 
-struct crypto_alg nx_ctr3686_aes_alg = {
-	.cra_name        = "rfc3686(ctr(aes))",
-	.cra_driver_name = "rfc3686-ctr-aes-nx",
-	.cra_priority    = 300,
-	.cra_flags       = CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize   = 1,
-	.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-	.cra_type        = &crypto_blkcipher_type,
-	.cra_module      = THIS_MODULE,
-	.cra_init        = nx_crypto_ctx_aes_ctr_init,
-	.cra_exit        = nx_crypto_ctx_exit,
-	.cra_blkcipher = {
-		.min_keysize = AES_MIN_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
-		.max_keysize = AES_MAX_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
-		.ivsize      = CTR_RFC3686_IV_SIZE,
-		.setkey      = ctr3686_aes_nx_set_key,
-		.encrypt     = ctr3686_aes_nx_crypt,
-		.decrypt     = ctr3686_aes_nx_crypt,
-	}
+struct skcipher_alg nx_ctr3686_aes_alg = {
+	.base.cra_name		= "rfc3686(ctr(aes))",
+	.base.cra_driver_name	= "rfc3686-ctr-aes-nx",
+	.base.cra_priority	= 300,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct nx_crypto_ctx),
+	.base.cra_module	= THIS_MODULE,
+	.init			= nx_crypto_ctx_aes_ctr_init,
+	.exit			= nx_crypto_ctx_skcipher_exit,
+	.min_keysize		= AES_MIN_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
+	.ivsize			= CTR_RFC3686_IV_SIZE,
+	.setkey			= ctr3686_aes_nx_set_key,
+	.encrypt		= ctr3686_aes_nx_crypt,
+	.decrypt		= ctr3686_aes_nx_crypt,
+	.chunksize		= AES_BLOCK_SIZE,
 };
diff --git a/drivers/crypto/nx/nx-aes-ecb.c b/drivers/crypto/nx/nx-aes-ecb.c
index c67570470c9d..77e338dc33f1 100644
--- a/drivers/crypto/nx/nx-aes-ecb.c
+++ b/drivers/crypto/nx/nx-aes-ecb.c
@@ -18,11 +18,11 @@
 #include "nx.h"
 
 
-static int ecb_aes_nx_set_key(struct crypto_tfm *tfm,
-			      const u8          *in_key,
-			      unsigned int       key_len)
+static int ecb_aes_nx_set_key(struct crypto_skcipher *tfm,
+			      const u8               *in_key,
+			      unsigned int            key_len)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
+	struct nx_crypto_ctx *nx_ctx = crypto_skcipher_ctx(tfm);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
 
 	nx_ctx_init(nx_ctx, HCOP_FC_AES);
@@ -50,13 +50,11 @@ static int ecb_aes_nx_set_key(struct crypto_tfm *tfm,
 	return 0;
 }
 
-static int ecb_aes_nx_crypt(struct blkcipher_desc *desc,
-			    struct scatterlist    *dst,
-			    struct scatterlist    *src,
-			    unsigned int           nbytes,
-			    int                    enc)
+static int ecb_aes_nx_crypt(struct skcipher_request *req,
+			    int                      enc)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct nx_crypto_ctx *nx_ctx = crypto_skcipher_ctx(tfm);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	unsigned long irq_flags;
 	unsigned int processed = 0, to_process;
@@ -70,10 +68,10 @@ static int ecb_aes_nx_crypt(struct blkcipher_desc *desc,
 		NX_CPB_FDM(csbcpb) &= ~NX_FDM_ENDE_ENCRYPT;
 
 	do {
-		to_process = nbytes - processed;
+		to_process = req->cryptlen - processed;
 
-		rc = nx_build_sg_lists(nx_ctx, desc, dst, src, &to_process,
-				processed, NULL);
+		rc = nx_build_sg_lists(nx_ctx, NULL, req->dst, req->src,
+				       &to_process, processed, NULL);
 		if (rc)
 			goto out;
 
@@ -83,7 +81,7 @@ static int ecb_aes_nx_crypt(struct blkcipher_desc *desc,
 		}
 
 		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-				   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+				   req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP);
 		if (rc)
 			goto out;
 
@@ -92,46 +90,36 @@ static int ecb_aes_nx_crypt(struct blkcipher_desc *desc,
 			     &(nx_ctx->stats->aes_bytes));
 
 		processed += to_process;
-	} while (processed < nbytes);
+	} while (processed < req->cryptlen);
 
 out:
 	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return rc;
 }
 
-static int ecb_aes_nx_encrypt(struct blkcipher_desc *desc,
-			      struct scatterlist    *dst,
-			      struct scatterlist    *src,
-			      unsigned int           nbytes)
+static int ecb_aes_nx_encrypt(struct skcipher_request *req)
 {
-	return ecb_aes_nx_crypt(desc, dst, src, nbytes, 1);
+	return ecb_aes_nx_crypt(req, 1);
 }
 
-static int ecb_aes_nx_decrypt(struct blkcipher_desc *desc,
-			      struct scatterlist    *dst,
-			      struct scatterlist    *src,
-			      unsigned int           nbytes)
+static int ecb_aes_nx_decrypt(struct skcipher_request *req)
 {
-	return ecb_aes_nx_crypt(desc, dst, src, nbytes, 0);
+	return ecb_aes_nx_crypt(req, 0);
 }
 
-struct crypto_alg nx_ecb_aes_alg = {
-	.cra_name        = "ecb(aes)",
-	.cra_driver_name = "ecb-aes-nx",
-	.cra_priority    = 300,
-	.cra_flags       = CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize   = AES_BLOCK_SIZE,
-	.cra_alignmask   = 0xf,
-	.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-	.cra_type        = &crypto_blkcipher_type,
-	.cra_module      = THIS_MODULE,
-	.cra_init        = nx_crypto_ctx_aes_ecb_init,
-	.cra_exit        = nx_crypto_ctx_exit,
-	.cra_blkcipher = {
-		.min_keysize = AES_MIN_KEY_SIZE,
-		.max_keysize = AES_MAX_KEY_SIZE,
-		.setkey      = ecb_aes_nx_set_key,
-		.encrypt     = ecb_aes_nx_encrypt,
-		.decrypt     = ecb_aes_nx_decrypt,
-	}
+struct skcipher_alg nx_ecb_aes_alg = {
+	.base.cra_name		= "ecb(aes)",
+	.base.cra_driver_name	= "ecb-aes-nx",
+	.base.cra_priority	= 300,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_alignmask	= 0xf,
+	.base.cra_ctxsize	= sizeof(struct nx_crypto_ctx),
+	.base.cra_module	= THIS_MODULE,
+	.init			= nx_crypto_ctx_aes_ecb_init,
+	.exit			= nx_crypto_ctx_skcipher_exit,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= ecb_aes_nx_set_key,
+	.encrypt		= ecb_aes_nx_encrypt,
+	.decrypt		= ecb_aes_nx_decrypt,
 };
diff --git a/drivers/crypto/nx/nx-aes-gcm.c b/drivers/crypto/nx/nx-aes-gcm.c
index 7d3d67871270..19c6ed5baea4 100644
--- a/drivers/crypto/nx/nx-aes-gcm.c
+++ b/drivers/crypto/nx/nx-aes-gcm.c
@@ -166,8 +166,7 @@ static int nx_gca(struct nx_crypto_ctx  *nx_ctx,
 	return rc;
 }
 
-static int gmac(struct aead_request *req, struct blkcipher_desc *desc,
-		unsigned int assoclen)
+static int gmac(struct aead_request *req, const u8 *iv, unsigned int assoclen)
 {
 	int rc;
 	struct nx_crypto_ctx *nx_ctx =
@@ -190,7 +189,7 @@ static int gmac(struct aead_request *req, struct blkcipher_desc *desc,
 			   nx_ctx->ap->databytelen/NX_PAGE_SIZE);
 
 	/* Copy IV */
-	memcpy(csbcpb->cpb.aes_gcm.iv_or_cnt, desc->info, AES_BLOCK_SIZE);
+	memcpy(csbcpb->cpb.aes_gcm.iv_or_cnt, iv, AES_BLOCK_SIZE);
 
 	do {
 		/*
@@ -240,8 +239,7 @@ out:
 	return rc;
 }
 
-static int gcm_empty(struct aead_request *req, struct blkcipher_desc *desc,
-		     int enc)
+static int gcm_empty(struct aead_request *req, const u8 *iv, int enc)
 {
 	int rc;
 	struct nx_crypto_ctx *nx_ctx =
@@ -268,7 +266,7 @@ static int gcm_empty(struct aead_request *req, struct blkcipher_desc *desc,
 	len = AES_BLOCK_SIZE;
 
 	/* Encrypt the counter/IV */
-	in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *) desc->info,
+	in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *) iv,
 				 &len, nx_ctx->ap->sglen);
 
 	if (len != AES_BLOCK_SIZE)
@@ -285,7 +283,7 @@ static int gcm_empty(struct aead_request *req, struct blkcipher_desc *desc,
 	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
 
 	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+			   req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP);
 	if (rc)
 		goto out;
 	atomic_inc(&(nx_ctx->stats->aes_ops));
@@ -313,7 +311,6 @@ static int gcm_aes_nx_crypt(struct aead_request *req, int enc,
 		crypto_aead_ctx(crypto_aead_reqtfm(req));
 	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
-	struct blkcipher_desc desc;
 	unsigned int nbytes = req->cryptlen;
 	unsigned int processed = 0, to_process;
 	unsigned long irq_flags;
@@ -321,15 +318,14 @@ static int gcm_aes_nx_crypt(struct aead_request *req, int enc,
 
 	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
-	desc.info = rctx->iv;
 	/* initialize the counter */
-	*(u32 *)(desc.info + NX_GCM_CTR_OFFSET) = 1;
+	*(u32 *)&rctx->iv[NX_GCM_CTR_OFFSET] = 1;
 
 	if (nbytes == 0) {
 		if (assoclen == 0)
-			rc = gcm_empty(req, &desc, enc);
+			rc = gcm_empty(req, rctx->iv, enc);
 		else
-			rc = gmac(req, &desc, assoclen);
+			rc = gmac(req, rctx->iv, assoclen);
 		if (rc)
 			goto out;
 		else
@@ -358,7 +354,7 @@ static int gcm_aes_nx_crypt(struct aead_request *req, int enc,
 		to_process = nbytes - processed;
 
 		csbcpb->cpb.aes_gcm.bit_length_data = nbytes * 8;
-		rc = nx_build_sg_lists(nx_ctx, &desc, req->dst,
+		rc = nx_build_sg_lists(nx_ctx, rctx->iv, req->dst,
 				       req->src, &to_process,
 				       processed + req->assoclen,
 				       csbcpb->cpb.aes_gcm.iv_or_cnt);
@@ -377,7 +373,7 @@ static int gcm_aes_nx_crypt(struct aead_request *req, int enc,
 		if (rc)
 			goto out;
 
-		memcpy(desc.info, csbcpb->cpb.aes_gcm.out_cnt, AES_BLOCK_SIZE);
+		memcpy(rctx->iv, csbcpb->cpb.aes_gcm.out_cnt, AES_BLOCK_SIZE);
 		memcpy(csbcpb->cpb.aes_gcm.in_pat_or_aad,
 			csbcpb->cpb.aes_gcm.out_pat_or_mac, AES_BLOCK_SIZE);
 		memcpy(csbcpb->cpb.aes_gcm.in_s0,
@@ -471,11 +467,6 @@ static int gcm4106_aes_nx_decrypt(struct aead_request *req)
 	return gcm_aes_nx_crypt(req, 0, req->assoclen - 8);
 }
 
-/* tell the block cipher walk routines that this is a stream cipher by
- * setting cra_blocksize to 1. Even using blkcipher_walk_virt_block
- * during encrypt/decrypt doesn't solve this problem, because it calls
- * blkcipher_walk_done under the covers, which doesn't use walk->blocksize,
- * but instead uses this tfm->blocksize. */
 struct aead_alg nx_gcm_aes_alg = {
 	.base = {
 		.cra_name        = "gcm(aes)",
diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c
index 28817880c76d..f03c238f5a31 100644
--- a/drivers/crypto/nx/nx.c
+++ b/drivers/crypto/nx/nx.c
@@ -243,25 +243,25 @@ static long int trim_sg_list(struct nx_sg *sg,
  *                     scatterlists based on them.
  *
  * @nx_ctx: NX crypto context for the lists we're building
- * @desc: the block cipher descriptor for the operation
+ * @iv: iv data, if the algorithm requires it
  * @dst: destination scatterlist
  * @src: source scatterlist
  * @nbytes: length of data described in the scatterlists
  * @offset: number of bytes to fast-forward past at the beginning of
  *          scatterlists.
- * @iv: destination for the iv data, if the algorithm requires it
+ * @oiv: destination for the iv data, if the algorithm requires it
  *
- * This is common code shared by all the AES algorithms. It uses the block
- * cipher walk routines to traverse input and output scatterlists, building
+ * This is common code shared by all the AES algorithms. It uses the crypto
+ * scatterlist walk routines to traverse input and output scatterlists, building
  * corresponding NX scatterlists
  */
 int nx_build_sg_lists(struct nx_crypto_ctx  *nx_ctx,
-		      struct blkcipher_desc *desc,
+		      const u8              *iv,
 		      struct scatterlist    *dst,
 		      struct scatterlist    *src,
 		      unsigned int          *nbytes,
 		      unsigned int           offset,
-		      u8                    *iv)
+		      u8                    *oiv)
 {
 	unsigned int delta = 0;
 	unsigned int total = *nbytes;
@@ -274,8 +274,8 @@ int nx_build_sg_lists(struct nx_crypto_ctx  *nx_ctx,
 	max_sg_len = min_t(u64, max_sg_len,
 			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
 
-	if (iv)
-		memcpy(iv, desc->info, AES_BLOCK_SIZE);
+	if (oiv)
+		memcpy(oiv, iv, AES_BLOCK_SIZE);
 
 	*nbytes = min_t(u64, *nbytes, nx_ctx->ap->databytelen);
 
@@ -511,10 +511,10 @@ static bool nx_check_props(struct device *dev, u32 fc, u32 mode)
 	return true;
 }
 
-static int nx_register_alg(struct crypto_alg *alg, u32 fc, u32 mode)
+static int nx_register_skcipher(struct skcipher_alg *alg, u32 fc, u32 mode)
 {
 	return nx_check_props(&nx_driver.viodev->dev, fc, mode) ?
-	       crypto_register_alg(alg) : 0;
+	       crypto_register_skcipher(alg) : 0;
 }
 
 static int nx_register_aead(struct aead_alg *alg, u32 fc, u32 mode)
@@ -531,10 +531,10 @@ static int nx_register_shash(struct shash_alg *alg, u32 fc, u32 mode, int slot)
 	       crypto_register_shash(alg) : 0;
 }
 
-static void nx_unregister_alg(struct crypto_alg *alg, u32 fc, u32 mode)
+static void nx_unregister_skcipher(struct skcipher_alg *alg, u32 fc, u32 mode)
 {
 	if (nx_check_props(NULL, fc, mode))
-		crypto_unregister_alg(alg);
+		crypto_unregister_skcipher(alg);
 }
 
 static void nx_unregister_aead(struct aead_alg *alg, u32 fc, u32 mode)
@@ -573,15 +573,16 @@ static int nx_register_algs(void)
 
 	nx_driver.of.status = NX_OKAY;
 
-	rc = nx_register_alg(&nx_ecb_aes_alg, NX_FC_AES, NX_MODE_AES_ECB);
+	rc = nx_register_skcipher(&nx_ecb_aes_alg, NX_FC_AES, NX_MODE_AES_ECB);
 	if (rc)
 		goto out;
 
-	rc = nx_register_alg(&nx_cbc_aes_alg, NX_FC_AES, NX_MODE_AES_CBC);
+	rc = nx_register_skcipher(&nx_cbc_aes_alg, NX_FC_AES, NX_MODE_AES_CBC);
 	if (rc)
 		goto out_unreg_ecb;
 
-	rc = nx_register_alg(&nx_ctr3686_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
+	rc = nx_register_skcipher(&nx_ctr3686_aes_alg, NX_FC_AES,
+				  NX_MODE_AES_CTR);
 	if (rc)
 		goto out_unreg_cbc;
 
@@ -633,11 +634,11 @@ out_unreg_gcm4106:
 out_unreg_gcm:
 	nx_unregister_aead(&nx_gcm_aes_alg, NX_FC_AES, NX_MODE_AES_GCM);
 out_unreg_ctr3686:
-	nx_unregister_alg(&nx_ctr3686_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
+	nx_unregister_skcipher(&nx_ctr3686_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
 out_unreg_cbc:
-	nx_unregister_alg(&nx_cbc_aes_alg, NX_FC_AES, NX_MODE_AES_CBC);
+	nx_unregister_skcipher(&nx_cbc_aes_alg, NX_FC_AES, NX_MODE_AES_CBC);
 out_unreg_ecb:
-	nx_unregister_alg(&nx_ecb_aes_alg, NX_FC_AES, NX_MODE_AES_ECB);
+	nx_unregister_skcipher(&nx_ecb_aes_alg, NX_FC_AES, NX_MODE_AES_ECB);
 out:
 	return rc;
 }
@@ -704,21 +705,21 @@ int nx_crypto_ctx_aes_gcm_init(struct crypto_aead *tfm)
 				  NX_MODE_AES_GCM);
 }
 
-int nx_crypto_ctx_aes_ctr_init(struct crypto_tfm *tfm)
+int nx_crypto_ctx_aes_ctr_init(struct crypto_skcipher *tfm)
 {
-	return nx_crypto_ctx_init(crypto_tfm_ctx(tfm), NX_FC_AES,
+	return nx_crypto_ctx_init(crypto_skcipher_ctx(tfm), NX_FC_AES,
 				  NX_MODE_AES_CTR);
 }
 
-int nx_crypto_ctx_aes_cbc_init(struct crypto_tfm *tfm)
+int nx_crypto_ctx_aes_cbc_init(struct crypto_skcipher *tfm)
 {
-	return nx_crypto_ctx_init(crypto_tfm_ctx(tfm), NX_FC_AES,
+	return nx_crypto_ctx_init(crypto_skcipher_ctx(tfm), NX_FC_AES,
 				  NX_MODE_AES_CBC);
 }
 
-int nx_crypto_ctx_aes_ecb_init(struct crypto_tfm *tfm)
+int nx_crypto_ctx_aes_ecb_init(struct crypto_skcipher *tfm)
 {
-	return nx_crypto_ctx_init(crypto_tfm_ctx(tfm), NX_FC_AES,
+	return nx_crypto_ctx_init(crypto_skcipher_ctx(tfm), NX_FC_AES,
 				  NX_MODE_AES_ECB);
 }
 
@@ -752,6 +753,11 @@ void nx_crypto_ctx_exit(struct crypto_tfm *tfm)
 	nx_ctx->out_sg = NULL;
 }
 
+void nx_crypto_ctx_skcipher_exit(struct crypto_skcipher *tfm)
+{
+	nx_crypto_ctx_exit(crypto_skcipher_ctx(tfm));
+}
+
 void nx_crypto_ctx_aead_exit(struct crypto_aead *tfm)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_aead_ctx(tfm);
@@ -798,10 +804,12 @@ static int nx_remove(struct vio_dev *viodev)
 				   NX_FC_AES, NX_MODE_AES_GCM);
 		nx_unregister_aead(&nx_gcm_aes_alg,
 				   NX_FC_AES, NX_MODE_AES_GCM);
-		nx_unregister_alg(&nx_ctr3686_aes_alg,
-				  NX_FC_AES, NX_MODE_AES_CTR);
-		nx_unregister_alg(&nx_cbc_aes_alg, NX_FC_AES, NX_MODE_AES_CBC);
-		nx_unregister_alg(&nx_ecb_aes_alg, NX_FC_AES, NX_MODE_AES_ECB);
+		nx_unregister_skcipher(&nx_ctr3686_aes_alg,
+				       NX_FC_AES, NX_MODE_AES_CTR);
+		nx_unregister_skcipher(&nx_cbc_aes_alg, NX_FC_AES,
+				       NX_MODE_AES_CBC);
+		nx_unregister_skcipher(&nx_ecb_aes_alg, NX_FC_AES,
+				       NX_MODE_AES_ECB);
 	}
 
 	return 0;
diff --git a/drivers/crypto/nx/nx.h b/drivers/crypto/nx/nx.h
index 7ecca168f8c4..91c54289124a 100644
--- a/drivers/crypto/nx/nx.h
+++ b/drivers/crypto/nx/nx.h
@@ -145,19 +145,20 @@ struct crypto_aead;
 int nx_crypto_ctx_aes_ccm_init(struct crypto_aead *tfm);
 int nx_crypto_ctx_aes_gcm_init(struct crypto_aead *tfm);
 int nx_crypto_ctx_aes_xcbc_init(struct crypto_tfm *tfm);
-int nx_crypto_ctx_aes_ctr_init(struct crypto_tfm *tfm);
-int nx_crypto_ctx_aes_cbc_init(struct crypto_tfm *tfm);
-int nx_crypto_ctx_aes_ecb_init(struct crypto_tfm *tfm);
+int nx_crypto_ctx_aes_ctr_init(struct crypto_skcipher *tfm);
+int nx_crypto_ctx_aes_cbc_init(struct crypto_skcipher *tfm);
+int nx_crypto_ctx_aes_ecb_init(struct crypto_skcipher *tfm);
 int nx_crypto_ctx_sha_init(struct crypto_tfm *tfm);
 void nx_crypto_ctx_exit(struct crypto_tfm *tfm);
+void nx_crypto_ctx_skcipher_exit(struct crypto_skcipher *tfm);
 void nx_crypto_ctx_aead_exit(struct crypto_aead *tfm);
 void nx_ctx_init(struct nx_crypto_ctx *nx_ctx, unsigned int function);
 int nx_hcall_sync(struct nx_crypto_ctx *ctx, struct vio_pfo_op *op,
 		  u32 may_sleep);
 struct nx_sg *nx_build_sg_list(struct nx_sg *, u8 *, unsigned int *, u32);
-int nx_build_sg_lists(struct nx_crypto_ctx *, struct blkcipher_desc *,
-		      struct scatterlist *, struct scatterlist *, unsigned int *,
-		      unsigned int, u8 *);
+int nx_build_sg_lists(struct nx_crypto_ctx *nx_ctx, const u8 *iv,
+		      struct scatterlist *dst, struct scatterlist *src,
+		      unsigned int *nbytes, unsigned int offset, u8 *oiv);
 struct nx_sg *nx_walk_and_build(struct nx_sg *, unsigned int,
 				struct scatterlist *, unsigned int,
 				unsigned int *);
@@ -175,11 +176,11 @@ void nx_debugfs_fini(struct nx_crypto_driver *);
 
 #define NX_PAGE_NUM(x)		((u64)(x) & 0xfffffffffffff000ULL)
 
-extern struct crypto_alg nx_cbc_aes_alg;
-extern struct crypto_alg nx_ecb_aes_alg;
+extern struct skcipher_alg nx_cbc_aes_alg;
+extern struct skcipher_alg nx_ecb_aes_alg;
 extern struct aead_alg nx_gcm_aes_alg;
 extern struct aead_alg nx_gcm4106_aes_alg;
-extern struct crypto_alg nx_ctr3686_aes_alg;
+extern struct skcipher_alg nx_ctr3686_aes_alg;
 extern struct aead_alg nx_ccm_aes_alg;
 extern struct aead_alg nx_ccm4309_aes_alg;
 extern struct shash_alg nx_shash_aes_xcbc_alg;
diff --git a/drivers/crypto/nx/nx_debugfs.c b/drivers/crypto/nx/nx_debugfs.c
index e0d44a5512ab..1975bcbee997 100644
--- a/drivers/crypto/nx/nx_debugfs.c
+++ b/drivers/crypto/nx/nx_debugfs.c
@@ -38,23 +38,23 @@ void nx_debugfs_init(struct nx_crypto_driver *drv)
 	drv->dfs_root = root;
 
 	debugfs_create_u32("aes_ops", S_IRUSR | S_IRGRP | S_IROTH,
-			   root, (u32 *)&drv->stats.aes_ops);
+			   root, &drv->stats.aes_ops.counter);
 	debugfs_create_u32("sha256_ops", S_IRUSR | S_IRGRP | S_IROTH,
-			   root, (u32 *)&drv->stats.sha256_ops);
+			   root, &drv->stats.sha256_ops.counter);
 	debugfs_create_u32("sha512_ops", S_IRUSR | S_IRGRP | S_IROTH,
-			   root, (u32 *)&drv->stats.sha512_ops);
+			   root, &drv->stats.sha512_ops.counter);
 	debugfs_create_u64("aes_bytes", S_IRUSR | S_IRGRP | S_IROTH,
-			   root, (u64 *)&drv->stats.aes_bytes);
+			   root, &drv->stats.aes_bytes.counter);
 	debugfs_create_u64("sha256_bytes", S_IRUSR | S_IRGRP | S_IROTH,
-			   root, (u64 *)&drv->stats.sha256_bytes);
+			   root, &drv->stats.sha256_bytes.counter);
 	debugfs_create_u64("sha512_bytes", S_IRUSR | S_IRGRP | S_IROTH,
-			   root, (u64 *)&drv->stats.sha512_bytes);
+			   root, &drv->stats.sha512_bytes.counter);
 	debugfs_create_u32("errors", S_IRUSR | S_IRGRP | S_IROTH,
-			   root, (u32 *)&drv->stats.errors);
+			   root, &drv->stats.errors.counter);
 	debugfs_create_u32("last_error", S_IRUSR | S_IRGRP | S_IROTH,
-			   root, (u32 *)&drv->stats.last_error);
+			   root, &drv->stats.last_error.counter);
 	debugfs_create_u32("last_error_pid", S_IRUSR | S_IRGRP | S_IROTH,
-			   root, (u32 *)&drv->stats.last_error_pid);
+			   root, &drv->stats.last_error_pid.counter);
 }
 
 void
diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c
index 2f53fbb74100..a1fc03ed01f3 100644
--- a/drivers/crypto/omap-aes.c
+++ b/drivers/crypto/omap-aes.c
@@ -142,8 +142,8 @@ int omap_aes_write_ctrl(struct omap_aes_dev *dd)
 			__le32_to_cpu(dd->ctx->key[i]));
 	}
 
-	if ((dd->flags & (FLAGS_CBC | FLAGS_CTR)) && dd->req->info)
-		omap_aes_write_n(dd, AES_REG_IV(dd, 0), dd->req->info, 4);
+	if ((dd->flags & (FLAGS_CBC | FLAGS_CTR)) && dd->req->iv)
+		omap_aes_write_n(dd, AES_REG_IV(dd, 0), (void *)dd->req->iv, 4);
 
 	if ((dd->flags & (FLAGS_GCM)) && dd->aead_req->iv) {
 		rctx = aead_request_ctx(dd->aead_req);
@@ -382,11 +382,11 @@ int omap_aes_crypt_dma_start(struct omap_aes_dev *dd)
 
 static void omap_aes_finish_req(struct omap_aes_dev *dd, int err)
 {
-	struct ablkcipher_request *req = dd->req;
+	struct skcipher_request *req = dd->req;
 
 	pr_debug("err: %d\n", err);
 
-	crypto_finalize_ablkcipher_request(dd->engine, req, err);
+	crypto_finalize_skcipher_request(dd->engine, req, err);
 
 	pm_runtime_mark_last_busy(dd->dev);
 	pm_runtime_put_autosuspend(dd->dev);
@@ -403,10 +403,10 @@ int omap_aes_crypt_dma_stop(struct omap_aes_dev *dd)
 }
 
 static int omap_aes_handle_queue(struct omap_aes_dev *dd,
-				 struct ablkcipher_request *req)
+				 struct skcipher_request *req)
 {
 	if (req)
-		return crypto_transfer_ablkcipher_request_to_engine(dd->engine, req);
+		return crypto_transfer_skcipher_request_to_engine(dd->engine, req);
 
 	return 0;
 }
@@ -414,10 +414,10 @@ static int omap_aes_handle_queue(struct omap_aes_dev *dd,
 static int omap_aes_prepare_req(struct crypto_engine *engine,
 				void *areq)
 {
-	struct ablkcipher_request *req = container_of(areq, struct ablkcipher_request, base);
-	struct omap_aes_ctx *ctx = crypto_ablkcipher_ctx(
-			crypto_ablkcipher_reqtfm(req));
-	struct omap_aes_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct skcipher_request *req = container_of(areq, struct skcipher_request, base);
+	struct omap_aes_ctx *ctx = crypto_skcipher_ctx(
+			crypto_skcipher_reqtfm(req));
+	struct omap_aes_reqctx *rctx = skcipher_request_ctx(req);
 	struct omap_aes_dev *dd = rctx->dd;
 	int ret;
 	u16 flags;
@@ -427,8 +427,8 @@ static int omap_aes_prepare_req(struct crypto_engine *engine,
 
 	/* assign new request to device */
 	dd->req = req;
-	dd->total = req->nbytes;
-	dd->total_save = req->nbytes;
+	dd->total = req->cryptlen;
+	dd->total_save = req->cryptlen;
 	dd->in_sg = req->src;
 	dd->out_sg = req->dst;
 	dd->orig_out = req->dst;
@@ -469,8 +469,8 @@ static int omap_aes_prepare_req(struct crypto_engine *engine,
 static int omap_aes_crypt_req(struct crypto_engine *engine,
 			      void *areq)
 {
-	struct ablkcipher_request *req = container_of(areq, struct ablkcipher_request, base);
-	struct omap_aes_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct skcipher_request *req = container_of(areq, struct skcipher_request, base);
+	struct omap_aes_reqctx *rctx = skcipher_request_ctx(req);
 	struct omap_aes_dev *dd = rctx->dd;
 
 	if (!dd)
@@ -505,26 +505,26 @@ static void omap_aes_done_task(unsigned long data)
 	pr_debug("exit\n");
 }
 
-static int omap_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
+static int omap_aes_crypt(struct skcipher_request *req, unsigned long mode)
 {
-	struct omap_aes_ctx *ctx = crypto_ablkcipher_ctx(
-			crypto_ablkcipher_reqtfm(req));
-	struct omap_aes_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct omap_aes_ctx *ctx = crypto_skcipher_ctx(
+			crypto_skcipher_reqtfm(req));
+	struct omap_aes_reqctx *rctx = skcipher_request_ctx(req);
 	struct omap_aes_dev *dd;
 	int ret;
 
-	pr_debug("nbytes: %d, enc: %d, cbc: %d\n", req->nbytes,
+	pr_debug("nbytes: %d, enc: %d, cbc: %d\n", req->cryptlen,
 		  !!(mode & FLAGS_ENCRYPT),
 		  !!(mode & FLAGS_CBC));
 
-	if (req->nbytes < aes_fallback_sz) {
+	if (req->cryptlen < aes_fallback_sz) {
 		SYNC_SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
 
 		skcipher_request_set_sync_tfm(subreq, ctx->fallback);
 		skcipher_request_set_callback(subreq, req->base.flags, NULL,
 					      NULL);
 		skcipher_request_set_crypt(subreq, req->src, req->dst,
-					   req->nbytes, req->info);
+					   req->cryptlen, req->iv);
 
 		if (mode & FLAGS_ENCRYPT)
 			ret = crypto_skcipher_encrypt(subreq);
@@ -545,10 +545,10 @@ static int omap_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 
 /* ********************** ALG API ************************************ */
 
-static int omap_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int omap_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			   unsigned int keylen)
 {
-	struct omap_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct omap_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
 	int ret;
 
 	if (keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_192 &&
@@ -571,32 +571,32 @@ static int omap_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 	return 0;
 }
 
-static int omap_aes_ecb_encrypt(struct ablkcipher_request *req)
+static int omap_aes_ecb_encrypt(struct skcipher_request *req)
 {
 	return omap_aes_crypt(req, FLAGS_ENCRYPT);
 }
 
-static int omap_aes_ecb_decrypt(struct ablkcipher_request *req)
+static int omap_aes_ecb_decrypt(struct skcipher_request *req)
 {
 	return omap_aes_crypt(req, 0);
 }
 
-static int omap_aes_cbc_encrypt(struct ablkcipher_request *req)
+static int omap_aes_cbc_encrypt(struct skcipher_request *req)
 {
 	return omap_aes_crypt(req, FLAGS_ENCRYPT | FLAGS_CBC);
 }
 
-static int omap_aes_cbc_decrypt(struct ablkcipher_request *req)
+static int omap_aes_cbc_decrypt(struct skcipher_request *req)
 {
 	return omap_aes_crypt(req, FLAGS_CBC);
 }
 
-static int omap_aes_ctr_encrypt(struct ablkcipher_request *req)
+static int omap_aes_ctr_encrypt(struct skcipher_request *req)
 {
 	return omap_aes_crypt(req, FLAGS_ENCRYPT | FLAGS_CTR);
 }
 
-static int omap_aes_ctr_decrypt(struct ablkcipher_request *req)
+static int omap_aes_ctr_decrypt(struct skcipher_request *req)
 {
 	return omap_aes_crypt(req, FLAGS_CTR);
 }
@@ -606,10 +606,10 @@ static int omap_aes_prepare_req(struct crypto_engine *engine,
 static int omap_aes_crypt_req(struct crypto_engine *engine,
 			      void *req);
 
-static int omap_aes_cra_init(struct crypto_tfm *tfm)
+static int omap_aes_init_tfm(struct crypto_skcipher *tfm)
 {
-	const char *name = crypto_tfm_alg_name(tfm);
-	struct omap_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	const char *name = crypto_tfm_alg_name(&tfm->base);
+	struct omap_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
 	struct crypto_sync_skcipher *blk;
 
 	blk = crypto_alloc_sync_skcipher(name, 0, CRYPTO_ALG_NEED_FALLBACK);
@@ -618,7 +618,7 @@ static int omap_aes_cra_init(struct crypto_tfm *tfm)
 
 	ctx->fallback = blk;
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct omap_aes_reqctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct omap_aes_reqctx));
 
 	ctx->enginectx.op.prepare_request = omap_aes_prepare_req;
 	ctx->enginectx.op.unprepare_request = NULL;
@@ -657,9 +657,9 @@ static int omap_aes_gcm_cra_init(struct crypto_aead *tfm)
 	return 0;
 }
 
-static void omap_aes_cra_exit(struct crypto_tfm *tfm)
+static void omap_aes_exit_tfm(struct crypto_skcipher *tfm)
 {
-	struct omap_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct omap_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	if (ctx->fallback)
 		crypto_free_sync_skcipher(ctx->fallback);
@@ -671,7 +671,10 @@ static void omap_aes_gcm_cra_exit(struct crypto_aead *tfm)
 {
 	struct omap_aes_ctx *ctx = crypto_aead_ctx(tfm);
 
-	omap_aes_cra_exit(crypto_aead_tfm(tfm));
+	if (ctx->fallback)
+		crypto_free_sync_skcipher(ctx->fallback);
+
+	ctx->fallback = NULL;
 
 	if (ctx->ctr)
 		crypto_free_skcipher(ctx->ctr);
@@ -679,78 +682,69 @@ static void omap_aes_gcm_cra_exit(struct crypto_aead *tfm)
 
 /* ********************** ALGS ************************************ */
 
-static struct crypto_alg algs_ecb_cbc[] = {
+static struct skcipher_alg algs_ecb_cbc[] = {
 {
-	.cra_name		= "ecb(aes)",
-	.cra_driver_name	= "ecb-aes-omap",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_KERN_DRIVER_ONLY |
-				  CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct omap_aes_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= omap_aes_cra_init,
-	.cra_exit		= omap_aes_cra_exit,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.setkey		= omap_aes_setkey,
-		.encrypt	= omap_aes_ecb_encrypt,
-		.decrypt	= omap_aes_ecb_decrypt,
-	}
+	.base.cra_name		= "ecb(aes)",
+	.base.cra_driver_name	= "ecb-aes-omap",
+	.base.cra_priority	= 300,
+	.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
+				  CRYPTO_ALG_ASYNC |
+				  CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct omap_aes_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= omap_aes_setkey,
+	.encrypt		= omap_aes_ecb_encrypt,
+	.decrypt		= omap_aes_ecb_decrypt,
+	.init			= omap_aes_init_tfm,
+	.exit			= omap_aes_exit_tfm,
 },
 {
-	.cra_name		= "cbc(aes)",
-	.cra_driver_name	= "cbc-aes-omap",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_KERN_DRIVER_ONLY |
-				  CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct omap_aes_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= omap_aes_cra_init,
-	.cra_exit		= omap_aes_cra_exit,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= omap_aes_setkey,
-		.encrypt	= omap_aes_cbc_encrypt,
-		.decrypt	= omap_aes_cbc_decrypt,
-	}
+	.base.cra_name		= "cbc(aes)",
+	.base.cra_driver_name	= "cbc-aes-omap",
+	.base.cra_priority	= 300,
+	.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
+				  CRYPTO_ALG_ASYNC |
+				  CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct omap_aes_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= omap_aes_setkey,
+	.encrypt		= omap_aes_cbc_encrypt,
+	.decrypt		= omap_aes_cbc_decrypt,
+	.init			= omap_aes_init_tfm,
+	.exit			= omap_aes_exit_tfm,
 }
 };
 
-static struct crypto_alg algs_ctr[] = {
+static struct skcipher_alg algs_ctr[] = {
 {
-	.cra_name		= "ctr(aes)",
-	.cra_driver_name	= "ctr-aes-omap",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_KERN_DRIVER_ONLY |
-				  CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct omap_aes_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= omap_aes_cra_init,
-	.cra_exit		= omap_aes_cra_exit,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= omap_aes_setkey,
-		.encrypt	= omap_aes_ctr_encrypt,
-		.decrypt	= omap_aes_ctr_decrypt,
-	}
-} ,
+	.base.cra_name		= "ctr(aes)",
+	.base.cra_driver_name	= "ctr-aes-omap",
+	.base.cra_priority	= 300,
+	.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
+				  CRYPTO_ALG_ASYNC |
+				  CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct omap_aes_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= omap_aes_setkey,
+	.encrypt		= omap_aes_ctr_encrypt,
+	.decrypt		= omap_aes_ctr_decrypt,
+	.init			= omap_aes_init_tfm,
+	.exit			= omap_aes_exit_tfm,
+}
 };
 
 static struct omap_aes_algs_info omap_aes_algs_info_ecb_cbc[] = {
@@ -1121,7 +1115,7 @@ static int omap_aes_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct omap_aes_dev *dd;
-	struct crypto_alg *algp;
+	struct skcipher_alg *algp;
 	struct aead_alg *aalg;
 	struct resource res;
 	int err = -ENOMEM, i, j, irq = -1;
@@ -1215,9 +1209,9 @@ static int omap_aes_probe(struct platform_device *pdev)
 			for (j = 0; j < dd->pdata->algs_info[i].size; j++) {
 				algp = &dd->pdata->algs_info[i].algs_list[j];
 
-				pr_debug("reg alg: %s\n", algp->cra_name);
+				pr_debug("reg alg: %s\n", algp->base.cra_name);
 
-				err = crypto_register_alg(algp);
+				err = crypto_register_skcipher(algp);
 				if (err)
 					goto err_algs;
 
@@ -1230,9 +1224,8 @@ static int omap_aes_probe(struct platform_device *pdev)
 	    !dd->pdata->aead_algs_info->registered) {
 		for (i = 0; i < dd->pdata->aead_algs_info->size; i++) {
 			aalg = &dd->pdata->aead_algs_info->algs_list[i];
-			algp = &aalg->base;
 
-			pr_debug("reg alg: %s\n", algp->cra_name);
+			pr_debug("reg alg: %s\n", aalg->base.cra_name);
 
 			err = crypto_register_aead(aalg);
 			if (err)
@@ -1257,7 +1250,7 @@ err_aead_algs:
 err_algs:
 	for (i = dd->pdata->algs_info_size - 1; i >= 0; i--)
 		for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--)
-			crypto_unregister_alg(
+			crypto_unregister_skcipher(
 					&dd->pdata->algs_info[i].algs_list[j]);
 
 err_engine:
@@ -1290,7 +1283,7 @@ static int omap_aes_remove(struct platform_device *pdev)
 
 	for (i = dd->pdata->algs_info_size - 1; i >= 0; i--)
 		for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--)
-			crypto_unregister_alg(
+			crypto_unregister_skcipher(
 					&dd->pdata->algs_info[i].algs_list[j]);
 
 	for (i = dd->pdata->aead_algs_info->size - 1; i >= 0; i--) {
diff --git a/drivers/crypto/omap-aes.h b/drivers/crypto/omap-aes.h
index 2d4b1f87a1c9..2d3575231e31 100644
--- a/drivers/crypto/omap-aes.h
+++ b/drivers/crypto/omap-aes.h
@@ -112,7 +112,7 @@ struct omap_aes_reqctx {
 #define OMAP_AES_CACHE_SIZE	0
 
 struct omap_aes_algs_info {
-	struct crypto_alg	*algs_list;
+	struct skcipher_alg	*algs_list;
 	unsigned int		size;
 	unsigned int		registered;
 };
@@ -162,7 +162,7 @@ struct omap_aes_dev {
 	struct aead_queue	aead_queue;
 	spinlock_t		lock;
 
-	struct ablkcipher_request	*req;
+	struct skcipher_request		*req;
 	struct aead_request		*aead_req;
 	struct crypto_engine		*engine;
 
diff --git a/drivers/crypto/omap-des.c b/drivers/crypto/omap-des.c
index b19d7e5d55ec..4c4dbc2b377e 100644
--- a/drivers/crypto/omap-des.c
+++ b/drivers/crypto/omap-des.c
@@ -34,6 +34,7 @@
 #include <linux/interrupt.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/des.h>
+#include <crypto/internal/skcipher.h>
 #include <crypto/algapi.h>
 #include <crypto/engine.h>
 
@@ -98,7 +99,7 @@ struct omap_des_reqctx {
 #define OMAP_DES_CACHE_SIZE	0
 
 struct omap_des_algs_info {
-	struct crypto_alg	*algs_list;
+	struct skcipher_alg	*algs_list;
 	unsigned int		size;
 	unsigned int		registered;
 };
@@ -139,7 +140,7 @@ struct omap_des_dev {
 
 	struct tasklet_struct	done_task;
 
-	struct ablkcipher_request	*req;
+	struct skcipher_request	*req;
 	struct crypto_engine		*engine;
 	/*
 	 * total is used by PIO mode for book keeping so introduce
@@ -261,8 +262,8 @@ static int omap_des_write_ctrl(struct omap_des_dev *dd)
 			       __le32_to_cpu(dd->ctx->key[i]));
 	}
 
-	if ((dd->flags & FLAGS_CBC) && dd->req->info)
-		omap_des_write_n(dd, DES_REG_IV(dd, 0), dd->req->info, 2);
+	if ((dd->flags & FLAGS_CBC) && dd->req->iv)
+		omap_des_write_n(dd, DES_REG_IV(dd, 0), (void *)dd->req->iv, 2);
 
 	if (dd->flags & FLAGS_CBC)
 		val |= DES_REG_CTRL_CBC;
@@ -456,8 +457,8 @@ static int omap_des_crypt_dma(struct crypto_tfm *tfm,
 
 static int omap_des_crypt_dma_start(struct omap_des_dev *dd)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(
-					crypto_ablkcipher_reqtfm(dd->req));
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(
+					crypto_skcipher_reqtfm(dd->req));
 	int err;
 
 	pr_debug("total: %d\n", dd->total);
@@ -491,11 +492,11 @@ static int omap_des_crypt_dma_start(struct omap_des_dev *dd)
 
 static void omap_des_finish_req(struct omap_des_dev *dd, int err)
 {
-	struct ablkcipher_request *req = dd->req;
+	struct skcipher_request *req = dd->req;
 
 	pr_debug("err: %d\n", err);
 
-	crypto_finalize_ablkcipher_request(dd->engine, req, err);
+	crypto_finalize_skcipher_request(dd->engine, req, err);
 
 	pm_runtime_mark_last_busy(dd->dev);
 	pm_runtime_put_autosuspend(dd->dev);
@@ -514,10 +515,10 @@ static int omap_des_crypt_dma_stop(struct omap_des_dev *dd)
 }
 
 static int omap_des_handle_queue(struct omap_des_dev *dd,
-				 struct ablkcipher_request *req)
+				 struct skcipher_request *req)
 {
 	if (req)
-		return crypto_transfer_ablkcipher_request_to_engine(dd->engine, req);
+		return crypto_transfer_skcipher_request_to_engine(dd->engine, req);
 
 	return 0;
 }
@@ -525,9 +526,9 @@ static int omap_des_handle_queue(struct omap_des_dev *dd,
 static int omap_des_prepare_req(struct crypto_engine *engine,
 				void *areq)
 {
-	struct ablkcipher_request *req = container_of(areq, struct ablkcipher_request, base);
-	struct omap_des_ctx *ctx = crypto_ablkcipher_ctx(
-			crypto_ablkcipher_reqtfm(req));
+	struct skcipher_request *req = container_of(areq, struct skcipher_request, base);
+	struct omap_des_ctx *ctx = crypto_skcipher_ctx(
+			crypto_skcipher_reqtfm(req));
 	struct omap_des_dev *dd = omap_des_find_dev(ctx);
 	struct omap_des_reqctx *rctx;
 	int ret;
@@ -538,8 +539,8 @@ static int omap_des_prepare_req(struct crypto_engine *engine,
 
 	/* assign new request to device */
 	dd->req = req;
-	dd->total = req->nbytes;
-	dd->total_save = req->nbytes;
+	dd->total = req->cryptlen;
+	dd->total_save = req->cryptlen;
 	dd->in_sg = req->src;
 	dd->out_sg = req->dst;
 	dd->orig_out = req->dst;
@@ -568,8 +569,8 @@ static int omap_des_prepare_req(struct crypto_engine *engine,
 	if (dd->out_sg_len < 0)
 		return dd->out_sg_len;
 
-	rctx = ablkcipher_request_ctx(req);
-	ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
+	rctx = skcipher_request_ctx(req);
+	ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req));
 	rctx->mode &= FLAGS_MODE_MASK;
 	dd->flags = (dd->flags & ~FLAGS_MODE_MASK) | rctx->mode;
 
@@ -582,9 +583,9 @@ static int omap_des_prepare_req(struct crypto_engine *engine,
 static int omap_des_crypt_req(struct crypto_engine *engine,
 			      void *areq)
 {
-	struct ablkcipher_request *req = container_of(areq, struct ablkcipher_request, base);
-	struct omap_des_ctx *ctx = crypto_ablkcipher_ctx(
-			crypto_ablkcipher_reqtfm(req));
+	struct skcipher_request *req = container_of(areq, struct skcipher_request, base);
+	struct omap_des_ctx *ctx = crypto_skcipher_ctx(
+			crypto_skcipher_reqtfm(req));
 	struct omap_des_dev *dd = omap_des_find_dev(ctx);
 
 	if (!dd)
@@ -619,18 +620,18 @@ static void omap_des_done_task(unsigned long data)
 	pr_debug("exit\n");
 }
 
-static int omap_des_crypt(struct ablkcipher_request *req, unsigned long mode)
+static int omap_des_crypt(struct skcipher_request *req, unsigned long mode)
 {
-	struct omap_des_ctx *ctx = crypto_ablkcipher_ctx(
-			crypto_ablkcipher_reqtfm(req));
-	struct omap_des_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct omap_des_ctx *ctx = crypto_skcipher_ctx(
+			crypto_skcipher_reqtfm(req));
+	struct omap_des_reqctx *rctx = skcipher_request_ctx(req);
 	struct omap_des_dev *dd;
 
-	pr_debug("nbytes: %d, enc: %d, cbc: %d\n", req->nbytes,
+	pr_debug("nbytes: %d, enc: %d, cbc: %d\n", req->cryptlen,
 		 !!(mode & FLAGS_ENCRYPT),
 		 !!(mode & FLAGS_CBC));
 
-	if (!IS_ALIGNED(req->nbytes, DES_BLOCK_SIZE)) {
+	if (!IS_ALIGNED(req->cryptlen, DES_BLOCK_SIZE)) {
 		pr_err("request size is not exact amount of DES blocks\n");
 		return -EINVAL;
 	}
@@ -646,15 +647,15 @@ static int omap_des_crypt(struct ablkcipher_request *req, unsigned long mode)
 
 /* ********************** ALG API ************************************ */
 
-static int omap_des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int omap_des_setkey(struct crypto_skcipher *cipher, const u8 *key,
 			   unsigned int keylen)
 {
-	struct omap_des_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	struct omap_des_ctx *ctx = crypto_skcipher_ctx(cipher);
 	int err;
 
 	pr_debug("enter, keylen: %d\n", keylen);
 
-	err = verify_ablkcipher_des_key(cipher, key);
+	err = verify_skcipher_des_key(cipher, key);
 	if (err)
 		return err;
 
@@ -664,15 +665,15 @@ static int omap_des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	return 0;
 }
 
-static int omap_des3_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int omap_des3_setkey(struct crypto_skcipher *cipher, const u8 *key,
 			    unsigned int keylen)
 {
-	struct omap_des_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	struct omap_des_ctx *ctx = crypto_skcipher_ctx(cipher);
 	int err;
 
 	pr_debug("enter, keylen: %d\n", keylen);
 
-	err = verify_ablkcipher_des3_key(cipher, key);
+	err = verify_skcipher_des3_key(cipher, key);
 	if (err)
 		return err;
 
@@ -682,22 +683,22 @@ static int omap_des3_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	return 0;
 }
 
-static int omap_des_ecb_encrypt(struct ablkcipher_request *req)
+static int omap_des_ecb_encrypt(struct skcipher_request *req)
 {
 	return omap_des_crypt(req, FLAGS_ENCRYPT);
 }
 
-static int omap_des_ecb_decrypt(struct ablkcipher_request *req)
+static int omap_des_ecb_decrypt(struct skcipher_request *req)
 {
 	return omap_des_crypt(req, 0);
 }
 
-static int omap_des_cbc_encrypt(struct ablkcipher_request *req)
+static int omap_des_cbc_encrypt(struct skcipher_request *req)
 {
 	return omap_des_crypt(req, FLAGS_ENCRYPT | FLAGS_CBC);
 }
 
-static int omap_des_cbc_decrypt(struct ablkcipher_request *req)
+static int omap_des_cbc_decrypt(struct skcipher_request *req)
 {
 	return omap_des_crypt(req, FLAGS_CBC);
 }
@@ -707,13 +708,13 @@ static int omap_des_prepare_req(struct crypto_engine *engine,
 static int omap_des_crypt_req(struct crypto_engine *engine,
 			      void *areq);
 
-static int omap_des_cra_init(struct crypto_tfm *tfm)
+static int omap_des_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct omap_des_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct omap_des_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	pr_debug("enter\n");
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct omap_des_reqctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct omap_des_reqctx));
 
 	ctx->enginectx.op.prepare_request = omap_des_prepare_req;
 	ctx->enginectx.op.unprepare_request = NULL;
@@ -722,103 +723,78 @@ static int omap_des_cra_init(struct crypto_tfm *tfm)
 	return 0;
 }
 
-static void omap_des_cra_exit(struct crypto_tfm *tfm)
-{
-	pr_debug("enter\n");
-}
-
 /* ********************** ALGS ************************************ */
 
-static struct crypto_alg algs_ecb_cbc[] = {
+static struct skcipher_alg algs_ecb_cbc[] = {
 {
-	.cra_name		= "ecb(des)",
-	.cra_driver_name	= "ecb-des-omap",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_KERN_DRIVER_ONLY |
+	.base.cra_name		= "ecb(des)",
+	.base.cra_driver_name	= "ecb-des-omap",
+	.base.cra_priority	= 100,
+	.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 				  CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct omap_des_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= omap_des_cra_init,
-	.cra_exit		= omap_des_cra_exit,
-	.cra_u.ablkcipher = {
-		.min_keysize	= DES_KEY_SIZE,
-		.max_keysize	= DES_KEY_SIZE,
-		.setkey		= omap_des_setkey,
-		.encrypt	= omap_des_ecb_encrypt,
-		.decrypt	= omap_des_ecb_decrypt,
-	}
+	.base.cra_blocksize	= DES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct omap_des_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= DES_KEY_SIZE,
+	.max_keysize		= DES_KEY_SIZE,
+	.setkey			= omap_des_setkey,
+	.encrypt		= omap_des_ecb_encrypt,
+	.decrypt		= omap_des_ecb_decrypt,
+	.init			= omap_des_init_tfm,
 },
 {
-	.cra_name		= "cbc(des)",
-	.cra_driver_name	= "cbc-des-omap",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_KERN_DRIVER_ONLY |
+	.base.cra_name		= "cbc(des)",
+	.base.cra_driver_name	= "cbc-des-omap",
+	.base.cra_priority	= 100,
+	.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 				  CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct omap_des_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= omap_des_cra_init,
-	.cra_exit		= omap_des_cra_exit,
-	.cra_u.ablkcipher = {
-		.min_keysize	= DES_KEY_SIZE,
-		.max_keysize	= DES_KEY_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= omap_des_setkey,
-		.encrypt	= omap_des_cbc_encrypt,
-		.decrypt	= omap_des_cbc_decrypt,
-	}
+	.base.cra_blocksize	= DES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct omap_des_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= DES_KEY_SIZE,
+	.max_keysize		= DES_KEY_SIZE,
+	.ivsize			= DES_BLOCK_SIZE,
+	.setkey			= omap_des_setkey,
+	.encrypt		= omap_des_cbc_encrypt,
+	.decrypt		= omap_des_cbc_decrypt,
+	.init			= omap_des_init_tfm,
 },
 {
-	.cra_name		= "ecb(des3_ede)",
-	.cra_driver_name	= "ecb-des3-omap",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_KERN_DRIVER_ONLY |
+	.base.cra_name		= "ecb(des3_ede)",
+	.base.cra_driver_name	= "ecb-des3-omap",
+	.base.cra_priority	= 100,
+	.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 				  CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct omap_des_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= omap_des_cra_init,
-	.cra_exit		= omap_des_cra_exit,
-	.cra_u.ablkcipher = {
-		.min_keysize	= 3*DES_KEY_SIZE,
-		.max_keysize	= 3*DES_KEY_SIZE,
-		.setkey		= omap_des3_setkey,
-		.encrypt	= omap_des_ecb_encrypt,
-		.decrypt	= omap_des_ecb_decrypt,
-	}
+	.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct omap_des_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= DES3_EDE_KEY_SIZE,
+	.max_keysize		= DES3_EDE_KEY_SIZE,
+	.setkey			= omap_des3_setkey,
+	.encrypt		= omap_des_ecb_encrypt,
+	.decrypt		= omap_des_ecb_decrypt,
+	.init			= omap_des_init_tfm,
 },
 {
-	.cra_name		= "cbc(des3_ede)",
-	.cra_driver_name	= "cbc-des3-omap",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_KERN_DRIVER_ONLY |
+	.base.cra_name		= "cbc(des3_ede)",
+	.base.cra_driver_name	= "cbc-des3-omap",
+	.base.cra_priority	= 100,
+	.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 				  CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct omap_des_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= omap_des_cra_init,
-	.cra_exit		= omap_des_cra_exit,
-	.cra_u.ablkcipher = {
-		.min_keysize	= 3*DES_KEY_SIZE,
-		.max_keysize	= 3*DES_KEY_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= omap_des3_setkey,
-		.encrypt	= omap_des_cbc_encrypt,
-		.decrypt	= omap_des_cbc_decrypt,
-	}
+	.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct omap_des_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= DES3_EDE_KEY_SIZE,
+	.max_keysize		= DES3_EDE_KEY_SIZE,
+	.ivsize			= DES3_EDE_BLOCK_SIZE,
+	.setkey			= omap_des3_setkey,
+	.encrypt		= omap_des_cbc_encrypt,
+	.decrypt		= omap_des_cbc_decrypt,
+	.init			= omap_des_init_tfm,
 }
 };
 
@@ -976,7 +952,7 @@ static int omap_des_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct omap_des_dev *dd;
-	struct crypto_alg *algp;
+	struct skcipher_alg *algp;
 	struct resource *res;
 	int err = -ENOMEM, i, j, irq = -1;
 	u32 reg;
@@ -1071,9 +1047,9 @@ static int omap_des_probe(struct platform_device *pdev)
 		for (j = 0; j < dd->pdata->algs_info[i].size; j++) {
 			algp = &dd->pdata->algs_info[i].algs_list[j];
 
-			pr_debug("reg alg: %s\n", algp->cra_name);
+			pr_debug("reg alg: %s\n", algp->base.cra_name);
 
-			err = crypto_register_alg(algp);
+			err = crypto_register_skcipher(algp);
 			if (err)
 				goto err_algs;
 
@@ -1086,7 +1062,7 @@ static int omap_des_probe(struct platform_device *pdev)
 err_algs:
 	for (i = dd->pdata->algs_info_size - 1; i >= 0; i--)
 		for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--)
-			crypto_unregister_alg(
+			crypto_unregister_skcipher(
 					&dd->pdata->algs_info[i].algs_list[j]);
 
 err_engine:
@@ -1119,7 +1095,7 @@ static int omap_des_remove(struct platform_device *pdev)
 
 	for (i = dd->pdata->algs_info_size - 1; i >= 0; i--)
 		for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--)
-			crypto_unregister_alg(
+			crypto_unregister_skcipher(
 					&dd->pdata->algs_info[i].algs_list[j]);
 
 	tasklet_kill(&dd->done_task);
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index 8a0661250078..c5b60f50e1b5 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -10,6 +10,7 @@
 
 #include <crypto/algapi.h>
 #include <crypto/aes.h>
+#include <crypto/internal/skcipher.h>
 #include <crypto/padlock.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -97,9 +98,9 @@ static inline struct aes_ctx *aes_ctx(struct crypto_tfm *tfm)
 	return aes_ctx_common(crypto_tfm_ctx(tfm));
 }
 
-static inline struct aes_ctx *blk_aes_ctx(struct crypto_blkcipher *tfm)
+static inline struct aes_ctx *skcipher_aes_ctx(struct crypto_skcipher *tfm)
 {
-	return aes_ctx_common(crypto_blkcipher_ctx(tfm));
+	return aes_ctx_common(crypto_skcipher_ctx(tfm));
 }
 
 static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
@@ -162,6 +163,12 @@ ok:
 	return 0;
 }
 
+static int aes_set_key_skcipher(struct crypto_skcipher *tfm, const u8 *in_key,
+				unsigned int key_len)
+{
+	return aes_set_key(crypto_skcipher_tfm(tfm), in_key, key_len);
+}
+
 /* ====== Encryption/decryption routines ====== */
 
 /* These are the real call to PadLock. */
@@ -338,25 +345,24 @@ static struct crypto_alg aes_alg = {
 	}
 };
 
-static int ecb_aes_encrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
+static int ecb_aes_encrypt(struct skcipher_request *req)
 {
-	struct aes_ctx *ctx = blk_aes_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct aes_ctx *ctx = skcipher_aes_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
 	padlock_reset_key(&ctx->cword.encrypt);
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	while ((nbytes = walk.nbytes)) {
+	while ((nbytes = walk.nbytes) != 0) {
 		padlock_xcrypt_ecb(walk.src.virt.addr, walk.dst.virt.addr,
 				   ctx->E, &ctx->cword.encrypt,
 				   nbytes / AES_BLOCK_SIZE);
 		nbytes &= AES_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	padlock_store_cword(&ctx->cword.encrypt);
@@ -364,25 +370,24 @@ static int ecb_aes_encrypt(struct blkcipher_desc *desc,
 	return err;
 }
 
-static int ecb_aes_decrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
+static int ecb_aes_decrypt(struct skcipher_request *req)
 {
-	struct aes_ctx *ctx = blk_aes_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct aes_ctx *ctx = skcipher_aes_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
 	padlock_reset_key(&ctx->cword.decrypt);
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	while ((nbytes = walk.nbytes)) {
+	while ((nbytes = walk.nbytes) != 0) {
 		padlock_xcrypt_ecb(walk.src.virt.addr, walk.dst.virt.addr,
 				   ctx->D, &ctx->cword.decrypt,
 				   nbytes / AES_BLOCK_SIZE);
 		nbytes &= AES_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	padlock_store_cword(&ctx->cword.encrypt);
@@ -390,48 +395,41 @@ static int ecb_aes_decrypt(struct blkcipher_desc *desc,
 	return err;
 }
 
-static struct crypto_alg ecb_aes_alg = {
-	.cra_name		=	"ecb(aes)",
-	.cra_driver_name	=	"ecb-aes-padlock",
-	.cra_priority		=	PADLOCK_COMPOSITE_PRIORITY,
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct aes_ctx),
-	.cra_alignmask		=	PADLOCK_ALIGNMENT - 1,
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	AES_MIN_KEY_SIZE,
-			.max_keysize		=	AES_MAX_KEY_SIZE,
-			.setkey	   		= 	aes_set_key,
-			.encrypt		=	ecb_aes_encrypt,
-			.decrypt		=	ecb_aes_decrypt,
-		}
-	}
+static struct skcipher_alg ecb_aes_alg = {
+	.base.cra_name		=	"ecb(aes)",
+	.base.cra_driver_name	=	"ecb-aes-padlock",
+	.base.cra_priority	=	PADLOCK_COMPOSITE_PRIORITY,
+	.base.cra_blocksize	=	AES_BLOCK_SIZE,
+	.base.cra_ctxsize	=	sizeof(struct aes_ctx),
+	.base.cra_alignmask	=	PADLOCK_ALIGNMENT - 1,
+	.base.cra_module	=	THIS_MODULE,
+	.min_keysize		=	AES_MIN_KEY_SIZE,
+	.max_keysize		=	AES_MAX_KEY_SIZE,
+	.setkey			=	aes_set_key_skcipher,
+	.encrypt		=	ecb_aes_encrypt,
+	.decrypt		=	ecb_aes_decrypt,
 };
 
-static int cbc_aes_encrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
+static int cbc_aes_encrypt(struct skcipher_request *req)
 {
-	struct aes_ctx *ctx = blk_aes_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct aes_ctx *ctx = skcipher_aes_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
 	padlock_reset_key(&ctx->cword.encrypt);
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	while ((nbytes = walk.nbytes)) {
+	while ((nbytes = walk.nbytes) != 0) {
 		u8 *iv = padlock_xcrypt_cbc(walk.src.virt.addr,
 					    walk.dst.virt.addr, ctx->E,
 					    walk.iv, &ctx->cword.encrypt,
 					    nbytes / AES_BLOCK_SIZE);
 		memcpy(walk.iv, iv, AES_BLOCK_SIZE);
 		nbytes &= AES_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	padlock_store_cword(&ctx->cword.decrypt);
@@ -439,25 +437,24 @@ static int cbc_aes_encrypt(struct blkcipher_desc *desc,
 	return err;
 }
 
-static int cbc_aes_decrypt(struct blkcipher_desc *desc,
-			   struct scatterlist *dst, struct scatterlist *src,
-			   unsigned int nbytes)
+static int cbc_aes_decrypt(struct skcipher_request *req)
 {
-	struct aes_ctx *ctx = blk_aes_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct aes_ctx *ctx = skcipher_aes_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
 	padlock_reset_key(&ctx->cword.encrypt);
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	while ((nbytes = walk.nbytes)) {
+	while ((nbytes = walk.nbytes) != 0) {
 		padlock_xcrypt_cbc(walk.src.virt.addr, walk.dst.virt.addr,
 				   ctx->D, walk.iv, &ctx->cword.decrypt,
 				   nbytes / AES_BLOCK_SIZE);
 		nbytes &= AES_BLOCK_SIZE - 1;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	padlock_store_cword(&ctx->cword.encrypt);
@@ -465,26 +462,20 @@ static int cbc_aes_decrypt(struct blkcipher_desc *desc,
 	return err;
 }
 
-static struct crypto_alg cbc_aes_alg = {
-	.cra_name		=	"cbc(aes)",
-	.cra_driver_name	=	"cbc-aes-padlock",
-	.cra_priority		=	PADLOCK_COMPOSITE_PRIORITY,
-	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct aes_ctx),
-	.cra_alignmask		=	PADLOCK_ALIGNMENT - 1,
-	.cra_type		=	&crypto_blkcipher_type,
-	.cra_module		=	THIS_MODULE,
-	.cra_u			=	{
-		.blkcipher = {
-			.min_keysize		=	AES_MIN_KEY_SIZE,
-			.max_keysize		=	AES_MAX_KEY_SIZE,
-			.ivsize			=	AES_BLOCK_SIZE,
-			.setkey	   		= 	aes_set_key,
-			.encrypt		=	cbc_aes_encrypt,
-			.decrypt		=	cbc_aes_decrypt,
-		}
-	}
+static struct skcipher_alg cbc_aes_alg = {
+	.base.cra_name		=	"cbc(aes)",
+	.base.cra_driver_name	=	"cbc-aes-padlock",
+	.base.cra_priority	=	PADLOCK_COMPOSITE_PRIORITY,
+	.base.cra_blocksize	=	AES_BLOCK_SIZE,
+	.base.cra_ctxsize	=	sizeof(struct aes_ctx),
+	.base.cra_alignmask	=	PADLOCK_ALIGNMENT - 1,
+	.base.cra_module	=	THIS_MODULE,
+	.min_keysize		=	AES_MIN_KEY_SIZE,
+	.max_keysize		=	AES_MAX_KEY_SIZE,
+	.ivsize			=	AES_BLOCK_SIZE,
+	.setkey			=	aes_set_key_skcipher,
+	.encrypt		=	cbc_aes_encrypt,
+	.decrypt		=	cbc_aes_decrypt,
 };
 
 static const struct x86_cpu_id padlock_cpu_id[] = {
@@ -506,13 +497,13 @@ static int __init padlock_init(void)
 		return -ENODEV;
 	}
 
-	if ((ret = crypto_register_alg(&aes_alg)))
+	if ((ret = crypto_register_alg(&aes_alg)) != 0)
 		goto aes_err;
 
-	if ((ret = crypto_register_alg(&ecb_aes_alg)))
+	if ((ret = crypto_register_skcipher(&ecb_aes_alg)) != 0)
 		goto ecb_aes_err;
 
-	if ((ret = crypto_register_alg(&cbc_aes_alg)))
+	if ((ret = crypto_register_skcipher(&cbc_aes_alg)) != 0)
 		goto cbc_aes_err;
 
 	printk(KERN_NOTICE PFX "Using VIA PadLock ACE for AES algorithm.\n");
@@ -527,7 +518,7 @@ out:
 	return ret;
 
 cbc_aes_err:
-	crypto_unregister_alg(&ecb_aes_alg);
+	crypto_unregister_skcipher(&ecb_aes_alg);
 ecb_aes_err:
 	crypto_unregister_alg(&aes_alg);
 aes_err:
@@ -537,8 +528,8 @@ aes_err:
 
 static void __exit padlock_fini(void)
 {
-	crypto_unregister_alg(&cbc_aes_alg);
-	crypto_unregister_alg(&ecb_aes_alg);
+	crypto_unregister_skcipher(&cbc_aes_alg);
+	crypto_unregister_skcipher(&ecb_aes_alg);
 	crypto_unregister_alg(&aes_alg);
 }
 
diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c
index 3cbefb41b099..29da449b3e9e 100644
--- a/drivers/crypto/picoxcell_crypto.c
+++ b/drivers/crypto/picoxcell_crypto.c
@@ -134,7 +134,7 @@ struct spacc_engine {
 struct spacc_alg {
 	unsigned long			ctrl_default;
 	unsigned long			type;
-	struct crypto_alg		alg;
+	struct skcipher_alg		alg;
 	struct spacc_engine		*engine;
 	struct list_head		entry;
 	int				key_offs;
@@ -173,7 +173,7 @@ struct spacc_aead_ctx {
 
 static int spacc_ablk_submit(struct spacc_req *req);
 
-static inline struct spacc_alg *to_spacc_alg(struct crypto_alg *alg)
+static inline struct spacc_alg *to_spacc_skcipher(struct skcipher_alg *alg)
 {
 	return alg ? container_of(alg, struct spacc_alg, alg) : NULL;
 }
@@ -733,13 +733,13 @@ static void spacc_aead_cra_exit(struct crypto_aead *tfm)
  * Set the DES key for a block cipher transform. This also performs weak key
  * checking if the transform has requested it.
  */
-static int spacc_des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int spacc_des_setkey(struct crypto_skcipher *cipher, const u8 *key,
 			    unsigned int len)
 {
-	struct spacc_ablk_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	struct spacc_ablk_ctx *ctx = crypto_skcipher_ctx(cipher);
 	int err;
 
-	err = verify_ablkcipher_des_key(cipher, key);
+	err = verify_skcipher_des_key(cipher, key);
 	if (err)
 		return err;
 
@@ -753,13 +753,13 @@ static int spacc_des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
  * Set the 3DES key for a block cipher transform. This also performs weak key
  * checking if the transform has requested it.
  */
-static int spacc_des3_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int spacc_des3_setkey(struct crypto_skcipher *cipher, const u8 *key,
 			     unsigned int len)
 {
-	struct spacc_ablk_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	struct spacc_ablk_ctx *ctx = crypto_skcipher_ctx(cipher);
 	int err;
 
-	err = verify_ablkcipher_des3_key(cipher, key);
+	err = verify_skcipher_des3_key(cipher, key);
 	if (err)
 		return err;
 
@@ -773,15 +773,15 @@ static int spacc_des3_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
  * Set the key for an AES block cipher. Some key lengths are not supported in
  * hardware so this must also check whether a fallback is needed.
  */
-static int spacc_aes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+static int spacc_aes_setkey(struct crypto_skcipher *cipher, const u8 *key,
 			    unsigned int len)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(cipher);
 	struct spacc_ablk_ctx *ctx = crypto_tfm_ctx(tfm);
 	int err = 0;
 
 	if (len > AES_MAX_KEY_SIZE) {
-		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		crypto_skcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
@@ -822,15 +822,15 @@ sw_setkey_failed:
 	return err;
 }
 
-static int spacc_kasumi_f8_setkey(struct crypto_ablkcipher *cipher,
+static int spacc_kasumi_f8_setkey(struct crypto_skcipher *cipher,
 				  const u8 *key, unsigned int len)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(cipher);
 	struct spacc_ablk_ctx *ctx = crypto_tfm_ctx(tfm);
 	int err = 0;
 
 	if (len > AES_MAX_KEY_SIZE) {
-		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		crypto_skcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		err = -EINVAL;
 		goto out;
 	}
@@ -844,12 +844,12 @@ out:
 
 static int spacc_ablk_need_fallback(struct spacc_req *req)
 {
+	struct skcipher_request *ablk_req = skcipher_request_cast(req->req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(ablk_req);
+	struct spacc_alg *spacc_alg = to_spacc_skcipher(crypto_skcipher_alg(tfm));
 	struct spacc_ablk_ctx *ctx;
-	struct crypto_tfm *tfm = req->req->tfm;
-	struct crypto_alg *alg = req->req->tfm->__crt_alg;
-	struct spacc_alg *spacc_alg = to_spacc_alg(alg);
 
-	ctx = crypto_tfm_ctx(tfm);
+	ctx = crypto_skcipher_ctx(tfm);
 
 	return (spacc_alg->ctrl_default & SPACC_CRYPTO_ALG_MASK) ==
 			SPA_CTRL_CIPH_ALG_AES &&
@@ -859,39 +859,39 @@ static int spacc_ablk_need_fallback(struct spacc_req *req)
 
 static void spacc_ablk_complete(struct spacc_req *req)
 {
-	struct ablkcipher_request *ablk_req = ablkcipher_request_cast(req->req);
+	struct skcipher_request *ablk_req = skcipher_request_cast(req->req);
 
 	if (ablk_req->src != ablk_req->dst) {
 		spacc_free_ddt(req, req->src_ddt, req->src_addr, ablk_req->src,
-			       ablk_req->nbytes, DMA_TO_DEVICE);
+			       ablk_req->cryptlen, DMA_TO_DEVICE);
 		spacc_free_ddt(req, req->dst_ddt, req->dst_addr, ablk_req->dst,
-			       ablk_req->nbytes, DMA_FROM_DEVICE);
+			       ablk_req->cryptlen, DMA_FROM_DEVICE);
 	} else
 		spacc_free_ddt(req, req->dst_ddt, req->dst_addr, ablk_req->dst,
-			       ablk_req->nbytes, DMA_BIDIRECTIONAL);
+			       ablk_req->cryptlen, DMA_BIDIRECTIONAL);
 
 	req->req->complete(req->req, req->result);
 }
 
 static int spacc_ablk_submit(struct spacc_req *req)
 {
-	struct crypto_tfm *tfm = req->req->tfm;
-	struct spacc_ablk_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct ablkcipher_request *ablk_req = ablkcipher_request_cast(req->req);
-	struct crypto_alg *alg = req->req->tfm->__crt_alg;
-	struct spacc_alg *spacc_alg = to_spacc_alg(alg);
+	struct skcipher_request *ablk_req = skcipher_request_cast(req->req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(ablk_req);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	struct spacc_alg *spacc_alg = to_spacc_skcipher(alg);
+	struct spacc_ablk_ctx *ctx = crypto_skcipher_ctx(tfm);
 	struct spacc_engine *engine = ctx->generic.engine;
 	u32 ctrl;
 
 	req->ctx_id = spacc_load_ctx(&ctx->generic, ctx->key,
-		ctx->key_len, ablk_req->info, alg->cra_ablkcipher.ivsize,
+		ctx->key_len, ablk_req->iv, alg->ivsize,
 		NULL, 0);
 
 	writel(req->src_addr, engine->regs + SPA_SRC_PTR_REG_OFFSET);
 	writel(req->dst_addr, engine->regs + SPA_DST_PTR_REG_OFFSET);
 	writel(0, engine->regs + SPA_OFFSET_REG_OFFSET);
 
-	writel(ablk_req->nbytes, engine->regs + SPA_PROC_LEN_REG_OFFSET);
+	writel(ablk_req->cryptlen, engine->regs + SPA_PROC_LEN_REG_OFFSET);
 	writel(0, engine->regs + SPA_ICV_OFFSET_REG_OFFSET);
 	writel(0, engine->regs + SPA_AUX_INFO_REG_OFFSET);
 	writel(0, engine->regs + SPA_AAD_LEN_REG_OFFSET);
@@ -907,11 +907,11 @@ static int spacc_ablk_submit(struct spacc_req *req)
 	return -EINPROGRESS;
 }
 
-static int spacc_ablk_do_fallback(struct ablkcipher_request *req,
+static int spacc_ablk_do_fallback(struct skcipher_request *req,
 				  unsigned alg_type, bool is_encrypt)
 {
 	struct crypto_tfm *old_tfm =
-	    crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
+	    crypto_skcipher_tfm(crypto_skcipher_reqtfm(req));
 	struct spacc_ablk_ctx *ctx = crypto_tfm_ctx(old_tfm);
 	SYNC_SKCIPHER_REQUEST_ON_STACK(subreq, ctx->sw_cipher);
 	int err;
@@ -924,7 +924,7 @@ static int spacc_ablk_do_fallback(struct ablkcipher_request *req,
 	skcipher_request_set_sync_tfm(subreq, ctx->sw_cipher);
 	skcipher_request_set_callback(subreq, req->base.flags, NULL, NULL);
 	skcipher_request_set_crypt(subreq, req->src, req->dst,
-				   req->nbytes, req->info);
+				   req->cryptlen, req->iv);
 	err = is_encrypt ? crypto_skcipher_encrypt(subreq) :
 			   crypto_skcipher_decrypt(subreq);
 	skcipher_request_zero(subreq);
@@ -932,12 +932,13 @@ static int spacc_ablk_do_fallback(struct ablkcipher_request *req,
 	return err;
 }
 
-static int spacc_ablk_setup(struct ablkcipher_request *req, unsigned alg_type,
+static int spacc_ablk_setup(struct skcipher_request *req, unsigned alg_type,
 			    bool is_encrypt)
 {
-	struct crypto_alg *alg = req->base.tfm->__crt_alg;
-	struct spacc_engine *engine = to_spacc_alg(alg)->engine;
-	struct spacc_req *dev_req = ablkcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	struct spacc_engine *engine = to_spacc_skcipher(alg)->engine;
+	struct spacc_req *dev_req = skcipher_request_ctx(req);
 	unsigned long flags;
 	int err = -ENOMEM;
 
@@ -956,17 +957,17 @@ static int spacc_ablk_setup(struct ablkcipher_request *req, unsigned alg_type,
 	 */
 	if (req->src != req->dst) {
 		dev_req->src_ddt = spacc_sg_to_ddt(engine, req->src,
-			req->nbytes, DMA_TO_DEVICE, &dev_req->src_addr);
+			req->cryptlen, DMA_TO_DEVICE, &dev_req->src_addr);
 		if (!dev_req->src_ddt)
 			goto out;
 
 		dev_req->dst_ddt = spacc_sg_to_ddt(engine, req->dst,
-			req->nbytes, DMA_FROM_DEVICE, &dev_req->dst_addr);
+			req->cryptlen, DMA_FROM_DEVICE, &dev_req->dst_addr);
 		if (!dev_req->dst_ddt)
 			goto out_free_src;
 	} else {
 		dev_req->dst_ddt = spacc_sg_to_ddt(engine, req->dst,
-			req->nbytes, DMA_BIDIRECTIONAL, &dev_req->dst_addr);
+			req->cryptlen, DMA_BIDIRECTIONAL, &dev_req->dst_addr);
 		if (!dev_req->dst_ddt)
 			goto out;
 
@@ -999,65 +1000,65 @@ static int spacc_ablk_setup(struct ablkcipher_request *req, unsigned alg_type,
 
 out_free_ddts:
 	spacc_free_ddt(dev_req, dev_req->dst_ddt, dev_req->dst_addr, req->dst,
-		       req->nbytes, req->src == req->dst ?
+		       req->cryptlen, req->src == req->dst ?
 		       DMA_BIDIRECTIONAL : DMA_FROM_DEVICE);
 out_free_src:
 	if (req->src != req->dst)
 		spacc_free_ddt(dev_req, dev_req->src_ddt, dev_req->src_addr,
-			       req->src, req->nbytes, DMA_TO_DEVICE);
+			       req->src, req->cryptlen, DMA_TO_DEVICE);
 out:
 	return err;
 }
 
-static int spacc_ablk_cra_init(struct crypto_tfm *tfm)
+static int spacc_ablk_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct spacc_ablk_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct crypto_alg *alg = tfm->__crt_alg;
-	struct spacc_alg *spacc_alg = to_spacc_alg(alg);
+	struct spacc_ablk_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	struct spacc_alg *spacc_alg = to_spacc_skcipher(alg);
 	struct spacc_engine *engine = spacc_alg->engine;
 
 	ctx->generic.flags = spacc_alg->type;
 	ctx->generic.engine = engine;
-	if (alg->cra_flags & CRYPTO_ALG_NEED_FALLBACK) {
+	if (alg->base.cra_flags & CRYPTO_ALG_NEED_FALLBACK) {
 		ctx->sw_cipher = crypto_alloc_sync_skcipher(
-			alg->cra_name, 0, CRYPTO_ALG_NEED_FALLBACK);
+			alg->base.cra_name, 0, CRYPTO_ALG_NEED_FALLBACK);
 		if (IS_ERR(ctx->sw_cipher)) {
 			dev_warn(engine->dev, "failed to allocate fallback for %s\n",
-				 alg->cra_name);
+				 alg->base.cra_name);
 			return PTR_ERR(ctx->sw_cipher);
 		}
 	}
 	ctx->generic.key_offs = spacc_alg->key_offs;
 	ctx->generic.iv_offs = spacc_alg->iv_offs;
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct spacc_req);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct spacc_req));
 
 	return 0;
 }
 
-static void spacc_ablk_cra_exit(struct crypto_tfm *tfm)
+static void spacc_ablk_exit_tfm(struct crypto_skcipher *tfm)
 {
-	struct spacc_ablk_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct spacc_ablk_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	crypto_free_sync_skcipher(ctx->sw_cipher);
 }
 
-static int spacc_ablk_encrypt(struct ablkcipher_request *req)
+static int spacc_ablk_encrypt(struct skcipher_request *req)
 {
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(req);
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
-	struct spacc_alg *alg = to_spacc_alg(tfm->__crt_alg);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(req);
+	struct skcipher_alg *alg = crypto_skcipher_alg(cipher);
+	struct spacc_alg *spacc_alg = to_spacc_skcipher(alg);
 
-	return spacc_ablk_setup(req, alg->type, 1);
+	return spacc_ablk_setup(req, spacc_alg->type, 1);
 }
 
-static int spacc_ablk_decrypt(struct ablkcipher_request *req)
+static int spacc_ablk_decrypt(struct skcipher_request *req)
 {
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(req);
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
-	struct spacc_alg *alg = to_spacc_alg(tfm->__crt_alg);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(req);
+	struct skcipher_alg *alg = crypto_skcipher_alg(cipher);
+	struct spacc_alg *spacc_alg = to_spacc_skcipher(alg);
 
-	return spacc_ablk_setup(req, alg->type, 0);
+	return spacc_ablk_setup(req, spacc_alg->type, 0);
 }
 
 static inline int spacc_fifo_stat_empty(struct spacc_engine *engine)
@@ -1233,27 +1234,24 @@ static struct spacc_alg ipsec_engine_algs[] = {
 		.key_offs = 0,
 		.iv_offs = AES_MAX_KEY_SIZE,
 		.alg = {
-			.cra_name = "cbc(aes)",
-			.cra_driver_name = "cbc-aes-picoxcell",
-			.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-				     CRYPTO_ALG_KERN_DRIVER_ONLY |
-				     CRYPTO_ALG_ASYNC |
-				     CRYPTO_ALG_NEED_FALLBACK,
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct spacc_ablk_ctx),
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_module = THIS_MODULE,
-			.cra_ablkcipher = {
-				.setkey = spacc_aes_setkey,
-				.encrypt = spacc_ablk_encrypt,
-				.decrypt = spacc_ablk_decrypt,
-				.min_keysize = AES_MIN_KEY_SIZE,
-				.max_keysize = AES_MAX_KEY_SIZE,
-				.ivsize = AES_BLOCK_SIZE,
-			},
-			.cra_init = spacc_ablk_cra_init,
-			.cra_exit = spacc_ablk_cra_exit,
+			.base.cra_name		= "cbc(aes)",
+			.base.cra_driver_name	= "cbc-aes-picoxcell",
+			.base.cra_priority	= SPACC_CRYPTO_ALG_PRIORITY,
+			.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
+						  CRYPTO_ALG_ASYNC |
+						  CRYPTO_ALG_NEED_FALLBACK,
+			.base.cra_blocksize	= AES_BLOCK_SIZE,
+			.base.cra_ctxsize	= sizeof(struct spacc_ablk_ctx),
+			.base.cra_module	= THIS_MODULE,
+
+			.setkey			= spacc_aes_setkey,
+			.encrypt 		= spacc_ablk_encrypt,
+			.decrypt 		= spacc_ablk_decrypt,
+			.min_keysize 		= AES_MIN_KEY_SIZE,
+			.max_keysize 		= AES_MAX_KEY_SIZE,
+			.ivsize			= AES_BLOCK_SIZE,
+			.init			= spacc_ablk_init_tfm,
+			.exit			= spacc_ablk_exit_tfm,
 		},
 	},
 	{
@@ -1261,25 +1259,23 @@ static struct spacc_alg ipsec_engine_algs[] = {
 		.iv_offs = AES_MAX_KEY_SIZE,
 		.ctrl_default = SPA_CTRL_CIPH_ALG_AES | SPA_CTRL_CIPH_MODE_ECB,
 		.alg = {
-			.cra_name = "ecb(aes)",
-			.cra_driver_name = "ecb-aes-picoxcell",
-			.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-				CRYPTO_ALG_KERN_DRIVER_ONLY |
-				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct spacc_ablk_ctx),
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_module = THIS_MODULE,
-			.cra_ablkcipher = {
-				.setkey = spacc_aes_setkey,
-				.encrypt = spacc_ablk_encrypt,
-				.decrypt = spacc_ablk_decrypt,
-				.min_keysize = AES_MIN_KEY_SIZE,
-				.max_keysize = AES_MAX_KEY_SIZE,
-			},
-			.cra_init = spacc_ablk_cra_init,
-			.cra_exit = spacc_ablk_cra_exit,
+			.base.cra_name		= "ecb(aes)",
+			.base.cra_driver_name	= "ecb-aes-picoxcell",
+			.base.cra_priority	= SPACC_CRYPTO_ALG_PRIORITY,
+			.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
+						  CRYPTO_ALG_ASYNC |
+						  CRYPTO_ALG_NEED_FALLBACK,
+			.base.cra_blocksize	= AES_BLOCK_SIZE,
+			.base.cra_ctxsize	= sizeof(struct spacc_ablk_ctx),
+			.base.cra_module	= THIS_MODULE,
+
+			.setkey			= spacc_aes_setkey,
+			.encrypt 		= spacc_ablk_encrypt,
+			.decrypt 		= spacc_ablk_decrypt,
+			.min_keysize 		= AES_MIN_KEY_SIZE,
+			.max_keysize 		= AES_MAX_KEY_SIZE,
+			.init			= spacc_ablk_init_tfm,
+			.exit			= spacc_ablk_exit_tfm,
 		},
 	},
 	{
@@ -1287,26 +1283,23 @@ static struct spacc_alg ipsec_engine_algs[] = {
 		.iv_offs = 0,
 		.ctrl_default = SPA_CTRL_CIPH_ALG_DES | SPA_CTRL_CIPH_MODE_CBC,
 		.alg = {
-			.cra_name = "cbc(des)",
-			.cra_driver_name = "cbc-des-picoxcell",
-			.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-					CRYPTO_ALG_ASYNC |
-					CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct spacc_ablk_ctx),
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_module = THIS_MODULE,
-			.cra_ablkcipher = {
-				.setkey = spacc_des_setkey,
-				.encrypt = spacc_ablk_encrypt,
-				.decrypt = spacc_ablk_decrypt,
-				.min_keysize = DES_KEY_SIZE,
-				.max_keysize = DES_KEY_SIZE,
-				.ivsize = DES_BLOCK_SIZE,
-			},
-			.cra_init = spacc_ablk_cra_init,
-			.cra_exit = spacc_ablk_cra_exit,
+			.base.cra_name		= "cbc(des)",
+			.base.cra_driver_name	= "cbc-des-picoxcell",
+			.base.cra_priority	= SPACC_CRYPTO_ALG_PRIORITY,
+			.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
+						  CRYPTO_ALG_ASYNC,
+			.base.cra_blocksize	= DES_BLOCK_SIZE,
+			.base.cra_ctxsize	= sizeof(struct spacc_ablk_ctx),
+			.base.cra_module	= THIS_MODULE,
+
+			.setkey			= spacc_des_setkey,
+			.encrypt		= spacc_ablk_encrypt,
+			.decrypt		= spacc_ablk_decrypt,
+			.min_keysize		= DES_KEY_SIZE,
+			.max_keysize		= DES_KEY_SIZE,
+			.ivsize			= DES_BLOCK_SIZE,
+			.init			= spacc_ablk_init_tfm,
+			.exit			= spacc_ablk_exit_tfm,
 		},
 	},
 	{
@@ -1314,25 +1307,22 @@ static struct spacc_alg ipsec_engine_algs[] = {
 		.iv_offs = 0,
 		.ctrl_default = SPA_CTRL_CIPH_ALG_DES | SPA_CTRL_CIPH_MODE_ECB,
 		.alg = {
-			.cra_name = "ecb(des)",
-			.cra_driver_name = "ecb-des-picoxcell",
-			.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-					CRYPTO_ALG_ASYNC |
-					CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct spacc_ablk_ctx),
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_module = THIS_MODULE,
-			.cra_ablkcipher = {
-				.setkey = spacc_des_setkey,
-				.encrypt = spacc_ablk_encrypt,
-				.decrypt = spacc_ablk_decrypt,
-				.min_keysize = DES_KEY_SIZE,
-				.max_keysize = DES_KEY_SIZE,
-			},
-			.cra_init = spacc_ablk_cra_init,
-			.cra_exit = spacc_ablk_cra_exit,
+			.base.cra_name		= "ecb(des)",
+			.base.cra_driver_name	= "ecb-des-picoxcell",
+			.base.cra_priority	= SPACC_CRYPTO_ALG_PRIORITY,
+			.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
+						  CRYPTO_ALG_ASYNC,
+			.base.cra_blocksize	= DES_BLOCK_SIZE,
+			.base.cra_ctxsize	= sizeof(struct spacc_ablk_ctx),
+			.base.cra_module	= THIS_MODULE,
+
+			.setkey			= spacc_des_setkey,
+			.encrypt		= spacc_ablk_encrypt,
+			.decrypt		= spacc_ablk_decrypt,
+			.min_keysize		= DES_KEY_SIZE,
+			.max_keysize		= DES_KEY_SIZE,
+			.init			= spacc_ablk_init_tfm,
+			.exit			= spacc_ablk_exit_tfm,
 		},
 	},
 	{
@@ -1340,26 +1330,23 @@ static struct spacc_alg ipsec_engine_algs[] = {
 		.iv_offs = 0,
 		.ctrl_default = SPA_CTRL_CIPH_ALG_DES | SPA_CTRL_CIPH_MODE_CBC,
 		.alg = {
-			.cra_name = "cbc(des3_ede)",
-			.cra_driver_name = "cbc-des3-ede-picoxcell",
-			.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-					CRYPTO_ALG_ASYNC |
-					CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct spacc_ablk_ctx),
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_module = THIS_MODULE,
-			.cra_ablkcipher = {
-				.setkey = spacc_des3_setkey,
-				.encrypt = spacc_ablk_encrypt,
-				.decrypt = spacc_ablk_decrypt,
-				.min_keysize = DES3_EDE_KEY_SIZE,
-				.max_keysize = DES3_EDE_KEY_SIZE,
-				.ivsize = DES3_EDE_BLOCK_SIZE,
-			},
-			.cra_init = spacc_ablk_cra_init,
-			.cra_exit = spacc_ablk_cra_exit,
+			.base.cra_name		= "cbc(des3_ede)",
+			.base.cra_driver_name	= "cbc-des3-ede-picoxcell",
+			.base.cra_priority	= SPACC_CRYPTO_ALG_PRIORITY,
+			.base.cra_flags		= CRYPTO_ALG_ASYNC |
+						  CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+			.base.cra_ctxsize	= sizeof(struct spacc_ablk_ctx),
+			.base.cra_module	= THIS_MODULE,
+
+			.setkey			= spacc_des3_setkey,
+			.encrypt		= spacc_ablk_encrypt,
+			.decrypt		= spacc_ablk_decrypt,
+			.min_keysize		= DES3_EDE_KEY_SIZE,
+			.max_keysize		= DES3_EDE_KEY_SIZE,
+			.ivsize			= DES3_EDE_BLOCK_SIZE,
+			.init			= spacc_ablk_init_tfm,
+			.exit			= spacc_ablk_exit_tfm,
 		},
 	},
 	{
@@ -1367,25 +1354,22 @@ static struct spacc_alg ipsec_engine_algs[] = {
 		.iv_offs = 0,
 		.ctrl_default = SPA_CTRL_CIPH_ALG_DES | SPA_CTRL_CIPH_MODE_ECB,
 		.alg = {
-			.cra_name = "ecb(des3_ede)",
-			.cra_driver_name = "ecb-des3-ede-picoxcell",
-			.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-					CRYPTO_ALG_ASYNC |
-					CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct spacc_ablk_ctx),
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_module = THIS_MODULE,
-			.cra_ablkcipher = {
-				.setkey = spacc_des3_setkey,
-				.encrypt = spacc_ablk_encrypt,
-				.decrypt = spacc_ablk_decrypt,
-				.min_keysize = DES3_EDE_KEY_SIZE,
-				.max_keysize = DES3_EDE_KEY_SIZE,
-			},
-			.cra_init = spacc_ablk_cra_init,
-			.cra_exit = spacc_ablk_cra_exit,
+			.base.cra_name		= "ecb(des3_ede)",
+			.base.cra_driver_name	= "ecb-des3-ede-picoxcell",
+			.base.cra_priority	= SPACC_CRYPTO_ALG_PRIORITY,
+			.base.cra_flags		= CRYPTO_ALG_ASYNC |
+						  CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+			.base.cra_ctxsize	= sizeof(struct spacc_ablk_ctx),
+			.base.cra_module	= THIS_MODULE,
+
+			.setkey			= spacc_des3_setkey,
+			.encrypt		= spacc_ablk_encrypt,
+			.decrypt		= spacc_ablk_decrypt,
+			.min_keysize		= DES3_EDE_KEY_SIZE,
+			.max_keysize		= DES3_EDE_KEY_SIZE,
+			.init			= spacc_ablk_init_tfm,
+			.exit			= spacc_ablk_exit_tfm,
 		},
 	},
 };
@@ -1581,25 +1565,23 @@ static struct spacc_alg l2_engine_algs[] = {
 		.ctrl_default = SPA_CTRL_CIPH_ALG_KASUMI |
 				SPA_CTRL_CIPH_MODE_F8,
 		.alg = {
-			.cra_name = "f8(kasumi)",
-			.cra_driver_name = "f8-kasumi-picoxcell",
-			.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-			.cra_flags = CRYPTO_ALG_ASYNC |
-					CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = 8,
-			.cra_ctxsize = sizeof(struct spacc_ablk_ctx),
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_module = THIS_MODULE,
-			.cra_ablkcipher = {
-				.setkey = spacc_kasumi_f8_setkey,
-				.encrypt = spacc_ablk_encrypt,
-				.decrypt = spacc_ablk_decrypt,
-				.min_keysize = 16,
-				.max_keysize = 16,
-				.ivsize = 8,
-			},
-			.cra_init = spacc_ablk_cra_init,
-			.cra_exit = spacc_ablk_cra_exit,
+			.base.cra_name		= "f8(kasumi)",
+			.base.cra_driver_name	= "f8-kasumi-picoxcell",
+			.base.cra_priority	= SPACC_CRYPTO_ALG_PRIORITY,
+			.base.cra_flags		= CRYPTO_ALG_ASYNC |
+						  CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.base.cra_blocksize	= 8,
+			.base.cra_ctxsize	= sizeof(struct spacc_ablk_ctx),
+			.base.cra_module	= THIS_MODULE,
+
+			.setkey			= spacc_kasumi_f8_setkey,
+			.encrypt		= spacc_ablk_encrypt,
+			.decrypt		= spacc_ablk_decrypt,
+			.min_keysize		= 16,
+			.max_keysize		= 16,
+			.ivsize			= 8,
+			.init			= spacc_ablk_init_tfm,
+			.exit			= spacc_ablk_exit_tfm,
 		},
 	},
 };
@@ -1721,7 +1703,7 @@ static int spacc_probe(struct platform_device *pdev)
 	INIT_LIST_HEAD(&engine->registered_algs);
 	for (i = 0; i < engine->num_algs; ++i) {
 		engine->algs[i].engine = engine;
-		err = crypto_register_alg(&engine->algs[i].alg);
+		err = crypto_register_skcipher(&engine->algs[i].alg);
 		if (!err) {
 			list_add_tail(&engine->algs[i].entry,
 				      &engine->registered_algs);
@@ -1729,10 +1711,10 @@ static int spacc_probe(struct platform_device *pdev)
 		}
 		if (err)
 			dev_err(engine->dev, "failed to register alg \"%s\"\n",
-				engine->algs[i].alg.cra_name);
+				engine->algs[i].alg.base.cra_name);
 		else
 			dev_dbg(engine->dev, "registered alg \"%s\"\n",
-				engine->algs[i].alg.cra_name);
+				engine->algs[i].alg.base.cra_name);
 	}
 
 	INIT_LIST_HEAD(&engine->registered_aeads);
@@ -1781,7 +1763,7 @@ static int spacc_remove(struct platform_device *pdev)
 
 	list_for_each_entry_safe(alg, next, &engine->registered_algs, entry) {
 		list_del(&alg->entry);
-		crypto_unregister_alg(&alg->alg);
+		crypto_unregister_skcipher(&alg->alg);
 	}
 
 	clk_disable_unprepare(engine->clk);
diff --git a/drivers/crypto/qat/Kconfig b/drivers/crypto/qat/Kconfig
index 6ab7e5a88756..2006322345de 100644
--- a/drivers/crypto/qat/Kconfig
+++ b/drivers/crypto/qat/Kconfig
@@ -3,7 +3,7 @@ config CRYPTO_DEV_QAT
 	tristate
 	select CRYPTO_AEAD
 	select CRYPTO_AUTHENC
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_AKCIPHER
 	select CRYPTO_DH
 	select CRYPTO_HMAC
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index b50eb55f8f57..35bca76b640f 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -48,6 +48,7 @@
 #include <linux/slab.h>
 #include <linux/crypto.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
 #include <crypto/aes.h>
 #include <crypto/sha.h>
 #include <crypto/hash.h>
@@ -122,7 +123,7 @@ struct qat_alg_aead_ctx {
 	char opad[SHA512_BLOCK_SIZE];
 };
 
-struct qat_alg_ablkcipher_ctx {
+struct qat_alg_skcipher_ctx {
 	struct icp_qat_hw_cipher_algo_blk *enc_cd;
 	struct icp_qat_hw_cipher_algo_blk *dec_cd;
 	dma_addr_t enc_cd_paddr;
@@ -130,7 +131,7 @@ struct qat_alg_ablkcipher_ctx {
 	struct icp_qat_fw_la_bulk_req enc_fw_req;
 	struct icp_qat_fw_la_bulk_req dec_fw_req;
 	struct qat_crypto_instance *inst;
-	struct crypto_tfm *tfm;
+	struct crypto_skcipher *tfm;
 };
 
 static int qat_get_inter_state_size(enum icp_qat_hw_auth_algo qat_hash_alg)
@@ -463,10 +464,10 @@ static int qat_alg_aead_init_dec_session(struct crypto_aead *aead_tfm,
 	return 0;
 }
 
-static void qat_alg_ablkcipher_init_com(struct qat_alg_ablkcipher_ctx *ctx,
-					struct icp_qat_fw_la_bulk_req *req,
-					struct icp_qat_hw_cipher_algo_blk *cd,
-					const uint8_t *key, unsigned int keylen)
+static void qat_alg_skcipher_init_com(struct qat_alg_skcipher_ctx *ctx,
+				      struct icp_qat_fw_la_bulk_req *req,
+				      struct icp_qat_hw_cipher_algo_blk *cd,
+				      const uint8_t *key, unsigned int keylen)
 {
 	struct icp_qat_fw_comn_req_hdr_cd_pars *cd_pars = &req->cd_pars;
 	struct icp_qat_fw_comn_req_hdr *header = &req->comn_hdr;
@@ -485,28 +486,28 @@ static void qat_alg_ablkcipher_init_com(struct qat_alg_ablkcipher_ctx *ctx,
 	ICP_QAT_FW_COMN_NEXT_ID_SET(cd_ctrl, ICP_QAT_FW_SLICE_DRAM_WR);
 }
 
-static void qat_alg_ablkcipher_init_enc(struct qat_alg_ablkcipher_ctx *ctx,
-					int alg, const uint8_t *key,
-					unsigned int keylen, int mode)
+static void qat_alg_skcipher_init_enc(struct qat_alg_skcipher_ctx *ctx,
+				      int alg, const uint8_t *key,
+				      unsigned int keylen, int mode)
 {
 	struct icp_qat_hw_cipher_algo_blk *enc_cd = ctx->enc_cd;
 	struct icp_qat_fw_la_bulk_req *req = &ctx->enc_fw_req;
 	struct icp_qat_fw_comn_req_hdr_cd_pars *cd_pars = &req->cd_pars;
 
-	qat_alg_ablkcipher_init_com(ctx, req, enc_cd, key, keylen);
+	qat_alg_skcipher_init_com(ctx, req, enc_cd, key, keylen);
 	cd_pars->u.s.content_desc_addr = ctx->enc_cd_paddr;
 	enc_cd->aes.cipher_config.val = QAT_AES_HW_CONFIG_ENC(alg, mode);
 }
 
-static void qat_alg_ablkcipher_init_dec(struct qat_alg_ablkcipher_ctx *ctx,
-					int alg, const uint8_t *key,
-					unsigned int keylen, int mode)
+static void qat_alg_skcipher_init_dec(struct qat_alg_skcipher_ctx *ctx,
+				      int alg, const uint8_t *key,
+				      unsigned int keylen, int mode)
 {
 	struct icp_qat_hw_cipher_algo_blk *dec_cd = ctx->dec_cd;
 	struct icp_qat_fw_la_bulk_req *req = &ctx->dec_fw_req;
 	struct icp_qat_fw_comn_req_hdr_cd_pars *cd_pars = &req->cd_pars;
 
-	qat_alg_ablkcipher_init_com(ctx, req, dec_cd, key, keylen);
+	qat_alg_skcipher_init_com(ctx, req, dec_cd, key, keylen);
 	cd_pars->u.s.content_desc_addr = ctx->dec_cd_paddr;
 
 	if (mode != ICP_QAT_HW_CIPHER_CTR_MODE)
@@ -577,21 +578,21 @@ error:
 	return -EFAULT;
 }
 
-static int qat_alg_ablkcipher_init_sessions(struct qat_alg_ablkcipher_ctx *ctx,
-					    const uint8_t *key,
-					    unsigned int keylen,
-					    int mode)
+static int qat_alg_skcipher_init_sessions(struct qat_alg_skcipher_ctx *ctx,
+					  const uint8_t *key,
+					  unsigned int keylen,
+					  int mode)
 {
 	int alg;
 
 	if (qat_alg_validate_key(keylen, &alg, mode))
 		goto bad_key;
 
-	qat_alg_ablkcipher_init_enc(ctx, alg, key, keylen, mode);
-	qat_alg_ablkcipher_init_dec(ctx, alg, key, keylen, mode);
+	qat_alg_skcipher_init_enc(ctx, alg, key, keylen, mode);
+	qat_alg_skcipher_init_dec(ctx, alg, key, keylen, mode);
 	return 0;
 bad_key:
-	crypto_tfm_set_flags(ctx->tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	crypto_skcipher_set_flags(ctx->tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 	return -EINVAL;
 }
 
@@ -832,12 +833,12 @@ static void qat_aead_alg_callback(struct icp_qat_fw_la_resp *qat_resp,
 	areq->base.complete(&areq->base, res);
 }
 
-static void qat_ablkcipher_alg_callback(struct icp_qat_fw_la_resp *qat_resp,
-					struct qat_crypto_request *qat_req)
+static void qat_skcipher_alg_callback(struct icp_qat_fw_la_resp *qat_resp,
+				      struct qat_crypto_request *qat_req)
 {
-	struct qat_alg_ablkcipher_ctx *ctx = qat_req->ablkcipher_ctx;
+	struct qat_alg_skcipher_ctx *ctx = qat_req->skcipher_ctx;
 	struct qat_crypto_instance *inst = ctx->inst;
-	struct ablkcipher_request *areq = qat_req->ablkcipher_req;
+	struct skcipher_request *sreq = qat_req->skcipher_req;
 	uint8_t stat_filed = qat_resp->comn_resp.comn_status;
 	struct device *dev = &GET_DEV(ctx->inst->accel_dev);
 	int res = 0, qat_res = ICP_QAT_FW_COMN_RESP_CRYPTO_STAT_GET(stat_filed);
@@ -846,11 +847,11 @@ static void qat_ablkcipher_alg_callback(struct icp_qat_fw_la_resp *qat_resp,
 	if (unlikely(qat_res != ICP_QAT_FW_COMN_STATUS_FLAG_OK))
 		res = -EINVAL;
 
-	memcpy(areq->info, qat_req->iv, AES_BLOCK_SIZE);
+	memcpy(sreq->iv, qat_req->iv, AES_BLOCK_SIZE);
 	dma_free_coherent(dev, AES_BLOCK_SIZE, qat_req->iv,
 			  qat_req->iv_paddr);
 
-	areq->base.complete(&areq->base, res);
+	sreq->base.complete(&sreq->base, res);
 }
 
 void qat_alg_callback(void *resp)
@@ -949,21 +950,21 @@ static int qat_alg_aead_enc(struct aead_request *areq)
 	return -EINPROGRESS;
 }
 
-static int qat_alg_ablkcipher_rekey(struct qat_alg_ablkcipher_ctx *ctx,
-				    const u8 *key, unsigned int keylen,
-				    int mode)
+static int qat_alg_skcipher_rekey(struct qat_alg_skcipher_ctx *ctx,
+				  const u8 *key, unsigned int keylen,
+				  int mode)
 {
 	memset(ctx->enc_cd, 0, sizeof(*ctx->enc_cd));
 	memset(ctx->dec_cd, 0, sizeof(*ctx->dec_cd));
 	memset(&ctx->enc_fw_req, 0, sizeof(ctx->enc_fw_req));
 	memset(&ctx->dec_fw_req, 0, sizeof(ctx->dec_fw_req));
 
-	return qat_alg_ablkcipher_init_sessions(ctx, key, keylen, mode);
+	return qat_alg_skcipher_init_sessions(ctx, key, keylen, mode);
 }
 
-static int qat_alg_ablkcipher_newkey(struct qat_alg_ablkcipher_ctx *ctx,
-				     const u8 *key, unsigned int keylen,
-				     int mode)
+static int qat_alg_skcipher_newkey(struct qat_alg_skcipher_ctx *ctx,
+				   const u8 *key, unsigned int keylen,
+				   int mode)
 {
 	struct qat_crypto_instance *inst = NULL;
 	struct device *dev;
@@ -990,7 +991,7 @@ static int qat_alg_ablkcipher_newkey(struct qat_alg_ablkcipher_ctx *ctx,
 		goto out_free_enc;
 	}
 
-	ret = qat_alg_ablkcipher_init_sessions(ctx, key, keylen, mode);
+	ret = qat_alg_skcipher_init_sessions(ctx, key, keylen, mode);
 	if (ret)
 		goto out_free_all;
 
@@ -1012,51 +1013,51 @@ out_free_instance:
 	return ret;
 }
 
-static int qat_alg_ablkcipher_setkey(struct crypto_ablkcipher *tfm,
-				     const u8 *key, unsigned int keylen,
-				     int mode)
+static int qat_alg_skcipher_setkey(struct crypto_skcipher *tfm,
+				   const u8 *key, unsigned int keylen,
+				   int mode)
 {
-	struct qat_alg_ablkcipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct qat_alg_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	if (ctx->enc_cd)
-		return qat_alg_ablkcipher_rekey(ctx, key, keylen, mode);
+		return qat_alg_skcipher_rekey(ctx, key, keylen, mode);
 	else
-		return qat_alg_ablkcipher_newkey(ctx, key, keylen, mode);
+		return qat_alg_skcipher_newkey(ctx, key, keylen, mode);
 }
 
-static int qat_alg_ablkcipher_cbc_setkey(struct crypto_ablkcipher *tfm,
-					 const u8 *key, unsigned int keylen)
+static int qat_alg_skcipher_cbc_setkey(struct crypto_skcipher *tfm,
+				       const u8 *key, unsigned int keylen)
 {
-	return qat_alg_ablkcipher_setkey(tfm, key, keylen,
-					 ICP_QAT_HW_CIPHER_CBC_MODE);
+	return qat_alg_skcipher_setkey(tfm, key, keylen,
+				       ICP_QAT_HW_CIPHER_CBC_MODE);
 }
 
-static int qat_alg_ablkcipher_ctr_setkey(struct crypto_ablkcipher *tfm,
-					 const u8 *key, unsigned int keylen)
+static int qat_alg_skcipher_ctr_setkey(struct crypto_skcipher *tfm,
+				       const u8 *key, unsigned int keylen)
 {
-	return qat_alg_ablkcipher_setkey(tfm, key, keylen,
-					 ICP_QAT_HW_CIPHER_CTR_MODE);
+	return qat_alg_skcipher_setkey(tfm, key, keylen,
+				       ICP_QAT_HW_CIPHER_CTR_MODE);
 }
 
-static int qat_alg_ablkcipher_xts_setkey(struct crypto_ablkcipher *tfm,
-					 const u8 *key, unsigned int keylen)
+static int qat_alg_skcipher_xts_setkey(struct crypto_skcipher *tfm,
+				       const u8 *key, unsigned int keylen)
 {
-	return qat_alg_ablkcipher_setkey(tfm, key, keylen,
-					 ICP_QAT_HW_CIPHER_XTS_MODE);
+	return qat_alg_skcipher_setkey(tfm, key, keylen,
+				       ICP_QAT_HW_CIPHER_XTS_MODE);
 }
 
-static int qat_alg_ablkcipher_encrypt(struct ablkcipher_request *req)
+static int qat_alg_skcipher_encrypt(struct skcipher_request *req)
 {
-	struct crypto_ablkcipher *atfm = crypto_ablkcipher_reqtfm(req);
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(atfm);
-	struct qat_alg_ablkcipher_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct qat_crypto_request *qat_req = ablkcipher_request_ctx(req);
+	struct crypto_skcipher *stfm = crypto_skcipher_reqtfm(req);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(stfm);
+	struct qat_alg_skcipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct qat_crypto_request *qat_req = skcipher_request_ctx(req);
 	struct icp_qat_fw_la_cipher_req_params *cipher_param;
 	struct icp_qat_fw_la_bulk_req *msg;
 	struct device *dev = &GET_DEV(ctx->inst->accel_dev);
 	int ret, ctr = 0;
 
-	if (req->nbytes == 0)
+	if (req->cryptlen == 0)
 		return 0;
 
 	qat_req->iv = dma_alloc_coherent(dev, AES_BLOCK_SIZE,
@@ -1073,17 +1074,17 @@ static int qat_alg_ablkcipher_encrypt(struct ablkcipher_request *req)
 
 	msg = &qat_req->req;
 	*msg = ctx->enc_fw_req;
-	qat_req->ablkcipher_ctx = ctx;
-	qat_req->ablkcipher_req = req;
-	qat_req->cb = qat_ablkcipher_alg_callback;
+	qat_req->skcipher_ctx = ctx;
+	qat_req->skcipher_req = req;
+	qat_req->cb = qat_skcipher_alg_callback;
 	qat_req->req.comn_mid.opaque_data = (uint64_t)(__force long)qat_req;
 	qat_req->req.comn_mid.src_data_addr = qat_req->buf.blp;
 	qat_req->req.comn_mid.dest_data_addr = qat_req->buf.bloutp;
 	cipher_param = (void *)&qat_req->req.serv_specif_rqpars;
-	cipher_param->cipher_length = req->nbytes;
+	cipher_param->cipher_length = req->cryptlen;
 	cipher_param->cipher_offset = 0;
 	cipher_param->u.s.cipher_IV_ptr = qat_req->iv_paddr;
-	memcpy(qat_req->iv, req->info, AES_BLOCK_SIZE);
+	memcpy(qat_req->iv, req->iv, AES_BLOCK_SIZE);
 	do {
 		ret = adf_send_message(ctx->inst->sym_tx, (uint32_t *)msg);
 	} while (ret == -EAGAIN && ctr++ < 10);
@@ -1097,26 +1098,26 @@ static int qat_alg_ablkcipher_encrypt(struct ablkcipher_request *req)
 	return -EINPROGRESS;
 }
 
-static int qat_alg_ablkcipher_blk_encrypt(struct ablkcipher_request *req)
+static int qat_alg_skcipher_blk_encrypt(struct skcipher_request *req)
 {
-	if (req->nbytes % AES_BLOCK_SIZE != 0)
+	if (req->cryptlen % AES_BLOCK_SIZE != 0)
 		return -EINVAL;
 
-	return qat_alg_ablkcipher_encrypt(req);
+	return qat_alg_skcipher_encrypt(req);
 }
 
-static int qat_alg_ablkcipher_decrypt(struct ablkcipher_request *req)
+static int qat_alg_skcipher_decrypt(struct skcipher_request *req)
 {
-	struct crypto_ablkcipher *atfm = crypto_ablkcipher_reqtfm(req);
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(atfm);
-	struct qat_alg_ablkcipher_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct qat_crypto_request *qat_req = ablkcipher_request_ctx(req);
+	struct crypto_skcipher *stfm = crypto_skcipher_reqtfm(req);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(stfm);
+	struct qat_alg_skcipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct qat_crypto_request *qat_req = skcipher_request_ctx(req);
 	struct icp_qat_fw_la_cipher_req_params *cipher_param;
 	struct icp_qat_fw_la_bulk_req *msg;
 	struct device *dev = &GET_DEV(ctx->inst->accel_dev);
 	int ret, ctr = 0;
 
-	if (req->nbytes == 0)
+	if (req->cryptlen == 0)
 		return 0;
 
 	qat_req->iv = dma_alloc_coherent(dev, AES_BLOCK_SIZE,
@@ -1133,17 +1134,17 @@ static int qat_alg_ablkcipher_decrypt(struct ablkcipher_request *req)
 
 	msg = &qat_req->req;
 	*msg = ctx->dec_fw_req;
-	qat_req->ablkcipher_ctx = ctx;
-	qat_req->ablkcipher_req = req;
-	qat_req->cb = qat_ablkcipher_alg_callback;
+	qat_req->skcipher_ctx = ctx;
+	qat_req->skcipher_req = req;
+	qat_req->cb = qat_skcipher_alg_callback;
 	qat_req->req.comn_mid.opaque_data = (uint64_t)(__force long)qat_req;
 	qat_req->req.comn_mid.src_data_addr = qat_req->buf.blp;
 	qat_req->req.comn_mid.dest_data_addr = qat_req->buf.bloutp;
 	cipher_param = (void *)&qat_req->req.serv_specif_rqpars;
-	cipher_param->cipher_length = req->nbytes;
+	cipher_param->cipher_length = req->cryptlen;
 	cipher_param->cipher_offset = 0;
 	cipher_param->u.s.cipher_IV_ptr = qat_req->iv_paddr;
-	memcpy(qat_req->iv, req->info, AES_BLOCK_SIZE);
+	memcpy(qat_req->iv, req->iv, AES_BLOCK_SIZE);
 	do {
 		ret = adf_send_message(ctx->inst->sym_tx, (uint32_t *)msg);
 	} while (ret == -EAGAIN && ctr++ < 10);
@@ -1157,12 +1158,12 @@ static int qat_alg_ablkcipher_decrypt(struct ablkcipher_request *req)
 	return -EINPROGRESS;
 }
 
-static int qat_alg_ablkcipher_blk_decrypt(struct ablkcipher_request *req)
+static int qat_alg_skcipher_blk_decrypt(struct skcipher_request *req)
 {
-	if (req->nbytes % AES_BLOCK_SIZE != 0)
+	if (req->cryptlen % AES_BLOCK_SIZE != 0)
 		return -EINVAL;
 
-	return qat_alg_ablkcipher_decrypt(req);
+	return qat_alg_skcipher_decrypt(req);
 }
 static int qat_alg_aead_init(struct crypto_aead *tfm,
 			     enum icp_qat_hw_auth_algo hash,
@@ -1218,18 +1219,18 @@ static void qat_alg_aead_exit(struct crypto_aead *tfm)
 	qat_crypto_put_instance(inst);
 }
 
-static int qat_alg_ablkcipher_init(struct crypto_tfm *tfm)
+static int qat_alg_skcipher_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct qat_alg_ablkcipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct qat_alg_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct qat_crypto_request);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct qat_crypto_request));
 	ctx->tfm = tfm;
 	return 0;
 }
 
-static void qat_alg_ablkcipher_exit(struct crypto_tfm *tfm)
+static void qat_alg_skcipher_exit_tfm(struct crypto_skcipher *tfm)
 {
-	struct qat_alg_ablkcipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct qat_alg_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm);
 	struct qat_crypto_instance *inst = ctx->inst;
 	struct device *dev;
 
@@ -1308,92 +1309,75 @@ static struct aead_alg qat_aeads[] = { {
 	.maxauthsize = SHA512_DIGEST_SIZE,
 } };
 
-static struct crypto_alg qat_algs[] = { {
-	.cra_name = "cbc(aes)",
-	.cra_driver_name = "qat_aes_cbc",
-	.cra_priority = 4001,
-	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize = AES_BLOCK_SIZE,
-	.cra_ctxsize = sizeof(struct qat_alg_ablkcipher_ctx),
-	.cra_alignmask = 0,
-	.cra_type = &crypto_ablkcipher_type,
-	.cra_module = THIS_MODULE,
-	.cra_init = qat_alg_ablkcipher_init,
-	.cra_exit = qat_alg_ablkcipher_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.setkey = qat_alg_ablkcipher_cbc_setkey,
-			.decrypt = qat_alg_ablkcipher_blk_decrypt,
-			.encrypt = qat_alg_ablkcipher_blk_encrypt,
-			.min_keysize = AES_MIN_KEY_SIZE,
-			.max_keysize = AES_MAX_KEY_SIZE,
-			.ivsize = AES_BLOCK_SIZE,
-		},
-	},
+static struct skcipher_alg qat_skciphers[] = { {
+	.base.cra_name = "cbc(aes)",
+	.base.cra_driver_name = "qat_aes_cbc",
+	.base.cra_priority = 4001,
+	.base.cra_flags = CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize = AES_BLOCK_SIZE,
+	.base.cra_ctxsize = sizeof(struct qat_alg_skcipher_ctx),
+	.base.cra_alignmask = 0,
+	.base.cra_module = THIS_MODULE,
+
+	.init = qat_alg_skcipher_init_tfm,
+	.exit = qat_alg_skcipher_exit_tfm,
+	.setkey = qat_alg_skcipher_cbc_setkey,
+	.decrypt = qat_alg_skcipher_blk_decrypt,
+	.encrypt = qat_alg_skcipher_blk_encrypt,
+	.min_keysize = AES_MIN_KEY_SIZE,
+	.max_keysize = AES_MAX_KEY_SIZE,
+	.ivsize = AES_BLOCK_SIZE,
 }, {
-	.cra_name = "ctr(aes)",
-	.cra_driver_name = "qat_aes_ctr",
-	.cra_priority = 4001,
-	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize = 1,
-	.cra_ctxsize = sizeof(struct qat_alg_ablkcipher_ctx),
-	.cra_alignmask = 0,
-	.cra_type = &crypto_ablkcipher_type,
-	.cra_module = THIS_MODULE,
-	.cra_init = qat_alg_ablkcipher_init,
-	.cra_exit = qat_alg_ablkcipher_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.setkey = qat_alg_ablkcipher_ctr_setkey,
-			.decrypt = qat_alg_ablkcipher_decrypt,
-			.encrypt = qat_alg_ablkcipher_encrypt,
-			.min_keysize = AES_MIN_KEY_SIZE,
-			.max_keysize = AES_MAX_KEY_SIZE,
-			.ivsize = AES_BLOCK_SIZE,
-		},
-	},
+	.base.cra_name = "ctr(aes)",
+	.base.cra_driver_name = "qat_aes_ctr",
+	.base.cra_priority = 4001,
+	.base.cra_flags = CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize = 1,
+	.base.cra_ctxsize = sizeof(struct qat_alg_skcipher_ctx),
+	.base.cra_alignmask = 0,
+	.base.cra_module = THIS_MODULE,
+
+	.init = qat_alg_skcipher_init_tfm,
+	.exit = qat_alg_skcipher_exit_tfm,
+	.setkey = qat_alg_skcipher_ctr_setkey,
+	.decrypt = qat_alg_skcipher_decrypt,
+	.encrypt = qat_alg_skcipher_encrypt,
+	.min_keysize = AES_MIN_KEY_SIZE,
+	.max_keysize = AES_MAX_KEY_SIZE,
+	.ivsize = AES_BLOCK_SIZE,
 }, {
-	.cra_name = "xts(aes)",
-	.cra_driver_name = "qat_aes_xts",
-	.cra_priority = 4001,
-	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize = AES_BLOCK_SIZE,
-	.cra_ctxsize = sizeof(struct qat_alg_ablkcipher_ctx),
-	.cra_alignmask = 0,
-	.cra_type = &crypto_ablkcipher_type,
-	.cra_module = THIS_MODULE,
-	.cra_init = qat_alg_ablkcipher_init,
-	.cra_exit = qat_alg_ablkcipher_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.setkey = qat_alg_ablkcipher_xts_setkey,
-			.decrypt = qat_alg_ablkcipher_blk_decrypt,
-			.encrypt = qat_alg_ablkcipher_blk_encrypt,
-			.min_keysize = 2 * AES_MIN_KEY_SIZE,
-			.max_keysize = 2 * AES_MAX_KEY_SIZE,
-			.ivsize = AES_BLOCK_SIZE,
-		},
-	},
+	.base.cra_name = "xts(aes)",
+	.base.cra_driver_name = "qat_aes_xts",
+	.base.cra_priority = 4001,
+	.base.cra_flags = CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize = AES_BLOCK_SIZE,
+	.base.cra_ctxsize = sizeof(struct qat_alg_skcipher_ctx),
+	.base.cra_alignmask = 0,
+	.base.cra_module = THIS_MODULE,
+
+	.init = qat_alg_skcipher_init_tfm,
+	.exit = qat_alg_skcipher_exit_tfm,
+	.setkey = qat_alg_skcipher_xts_setkey,
+	.decrypt = qat_alg_skcipher_blk_decrypt,
+	.encrypt = qat_alg_skcipher_blk_encrypt,
+	.min_keysize = 2 * AES_MIN_KEY_SIZE,
+	.max_keysize = 2 * AES_MAX_KEY_SIZE,
+	.ivsize = AES_BLOCK_SIZE,
 } };
 
 int qat_algs_register(void)
 {
-	int ret = 0, i;
+	int ret = 0;
 
 	mutex_lock(&algs_lock);
 	if (++active_devs != 1)
 		goto unlock;
 
-	for (i = 0; i < ARRAY_SIZE(qat_algs); i++)
-		qat_algs[i].cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC;
-
-	ret = crypto_register_algs(qat_algs, ARRAY_SIZE(qat_algs));
+	ret = crypto_register_skciphers(qat_skciphers,
+					ARRAY_SIZE(qat_skciphers));
 	if (ret)
 		goto unlock;
 
-	for (i = 0; i < ARRAY_SIZE(qat_aeads); i++)
-		qat_aeads[i].base.cra_flags = CRYPTO_ALG_ASYNC;
-
 	ret = crypto_register_aeads(qat_aeads, ARRAY_SIZE(qat_aeads));
 	if (ret)
 		goto unreg_algs;
@@ -1403,7 +1387,7 @@ unlock:
 	return ret;
 
 unreg_algs:
-	crypto_unregister_algs(qat_algs, ARRAY_SIZE(qat_algs));
+	crypto_unregister_skciphers(qat_skciphers, ARRAY_SIZE(qat_skciphers));
 	goto unlock;
 }
 
@@ -1414,7 +1398,7 @@ void qat_algs_unregister(void)
 		goto unlock;
 
 	crypto_unregister_aeads(qat_aeads, ARRAY_SIZE(qat_aeads));
-	crypto_unregister_algs(qat_algs, ARRAY_SIZE(qat_algs));
+	crypto_unregister_skciphers(qat_skciphers, ARRAY_SIZE(qat_skciphers));
 
 unlock:
 	mutex_unlock(&algs_lock);
diff --git a/drivers/crypto/qat/qat_common/qat_crypto.h b/drivers/crypto/qat/qat_common/qat_crypto.h
index c77a80020cde..300bb919a33a 100644
--- a/drivers/crypto/qat/qat_common/qat_crypto.h
+++ b/drivers/crypto/qat/qat_common/qat_crypto.h
@@ -79,11 +79,11 @@ struct qat_crypto_request {
 	struct icp_qat_fw_la_bulk_req req;
 	union {
 		struct qat_alg_aead_ctx *aead_ctx;
-		struct qat_alg_ablkcipher_ctx *ablkcipher_ctx;
+		struct qat_alg_skcipher_ctx *skcipher_ctx;
 	};
 	union {
 		struct aead_request *aead_req;
-		struct ablkcipher_request *ablkcipher_req;
+		struct skcipher_request *skcipher_req;
 	};
 	struct qat_crypto_request_buffs buf;
 	void (*cb)(struct icp_qat_fw_la_resp *resp,
diff --git a/drivers/crypto/qce/Makefile b/drivers/crypto/qce/Makefile
index 19a7f899acff..8caa04e1ec43 100644
--- a/drivers/crypto/qce/Makefile
+++ b/drivers/crypto/qce/Makefile
@@ -4,4 +4,4 @@ qcrypto-objs := core.o \
 		common.o \
 		dma.o \
 		sha.o \
-		ablkcipher.o
+		skcipher.o
diff --git a/drivers/crypto/qce/cipher.h b/drivers/crypto/qce/cipher.h
index 5cab8f0706a8..7770660bc853 100644
--- a/drivers/crypto/qce/cipher.h
+++ b/drivers/crypto/qce/cipher.h
@@ -45,12 +45,12 @@ struct qce_cipher_reqctx {
 	unsigned int cryptlen;
 };
 
-static inline struct qce_alg_template *to_cipher_tmpl(struct crypto_tfm *tfm)
+static inline struct qce_alg_template *to_cipher_tmpl(struct crypto_skcipher *tfm)
 {
-	struct crypto_alg *alg = tfm->__crt_alg;
-	return container_of(alg, struct qce_alg_template, alg.crypto);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	return container_of(alg, struct qce_alg_template, alg.skcipher);
 }
 
-extern const struct qce_algo_ops ablkcipher_ops;
+extern const struct qce_algo_ops skcipher_ops;
 
 #endif /* _CIPHER_H_ */
diff --git a/drivers/crypto/qce/common.c b/drivers/crypto/qce/common.c
index 3fb510164326..da1188abc9ba 100644
--- a/drivers/crypto/qce/common.c
+++ b/drivers/crypto/qce/common.c
@@ -304,13 +304,13 @@ go_proc:
 	return 0;
 }
 
-static int qce_setup_regs_ablkcipher(struct crypto_async_request *async_req,
+static int qce_setup_regs_skcipher(struct crypto_async_request *async_req,
 				     u32 totallen, u32 offset)
 {
-	struct ablkcipher_request *req = ablkcipher_request_cast(async_req);
-	struct qce_cipher_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct skcipher_request *req = skcipher_request_cast(async_req);
+	struct qce_cipher_reqctx *rctx = skcipher_request_ctx(req);
 	struct qce_cipher_ctx *ctx = crypto_tfm_ctx(async_req->tfm);
-	struct qce_alg_template *tmpl = to_cipher_tmpl(async_req->tfm);
+	struct qce_alg_template *tmpl = to_cipher_tmpl(crypto_skcipher_reqtfm(req));
 	struct qce_device *qce = tmpl->qce;
 	__be32 enckey[QCE_MAX_CIPHER_KEY_SIZE / sizeof(__be32)] = {0};
 	__be32 enciv[QCE_MAX_IV_SIZE / sizeof(__be32)] = {0};
@@ -389,8 +389,8 @@ int qce_start(struct crypto_async_request *async_req, u32 type, u32 totallen,
 	      u32 offset)
 {
 	switch (type) {
-	case CRYPTO_ALG_TYPE_ABLKCIPHER:
-		return qce_setup_regs_ablkcipher(async_req, totallen, offset);
+	case CRYPTO_ALG_TYPE_SKCIPHER:
+		return qce_setup_regs_skcipher(async_req, totallen, offset);
 	case CRYPTO_ALG_TYPE_AHASH:
 		return qce_setup_regs_ahash(async_req, totallen, offset);
 	default:
diff --git a/drivers/crypto/qce/common.h b/drivers/crypto/qce/common.h
index 47fb523357ac..282d4317470d 100644
--- a/drivers/crypto/qce/common.h
+++ b/drivers/crypto/qce/common.h
@@ -10,6 +10,7 @@
 #include <linux/types.h>
 #include <crypto/aes.h>
 #include <crypto/hash.h>
+#include <crypto/internal/skcipher.h>
 
 /* key size in bytes */
 #define QCE_SHA_HMAC_KEY_SIZE		64
@@ -79,7 +80,7 @@ struct qce_alg_template {
 	unsigned long alg_flags;
 	const u32 *std_iv;
 	union {
-		struct crypto_alg crypto;
+		struct skcipher_alg skcipher;
 		struct ahash_alg ahash;
 	} alg;
 	struct qce_device *qce;
diff --git a/drivers/crypto/qce/core.c b/drivers/crypto/qce/core.c
index 08d4ce3bfddf..0a44a6eeacf5 100644
--- a/drivers/crypto/qce/core.c
+++ b/drivers/crypto/qce/core.c
@@ -22,7 +22,7 @@
 #define QCE_QUEUE_LENGTH	1
 
 static const struct qce_algo_ops *qce_ops[] = {
-	&ablkcipher_ops,
+	&skcipher_ops,
 	&ahash_ops,
 };
 
diff --git a/drivers/crypto/qce/dma.c b/drivers/crypto/qce/dma.c
index 0984a719144d..40a59214d2e1 100644
--- a/drivers/crypto/qce/dma.c
+++ b/drivers/crypto/qce/dma.c
@@ -12,11 +12,11 @@ int qce_dma_request(struct device *dev, struct qce_dma_data *dma)
 {
 	int ret;
 
-	dma->txchan = dma_request_slave_channel_reason(dev, "tx");
+	dma->txchan = dma_request_chan(dev, "tx");
 	if (IS_ERR(dma->txchan))
 		return PTR_ERR(dma->txchan);
 
-	dma->rxchan = dma_request_slave_channel_reason(dev, "rx");
+	dma->rxchan = dma_request_chan(dev, "rx");
 	if (IS_ERR(dma->rxchan)) {
 		ret = PTR_ERR(dma->rxchan);
 		goto error_rx;
diff --git a/drivers/crypto/qce/sha.c b/drivers/crypto/qce/sha.c
index 0853e74583ad..95ab16fc8fd6 100644
--- a/drivers/crypto/qce/sha.c
+++ b/drivers/crypto/qce/sha.c
@@ -495,7 +495,7 @@ static int qce_ahash_register_one(const struct qce_ahash_def *def,
 	base = &alg->halg.base;
 	base->cra_blocksize = def->blocksize;
 	base->cra_priority = 300;
-	base->cra_flags = CRYPTO_ALG_ASYNC;
+	base->cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY;
 	base->cra_ctxsize = sizeof(struct qce_sha_ctx);
 	base->cra_alignmask = 0;
 	base->cra_module = THIS_MODULE;
diff --git a/drivers/crypto/qce/ablkcipher.c b/drivers/crypto/qce/skcipher.c
index 7a98bf5cc967..fee07323f8f9 100644
--- a/drivers/crypto/qce/ablkcipher.c
+++ b/drivers/crypto/qce/skcipher.c
@@ -12,14 +12,14 @@
 
 #include "cipher.h"
 
-static LIST_HEAD(ablkcipher_algs);
+static LIST_HEAD(skcipher_algs);
 
-static void qce_ablkcipher_done(void *data)
+static void qce_skcipher_done(void *data)
 {
 	struct crypto_async_request *async_req = data;
-	struct ablkcipher_request *req = ablkcipher_request_cast(async_req);
-	struct qce_cipher_reqctx *rctx = ablkcipher_request_ctx(req);
-	struct qce_alg_template *tmpl = to_cipher_tmpl(async_req->tfm);
+	struct skcipher_request *req = skcipher_request_cast(async_req);
+	struct qce_cipher_reqctx *rctx = skcipher_request_ctx(req);
+	struct qce_alg_template *tmpl = to_cipher_tmpl(crypto_skcipher_reqtfm(req));
 	struct qce_device *qce = tmpl->qce;
 	enum dma_data_direction dir_src, dir_dst;
 	u32 status;
@@ -32,7 +32,7 @@ static void qce_ablkcipher_done(void *data)
 
 	error = qce_dma_terminate_all(&qce->dma);
 	if (error)
-		dev_dbg(qce->dev, "ablkcipher dma termination error (%d)\n",
+		dev_dbg(qce->dev, "skcipher dma termination error (%d)\n",
 			error);
 
 	if (diff_dst)
@@ -43,18 +43,18 @@ static void qce_ablkcipher_done(void *data)
 
 	error = qce_check_status(qce, &status);
 	if (error < 0)
-		dev_dbg(qce->dev, "ablkcipher operation error (%x)\n", status);
+		dev_dbg(qce->dev, "skcipher operation error (%x)\n", status);
 
 	qce->async_req_done(tmpl->qce, error);
 }
 
 static int
-qce_ablkcipher_async_req_handle(struct crypto_async_request *async_req)
+qce_skcipher_async_req_handle(struct crypto_async_request *async_req)
 {
-	struct ablkcipher_request *req = ablkcipher_request_cast(async_req);
-	struct qce_cipher_reqctx *rctx = ablkcipher_request_ctx(req);
-	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
-	struct qce_alg_template *tmpl = to_cipher_tmpl(async_req->tfm);
+	struct skcipher_request *req = skcipher_request_cast(async_req);
+	struct qce_cipher_reqctx *rctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
+	struct qce_alg_template *tmpl = to_cipher_tmpl(crypto_skcipher_reqtfm(req));
 	struct qce_device *qce = tmpl->qce;
 	enum dma_data_direction dir_src, dir_dst;
 	struct scatterlist *sg;
@@ -62,17 +62,17 @@ qce_ablkcipher_async_req_handle(struct crypto_async_request *async_req)
 	gfp_t gfp;
 	int ret;
 
-	rctx->iv = req->info;
-	rctx->ivsize = crypto_ablkcipher_ivsize(ablkcipher);
-	rctx->cryptlen = req->nbytes;
+	rctx->iv = req->iv;
+	rctx->ivsize = crypto_skcipher_ivsize(skcipher);
+	rctx->cryptlen = req->cryptlen;
 
 	diff_dst = (req->src != req->dst) ? true : false;
 	dir_src = diff_dst ? DMA_TO_DEVICE : DMA_BIDIRECTIONAL;
 	dir_dst = diff_dst ? DMA_FROM_DEVICE : DMA_BIDIRECTIONAL;
 
-	rctx->src_nents = sg_nents_for_len(req->src, req->nbytes);
+	rctx->src_nents = sg_nents_for_len(req->src, req->cryptlen);
 	if (diff_dst)
-		rctx->dst_nents = sg_nents_for_len(req->dst, req->nbytes);
+		rctx->dst_nents = sg_nents_for_len(req->dst, req->cryptlen);
 	else
 		rctx->dst_nents = rctx->src_nents;
 	if (rctx->src_nents < 0) {
@@ -125,13 +125,13 @@ qce_ablkcipher_async_req_handle(struct crypto_async_request *async_req)
 
 	ret = qce_dma_prep_sgs(&qce->dma, rctx->src_sg, rctx->src_nents,
 			       rctx->dst_sg, rctx->dst_nents,
-			       qce_ablkcipher_done, async_req);
+			       qce_skcipher_done, async_req);
 	if (ret)
 		goto error_unmap_src;
 
 	qce_dma_issue_pending(&qce->dma);
 
-	ret = qce_start(async_req, tmpl->crypto_alg_type, req->nbytes, 0);
+	ret = qce_start(async_req, tmpl->crypto_alg_type, req->cryptlen, 0);
 	if (ret)
 		goto error_terminate;
 
@@ -149,10 +149,10 @@ error_free:
 	return ret;
 }
 
-static int qce_ablkcipher_setkey(struct crypto_ablkcipher *ablk, const u8 *key,
+static int qce_skcipher_setkey(struct crypto_skcipher *ablk, const u8 *key,
 				 unsigned int keylen)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(ablk);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(ablk);
 	struct qce_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
 	int ret;
 
@@ -177,13 +177,13 @@ fallback:
 	return ret;
 }
 
-static int qce_des_setkey(struct crypto_ablkcipher *ablk, const u8 *key,
+static int qce_des_setkey(struct crypto_skcipher *ablk, const u8 *key,
 			  unsigned int keylen)
 {
-	struct qce_cipher_ctx *ctx = crypto_ablkcipher_ctx(ablk);
+	struct qce_cipher_ctx *ctx = crypto_skcipher_ctx(ablk);
 	int err;
 
-	err = verify_ablkcipher_des_key(ablk, key);
+	err = verify_skcipher_des_key(ablk, key);
 	if (err)
 		return err;
 
@@ -192,13 +192,13 @@ static int qce_des_setkey(struct crypto_ablkcipher *ablk, const u8 *key,
 	return 0;
 }
 
-static int qce_des3_setkey(struct crypto_ablkcipher *ablk, const u8 *key,
+static int qce_des3_setkey(struct crypto_skcipher *ablk, const u8 *key,
 			   unsigned int keylen)
 {
-	struct qce_cipher_ctx *ctx = crypto_ablkcipher_ctx(ablk);
+	struct qce_cipher_ctx *ctx = crypto_skcipher_ctx(ablk);
 	int err;
 
-	err = verify_ablkcipher_des3_key(ablk, key);
+	err = verify_skcipher_des3_key(ablk, key);
 	if (err)
 		return err;
 
@@ -207,12 +207,11 @@ static int qce_des3_setkey(struct crypto_ablkcipher *ablk, const u8 *key,
 	return 0;
 }
 
-static int qce_ablkcipher_crypt(struct ablkcipher_request *req, int encrypt)
+static int qce_skcipher_crypt(struct skcipher_request *req, int encrypt)
 {
-	struct crypto_tfm *tfm =
-			crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
-	struct qce_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct qce_cipher_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct qce_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct qce_cipher_reqctx *rctx = skcipher_request_ctx(req);
 	struct qce_alg_template *tmpl = to_cipher_tmpl(tfm);
 	int ret;
 
@@ -227,7 +226,7 @@ static int qce_ablkcipher_crypt(struct ablkcipher_request *req, int encrypt)
 		skcipher_request_set_callback(subreq, req->base.flags,
 					      NULL, NULL);
 		skcipher_request_set_crypt(subreq, req->src, req->dst,
-					   req->nbytes, req->info);
+					   req->cryptlen, req->iv);
 		ret = encrypt ? crypto_skcipher_encrypt(subreq) :
 				crypto_skcipher_decrypt(subreq);
 		skcipher_request_zero(subreq);
@@ -237,36 +236,36 @@ static int qce_ablkcipher_crypt(struct ablkcipher_request *req, int encrypt)
 	return tmpl->qce->async_req_enqueue(tmpl->qce, &req->base);
 }
 
-static int qce_ablkcipher_encrypt(struct ablkcipher_request *req)
+static int qce_skcipher_encrypt(struct skcipher_request *req)
 {
-	return qce_ablkcipher_crypt(req, 1);
+	return qce_skcipher_crypt(req, 1);
 }
 
-static int qce_ablkcipher_decrypt(struct ablkcipher_request *req)
+static int qce_skcipher_decrypt(struct skcipher_request *req)
 {
-	return qce_ablkcipher_crypt(req, 0);
+	return qce_skcipher_crypt(req, 0);
 }
 
-static int qce_ablkcipher_init(struct crypto_tfm *tfm)
+static int qce_skcipher_init(struct crypto_skcipher *tfm)
 {
-	struct qce_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct qce_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	memset(ctx, 0, sizeof(*ctx));
-	tfm->crt_ablkcipher.reqsize = sizeof(struct qce_cipher_reqctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct qce_cipher_reqctx));
 
-	ctx->fallback = crypto_alloc_sync_skcipher(crypto_tfm_alg_name(tfm),
+	ctx->fallback = crypto_alloc_sync_skcipher(crypto_tfm_alg_name(&tfm->base),
 						   0, CRYPTO_ALG_NEED_FALLBACK);
 	return PTR_ERR_OR_ZERO(ctx->fallback);
 }
 
-static void qce_ablkcipher_exit(struct crypto_tfm *tfm)
+static void qce_skcipher_exit(struct crypto_skcipher *tfm)
 {
-	struct qce_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct qce_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	crypto_free_sync_skcipher(ctx->fallback);
 }
 
-struct qce_ablkcipher_def {
+struct qce_skcipher_def {
 	unsigned long flags;
 	const char *name;
 	const char *drv_name;
@@ -276,7 +275,7 @@ struct qce_ablkcipher_def {
 	unsigned int max_keysize;
 };
 
-static const struct qce_ablkcipher_def ablkcipher_def[] = {
+static const struct qce_skcipher_def skcipher_def[] = {
 	{
 		.flags		= QCE_ALG_AES | QCE_MODE_ECB,
 		.name		= "ecb(aes)",
@@ -351,90 +350,91 @@ static const struct qce_ablkcipher_def ablkcipher_def[] = {
 	},
 };
 
-static int qce_ablkcipher_register_one(const struct qce_ablkcipher_def *def,
+static int qce_skcipher_register_one(const struct qce_skcipher_def *def,
 				       struct qce_device *qce)
 {
 	struct qce_alg_template *tmpl;
-	struct crypto_alg *alg;
+	struct skcipher_alg *alg;
 	int ret;
 
 	tmpl = kzalloc(sizeof(*tmpl), GFP_KERNEL);
 	if (!tmpl)
 		return -ENOMEM;
 
-	alg = &tmpl->alg.crypto;
+	alg = &tmpl->alg.skcipher;
 
-	snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
-	snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+	snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
+	snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 		 def->drv_name);
 
-	alg->cra_blocksize = def->blocksize;
-	alg->cra_ablkcipher.ivsize = def->ivsize;
-	alg->cra_ablkcipher.min_keysize = def->min_keysize;
-	alg->cra_ablkcipher.max_keysize = def->max_keysize;
-	alg->cra_ablkcipher.setkey = IS_3DES(def->flags) ? qce_des3_setkey :
-				     IS_DES(def->flags) ? qce_des_setkey :
-				     qce_ablkcipher_setkey;
-	alg->cra_ablkcipher.encrypt = qce_ablkcipher_encrypt;
-	alg->cra_ablkcipher.decrypt = qce_ablkcipher_decrypt;
-
-	alg->cra_priority = 300;
-	alg->cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC |
-			 CRYPTO_ALG_NEED_FALLBACK;
-	alg->cra_ctxsize = sizeof(struct qce_cipher_ctx);
-	alg->cra_alignmask = 0;
-	alg->cra_type = &crypto_ablkcipher_type;
-	alg->cra_module = THIS_MODULE;
-	alg->cra_init = qce_ablkcipher_init;
-	alg->cra_exit = qce_ablkcipher_exit;
+	alg->base.cra_blocksize		= def->blocksize;
+	alg->ivsize			= def->ivsize;
+	alg->min_keysize		= def->min_keysize;
+	alg->max_keysize		= def->max_keysize;
+	alg->setkey			= IS_3DES(def->flags) ? qce_des3_setkey :
+					  IS_DES(def->flags) ? qce_des_setkey :
+					  qce_skcipher_setkey;
+	alg->encrypt			= qce_skcipher_encrypt;
+	alg->decrypt			= qce_skcipher_decrypt;
+
+	alg->base.cra_priority		= 300;
+	alg->base.cra_flags		= CRYPTO_ALG_ASYNC |
+					  CRYPTO_ALG_NEED_FALLBACK |
+					  CRYPTO_ALG_KERN_DRIVER_ONLY;
+	alg->base.cra_ctxsize		= sizeof(struct qce_cipher_ctx);
+	alg->base.cra_alignmask		= 0;
+	alg->base.cra_module		= THIS_MODULE;
+
+	alg->init			= qce_skcipher_init;
+	alg->exit			= qce_skcipher_exit;
 
 	INIT_LIST_HEAD(&tmpl->entry);
-	tmpl->crypto_alg_type = CRYPTO_ALG_TYPE_ABLKCIPHER;
+	tmpl->crypto_alg_type = CRYPTO_ALG_TYPE_SKCIPHER;
 	tmpl->alg_flags = def->flags;
 	tmpl->qce = qce;
 
-	ret = crypto_register_alg(alg);
+	ret = crypto_register_skcipher(alg);
 	if (ret) {
 		kfree(tmpl);
-		dev_err(qce->dev, "%s registration failed\n", alg->cra_name);
+		dev_err(qce->dev, "%s registration failed\n", alg->base.cra_name);
 		return ret;
 	}
 
-	list_add_tail(&tmpl->entry, &ablkcipher_algs);
-	dev_dbg(qce->dev, "%s is registered\n", alg->cra_name);
+	list_add_tail(&tmpl->entry, &skcipher_algs);
+	dev_dbg(qce->dev, "%s is registered\n", alg->base.cra_name);
 	return 0;
 }
 
-static void qce_ablkcipher_unregister(struct qce_device *qce)
+static void qce_skcipher_unregister(struct qce_device *qce)
 {
 	struct qce_alg_template *tmpl, *n;
 
-	list_for_each_entry_safe(tmpl, n, &ablkcipher_algs, entry) {
-		crypto_unregister_alg(&tmpl->alg.crypto);
+	list_for_each_entry_safe(tmpl, n, &skcipher_algs, entry) {
+		crypto_unregister_skcipher(&tmpl->alg.skcipher);
 		list_del(&tmpl->entry);
 		kfree(tmpl);
 	}
 }
 
-static int qce_ablkcipher_register(struct qce_device *qce)
+static int qce_skcipher_register(struct qce_device *qce)
 {
 	int ret, i;
 
-	for (i = 0; i < ARRAY_SIZE(ablkcipher_def); i++) {
-		ret = qce_ablkcipher_register_one(&ablkcipher_def[i], qce);
+	for (i = 0; i < ARRAY_SIZE(skcipher_def); i++) {
+		ret = qce_skcipher_register_one(&skcipher_def[i], qce);
 		if (ret)
 			goto err;
 	}
 
 	return 0;
 err:
-	qce_ablkcipher_unregister(qce);
+	qce_skcipher_unregister(qce);
 	return ret;
 }
 
-const struct qce_algo_ops ablkcipher_ops = {
-	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-	.register_algs = qce_ablkcipher_register,
-	.unregister_algs = qce_ablkcipher_unregister,
-	.async_req_handle = qce_ablkcipher_async_req_handle,
+const struct qce_algo_ops skcipher_ops = {
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.register_algs = qce_skcipher_register,
+	.unregister_algs = qce_skcipher_unregister,
+	.async_req_handle = qce_skcipher_async_req_handle,
 };
diff --git a/drivers/crypto/rockchip/Makefile b/drivers/crypto/rockchip/Makefile
index 6e23764e6c8a..785277aca71e 100644
--- a/drivers/crypto/rockchip/Makefile
+++ b/drivers/crypto/rockchip/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_CRYPTO_DEV_ROCKCHIP) += rk_crypto.o
 rk_crypto-objs := rk3288_crypto.o \
-		  rk3288_crypto_ablkcipher.o \
+		  rk3288_crypto_skcipher.o \
 		  rk3288_crypto_ahash.o
diff --git a/drivers/crypto/rockchip/rk3288_crypto.c b/drivers/crypto/rockchip/rk3288_crypto.c
index e5714ef24bf2..f385587f99af 100644
--- a/drivers/crypto/rockchip/rk3288_crypto.c
+++ b/drivers/crypto/rockchip/rk3288_crypto.c
@@ -264,8 +264,8 @@ static int rk_crypto_register(struct rk_crypto_info *crypto_info)
 	for (i = 0; i < ARRAY_SIZE(rk_cipher_algs); i++) {
 		rk_cipher_algs[i]->dev = crypto_info;
 		if (rk_cipher_algs[i]->type == ALG_TYPE_CIPHER)
-			err = crypto_register_alg(
-					&rk_cipher_algs[i]->alg.crypto);
+			err = crypto_register_skcipher(
+					&rk_cipher_algs[i]->alg.skcipher);
 		else
 			err = crypto_register_ahash(
 					&rk_cipher_algs[i]->alg.hash);
@@ -277,7 +277,7 @@ static int rk_crypto_register(struct rk_crypto_info *crypto_info)
 err_cipher_algs:
 	for (k = 0; k < i; k++) {
 		if (rk_cipher_algs[i]->type == ALG_TYPE_CIPHER)
-			crypto_unregister_alg(&rk_cipher_algs[k]->alg.crypto);
+			crypto_unregister_skcipher(&rk_cipher_algs[k]->alg.skcipher);
 		else
 			crypto_unregister_ahash(&rk_cipher_algs[i]->alg.hash);
 	}
@@ -290,7 +290,7 @@ static void rk_crypto_unregister(void)
 
 	for (i = 0; i < ARRAY_SIZE(rk_cipher_algs); i++) {
 		if (rk_cipher_algs[i]->type == ALG_TYPE_CIPHER)
-			crypto_unregister_alg(&rk_cipher_algs[i]->alg.crypto);
+			crypto_unregister_skcipher(&rk_cipher_algs[i]->alg.skcipher);
 		else
 			crypto_unregister_ahash(&rk_cipher_algs[i]->alg.hash);
 	}
diff --git a/drivers/crypto/rockchip/rk3288_crypto.h b/drivers/crypto/rockchip/rk3288_crypto.h
index 18e2b3f29336..2b49c677afdb 100644
--- a/drivers/crypto/rockchip/rk3288_crypto.h
+++ b/drivers/crypto/rockchip/rk3288_crypto.h
@@ -8,6 +8,7 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
 
 #include <crypto/md5.h>
 #include <crypto/sha.h>
@@ -256,7 +257,7 @@ enum alg_type {
 struct rk_crypto_tmp {
 	struct rk_crypto_info		*dev;
 	union {
-		struct crypto_alg	crypto;
+		struct skcipher_alg	skcipher;
 		struct ahash_alg	hash;
 	} alg;
 	enum alg_type			type;
diff --git a/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c b/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c
deleted file mode 100644
index d0f4b2d18059..000000000000
--- a/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c
+++ /dev/null
@@ -1,556 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Crypto acceleration support for Rockchip RK3288
- *
- * Copyright (c) 2015, Fuzhou Rockchip Electronics Co., Ltd
- *
- * Author: Zain Wang <zain.wang@rock-chips.com>
- *
- * Some ideas are from marvell-cesa.c and s5p-sss.c driver.
- */
-#include "rk3288_crypto.h"
-
-#define RK_CRYPTO_DEC			BIT(0)
-
-static void rk_crypto_complete(struct crypto_async_request *base, int err)
-{
-	if (base->complete)
-		base->complete(base, err);
-}
-
-static int rk_handle_req(struct rk_crypto_info *dev,
-			 struct ablkcipher_request *req)
-{
-	if (!IS_ALIGNED(req->nbytes, dev->align_size))
-		return -EINVAL;
-	else
-		return dev->enqueue(dev, &req->base);
-}
-
-static int rk_aes_setkey(struct crypto_ablkcipher *cipher,
-			 const u8 *key, unsigned int keylen)
-{
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
-	struct rk_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	if (keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_192 &&
-	    keylen != AES_KEYSIZE_256) {
-		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
-	}
-	ctx->keylen = keylen;
-	memcpy_toio(ctx->dev->reg + RK_CRYPTO_AES_KEY_0, key, keylen);
-	return 0;
-}
-
-static int rk_des_setkey(struct crypto_ablkcipher *cipher,
-			 const u8 *key, unsigned int keylen)
-{
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(cipher);
-	int err;
-
-	err = verify_ablkcipher_des_key(cipher, key);
-	if (err)
-		return err;
-
-	ctx->keylen = keylen;
-	memcpy_toio(ctx->dev->reg + RK_CRYPTO_TDES_KEY1_0, key, keylen);
-	return 0;
-}
-
-static int rk_tdes_setkey(struct crypto_ablkcipher *cipher,
-			  const u8 *key, unsigned int keylen)
-{
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(cipher);
-	int err;
-
-	err = verify_ablkcipher_des3_key(cipher, key);
-	if (err)
-		return err;
-
-	ctx->keylen = keylen;
-	memcpy_toio(ctx->dev->reg + RK_CRYPTO_TDES_KEY1_0, key, keylen);
-	return 0;
-}
-
-static int rk_aes_ecb_encrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct rk_crypto_info *dev = ctx->dev;
-
-	ctx->mode = RK_CRYPTO_AES_ECB_MODE;
-	return rk_handle_req(dev, req);
-}
-
-static int rk_aes_ecb_decrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct rk_crypto_info *dev = ctx->dev;
-
-	ctx->mode = RK_CRYPTO_AES_ECB_MODE | RK_CRYPTO_DEC;
-	return rk_handle_req(dev, req);
-}
-
-static int rk_aes_cbc_encrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct rk_crypto_info *dev = ctx->dev;
-
-	ctx->mode = RK_CRYPTO_AES_CBC_MODE;
-	return rk_handle_req(dev, req);
-}
-
-static int rk_aes_cbc_decrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct rk_crypto_info *dev = ctx->dev;
-
-	ctx->mode = RK_CRYPTO_AES_CBC_MODE | RK_CRYPTO_DEC;
-	return rk_handle_req(dev, req);
-}
-
-static int rk_des_ecb_encrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct rk_crypto_info *dev = ctx->dev;
-
-	ctx->mode = 0;
-	return rk_handle_req(dev, req);
-}
-
-static int rk_des_ecb_decrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct rk_crypto_info *dev = ctx->dev;
-
-	ctx->mode = RK_CRYPTO_DEC;
-	return rk_handle_req(dev, req);
-}
-
-static int rk_des_cbc_encrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct rk_crypto_info *dev = ctx->dev;
-
-	ctx->mode = RK_CRYPTO_TDES_CHAINMODE_CBC;
-	return rk_handle_req(dev, req);
-}
-
-static int rk_des_cbc_decrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct rk_crypto_info *dev = ctx->dev;
-
-	ctx->mode = RK_CRYPTO_TDES_CHAINMODE_CBC | RK_CRYPTO_DEC;
-	return rk_handle_req(dev, req);
-}
-
-static int rk_des3_ede_ecb_encrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct rk_crypto_info *dev = ctx->dev;
-
-	ctx->mode = RK_CRYPTO_TDES_SELECT;
-	return rk_handle_req(dev, req);
-}
-
-static int rk_des3_ede_ecb_decrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct rk_crypto_info *dev = ctx->dev;
-
-	ctx->mode = RK_CRYPTO_TDES_SELECT | RK_CRYPTO_DEC;
-	return rk_handle_req(dev, req);
-}
-
-static int rk_des3_ede_cbc_encrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct rk_crypto_info *dev = ctx->dev;
-
-	ctx->mode = RK_CRYPTO_TDES_SELECT | RK_CRYPTO_TDES_CHAINMODE_CBC;
-	return rk_handle_req(dev, req);
-}
-
-static int rk_des3_ede_cbc_decrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct rk_crypto_info *dev = ctx->dev;
-
-	ctx->mode = RK_CRYPTO_TDES_SELECT | RK_CRYPTO_TDES_CHAINMODE_CBC |
-		    RK_CRYPTO_DEC;
-	return rk_handle_req(dev, req);
-}
-
-static void rk_ablk_hw_init(struct rk_crypto_info *dev)
-{
-	struct ablkcipher_request *req =
-		ablkcipher_request_cast(dev->async_req);
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(req);
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(cipher);
-	u32 ivsize, block, conf_reg = 0;
-
-	block = crypto_tfm_alg_blocksize(tfm);
-	ivsize = crypto_ablkcipher_ivsize(cipher);
-
-	if (block == DES_BLOCK_SIZE) {
-		ctx->mode |= RK_CRYPTO_TDES_FIFO_MODE |
-			     RK_CRYPTO_TDES_BYTESWAP_KEY |
-			     RK_CRYPTO_TDES_BYTESWAP_IV;
-		CRYPTO_WRITE(dev, RK_CRYPTO_TDES_CTRL, ctx->mode);
-		memcpy_toio(dev->reg + RK_CRYPTO_TDES_IV_0, req->info, ivsize);
-		conf_reg = RK_CRYPTO_DESSEL;
-	} else {
-		ctx->mode |= RK_CRYPTO_AES_FIFO_MODE |
-			     RK_CRYPTO_AES_KEY_CHANGE |
-			     RK_CRYPTO_AES_BYTESWAP_KEY |
-			     RK_CRYPTO_AES_BYTESWAP_IV;
-		if (ctx->keylen == AES_KEYSIZE_192)
-			ctx->mode |= RK_CRYPTO_AES_192BIT_key;
-		else if (ctx->keylen == AES_KEYSIZE_256)
-			ctx->mode |= RK_CRYPTO_AES_256BIT_key;
-		CRYPTO_WRITE(dev, RK_CRYPTO_AES_CTRL, ctx->mode);
-		memcpy_toio(dev->reg + RK_CRYPTO_AES_IV_0, req->info, ivsize);
-	}
-	conf_reg |= RK_CRYPTO_BYTESWAP_BTFIFO |
-		    RK_CRYPTO_BYTESWAP_BRFIFO;
-	CRYPTO_WRITE(dev, RK_CRYPTO_CONF, conf_reg);
-	CRYPTO_WRITE(dev, RK_CRYPTO_INTENA,
-		     RK_CRYPTO_BCDMA_ERR_ENA | RK_CRYPTO_BCDMA_DONE_ENA);
-}
-
-static void crypto_dma_start(struct rk_crypto_info *dev)
-{
-	CRYPTO_WRITE(dev, RK_CRYPTO_BRDMAS, dev->addr_in);
-	CRYPTO_WRITE(dev, RK_CRYPTO_BRDMAL, dev->count / 4);
-	CRYPTO_WRITE(dev, RK_CRYPTO_BTDMAS, dev->addr_out);
-	CRYPTO_WRITE(dev, RK_CRYPTO_CTRL, RK_CRYPTO_BLOCK_START |
-		     _SBF(RK_CRYPTO_BLOCK_START, 16));
-}
-
-static int rk_set_data_start(struct rk_crypto_info *dev)
-{
-	int err;
-	struct ablkcipher_request *req =
-		ablkcipher_request_cast(dev->async_req);
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	u32 ivsize = crypto_ablkcipher_ivsize(tfm);
-	u8 *src_last_blk = page_address(sg_page(dev->sg_src)) +
-		dev->sg_src->offset + dev->sg_src->length - ivsize;
-
-	/* Store the iv that need to be updated in chain mode.
-	 * And update the IV buffer to contain the next IV for decryption mode.
-	 */
-	if (ctx->mode & RK_CRYPTO_DEC) {
-		memcpy(ctx->iv, src_last_blk, ivsize);
-		sg_pcopy_to_buffer(dev->first, dev->src_nents, req->info,
-				   ivsize, dev->total - ivsize);
-	}
-
-	err = dev->load_data(dev, dev->sg_src, dev->sg_dst);
-	if (!err)
-		crypto_dma_start(dev);
-	return err;
-}
-
-static int rk_ablk_start(struct rk_crypto_info *dev)
-{
-	struct ablkcipher_request *req =
-		ablkcipher_request_cast(dev->async_req);
-	unsigned long flags;
-	int err = 0;
-
-	dev->left_bytes = req->nbytes;
-	dev->total = req->nbytes;
-	dev->sg_src = req->src;
-	dev->first = req->src;
-	dev->src_nents = sg_nents(req->src);
-	dev->sg_dst = req->dst;
-	dev->dst_nents = sg_nents(req->dst);
-	dev->aligned = 1;
-
-	spin_lock_irqsave(&dev->lock, flags);
-	rk_ablk_hw_init(dev);
-	err = rk_set_data_start(dev);
-	spin_unlock_irqrestore(&dev->lock, flags);
-	return err;
-}
-
-static void rk_iv_copyback(struct rk_crypto_info *dev)
-{
-	struct ablkcipher_request *req =
-		ablkcipher_request_cast(dev->async_req);
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	u32 ivsize = crypto_ablkcipher_ivsize(tfm);
-
-	/* Update the IV buffer to contain the next IV for encryption mode. */
-	if (!(ctx->mode & RK_CRYPTO_DEC)) {
-		if (dev->aligned) {
-			memcpy(req->info, sg_virt(dev->sg_dst) +
-				dev->sg_dst->length - ivsize, ivsize);
-		} else {
-			memcpy(req->info, dev->addr_vir +
-				dev->count - ivsize, ivsize);
-		}
-	}
-}
-
-static void rk_update_iv(struct rk_crypto_info *dev)
-{
-	struct ablkcipher_request *req =
-		ablkcipher_request_cast(dev->async_req);
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	u32 ivsize = crypto_ablkcipher_ivsize(tfm);
-	u8 *new_iv = NULL;
-
-	if (ctx->mode & RK_CRYPTO_DEC) {
-		new_iv = ctx->iv;
-	} else {
-		new_iv = page_address(sg_page(dev->sg_dst)) +
-			 dev->sg_dst->offset + dev->sg_dst->length - ivsize;
-	}
-
-	if (ivsize == DES_BLOCK_SIZE)
-		memcpy_toio(dev->reg + RK_CRYPTO_TDES_IV_0, new_iv, ivsize);
-	else if (ivsize == AES_BLOCK_SIZE)
-		memcpy_toio(dev->reg + RK_CRYPTO_AES_IV_0, new_iv, ivsize);
-}
-
-/* return:
- *	true	some err was occurred
- *	fault	no err, continue
- */
-static int rk_ablk_rx(struct rk_crypto_info *dev)
-{
-	int err = 0;
-	struct ablkcipher_request *req =
-		ablkcipher_request_cast(dev->async_req);
-
-	dev->unload_data(dev);
-	if (!dev->aligned) {
-		if (!sg_pcopy_from_buffer(req->dst, dev->dst_nents,
-					  dev->addr_vir, dev->count,
-					  dev->total - dev->left_bytes -
-					  dev->count)) {
-			err = -EINVAL;
-			goto out_rx;
-		}
-	}
-	if (dev->left_bytes) {
-		rk_update_iv(dev);
-		if (dev->aligned) {
-			if (sg_is_last(dev->sg_src)) {
-				dev_err(dev->dev, "[%s:%d] Lack of data\n",
-					__func__, __LINE__);
-				err = -ENOMEM;
-				goto out_rx;
-			}
-			dev->sg_src = sg_next(dev->sg_src);
-			dev->sg_dst = sg_next(dev->sg_dst);
-		}
-		err = rk_set_data_start(dev);
-	} else {
-		rk_iv_copyback(dev);
-		/* here show the calculation is over without any err */
-		dev->complete(dev->async_req, 0);
-		tasklet_schedule(&dev->queue_task);
-	}
-out_rx:
-	return err;
-}
-
-static int rk_ablk_cra_init(struct crypto_tfm *tfm)
-{
-	struct rk_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct crypto_alg *alg = tfm->__crt_alg;
-	struct rk_crypto_tmp *algt;
-
-	algt = container_of(alg, struct rk_crypto_tmp, alg.crypto);
-
-	ctx->dev = algt->dev;
-	ctx->dev->align_size = crypto_tfm_alg_alignmask(tfm) + 1;
-	ctx->dev->start = rk_ablk_start;
-	ctx->dev->update = rk_ablk_rx;
-	ctx->dev->complete = rk_crypto_complete;
-	ctx->dev->addr_vir = (char *)__get_free_page(GFP_KERNEL);
-
-	return ctx->dev->addr_vir ? ctx->dev->enable_clk(ctx->dev) : -ENOMEM;
-}
-
-static void rk_ablk_cra_exit(struct crypto_tfm *tfm)
-{
-	struct rk_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	free_page((unsigned long)ctx->dev->addr_vir);
-	ctx->dev->disable_clk(ctx->dev);
-}
-
-struct rk_crypto_tmp rk_ecb_aes_alg = {
-	.type = ALG_TYPE_CIPHER,
-	.alg.crypto = {
-		.cra_name		= "ecb(aes)",
-		.cra_driver_name	= "ecb-aes-rk",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-					  CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= AES_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct rk_cipher_ctx),
-		.cra_alignmask		= 0x0f,
-		.cra_type		= &crypto_ablkcipher_type,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= rk_ablk_cra_init,
-		.cra_exit		= rk_ablk_cra_exit,
-		.cra_u.ablkcipher	= {
-			.min_keysize	= AES_MIN_KEY_SIZE,
-			.max_keysize	= AES_MAX_KEY_SIZE,
-			.setkey		= rk_aes_setkey,
-			.encrypt	= rk_aes_ecb_encrypt,
-			.decrypt	= rk_aes_ecb_decrypt,
-		}
-	}
-};
-
-struct rk_crypto_tmp rk_cbc_aes_alg = {
-	.type = ALG_TYPE_CIPHER,
-	.alg.crypto = {
-		.cra_name		= "cbc(aes)",
-		.cra_driver_name	= "cbc-aes-rk",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-					  CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= AES_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct rk_cipher_ctx),
-		.cra_alignmask		= 0x0f,
-		.cra_type		= &crypto_ablkcipher_type,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= rk_ablk_cra_init,
-		.cra_exit		= rk_ablk_cra_exit,
-		.cra_u.ablkcipher	= {
-			.min_keysize	= AES_MIN_KEY_SIZE,
-			.max_keysize	= AES_MAX_KEY_SIZE,
-			.ivsize		= AES_BLOCK_SIZE,
-			.setkey		= rk_aes_setkey,
-			.encrypt	= rk_aes_cbc_encrypt,
-			.decrypt	= rk_aes_cbc_decrypt,
-		}
-	}
-};
-
-struct rk_crypto_tmp rk_ecb_des_alg = {
-	.type = ALG_TYPE_CIPHER,
-	.alg.crypto = {
-		.cra_name		= "ecb(des)",
-		.cra_driver_name	= "ecb-des-rk",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-					  CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= DES_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct rk_cipher_ctx),
-		.cra_alignmask		= 0x07,
-		.cra_type		= &crypto_ablkcipher_type,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= rk_ablk_cra_init,
-		.cra_exit		= rk_ablk_cra_exit,
-		.cra_u.ablkcipher	= {
-			.min_keysize	= DES_KEY_SIZE,
-			.max_keysize	= DES_KEY_SIZE,
-			.setkey		= rk_des_setkey,
-			.encrypt	= rk_des_ecb_encrypt,
-			.decrypt	= rk_des_ecb_decrypt,
-		}
-	}
-};
-
-struct rk_crypto_tmp rk_cbc_des_alg = {
-	.type = ALG_TYPE_CIPHER,
-	.alg.crypto = {
-		.cra_name		= "cbc(des)",
-		.cra_driver_name	= "cbc-des-rk",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-					  CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= DES_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct rk_cipher_ctx),
-		.cra_alignmask		= 0x07,
-		.cra_type		= &crypto_ablkcipher_type,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= rk_ablk_cra_init,
-		.cra_exit		= rk_ablk_cra_exit,
-		.cra_u.ablkcipher	= {
-			.min_keysize	= DES_KEY_SIZE,
-			.max_keysize	= DES_KEY_SIZE,
-			.ivsize		= DES_BLOCK_SIZE,
-			.setkey		= rk_des_setkey,
-			.encrypt	= rk_des_cbc_encrypt,
-			.decrypt	= rk_des_cbc_decrypt,
-		}
-	}
-};
-
-struct rk_crypto_tmp rk_ecb_des3_ede_alg = {
-	.type = ALG_TYPE_CIPHER,
-	.alg.crypto = {
-		.cra_name		= "ecb(des3_ede)",
-		.cra_driver_name	= "ecb-des3-ede-rk",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-					  CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= DES_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct rk_cipher_ctx),
-		.cra_alignmask		= 0x07,
-		.cra_type		= &crypto_ablkcipher_type,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= rk_ablk_cra_init,
-		.cra_exit		= rk_ablk_cra_exit,
-		.cra_u.ablkcipher	= {
-			.min_keysize	= DES3_EDE_KEY_SIZE,
-			.max_keysize	= DES3_EDE_KEY_SIZE,
-			.ivsize		= DES_BLOCK_SIZE,
-			.setkey		= rk_tdes_setkey,
-			.encrypt	= rk_des3_ede_ecb_encrypt,
-			.decrypt	= rk_des3_ede_ecb_decrypt,
-		}
-	}
-};
-
-struct rk_crypto_tmp rk_cbc_des3_ede_alg = {
-	.type = ALG_TYPE_CIPHER,
-	.alg.crypto = {
-		.cra_name		= "cbc(des3_ede)",
-		.cra_driver_name	= "cbc-des3-ede-rk",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-					  CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= DES_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct rk_cipher_ctx),
-		.cra_alignmask		= 0x07,
-		.cra_type		= &crypto_ablkcipher_type,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= rk_ablk_cra_init,
-		.cra_exit		= rk_ablk_cra_exit,
-		.cra_u.ablkcipher	= {
-			.min_keysize	= DES3_EDE_KEY_SIZE,
-			.max_keysize	= DES3_EDE_KEY_SIZE,
-			.ivsize		= DES_BLOCK_SIZE,
-			.setkey		= rk_tdes_setkey,
-			.encrypt	= rk_des3_ede_cbc_encrypt,
-			.decrypt	= rk_des3_ede_cbc_decrypt,
-		}
-	}
-};
diff --git a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c
new file mode 100644
index 000000000000..ca4de4ddfe1f
--- /dev/null
+++ b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c
@@ -0,0 +1,538 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Crypto acceleration support for Rockchip RK3288
+ *
+ * Copyright (c) 2015, Fuzhou Rockchip Electronics Co., Ltd
+ *
+ * Author: Zain Wang <zain.wang@rock-chips.com>
+ *
+ * Some ideas are from marvell-cesa.c and s5p-sss.c driver.
+ */
+#include "rk3288_crypto.h"
+
+#define RK_CRYPTO_DEC			BIT(0)
+
+static void rk_crypto_complete(struct crypto_async_request *base, int err)
+{
+	if (base->complete)
+		base->complete(base, err);
+}
+
+static int rk_handle_req(struct rk_crypto_info *dev,
+			 struct skcipher_request *req)
+{
+	if (!IS_ALIGNED(req->cryptlen, dev->align_size))
+		return -EINVAL;
+	else
+		return dev->enqueue(dev, &req->base);
+}
+
+static int rk_aes_setkey(struct crypto_skcipher *cipher,
+			 const u8 *key, unsigned int keylen)
+{
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(cipher);
+	struct rk_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_192 &&
+	    keylen != AES_KEYSIZE_256) {
+		crypto_skcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	ctx->keylen = keylen;
+	memcpy_toio(ctx->dev->reg + RK_CRYPTO_AES_KEY_0, key, keylen);
+	return 0;
+}
+
+static int rk_des_setkey(struct crypto_skcipher *cipher,
+			 const u8 *key, unsigned int keylen)
+{
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(cipher);
+	int err;
+
+	err = verify_skcipher_des_key(cipher, key);
+	if (err)
+		return err;
+
+	ctx->keylen = keylen;
+	memcpy_toio(ctx->dev->reg + RK_CRYPTO_TDES_KEY1_0, key, keylen);
+	return 0;
+}
+
+static int rk_tdes_setkey(struct crypto_skcipher *cipher,
+			  const u8 *key, unsigned int keylen)
+{
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(cipher);
+	int err;
+
+	err = verify_skcipher_des3_key(cipher, key);
+	if (err)
+		return err;
+
+	ctx->keylen = keylen;
+	memcpy_toio(ctx->dev->reg + RK_CRYPTO_TDES_KEY1_0, key, keylen);
+	return 0;
+}
+
+static int rk_aes_ecb_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	ctx->mode = RK_CRYPTO_AES_ECB_MODE;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_aes_ecb_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	ctx->mode = RK_CRYPTO_AES_ECB_MODE | RK_CRYPTO_DEC;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_aes_cbc_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	ctx->mode = RK_CRYPTO_AES_CBC_MODE;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_aes_cbc_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	ctx->mode = RK_CRYPTO_AES_CBC_MODE | RK_CRYPTO_DEC;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des_ecb_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	ctx->mode = 0;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des_ecb_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	ctx->mode = RK_CRYPTO_DEC;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des_cbc_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	ctx->mode = RK_CRYPTO_TDES_CHAINMODE_CBC;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des_cbc_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	ctx->mode = RK_CRYPTO_TDES_CHAINMODE_CBC | RK_CRYPTO_DEC;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des3_ede_ecb_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	ctx->mode = RK_CRYPTO_TDES_SELECT;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des3_ede_ecb_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	ctx->mode = RK_CRYPTO_TDES_SELECT | RK_CRYPTO_DEC;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des3_ede_cbc_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	ctx->mode = RK_CRYPTO_TDES_SELECT | RK_CRYPTO_TDES_CHAINMODE_CBC;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des3_ede_cbc_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	ctx->mode = RK_CRYPTO_TDES_SELECT | RK_CRYPTO_TDES_CHAINMODE_CBC |
+		    RK_CRYPTO_DEC;
+	return rk_handle_req(dev, req);
+}
+
+static void rk_ablk_hw_init(struct rk_crypto_info *dev)
+{
+	struct skcipher_request *req =
+		skcipher_request_cast(dev->async_req);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(req);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(cipher);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(cipher);
+	u32 ivsize, block, conf_reg = 0;
+
+	block = crypto_tfm_alg_blocksize(tfm);
+	ivsize = crypto_skcipher_ivsize(cipher);
+
+	if (block == DES_BLOCK_SIZE) {
+		ctx->mode |= RK_CRYPTO_TDES_FIFO_MODE |
+			     RK_CRYPTO_TDES_BYTESWAP_KEY |
+			     RK_CRYPTO_TDES_BYTESWAP_IV;
+		CRYPTO_WRITE(dev, RK_CRYPTO_TDES_CTRL, ctx->mode);
+		memcpy_toio(dev->reg + RK_CRYPTO_TDES_IV_0, req->iv, ivsize);
+		conf_reg = RK_CRYPTO_DESSEL;
+	} else {
+		ctx->mode |= RK_CRYPTO_AES_FIFO_MODE |
+			     RK_CRYPTO_AES_KEY_CHANGE |
+			     RK_CRYPTO_AES_BYTESWAP_KEY |
+			     RK_CRYPTO_AES_BYTESWAP_IV;
+		if (ctx->keylen == AES_KEYSIZE_192)
+			ctx->mode |= RK_CRYPTO_AES_192BIT_key;
+		else if (ctx->keylen == AES_KEYSIZE_256)
+			ctx->mode |= RK_CRYPTO_AES_256BIT_key;
+		CRYPTO_WRITE(dev, RK_CRYPTO_AES_CTRL, ctx->mode);
+		memcpy_toio(dev->reg + RK_CRYPTO_AES_IV_0, req->iv, ivsize);
+	}
+	conf_reg |= RK_CRYPTO_BYTESWAP_BTFIFO |
+		    RK_CRYPTO_BYTESWAP_BRFIFO;
+	CRYPTO_WRITE(dev, RK_CRYPTO_CONF, conf_reg);
+	CRYPTO_WRITE(dev, RK_CRYPTO_INTENA,
+		     RK_CRYPTO_BCDMA_ERR_ENA | RK_CRYPTO_BCDMA_DONE_ENA);
+}
+
+static void crypto_dma_start(struct rk_crypto_info *dev)
+{
+	CRYPTO_WRITE(dev, RK_CRYPTO_BRDMAS, dev->addr_in);
+	CRYPTO_WRITE(dev, RK_CRYPTO_BRDMAL, dev->count / 4);
+	CRYPTO_WRITE(dev, RK_CRYPTO_BTDMAS, dev->addr_out);
+	CRYPTO_WRITE(dev, RK_CRYPTO_CTRL, RK_CRYPTO_BLOCK_START |
+		     _SBF(RK_CRYPTO_BLOCK_START, 16));
+}
+
+static int rk_set_data_start(struct rk_crypto_info *dev)
+{
+	int err;
+	struct skcipher_request *req =
+		skcipher_request_cast(dev->async_req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	u32 ivsize = crypto_skcipher_ivsize(tfm);
+	u8 *src_last_blk = page_address(sg_page(dev->sg_src)) +
+		dev->sg_src->offset + dev->sg_src->length - ivsize;
+
+	/* Store the iv that need to be updated in chain mode.
+	 * And update the IV buffer to contain the next IV for decryption mode.
+	 */
+	if (ctx->mode & RK_CRYPTO_DEC) {
+		memcpy(ctx->iv, src_last_blk, ivsize);
+		sg_pcopy_to_buffer(dev->first, dev->src_nents, req->iv,
+				   ivsize, dev->total - ivsize);
+	}
+
+	err = dev->load_data(dev, dev->sg_src, dev->sg_dst);
+	if (!err)
+		crypto_dma_start(dev);
+	return err;
+}
+
+static int rk_ablk_start(struct rk_crypto_info *dev)
+{
+	struct skcipher_request *req =
+		skcipher_request_cast(dev->async_req);
+	unsigned long flags;
+	int err = 0;
+
+	dev->left_bytes = req->cryptlen;
+	dev->total = req->cryptlen;
+	dev->sg_src = req->src;
+	dev->first = req->src;
+	dev->src_nents = sg_nents(req->src);
+	dev->sg_dst = req->dst;
+	dev->dst_nents = sg_nents(req->dst);
+	dev->aligned = 1;
+
+	spin_lock_irqsave(&dev->lock, flags);
+	rk_ablk_hw_init(dev);
+	err = rk_set_data_start(dev);
+	spin_unlock_irqrestore(&dev->lock, flags);
+	return err;
+}
+
+static void rk_iv_copyback(struct rk_crypto_info *dev)
+{
+	struct skcipher_request *req =
+		skcipher_request_cast(dev->async_req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	u32 ivsize = crypto_skcipher_ivsize(tfm);
+
+	/* Update the IV buffer to contain the next IV for encryption mode. */
+	if (!(ctx->mode & RK_CRYPTO_DEC)) {
+		if (dev->aligned) {
+			memcpy(req->iv, sg_virt(dev->sg_dst) +
+				dev->sg_dst->length - ivsize, ivsize);
+		} else {
+			memcpy(req->iv, dev->addr_vir +
+				dev->count - ivsize, ivsize);
+		}
+	}
+}
+
+static void rk_update_iv(struct rk_crypto_info *dev)
+{
+	struct skcipher_request *req =
+		skcipher_request_cast(dev->async_req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	u32 ivsize = crypto_skcipher_ivsize(tfm);
+	u8 *new_iv = NULL;
+
+	if (ctx->mode & RK_CRYPTO_DEC) {
+		new_iv = ctx->iv;
+	} else {
+		new_iv = page_address(sg_page(dev->sg_dst)) +
+			 dev->sg_dst->offset + dev->sg_dst->length - ivsize;
+	}
+
+	if (ivsize == DES_BLOCK_SIZE)
+		memcpy_toio(dev->reg + RK_CRYPTO_TDES_IV_0, new_iv, ivsize);
+	else if (ivsize == AES_BLOCK_SIZE)
+		memcpy_toio(dev->reg + RK_CRYPTO_AES_IV_0, new_iv, ivsize);
+}
+
+/* return:
+ *	true	some err was occurred
+ *	fault	no err, continue
+ */
+static int rk_ablk_rx(struct rk_crypto_info *dev)
+{
+	int err = 0;
+	struct skcipher_request *req =
+		skcipher_request_cast(dev->async_req);
+
+	dev->unload_data(dev);
+	if (!dev->aligned) {
+		if (!sg_pcopy_from_buffer(req->dst, dev->dst_nents,
+					  dev->addr_vir, dev->count,
+					  dev->total - dev->left_bytes -
+					  dev->count)) {
+			err = -EINVAL;
+			goto out_rx;
+		}
+	}
+	if (dev->left_bytes) {
+		rk_update_iv(dev);
+		if (dev->aligned) {
+			if (sg_is_last(dev->sg_src)) {
+				dev_err(dev->dev, "[%s:%d] Lack of data\n",
+					__func__, __LINE__);
+				err = -ENOMEM;
+				goto out_rx;
+			}
+			dev->sg_src = sg_next(dev->sg_src);
+			dev->sg_dst = sg_next(dev->sg_dst);
+		}
+		err = rk_set_data_start(dev);
+	} else {
+		rk_iv_copyback(dev);
+		/* here show the calculation is over without any err */
+		dev->complete(dev->async_req, 0);
+		tasklet_schedule(&dev->queue_task);
+	}
+out_rx:
+	return err;
+}
+
+static int rk_ablk_init_tfm(struct crypto_skcipher *tfm)
+{
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	struct rk_crypto_tmp *algt;
+
+	algt = container_of(alg, struct rk_crypto_tmp, alg.skcipher);
+
+	ctx->dev = algt->dev;
+	ctx->dev->align_size = crypto_tfm_alg_alignmask(crypto_skcipher_tfm(tfm)) + 1;
+	ctx->dev->start = rk_ablk_start;
+	ctx->dev->update = rk_ablk_rx;
+	ctx->dev->complete = rk_crypto_complete;
+	ctx->dev->addr_vir = (char *)__get_free_page(GFP_KERNEL);
+
+	return ctx->dev->addr_vir ? ctx->dev->enable_clk(ctx->dev) : -ENOMEM;
+}
+
+static void rk_ablk_exit_tfm(struct crypto_skcipher *tfm)
+{
+	struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	free_page((unsigned long)ctx->dev->addr_vir);
+	ctx->dev->disable_clk(ctx->dev);
+}
+
+struct rk_crypto_tmp rk_ecb_aes_alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.skcipher = {
+		.base.cra_name		= "ecb(aes)",
+		.base.cra_driver_name	= "ecb-aes-rk",
+		.base.cra_priority	= 300,
+		.base.cra_flags		= CRYPTO_ALG_ASYNC,
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct rk_cipher_ctx),
+		.base.cra_alignmask	= 0x0f,
+		.base.cra_module	= THIS_MODULE,
+
+		.init			= rk_ablk_init_tfm,
+		.exit			= rk_ablk_exit_tfm,
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.setkey			= rk_aes_setkey,
+		.encrypt		= rk_aes_ecb_encrypt,
+		.decrypt		= rk_aes_ecb_decrypt,
+	}
+};
+
+struct rk_crypto_tmp rk_cbc_aes_alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.skcipher = {
+		.base.cra_name		= "cbc(aes)",
+		.base.cra_driver_name	= "cbc-aes-rk",
+		.base.cra_priority	= 300,
+		.base.cra_flags		= CRYPTO_ALG_ASYNC,
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct rk_cipher_ctx),
+		.base.cra_alignmask	= 0x0f,
+		.base.cra_module	= THIS_MODULE,
+
+		.init			= rk_ablk_init_tfm,
+		.exit			= rk_ablk_exit_tfm,
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.ivsize			= AES_BLOCK_SIZE,
+		.setkey			= rk_aes_setkey,
+		.encrypt		= rk_aes_cbc_encrypt,
+		.decrypt		= rk_aes_cbc_decrypt,
+	}
+};
+
+struct rk_crypto_tmp rk_ecb_des_alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.skcipher = {
+		.base.cra_name		= "ecb(des)",
+		.base.cra_driver_name	= "ecb-des-rk",
+		.base.cra_priority	= 300,
+		.base.cra_flags		= CRYPTO_ALG_ASYNC,
+		.base.cra_blocksize	= DES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct rk_cipher_ctx),
+		.base.cra_alignmask	= 0x07,
+		.base.cra_module	= THIS_MODULE,
+
+		.init			= rk_ablk_init_tfm,
+		.exit			= rk_ablk_exit_tfm,
+		.min_keysize		= DES_KEY_SIZE,
+		.max_keysize		= DES_KEY_SIZE,
+		.setkey			= rk_des_setkey,
+		.encrypt		= rk_des_ecb_encrypt,
+		.decrypt		= rk_des_ecb_decrypt,
+	}
+};
+
+struct rk_crypto_tmp rk_cbc_des_alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.skcipher = {
+		.base.cra_name		= "cbc(des)",
+		.base.cra_driver_name	= "cbc-des-rk",
+		.base.cra_priority	= 300,
+		.base.cra_flags		= CRYPTO_ALG_ASYNC,
+		.base.cra_blocksize	= DES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct rk_cipher_ctx),
+		.base.cra_alignmask	= 0x07,
+		.base.cra_module	= THIS_MODULE,
+
+		.init			= rk_ablk_init_tfm,
+		.exit			= rk_ablk_exit_tfm,
+		.min_keysize		= DES_KEY_SIZE,
+		.max_keysize		= DES_KEY_SIZE,
+		.ivsize			= DES_BLOCK_SIZE,
+		.setkey			= rk_des_setkey,
+		.encrypt		= rk_des_cbc_encrypt,
+		.decrypt		= rk_des_cbc_decrypt,
+	}
+};
+
+struct rk_crypto_tmp rk_ecb_des3_ede_alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.skcipher = {
+		.base.cra_name		= "ecb(des3_ede)",
+		.base.cra_driver_name	= "ecb-des3-ede-rk",
+		.base.cra_priority	= 300,
+		.base.cra_flags		= CRYPTO_ALG_ASYNC,
+		.base.cra_blocksize	= DES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct rk_cipher_ctx),
+		.base.cra_alignmask	= 0x07,
+		.base.cra_module	= THIS_MODULE,
+
+		.init			= rk_ablk_init_tfm,
+		.exit			= rk_ablk_exit_tfm,
+		.min_keysize		= DES3_EDE_KEY_SIZE,
+		.max_keysize		= DES3_EDE_KEY_SIZE,
+		.ivsize			= DES_BLOCK_SIZE,
+		.setkey			= rk_tdes_setkey,
+		.encrypt		= rk_des3_ede_ecb_encrypt,
+		.decrypt		= rk_des3_ede_ecb_decrypt,
+	}
+};
+
+struct rk_crypto_tmp rk_cbc_des3_ede_alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.skcipher = {
+		.base.cra_name		= "cbc(des3_ede)",
+		.base.cra_driver_name	= "cbc-des3-ede-rk",
+		.base.cra_priority	= 300,
+		.base.cra_flags		= CRYPTO_ALG_ASYNC,
+		.base.cra_blocksize	= DES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct rk_cipher_ctx),
+		.base.cra_alignmask	= 0x07,
+		.base.cra_module	= THIS_MODULE,
+
+		.init			= rk_ablk_init_tfm,
+		.exit			= rk_ablk_exit_tfm,
+		.min_keysize		= DES3_EDE_KEY_SIZE,
+		.max_keysize		= DES3_EDE_KEY_SIZE,
+		.ivsize			= DES_BLOCK_SIZE,
+		.setkey			= rk_tdes_setkey,
+		.encrypt		= rk_des3_ede_cbc_encrypt,
+		.decrypt		= rk_des3_ede_cbc_decrypt,
+	}
+};
diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index 010f1bb20dad..d66e20a2f54c 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -303,7 +303,7 @@ struct s5p_aes_dev {
 	void __iomem			*aes_ioaddr;
 	int				irq_fc;
 
-	struct ablkcipher_request	*req;
+	struct skcipher_request		*req;
 	struct s5p_aes_ctx		*ctx;
 	struct scatterlist		*sg_src;
 	struct scatterlist		*sg_dst;
@@ -456,7 +456,7 @@ static void s5p_free_sg_cpy(struct s5p_aes_dev *dev, struct scatterlist **sg)
 	if (!*sg)
 		return;
 
-	len = ALIGN(dev->req->nbytes, AES_BLOCK_SIZE);
+	len = ALIGN(dev->req->cryptlen, AES_BLOCK_SIZE);
 	free_pages((unsigned long)sg_virt(*sg), get_order(len));
 
 	kfree(*sg);
@@ -478,27 +478,27 @@ static void s5p_sg_copy_buf(void *buf, struct scatterlist *sg,
 
 static void s5p_sg_done(struct s5p_aes_dev *dev)
 {
-	struct ablkcipher_request *req = dev->req;
-	struct s5p_aes_reqctx *reqctx = ablkcipher_request_ctx(req);
+	struct skcipher_request *req = dev->req;
+	struct s5p_aes_reqctx *reqctx = skcipher_request_ctx(req);
 
 	if (dev->sg_dst_cpy) {
 		dev_dbg(dev->dev,
 			"Copying %d bytes of output data back to original place\n",
-			dev->req->nbytes);
+			dev->req->cryptlen);
 		s5p_sg_copy_buf(sg_virt(dev->sg_dst_cpy), dev->req->dst,
-				dev->req->nbytes, 1);
+				dev->req->cryptlen, 1);
 	}
 	s5p_free_sg_cpy(dev, &dev->sg_src_cpy);
 	s5p_free_sg_cpy(dev, &dev->sg_dst_cpy);
 	if (reqctx->mode & FLAGS_AES_CBC)
-		memcpy_fromio(req->info, dev->aes_ioaddr + SSS_REG_AES_IV_DATA(0), AES_BLOCK_SIZE);
+		memcpy_fromio(req->iv, dev->aes_ioaddr + SSS_REG_AES_IV_DATA(0), AES_BLOCK_SIZE);
 
 	else if (reqctx->mode & FLAGS_AES_CTR)
-		memcpy_fromio(req->info, dev->aes_ioaddr + SSS_REG_AES_CNT_DATA(0), AES_BLOCK_SIZE);
+		memcpy_fromio(req->iv, dev->aes_ioaddr + SSS_REG_AES_CNT_DATA(0), AES_BLOCK_SIZE);
 }
 
 /* Calls the completion. Cannot be called with dev->lock hold. */
-static void s5p_aes_complete(struct ablkcipher_request *req, int err)
+static void s5p_aes_complete(struct skcipher_request *req, int err)
 {
 	req->base.complete(&req->base, err);
 }
@@ -523,7 +523,7 @@ static int s5p_make_sg_cpy(struct s5p_aes_dev *dev, struct scatterlist *src,
 	if (!*dst)
 		return -ENOMEM;
 
-	len = ALIGN(dev->req->nbytes, AES_BLOCK_SIZE);
+	len = ALIGN(dev->req->cryptlen, AES_BLOCK_SIZE);
 	pages = (void *)__get_free_pages(GFP_ATOMIC, get_order(len));
 	if (!pages) {
 		kfree(*dst);
@@ -531,7 +531,7 @@ static int s5p_make_sg_cpy(struct s5p_aes_dev *dev, struct scatterlist *src,
 		return -ENOMEM;
 	}
 
-	s5p_sg_copy_buf(pages, src, dev->req->nbytes, 0);
+	s5p_sg_copy_buf(pages, src, dev->req->cryptlen, 0);
 
 	sg_init_table(*dst, 1);
 	sg_set_buf(*dst, pages, len);
@@ -660,7 +660,7 @@ static irqreturn_t s5p_aes_interrupt(int irq, void *dev_id)
 {
 	struct platform_device *pdev = dev_id;
 	struct s5p_aes_dev *dev = platform_get_drvdata(pdev);
-	struct ablkcipher_request *req;
+	struct skcipher_request *req;
 	int err_dma_tx = 0;
 	int err_dma_rx = 0;
 	int err_dma_hx = 0;
@@ -1870,7 +1870,7 @@ static bool s5p_is_sg_aligned(struct scatterlist *sg)
 }
 
 static int s5p_set_indata_start(struct s5p_aes_dev *dev,
-				struct ablkcipher_request *req)
+				struct skcipher_request *req)
 {
 	struct scatterlist *sg;
 	int err;
@@ -1897,7 +1897,7 @@ static int s5p_set_indata_start(struct s5p_aes_dev *dev,
 }
 
 static int s5p_set_outdata_start(struct s5p_aes_dev *dev,
-				 struct ablkcipher_request *req)
+				 struct skcipher_request *req)
 {
 	struct scatterlist *sg;
 	int err;
@@ -1925,7 +1925,7 @@ static int s5p_set_outdata_start(struct s5p_aes_dev *dev,
 
 static void s5p_aes_crypt_start(struct s5p_aes_dev *dev, unsigned long mode)
 {
-	struct ablkcipher_request *req = dev->req;
+	struct skcipher_request *req = dev->req;
 	u32 aes_control;
 	unsigned long flags;
 	int err;
@@ -1938,12 +1938,12 @@ static void s5p_aes_crypt_start(struct s5p_aes_dev *dev, unsigned long mode)
 
 	if ((mode & FLAGS_AES_MODE_MASK) == FLAGS_AES_CBC) {
 		aes_control |= SSS_AES_CHAIN_MODE_CBC;
-		iv = req->info;
+		iv = req->iv;
 		ctr = NULL;
 	} else if ((mode & FLAGS_AES_MODE_MASK) == FLAGS_AES_CTR) {
 		aes_control |= SSS_AES_CHAIN_MODE_CTR;
 		iv = NULL;
-		ctr = req->info;
+		ctr = req->iv;
 	} else {
 		iv = NULL; /* AES_ECB */
 		ctr = NULL;
@@ -2021,21 +2021,21 @@ static void s5p_tasklet_cb(unsigned long data)
 	if (backlog)
 		backlog->complete(backlog, -EINPROGRESS);
 
-	dev->req = ablkcipher_request_cast(async_req);
+	dev->req = skcipher_request_cast(async_req);
 	dev->ctx = crypto_tfm_ctx(dev->req->base.tfm);
-	reqctx   = ablkcipher_request_ctx(dev->req);
+	reqctx   = skcipher_request_ctx(dev->req);
 
 	s5p_aes_crypt_start(dev, reqctx->mode);
 }
 
 static int s5p_aes_handle_req(struct s5p_aes_dev *dev,
-			      struct ablkcipher_request *req)
+			      struct skcipher_request *req)
 {
 	unsigned long flags;
 	int err;
 
 	spin_lock_irqsave(&dev->lock, flags);
-	err = ablkcipher_enqueue_request(&dev->queue, req);
+	err = crypto_enqueue_request(&dev->queue, &req->base);
 	if (dev->busy) {
 		spin_unlock_irqrestore(&dev->lock, flags);
 		return err;
@@ -2049,17 +2049,17 @@ static int s5p_aes_handle_req(struct s5p_aes_dev *dev,
 	return err;
 }
 
-static int s5p_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
+static int s5p_aes_crypt(struct skcipher_request *req, unsigned long mode)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct s5p_aes_reqctx *reqctx = ablkcipher_request_ctx(req);
-	struct s5p_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s5p_aes_reqctx *reqctx = skcipher_request_ctx(req);
+	struct s5p_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
 	struct s5p_aes_dev *dev = ctx->dev;
 
-	if (!req->nbytes)
+	if (!req->cryptlen)
 		return 0;
 
-	if (!IS_ALIGNED(req->nbytes, AES_BLOCK_SIZE) &&
+	if (!IS_ALIGNED(req->cryptlen, AES_BLOCK_SIZE) &&
 			((mode & FLAGS_AES_MODE_MASK) != FLAGS_AES_CTR)) {
 		dev_dbg(dev->dev, "request size is not exact amount of AES blocks\n");
 		return -EINVAL;
@@ -2070,10 +2070,10 @@ static int s5p_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 	return s5p_aes_handle_req(dev, req);
 }
 
-static int s5p_aes_setkey(struct crypto_ablkcipher *cipher,
+static int s5p_aes_setkey(struct crypto_skcipher *cipher,
 			  const u8 *key, unsigned int keylen)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(cipher);
 	struct s5p_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	if (keylen != AES_KEYSIZE_128 &&
@@ -2087,106 +2087,97 @@ static int s5p_aes_setkey(struct crypto_ablkcipher *cipher,
 	return 0;
 }
 
-static int s5p_aes_ecb_encrypt(struct ablkcipher_request *req)
+static int s5p_aes_ecb_encrypt(struct skcipher_request *req)
 {
 	return s5p_aes_crypt(req, 0);
 }
 
-static int s5p_aes_ecb_decrypt(struct ablkcipher_request *req)
+static int s5p_aes_ecb_decrypt(struct skcipher_request *req)
 {
 	return s5p_aes_crypt(req, FLAGS_AES_DECRYPT);
 }
 
-static int s5p_aes_cbc_encrypt(struct ablkcipher_request *req)
+static int s5p_aes_cbc_encrypt(struct skcipher_request *req)
 {
 	return s5p_aes_crypt(req, FLAGS_AES_CBC);
 }
 
-static int s5p_aes_cbc_decrypt(struct ablkcipher_request *req)
+static int s5p_aes_cbc_decrypt(struct skcipher_request *req)
 {
 	return s5p_aes_crypt(req, FLAGS_AES_DECRYPT | FLAGS_AES_CBC);
 }
 
-static int s5p_aes_ctr_crypt(struct ablkcipher_request *req)
+static int s5p_aes_ctr_crypt(struct skcipher_request *req)
 {
 	return s5p_aes_crypt(req, FLAGS_AES_CTR);
 }
 
-static int s5p_aes_cra_init(struct crypto_tfm *tfm)
+static int s5p_aes_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct s5p_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct s5p_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	ctx->dev = s5p_dev;
-	tfm->crt_ablkcipher.reqsize = sizeof(struct s5p_aes_reqctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct s5p_aes_reqctx));
 
 	return 0;
 }
 
-static struct crypto_alg algs[] = {
+static struct skcipher_alg algs[] = {
 	{
-		.cra_name		= "ecb(aes)",
-		.cra_driver_name	= "ecb-aes-s5p",
-		.cra_priority		= 100,
-		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-					  CRYPTO_ALG_ASYNC |
+		.base.cra_name		= "ecb(aes)",
+		.base.cra_driver_name	= "ecb-aes-s5p",
+		.base.cra_priority	= 100,
+		.base.cra_flags		= CRYPTO_ALG_ASYNC |
 					  CRYPTO_ALG_KERN_DRIVER_ONLY,
-		.cra_blocksize		= AES_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct s5p_aes_ctx),
-		.cra_alignmask		= 0x0f,
-		.cra_type		= &crypto_ablkcipher_type,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= s5p_aes_cra_init,
-		.cra_u.ablkcipher = {
-			.min_keysize	= AES_MIN_KEY_SIZE,
-			.max_keysize	= AES_MAX_KEY_SIZE,
-			.setkey		= s5p_aes_setkey,
-			.encrypt	= s5p_aes_ecb_encrypt,
-			.decrypt	= s5p_aes_ecb_decrypt,
-		}
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct s5p_aes_ctx),
+		.base.cra_alignmask	= 0x0f,
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.setkey			= s5p_aes_setkey,
+		.encrypt		= s5p_aes_ecb_encrypt,
+		.decrypt		= s5p_aes_ecb_decrypt,
+		.init			= s5p_aes_init_tfm,
 	},
 	{
-		.cra_name		= "cbc(aes)",
-		.cra_driver_name	= "cbc-aes-s5p",
-		.cra_priority		= 100,
-		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-					  CRYPTO_ALG_ASYNC |
+		.base.cra_name		= "cbc(aes)",
+		.base.cra_driver_name	= "cbc-aes-s5p",
+		.base.cra_priority	= 100,
+		.base.cra_flags		= CRYPTO_ALG_ASYNC |
 					  CRYPTO_ALG_KERN_DRIVER_ONLY,
-		.cra_blocksize		= AES_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct s5p_aes_ctx),
-		.cra_alignmask		= 0x0f,
-		.cra_type		= &crypto_ablkcipher_type,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= s5p_aes_cra_init,
-		.cra_u.ablkcipher = {
-			.min_keysize	= AES_MIN_KEY_SIZE,
-			.max_keysize	= AES_MAX_KEY_SIZE,
-			.ivsize		= AES_BLOCK_SIZE,
-			.setkey		= s5p_aes_setkey,
-			.encrypt	= s5p_aes_cbc_encrypt,
-			.decrypt	= s5p_aes_cbc_decrypt,
-		}
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct s5p_aes_ctx),
+		.base.cra_alignmask	= 0x0f,
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.ivsize			= AES_BLOCK_SIZE,
+		.setkey			= s5p_aes_setkey,
+		.encrypt		= s5p_aes_cbc_encrypt,
+		.decrypt		= s5p_aes_cbc_decrypt,
+		.init			= s5p_aes_init_tfm,
 	},
 	{
-		.cra_name		= "ctr(aes)",
-		.cra_driver_name	= "ctr-aes-s5p",
-		.cra_priority		= 100,
-		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-					  CRYPTO_ALG_ASYNC |
+		.base.cra_name		= "ctr(aes)",
+		.base.cra_driver_name	= "ctr-aes-s5p",
+		.base.cra_priority	= 100,
+		.base.cra_flags		= CRYPTO_ALG_ASYNC |
 					  CRYPTO_ALG_KERN_DRIVER_ONLY,
-		.cra_blocksize		= 1,
-		.cra_ctxsize		= sizeof(struct s5p_aes_ctx),
-		.cra_alignmask		= 0x0f,
-		.cra_type		= &crypto_ablkcipher_type,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= s5p_aes_cra_init,
-		.cra_u.ablkcipher = {
-			.min_keysize	= AES_MIN_KEY_SIZE,
-			.max_keysize	= AES_MAX_KEY_SIZE,
-			.ivsize		= AES_BLOCK_SIZE,
-			.setkey		= s5p_aes_setkey,
-			.encrypt	= s5p_aes_ctr_crypt,
-			.decrypt	= s5p_aes_ctr_crypt,
-		}
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct s5p_aes_ctx),
+		.base.cra_alignmask	= 0x0f,
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.ivsize			= AES_BLOCK_SIZE,
+		.setkey			= s5p_aes_setkey,
+		.encrypt		= s5p_aes_ctr_crypt,
+		.decrypt		= s5p_aes_ctr_crypt,
+		.init			= s5p_aes_init_tfm,
 	},
 };
 
@@ -2297,7 +2288,7 @@ static int s5p_aes_probe(struct platform_device *pdev)
 	crypto_init_queue(&pdata->queue, CRYPTO_QUEUE_LEN);
 
 	for (i = 0; i < ARRAY_SIZE(algs); i++) {
-		err = crypto_register_alg(&algs[i]);
+		err = crypto_register_skcipher(&algs[i]);
 		if (err)
 			goto err_algs;
 	}
@@ -2334,11 +2325,11 @@ err_hash:
 
 err_algs:
 	if (i < ARRAY_SIZE(algs))
-		dev_err(dev, "can't register '%s': %d\n", algs[i].cra_name,
+		dev_err(dev, "can't register '%s': %d\n", algs[i].base.cra_name,
 			err);
 
 	for (j = 0; j < i; j++)
-		crypto_unregister_alg(&algs[j]);
+		crypto_unregister_skcipher(&algs[j]);
 
 	tasklet_kill(&pdata->tasklet);
 
@@ -2362,7 +2353,7 @@ static int s5p_aes_remove(struct platform_device *pdev)
 		return -ENODEV;
 
 	for (i = 0; i < ARRAY_SIZE(algs); i++)
-		crypto_unregister_alg(&algs[i]);
+		crypto_unregister_skcipher(&algs[i]);
 
 	tasklet_kill(&pdata->tasklet);
 	if (pdata->use_hash) {
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index 8ac8ec6decd5..d4ea2f11ca68 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -547,7 +547,7 @@ unmap_in:
 	return -EINVAL;
 }
 
-static int sahara_aes_process(struct ablkcipher_request *req)
+static int sahara_aes_process(struct skcipher_request *req)
 {
 	struct sahara_dev *dev = dev_ptr;
 	struct sahara_ctx *ctx;
@@ -558,20 +558,20 @@ static int sahara_aes_process(struct ablkcipher_request *req)
 	/* Request is ready to be dispatched by the device */
 	dev_dbg(dev->device,
 		"dispatch request (nbytes=%d, src=%p, dst=%p)\n",
-		req->nbytes, req->src, req->dst);
+		req->cryptlen, req->src, req->dst);
 
 	/* assign new request to device */
-	dev->total = req->nbytes;
+	dev->total = req->cryptlen;
 	dev->in_sg = req->src;
 	dev->out_sg = req->dst;
 
-	rctx = ablkcipher_request_ctx(req);
-	ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
+	rctx = skcipher_request_ctx(req);
+	ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req));
 	rctx->mode &= FLAGS_MODE_MASK;
 	dev->flags = (dev->flags & ~FLAGS_MODE_MASK) | rctx->mode;
 
-	if ((dev->flags & FLAGS_CBC) && req->info)
-		memcpy(dev->iv_base, req->info, AES_KEYSIZE_128);
+	if ((dev->flags & FLAGS_CBC) && req->iv)
+		memcpy(dev->iv_base, req->iv, AES_KEYSIZE_128);
 
 	/* assign new context to device */
 	dev->ctx = ctx;
@@ -597,10 +597,10 @@ static int sahara_aes_process(struct ablkcipher_request *req)
 	return 0;
 }
 
-static int sahara_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int sahara_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			     unsigned int keylen)
 {
-	struct sahara_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct sahara_ctx *ctx = crypto_skcipher_ctx(tfm);
 	int ret;
 
 	ctx->keylen = keylen;
@@ -630,16 +630,16 @@ static int sahara_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 	return ret;
 }
 
-static int sahara_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
+static int sahara_aes_crypt(struct skcipher_request *req, unsigned long mode)
 {
-	struct sahara_aes_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req);
 	struct sahara_dev *dev = dev_ptr;
 	int err = 0;
 
 	dev_dbg(dev->device, "nbytes: %d, enc: %d, cbc: %d\n",
-		req->nbytes, !!(mode & FLAGS_ENCRYPT), !!(mode & FLAGS_CBC));
+		req->cryptlen, !!(mode & FLAGS_ENCRYPT), !!(mode & FLAGS_CBC));
 
-	if (!IS_ALIGNED(req->nbytes, AES_BLOCK_SIZE)) {
+	if (!IS_ALIGNED(req->cryptlen, AES_BLOCK_SIZE)) {
 		dev_err(dev->device,
 			"request size is not exact amount of AES blocks\n");
 		return -EINVAL;
@@ -648,7 +648,7 @@ static int sahara_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 	rctx->mode = mode;
 
 	mutex_lock(&dev->queue_mutex);
-	err = ablkcipher_enqueue_request(&dev->queue, req);
+	err = crypto_enqueue_request(&dev->queue, &req->base);
 	mutex_unlock(&dev->queue_mutex);
 
 	wake_up_process(dev->kthread);
@@ -656,10 +656,10 @@ static int sahara_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 	return err;
 }
 
-static int sahara_aes_ecb_encrypt(struct ablkcipher_request *req)
+static int sahara_aes_ecb_encrypt(struct skcipher_request *req)
 {
-	struct sahara_ctx *ctx = crypto_ablkcipher_ctx(
-		crypto_ablkcipher_reqtfm(req));
+	struct sahara_ctx *ctx = crypto_skcipher_ctx(
+		crypto_skcipher_reqtfm(req));
 	int err;
 
 	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
@@ -669,7 +669,7 @@ static int sahara_aes_ecb_encrypt(struct ablkcipher_request *req)
 		skcipher_request_set_callback(subreq, req->base.flags,
 					      NULL, NULL);
 		skcipher_request_set_crypt(subreq, req->src, req->dst,
-					   req->nbytes, req->info);
+					   req->cryptlen, req->iv);
 		err = crypto_skcipher_encrypt(subreq);
 		skcipher_request_zero(subreq);
 		return err;
@@ -678,10 +678,10 @@ static int sahara_aes_ecb_encrypt(struct ablkcipher_request *req)
 	return sahara_aes_crypt(req, FLAGS_ENCRYPT);
 }
 
-static int sahara_aes_ecb_decrypt(struct ablkcipher_request *req)
+static int sahara_aes_ecb_decrypt(struct skcipher_request *req)
 {
-	struct sahara_ctx *ctx = crypto_ablkcipher_ctx(
-		crypto_ablkcipher_reqtfm(req));
+	struct sahara_ctx *ctx = crypto_skcipher_ctx(
+		crypto_skcipher_reqtfm(req));
 	int err;
 
 	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
@@ -691,7 +691,7 @@ static int sahara_aes_ecb_decrypt(struct ablkcipher_request *req)
 		skcipher_request_set_callback(subreq, req->base.flags,
 					      NULL, NULL);
 		skcipher_request_set_crypt(subreq, req->src, req->dst,
-					   req->nbytes, req->info);
+					   req->cryptlen, req->iv);
 		err = crypto_skcipher_decrypt(subreq);
 		skcipher_request_zero(subreq);
 		return err;
@@ -700,10 +700,10 @@ static int sahara_aes_ecb_decrypt(struct ablkcipher_request *req)
 	return sahara_aes_crypt(req, 0);
 }
 
-static int sahara_aes_cbc_encrypt(struct ablkcipher_request *req)
+static int sahara_aes_cbc_encrypt(struct skcipher_request *req)
 {
-	struct sahara_ctx *ctx = crypto_ablkcipher_ctx(
-		crypto_ablkcipher_reqtfm(req));
+	struct sahara_ctx *ctx = crypto_skcipher_ctx(
+		crypto_skcipher_reqtfm(req));
 	int err;
 
 	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
@@ -713,7 +713,7 @@ static int sahara_aes_cbc_encrypt(struct ablkcipher_request *req)
 		skcipher_request_set_callback(subreq, req->base.flags,
 					      NULL, NULL);
 		skcipher_request_set_crypt(subreq, req->src, req->dst,
-					   req->nbytes, req->info);
+					   req->cryptlen, req->iv);
 		err = crypto_skcipher_encrypt(subreq);
 		skcipher_request_zero(subreq);
 		return err;
@@ -722,10 +722,10 @@ static int sahara_aes_cbc_encrypt(struct ablkcipher_request *req)
 	return sahara_aes_crypt(req, FLAGS_ENCRYPT | FLAGS_CBC);
 }
 
-static int sahara_aes_cbc_decrypt(struct ablkcipher_request *req)
+static int sahara_aes_cbc_decrypt(struct skcipher_request *req)
 {
-	struct sahara_ctx *ctx = crypto_ablkcipher_ctx(
-		crypto_ablkcipher_reqtfm(req));
+	struct sahara_ctx *ctx = crypto_skcipher_ctx(
+		crypto_skcipher_reqtfm(req));
 	int err;
 
 	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
@@ -735,7 +735,7 @@ static int sahara_aes_cbc_decrypt(struct ablkcipher_request *req)
 		skcipher_request_set_callback(subreq, req->base.flags,
 					      NULL, NULL);
 		skcipher_request_set_crypt(subreq, req->src, req->dst,
-					   req->nbytes, req->info);
+					   req->cryptlen, req->iv);
 		err = crypto_skcipher_decrypt(subreq);
 		skcipher_request_zero(subreq);
 		return err;
@@ -744,10 +744,10 @@ static int sahara_aes_cbc_decrypt(struct ablkcipher_request *req)
 	return sahara_aes_crypt(req, FLAGS_CBC);
 }
 
-static int sahara_aes_cra_init(struct crypto_tfm *tfm)
+static int sahara_aes_init_tfm(struct crypto_skcipher *tfm)
 {
-	const char *name = crypto_tfm_alg_name(tfm);
-	struct sahara_ctx *ctx = crypto_tfm_ctx(tfm);
+	const char *name = crypto_tfm_alg_name(&tfm->base);
+	struct sahara_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	ctx->fallback = crypto_alloc_sync_skcipher(name, 0,
 					      CRYPTO_ALG_NEED_FALLBACK);
@@ -756,14 +756,14 @@ static int sahara_aes_cra_init(struct crypto_tfm *tfm)
 		return PTR_ERR(ctx->fallback);
 	}
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct sahara_aes_reqctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct sahara_aes_reqctx));
 
 	return 0;
 }
 
-static void sahara_aes_cra_exit(struct crypto_tfm *tfm)
+static void sahara_aes_exit_tfm(struct crypto_skcipher *tfm)
 {
-	struct sahara_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct sahara_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	crypto_free_sync_skcipher(ctx->fallback);
 }
@@ -1071,8 +1071,8 @@ static int sahara_queue_manage(void *data)
 
 				ret = sahara_sha_process(req);
 			} else {
-				struct ablkcipher_request *req =
-					ablkcipher_request_cast(async_req);
+				struct skcipher_request *req =
+					skcipher_request_cast(async_req);
 
 				ret = sahara_aes_process(req);
 			}
@@ -1189,48 +1189,42 @@ static int sahara_sha_cra_init(struct crypto_tfm *tfm)
 	return 0;
 }
 
-static struct crypto_alg aes_algs[] = {
+static struct skcipher_alg aes_algs[] = {
 {
-	.cra_name		= "ecb(aes)",
-	.cra_driver_name	= "sahara-ecb-aes",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-			CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct sahara_ctx),
-	.cra_alignmask		= 0x0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= sahara_aes_cra_init,
-	.cra_exit		= sahara_aes_cra_exit,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE ,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.setkey		= sahara_aes_setkey,
-		.encrypt	= sahara_aes_ecb_encrypt,
-		.decrypt	= sahara_aes_ecb_decrypt,
-	}
+	.base.cra_name		= "ecb(aes)",
+	.base.cra_driver_name	= "sahara-ecb-aes",
+	.base.cra_priority	= 300,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct sahara_ctx),
+	.base.cra_alignmask	= 0x0,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= sahara_aes_init_tfm,
+	.exit			= sahara_aes_exit_tfm,
+	.min_keysize		= AES_MIN_KEY_SIZE ,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= sahara_aes_setkey,
+	.encrypt		= sahara_aes_ecb_encrypt,
+	.decrypt		= sahara_aes_ecb_decrypt,
 }, {
-	.cra_name		= "cbc(aes)",
-	.cra_driver_name	= "sahara-cbc-aes",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-			CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct sahara_ctx),
-	.cra_alignmask		= 0x0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= sahara_aes_cra_init,
-	.cra_exit		= sahara_aes_cra_exit,
-	.cra_u.ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE ,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= sahara_aes_setkey,
-		.encrypt	= sahara_aes_cbc_encrypt,
-		.decrypt	= sahara_aes_cbc_decrypt,
-	}
+	.base.cra_name		= "cbc(aes)",
+	.base.cra_driver_name	= "sahara-cbc-aes",
+	.base.cra_priority	= 300,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct sahara_ctx),
+	.base.cra_alignmask	= 0x0,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= sahara_aes_init_tfm,
+	.exit			= sahara_aes_exit_tfm,
+	.min_keysize		= AES_MIN_KEY_SIZE ,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= sahara_aes_setkey,
+	.encrypt		= sahara_aes_cbc_encrypt,
+	.decrypt		= sahara_aes_cbc_decrypt,
 }
 };
 
@@ -1318,7 +1312,7 @@ static int sahara_register_algs(struct sahara_dev *dev)
 	unsigned int i, j, k, l;
 
 	for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
-		err = crypto_register_alg(&aes_algs[i]);
+		err = crypto_register_skcipher(&aes_algs[i]);
 		if (err)
 			goto err_aes_algs;
 	}
@@ -1348,7 +1342,7 @@ err_sha_v3_algs:
 
 err_aes_algs:
 	for (j = 0; j < i; j++)
-		crypto_unregister_alg(&aes_algs[j]);
+		crypto_unregister_skcipher(&aes_algs[j]);
 
 	return err;
 }
@@ -1358,7 +1352,7 @@ static void sahara_unregister_algs(struct sahara_dev *dev)
 	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(aes_algs); i++)
-		crypto_unregister_alg(&aes_algs[i]);
+		crypto_unregister_skcipher(&aes_algs[i]);
 
 	for (i = 0; i < ARRAY_SIZE(sha_v3_algs); i++)
 		crypto_unregister_ahash(&sha_v3_algs[i]);
diff --git a/drivers/crypto/stm32/stm32-cryp.c b/drivers/crypto/stm32/stm32-cryp.c
index ba5ea6434f9c..d347a1d6e351 100644
--- a/drivers/crypto/stm32/stm32-cryp.c
+++ b/drivers/crypto/stm32/stm32-cryp.c
@@ -19,6 +19,7 @@
 #include <crypto/engine.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
 
 #define DRIVER_NAME             "stm32-cryp"
 
@@ -137,7 +138,7 @@ struct stm32_cryp {
 
 	struct crypto_engine    *engine;
 
-	struct ablkcipher_request *req;
+	struct skcipher_request *req;
 	struct aead_request     *areq;
 
 	size_t                  authsize;
@@ -395,8 +396,8 @@ static void stm32_cryp_hw_write_iv(struct stm32_cryp *cryp, u32 *iv)
 
 static void stm32_cryp_get_iv(struct stm32_cryp *cryp)
 {
-	struct ablkcipher_request *req = cryp->req;
-	u32 *tmp = req->info;
+	struct skcipher_request *req = cryp->req;
+	u32 *tmp = (void *)req->iv;
 
 	if (!tmp)
 		return;
@@ -616,7 +617,7 @@ static int stm32_cryp_hw_init(struct stm32_cryp *cryp)
 	case CR_TDES_CBC:
 	case CR_AES_CBC:
 	case CR_AES_CTR:
-		stm32_cryp_hw_write_iv(cryp, (u32 *)cryp->req->info);
+		stm32_cryp_hw_write_iv(cryp, (u32 *)cryp->req->iv);
 		break;
 
 	default:
@@ -667,7 +668,7 @@ static void stm32_cryp_finish_req(struct stm32_cryp *cryp, int err)
 	if (is_gcm(cryp) || is_ccm(cryp))
 		crypto_finalize_aead_request(cryp->engine, cryp->areq, err);
 	else
-		crypto_finalize_ablkcipher_request(cryp->engine, cryp->req,
+		crypto_finalize_skcipher_request(cryp->engine, cryp->req,
 						   err);
 
 	memset(cryp->ctx->key, 0, cryp->ctx->keylen);
@@ -685,11 +686,11 @@ static int stm32_cryp_cipher_one_req(struct crypto_engine *engine, void *areq);
 static int stm32_cryp_prepare_cipher_req(struct crypto_engine *engine,
 					 void *areq);
 
-static int stm32_cryp_cra_init(struct crypto_tfm *tfm)
+static int stm32_cryp_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct stm32_cryp_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct stm32_cryp_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct stm32_cryp_reqctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct stm32_cryp_reqctx));
 
 	ctx->enginectx.op.do_one_request = stm32_cryp_cipher_one_req;
 	ctx->enginectx.op.prepare_request = stm32_cryp_prepare_cipher_req;
@@ -714,11 +715,11 @@ static int stm32_cryp_aes_aead_init(struct crypto_aead *tfm)
 	return 0;
 }
 
-static int stm32_cryp_crypt(struct ablkcipher_request *req, unsigned long mode)
+static int stm32_cryp_crypt(struct skcipher_request *req, unsigned long mode)
 {
-	struct stm32_cryp_ctx *ctx = crypto_ablkcipher_ctx(
-			crypto_ablkcipher_reqtfm(req));
-	struct stm32_cryp_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct stm32_cryp_ctx *ctx = crypto_skcipher_ctx(
+			crypto_skcipher_reqtfm(req));
+	struct stm32_cryp_reqctx *rctx = skcipher_request_ctx(req);
 	struct stm32_cryp *cryp = stm32_cryp_find_dev(ctx);
 
 	if (!cryp)
@@ -726,7 +727,7 @@ static int stm32_cryp_crypt(struct ablkcipher_request *req, unsigned long mode)
 
 	rctx->mode = mode;
 
-	return crypto_transfer_ablkcipher_request_to_engine(cryp->engine, req);
+	return crypto_transfer_skcipher_request_to_engine(cryp->engine, req);
 }
 
 static int stm32_cryp_aead_crypt(struct aead_request *req, unsigned long mode)
@@ -743,10 +744,10 @@ static int stm32_cryp_aead_crypt(struct aead_request *req, unsigned long mode)
 	return crypto_transfer_aead_request_to_engine(cryp->engine, req);
 }
 
-static int stm32_cryp_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int stm32_cryp_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			     unsigned int keylen)
 {
-	struct stm32_cryp_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct stm32_cryp_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	memcpy(ctx->key, key, keylen);
 	ctx->keylen = keylen;
@@ -754,7 +755,7 @@ static int stm32_cryp_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 	return 0;
 }
 
-static int stm32_cryp_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int stm32_cryp_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
 				 unsigned int keylen)
 {
 	if (keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_192 &&
@@ -764,17 +765,17 @@ static int stm32_cryp_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 		return stm32_cryp_setkey(tfm, key, keylen);
 }
 
-static int stm32_cryp_des_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int stm32_cryp_des_setkey(struct crypto_skcipher *tfm, const u8 *key,
 				 unsigned int keylen)
 {
-	return verify_ablkcipher_des_key(tfm, key) ?:
+	return verify_skcipher_des_key(tfm, key) ?:
 	       stm32_cryp_setkey(tfm, key, keylen);
 }
 
-static int stm32_cryp_tdes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+static int stm32_cryp_tdes_setkey(struct crypto_skcipher *tfm, const u8 *key,
 				  unsigned int keylen)
 {
-	return verify_ablkcipher_des3_key(tfm, key) ?:
+	return verify_skcipher_des3_key(tfm, key) ?:
 	       stm32_cryp_setkey(tfm, key, keylen);
 }
 
@@ -818,32 +819,32 @@ static int stm32_cryp_aes_ccm_setauthsize(struct crypto_aead *tfm,
 	return 0;
 }
 
-static int stm32_cryp_aes_ecb_encrypt(struct ablkcipher_request *req)
+static int stm32_cryp_aes_ecb_encrypt(struct skcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_AES | FLG_ECB | FLG_ENCRYPT);
 }
 
-static int stm32_cryp_aes_ecb_decrypt(struct ablkcipher_request *req)
+static int stm32_cryp_aes_ecb_decrypt(struct skcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_AES | FLG_ECB);
 }
 
-static int stm32_cryp_aes_cbc_encrypt(struct ablkcipher_request *req)
+static int stm32_cryp_aes_cbc_encrypt(struct skcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_AES | FLG_CBC | FLG_ENCRYPT);
 }
 
-static int stm32_cryp_aes_cbc_decrypt(struct ablkcipher_request *req)
+static int stm32_cryp_aes_cbc_decrypt(struct skcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_AES | FLG_CBC);
 }
 
-static int stm32_cryp_aes_ctr_encrypt(struct ablkcipher_request *req)
+static int stm32_cryp_aes_ctr_encrypt(struct skcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_AES | FLG_CTR | FLG_ENCRYPT);
 }
 
-static int stm32_cryp_aes_ctr_decrypt(struct ablkcipher_request *req)
+static int stm32_cryp_aes_ctr_decrypt(struct skcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_AES | FLG_CTR);
 }
@@ -868,47 +869,47 @@ static int stm32_cryp_aes_ccm_decrypt(struct aead_request *req)
 	return stm32_cryp_aead_crypt(req, FLG_AES | FLG_CCM);
 }
 
-static int stm32_cryp_des_ecb_encrypt(struct ablkcipher_request *req)
+static int stm32_cryp_des_ecb_encrypt(struct skcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_DES | FLG_ECB | FLG_ENCRYPT);
 }
 
-static int stm32_cryp_des_ecb_decrypt(struct ablkcipher_request *req)
+static int stm32_cryp_des_ecb_decrypt(struct skcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_DES | FLG_ECB);
 }
 
-static int stm32_cryp_des_cbc_encrypt(struct ablkcipher_request *req)
+static int stm32_cryp_des_cbc_encrypt(struct skcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_DES | FLG_CBC | FLG_ENCRYPT);
 }
 
-static int stm32_cryp_des_cbc_decrypt(struct ablkcipher_request *req)
+static int stm32_cryp_des_cbc_decrypt(struct skcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_DES | FLG_CBC);
 }
 
-static int stm32_cryp_tdes_ecb_encrypt(struct ablkcipher_request *req)
+static int stm32_cryp_tdes_ecb_encrypt(struct skcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_TDES | FLG_ECB | FLG_ENCRYPT);
 }
 
-static int stm32_cryp_tdes_ecb_decrypt(struct ablkcipher_request *req)
+static int stm32_cryp_tdes_ecb_decrypt(struct skcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_TDES | FLG_ECB);
 }
 
-static int stm32_cryp_tdes_cbc_encrypt(struct ablkcipher_request *req)
+static int stm32_cryp_tdes_cbc_encrypt(struct skcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_TDES | FLG_CBC | FLG_ENCRYPT);
 }
 
-static int stm32_cryp_tdes_cbc_decrypt(struct ablkcipher_request *req)
+static int stm32_cryp_tdes_cbc_decrypt(struct skcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_TDES | FLG_CBC);
 }
 
-static int stm32_cryp_prepare_req(struct ablkcipher_request *req,
+static int stm32_cryp_prepare_req(struct skcipher_request *req,
 				  struct aead_request *areq)
 {
 	struct stm32_cryp_ctx *ctx;
@@ -919,7 +920,7 @@ static int stm32_cryp_prepare_req(struct ablkcipher_request *req,
 	if (!req && !areq)
 		return -EINVAL;
 
-	ctx = req ? crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req)) :
+	ctx = req ? crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)) :
 		    crypto_aead_ctx(crypto_aead_reqtfm(areq));
 
 	cryp = ctx->cryp;
@@ -927,7 +928,7 @@ static int stm32_cryp_prepare_req(struct ablkcipher_request *req,
 	if (!cryp)
 		return -ENODEV;
 
-	rctx = req ? ablkcipher_request_ctx(req) : aead_request_ctx(areq);
+	rctx = req ? skcipher_request_ctx(req) : aead_request_ctx(areq);
 	rctx->mode &= FLG_MODE_MASK;
 
 	ctx->cryp = cryp;
@@ -939,7 +940,7 @@ static int stm32_cryp_prepare_req(struct ablkcipher_request *req,
 	if (req) {
 		cryp->req = req;
 		cryp->areq = NULL;
-		cryp->total_in = req->nbytes;
+		cryp->total_in = req->cryptlen;
 		cryp->total_out = cryp->total_in;
 	} else {
 		/*
@@ -1016,8 +1017,8 @@ static int stm32_cryp_prepare_req(struct ablkcipher_request *req,
 static int stm32_cryp_prepare_cipher_req(struct crypto_engine *engine,
 					 void *areq)
 {
-	struct ablkcipher_request *req = container_of(areq,
-						      struct ablkcipher_request,
+	struct skcipher_request *req = container_of(areq,
+						      struct skcipher_request,
 						      base);
 
 	return stm32_cryp_prepare_req(req, NULL);
@@ -1025,11 +1026,11 @@ static int stm32_cryp_prepare_cipher_req(struct crypto_engine *engine,
 
 static int stm32_cryp_cipher_one_req(struct crypto_engine *engine, void *areq)
 {
-	struct ablkcipher_request *req = container_of(areq,
-						      struct ablkcipher_request,
+	struct skcipher_request *req = container_of(areq,
+						      struct skcipher_request,
 						      base);
-	struct stm32_cryp_ctx *ctx = crypto_ablkcipher_ctx(
-			crypto_ablkcipher_reqtfm(req));
+	struct stm32_cryp_ctx *ctx = crypto_skcipher_ctx(
+			crypto_skcipher_reqtfm(req));
 	struct stm32_cryp *cryp = ctx->cryp;
 
 	if (!cryp)
@@ -1724,150 +1725,129 @@ static irqreturn_t stm32_cryp_irq(int irq, void *arg)
 	return IRQ_WAKE_THREAD;
 }
 
-static struct crypto_alg crypto_algs[] = {
-{
-	.cra_name		= "ecb(aes)",
-	.cra_driver_name	= "stm32-ecb-aes",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= stm32_cryp_cra_init,
-	.cra_ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.setkey		= stm32_cryp_aes_setkey,
-		.encrypt	= stm32_cryp_aes_ecb_encrypt,
-		.decrypt	= stm32_cryp_aes_ecb_decrypt,
-	}
+static struct skcipher_alg crypto_algs[] = {
+{
+	.base.cra_name		= "ecb(aes)",
+	.base.cra_driver_name	= "stm32-ecb-aes",
+	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct stm32_cryp_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= stm32_cryp_init_tfm,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= stm32_cryp_aes_setkey,
+	.encrypt		= stm32_cryp_aes_ecb_encrypt,
+	.decrypt		= stm32_cryp_aes_ecb_decrypt,
 },
 {
-	.cra_name		= "cbc(aes)",
-	.cra_driver_name	= "stm32-cbc-aes",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= stm32_cryp_cra_init,
-	.cra_ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= stm32_cryp_aes_setkey,
-		.encrypt	= stm32_cryp_aes_cbc_encrypt,
-		.decrypt	= stm32_cryp_aes_cbc_decrypt,
-	}
+	.base.cra_name		= "cbc(aes)",
+	.base.cra_driver_name	= "stm32-cbc-aes",
+	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct stm32_cryp_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= stm32_cryp_init_tfm,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= stm32_cryp_aes_setkey,
+	.encrypt		= stm32_cryp_aes_cbc_encrypt,
+	.decrypt		= stm32_cryp_aes_cbc_decrypt,
 },
 {
-	.cra_name		= "ctr(aes)",
-	.cra_driver_name	= "stm32-ctr-aes",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= stm32_cryp_cra_init,
-	.cra_ablkcipher = {
-		.min_keysize	= AES_MIN_KEY_SIZE,
-		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
-		.setkey		= stm32_cryp_aes_setkey,
-		.encrypt	= stm32_cryp_aes_ctr_encrypt,
-		.decrypt	= stm32_cryp_aes_ctr_decrypt,
-	}
+	.base.cra_name		= "ctr(aes)",
+	.base.cra_driver_name	= "stm32-ctr-aes",
+	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct stm32_cryp_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= stm32_cryp_init_tfm,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= stm32_cryp_aes_setkey,
+	.encrypt		= stm32_cryp_aes_ctr_encrypt,
+	.decrypt		= stm32_cryp_aes_ctr_decrypt,
 },
 {
-	.cra_name		= "ecb(des)",
-	.cra_driver_name	= "stm32-ecb-des",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= stm32_cryp_cra_init,
-	.cra_ablkcipher = {
-		.min_keysize	= DES_BLOCK_SIZE,
-		.max_keysize	= DES_BLOCK_SIZE,
-		.setkey		= stm32_cryp_des_setkey,
-		.encrypt	= stm32_cryp_des_ecb_encrypt,
-		.decrypt	= stm32_cryp_des_ecb_decrypt,
-	}
+	.base.cra_name		= "ecb(des)",
+	.base.cra_driver_name	= "stm32-ecb-des",
+	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= DES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct stm32_cryp_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= stm32_cryp_init_tfm,
+	.min_keysize		= DES_BLOCK_SIZE,
+	.max_keysize		= DES_BLOCK_SIZE,
+	.setkey			= stm32_cryp_des_setkey,
+	.encrypt		= stm32_cryp_des_ecb_encrypt,
+	.decrypt		= stm32_cryp_des_ecb_decrypt,
 },
 {
-	.cra_name		= "cbc(des)",
-	.cra_driver_name	= "stm32-cbc-des",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= stm32_cryp_cra_init,
-	.cra_ablkcipher = {
-		.min_keysize	= DES_BLOCK_SIZE,
-		.max_keysize	= DES_BLOCK_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= stm32_cryp_des_setkey,
-		.encrypt	= stm32_cryp_des_cbc_encrypt,
-		.decrypt	= stm32_cryp_des_cbc_decrypt,
-	}
+	.base.cra_name		= "cbc(des)",
+	.base.cra_driver_name	= "stm32-cbc-des",
+	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= DES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct stm32_cryp_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= stm32_cryp_init_tfm,
+	.min_keysize		= DES_BLOCK_SIZE,
+	.max_keysize		= DES_BLOCK_SIZE,
+	.ivsize			= DES_BLOCK_SIZE,
+	.setkey			= stm32_cryp_des_setkey,
+	.encrypt		= stm32_cryp_des_cbc_encrypt,
+	.decrypt		= stm32_cryp_des_cbc_decrypt,
 },
 {
-	.cra_name		= "ecb(des3_ede)",
-	.cra_driver_name	= "stm32-ecb-des3",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= stm32_cryp_cra_init,
-	.cra_ablkcipher = {
-		.min_keysize	= 3 * DES_BLOCK_SIZE,
-		.max_keysize	= 3 * DES_BLOCK_SIZE,
-		.setkey		= stm32_cryp_tdes_setkey,
-		.encrypt	= stm32_cryp_tdes_ecb_encrypt,
-		.decrypt	= stm32_cryp_tdes_ecb_decrypt,
-	}
+	.base.cra_name		= "ecb(des3_ede)",
+	.base.cra_driver_name	= "stm32-ecb-des3",
+	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= DES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct stm32_cryp_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= stm32_cryp_init_tfm,
+	.min_keysize		= 3 * DES_BLOCK_SIZE,
+	.max_keysize		= 3 * DES_BLOCK_SIZE,
+	.setkey			= stm32_cryp_tdes_setkey,
+	.encrypt		= stm32_cryp_tdes_ecb_encrypt,
+	.decrypt		= stm32_cryp_tdes_ecb_decrypt,
 },
 {
-	.cra_name		= "cbc(des3_ede)",
-	.cra_driver_name	= "stm32-cbc-des3",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
-	.cra_alignmask		= 0xf,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= stm32_cryp_cra_init,
-	.cra_ablkcipher = {
-		.min_keysize	= 3 * DES_BLOCK_SIZE,
-		.max_keysize	= 3 * DES_BLOCK_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= stm32_cryp_tdes_setkey,
-		.encrypt	= stm32_cryp_tdes_cbc_encrypt,
-		.decrypt	= stm32_cryp_tdes_cbc_decrypt,
-	}
+	.base.cra_name		= "cbc(des3_ede)",
+	.base.cra_driver_name	= "stm32-cbc-des3",
+	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_ASYNC,
+	.base.cra_blocksize	= DES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct stm32_cryp_ctx),
+	.base.cra_alignmask	= 0xf,
+	.base.cra_module	= THIS_MODULE,
+
+	.init			= stm32_cryp_init_tfm,
+	.min_keysize		= 3 * DES_BLOCK_SIZE,
+	.max_keysize		= 3 * DES_BLOCK_SIZE,
+	.ivsize			= DES_BLOCK_SIZE,
+	.setkey			= stm32_cryp_tdes_setkey,
+	.encrypt		= stm32_cryp_tdes_cbc_encrypt,
+	.decrypt		= stm32_cryp_tdes_cbc_decrypt,
 },
 };
 
@@ -2010,7 +1990,7 @@ static int stm32_cryp_probe(struct platform_device *pdev)
 		goto err_engine2;
 	}
 
-	ret = crypto_register_algs(crypto_algs, ARRAY_SIZE(crypto_algs));
+	ret = crypto_register_skciphers(crypto_algs, ARRAY_SIZE(crypto_algs));
 	if (ret) {
 		dev_err(dev, "Could not register algs\n");
 		goto err_algs;
@@ -2027,7 +2007,7 @@ static int stm32_cryp_probe(struct platform_device *pdev)
 	return 0;
 
 err_aead_algs:
-	crypto_unregister_algs(crypto_algs, ARRAY_SIZE(crypto_algs));
+	crypto_unregister_skciphers(crypto_algs, ARRAY_SIZE(crypto_algs));
 err_algs:
 err_engine2:
 	crypto_engine_exit(cryp->engine);
@@ -2059,7 +2039,7 @@ static int stm32_cryp_remove(struct platform_device *pdev)
 		return ret;
 
 	crypto_unregister_aeads(aead_algs, ARRAY_SIZE(aead_algs));
-	crypto_unregister_algs(crypto_algs, ARRAY_SIZE(crypto_algs));
+	crypto_unregister_skciphers(crypto_algs, ARRAY_SIZE(crypto_algs));
 
 	crypto_engine_exit(cryp->engine);
 
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 56e3068c9947..d71d65846e47 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -35,7 +35,7 @@
 #include <crypto/md5.h>
 #include <crypto/internal/aead.h>
 #include <crypto/authenc.h>
-#include <crypto/skcipher.h>
+#include <crypto/internal/skcipher.h>
 #include <crypto/hash.h>
 #include <crypto/internal/hash.h>
 #include <crypto/scatterwalk.h>
@@ -1490,10 +1490,10 @@ static int aead_decrypt(struct aead_request *req)
 	return ipsec_esp(edesc, req, false, ipsec_esp_decrypt_swauth_done);
 }
 
-static int ablkcipher_setkey(struct crypto_ablkcipher *cipher,
+static int skcipher_setkey(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen)
 {
-	struct talitos_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	struct talitos_ctx *ctx = crypto_skcipher_ctx(cipher);
 	struct device *dev = ctx->dev;
 
 	if (ctx->keylen)
@@ -1507,39 +1507,39 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *cipher,
 	return 0;
 }
 
-static int ablkcipher_des_setkey(struct crypto_ablkcipher *cipher,
+static int skcipher_des_setkey(struct crypto_skcipher *cipher,
 				 const u8 *key, unsigned int keylen)
 {
-	return verify_ablkcipher_des_key(cipher, key) ?:
-	       ablkcipher_setkey(cipher, key, keylen);
+	return verify_skcipher_des_key(cipher, key) ?:
+	       skcipher_setkey(cipher, key, keylen);
 }
 
-static int ablkcipher_des3_setkey(struct crypto_ablkcipher *cipher,
+static int skcipher_des3_setkey(struct crypto_skcipher *cipher,
 				  const u8 *key, unsigned int keylen)
 {
-	return verify_ablkcipher_des3_key(cipher, key) ?:
-	       ablkcipher_setkey(cipher, key, keylen);
+	return verify_skcipher_des3_key(cipher, key) ?:
+	       skcipher_setkey(cipher, key, keylen);
 }
 
-static int ablkcipher_aes_setkey(struct crypto_ablkcipher *cipher,
+static int skcipher_aes_setkey(struct crypto_skcipher *cipher,
 				  const u8 *key, unsigned int keylen)
 {
 	if (keylen == AES_KEYSIZE_128 || keylen == AES_KEYSIZE_192 ||
 	    keylen == AES_KEYSIZE_256)
-		return ablkcipher_setkey(cipher, key, keylen);
+		return skcipher_setkey(cipher, key, keylen);
 
-	crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	crypto_skcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
 
 	return -EINVAL;
 }
 
 static void common_nonsnoop_unmap(struct device *dev,
 				  struct talitos_edesc *edesc,
-				  struct ablkcipher_request *areq)
+				  struct skcipher_request *areq)
 {
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[5], DMA_FROM_DEVICE);
 
-	talitos_sg_unmap(dev, edesc, areq->src, areq->dst, areq->nbytes, 0);
+	talitos_sg_unmap(dev, edesc, areq->src, areq->dst, areq->cryptlen, 0);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[1], DMA_TO_DEVICE);
 
 	if (edesc->dma_len)
@@ -1547,20 +1547,20 @@ static void common_nonsnoop_unmap(struct device *dev,
 				 DMA_BIDIRECTIONAL);
 }
 
-static void ablkcipher_done(struct device *dev,
+static void skcipher_done(struct device *dev,
 			    struct talitos_desc *desc, void *context,
 			    int err)
 {
-	struct ablkcipher_request *areq = context;
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(areq);
-	struct talitos_ctx *ctx = crypto_ablkcipher_ctx(cipher);
-	unsigned int ivsize = crypto_ablkcipher_ivsize(cipher);
+	struct skcipher_request *areq = context;
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(areq);
+	struct talitos_ctx *ctx = crypto_skcipher_ctx(cipher);
+	unsigned int ivsize = crypto_skcipher_ivsize(cipher);
 	struct talitos_edesc *edesc;
 
 	edesc = container_of(desc, struct talitos_edesc, desc);
 
 	common_nonsnoop_unmap(dev, edesc, areq);
-	memcpy(areq->info, ctx->iv, ivsize);
+	memcpy(areq->iv, ctx->iv, ivsize);
 
 	kfree(edesc);
 
@@ -1568,17 +1568,17 @@ static void ablkcipher_done(struct device *dev,
 }
 
 static int common_nonsnoop(struct talitos_edesc *edesc,
-			   struct ablkcipher_request *areq,
+			   struct skcipher_request *areq,
 			   void (*callback) (struct device *dev,
 					     struct talitos_desc *desc,
 					     void *context, int error))
 {
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(areq);
-	struct talitos_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(areq);
+	struct talitos_ctx *ctx = crypto_skcipher_ctx(cipher);
 	struct device *dev = ctx->dev;
 	struct talitos_desc *desc = &edesc->desc;
-	unsigned int cryptlen = areq->nbytes;
-	unsigned int ivsize = crypto_ablkcipher_ivsize(cipher);
+	unsigned int cryptlen = areq->cryptlen;
+	unsigned int ivsize = crypto_skcipher_ivsize(cipher);
 	int sg_count, ret;
 	bool sync_needed = false;
 	struct talitos_private *priv = dev_get_drvdata(dev);
@@ -1638,65 +1638,65 @@ static int common_nonsnoop(struct talitos_edesc *edesc,
 	return ret;
 }
 
-static struct talitos_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request *
+static struct talitos_edesc *skcipher_edesc_alloc(struct skcipher_request *
 						    areq, bool encrypt)
 {
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(areq);
-	struct talitos_ctx *ctx = crypto_ablkcipher_ctx(cipher);
-	unsigned int ivsize = crypto_ablkcipher_ivsize(cipher);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(areq);
+	struct talitos_ctx *ctx = crypto_skcipher_ctx(cipher);
+	unsigned int ivsize = crypto_skcipher_ivsize(cipher);
 
 	return talitos_edesc_alloc(ctx->dev, areq->src, areq->dst,
-				   areq->info, 0, areq->nbytes, 0, ivsize, 0,
+				   areq->iv, 0, areq->cryptlen, 0, ivsize, 0,
 				   areq->base.flags, encrypt);
 }
 
-static int ablkcipher_encrypt(struct ablkcipher_request *areq)
+static int skcipher_encrypt(struct skcipher_request *areq)
 {
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(areq);
-	struct talitos_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(areq);
+	struct talitos_ctx *ctx = crypto_skcipher_ctx(cipher);
 	struct talitos_edesc *edesc;
 	unsigned int blocksize =
-			crypto_tfm_alg_blocksize(crypto_ablkcipher_tfm(cipher));
+			crypto_tfm_alg_blocksize(crypto_skcipher_tfm(cipher));
 
-	if (!areq->nbytes)
+	if (!areq->cryptlen)
 		return 0;
 
-	if (areq->nbytes % blocksize)
+	if (areq->cryptlen % blocksize)
 		return -EINVAL;
 
 	/* allocate extended descriptor */
-	edesc = ablkcipher_edesc_alloc(areq, true);
+	edesc = skcipher_edesc_alloc(areq, true);
 	if (IS_ERR(edesc))
 		return PTR_ERR(edesc);
 
 	/* set encrypt */
 	edesc->desc.hdr = ctx->desc_hdr_template | DESC_HDR_MODE0_ENCRYPT;
 
-	return common_nonsnoop(edesc, areq, ablkcipher_done);
+	return common_nonsnoop(edesc, areq, skcipher_done);
 }
 
-static int ablkcipher_decrypt(struct ablkcipher_request *areq)
+static int skcipher_decrypt(struct skcipher_request *areq)
 {
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(areq);
-	struct talitos_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(areq);
+	struct talitos_ctx *ctx = crypto_skcipher_ctx(cipher);
 	struct talitos_edesc *edesc;
 	unsigned int blocksize =
-			crypto_tfm_alg_blocksize(crypto_ablkcipher_tfm(cipher));
+			crypto_tfm_alg_blocksize(crypto_skcipher_tfm(cipher));
 
-	if (!areq->nbytes)
+	if (!areq->cryptlen)
 		return 0;
 
-	if (areq->nbytes % blocksize)
+	if (areq->cryptlen % blocksize)
 		return -EINVAL;
 
 	/* allocate extended descriptor */
-	edesc = ablkcipher_edesc_alloc(areq, false);
+	edesc = skcipher_edesc_alloc(areq, false);
 	if (IS_ERR(edesc))
 		return PTR_ERR(edesc);
 
 	edesc->desc.hdr = ctx->desc_hdr_template | DESC_HDR_DIR_INBOUND;
 
-	return common_nonsnoop(edesc, areq, ablkcipher_done);
+	return common_nonsnoop(edesc, areq, skcipher_done);
 }
 
 static void common_nonsnoop_hash_unmap(struct device *dev,
@@ -1704,6 +1704,7 @@ static void common_nonsnoop_hash_unmap(struct device *dev,
 				       struct ahash_request *areq)
 {
 	struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	bool is_sec1 = has_ftr_sec1(priv);
 	struct talitos_desc *desc = &edesc->desc;
@@ -1714,6 +1715,9 @@ static void common_nonsnoop_hash_unmap(struct device *dev,
 	if (desc->next_desc &&
 	    desc->ptr[5].ptr != desc2->ptr[5].ptr)
 		unmap_single_talitos_ptr(dev, &desc2->ptr[5], DMA_FROM_DEVICE);
+	if (req_ctx->last)
+		memcpy(areq->result, req_ctx->hw_context,
+		       crypto_ahash_digestsize(tfm));
 
 	if (req_ctx->psrc)
 		talitos_sg_unmap(dev, edesc, req_ctx->psrc, NULL, 0, 0);
@@ -1845,7 +1849,7 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 	if (req_ctx->last)
 		map_single_talitos_ptr(dev, &desc->ptr[5],
 				       crypto_ahash_digestsize(tfm),
-				       areq->result, DMA_FROM_DEVICE);
+				       req_ctx->hw_context, DMA_FROM_DEVICE);
 	else
 		map_single_talitos_ptr_nosync(dev, &desc->ptr[5],
 					      req_ctx->hw_context_size,
@@ -2253,7 +2257,7 @@ struct talitos_alg_template {
 	u32 type;
 	u32 priority;
 	union {
-		struct crypto_alg crypto;
+		struct skcipher_alg skcipher;
 		struct ahash_alg hash;
 		struct aead_alg aead;
 	} alg;
@@ -2698,123 +2702,102 @@ static struct talitos_alg_template driver_algs[] = {
 				     DESC_HDR_MODE1_MDEU_PAD |
 				     DESC_HDR_MODE1_MDEU_MD5_HMAC,
 	},
-	/* ABLKCIPHER algorithms. */
-	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-		.alg.crypto = {
-			.cra_name = "ecb(aes)",
-			.cra_driver_name = "ecb-aes-talitos",
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-				     CRYPTO_ALG_ASYNC,
-			.cra_ablkcipher = {
-				.min_keysize = AES_MIN_KEY_SIZE,
-				.max_keysize = AES_MAX_KEY_SIZE,
-				.setkey = ablkcipher_aes_setkey,
-			}
+	/* SKCIPHER algorithms. */
+	{	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+		.alg.skcipher = {
+			.base.cra_name = "ecb(aes)",
+			.base.cra_driver_name = "ecb-aes-talitos",
+			.base.cra_blocksize = AES_BLOCK_SIZE,
+			.base.cra_flags = CRYPTO_ALG_ASYNC,
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.setkey = skcipher_aes_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
 				     DESC_HDR_SEL0_AESU,
 	},
-	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-		.alg.crypto = {
-			.cra_name = "cbc(aes)",
-			.cra_driver_name = "cbc-aes-talitos",
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-                                     CRYPTO_ALG_ASYNC,
-			.cra_ablkcipher = {
-				.min_keysize = AES_MIN_KEY_SIZE,
-				.max_keysize = AES_MAX_KEY_SIZE,
-				.ivsize = AES_BLOCK_SIZE,
-				.setkey = ablkcipher_aes_setkey,
-			}
+	{	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+		.alg.skcipher = {
+			.base.cra_name = "cbc(aes)",
+			.base.cra_driver_name = "cbc-aes-talitos",
+			.base.cra_blocksize = AES_BLOCK_SIZE,
+			.base.cra_flags = CRYPTO_ALG_ASYNC,
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			.setkey = skcipher_aes_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
 				     DESC_HDR_SEL0_AESU |
 				     DESC_HDR_MODE0_AESU_CBC,
 	},
-	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-		.alg.crypto = {
-			.cra_name = "ctr(aes)",
-			.cra_driver_name = "ctr-aes-talitos",
-			.cra_blocksize = 1,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-				     CRYPTO_ALG_ASYNC,
-			.cra_ablkcipher = {
-				.min_keysize = AES_MIN_KEY_SIZE,
-				.max_keysize = AES_MAX_KEY_SIZE,
-				.ivsize = AES_BLOCK_SIZE,
-				.setkey = ablkcipher_aes_setkey,
-			}
+	{	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+		.alg.skcipher = {
+			.base.cra_name = "ctr(aes)",
+			.base.cra_driver_name = "ctr-aes-talitos",
+			.base.cra_blocksize = 1,
+			.base.cra_flags = CRYPTO_ALG_ASYNC,
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			.setkey = skcipher_aes_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_AESU_CTR_NONSNOOP |
 				     DESC_HDR_SEL0_AESU |
 				     DESC_HDR_MODE0_AESU_CTR,
 	},
-	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-		.alg.crypto = {
-			.cra_name = "ecb(des)",
-			.cra_driver_name = "ecb-des-talitos",
-			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-				     CRYPTO_ALG_ASYNC,
-			.cra_ablkcipher = {
-				.min_keysize = DES_KEY_SIZE,
-				.max_keysize = DES_KEY_SIZE,
-				.setkey = ablkcipher_des_setkey,
-			}
+	{	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+		.alg.skcipher = {
+			.base.cra_name = "ecb(des)",
+			.base.cra_driver_name = "ecb-des-talitos",
+			.base.cra_blocksize = DES_BLOCK_SIZE,
+			.base.cra_flags = CRYPTO_ALG_ASYNC,
+			.min_keysize = DES_KEY_SIZE,
+			.max_keysize = DES_KEY_SIZE,
+			.setkey = skcipher_des_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
 				     DESC_HDR_SEL0_DEU,
 	},
-	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-		.alg.crypto = {
-			.cra_name = "cbc(des)",
-			.cra_driver_name = "cbc-des-talitos",
-			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-				     CRYPTO_ALG_ASYNC,
-			.cra_ablkcipher = {
-				.min_keysize = DES_KEY_SIZE,
-				.max_keysize = DES_KEY_SIZE,
-				.ivsize = DES_BLOCK_SIZE,
-				.setkey = ablkcipher_des_setkey,
-			}
+	{	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+		.alg.skcipher = {
+			.base.cra_name = "cbc(des)",
+			.base.cra_driver_name = "cbc-des-talitos",
+			.base.cra_blocksize = DES_BLOCK_SIZE,
+			.base.cra_flags = CRYPTO_ALG_ASYNC,
+			.min_keysize = DES_KEY_SIZE,
+			.max_keysize = DES_KEY_SIZE,
+			.ivsize = DES_BLOCK_SIZE,
+			.setkey = skcipher_des_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
 				     DESC_HDR_SEL0_DEU |
 				     DESC_HDR_MODE0_DEU_CBC,
 	},
-	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-		.alg.crypto = {
-			.cra_name = "ecb(des3_ede)",
-			.cra_driver_name = "ecb-3des-talitos",
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-				     CRYPTO_ALG_ASYNC,
-			.cra_ablkcipher = {
-				.min_keysize = DES3_EDE_KEY_SIZE,
-				.max_keysize = DES3_EDE_KEY_SIZE,
-				.setkey = ablkcipher_des3_setkey,
-			}
+	{	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+		.alg.skcipher = {
+			.base.cra_name = "ecb(des3_ede)",
+			.base.cra_driver_name = "ecb-3des-talitos",
+			.base.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.base.cra_flags = CRYPTO_ALG_ASYNC,
+			.min_keysize = DES3_EDE_KEY_SIZE,
+			.max_keysize = DES3_EDE_KEY_SIZE,
+			.setkey = skcipher_des3_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
 				     DESC_HDR_SEL0_DEU |
 				     DESC_HDR_MODE0_DEU_3DES,
 	},
-	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-		.alg.crypto = {
-			.cra_name = "cbc(des3_ede)",
-			.cra_driver_name = "cbc-3des-talitos",
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-                                     CRYPTO_ALG_ASYNC,
-			.cra_ablkcipher = {
-				.min_keysize = DES3_EDE_KEY_SIZE,
-				.max_keysize = DES3_EDE_KEY_SIZE,
-				.ivsize = DES3_EDE_BLOCK_SIZE,
-				.setkey = ablkcipher_des3_setkey,
-			}
+	{	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+		.alg.skcipher = {
+			.base.cra_name = "cbc(des3_ede)",
+			.base.cra_driver_name = "cbc-3des-talitos",
+			.base.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.base.cra_flags = CRYPTO_ALG_ASYNC,
+			.min_keysize = DES3_EDE_KEY_SIZE,
+			.max_keysize = DES3_EDE_KEY_SIZE,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.setkey = skcipher_des3_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
 			             DESC_HDR_SEL0_DEU |
@@ -3032,46 +3015,45 @@ static int talitos_init_common(struct talitos_ctx *ctx,
 	return 0;
 }
 
-static int talitos_cra_init(struct crypto_tfm *tfm)
+static int talitos_cra_init_aead(struct crypto_aead *tfm)
 {
-	struct crypto_alg *alg = tfm->__crt_alg;
+	struct aead_alg *alg = crypto_aead_alg(tfm);
 	struct talitos_crypto_alg *talitos_alg;
-	struct talitos_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct talitos_ctx *ctx = crypto_aead_ctx(tfm);
 
-	if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_AHASH)
-		talitos_alg = container_of(__crypto_ahash_alg(alg),
-					   struct talitos_crypto_alg,
-					   algt.alg.hash);
-	else
-		talitos_alg = container_of(alg, struct talitos_crypto_alg,
-					   algt.alg.crypto);
+	talitos_alg = container_of(alg, struct talitos_crypto_alg,
+				   algt.alg.aead);
 
 	return talitos_init_common(ctx, talitos_alg);
 }
 
-static int talitos_cra_init_aead(struct crypto_aead *tfm)
+static int talitos_cra_init_skcipher(struct crypto_skcipher *tfm)
 {
-	struct aead_alg *alg = crypto_aead_alg(tfm);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
 	struct talitos_crypto_alg *talitos_alg;
-	struct talitos_ctx *ctx = crypto_aead_ctx(tfm);
+	struct talitos_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	talitos_alg = container_of(alg, struct talitos_crypto_alg,
-				   algt.alg.aead);
+				   algt.alg.skcipher);
 
 	return talitos_init_common(ctx, talitos_alg);
 }
 
 static int talitos_cra_init_ahash(struct crypto_tfm *tfm)
 {
+	struct crypto_alg *alg = tfm->__crt_alg;
+	struct talitos_crypto_alg *talitos_alg;
 	struct talitos_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	talitos_cra_init(tfm);
+	talitos_alg = container_of(__crypto_ahash_alg(alg),
+				   struct talitos_crypto_alg,
+				   algt.alg.hash);
 
 	ctx->keylen = 0;
 	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
 				 sizeof(struct talitos_ahash_req_ctx));
 
-	return 0;
+	return talitos_init_common(ctx, talitos_alg);
 }
 
 static void talitos_cra_exit(struct crypto_tfm *tfm)
@@ -3112,7 +3094,8 @@ static int talitos_remove(struct platform_device *ofdev)
 
 	list_for_each_entry_safe(t_alg, n, &priv->alg_list, entry) {
 		switch (t_alg->algt.type) {
-		case CRYPTO_ALG_TYPE_ABLKCIPHER:
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			crypto_unregister_skcipher(&t_alg->algt.alg.skcipher);
 			break;
 		case CRYPTO_ALG_TYPE_AEAD:
 			crypto_unregister_aead(&t_alg->algt.alg.aead);
@@ -3156,15 +3139,14 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
 	t_alg->algt = *template;
 
 	switch (t_alg->algt.type) {
-	case CRYPTO_ALG_TYPE_ABLKCIPHER:
-		alg = &t_alg->algt.alg.crypto;
-		alg->cra_init = talitos_cra_init;
+	case CRYPTO_ALG_TYPE_SKCIPHER:
+		alg = &t_alg->algt.alg.skcipher.base;
 		alg->cra_exit = talitos_cra_exit;
-		alg->cra_type = &crypto_ablkcipher_type;
-		alg->cra_ablkcipher.setkey = alg->cra_ablkcipher.setkey ?:
-					     ablkcipher_setkey;
-		alg->cra_ablkcipher.encrypt = ablkcipher_encrypt;
-		alg->cra_ablkcipher.decrypt = ablkcipher_decrypt;
+		t_alg->algt.alg.skcipher.init = talitos_cra_init_skcipher;
+		t_alg->algt.alg.skcipher.setkey =
+			t_alg->algt.alg.skcipher.setkey ?: skcipher_setkey;
+		t_alg->algt.alg.skcipher.encrypt = skcipher_encrypt;
+		t_alg->algt.alg.skcipher.decrypt = skcipher_decrypt;
 		break;
 	case CRYPTO_ALG_TYPE_AEAD:
 		alg = &t_alg->algt.alg.aead.base;
@@ -3461,10 +3443,10 @@ static int talitos_probe(struct platform_device *ofdev)
 			}
 
 			switch (t_alg->algt.type) {
-			case CRYPTO_ALG_TYPE_ABLKCIPHER:
-				err = crypto_register_alg(
-						&t_alg->algt.alg.crypto);
-				alg = &t_alg->algt.alg.crypto;
+			case CRYPTO_ALG_TYPE_SKCIPHER:
+				err = crypto_register_skcipher(
+						&t_alg->algt.alg.skcipher);
+				alg = &t_alg->algt.alg.skcipher.base;
 				break;
 
 			case CRYPTO_ALG_TYPE_AEAD:
diff --git a/drivers/crypto/ux500/Kconfig b/drivers/crypto/ux500/Kconfig
index b1c6f739f77b..b731895aa241 100644
--- a/drivers/crypto/ux500/Kconfig
+++ b/drivers/crypto/ux500/Kconfig
@@ -8,7 +8,7 @@ config CRYPTO_DEV_UX500_CRYP
 	tristate "UX500 crypto driver for CRYP block"
 	depends on CRYPTO_DEV_UX500
 	select CRYPTO_ALGAPI
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_DES
 	help
         This selects the crypto driver for the UX500_CRYP hardware. It supports
diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c
index 1628ae7a1467..95fb694a2667 100644
--- a/drivers/crypto/ux500/cryp/cryp_core.c
+++ b/drivers/crypto/ux500/cryp/cryp_core.c
@@ -30,6 +30,7 @@
 #include <crypto/algapi.h>
 #include <crypto/ctr.h>
 #include <crypto/internal/des.h>
+#include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 
 #include <linux/platform_data/crypto-ux500.h>
@@ -828,10 +829,10 @@ static int get_nents(struct scatterlist *sg, int nbytes)
 	return nents;
 }
 
-static int ablk_dma_crypt(struct ablkcipher_request *areq)
+static int ablk_dma_crypt(struct skcipher_request *areq)
 {
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(areq);
-	struct cryp_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(areq);
+	struct cryp_ctx *ctx = crypto_skcipher_ctx(cipher);
 	struct cryp_device_data *device_data;
 
 	int bytes_written = 0;
@@ -840,8 +841,8 @@ static int ablk_dma_crypt(struct ablkcipher_request *areq)
 
 	pr_debug(DEV_DBG_NAME " [%s]", __func__);
 
-	ctx->datalen = areq->nbytes;
-	ctx->outlen = areq->nbytes;
+	ctx->datalen = areq->cryptlen;
+	ctx->outlen = areq->cryptlen;
 
 	ret = cryp_get_device_data(ctx, &device_data);
 	if (ret)
@@ -885,11 +886,11 @@ out:
 	return 0;
 }
 
-static int ablk_crypt(struct ablkcipher_request *areq)
+static int ablk_crypt(struct skcipher_request *areq)
 {
-	struct ablkcipher_walk walk;
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(areq);
-	struct cryp_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	struct skcipher_walk walk;
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(areq);
+	struct cryp_ctx *ctx = crypto_skcipher_ctx(cipher);
 	struct cryp_device_data *device_data;
 	unsigned long src_paddr;
 	unsigned long dst_paddr;
@@ -902,21 +903,20 @@ static int ablk_crypt(struct ablkcipher_request *areq)
 	if (ret)
 		goto out;
 
-	ablkcipher_walk_init(&walk, areq->dst, areq->src, areq->nbytes);
-	ret = ablkcipher_walk_phys(areq, &walk);
+	ret = skcipher_walk_async(&walk, areq);
 
 	if (ret) {
-		pr_err(DEV_DBG_NAME "[%s]: ablkcipher_walk_phys() failed!",
+		pr_err(DEV_DBG_NAME "[%s]: skcipher_walk_async() failed!",
 			__func__);
 		goto out;
 	}
 
 	while ((nbytes = walk.nbytes) > 0) {
 		ctx->iv = walk.iv;
-		src_paddr = (page_to_phys(walk.src.page) + walk.src.offset);
+		src_paddr = (page_to_phys(walk.src.phys.page) + walk.src.phys.offset);
 		ctx->indata = phys_to_virt(src_paddr);
 
-		dst_paddr = (page_to_phys(walk.dst.page) + walk.dst.offset);
+		dst_paddr = (page_to_phys(walk.dst.phys.page) + walk.dst.phys.offset);
 		ctx->outdata = phys_to_virt(dst_paddr);
 
 		ctx->datalen = nbytes - (nbytes % ctx->blocksize);
@@ -926,11 +926,10 @@ static int ablk_crypt(struct ablkcipher_request *areq)
 			goto out;
 
 		nbytes -= ctx->datalen;
-		ret = ablkcipher_walk_done(areq, &walk, nbytes);
+		ret = skcipher_walk_done(&walk, nbytes);
 		if (ret)
 			goto out;
 	}
-	ablkcipher_walk_complete(&walk);
 
 out:
 	/* Release the device */
@@ -948,10 +947,10 @@ out:
 	return ret;
 }
 
-static int aes_ablkcipher_setkey(struct crypto_ablkcipher *cipher,
+static int aes_skcipher_setkey(struct crypto_skcipher *cipher,
 				 const u8 *key, unsigned int keylen)
 {
-	struct cryp_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	struct cryp_ctx *ctx = crypto_skcipher_ctx(cipher);
 	u32 *flags = &cipher->base.crt_flags;
 
 	pr_debug(DEV_DBG_NAME " [%s]", __func__);
@@ -983,15 +982,15 @@ static int aes_ablkcipher_setkey(struct crypto_ablkcipher *cipher,
 	return 0;
 }
 
-static int des_ablkcipher_setkey(struct crypto_ablkcipher *cipher,
+static int des_skcipher_setkey(struct crypto_skcipher *cipher,
 				 const u8 *key, unsigned int keylen)
 {
-	struct cryp_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	struct cryp_ctx *ctx = crypto_skcipher_ctx(cipher);
 	int err;
 
 	pr_debug(DEV_DBG_NAME " [%s]", __func__);
 
-	err = verify_ablkcipher_des_key(cipher, key);
+	err = verify_skcipher_des_key(cipher, key);
 	if (err)
 		return err;
 
@@ -1002,15 +1001,15 @@ static int des_ablkcipher_setkey(struct crypto_ablkcipher *cipher,
 	return 0;
 }
 
-static int des3_ablkcipher_setkey(struct crypto_ablkcipher *cipher,
+static int des3_skcipher_setkey(struct crypto_skcipher *cipher,
 				  const u8 *key, unsigned int keylen)
 {
-	struct cryp_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	struct cryp_ctx *ctx = crypto_skcipher_ctx(cipher);
 	int err;
 
 	pr_debug(DEV_DBG_NAME " [%s]", __func__);
 
-	err = verify_ablkcipher_des3_key(cipher, key);
+	err = verify_skcipher_des3_key(cipher, key);
 	if (err)
 		return err;
 
@@ -1021,10 +1020,10 @@ static int des3_ablkcipher_setkey(struct crypto_ablkcipher *cipher,
 	return 0;
 }
 
-static int cryp_blk_encrypt(struct ablkcipher_request *areq)
+static int cryp_blk_encrypt(struct skcipher_request *areq)
 {
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(areq);
-	struct cryp_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(areq);
+	struct cryp_ctx *ctx = crypto_skcipher_ctx(cipher);
 
 	pr_debug(DEV_DBG_NAME " [%s]", __func__);
 
@@ -1039,10 +1038,10 @@ static int cryp_blk_encrypt(struct ablkcipher_request *areq)
 	return ablk_crypt(areq);
 }
 
-static int cryp_blk_decrypt(struct ablkcipher_request *areq)
+static int cryp_blk_decrypt(struct skcipher_request *areq)
 {
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(areq);
-	struct cryp_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(areq);
+	struct cryp_ctx *ctx = crypto_skcipher_ctx(cipher);
 
 	pr_debug(DEV_DBG_NAME " [%s]", __func__);
 
@@ -1058,19 +1057,19 @@ static int cryp_blk_decrypt(struct ablkcipher_request *areq)
 
 struct cryp_algo_template {
 	enum cryp_algo_mode algomode;
-	struct crypto_alg crypto;
+	struct skcipher_alg skcipher;
 };
 
-static int cryp_cra_init(struct crypto_tfm *tfm)
+static int cryp_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct cryp_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct crypto_alg *alg = tfm->__crt_alg;
+	struct cryp_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
 	struct cryp_algo_template *cryp_alg = container_of(alg,
 			struct cryp_algo_template,
-			crypto);
+			skcipher);
 
 	ctx->config.algomode = cryp_alg->algomode;
-	ctx->blocksize = crypto_tfm_alg_blocksize(tfm);
+	ctx->blocksize = crypto_skcipher_blocksize(tfm);
 
 	return 0;
 }
@@ -1078,205 +1077,147 @@ static int cryp_cra_init(struct crypto_tfm *tfm)
 static struct cryp_algo_template cryp_algs[] = {
 	{
 		.algomode = CRYP_ALGO_AES_ECB,
-		.crypto = {
-			.cra_name = "aes",
-			.cra_driver_name = "aes-ux500",
-			.cra_priority =	300,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-					CRYPTO_ALG_ASYNC,
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct cryp_ctx),
-			.cra_alignmask = 3,
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_init = cryp_cra_init,
-			.cra_module = THIS_MODULE,
-			.cra_u = {
-				.ablkcipher = {
-					.min_keysize = AES_MIN_KEY_SIZE,
-					.max_keysize = AES_MAX_KEY_SIZE,
-					.setkey = aes_ablkcipher_setkey,
-					.encrypt = cryp_blk_encrypt,
-					.decrypt = cryp_blk_decrypt
-				}
-			}
-		}
-	},
-	{
-		.algomode = CRYP_ALGO_AES_ECB,
-		.crypto = {
-			.cra_name = "ecb(aes)",
-			.cra_driver_name = "ecb-aes-ux500",
-			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-					CRYPTO_ALG_ASYNC,
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct cryp_ctx),
-			.cra_alignmask = 3,
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_init = cryp_cra_init,
-			.cra_module = THIS_MODULE,
-			.cra_u = {
-				.ablkcipher = {
-					.min_keysize = AES_MIN_KEY_SIZE,
-					.max_keysize = AES_MAX_KEY_SIZE,
-					.setkey = aes_ablkcipher_setkey,
-					.encrypt = cryp_blk_encrypt,
-					.decrypt = cryp_blk_decrypt,
-				}
-			}
+		.skcipher = {
+			.base.cra_name		= "ecb(aes)",
+			.base.cra_driver_name	= "ecb-aes-ux500",
+			.base.cra_priority	= 300,
+			.base.cra_flags		= CRYPTO_ALG_ASYNC,
+			.base.cra_blocksize	= AES_BLOCK_SIZE,
+			.base.cra_ctxsize	= sizeof(struct cryp_ctx),
+			.base.cra_alignmask	= 3,
+			.base.cra_module	= THIS_MODULE,
+
+			.min_keysize		= AES_MIN_KEY_SIZE,
+			.max_keysize		= AES_MAX_KEY_SIZE,
+			.setkey			= aes_skcipher_setkey,
+			.encrypt		= cryp_blk_encrypt,
+			.decrypt		= cryp_blk_decrypt,
+			.init			= cryp_init_tfm,
 		}
 	},
 	{
 		.algomode = CRYP_ALGO_AES_CBC,
-		.crypto = {
-			.cra_name = "cbc(aes)",
-			.cra_driver_name = "cbc-aes-ux500",
-			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-					CRYPTO_ALG_ASYNC,
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct cryp_ctx),
-			.cra_alignmask = 3,
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_init = cryp_cra_init,
-			.cra_module = THIS_MODULE,
-			.cra_u = {
-				.ablkcipher = {
-					.min_keysize = AES_MIN_KEY_SIZE,
-					.max_keysize = AES_MAX_KEY_SIZE,
-					.setkey = aes_ablkcipher_setkey,
-					.encrypt = cryp_blk_encrypt,
-					.decrypt = cryp_blk_decrypt,
-					.ivsize = AES_BLOCK_SIZE,
-				}
-			}
+		.skcipher = {
+			.base.cra_name		= "cbc(aes)",
+			.base.cra_driver_name	= "cbc-aes-ux500",
+			.base.cra_priority	= 300,
+			.base.cra_flags		= CRYPTO_ALG_ASYNC,
+			.base.cra_blocksize	= AES_BLOCK_SIZE,
+			.base.cra_ctxsize	= sizeof(struct cryp_ctx),
+			.base.cra_alignmask	= 3,
+			.base.cra_module	= THIS_MODULE,
+
+			.min_keysize		= AES_MIN_KEY_SIZE,
+			.max_keysize		= AES_MAX_KEY_SIZE,
+			.setkey			= aes_skcipher_setkey,
+			.encrypt		= cryp_blk_encrypt,
+			.decrypt		= cryp_blk_decrypt,
+			.init			= cryp_init_tfm,
+			.ivsize			= AES_BLOCK_SIZE,
 		}
 	},
 	{
 		.algomode = CRYP_ALGO_AES_CTR,
-		.crypto = {
-			.cra_name = "ctr(aes)",
-			.cra_driver_name = "ctr-aes-ux500",
-			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-						CRYPTO_ALG_ASYNC,
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct cryp_ctx),
-			.cra_alignmask = 3,
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_init = cryp_cra_init,
-			.cra_module = THIS_MODULE,
-			.cra_u = {
-				.ablkcipher = {
-					.min_keysize = AES_MIN_KEY_SIZE,
-					.max_keysize = AES_MAX_KEY_SIZE,
-					.setkey = aes_ablkcipher_setkey,
-					.encrypt = cryp_blk_encrypt,
-					.decrypt = cryp_blk_decrypt,
-					.ivsize = AES_BLOCK_SIZE,
-				}
-			}
+		.skcipher = {
+			.base.cra_name		= "ctr(aes)",
+			.base.cra_driver_name	= "ctr-aes-ux500",
+			.base.cra_priority	= 300,
+			.base.cra_flags		= CRYPTO_ALG_ASYNC,
+			.base.cra_blocksize	= 1,
+			.base.cra_ctxsize	= sizeof(struct cryp_ctx),
+			.base.cra_alignmask	= 3,
+			.base.cra_module	= THIS_MODULE,
+
+			.min_keysize		= AES_MIN_KEY_SIZE,
+			.max_keysize		= AES_MAX_KEY_SIZE,
+			.setkey			= aes_skcipher_setkey,
+			.encrypt		= cryp_blk_encrypt,
+			.decrypt		= cryp_blk_decrypt,
+			.init			= cryp_init_tfm,
+			.ivsize			= AES_BLOCK_SIZE,
+			.chunksize		= AES_BLOCK_SIZE,
 		}
 	},
 	{
 		.algomode = CRYP_ALGO_DES_ECB,
-		.crypto = {
-			.cra_name = "ecb(des)",
-			.cra_driver_name = "ecb-des-ux500",
-			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-					CRYPTO_ALG_ASYNC,
-			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct cryp_ctx),
-			.cra_alignmask = 3,
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_init = cryp_cra_init,
-			.cra_module = THIS_MODULE,
-			.cra_u = {
-				.ablkcipher = {
-					.min_keysize = DES_KEY_SIZE,
-					.max_keysize = DES_KEY_SIZE,
-					.setkey = des_ablkcipher_setkey,
-					.encrypt = cryp_blk_encrypt,
-					.decrypt = cryp_blk_decrypt,
-				}
-			}
+		.skcipher = {
+			.base.cra_name		= "ecb(des)",
+			.base.cra_driver_name	= "ecb-des-ux500",
+			.base.cra_priority	= 300,
+			.base.cra_flags		= CRYPTO_ALG_ASYNC,
+			.base.cra_blocksize	= DES_BLOCK_SIZE,
+			.base.cra_ctxsize	= sizeof(struct cryp_ctx),
+			.base.cra_alignmask	= 3,
+			.base.cra_module	= THIS_MODULE,
+
+			.min_keysize		= DES_KEY_SIZE,
+			.max_keysize		= DES_KEY_SIZE,
+			.setkey			= des_skcipher_setkey,
+			.encrypt		= cryp_blk_encrypt,
+			.decrypt		= cryp_blk_decrypt,
+			.init			= cryp_init_tfm,
 		}
 	},
 	{
 		.algomode = CRYP_ALGO_TDES_ECB,
-		.crypto = {
-			.cra_name = "ecb(des3_ede)",
-			.cra_driver_name = "ecb-des3_ede-ux500",
-			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-					CRYPTO_ALG_ASYNC,
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct cryp_ctx),
-			.cra_alignmask = 3,
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_init = cryp_cra_init,
-			.cra_module = THIS_MODULE,
-			.cra_u = {
-				.ablkcipher = {
-					.min_keysize = DES3_EDE_KEY_SIZE,
-					.max_keysize = DES3_EDE_KEY_SIZE,
-					.setkey = des3_ablkcipher_setkey,
-					.encrypt = cryp_blk_encrypt,
-					.decrypt = cryp_blk_decrypt,
-				}
-			}
+		.skcipher = {
+			.base.cra_name		= "ecb(des3_ede)",
+			.base.cra_driver_name	= "ecb-des3_ede-ux500",
+			.base.cra_priority	= 300,
+			.base.cra_flags		= CRYPTO_ALG_ASYNC,
+			.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+			.base.cra_ctxsize	= sizeof(struct cryp_ctx),
+			.base.cra_alignmask	= 3,
+			.base.cra_module	= THIS_MODULE,
+
+			.min_keysize		= DES3_EDE_KEY_SIZE,
+			.max_keysize		= DES3_EDE_KEY_SIZE,
+			.setkey			= des3_skcipher_setkey,
+			.encrypt		= cryp_blk_encrypt,
+			.decrypt		= cryp_blk_decrypt,
+			.init			= cryp_init_tfm,
 		}
 	},
 	{
 		.algomode = CRYP_ALGO_DES_CBC,
-		.crypto = {
-			.cra_name = "cbc(des)",
-			.cra_driver_name = "cbc-des-ux500",
-			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-					CRYPTO_ALG_ASYNC,
-			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct cryp_ctx),
-			.cra_alignmask = 3,
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_init = cryp_cra_init,
-			.cra_module = THIS_MODULE,
-			.cra_u = {
-				.ablkcipher = {
-					.min_keysize = DES_KEY_SIZE,
-					.max_keysize = DES_KEY_SIZE,
-					.setkey = des_ablkcipher_setkey,
-					.encrypt = cryp_blk_encrypt,
-					.decrypt = cryp_blk_decrypt,
-				}
-			}
+		.skcipher = {
+			.base.cra_name		= "cbc(des)",
+			.base.cra_driver_name	= "cbc-des-ux500",
+			.base.cra_priority	= 300,
+			.base.cra_flags		= CRYPTO_ALG_ASYNC,
+			.base.cra_blocksize	= DES_BLOCK_SIZE,
+			.base.cra_ctxsize	= sizeof(struct cryp_ctx),
+			.base.cra_alignmask	= 3,
+			.base.cra_module	= THIS_MODULE,
+
+			.min_keysize		= DES_KEY_SIZE,
+			.max_keysize		= DES_KEY_SIZE,
+			.setkey			= des_skcipher_setkey,
+			.encrypt		= cryp_blk_encrypt,
+			.decrypt		= cryp_blk_decrypt,
+			.ivsize			= DES_BLOCK_SIZE,
+			.init			= cryp_init_tfm,
 		}
 	},
 	{
 		.algomode = CRYP_ALGO_TDES_CBC,
-		.crypto = {
-			.cra_name = "cbc(des3_ede)",
-			.cra_driver_name = "cbc-des3_ede-ux500",
-			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-					CRYPTO_ALG_ASYNC,
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct cryp_ctx),
-			.cra_alignmask = 3,
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_init = cryp_cra_init,
-			.cra_module = THIS_MODULE,
-			.cra_u = {
-				.ablkcipher = {
-					.min_keysize = DES3_EDE_KEY_SIZE,
-					.max_keysize = DES3_EDE_KEY_SIZE,
-					.setkey = des3_ablkcipher_setkey,
-					.encrypt = cryp_blk_encrypt,
-					.decrypt = cryp_blk_decrypt,
-					.ivsize = DES3_EDE_BLOCK_SIZE,
-				}
-			}
+		.skcipher = {
+			.base.cra_name		= "cbc(des3_ede)",
+			.base.cra_driver_name	= "cbc-des3_ede-ux500",
+			.base.cra_priority	= 300,
+			.base.cra_flags		= CRYPTO_ALG_ASYNC,
+			.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+			.base.cra_ctxsize	= sizeof(struct cryp_ctx),
+			.base.cra_alignmask	= 3,
+			.base.cra_module	= THIS_MODULE,
+
+			.min_keysize		= DES3_EDE_KEY_SIZE,
+			.max_keysize		= DES3_EDE_KEY_SIZE,
+			.setkey			= des3_skcipher_setkey,
+			.encrypt		= cryp_blk_encrypt,
+			.decrypt		= cryp_blk_decrypt,
+			.ivsize			= DES3_EDE_BLOCK_SIZE,
+			.init			= cryp_init_tfm,
 		}
 	}
 };
@@ -1293,18 +1234,18 @@ static int cryp_algs_register_all(void)
 	pr_debug("[%s]", __func__);
 
 	for (i = 0; i < ARRAY_SIZE(cryp_algs); i++) {
-		ret = crypto_register_alg(&cryp_algs[i].crypto);
+		ret = crypto_register_skcipher(&cryp_algs[i].skcipher);
 		if (ret) {
 			count = i;
 			pr_err("[%s] alg registration failed",
-					cryp_algs[i].crypto.cra_driver_name);
+					cryp_algs[i].skcipher.base.cra_driver_name);
 			goto unreg;
 		}
 	}
 	return 0;
 unreg:
 	for (i = 0; i < count; i++)
-		crypto_unregister_alg(&cryp_algs[i].crypto);
+		crypto_unregister_skcipher(&cryp_algs[i].skcipher);
 	return ret;
 }
 
@@ -1318,7 +1259,7 @@ static void cryp_algs_unregister_all(void)
 	pr_debug(DEV_DBG_NAME " [%s]", __func__);
 
 	for (i = 0; i < ARRAY_SIZE(cryp_algs); i++)
-		crypto_unregister_alg(&cryp_algs[i].crypto);
+		crypto_unregister_skcipher(&cryp_algs[i].skcipher);
 }
 
 static int ux500_cryp_probe(struct platform_device *pdev)
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index c172a6953477..c24f2db8d5e8 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -140,7 +140,6 @@ static int hash_set_dma_transfer(struct hash_ctx *ctx, struct scatterlist *sg,
 {
 	struct dma_async_tx_descriptor *desc = NULL;
 	struct dma_chan *channel = NULL;
-	dma_cookie_t cookie;
 
 	if (direction != DMA_TO_DEVICE) {
 		dev_err(ctx->device->dev, "%s: Invalid DMA direction\n",
@@ -176,7 +175,7 @@ static int hash_set_dma_transfer(struct hash_ctx *ctx, struct scatterlist *sg,
 	desc->callback = hash_dma_callback;
 	desc->callback_param = ctx;
 
-	cookie = dmaengine_submit(desc);
+	dmaengine_submit(desc);
 	dma_async_issue_pending(channel);
 
 	return 0;
diff --git a/drivers/crypto/virtio/Kconfig b/drivers/crypto/virtio/Kconfig
index 01b625e4e5ad..fb294174e408 100644
--- a/drivers/crypto/virtio/Kconfig
+++ b/drivers/crypto/virtio/Kconfig
@@ -3,7 +3,7 @@ config CRYPTO_DEV_VIRTIO
 	tristate "VirtIO crypto driver"
 	depends on VIRTIO
 	select CRYPTO_AEAD
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_ENGINE
 	default m
 	help
diff --git a/drivers/crypto/virtio/virtio_crypto_algs.c b/drivers/crypto/virtio/virtio_crypto_algs.c
index 42d19205166b..4b71e80951b7 100644
--- a/drivers/crypto/virtio/virtio_crypto_algs.c
+++ b/drivers/crypto/virtio/virtio_crypto_algs.c
@@ -8,6 +8,7 @@
 
 #include <linux/scatterlist.h>
 #include <crypto/algapi.h>
+#include <crypto/internal/skcipher.h>
 #include <linux/err.h>
 #include <crypto/scatterwalk.h>
 #include <linux/atomic.h>
@@ -16,10 +17,10 @@
 #include "virtio_crypto_common.h"
 
 
-struct virtio_crypto_ablkcipher_ctx {
+struct virtio_crypto_skcipher_ctx {
 	struct crypto_engine_ctx enginectx;
 	struct virtio_crypto *vcrypto;
-	struct crypto_tfm *tfm;
+	struct crypto_skcipher *tfm;
 
 	struct virtio_crypto_sym_session_info enc_sess_info;
 	struct virtio_crypto_sym_session_info dec_sess_info;
@@ -30,8 +31,8 @@ struct virtio_crypto_sym_request {
 
 	/* Cipher or aead */
 	uint32_t type;
-	struct virtio_crypto_ablkcipher_ctx *ablkcipher_ctx;
-	struct ablkcipher_request *ablkcipher_req;
+	struct virtio_crypto_skcipher_ctx *skcipher_ctx;
+	struct skcipher_request *skcipher_req;
 	uint8_t *iv;
 	/* Encryption? */
 	bool encrypt;
@@ -41,7 +42,7 @@ struct virtio_crypto_algo {
 	uint32_t algonum;
 	uint32_t service;
 	unsigned int active_devs;
-	struct crypto_alg algo;
+	struct skcipher_alg algo;
 };
 
 /*
@@ -49,9 +50,9 @@ struct virtio_crypto_algo {
  * and crypto algorithms registion.
  */
 static DEFINE_MUTEX(algs_lock);
-static void virtio_crypto_ablkcipher_finalize_req(
+static void virtio_crypto_skcipher_finalize_req(
 	struct virtio_crypto_sym_request *vc_sym_req,
-	struct ablkcipher_request *req,
+	struct skcipher_request *req,
 	int err);
 
 static void virtio_crypto_dataq_sym_callback
@@ -59,7 +60,7 @@ static void virtio_crypto_dataq_sym_callback
 {
 	struct virtio_crypto_sym_request *vc_sym_req =
 		container_of(vc_req, struct virtio_crypto_sym_request, base);
-	struct ablkcipher_request *ablk_req;
+	struct skcipher_request *ablk_req;
 	int error;
 
 	/* Finish the encrypt or decrypt process */
@@ -79,8 +80,8 @@ static void virtio_crypto_dataq_sym_callback
 			error = -EIO;
 			break;
 		}
-		ablk_req = vc_sym_req->ablkcipher_req;
-		virtio_crypto_ablkcipher_finalize_req(vc_sym_req,
+		ablk_req = vc_sym_req->skcipher_req;
+		virtio_crypto_skcipher_finalize_req(vc_sym_req,
 							ablk_req, error);
 	}
 }
@@ -105,15 +106,13 @@ virtio_crypto_alg_validate_key(int key_len, uint32_t *alg)
 		*alg = VIRTIO_CRYPTO_CIPHER_AES_CBC;
 		break;
 	default:
-		pr_err("virtio_crypto: Unsupported key length: %d\n",
-			key_len);
 		return -EINVAL;
 	}
 	return 0;
 }
 
-static int virtio_crypto_alg_ablkcipher_init_session(
-		struct virtio_crypto_ablkcipher_ctx *ctx,
+static int virtio_crypto_alg_skcipher_init_session(
+		struct virtio_crypto_skcipher_ctx *ctx,
 		uint32_t alg, const uint8_t *key,
 		unsigned int keylen,
 		int encrypt)
@@ -202,8 +201,8 @@ static int virtio_crypto_alg_ablkcipher_init_session(
 	return 0;
 }
 
-static int virtio_crypto_alg_ablkcipher_close_session(
-		struct virtio_crypto_ablkcipher_ctx *ctx,
+static int virtio_crypto_alg_skcipher_close_session(
+		struct virtio_crypto_skcipher_ctx *ctx,
 		int encrypt)
 {
 	struct scatterlist outhdr, status_sg, *sgs[2];
@@ -263,8 +262,8 @@ static int virtio_crypto_alg_ablkcipher_close_session(
 	return 0;
 }
 
-static int virtio_crypto_alg_ablkcipher_init_sessions(
-		struct virtio_crypto_ablkcipher_ctx *ctx,
+static int virtio_crypto_alg_skcipher_init_sessions(
+		struct virtio_crypto_skcipher_ctx *ctx,
 		const uint8_t *key, unsigned int keylen)
 {
 	uint32_t alg;
@@ -280,30 +279,30 @@ static int virtio_crypto_alg_ablkcipher_init_sessions(
 		goto bad_key;
 
 	/* Create encryption session */
-	ret = virtio_crypto_alg_ablkcipher_init_session(ctx,
+	ret = virtio_crypto_alg_skcipher_init_session(ctx,
 			alg, key, keylen, 1);
 	if (ret)
 		return ret;
 	/* Create decryption session */
-	ret = virtio_crypto_alg_ablkcipher_init_session(ctx,
+	ret = virtio_crypto_alg_skcipher_init_session(ctx,
 			alg, key, keylen, 0);
 	if (ret) {
-		virtio_crypto_alg_ablkcipher_close_session(ctx, 1);
+		virtio_crypto_alg_skcipher_close_session(ctx, 1);
 		return ret;
 	}
 	return 0;
 
 bad_key:
-	crypto_tfm_set_flags(ctx->tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	crypto_skcipher_set_flags(ctx->tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 	return -EINVAL;
 }
 
 /* Note: kernel crypto API realization */
-static int virtio_crypto_ablkcipher_setkey(struct crypto_ablkcipher *tfm,
+static int virtio_crypto_skcipher_setkey(struct crypto_skcipher *tfm,
 					 const uint8_t *key,
 					 unsigned int keylen)
 {
-	struct virtio_crypto_ablkcipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct virtio_crypto_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm);
 	uint32_t alg;
 	int ret;
 
@@ -325,11 +324,11 @@ static int virtio_crypto_ablkcipher_setkey(struct crypto_ablkcipher *tfm,
 		ctx->vcrypto = vcrypto;
 	} else {
 		/* Rekeying, we should close the created sessions previously */
-		virtio_crypto_alg_ablkcipher_close_session(ctx, 1);
-		virtio_crypto_alg_ablkcipher_close_session(ctx, 0);
+		virtio_crypto_alg_skcipher_close_session(ctx, 1);
+		virtio_crypto_alg_skcipher_close_session(ctx, 0);
 	}
 
-	ret = virtio_crypto_alg_ablkcipher_init_sessions(ctx, key, keylen);
+	ret = virtio_crypto_alg_skcipher_init_sessions(ctx, key, keylen);
 	if (ret) {
 		virtcrypto_dev_put(ctx->vcrypto);
 		ctx->vcrypto = NULL;
@@ -341,14 +340,14 @@ static int virtio_crypto_ablkcipher_setkey(struct crypto_ablkcipher *tfm,
 }
 
 static int
-__virtio_crypto_ablkcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req,
-		struct ablkcipher_request *req,
+__virtio_crypto_skcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req,
+		struct skcipher_request *req,
 		struct data_queue *data_vq)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct virtio_crypto_ablkcipher_ctx *ctx = vc_sym_req->ablkcipher_ctx;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct virtio_crypto_skcipher_ctx *ctx = vc_sym_req->skcipher_ctx;
 	struct virtio_crypto_request *vc_req = &vc_sym_req->base;
-	unsigned int ivsize = crypto_ablkcipher_ivsize(tfm);
+	unsigned int ivsize = crypto_skcipher_ivsize(tfm);
 	struct virtio_crypto *vcrypto = ctx->vcrypto;
 	struct virtio_crypto_op_data_req *req_data;
 	int src_nents, dst_nents;
@@ -361,7 +360,7 @@ __virtio_crypto_ablkcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req,
 	int sg_total;
 	uint8_t *iv;
 
-	src_nents = sg_nents_for_len(req->src, req->nbytes);
+	src_nents = sg_nents_for_len(req->src, req->cryptlen);
 	dst_nents = sg_nents(req->dst);
 
 	pr_debug("virtio_crypto: Number of sgs (src_nents: %d, dst_nents: %d)\n",
@@ -398,7 +397,7 @@ __virtio_crypto_ablkcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req,
 	req_data->u.sym_req.op_type = cpu_to_le32(VIRTIO_CRYPTO_SYM_OP_CIPHER);
 	req_data->u.sym_req.u.cipher.para.iv_len = cpu_to_le32(ivsize);
 	req_data->u.sym_req.u.cipher.para.src_data_len =
-			cpu_to_le32(req->nbytes);
+			cpu_to_le32(req->cryptlen);
 
 	dst_len = virtio_crypto_alg_sg_nents_length(req->dst);
 	if (unlikely(dst_len > U32_MAX)) {
@@ -408,9 +407,9 @@ __virtio_crypto_ablkcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req,
 	}
 
 	pr_debug("virtio_crypto: src_len: %u, dst_len: %llu\n",
-			req->nbytes, dst_len);
+			req->cryptlen, dst_len);
 
-	if (unlikely(req->nbytes + dst_len + ivsize +
+	if (unlikely(req->cryptlen + dst_len + ivsize +
 		sizeof(vc_req->status) > vcrypto->max_size)) {
 		pr_err("virtio_crypto: The length is too big\n");
 		err = -EINVAL;
@@ -436,7 +435,12 @@ __virtio_crypto_ablkcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req,
 		err = -ENOMEM;
 		goto free;
 	}
-	memcpy(iv, req->info, ivsize);
+	memcpy(iv, req->iv, ivsize);
+	if (!vc_sym_req->encrypt)
+		scatterwalk_map_and_copy(req->iv, req->src,
+					 req->cryptlen - AES_BLOCK_SIZE,
+					 AES_BLOCK_SIZE, 0);
+
 	sg_init_one(&iv_sg, iv, ivsize);
 	sgs[num_out++] = &iv_sg;
 	vc_sym_req->iv = iv;
@@ -473,83 +477,93 @@ free:
 	return err;
 }
 
-static int virtio_crypto_ablkcipher_encrypt(struct ablkcipher_request *req)
+static int virtio_crypto_skcipher_encrypt(struct skcipher_request *req)
 {
-	struct crypto_ablkcipher *atfm = crypto_ablkcipher_reqtfm(req);
-	struct virtio_crypto_ablkcipher_ctx *ctx = crypto_ablkcipher_ctx(atfm);
+	struct crypto_skcipher *atfm = crypto_skcipher_reqtfm(req);
+	struct virtio_crypto_skcipher_ctx *ctx = crypto_skcipher_ctx(atfm);
 	struct virtio_crypto_sym_request *vc_sym_req =
-				ablkcipher_request_ctx(req);
+				skcipher_request_ctx(req);
 	struct virtio_crypto_request *vc_req = &vc_sym_req->base;
 	struct virtio_crypto *vcrypto = ctx->vcrypto;
 	/* Use the first data virtqueue as default */
 	struct data_queue *data_vq = &vcrypto->data_vq[0];
 
+	if (!req->cryptlen)
+		return 0;
+	if (req->cryptlen % AES_BLOCK_SIZE)
+		return -EINVAL;
+
 	vc_req->dataq = data_vq;
 	vc_req->alg_cb = virtio_crypto_dataq_sym_callback;
-	vc_sym_req->ablkcipher_ctx = ctx;
-	vc_sym_req->ablkcipher_req = req;
+	vc_sym_req->skcipher_ctx = ctx;
+	vc_sym_req->skcipher_req = req;
 	vc_sym_req->encrypt = true;
 
-	return crypto_transfer_ablkcipher_request_to_engine(data_vq->engine, req);
+	return crypto_transfer_skcipher_request_to_engine(data_vq->engine, req);
 }
 
-static int virtio_crypto_ablkcipher_decrypt(struct ablkcipher_request *req)
+static int virtio_crypto_skcipher_decrypt(struct skcipher_request *req)
 {
-	struct crypto_ablkcipher *atfm = crypto_ablkcipher_reqtfm(req);
-	struct virtio_crypto_ablkcipher_ctx *ctx = crypto_ablkcipher_ctx(atfm);
+	struct crypto_skcipher *atfm = crypto_skcipher_reqtfm(req);
+	struct virtio_crypto_skcipher_ctx *ctx = crypto_skcipher_ctx(atfm);
 	struct virtio_crypto_sym_request *vc_sym_req =
-				ablkcipher_request_ctx(req);
+				skcipher_request_ctx(req);
 	struct virtio_crypto_request *vc_req = &vc_sym_req->base;
 	struct virtio_crypto *vcrypto = ctx->vcrypto;
 	/* Use the first data virtqueue as default */
 	struct data_queue *data_vq = &vcrypto->data_vq[0];
 
+	if (!req->cryptlen)
+		return 0;
+	if (req->cryptlen % AES_BLOCK_SIZE)
+		return -EINVAL;
+
 	vc_req->dataq = data_vq;
 	vc_req->alg_cb = virtio_crypto_dataq_sym_callback;
-	vc_sym_req->ablkcipher_ctx = ctx;
-	vc_sym_req->ablkcipher_req = req;
+	vc_sym_req->skcipher_ctx = ctx;
+	vc_sym_req->skcipher_req = req;
 	vc_sym_req->encrypt = false;
 
-	return crypto_transfer_ablkcipher_request_to_engine(data_vq->engine, req);
+	return crypto_transfer_skcipher_request_to_engine(data_vq->engine, req);
 }
 
-static int virtio_crypto_ablkcipher_init(struct crypto_tfm *tfm)
+static int virtio_crypto_skcipher_init(struct crypto_skcipher *tfm)
 {
-	struct virtio_crypto_ablkcipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct virtio_crypto_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct virtio_crypto_sym_request);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct virtio_crypto_sym_request));
 	ctx->tfm = tfm;
 
-	ctx->enginectx.op.do_one_request = virtio_crypto_ablkcipher_crypt_req;
+	ctx->enginectx.op.do_one_request = virtio_crypto_skcipher_crypt_req;
 	ctx->enginectx.op.prepare_request = NULL;
 	ctx->enginectx.op.unprepare_request = NULL;
 	return 0;
 }
 
-static void virtio_crypto_ablkcipher_exit(struct crypto_tfm *tfm)
+static void virtio_crypto_skcipher_exit(struct crypto_skcipher *tfm)
 {
-	struct virtio_crypto_ablkcipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct virtio_crypto_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	if (!ctx->vcrypto)
 		return;
 
-	virtio_crypto_alg_ablkcipher_close_session(ctx, 1);
-	virtio_crypto_alg_ablkcipher_close_session(ctx, 0);
+	virtio_crypto_alg_skcipher_close_session(ctx, 1);
+	virtio_crypto_alg_skcipher_close_session(ctx, 0);
 	virtcrypto_dev_put(ctx->vcrypto);
 	ctx->vcrypto = NULL;
 }
 
-int virtio_crypto_ablkcipher_crypt_req(
+int virtio_crypto_skcipher_crypt_req(
 	struct crypto_engine *engine, void *vreq)
 {
-	struct ablkcipher_request *req = container_of(vreq, struct ablkcipher_request, base);
+	struct skcipher_request *req = container_of(vreq, struct skcipher_request, base);
 	struct virtio_crypto_sym_request *vc_sym_req =
-				ablkcipher_request_ctx(req);
+				skcipher_request_ctx(req);
 	struct virtio_crypto_request *vc_req = &vc_sym_req->base;
 	struct data_queue *data_vq = vc_req->dataq;
 	int ret;
 
-	ret = __virtio_crypto_ablkcipher_do_req(vc_sym_req, req, data_vq);
+	ret = __virtio_crypto_skcipher_do_req(vc_sym_req, req, data_vq);
 	if (ret < 0)
 		return ret;
 
@@ -558,12 +572,16 @@ int virtio_crypto_ablkcipher_crypt_req(
 	return 0;
 }
 
-static void virtio_crypto_ablkcipher_finalize_req(
+static void virtio_crypto_skcipher_finalize_req(
 	struct virtio_crypto_sym_request *vc_sym_req,
-	struct ablkcipher_request *req,
+	struct skcipher_request *req,
 	int err)
 {
-	crypto_finalize_ablkcipher_request(vc_sym_req->base.dataq->engine,
+	if (vc_sym_req->encrypt)
+		scatterwalk_map_and_copy(req->iv, req->dst,
+					 req->cryptlen - AES_BLOCK_SIZE,
+					 AES_BLOCK_SIZE, 0);
+	crypto_finalize_skcipher_request(vc_sym_req->base.dataq->engine,
 					   req, err);
 	kzfree(vc_sym_req->iv);
 	virtcrypto_clear_request(&vc_sym_req->base);
@@ -573,27 +591,21 @@ static struct virtio_crypto_algo virtio_crypto_algs[] = { {
 	.algonum = VIRTIO_CRYPTO_CIPHER_AES_CBC,
 	.service = VIRTIO_CRYPTO_SERVICE_CIPHER,
 	.algo = {
-		.cra_name = "cbc(aes)",
-		.cra_driver_name = "virtio_crypto_aes_cbc",
-		.cra_priority = 150,
-		.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-		.cra_blocksize = AES_BLOCK_SIZE,
-		.cra_ctxsize  = sizeof(struct virtio_crypto_ablkcipher_ctx),
-		.cra_alignmask = 0,
-		.cra_module = THIS_MODULE,
-		.cra_type = &crypto_ablkcipher_type,
-		.cra_init = virtio_crypto_ablkcipher_init,
-		.cra_exit = virtio_crypto_ablkcipher_exit,
-		.cra_u = {
-			.ablkcipher = {
-				.setkey = virtio_crypto_ablkcipher_setkey,
-				.decrypt = virtio_crypto_ablkcipher_decrypt,
-				.encrypt = virtio_crypto_ablkcipher_encrypt,
-				.min_keysize = AES_MIN_KEY_SIZE,
-				.max_keysize = AES_MAX_KEY_SIZE,
-				.ivsize = AES_BLOCK_SIZE,
-			},
-		},
+		.base.cra_name		= "cbc(aes)",
+		.base.cra_driver_name	= "virtio_crypto_aes_cbc",
+		.base.cra_priority	= 150,
+		.base.cra_flags		= CRYPTO_ALG_ASYNC,
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct virtio_crypto_skcipher_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.init			= virtio_crypto_skcipher_init,
+		.exit			= virtio_crypto_skcipher_exit,
+		.setkey			= virtio_crypto_skcipher_setkey,
+		.decrypt		= virtio_crypto_skcipher_decrypt,
+		.encrypt		= virtio_crypto_skcipher_encrypt,
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.ivsize			= AES_BLOCK_SIZE,
 	},
 } };
 
@@ -613,14 +625,14 @@ int virtio_crypto_algs_register(struct virtio_crypto *vcrypto)
 			continue;
 
 		if (virtio_crypto_algs[i].active_devs == 0) {
-			ret = crypto_register_alg(&virtio_crypto_algs[i].algo);
+			ret = crypto_register_skcipher(&virtio_crypto_algs[i].algo);
 			if (ret)
 				goto unlock;
 		}
 
 		virtio_crypto_algs[i].active_devs++;
 		dev_info(&vcrypto->vdev->dev, "Registered algo %s\n",
-			 virtio_crypto_algs[i].algo.cra_name);
+			 virtio_crypto_algs[i].algo.base.cra_name);
 	}
 
 unlock:
@@ -644,7 +656,7 @@ void virtio_crypto_algs_unregister(struct virtio_crypto *vcrypto)
 			continue;
 
 		if (virtio_crypto_algs[i].active_devs == 1)
-			crypto_unregister_alg(&virtio_crypto_algs[i].algo);
+			crypto_unregister_skcipher(&virtio_crypto_algs[i].algo);
 
 		virtio_crypto_algs[i].active_devs--;
 	}
diff --git a/drivers/crypto/virtio/virtio_crypto_common.h b/drivers/crypto/virtio/virtio_crypto_common.h
index 1c6e00da5a29..a24f85c589e7 100644
--- a/drivers/crypto/virtio/virtio_crypto_common.h
+++ b/drivers/crypto/virtio/virtio_crypto_common.h
@@ -112,7 +112,7 @@ struct virtio_crypto *virtcrypto_get_dev_node(int node,
 					      uint32_t algo);
 int virtcrypto_dev_start(struct virtio_crypto *vcrypto);
 void virtcrypto_dev_stop(struct virtio_crypto *vcrypto);
-int virtio_crypto_ablkcipher_crypt_req(
+int virtio_crypto_skcipher_crypt_req(
 	struct crypto_engine *engine, void *vreq);
 
 void
diff --git a/drivers/crypto/vmx/Makefile b/drivers/crypto/vmx/Makefile
index cab32cfec9c4..709670d2b553 100644
--- a/drivers/crypto/vmx/Makefile
+++ b/drivers/crypto/vmx/Makefile
@@ -3,13 +3,13 @@ obj-$(CONFIG_CRYPTO_DEV_VMX_ENCRYPT) += vmx-crypto.o
 vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o aes_xts.o ghash.o
 
 ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
-TARGET := linux-ppc64le
+override flavour := linux-ppc64le
 else
-TARGET := linux-ppc64
+override flavour := linux-ppc64
 endif
 
 quiet_cmd_perl = PERL $@
-      cmd_perl = $(PERL) $(<) $(TARGET) > $(@)
+      cmd_perl = $(PERL) $(<) $(flavour) > $(@)
 
 targets += aesp8-ppc.S ghashp8-ppc.S
 
diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index fbda4b876afd..e91cf1147a4e 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -14,6 +14,7 @@
 #include <linux/interrupt.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/kernel.h>
+#include <linux/mfd/altera-sysmgr.h>
 #include <linux/mfd/syscon.h>
 #include <linux/notifier.h>
 #include <linux/of_address.h>
@@ -275,7 +276,6 @@ release:
 	return ret;
 }
 
-static int socfpga_is_a10(void);
 static int altr_sdram_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *id;
@@ -399,7 +399,7 @@ static int altr_sdram_probe(struct platform_device *pdev)
 		goto err;
 
 	/* Only the Arria10 has separate IRQs */
-	if (socfpga_is_a10()) {
+	if (of_machine_is_compatible("altr,socfpga-arria10")) {
 		/* Arria10 specific initialization */
 		res = a10_init(mc_vbase);
 		if (res < 0)
@@ -502,68 +502,6 @@ module_platform_driver(altr_sdram_edac_driver);
 
 #endif	/* CONFIG_EDAC_ALTERA_SDRAM */
 
-/**************** Stratix 10 EDAC Memory Controller Functions ************/
-
-/**
- * s10_protected_reg_write
- * Write to a protected SMC register.
- * @context: Not used.
- * @reg: Address of register
- * @value: Value to write
- * Return: INTEL_SIP_SMC_STATUS_OK (0) on success
- *	   INTEL_SIP_SMC_REG_ERROR on error
- *	   INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION if not supported
- */
-static int s10_protected_reg_write(void *context, unsigned int reg,
-				   unsigned int val)
-{
-	struct arm_smccc_res result;
-	unsigned long offset = (unsigned long)context;
-
-	arm_smccc_smc(INTEL_SIP_SMC_REG_WRITE, offset + reg, val, 0, 0,
-		      0, 0, 0, &result);
-
-	return (int)result.a0;
-}
-
-/**
- * s10_protected_reg_read
- * Read the status of a protected SMC register
- * @context: Not used.
- * @reg: Address of register
- * @value: Value read.
- * Return: INTEL_SIP_SMC_STATUS_OK (0) on success
- *	   INTEL_SIP_SMC_REG_ERROR on error
- *	   INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION if not supported
- */
-static int s10_protected_reg_read(void *context, unsigned int reg,
-				  unsigned int *val)
-{
-	struct arm_smccc_res result;
-	unsigned long offset = (unsigned long)context;
-
-	arm_smccc_smc(INTEL_SIP_SMC_REG_READ, offset + reg, 0, 0, 0,
-		      0, 0, 0, &result);
-
-	*val = (unsigned int)result.a1;
-
-	return (int)result.a0;
-}
-
-static const struct regmap_config s10_sdram_regmap_cfg = {
-	.name = "s10_ddr",
-	.reg_bits = 32,
-	.reg_stride = 4,
-	.val_bits = 32,
-	.max_register = 0xffd12228,
-	.reg_read = s10_protected_reg_read,
-	.reg_write = s10_protected_reg_write,
-	.use_single_read = true,
-	.use_single_write = true,
-};
-
-/************** </Stratix10 EDAC Memory Controller Functions> ***********/
-
 /************************* EDAC Parent Probe *************************/
 
 static const struct of_device_id altr_edac_device_of_match[];
@@ -1008,16 +946,6 @@ static int __maybe_unused altr_init_memory_port(void __iomem *ioaddr, int port)
 	return ret;
 }
 
-static int socfpga_is_a10(void)
-{
-	return of_machine_is_compatible("altr,socfpga-arria10");
-}
-
-static int socfpga_is_s10(void)
-{
-	return of_machine_is_compatible("altr,socfpga-stratix10");
-}
-
 static __init int __maybe_unused
 altr_init_a10_ecc_block(struct device_node *np, u32 irq_mask,
 			u32 ecc_ctrl_en_mask, bool dual_port)
@@ -1033,34 +961,10 @@ altr_init_a10_ecc_block(struct device_node *np, u32 irq_mask,
 	/* Get the ECC Manager - parent of the device EDACs */
 	np_eccmgr = of_get_parent(np);
 
-	if (socfpga_is_a10()) {
-		ecc_mgr_map = syscon_regmap_lookup_by_phandle(np_eccmgr,
-							      "altr,sysmgr-syscon");
-	} else {
-		struct device_node *sysmgr_np;
-		struct resource res;
-		uintptr_t base;
-
-		sysmgr_np = of_parse_phandle(np_eccmgr,
-					     "altr,sysmgr-syscon", 0);
-		if (!sysmgr_np) {
-			edac_printk(KERN_ERR, EDAC_DEVICE,
-				    "Unable to find altr,sysmgr-syscon\n");
-			return -ENODEV;
-		}
-
-		if (of_address_to_resource(sysmgr_np, 0, &res)) {
-			of_node_put(sysmgr_np);
-			return -ENOMEM;
-		}
+	ecc_mgr_map =
+		altr_sysmgr_regmap_lookup_by_phandle(np_eccmgr,
+						     "altr,sysmgr-syscon");
 
-		/* Need physical address for SMCC call */
-		base = res.start;
-
-		ecc_mgr_map = regmap_init(NULL, NULL, (void *)base,
-					  &s10_sdram_regmap_cfg);
-		of_node_put(sysmgr_np);
-	}
 	of_node_put(np_eccmgr);
 	if (IS_ERR(ecc_mgr_map)) {
 		edac_printk(KERN_ERR, EDAC_DEVICE,
@@ -1125,9 +1029,6 @@ static int __init __maybe_unused altr_init_a10_ecc_device_type(char *compat)
 	int irq;
 	struct device_node *child, *np;
 
-	if (!socfpga_is_a10() && !socfpga_is_s10())
-		return -ENODEV;
-
 	np = of_find_compatible_node(NULL, NULL,
 				     "altr,socfpga-a10-ecc-manager");
 	if (!np) {
@@ -2178,33 +2079,9 @@ static int altr_edac_a10_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, edac);
 	INIT_LIST_HEAD(&edac->a10_ecc_devices);
 
-	if (socfpga_is_a10()) {
-		edac->ecc_mgr_map =
-			syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
-							"altr,sysmgr-syscon");
-	} else {
-		struct device_node *sysmgr_np;
-		struct resource res;
-		uintptr_t base;
-
-		sysmgr_np = of_parse_phandle(pdev->dev.of_node,
-					     "altr,sysmgr-syscon", 0);
-		if (!sysmgr_np) {
-			edac_printk(KERN_ERR, EDAC_DEVICE,
-				    "Unable to find altr,sysmgr-syscon\n");
-			return -ENODEV;
-		}
-
-		if (of_address_to_resource(sysmgr_np, 0, &res))
-			return -ENOMEM;
-
-		/* Need physical address for SMCC call */
-		base = res.start;
-
-		edac->ecc_mgr_map = devm_regmap_init(&pdev->dev, NULL,
-						     (void *)base,
-						     &s10_sdram_regmap_cfg);
-	}
+	edac->ecc_mgr_map =
+		altr_sysmgr_regmap_lookup_by_phandle(pdev->dev.of_node,
+						     "altr,sysmgr-syscon");
 
 	if (IS_ERR(edac->ecc_mgr_map)) {
 		edac_printk(KERN_ERR, EDAC_DEVICE,
@@ -2270,18 +2147,7 @@ static int altr_edac_a10_probe(struct platform_device *pdev)
 		if (!of_device_is_available(child))
 			continue;
 
-		if (of_device_is_compatible(child, "altr,socfpga-a10-l2-ecc") || 
-		    of_device_is_compatible(child, "altr,socfpga-a10-ocram-ecc") ||
-		    of_device_is_compatible(child, "altr,socfpga-eth-mac-ecc") ||
-		    of_device_is_compatible(child, "altr,socfpga-nand-ecc") ||
-		    of_device_is_compatible(child, "altr,socfpga-dma-ecc") ||
-		    of_device_is_compatible(child, "altr,socfpga-usb-ecc") ||
-		    of_device_is_compatible(child, "altr,socfpga-qspi-ecc") ||
-#ifdef CONFIG_EDAC_ALTERA_SDRAM
-		    of_device_is_compatible(child, "altr,sdram-edac-s10") ||
-#endif
-		    of_device_is_compatible(child, "altr,socfpga-sdmmc-ecc"))
-
+		if (of_match_node(altr_edac_a10_device_of_match, child))
 			altr_edac_a10_device_add(edac, child);
 
 #ifdef CONFIG_EDAC_ALTERA_SDRAM
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index c1d4536ae466..428ce98f6776 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -16,12 +16,11 @@ module_param(ecc_enable_override, int, 0644);
 
 static struct msr __percpu *msrs;
 
+static struct amd64_family_type *fam_type;
+
 /* Per-node stuff */
 static struct ecc_settings **ecc_stngs;
 
-/* Number of Unified Memory Controllers */
-static u8 num_umcs;
-
 /*
  * Valid scrub rates for the K8 hardware memory scrubber. We map the scrubbing
  * bandwidth to a valid bit pattern. The 'set' operation finds the 'matching-
@@ -454,7 +453,7 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct,
 	for (i = 0; i < pvt->csels[dct].m_cnt; i++)
 
 #define for_each_umc(i) \
-	for (i = 0; i < num_umcs; i++)
+	for (i = 0; i < fam_type->max_mcs; i++)
 
 /*
  * @input_addr is an InputAddr associated with the node given by mci. Return the
@@ -2224,6 +2223,7 @@ static struct amd64_family_type family_types[] = {
 		.ctl_name = "K8",
 		.f1_id = PCI_DEVICE_ID_AMD_K8_NB_ADDRMAP,
 		.f2_id = PCI_DEVICE_ID_AMD_K8_NB_MEMCTL,
+		.max_mcs = 2,
 		.ops = {
 			.early_channel_count	= k8_early_channel_count,
 			.map_sysaddr_to_csrow	= k8_map_sysaddr_to_csrow,
@@ -2234,6 +2234,7 @@ static struct amd64_family_type family_types[] = {
 		.ctl_name = "F10h",
 		.f1_id = PCI_DEVICE_ID_AMD_10H_NB_MAP,
 		.f2_id = PCI_DEVICE_ID_AMD_10H_NB_DRAM,
+		.max_mcs = 2,
 		.ops = {
 			.early_channel_count	= f1x_early_channel_count,
 			.map_sysaddr_to_csrow	= f1x_map_sysaddr_to_csrow,
@@ -2244,6 +2245,7 @@ static struct amd64_family_type family_types[] = {
 		.ctl_name = "F15h",
 		.f1_id = PCI_DEVICE_ID_AMD_15H_NB_F1,
 		.f2_id = PCI_DEVICE_ID_AMD_15H_NB_F2,
+		.max_mcs = 2,
 		.ops = {
 			.early_channel_count	= f1x_early_channel_count,
 			.map_sysaddr_to_csrow	= f1x_map_sysaddr_to_csrow,
@@ -2254,6 +2256,7 @@ static struct amd64_family_type family_types[] = {
 		.ctl_name = "F15h_M30h",
 		.f1_id = PCI_DEVICE_ID_AMD_15H_M30H_NB_F1,
 		.f2_id = PCI_DEVICE_ID_AMD_15H_M30H_NB_F2,
+		.max_mcs = 2,
 		.ops = {
 			.early_channel_count	= f1x_early_channel_count,
 			.map_sysaddr_to_csrow	= f1x_map_sysaddr_to_csrow,
@@ -2264,6 +2267,7 @@ static struct amd64_family_type family_types[] = {
 		.ctl_name = "F15h_M60h",
 		.f1_id = PCI_DEVICE_ID_AMD_15H_M60H_NB_F1,
 		.f2_id = PCI_DEVICE_ID_AMD_15H_M60H_NB_F2,
+		.max_mcs = 2,
 		.ops = {
 			.early_channel_count	= f1x_early_channel_count,
 			.map_sysaddr_to_csrow	= f1x_map_sysaddr_to_csrow,
@@ -2274,6 +2278,7 @@ static struct amd64_family_type family_types[] = {
 		.ctl_name = "F16h",
 		.f1_id = PCI_DEVICE_ID_AMD_16H_NB_F1,
 		.f2_id = PCI_DEVICE_ID_AMD_16H_NB_F2,
+		.max_mcs = 2,
 		.ops = {
 			.early_channel_count	= f1x_early_channel_count,
 			.map_sysaddr_to_csrow	= f1x_map_sysaddr_to_csrow,
@@ -2284,6 +2289,7 @@ static struct amd64_family_type family_types[] = {
 		.ctl_name = "F16h_M30h",
 		.f1_id = PCI_DEVICE_ID_AMD_16H_M30H_NB_F1,
 		.f2_id = PCI_DEVICE_ID_AMD_16H_M30H_NB_F2,
+		.max_mcs = 2,
 		.ops = {
 			.early_channel_count	= f1x_early_channel_count,
 			.map_sysaddr_to_csrow	= f1x_map_sysaddr_to_csrow,
@@ -2294,6 +2300,7 @@ static struct amd64_family_type family_types[] = {
 		.ctl_name = "F17h",
 		.f0_id = PCI_DEVICE_ID_AMD_17H_DF_F0,
 		.f6_id = PCI_DEVICE_ID_AMD_17H_DF_F6,
+		.max_mcs = 2,
 		.ops = {
 			.early_channel_count	= f17_early_channel_count,
 			.dbam_to_cs		= f17_addr_mask_to_cs_size,
@@ -2303,6 +2310,7 @@ static struct amd64_family_type family_types[] = {
 		.ctl_name = "F17h_M10h",
 		.f0_id = PCI_DEVICE_ID_AMD_17H_M10H_DF_F0,
 		.f6_id = PCI_DEVICE_ID_AMD_17H_M10H_DF_F6,
+		.max_mcs = 2,
 		.ops = {
 			.early_channel_count	= f17_early_channel_count,
 			.dbam_to_cs		= f17_addr_mask_to_cs_size,
@@ -2312,6 +2320,7 @@ static struct amd64_family_type family_types[] = {
 		.ctl_name = "F17h_M30h",
 		.f0_id = PCI_DEVICE_ID_AMD_17H_M30H_DF_F0,
 		.f6_id = PCI_DEVICE_ID_AMD_17H_M30H_DF_F6,
+		.max_mcs = 8,
 		.ops = {
 			.early_channel_count	= f17_early_channel_count,
 			.dbam_to_cs		= f17_addr_mask_to_cs_size,
@@ -2321,6 +2330,7 @@ static struct amd64_family_type family_types[] = {
 		.ctl_name = "F17h_M70h",
 		.f0_id = PCI_DEVICE_ID_AMD_17H_M70H_DF_F0,
 		.f6_id = PCI_DEVICE_ID_AMD_17H_M70H_DF_F6,
+		.max_mcs = 2,
 		.ops = {
 			.early_channel_count	= f17_early_channel_count,
 			.dbam_to_cs		= f17_addr_mask_to_cs_size,
@@ -2838,8 +2848,6 @@ skip:
 	edac_dbg(1, "  DIMM type: %s\n", edac_mem_types[pvt->dram_type]);
 
 	determine_ecc_sym_sz(pvt);
-
-	dump_misc_regs(pvt);
 }
 
 /*
@@ -2936,6 +2944,7 @@ static int init_csrows_df(struct mem_ctl_info *mci)
 			dimm->mtype = pvt->dram_type;
 			dimm->edac_mode = edac_mode;
 			dimm->dtype = dev_type;
+			dimm->grain = 64;
 		}
 	}
 
@@ -3012,6 +3021,7 @@ static int init_csrows(struct mem_ctl_info *mci)
 			dimm = csrow->channels[j]->dimm;
 			dimm->mtype = pvt->dram_type;
 			dimm->edac_mode = edac_mode;
+			dimm->grain = 64;
 		}
 	}
 
@@ -3178,43 +3188,27 @@ static void restore_ecc_error_reporting(struct ecc_settings *s, u16 nid,
 		amd64_warn("Error restoring NB MCGCTL settings!\n");
 }
 
-/*
- * EDAC requires that the BIOS have ECC enabled before
- * taking over the processing of ECC errors. A command line
- * option allows to force-enable hardware ECC later in
- * enable_ecc_error_reporting().
- */
-static const char *ecc_msg =
-	"ECC disabled in the BIOS or no ECC capability, module will not load.\n"
-	" Either enable ECC checking or force module loading by setting "
-	"'ecc_enable_override'.\n"
-	" (Note that use of the override may cause unknown side effects.)\n";
-
-static bool ecc_enabled(struct pci_dev *F3, u16 nid)
+static bool ecc_enabled(struct amd64_pvt *pvt)
 {
+	u16 nid = pvt->mc_node_id;
 	bool nb_mce_en = false;
 	u8 ecc_en = 0, i;
 	u32 value;
 
 	if (boot_cpu_data.x86 >= 0x17) {
 		u8 umc_en_mask = 0, ecc_en_mask = 0;
+		struct amd64_umc *umc;
 
 		for_each_umc(i) {
-			u32 base = get_umc_base(i);
+			umc = &pvt->umc[i];
 
 			/* Only check enabled UMCs. */
-			if (amd_smn_read(nid, base + UMCCH_SDP_CTRL, &value))
-				continue;
-
-			if (!(value & UMC_SDP_INIT))
+			if (!(umc->sdp_ctrl & UMC_SDP_INIT))
 				continue;
 
 			umc_en_mask |= BIT(i);
 
-			if (amd_smn_read(nid, base + UMCCH_UMC_CAP_HI, &value))
-				continue;
-
-			if (value & UMC_ECC_ENABLED)
+			if (umc->umc_cap_hi & UMC_ECC_ENABLED)
 				ecc_en_mask |= BIT(i);
 		}
 
@@ -3227,7 +3221,7 @@ static bool ecc_enabled(struct pci_dev *F3, u16 nid)
 		/* Assume UMC MCA banks are enabled. */
 		nb_mce_en = true;
 	} else {
-		amd64_read_pci_cfg(F3, NBCFG, &value);
+		amd64_read_pci_cfg(pvt->F3, NBCFG, &value);
 
 		ecc_en = !!(value & NBCFG_ECC_ENABLE);
 
@@ -3240,11 +3234,10 @@ static bool ecc_enabled(struct pci_dev *F3, u16 nid)
 	amd64_info("Node %d: DRAM ECC %s.\n",
 		   nid, (ecc_en ? "enabled" : "disabled"));
 
-	if (!ecc_en || !nb_mce_en) {
-		amd64_info("%s", ecc_msg);
+	if (!ecc_en || !nb_mce_en)
 		return false;
-	}
-	return true;
+	else
+		return true;
 }
 
 static inline void
@@ -3278,8 +3271,7 @@ f17h_determine_edac_ctl_cap(struct mem_ctl_info *mci, struct amd64_pvt *pvt)
 	}
 }
 
-static void setup_mci_misc_attrs(struct mem_ctl_info *mci,
-				 struct amd64_family_type *fam)
+static void setup_mci_misc_attrs(struct mem_ctl_info *mci)
 {
 	struct amd64_pvt *pvt = mci->pvt_info;
 
@@ -3298,7 +3290,7 @@ static void setup_mci_misc_attrs(struct mem_ctl_info *mci,
 
 	mci->edac_cap		= determine_edac_cap(pvt);
 	mci->mod_name		= EDAC_MOD_STR;
-	mci->ctl_name		= fam->ctl_name;
+	mci->ctl_name		= fam_type->ctl_name;
 	mci->dev_name		= pci_name(pvt->F3);
 	mci->ctl_page_to_phys	= NULL;
 
@@ -3312,8 +3304,6 @@ static void setup_mci_misc_attrs(struct mem_ctl_info *mci,
  */
 static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt)
 {
-	struct amd64_family_type *fam_type = NULL;
-
 	pvt->ext_model  = boot_cpu_data.x86_model >> 4;
 	pvt->stepping	= boot_cpu_data.x86_stepping;
 	pvt->model	= boot_cpu_data.x86_model;
@@ -3401,51 +3391,15 @@ static const struct attribute_group *amd64_edac_attr_groups[] = {
 	NULL
 };
 
-/* Set the number of Unified Memory Controllers in the system. */
-static void compute_num_umcs(void)
-{
-	u8 model = boot_cpu_data.x86_model;
-
-	if (boot_cpu_data.x86 < 0x17)
-		return;
-
-	if (model >= 0x30 && model <= 0x3f)
-		num_umcs = 8;
-	else
-		num_umcs = 2;
-
-	edac_dbg(1, "Number of UMCs: %x", num_umcs);
-}
-
-static int init_one_instance(unsigned int nid)
+static int hw_info_get(struct amd64_pvt *pvt)
 {
-	struct pci_dev *F3 = node_to_amd_nb(nid)->misc;
-	struct amd64_family_type *fam_type = NULL;
-	struct mem_ctl_info *mci = NULL;
-	struct edac_mc_layer layers[2];
-	struct amd64_pvt *pvt = NULL;
 	u16 pci_id1, pci_id2;
-	int err = 0, ret;
-
-	ret = -ENOMEM;
-	pvt = kzalloc(sizeof(struct amd64_pvt), GFP_KERNEL);
-	if (!pvt)
-		goto err_ret;
-
-	pvt->mc_node_id	= nid;
-	pvt->F3 = F3;
-
-	ret = -EINVAL;
-	fam_type = per_family_init(pvt);
-	if (!fam_type)
-		goto err_free;
+	int ret = -EINVAL;
 
 	if (pvt->fam >= 0x17) {
-		pvt->umc = kcalloc(num_umcs, sizeof(struct amd64_umc), GFP_KERNEL);
-		if (!pvt->umc) {
-			ret = -ENOMEM;
-			goto err_free;
-		}
+		pvt->umc = kcalloc(fam_type->max_mcs, sizeof(struct amd64_umc), GFP_KERNEL);
+		if (!pvt->umc)
+			return -ENOMEM;
 
 		pci_id1 = fam_type->f0_id;
 		pci_id2 = fam_type->f6_id;
@@ -3454,21 +3408,37 @@ static int init_one_instance(unsigned int nid)
 		pci_id2 = fam_type->f2_id;
 	}
 
-	err = reserve_mc_sibling_devs(pvt, pci_id1, pci_id2);
-	if (err)
-		goto err_post_init;
+	ret = reserve_mc_sibling_devs(pvt, pci_id1, pci_id2);
+	if (ret)
+		return ret;
 
 	read_mc_regs(pvt);
 
+	return 0;
+}
+
+static void hw_info_put(struct amd64_pvt *pvt)
+{
+	if (pvt->F0 || pvt->F1)
+		free_mc_sibling_devs(pvt);
+
+	kfree(pvt->umc);
+}
+
+static int init_one_instance(struct amd64_pvt *pvt)
+{
+	struct mem_ctl_info *mci = NULL;
+	struct edac_mc_layer layers[2];
+	int ret = -EINVAL;
+
 	/*
 	 * We need to determine how many memory channels there are. Then use
 	 * that information for calculating the size of the dynamic instance
 	 * tables in the 'mci' structure.
 	 */
-	ret = -EINVAL;
 	pvt->channel_count = pvt->ops->early_channel_count(pvt);
 	if (pvt->channel_count < 0)
-		goto err_siblings;
+		return ret;
 
 	ret = -ENOMEM;
 	layers[0].type = EDAC_MC_LAYER_CHIP_SELECT;
@@ -3480,24 +3450,18 @@ static int init_one_instance(unsigned int nid)
 	 * Always allocate two channels since we can have setups with DIMMs on
 	 * only one channel. Also, this simplifies handling later for the price
 	 * of a couple of KBs tops.
-	 *
-	 * On Fam17h+, the number of controllers may be greater than two. So set
-	 * the size equal to the maximum number of UMCs.
 	 */
-	if (pvt->fam >= 0x17)
-		layers[1].size = num_umcs;
-	else
-		layers[1].size = 2;
+	layers[1].size = fam_type->max_mcs;
 	layers[1].is_virt_csrow = false;
 
-	mci = edac_mc_alloc(nid, ARRAY_SIZE(layers), layers, 0);
+	mci = edac_mc_alloc(pvt->mc_node_id, ARRAY_SIZE(layers), layers, 0);
 	if (!mci)
-		goto err_siblings;
+		return ret;
 
 	mci->pvt_info = pvt;
 	mci->pdev = &pvt->F3->dev;
 
-	setup_mci_misc_attrs(mci, fam_type);
+	setup_mci_misc_attrs(mci);
 
 	if (init_csrows(mci))
 		mci->edac_cap = EDAC_FLAG_NONE;
@@ -3505,31 +3469,30 @@ static int init_one_instance(unsigned int nid)
 	ret = -ENODEV;
 	if (edac_mc_add_mc_with_groups(mci, amd64_edac_attr_groups)) {
 		edac_dbg(1, "failed edac_mc_add_mc()\n");
-		goto err_add_mc;
+		edac_mc_free(mci);
+		return ret;
 	}
 
 	return 0;
+}
 
-err_add_mc:
-	edac_mc_free(mci);
-
-err_siblings:
-	free_mc_sibling_devs(pvt);
-
-err_post_init:
-	if (pvt->fam >= 0x17)
-		kfree(pvt->umc);
+static bool instance_has_memory(struct amd64_pvt *pvt)
+{
+	bool cs_enabled = false;
+	int cs = 0, dct = 0;
 
-err_free:
-	kfree(pvt);
+	for (dct = 0; dct < fam_type->max_mcs; dct++) {
+		for_each_chip_select(cs, dct, pvt)
+			cs_enabled |= csrow_enabled(cs, dct, pvt);
+	}
 
-err_ret:
-	return ret;
+	return cs_enabled;
 }
 
 static int probe_one_instance(unsigned int nid)
 {
 	struct pci_dev *F3 = node_to_amd_nb(nid)->misc;
+	struct amd64_pvt *pvt = NULL;
 	struct ecc_settings *s;
 	int ret;
 
@@ -3540,8 +3503,29 @@ static int probe_one_instance(unsigned int nid)
 
 	ecc_stngs[nid] = s;
 
-	if (!ecc_enabled(F3, nid)) {
-		ret = 0;
+	pvt = kzalloc(sizeof(struct amd64_pvt), GFP_KERNEL);
+	if (!pvt)
+		goto err_settings;
+
+	pvt->mc_node_id	= nid;
+	pvt->F3 = F3;
+
+	fam_type = per_family_init(pvt);
+	if (!fam_type)
+		goto err_enable;
+
+	ret = hw_info_get(pvt);
+	if (ret < 0)
+		goto err_enable;
+
+	ret = 0;
+	if (!instance_has_memory(pvt)) {
+		amd64_info("Node %d: No DIMMs detected.\n", nid);
+		goto err_enable;
+	}
+
+	if (!ecc_enabled(pvt)) {
+		ret = -ENODEV;
 
 		if (!ecc_enable_override)
 			goto err_enable;
@@ -3556,7 +3540,7 @@ static int probe_one_instance(unsigned int nid)
 			goto err_enable;
 	}
 
-	ret = init_one_instance(nid);
+	ret = init_one_instance(pvt);
 	if (ret < 0) {
 		amd64_err("Error probing instance: %d\n", nid);
 
@@ -3566,9 +3550,15 @@ static int probe_one_instance(unsigned int nid)
 		goto err_enable;
 	}
 
+	dump_misc_regs(pvt);
+
 	return ret;
 
 err_enable:
+	hw_info_put(pvt);
+	kfree(pvt);
+
+err_settings:
 	kfree(s);
 	ecc_stngs[nid] = NULL;
 
@@ -3595,14 +3585,13 @@ static void remove_one_instance(unsigned int nid)
 
 	restore_ecc_error_reporting(s, nid, F3);
 
-	free_mc_sibling_devs(pvt);
-
 	kfree(ecc_stngs[nid]);
 	ecc_stngs[nid] = NULL;
 
 	/* Free the EDAC CORE resources */
 	mci->pvt_info = NULL;
 
+	hw_info_put(pvt);
 	kfree(pvt);
 	edac_mc_free(mci);
 }
@@ -3668,8 +3657,6 @@ static int __init amd64_edac_init(void)
 	if (!msrs)
 		goto err_free;
 
-	compute_num_umcs();
-
 	for (i = 0; i < amd_nb_num(); i++) {
 		err = probe_one_instance(i);
 		if (err) {
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
index 8c3cda81e619..9be31688110b 100644
--- a/drivers/edac/amd64_edac.h
+++ b/drivers/edac/amd64_edac.h
@@ -479,6 +479,8 @@ struct low_ops {
 struct amd64_family_type {
 	const char *ctl_name;
 	u16 f0_id, f1_id, f2_id, f6_id;
+	/* Maximum number of memory controllers per die/node. */
+	u8 max_mcs;
 	struct low_ops ops;
 };
 
diff --git a/drivers/edac/aspeed_edac.c b/drivers/edac/aspeed_edac.c
index 5634437bb39d..09a9e3de9595 100644
--- a/drivers/edac/aspeed_edac.c
+++ b/drivers/edac/aspeed_edac.c
@@ -281,16 +281,11 @@ static int aspeed_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct edac_mc_layer layers[2];
 	struct mem_ctl_info *mci;
-	struct resource *res;
 	void __iomem *regs;
 	u32 reg04;
 	int rc;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENOENT;
-
-	regs = devm_ioremap_resource(dev, res);
+	regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(regs))
 		return PTR_ERR(regs);
 
diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c
index 65cf2b9355c4..8c4d947fb848 100644
--- a/drivers/edac/edac_device.c
+++ b/drivers/edac/edac_device.c
@@ -555,12 +555,16 @@ static inline int edac_device_get_panic_on_ue(struct edac_device_ctl_info
 	return edac_dev->panic_on_ue;
 }
 
-void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev,
-			int inst_nr, int block_nr, const char *msg)
+void edac_device_handle_ce_count(struct edac_device_ctl_info *edac_dev,
+				 unsigned int count, int inst_nr, int block_nr,
+				 const char *msg)
 {
 	struct edac_device_instance *instance;
 	struct edac_device_block *block = NULL;
 
+	if (!count)
+		return;
+
 	if ((inst_nr >= edac_dev->nr_instances) || (inst_nr < 0)) {
 		edac_device_printk(edac_dev, KERN_ERR,
 				"INTERNAL ERROR: 'instance' out of range "
@@ -582,27 +586,31 @@ void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev,
 
 	if (instance->nr_blocks > 0) {
 		block = instance->blocks + block_nr;
-		block->counters.ce_count++;
+		block->counters.ce_count += count;
 	}
 
 	/* Propagate the count up the 'totals' tree */
-	instance->counters.ce_count++;
-	edac_dev->counters.ce_count++;
+	instance->counters.ce_count += count;
+	edac_dev->counters.ce_count += count;
 
 	if (edac_device_get_log_ce(edac_dev))
 		edac_device_printk(edac_dev, KERN_WARNING,
-				"CE: %s instance: %s block: %s '%s'\n",
-				edac_dev->ctl_name, instance->name,
-				block ? block->name : "N/A", msg);
+				   "CE: %s instance: %s block: %s count: %d '%s'\n",
+				   edac_dev->ctl_name, instance->name,
+				   block ? block->name : "N/A", count, msg);
 }
-EXPORT_SYMBOL_GPL(edac_device_handle_ce);
+EXPORT_SYMBOL_GPL(edac_device_handle_ce_count);
 
-void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev,
-			int inst_nr, int block_nr, const char *msg)
+void edac_device_handle_ue_count(struct edac_device_ctl_info *edac_dev,
+				 unsigned int count, int inst_nr, int block_nr,
+				 const char *msg)
 {
 	struct edac_device_instance *instance;
 	struct edac_device_block *block = NULL;
 
+	if (!count)
+		return;
+
 	if ((inst_nr >= edac_dev->nr_instances) || (inst_nr < 0)) {
 		edac_device_printk(edac_dev, KERN_ERR,
 				"INTERNAL ERROR: 'instance' out of range "
@@ -624,22 +632,22 @@ void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev,
 
 	if (instance->nr_blocks > 0) {
 		block = instance->blocks + block_nr;
-		block->counters.ue_count++;
+		block->counters.ue_count += count;
 	}
 
 	/* Propagate the count up the 'totals' tree */
-	instance->counters.ue_count++;
-	edac_dev->counters.ue_count++;
+	instance->counters.ue_count += count;
+	edac_dev->counters.ue_count += count;
 
 	if (edac_device_get_log_ue(edac_dev))
 		edac_device_printk(edac_dev, KERN_EMERG,
-				"UE: %s instance: %s block: %s '%s'\n",
-				edac_dev->ctl_name, instance->name,
-				block ? block->name : "N/A", msg);
+				   "UE: %s instance: %s block: %s count: %d '%s'\n",
+				   edac_dev->ctl_name, instance->name,
+				   block ? block->name : "N/A", count, msg);
 
 	if (edac_device_get_panic_on_ue(edac_dev))
-		panic("EDAC %s: UE instance: %s block %s '%s'\n",
-			edac_dev->ctl_name, instance->name,
-			block ? block->name : "N/A", msg);
+		panic("EDAC %s: UE instance: %s block %s count: %d '%s'\n",
+		      edac_dev->ctl_name, instance->name,
+		      block ? block->name : "N/A", count, msg);
 }
-EXPORT_SYMBOL_GPL(edac_device_handle_ue);
+EXPORT_SYMBOL_GPL(edac_device_handle_ue_count);
diff --git a/drivers/edac/edac_device.h b/drivers/edac/edac_device.h
index 1aaba74ae411..c4c0e0bdce14 100644
--- a/drivers/edac/edac_device.h
+++ b/drivers/edac/edac_device.h
@@ -286,27 +286,60 @@ extern int edac_device_add_device(struct edac_device_ctl_info *edac_dev);
 extern struct edac_device_ctl_info *edac_device_del_device(struct device *dev);
 
 /**
- * edac_device_handle_ue():
- *	perform a common output and handling of an 'edac_dev' UE event
+ * Log correctable errors.
  *
  * @edac_dev: pointer to struct &edac_device_ctl_info
- * @inst_nr: number of the instance where the UE error happened
- * @block_nr: number of the block where the UE error happened
+ * @inst_nr: number of the instance where the CE error happened
+ * @count: Number of errors to log.
+ * @block_nr: number of the block where the CE error happened
+ * @msg: message to be printed
+ */
+void edac_device_handle_ce_count(struct edac_device_ctl_info *edac_dev,
+				 unsigned int count, int inst_nr, int block_nr,
+				 const char *msg);
+
+/**
+ * Log uncorrectable errors.
+ *
+ * @edac_dev: pointer to struct &edac_device_ctl_info
+ * @inst_nr: number of the instance where the CE error happened
+ * @count: Number of errors to log.
+ * @block_nr: number of the block where the CE error happened
  * @msg: message to be printed
  */
-extern void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev,
-				int inst_nr, int block_nr, const char *msg);
+void edac_device_handle_ue_count(struct edac_device_ctl_info *edac_dev,
+				 unsigned int count, int inst_nr, int block_nr,
+				 const char *msg);
+
 /**
- * edac_device_handle_ce():
- *	perform a common output and handling of an 'edac_dev' CE event
+ * edac_device_handle_ce(): Log a single correctable error
  *
  * @edac_dev: pointer to struct &edac_device_ctl_info
  * @inst_nr: number of the instance where the CE error happened
  * @block_nr: number of the block where the CE error happened
  * @msg: message to be printed
  */
-extern void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev,
-				int inst_nr, int block_nr, const char *msg);
+static inline void
+edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, int inst_nr,
+		      int block_nr, const char *msg)
+{
+	edac_device_handle_ce_count(edac_dev, 1, inst_nr, block_nr, msg);
+}
+
+/**
+ * edac_device_handle_ue(): Log a single uncorrectable error
+ *
+ * @edac_dev: pointer to struct &edac_device_ctl_info
+ * @inst_nr: number of the instance where the UE error happened
+ * @block_nr: number of the block where the UE error happened
+ * @msg: message to be printed
+ */
+static inline void
+edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, int inst_nr,
+		      int block_nr, const char *msg)
+{
+	edac_device_handle_ue_count(edac_dev, 1, inst_nr, block_nr, msg);
+}
 
 /**
  * edac_device_alloc_index: Allocate a unique device index number
@@ -316,5 +349,4 @@ extern void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev,
  */
 extern int edac_device_alloc_index(void);
 extern const char *edac_layer_name[];
-
 #endif
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index e6fd079783bd..7243b88f81d8 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -145,15 +145,18 @@ static void edac_mc_dump_channel(struct rank_info *chan)
 	edac_dbg(4, "    channel->dimm = %p\n", chan->dimm);
 }
 
-static void edac_mc_dump_dimm(struct dimm_info *dimm, int number)
+static void edac_mc_dump_dimm(struct dimm_info *dimm)
 {
 	char location[80];
 
+	if (!dimm->nr_pages)
+		return;
+
 	edac_dimm_info_location(dimm, location, sizeof(location));
 
 	edac_dbg(4, "%s%i: %smapped as virtual row %d, chan %d\n",
 		 dimm->mci->csbased ? "rank" : "dimm",
-		 number, location, dimm->csrow, dimm->cschannel);
+		 dimm->idx, location, dimm->csrow, dimm->cschannel);
 	edac_dbg(4, "  dimm = %p\n", dimm);
 	edac_dbg(4, "  dimm->label = '%s'\n", dimm->label);
 	edac_dbg(4, "  dimm->nr_pages = 0x%x\n", dimm->nr_pages);
@@ -314,25 +317,28 @@ struct mem_ctl_info *edac_mc_alloc(unsigned int mc_num,
 	struct dimm_info *dimm;
 	u32 *ce_per_layer[EDAC_MAX_LAYERS], *ue_per_layer[EDAC_MAX_LAYERS];
 	unsigned int pos[EDAC_MAX_LAYERS];
-	unsigned int size, tot_dimms = 1, count = 1;
+	unsigned int idx, size, tot_dimms = 1, count = 1;
 	unsigned int tot_csrows = 1, tot_channels = 1, tot_errcount = 0;
 	void *pvt, *p, *ptr = NULL;
-	int i, j, row, chn, n, len, off;
+	int i, j, row, chn, n, len;
 	bool per_rank = false;
 
-	BUG_ON(n_layers > EDAC_MAX_LAYERS || n_layers == 0);
+	if (WARN_ON(n_layers > EDAC_MAX_LAYERS || n_layers == 0))
+		return NULL;
+
 	/*
 	 * Calculate the total amount of dimms and csrows/cschannels while
 	 * in the old API emulation mode
 	 */
-	for (i = 0; i < n_layers; i++) {
-		tot_dimms *= layers[i].size;
-		if (layers[i].is_virt_csrow)
-			tot_csrows *= layers[i].size;
+	for (idx = 0; idx < n_layers; idx++) {
+		tot_dimms *= layers[idx].size;
+
+		if (layers[idx].is_virt_csrow)
+			tot_csrows *= layers[idx].size;
 		else
-			tot_channels *= layers[i].size;
+			tot_channels *= layers[idx].size;
 
-		if (layers[i].type == EDAC_MC_LAYER_CHIP_SELECT)
+		if (layers[idx].type == EDAC_MC_LAYER_CHIP_SELECT)
 			per_rank = true;
 	}
 
@@ -425,19 +431,15 @@ struct mem_ctl_info *edac_mc_alloc(unsigned int mc_num,
 	memset(&pos, 0, sizeof(pos));
 	row = 0;
 	chn = 0;
-	for (i = 0; i < tot_dimms; i++) {
+	for (idx = 0; idx < tot_dimms; idx++) {
 		chan = mci->csrows[row]->channels[chn];
-		off = EDAC_DIMM_OFF(layer, n_layers, pos[0], pos[1], pos[2]);
-		if (off < 0 || off >= tot_dimms) {
-			edac_mc_printk(mci, KERN_ERR, "EDAC core bug: EDAC_DIMM_OFF is trying to do an illegal data access\n");
-			goto error;
-		}
 
 		dimm = kzalloc(sizeof(**mci->dimms), GFP_KERNEL);
 		if (!dimm)
 			goto error;
-		mci->dimms[off] = dimm;
+		mci->dimms[idx] = dimm;
 		dimm->mci = mci;
+		dimm->idx = idx;
 
 		/*
 		 * Copy DIMM location and initialize it.
@@ -714,6 +716,7 @@ int edac_mc_add_mc_with_groups(struct mem_ctl_info *mci,
 		edac_mc_dump_mci(mci);
 
 	if (edac_debug_level >= 4) {
+		struct dimm_info *dimm;
 		int i;
 
 		for (i = 0; i < mci->nr_csrows; i++) {
@@ -730,9 +733,9 @@ int edac_mc_add_mc_with_groups(struct mem_ctl_info *mci,
 				if (csrow->channels[j]->dimm->nr_pages)
 					edac_mc_dump_channel(csrow->channels[j]);
 		}
-		for (i = 0; i < mci->tot_dimms; i++)
-			if (mci->dimms[i]->nr_pages)
-				edac_mc_dump_dimm(mci->dimms[i], i);
+
+		mci_for_each_dimm(mci, dimm)
+			edac_mc_dump_dimm(dimm);
 	}
 #endif
 	mutex_lock(&mem_ctls_mutex);
@@ -1055,6 +1058,21 @@ void edac_raw_mc_handle_error(const enum hw_event_mc_err_type type,
 {
 	char detail[80];
 	int pos[EDAC_MAX_LAYERS] = { e->top_layer, e->mid_layer, e->low_layer };
+	u8 grain_bits;
+
+	/* Sanity-check driver-supplied grain value. */
+	if (WARN_ON_ONCE(!e->grain))
+		e->grain = 1;
+
+	grain_bits = fls_long(e->grain - 1);
+
+	/* Report the error via the trace interface */
+	if (IS_ENABLED(CONFIG_RAS))
+		trace_mc_event(type, e->msg, e->label, e->error_count,
+			       mci->mc_idx, e->top_layer, e->mid_layer,
+			       e->low_layer,
+			       (e->page_frame_number << PAGE_SHIFT) | e->offset_in_page,
+			       grain_bits, e->syndrome, e->other_detail);
 
 	/* Memory type dependent details about the error */
 	if (type == HW_EVENT_ERR_CORRECTED) {
@@ -1090,11 +1108,11 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
 			  const char *msg,
 			  const char *other_detail)
 {
+	struct dimm_info *dimm;
 	char *p;
 	int row = -1, chan = -1;
 	int pos[EDAC_MAX_LAYERS] = { top_layer, mid_layer, low_layer };
 	int i, n_labels = 0;
-	u8 grain_bits;
 	struct edac_raw_error_desc *e = &mci->error_desc;
 
 	edac_dbg(3, "MC%d\n", mci->mc_idx);
@@ -1150,9 +1168,7 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
 	p = e->label;
 	*p = '\0';
 
-	for (i = 0; i < mci->tot_dimms; i++) {
-		struct dimm_info *dimm = mci->dimms[i];
-
+	mci_for_each_dimm(mci, dimm) {
 		if (top_layer >= 0 && top_layer != dimm->location[0])
 			continue;
 		if (mid_layer >= 0 && mid_layer != dimm->location[1])
@@ -1170,37 +1186,37 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
 		 * channel/memory controller/...  may be affected.
 		 * Also, don't show errors for empty DIMM slots.
 		 */
-		if (e->enable_per_layer_report && dimm->nr_pages) {
-			if (n_labels >= EDAC_MAX_LABELS) {
-				e->enable_per_layer_report = false;
-				break;
-			}
-			n_labels++;
-			if (p != e->label) {
-				strcpy(p, OTHER_LABEL);
-				p += strlen(OTHER_LABEL);
-			}
-			strcpy(p, dimm->label);
-			p += strlen(p);
-			*p = '\0';
+		if (!e->enable_per_layer_report || !dimm->nr_pages)
+			continue;
 
-			/*
-			 * get csrow/channel of the DIMM, in order to allow
-			 * incrementing the compat API counters
-			 */
-			edac_dbg(4, "%s csrows map: (%d,%d)\n",
-				 mci->csbased ? "rank" : "dimm",
-				 dimm->csrow, dimm->cschannel);
-			if (row == -1)
-				row = dimm->csrow;
-			else if (row >= 0 && row != dimm->csrow)
-				row = -2;
-
-			if (chan == -1)
-				chan = dimm->cschannel;
-			else if (chan >= 0 && chan != dimm->cschannel)
-				chan = -2;
+		if (n_labels >= EDAC_MAX_LABELS) {
+			e->enable_per_layer_report = false;
+			break;
+		}
+		n_labels++;
+		if (p != e->label) {
+			strcpy(p, OTHER_LABEL);
+			p += strlen(OTHER_LABEL);
 		}
+		strcpy(p, dimm->label);
+		p += strlen(p);
+
+		/*
+		 * get csrow/channel of the DIMM, in order to allow
+		 * incrementing the compat API counters
+		 */
+		edac_dbg(4, "%s csrows map: (%d,%d)\n",
+			mci->csbased ? "rank" : "dimm",
+			dimm->csrow, dimm->cschannel);
+		if (row == -1)
+			row = dimm->csrow;
+		else if (row >= 0 && row != dimm->csrow)
+			row = -2;
+
+		if (chan == -1)
+			chan = dimm->cschannel;
+		else if (chan >= 0 && chan != dimm->cschannel)
+			chan = -2;
 	}
 
 	if (!e->enable_per_layer_report) {
@@ -1234,20 +1250,6 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
 	if (p > e->location)
 		*(p - 1) = '\0';
 
-	/* Sanity-check driver-supplied grain value. */
-	if (WARN_ON_ONCE(!e->grain))
-		e->grain = 1;
-
-	grain_bits = fls_long(e->grain - 1);
-
-	/* Report the error via the trace interface */
-	if (IS_ENABLED(CONFIG_RAS))
-		trace_mc_event(type, e->msg, e->label, e->error_count,
-			       mci->mc_idx, e->top_layer, e->mid_layer,
-			       e->low_layer,
-			       (e->page_frame_number << PAGE_SHIFT) | e->offset_in_page,
-			       grain_bits, e->syndrome, e->other_detail);
-
 	edac_raw_mc_handle_error(type, mci, e);
 }
 EXPORT_SYMBOL_GPL(edac_mc_handle_error);
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 32d016f1ecd1..0367554e7437 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -557,14 +557,8 @@ static ssize_t dimmdev_ce_count_show(struct device *dev,
 {
 	struct dimm_info *dimm = to_dimm(dev);
 	u32 count;
-	int off;
-
-	off = EDAC_DIMM_OFF(dimm->mci->layers,
-			    dimm->mci->n_layers,
-			    dimm->location[0],
-			    dimm->location[1],
-			    dimm->location[2]);
-	count = dimm->mci->ce_per_layer[dimm->mci->n_layers-1][off];
+
+	count = dimm->mci->ce_per_layer[dimm->mci->n_layers-1][dimm->idx];
 	return sprintf(data, "%u\n", count);
 }
 
@@ -574,14 +568,8 @@ static ssize_t dimmdev_ue_count_show(struct device *dev,
 {
 	struct dimm_info *dimm = to_dimm(dev);
 	u32 count;
-	int off;
-
-	off = EDAC_DIMM_OFF(dimm->mci->layers,
-			    dimm->mci->n_layers,
-			    dimm->location[0],
-			    dimm->location[1],
-			    dimm->location[2]);
-	count = dimm->mci->ue_per_layer[dimm->mci->n_layers-1][off];
+
+	count = dimm->mci->ue_per_layer[dimm->mci->n_layers-1][dimm->idx];
 	return sprintf(data, "%u\n", count);
 }
 
@@ -633,8 +621,7 @@ static const struct device_type dimm_attr_type = {
 
 /* Create a DIMM object under specifed memory controller device */
 static int edac_create_dimm_object(struct mem_ctl_info *mci,
-				   struct dimm_info *dimm,
-				   int index)
+				   struct dimm_info *dimm)
 {
 	int err;
 	dimm->mci = mci;
@@ -644,9 +631,9 @@ static int edac_create_dimm_object(struct mem_ctl_info *mci,
 
 	dimm->dev.parent = &mci->dev;
 	if (mci->csbased)
-		dev_set_name(&dimm->dev, "rank%d", index);
+		dev_set_name(&dimm->dev, "rank%d", dimm->idx);
 	else
-		dev_set_name(&dimm->dev, "dimm%d", index);
+		dev_set_name(&dimm->dev, "dimm%d", dimm->idx);
 	dev_set_drvdata(&dimm->dev, dimm);
 	pm_runtime_forbid(&mci->dev);
 
@@ -928,7 +915,8 @@ static const struct device_type mci_attr_type = {
 int edac_create_sysfs_mci_device(struct mem_ctl_info *mci,
 				 const struct attribute_group **groups)
 {
-	int i, err;
+	struct dimm_info *dimm;
+	int err;
 
 	/* get the /sys/devices/system/edac subsys reference */
 	mci->dev.type = &mci_attr_type;
@@ -952,13 +940,12 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci,
 	/*
 	 * Create the dimm/rank devices
 	 */
-	for (i = 0; i < mci->tot_dimms; i++) {
-		struct dimm_info *dimm = mci->dimms[i];
+	mci_for_each_dimm(mci, dimm) {
 		/* Only expose populated DIMMs */
 		if (!dimm->nr_pages)
 			continue;
 
-		err = edac_create_dimm_object(mci, dimm, i);
+		err = edac_create_dimm_object(mci, dimm);
 		if (err)
 			goto fail_unregister_dimm;
 	}
@@ -973,12 +960,9 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci,
 	return 0;
 
 fail_unregister_dimm:
-	for (i--; i >= 0; i--) {
-		struct dimm_info *dimm = mci->dimms[i];
-		if (!dimm->nr_pages)
-			continue;
-
-		device_unregister(&dimm->dev);
+	mci_for_each_dimm(mci, dimm) {
+		if (device_is_registered(&dimm->dev))
+			device_unregister(&dimm->dev);
 	}
 	device_unregister(&mci->dev);
 
@@ -990,7 +974,7 @@ fail_unregister_dimm:
  */
 void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci)
 {
-	int i;
+	struct dimm_info *dimm;
 
 	edac_dbg(0, "\n");
 
@@ -1001,8 +985,7 @@ void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci)
 	edac_delete_csrow_objects(mci);
 #endif
 
-	for (i = 0; i < mci->tot_dimms; i++) {
-		struct dimm_info *dimm = mci->dimms[i];
+	mci_for_each_dimm(mci, dimm) {
 		if (dimm->nr_pages == 0)
 			continue;
 		edac_dbg(1, "unregistering device %s\n", dev_name(&dimm->dev));
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 0bb62857ffb2..b99080d8a10c 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -21,14 +21,22 @@ struct ghes_edac_pvt {
 	struct mem_ctl_info *mci;
 
 	/* Buffers for the error handling routine */
-	char detail_location[240];
-	char other_detail[160];
+	char other_detail[400];
 	char msg[80];
 };
 
-static atomic_t ghes_init = ATOMIC_INIT(0);
+static refcount_t ghes_refcount = REFCOUNT_INIT(0);
+
+/*
+ * Access to ghes_pvt must be protected by ghes_lock. The spinlock
+ * also provides the necessary (implicit) memory barrier for the SMP
+ * case to make the pointer visible on another CPU.
+ */
 static struct ghes_edac_pvt *ghes_pvt;
 
+/* GHES registration mutex */
+static DEFINE_MUTEX(ghes_reg_mutex);
+
 /*
  * Sync with other, potentially concurrent callers of
  * ghes_edac_report_mem_error(). We don't know what the
@@ -79,15 +87,15 @@ static void ghes_edac_count_dimms(const struct dmi_header *dh, void *arg)
 		(*num_dimm)++;
 }
 
-static int get_dimm_smbios_index(u16 handle)
+static int get_dimm_smbios_index(struct mem_ctl_info *mci, u16 handle)
 {
-	struct mem_ctl_info *mci = ghes_pvt->mci;
-	int i;
+	struct dimm_info *dimm;
 
-	for (i = 0; i < mci->tot_dimms; i++) {
-		if (mci->dimms[i]->smbios_handle == handle)
-			return i;
+	mci_for_each_dimm(mci, dimm) {
+		if (dimm->smbios_handle == handle)
+			return dimm->idx;
 	}
+
 	return -1;
 }
 
@@ -98,9 +106,7 @@ static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg)
 
 	if (dh->type == DMI_ENTRY_MEM_DEVICE) {
 		struct memdev_dmi_entry *entry = (struct memdev_dmi_entry *)dh;
-		struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
-						       mci->n_layers,
-						       dimm_fill->count, 0, 0);
+		struct dimm_info *dimm = edac_get_dimm(mci, dimm_fill->count, 0, 0);
 		u16 rdr_mask = BIT(7) | BIT(13);
 
 		if (entry->size == 0xffff) {
@@ -198,13 +204,9 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 	enum hw_event_mc_err_type type;
 	struct edac_raw_error_desc *e;
 	struct mem_ctl_info *mci;
-	struct ghes_edac_pvt *pvt = ghes_pvt;
+	struct ghes_edac_pvt *pvt;
 	unsigned long flags;
 	char *p;
-	u8 grain_bits;
-
-	if (!pvt)
-		return;
 
 	/*
 	 * We can do the locking below because GHES defers error processing
@@ -216,12 +218,17 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 
 	spin_lock_irqsave(&ghes_lock, flags);
 
+	pvt = ghes_pvt;
+	if (!pvt)
+		goto unlock;
+
 	mci = pvt->mci;
 	e = &mci->error_desc;
 
 	/* Cleans the error report buffer */
 	memset(e, 0, sizeof (*e));
 	e->error_count = 1;
+	e->grain = 1;
 	strcpy(e->label, "unknown label");
 	e->msg = pvt->msg;
 	e->other_detail = pvt->other_detail;
@@ -311,13 +318,13 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 
 	/* Error address */
 	if (mem_err->validation_bits & CPER_MEM_VALID_PA) {
-		e->page_frame_number = mem_err->physical_addr >> PAGE_SHIFT;
-		e->offset_in_page = mem_err->physical_addr & ~PAGE_MASK;
+		e->page_frame_number = PHYS_PFN(mem_err->physical_addr);
+		e->offset_in_page = offset_in_page(mem_err->physical_addr);
 	}
 
 	/* Error grain */
 	if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK)
-		e->grain = ~(mem_err->physical_addr_mask & ~PAGE_MASK);
+		e->grain = ~mem_err->physical_addr_mask + 1;
 
 	/* Memory error location, mapped on e->location */
 	p = e->location;
@@ -348,7 +355,7 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 			p += sprintf(p, "DIMM DMI handle: 0x%.4x ",
 				     mem_err->mem_dev_handle);
 
-		index = get_dimm_smbios_index(mem_err->mem_dev_handle);
+		index = get_dimm_smbios_index(mci, mem_err->mem_dev_handle);
 		if (index >= 0) {
 			e->top_layer = index;
 			e->enable_per_layer_report = true;
@@ -360,6 +367,8 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 
 	/* All other fields are mapped on e->other_detail */
 	p = pvt->other_detail;
+	p += snprintf(p, sizeof(pvt->other_detail),
+		"APEI location: %s ", e->location);
 	if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_STATUS) {
 		u64 status = mem_err->error_status;
 
@@ -433,16 +442,9 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 	if (p > pvt->other_detail)
 		*(p - 1) = '\0';
 
-	/* Generate the trace event */
-	grain_bits = fls_long(e->grain);
-	snprintf(pvt->detail_location, sizeof(pvt->detail_location),
-		 "APEI location: %s %s", e->location, e->other_detail);
-	trace_mc_event(type, e->msg, e->label, e->error_count,
-		       mci->mc_idx, e->top_layer, e->mid_layer, e->low_layer,
-		       (e->page_frame_number << PAGE_SHIFT) | e->offset_in_page,
-		       grain_bits, e->syndrome, pvt->detail_location);
-
 	edac_raw_mc_handle_error(type, mci, e);
+
+unlock:
 	spin_unlock_irqrestore(&ghes_lock, flags);
 }
 
@@ -457,10 +459,12 @@ static struct acpi_platform_list plat_list[] = {
 int ghes_edac_register(struct ghes *ghes, struct device *dev)
 {
 	bool fake = false;
-	int rc, num_dimm = 0;
+	int rc = 0, num_dimm = 0;
 	struct mem_ctl_info *mci;
+	struct ghes_edac_pvt *pvt;
 	struct edac_mc_layer layers[1];
 	struct ghes_edac_dimm_fill dimm_fill;
+	unsigned long flags;
 	int idx = -1;
 
 	if (IS_ENABLED(CONFIG_X86)) {
@@ -472,11 +476,14 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev)
 		idx = 0;
 	}
 
+	/* finish another registration/unregistration instance first */
+	mutex_lock(&ghes_reg_mutex);
+
 	/*
 	 * We have only one logical memory controller to which all DIMMs belong.
 	 */
-	if (atomic_inc_return(&ghes_init) > 1)
-		return 0;
+	if (refcount_inc_not_zero(&ghes_refcount))
+		goto unlock;
 
 	/* Get the number of DIMMs */
 	dmi_walk(ghes_edac_count_dimms, &num_dimm);
@@ -494,12 +501,13 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev)
 	mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(struct ghes_edac_pvt));
 	if (!mci) {
 		pr_info("Can't allocate memory for EDAC data\n");
-		return -ENOMEM;
+		rc = -ENOMEM;
+		goto unlock;
 	}
 
-	ghes_pvt	= mci->pvt_info;
-	ghes_pvt->ghes	= ghes;
-	ghes_pvt->mci	= mci;
+	pvt		= mci->pvt_info;
+	pvt->ghes	= ghes;
+	pvt->mci	= mci;
 
 	mci->pdev = dev;
 	mci->mtype_cap = MEM_FLAG_EMPTY;
@@ -527,8 +535,7 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev)
 		dimm_fill.mci = mci;
 		dmi_walk(ghes_edac_dmidecode, &dimm_fill);
 	} else {
-		struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
-						       mci->n_layers, 0, 0, 0);
+		struct dimm_info *dimm = edac_get_dimm(mci, 0, 0, 0);
 
 		dimm->nr_pages = 1;
 		dimm->grain = 128;
@@ -541,23 +548,48 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev)
 	if (rc < 0) {
 		pr_info("Can't register at EDAC core\n");
 		edac_mc_free(mci);
-		return -ENODEV;
+		rc = -ENODEV;
+		goto unlock;
 	}
-	return 0;
+
+	spin_lock_irqsave(&ghes_lock, flags);
+	ghes_pvt = pvt;
+	spin_unlock_irqrestore(&ghes_lock, flags);
+
+	/* only set on success */
+	refcount_set(&ghes_refcount, 1);
+
+unlock:
+	mutex_unlock(&ghes_reg_mutex);
+
+	return rc;
 }
 
 void ghes_edac_unregister(struct ghes *ghes)
 {
 	struct mem_ctl_info *mci;
+	unsigned long flags;
 
-	if (!ghes_pvt)
-		return;
+	mutex_lock(&ghes_reg_mutex);
 
-	if (atomic_dec_return(&ghes_init))
-		return;
+	if (!refcount_dec_and_test(&ghes_refcount))
+		goto unlock;
 
-	mci = ghes_pvt->mci;
+	/*
+	 * Wait for the irq handler being finished.
+	 */
+	spin_lock_irqsave(&ghes_lock, flags);
+	mci = ghes_pvt ? ghes_pvt->mci : NULL;
 	ghes_pvt = NULL;
-	edac_mc_del_mc(mci->pdev);
-	edac_mc_free(mci);
+	spin_unlock_irqrestore(&ghes_lock, flags);
+
+	if (!mci)
+		goto unlock;
+
+	mci = edac_mc_del_mc(mci->pdev);
+	if (mci)
+		edac_mc_free(mci);
+
+unlock:
+	mutex_unlock(&ghes_reg_mutex);
 }
diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c
index c370d5457e6b..059eccf0582b 100644
--- a/drivers/edac/i10nm_base.c
+++ b/drivers/edac/i10nm_base.c
@@ -154,8 +154,7 @@ static int i10nm_get_dimm_config(struct mem_ctl_info *mci)
 
 		ndimms = 0;
 		for (j = 0; j < I10NM_NUM_DIMMS; j++) {
-			dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
-					     mci->n_layers, i, j, 0);
+			dimm = edac_get_dimm(mci, i, j, 0);
 			mtr = I10NM_GET_DIMMMTR(imc, i, j);
 			mcddrtcfg = I10NM_GET_MCDDRTCFG(imc, i, j);
 			edac_dbg(1, "dimmmtr 0x%x mcddrtcfg 0x%x (mc%d ch%d dimm%d)\n",
diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c
index 299b441647cd..432b375a4075 100644
--- a/drivers/edac/i3200_edac.c
+++ b/drivers/edac/i3200_edac.c
@@ -392,8 +392,7 @@ static int i3200_probe1(struct pci_dev *pdev, int dev_idx)
 		unsigned long nr_pages;
 
 		for (j = 0; j < nr_channels; j++) {
-			struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
-							       mci->n_layers, i, j, 0);
+			struct dimm_info *dimm = edac_get_dimm(mci, i, j, 0);
 
 			nr_pages = drb_to_nr_pages(drbs, stacked, j, i);
 			if (nr_pages == 0)
diff --git a/drivers/edac/i5000_edac.c b/drivers/edac/i5000_edac.c
index 078a7351bf05..1a6f69c859ab 100644
--- a/drivers/edac/i5000_edac.c
+++ b/drivers/edac/i5000_edac.c
@@ -1275,9 +1275,8 @@ static int i5000_init_csrows(struct mem_ctl_info *mci)
 			if (!MTR_DIMMS_PRESENT(mtr))
 				continue;
 
-			dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers,
-				       channel / MAX_BRANCHES,
-				       channel % MAX_BRANCHES, slot);
+			dimm = edac_get_dimm(mci, channel / MAX_BRANCHES,
+					     channel % MAX_BRANCHES, slot);
 
 			csrow_megs = pvt->dimm_info[slot][channel].megabytes;
 			dimm->grain = 8;
diff --git a/drivers/edac/i5100_edac.c b/drivers/edac/i5100_edac.c
index 251f2b692785..0ddc41e47a96 100644
--- a/drivers/edac/i5100_edac.c
+++ b/drivers/edac/i5100_edac.c
@@ -713,7 +713,6 @@ static int i5100_read_spd_byte(const struct mem_ctl_info *mci,
 {
 	struct i5100_priv *priv = mci->pvt_info;
 	u16 w;
-	unsigned long et;
 
 	pci_read_config_word(priv->mc, I5100_SPDDATA, &w);
 	if (i5100_spddata_busy(w))
@@ -724,7 +723,6 @@ static int i5100_read_spd_byte(const struct mem_ctl_info *mci,
 						   0, 0));
 
 	/* wait up to 100ms */
-	et = jiffies + HZ / 10;
 	udelay(100);
 	while (1) {
 		pci_read_config_word(priv->mc, I5100_SPDDATA, &w);
@@ -848,21 +846,17 @@ static void i5100_init_interleaving(struct pci_dev *pdev,
 
 static void i5100_init_csrows(struct mem_ctl_info *mci)
 {
-	int i;
 	struct i5100_priv *priv = mci->pvt_info;
+	struct dimm_info *dimm;
 
-	for (i = 0; i < mci->tot_dimms; i++) {
-		struct dimm_info *dimm;
-		const unsigned long npages = i5100_npages(mci, i);
-		const unsigned int chan = i5100_csrow_to_chan(mci, i);
-		const unsigned int rank = i5100_csrow_to_rank(mci, i);
+	mci_for_each_dimm(mci, dimm) {
+		const unsigned long npages = i5100_npages(mci, dimm->idx);
+		const unsigned int chan = i5100_csrow_to_chan(mci, dimm->idx);
+		const unsigned int rank = i5100_csrow_to_rank(mci, dimm->idx);
 
 		if (!npages)
 			continue;
 
-		dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers,
-			       chan, rank, 0);
-
 		dimm->nr_pages = npages;
 		dimm->grain = 32;
 		dimm->dtype = (priv->mtr[chan][rank].width == 4) ?
diff --git a/drivers/edac/i5400_edac.c b/drivers/edac/i5400_edac.c
index 6f8bcdb9256a..f131c05ade9f 100644
--- a/drivers/edac/i5400_edac.c
+++ b/drivers/edac/i5400_edac.c
@@ -548,8 +548,8 @@ static void i5400_proccess_non_recoverable_info(struct mem_ctl_info *mci,
 	ras = nrec_ras(info);
 	cas = nrec_cas(info);
 
-	edac_dbg(0, "\t\tDIMM= %d  Channels= %d,%d  (Branch= %d DRAM Bank= %d Buffer ID = %d rdwr= %s ras= %d cas= %d)\n",
-		 rank, channel, channel + 1, branch >> 1, bank,
+	edac_dbg(0, "\t\t%s DIMM= %d  Channels= %d,%d  (Branch= %d DRAM Bank= %d Buffer ID = %d rdwr= %s ras= %d cas= %d)\n",
+		 type, rank, channel, channel + 1, branch >> 1, bank,
 		 buf_id, rdwr_str(rdwr), ras, cas);
 
 	/* Only 1 bit will be on */
@@ -1054,8 +1054,6 @@ static void i5400_get_mc_regs(struct mem_ctl_info *mci)
 	u32 actual_tolm;
 	u16 limit;
 	int slot_row;
-	int maxch;
-	int maxdimmperch;
 	int way0, way1;
 
 	pvt = mci->pvt_info;
@@ -1065,9 +1063,6 @@ static void i5400_get_mc_regs(struct mem_ctl_info *mci)
 	pci_read_config_dword(pvt->system_address, AMBASE + sizeof(u32),
 			&pvt->u.ambase_top);
 
-	maxdimmperch = pvt->maxdimmperch;
-	maxch = pvt->maxch;
-
 	edac_dbg(2, "AMBASE= 0x%lx  MAXCH= %d  MAX-DIMM-Per-CH= %d\n",
 		 (long unsigned int)pvt->ambase, pvt->maxch, pvt->maxdimmperch);
 
@@ -1170,17 +1165,13 @@ static int i5400_init_dimms(struct mem_ctl_info *mci)
 {
 	struct i5400_pvt *pvt;
 	struct dimm_info *dimm;
-	int ndimms, channel_count;
-	int max_dimms;
+	int ndimms;
 	int mtr;
 	int size_mb;
 	int  channel, slot;
 
 	pvt = mci->pvt_info;
 
-	channel_count = pvt->maxch;
-	max_dimms = pvt->maxdimmperch;
-
 	ndimms = 0;
 
 	/*
@@ -1196,8 +1187,7 @@ static int i5400_init_dimms(struct mem_ctl_info *mci)
 			if (!MTR_DIMMS_PRESENT(mtr))
 				continue;
 
-			dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers,
-				       channel / 2, channel % 2, slot);
+			dimm = edac_get_dimm(mci, channel / 2, channel % 2, slot);
 
 			size_mb =  pvt->dimm_info[slot][channel].megabytes;
 
diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c
index 7bf910d54d11..2e9bbe56cde9 100644
--- a/drivers/edac/i7300_edac.c
+++ b/drivers/edac/i7300_edac.c
@@ -580,7 +580,7 @@ static void i7300_enable_error_reporting(struct mem_ctl_info *mci)
  * @ch: Channel number within the branch (0 or 1)
  * @branch: Branch number (0 or 1)
  * @dinfo: Pointer to DIMM info where dimm size is stored
- * @p_csrow: Pointer to the struct csrow_info that corresponds to that element
+ * @dimm: Pointer to the struct dimm_info that corresponds to that element
  */
 static int decode_mtr(struct i7300_pvt *pvt,
 		      int slot, int ch, int branch,
@@ -794,8 +794,7 @@ static int i7300_init_csrows(struct mem_ctl_info *mci)
 			for (ch = 0; ch < max_channel; ch++) {
 				int channel = to_channel(ch, branch);
 
-				dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
-					       mci->n_layers, branch, ch, slot);
+				dimm = edac_get_dimm(mci, branch, ch, slot);
 
 				dinfo = &pvt->dimm_info[slot][channel];
 
@@ -817,7 +816,7 @@ static int i7300_init_csrows(struct mem_ctl_info *mci)
 
 /**
  * decode_mir() - Decodes Memory Interleave Register (MIR) info
- * @int mir_no: number of the MIR register to decode
+ * @mir_no: number of the MIR register to decode
  * @mir: array with the MIR data cached on the driver
  */
 static void decode_mir(int mir_no, u16 mir[MAX_MIR])
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index a71cca6eeb33..b3135b208f9a 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -585,8 +585,7 @@ static int get_dimm_config(struct mem_ctl_info *mci)
 			if (!DIMM_PRESENT(dimm_dod[j]))
 				continue;
 
-			dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers,
-				       i, j, 0);
+			dimm = edac_get_dimm(mci, i, j, 0);
 			banks = numbank(MC_DOD_NUMBANK(dimm_dod[j]));
 			ranks = numrank(MC_DOD_NUMRANK(dimm_dod[j]));
 			rows = numrow(MC_DOD_NUMROW(dimm_dod[j]));
diff --git a/drivers/edac/ie31200_edac.c b/drivers/edac/ie31200_edac.c
index d26300f9cb07..4f65073f230b 100644
--- a/drivers/edac/ie31200_edac.c
+++ b/drivers/edac/ie31200_edac.c
@@ -490,9 +490,7 @@ static int ie31200_probe1(struct pci_dev *pdev, int dev_idx)
 
 			if (dimm_info[j][i].dual_rank) {
 				nr_pages = nr_pages / 2;
-				dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
-						     mci->n_layers, (i * 2) + 1,
-						     j, 0);
+				dimm = edac_get_dimm(mci, (i * 2) + 1, j, 0);
 				dimm->nr_pages = nr_pages;
 				edac_dbg(0, "set nr pages: 0x%lx\n", nr_pages);
 				dimm->grain = 8; /* just a guess */
@@ -503,8 +501,7 @@ static int ie31200_probe1(struct pci_dev *pdev, int dev_idx)
 				dimm->dtype = DEV_UNKNOWN;
 				dimm->edac_mode = EDAC_UNKNOWN;
 			}
-			dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
-					     mci->n_layers, i * 2, j, 0);
+			dimm = edac_get_dimm(mci, i * 2, j, 0);
 			dimm->nr_pages = nr_pages;
 			edac_dbg(0, "set nr pages: 0x%lx\n", nr_pages);
 			dimm->grain = 8; /* same guess */
diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c
index b1193be1ef1d..933f7722b893 100644
--- a/drivers/edac/pnd2_edac.c
+++ b/drivers/edac/pnd2_edac.c
@@ -1231,7 +1231,7 @@ static void apl_get_dimm_config(struct mem_ctl_info *mci)
 		if (!(chan_mask & BIT(i)))
 			continue;
 
-		dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, i, 0, 0);
+		dimm = edac_get_dimm(mci, i, 0, 0);
 		if (!dimm) {
 			edac_dbg(0, "No allocated DIMM for channel %d\n", i);
 			continue;
@@ -1311,7 +1311,7 @@ static void dnv_get_dimm_config(struct mem_ctl_info *mci)
 			if (!ranks_of_dimm[j])
 				continue;
 
-			dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, i, j, 0);
+			dimm = edac_get_dimm(mci, i, j, 0);
 			if (!dimm) {
 				edac_dbg(0, "No allocated DIMM for channel %d DIMM %d\n", i, j);
 				continue;
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index f743502ca9b7..4957e8ee1879 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -254,18 +254,20 @@ static const u32 rir_offset[MAX_RIR_RANGES][MAX_RIR_WAY] = {
  * FIXME: Implement the error count reads directly
  */
 
-static const u32 correrrcnt[] = {
-	0x104, 0x108, 0x10c, 0x110,
-};
-
 #define RANK_ODD_OV(reg)		GET_BITFIELD(reg, 31, 31)
 #define RANK_ODD_ERR_CNT(reg)		GET_BITFIELD(reg, 16, 30)
 #define RANK_EVEN_OV(reg)		GET_BITFIELD(reg, 15, 15)
 #define RANK_EVEN_ERR_CNT(reg)		GET_BITFIELD(reg,  0, 14)
 
+#if 0 /* Currently unused*/
+static const u32 correrrcnt[] = {
+	0x104, 0x108, 0x10c, 0x110,
+};
+
 static const u32 correrrthrsld[] = {
 	0x11c, 0x120, 0x124, 0x128,
 };
+#endif
 
 #define RANK_ODD_ERR_THRSLD(reg)	GET_BITFIELD(reg, 16, 30)
 #define RANK_EVEN_ERR_THRSLD(reg)	GET_BITFIELD(reg,  0, 14)
@@ -1340,7 +1342,7 @@ static void knl_show_mc_route(u32 reg, char *s)
  */
 static int knl_get_dimm_capacity(struct sbridge_pvt *pvt, u64 *mc_sizes)
 {
-	u64 sad_base, sad_size, sad_limit = 0;
+	u64 sad_base, sad_limit = 0;
 	u64 tad_base, tad_size, tad_limit, tad_deadspace, tad_livespace;
 	int sad_rule = 0;
 	int tad_rule = 0;
@@ -1427,7 +1429,6 @@ static int knl_get_dimm_capacity(struct sbridge_pvt *pvt, u64 *mc_sizes)
 		edram_only = KNL_EDRAM_ONLY(dram_rule);
 
 		sad_limit = pvt->info.sad_limit(dram_rule)+1;
-		sad_size = sad_limit - sad_base;
 
 		pci_read_config_dword(pvt->pci_sad0,
 			pvt->info.interleave_list[sad_rule], &interleave_reg);
@@ -1620,7 +1621,7 @@ static int __populate_dimms(struct mem_ctl_info *mci,
 		}
 
 		for (j = 0; j < max_dimms_per_channel; j++) {
-			dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, i, j, 0);
+			dimm = edac_get_dimm(mci, i, j, 0);
 			if (pvt->info.type == KNIGHTS_LANDING) {
 				pci_read_config_dword(pvt->knl.pci_channel[i],
 					knl_mtr_reg, &mtr);
@@ -2952,7 +2953,7 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci,
 	struct mem_ctl_info *new_mci;
 	struct sbridge_pvt *pvt = mci->pvt_info;
 	enum hw_event_mc_err_type tp_event;
-	char *type, *optype, msg[256];
+	char *optype, msg[256];
 	bool ripv = GET_BITFIELD(m->mcgstatus, 0, 0);
 	bool overflow = GET_BITFIELD(m->status, 62, 62);
 	bool uncorrected_error = GET_BITFIELD(m->status, 61, 61);
@@ -2981,14 +2982,11 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci,
 	if (uncorrected_error) {
 		core_err_cnt = 1;
 		if (ripv) {
-			type = "FATAL";
 			tp_event = HW_EVENT_ERR_FATAL;
 		} else {
-			type = "NON_FATAL";
 			tp_event = HW_EVENT_ERR_UNCORRECTED;
 		}
 	} else {
-		type = "CORRECTED";
 		tp_event = HW_EVENT_ERR_CORRECTED;
 	}
 
@@ -3200,7 +3198,6 @@ static struct notifier_block sbridge_mce_dec = {
 static void sbridge_unregister_mci(struct sbridge_dev *sbridge_dev)
 {
 	struct mem_ctl_info *mci = sbridge_dev->mci;
-	struct sbridge_pvt *pvt;
 
 	if (unlikely(!mci || !mci->pvt_info)) {
 		edac_dbg(0, "MC: dev = %p\n", &sbridge_dev->pdev[0]->dev);
@@ -3209,8 +3206,6 @@ static void sbridge_unregister_mci(struct sbridge_dev *sbridge_dev)
 		return;
 	}
 
-	pvt = mci->pvt_info;
-
 	edac_dbg(0, "MC: mci = %p, dev = %p\n",
 		 mci, &sbridge_dev->pdev[0]->dev);
 
diff --git a/drivers/edac/skx_base.c b/drivers/edac/skx_base.c
index 0fcf3785e8f3..83545b4facb7 100644
--- a/drivers/edac/skx_base.c
+++ b/drivers/edac/skx_base.c
@@ -46,7 +46,8 @@ static struct skx_dev *get_skx_dev(struct pci_bus *bus, u8 idx)
 }
 
 enum munittype {
-	CHAN0, CHAN1, CHAN2, SAD_ALL, UTIL_ALL, SAD
+	CHAN0, CHAN1, CHAN2, SAD_ALL, UTIL_ALL, SAD,
+	ERRCHAN0, ERRCHAN1, ERRCHAN2,
 };
 
 struct munit {
@@ -68,6 +69,9 @@ static const struct munit skx_all_munits[] = {
 	{ 0x2040, { PCI_DEVFN(10, 0), PCI_DEVFN(12, 0) }, 2, 2, CHAN0 },
 	{ 0x2044, { PCI_DEVFN(10, 4), PCI_DEVFN(12, 4) }, 2, 2, CHAN1 },
 	{ 0x2048, { PCI_DEVFN(11, 0), PCI_DEVFN(13, 0) }, 2, 2, CHAN2 },
+	{ 0x2043, { PCI_DEVFN(10, 3), PCI_DEVFN(12, 3) }, 2, 2, ERRCHAN0 },
+	{ 0x2047, { PCI_DEVFN(10, 7), PCI_DEVFN(12, 7) }, 2, 2, ERRCHAN1 },
+	{ 0x204b, { PCI_DEVFN(11, 3), PCI_DEVFN(13, 3) }, 2, 2, ERRCHAN2 },
 	{ 0x208e, { }, 1, 0, SAD },
 	{ }
 };
@@ -104,10 +108,18 @@ static int get_all_munits(const struct munit *m)
 		}
 
 		switch (m->mtype) {
-		case CHAN0: case CHAN1: case CHAN2:
+		case CHAN0:
+		case CHAN1:
+		case CHAN2:
 			pci_dev_get(pdev);
 			d->imc[i].chan[m->mtype].cdev = pdev;
 			break;
+		case ERRCHAN0:
+		case ERRCHAN1:
+		case ERRCHAN2:
+			pci_dev_get(pdev);
+			d->imc[i].chan[m->mtype - ERRCHAN0].edev = pdev;
+			break;
 		case SAD_ALL:
 			pci_dev_get(pdev);
 			d->sad_all = pdev;
@@ -177,8 +189,7 @@ static int skx_get_dimm_config(struct mem_ctl_info *mci)
 		pci_read_config_dword(imc->chan[i].cdev, 0x8C, &amap);
 		pci_read_config_dword(imc->chan[i].cdev, 0x400, &mcddrtcfg);
 		for (j = 0; j < SKX_NUM_DIMMS; j++) {
-			dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
-					     mci->n_layers, i, j, 0);
+			dimm = edac_get_dimm(mci, i, j, 0);
 			pci_read_config_dword(imc->chan[i].cdev,
 					      0x80 + 4 * j, &mtr);
 			if (IS_DIMM_PRESENT(mtr)) {
@@ -216,6 +227,39 @@ static int skx_get_dimm_config(struct mem_ctl_info *mci)
 #define SKX_ILV_REMOTE(tgt)	(((tgt) & 8) == 0)
 #define SKX_ILV_TARGET(tgt)	((tgt) & 7)
 
+static void skx_show_retry_rd_err_log(struct decoded_addr *res,
+				      char *msg, int len)
+{
+	u32 log0, log1, log2, log3, log4;
+	u32 corr0, corr1, corr2, corr3;
+	struct pci_dev *edev;
+	int n;
+
+	edev = res->dev->imc[res->imc].chan[res->channel].edev;
+
+	pci_read_config_dword(edev, 0x154, &log0);
+	pci_read_config_dword(edev, 0x148, &log1);
+	pci_read_config_dword(edev, 0x150, &log2);
+	pci_read_config_dword(edev, 0x15c, &log3);
+	pci_read_config_dword(edev, 0x114, &log4);
+
+	n = snprintf(msg, len, " retry_rd_err_log[%.8x %.8x %.8x %.8x %.8x]",
+		     log0, log1, log2, log3, log4);
+
+	pci_read_config_dword(edev, 0x104, &corr0);
+	pci_read_config_dword(edev, 0x108, &corr1);
+	pci_read_config_dword(edev, 0x10c, &corr2);
+	pci_read_config_dword(edev, 0x110, &corr3);
+
+	if (len - n > 0)
+		snprintf(msg + n, len - n,
+			 " correrrcnt[%.4x %.4x %.4x %.4x %.4x %.4x %.4x %.4x]",
+			 corr0 & 0xffff, corr0 >> 16,
+			 corr1 & 0xffff, corr1 >> 16,
+			 corr2 & 0xffff, corr2 >> 16,
+			 corr3 & 0xffff, corr3 >> 16);
+}
+
 static bool skx_sad_decode(struct decoded_addr *res)
 {
 	struct skx_dev *d = list_first_entry(skx_edac_list, typeof(*d), list);
@@ -659,7 +703,7 @@ static int __init skx_init(void)
 		}
 	}
 
-	skx_set_decode(skx_decode);
+	skx_set_decode(skx_decode, skx_show_retry_rd_err_log);
 
 	if (nvdimm_count && skx_adxl_get() == -ENODEV)
 		skx_printk(KERN_NOTICE, "Only decoding DDR4 address!\n");
diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c
index d8ff63d91b86..95662a4ff4c4 100644
--- a/drivers/edac/skx_common.c
+++ b/drivers/edac/skx_common.c
@@ -37,6 +37,7 @@ static char *adxl_msg;
 
 static char skx_msg[MSG_SIZE];
 static skx_decode_f skx_decode;
+static skx_show_retry_log_f skx_show_retry_rd_err_log;
 static u64 skx_tolm, skx_tohm;
 static LIST_HEAD(dev_edac_list);
 
@@ -100,6 +101,7 @@ void __exit skx_adxl_put(void)
 
 static bool skx_adxl_decode(struct decoded_addr *res)
 {
+	struct skx_dev *d;
 	int i, len = 0;
 
 	if (res->addr >= skx_tohm || (res->addr >= skx_tolm &&
@@ -118,6 +120,24 @@ static bool skx_adxl_decode(struct decoded_addr *res)
 	res->channel = (int)adxl_values[component_indices[INDEX_CHANNEL]];
 	res->dimm    = (int)adxl_values[component_indices[INDEX_DIMM]];
 
+	if (res->imc > NUM_IMC - 1) {
+		skx_printk(KERN_ERR, "Bad imc %d\n", res->imc);
+		return false;
+	}
+
+	list_for_each_entry(d, &dev_edac_list, list) {
+		if (d->imc[0].src_id == res->socket) {
+			res->dev = d;
+			break;
+		}
+	}
+
+	if (!res->dev) {
+		skx_printk(KERN_ERR, "No device for src_id %d imc %d\n",
+			   res->socket, res->imc);
+		return false;
+	}
+
 	for (i = 0; i < adxl_component_count; i++) {
 		if (adxl_values[i] == ~0x0ull)
 			continue;
@@ -131,9 +151,10 @@ static bool skx_adxl_decode(struct decoded_addr *res)
 	return true;
 }
 
-void skx_set_decode(skx_decode_f decode)
+void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log)
 {
 	skx_decode = decode;
+	skx_show_retry_rd_err_log = show_retry_log;
 }
 
 int skx_get_src_id(struct skx_dev *d, int off, u8 *id)
@@ -452,34 +473,17 @@ static void skx_unregister_mci(struct skx_imc *imc)
 	edac_mc_free(mci);
 }
 
-static struct mem_ctl_info *get_mci(int src_id, int lmc)
-{
-	struct skx_dev *d;
-
-	if (lmc > NUM_IMC - 1) {
-		skx_printk(KERN_ERR, "Bad lmc %d\n", lmc);
-		return NULL;
-	}
-
-	list_for_each_entry(d, &dev_edac_list, list) {
-		if (d->imc[0].src_id == src_id)
-			return d->imc[lmc].mci;
-	}
-
-	skx_printk(KERN_ERR, "No mci for src_id %d lmc %d\n", src_id, lmc);
-	return NULL;
-}
-
 static void skx_mce_output_error(struct mem_ctl_info *mci,
 				 const struct mce *m,
 				 struct decoded_addr *res)
 {
 	enum hw_event_mc_err_type tp_event;
-	char *type, *optype;
+	char *optype;
 	bool ripv = GET_BITFIELD(m->mcgstatus, 0, 0);
 	bool overflow = GET_BITFIELD(m->status, 62, 62);
 	bool uncorrected_error = GET_BITFIELD(m->status, 61, 61);
 	bool recoverable;
+	int len;
 	u32 core_err_cnt = GET_BITFIELD(m->status, 38, 52);
 	u32 mscod = GET_BITFIELD(m->status, 16, 31);
 	u32 errcode = GET_BITFIELD(m->status, 0, 15);
@@ -490,14 +494,11 @@ static void skx_mce_output_error(struct mem_ctl_info *mci,
 	if (uncorrected_error) {
 		core_err_cnt = 1;
 		if (ripv) {
-			type = "FATAL";
 			tp_event = HW_EVENT_ERR_FATAL;
 		} else {
-			type = "NON_FATAL";
 			tp_event = HW_EVENT_ERR_UNCORRECTED;
 		}
 	} else {
-		type = "CORRECTED";
 		tp_event = HW_EVENT_ERR_CORRECTED;
 	}
 
@@ -539,12 +540,12 @@ static void skx_mce_output_error(struct mem_ctl_info *mci,
 		}
 	}
 	if (adxl_component_count) {
-		snprintf(skx_msg, MSG_SIZE, "%s%s err_code:0x%04x:0x%04x %s",
+		len = snprintf(skx_msg, MSG_SIZE, "%s%s err_code:0x%04x:0x%04x %s",
 			 overflow ? " OVERFLOW" : "",
 			 (uncorrected_error && recoverable) ? " recoverable" : "",
 			 mscod, errcode, adxl_msg);
 	} else {
-		snprintf(skx_msg, MSG_SIZE,
+		len = snprintf(skx_msg, MSG_SIZE,
 			 "%s%s err_code:0x%04x:0x%04x socket:%d imc:%d rank:%d bg:%d ba:%d row:0x%x col:0x%x",
 			 overflow ? " OVERFLOW" : "",
 			 (uncorrected_error && recoverable) ? " recoverable" : "",
@@ -553,6 +554,9 @@ static void skx_mce_output_error(struct mem_ctl_info *mci,
 			 res->bank_group, res->bank_address, res->row, res->column);
 	}
 
+	if (skx_show_retry_rd_err_log)
+		skx_show_retry_rd_err_log(res, skx_msg + len, MSG_SIZE - len);
+
 	edac_dbg(0, "%s\n", skx_msg);
 
 	/* Call the helper to output message */
@@ -583,15 +587,12 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
 	if (adxl_component_count) {
 		if (!skx_adxl_decode(&res))
 			return NOTIFY_DONE;
-
-		mci = get_mci(res.socket, res.imc);
-	} else {
-		if (!skx_decode || !skx_decode(&res))
-			return NOTIFY_DONE;
-
-		mci = res.dev->imc[res.imc].mci;
+	} else if (!skx_decode || !skx_decode(&res)) {
+		return NOTIFY_DONE;
 	}
 
+	mci = res.dev->imc[res.imc].mci;
+
 	if (!mci)
 		return NOTIFY_DONE;
 
diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h
index 08cc971a50ea..60d1ea669afd 100644
--- a/drivers/edac/skx_common.h
+++ b/drivers/edac/skx_common.h
@@ -64,6 +64,7 @@ struct skx_dev {
 		u8 src_id, node_id;
 		struct skx_channel {
 			struct pci_dev	*cdev;
+			struct pci_dev	*edev;
 			struct skx_dimm {
 				u8 close_pg;
 				u8 bank_xor_enable;
@@ -113,10 +114,11 @@ struct decoded_addr {
 
 typedef int (*get_dimm_config_f)(struct mem_ctl_info *mci);
 typedef bool (*skx_decode_f)(struct decoded_addr *res);
+typedef void (*skx_show_retry_log_f)(struct decoded_addr *res, char *msg, int len);
 
 int __init skx_adxl_get(void);
 void __exit skx_adxl_put(void);
-void skx_set_decode(skx_decode_f decode);
+void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log);
 
 int skx_get_src_id(struct skx_dev *d, int off, u8 *id);
 int skx_get_node_id(struct skx_dev *d, u8 *id);
diff --git a/drivers/edac/ti_edac.c b/drivers/edac/ti_edac.c
index 6ac26d1b929f..8be3e89a510e 100644
--- a/drivers/edac/ti_edac.c
+++ b/drivers/edac/ti_edac.c
@@ -135,7 +135,7 @@ static void ti_edac_setup_dimm(struct mem_ctl_info *mci, u32 type)
 	u32 val;
 	u32 memsize;
 
-	dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, 0, 0, 0);
+	dimm = edac_get_dimm(mci, 0, 0, 0);
 
 	val = ti_edac_readl(edac, EMIF_SDRAM_CONFIG);
 
diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
index 9cd70d1a5622..a479023fa036 100644
--- a/drivers/firmware/arm_sdei.c
+++ b/drivers/firmware/arm_sdei.c
@@ -967,29 +967,29 @@ static int sdei_get_conduit(struct platform_device *pdev)
 	if (np) {
 		if (of_property_read_string(np, "method", &method)) {
 			pr_warn("missing \"method\" property\n");
-			return CONDUIT_INVALID;
+			return SMCCC_CONDUIT_NONE;
 		}
 
 		if (!strcmp("hvc", method)) {
 			sdei_firmware_call = &sdei_smccc_hvc;
-			return CONDUIT_HVC;
+			return SMCCC_CONDUIT_HVC;
 		} else if (!strcmp("smc", method)) {
 			sdei_firmware_call = &sdei_smccc_smc;
-			return CONDUIT_SMC;
+			return SMCCC_CONDUIT_SMC;
 		}
 
 		pr_warn("invalid \"method\" property: %s\n", method);
 	} else if (IS_ENABLED(CONFIG_ACPI) && !acpi_disabled) {
 		if (acpi_psci_use_hvc()) {
 			sdei_firmware_call = &sdei_smccc_hvc;
-			return CONDUIT_HVC;
+			return SMCCC_CONDUIT_HVC;
 		} else {
 			sdei_firmware_call = &sdei_smccc_smc;
-			return CONDUIT_SMC;
+			return SMCCC_CONDUIT_SMC;
 		}
 	}
 
-	return CONDUIT_INVALID;
+	return SMCCC_CONDUIT_NONE;
 }
 
 static int sdei_probe(struct platform_device *pdev)
diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index 84f4ff351c62..b3b6c15e7b36 100644
--- a/drivers/firmware/psci/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -53,10 +53,18 @@ bool psci_tos_resident_on(int cpu)
 }
 
 struct psci_operations psci_ops = {
-	.conduit = PSCI_CONDUIT_NONE,
+	.conduit = SMCCC_CONDUIT_NONE,
 	.smccc_version = SMCCC_VERSION_1_0,
 };
 
+enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void)
+{
+	if (psci_ops.smccc_version < SMCCC_VERSION_1_1)
+		return SMCCC_CONDUIT_NONE;
+
+	return psci_ops.conduit;
+}
+
 typedef unsigned long (psci_fn)(unsigned long, unsigned long,
 				unsigned long, unsigned long);
 static psci_fn *invoke_psci_fn;
@@ -212,13 +220,13 @@ static unsigned long psci_migrate_info_up_cpu(void)
 			      0, 0, 0);
 }
 
-static void set_conduit(enum psci_conduit conduit)
+static void set_conduit(enum arm_smccc_conduit conduit)
 {
 	switch (conduit) {
-	case PSCI_CONDUIT_HVC:
+	case SMCCC_CONDUIT_HVC:
 		invoke_psci_fn = __invoke_psci_fn_hvc;
 		break;
-	case PSCI_CONDUIT_SMC:
+	case SMCCC_CONDUIT_SMC:
 		invoke_psci_fn = __invoke_psci_fn_smc;
 		break;
 	default:
@@ -240,9 +248,9 @@ static int get_set_conduit_method(struct device_node *np)
 	}
 
 	if (!strcmp("hvc", method)) {
-		set_conduit(PSCI_CONDUIT_HVC);
+		set_conduit(SMCCC_CONDUIT_HVC);
 	} else if (!strcmp("smc", method)) {
-		set_conduit(PSCI_CONDUIT_SMC);
+		set_conduit(SMCCC_CONDUIT_SMC);
 	} else {
 		pr_warn("invalid \"method\" property: %s\n", method);
 		return -EINVAL;
@@ -583,9 +591,9 @@ int __init psci_acpi_init(void)
 	pr_info("probing for conduit method from ACPI.\n");
 
 	if (acpi_psci_use_hvc())
-		set_conduit(PSCI_CONDUIT_HVC);
+		set_conduit(SMCCC_CONDUIT_HVC);
 	else
-		set_conduit(PSCI_CONDUIT_SMC);
+		set_conduit(SMCCC_CONDUIT_SMC);
 
 	return psci_probe();
 }
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 38e096e6925f..92d0ff63b3ea 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -298,7 +298,7 @@ config GPIO_IXP4XX
 
 config GPIO_LOONGSON
 	bool "Loongson-2/3 GPIO support"
-	depends on CPU_LOONGSON2 || CPU_LOONGSON3
+	depends on CPU_LOONGSON2EF || CPU_LOONGSON64
 	help
 	  driver for GPIO functionality on Loongson-2F/3A/3B processors.
 
diff --git a/drivers/gpio/gpio-loongson.c b/drivers/gpio/gpio-loongson.c
index 00943170ce36..a42145873cc9 100644
--- a/drivers/gpio/gpio-loongson.c
+++ b/drivers/gpio/gpio-loongson.c
@@ -22,7 +22,7 @@
 #define STLS2F_N_GPIO		4
 #define STLS3A_N_GPIO		16
 
-#ifdef CONFIG_CPU_LOONGSON3
+#ifdef CONFIG_CPU_LOONGSON64
 #define LOONGSON_N_GPIO	STLS3A_N_GPIO
 #else
 #define LOONGSON_N_GPIO	STLS2F_N_GPIO
diff --git a/drivers/ide/falconide.c b/drivers/ide/falconide.c
index a5a07ccb81a7..dbeb2605e5f6 100644
--- a/drivers/ide/falconide.c
+++ b/drivers/ide/falconide.c
@@ -15,6 +15,7 @@
 #include <linux/blkdev.h>
 #include <linux/ide.h>
 #include <linux/init.h>
+#include <linux/platform_device.h>
 
 #include <asm/setup.h>
 #include <asm/atarihw.h>
@@ -25,13 +26,7 @@
 #define DRV_NAME "falconide"
 
     /*
-     *  Base of the IDE interface
-     */
-
-#define ATA_HD_BASE	0xfff00000
-
-    /*
-     *  Offsets from the above base
+     *  Offsets from base address
      */
 
 #define ATA_HD_CONTROL	0x39
@@ -114,18 +109,18 @@ static const struct ide_port_info falconide_port_info = {
 	.chipset		= ide_generic,
 };
 
-static void __init falconide_setup_ports(struct ide_hw *hw)
+static void __init falconide_setup_ports(struct ide_hw *hw, unsigned long base)
 {
 	int i;
 
 	memset(hw, 0, sizeof(*hw));
 
-	hw->io_ports.data_addr = ATA_HD_BASE;
+	hw->io_ports.data_addr = base;
 
 	for (i = 1; i < 8; i++)
-		hw->io_ports_array[i] = ATA_HD_BASE + 1 + i * 4;
+		hw->io_ports_array[i] = base + 1 + i * 4;
 
-	hw->io_ports.ctl_addr = ATA_HD_BASE + ATA_HD_CONTROL;
+	hw->io_ports.ctl_addr = base + ATA_HD_CONTROL;
 
 	hw->irq = IRQ_MFP_IDE;
 }
@@ -134,23 +129,29 @@ static void __init falconide_setup_ports(struct ide_hw *hw)
      *  Probe for a Falcon IDE interface
      */
 
-static int __init falconide_init(void)
+static int __init falconide_init(struct platform_device *pdev)
 {
+	struct resource *res;
 	struct ide_host *host;
 	struct ide_hw hw, *hws[] = { &hw };
+	unsigned long base;
 	int rc;
 
-	if (!MACH_IS_ATARI || !ATARIHW_PRESENT(IDE))
-		return -ENODEV;
+	dev_info(&pdev->dev, "Atari Falcon IDE controller\n");
 
-	printk(KERN_INFO "ide: Falcon IDE controller\n");
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENODEV;
 
-	if (!request_mem_region(ATA_HD_BASE, 0x40, DRV_NAME)) {
-		printk(KERN_ERR "%s: resources busy\n", DRV_NAME);
+	if (!devm_request_mem_region(&pdev->dev, res->start,
+				     resource_size(res), DRV_NAME)) {
+		dev_err(&pdev->dev, "resources busy\n");
 		return -EBUSY;
 	}
 
-	falconide_setup_ports(&hw);
+	base = (unsigned long)res->start;
+
+	falconide_setup_ports(&hw, base);
 
 	host = ide_host_alloc(&falconide_port_info, hws, 1);
 	if (host == NULL) {
@@ -169,10 +170,29 @@ static int __init falconide_init(void)
 err_free:
 	ide_host_free(host);
 err:
-	release_mem_region(ATA_HD_BASE, 0x40);
+	release_mem_region(res->start, resource_size(res));
 	return rc;
 }
 
-module_init(falconide_init);
+static int falconide_remove(struct platform_device *pdev)
+{
+	struct ide_host *host = dev_get_drvdata(&pdev->dev);
+
+	ide_host_remove(host);
+
+	return 0;
+}
+
+static struct platform_driver ide_falcon_driver = {
+	.remove = falconide_remove,
+	.driver   = {
+		.name	= "atari-falcon-ide",
+	},
+};
+
+module_platform_driver_probe(ide_falcon_driver, falconide_init);
 
+MODULE_AUTHOR("Geert Uytterhoeven");
+MODULE_DESCRIPTION("low-level driver for Atari Falcon IDE");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:atari-falcon-ide");
diff --git a/drivers/ide/tx4938ide.c b/drivers/ide/tx4938ide.c
index 40a3f55b08dd..962eb92501b5 100644
--- a/drivers/ide/tx4938ide.c
+++ b/drivers/ide/tx4938ide.c
@@ -46,7 +46,7 @@ static void tx4938ide_tune_ebusc(unsigned int ebus_ch,
 	while ((shwt * 4 + wt + (wt ? 2 : 3)) * cycle < t->cycle)
 		shwt++;
 	if (shwt > 7) {
-		pr_warning("tx4938ide: SHWT violation (%d)\n", shwt);
+		pr_warn("tx4938ide: SHWT violation (%d)\n", shwt);
 		shwt = 7;
 	}
 	pr_debug("tx4938ide: ebus %d, bus cycle %dns, WT %d, SHWT %d\n",
diff --git a/drivers/ide/tx4939ide.c b/drivers/ide/tx4939ide.c
index 88d132edc4e3..d5e871fe840d 100644
--- a/drivers/ide/tx4939ide.c
+++ b/drivers/ide/tx4939ide.c
@@ -363,9 +363,9 @@ static int tx4939ide_dma_test_irq(ide_drive_t *drive)
 	case TX4939IDE_INT_HOST | TX4939IDE_INT_XFEREND:
 		dma_stat = tx4939ide_readb(base, TX4939IDE_DMA_Stat);
 		if (!(dma_stat & ATA_DMA_INTR))
-			pr_warning("%s: weird interrupt status. "
-				   "DMA_Stat %#02x int_ctl %#04x\n",
-				   hwif->name, dma_stat, ctl);
+			pr_warn("%s: weird interrupt status. "
+				"DMA_Stat %#02x int_ctl %#04x\n",
+				hwif->name, dma_stat, ctl);
 		found = 1;
 		break;
 	}
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 704558d449a2..56fae3472114 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -177,7 +177,6 @@ static const char * const smbus_pnp_ids[] = {
 	"LEN0096", /* X280 */
 	"LEN0097", /* X280 -> ALPS trackpoint */
 	"LEN009b", /* T580 */
-	"LEN0402", /* X1 Extreme 2nd Generation */
 	"LEN200f", /* T450s */
 	"LEN2054", /* E480 */
 	"LEN2055", /* E580 */
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 1edc99335a94..6bb1f682f78b 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -87,6 +87,15 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key);
  */
 static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis);
 
+/*
+ * Global static key controlling whether an update to PMR allowing more
+ * interrupts requires to be propagated to the redistributor (DSB SY).
+ * And this needs to be exported for modules to be able to enable
+ * interrupts...
+ */
+DEFINE_STATIC_KEY_FALSE(gic_pmr_sync);
+EXPORT_SYMBOL(gic_pmr_sync);
+
 /* ppi_nmi_refs[n] == number of cpus having ppi[n + 16] set as NMI */
 static refcount_t *ppi_nmi_refs;
 
@@ -1502,6 +1511,17 @@ static void gic_enable_nmi_support(void)
 	for (i = 0; i < gic_data.ppi_nr; i++)
 		refcount_set(&ppi_nmi_refs[i], 0);
 
+	/*
+	 * Linux itself doesn't use 1:N distribution, so has no need to
+	 * set PMHE. The only reason to have it set is if EL3 requires it
+	 * (and we can't change it).
+	 */
+	if (gic_read_ctlr() & ICC_CTLR_EL1_PMHE_MASK)
+		static_branch_enable(&gic_pmr_sync);
+
+	pr_info("%s ICC_PMR_EL1 synchronisation\n",
+		static_branch_unlikely(&gic_pmr_sync) ? "Forcing" : "Relaxing");
+
 	static_branch_enable(&supports_pseudo_nmis);
 
 	if (static_branch_likely(&supports_deactivate_key))
diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c
index 563e87ed0766..45969927cc81 100644
--- a/drivers/irqchip/irq-gic-v4.c
+++ b/drivers/irqchip/irq-gic-v4.c
@@ -141,12 +141,17 @@ static int its_send_vpe_cmd(struct its_vpe *vpe, struct its_cmd_info *info)
 int its_schedule_vpe(struct its_vpe *vpe, bool on)
 {
 	struct its_cmd_info info;
+	int ret;
 
 	WARN_ON(preemptible());
 
 	info.cmd_type = on ? SCHEDULE_VPE : DESCHEDULE_VPE;
 
-	return its_send_vpe_cmd(vpe, &info);
+	ret = its_send_vpe_cmd(vpe, &info);
+	if (!ret)
+		vpe->resident = on;
+
+	return ret;
 }
 
 int its_invall_vpe(struct its_vpe *vpe)
diff --git a/drivers/isdn/hardware/mISDN/avmfritz.c b/drivers/isdn/hardware/mISDN/avmfritz.c
index 1137dd152b5c..ecc1ef6c386d 100644
--- a/drivers/isdn/hardware/mISDN/avmfritz.c
+++ b/drivers/isdn/hardware/mISDN/avmfritz.c
@@ -402,8 +402,8 @@ hdlc_empty_fifo(struct bchannel *bch, int count)
 	} else {
 		cnt = bchannel_get_rxbuf(bch, count);
 		if (cnt < 0) {
-			pr_warning("%s.B%d: No bufferspace for %d bytes\n",
-				   fc->name, bch->nr, count);
+			pr_warn("%s.B%d: No bufferspace for %d bytes\n",
+				fc->name, bch->nr, count);
 			return;
 		}
 		p = skb_put(bch->rx_skb, count);
@@ -538,8 +538,8 @@ HDLC_irq(struct bchannel *bch, u32 stat)
 	}
 	if (stat & HDLC_INT_RPR) {
 		if (stat & HDLC_STAT_RDO) {
-			pr_warning("%s: ch%d stat %x RDO\n",
-				   fc->name, bch->nr, stat);
+			pr_warn("%s: ch%d stat %x RDO\n",
+				fc->name, bch->nr, stat);
 			hdlc->ctrl.sr.xml = 0;
 			hdlc->ctrl.sr.cmd |= HDLC_CMD_RRS;
 			write_ctrl(bch, 1);
@@ -561,8 +561,8 @@ HDLC_irq(struct bchannel *bch, u32 stat)
 				    HDLC_STAT_CRCVFR) {
 					recv_Bchannel(bch, 0, false);
 				} else {
-					pr_warning("%s: got invalid frame\n",
-						   fc->name);
+					pr_warn("%s: got invalid frame\n",
+						fc->name);
 					skb_trim(bch->rx_skb, 0);
 				}
 			}
@@ -574,8 +574,8 @@ handle_tx:
 		 * restart transmitting the whole frame on HDLC
 		 * in transparent mode we send the next data
 		 */
-		pr_warning("%s: ch%d stat %x XDU %s\n", fc->name, bch->nr,
-			   stat, bch->tx_skb ? "tx_skb" : "no tx_skb");
+		pr_warn("%s: ch%d stat %x XDU %s\n", fc->name, bch->nr,
+			stat, bch->tx_skb ? "tx_skb" : "no tx_skb");
 		if (bch->tx_skb && bch->tx_skb->len) {
 			if (!test_bit(FLG_TRANSPARENT, &bch->Flags))
 				bch->tx_idx = 0;
diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c
index 86669ec8b977..7013a3f08429 100644
--- a/drivers/isdn/hardware/mISDN/hfcmulti.c
+++ b/drivers/isdn/hardware/mISDN/hfcmulti.c
@@ -2248,8 +2248,8 @@ next_frame:
 	if (bch) {
 		maxlen = bchannel_get_rxbuf(bch, Zsize);
 		if (maxlen < 0) {
-			pr_warning("card%d.B%d: No bufferspace for %d bytes\n",
-				   hc->id + 1, bch->nr, Zsize);
+			pr_warn("card%d.B%d: No bufferspace for %d bytes\n",
+				hc->id + 1, bch->nr, Zsize);
 			return;
 		}
 		sp = &bch->rx_skb;
@@ -2260,8 +2260,8 @@ next_frame:
 		if (*sp == NULL) {
 			*sp = mI_alloc_skb(maxlen, GFP_ATOMIC);
 			if (*sp == NULL) {
-				pr_warning("card%d: No mem for dch rx_skb\n",
-					   hc->id + 1);
+				pr_warn("card%d: No mem for dch rx_skb\n",
+					hc->id + 1);
 				return;
 			}
 		}
diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index 2330a7d24267..abdf787c1a71 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -566,8 +566,7 @@ hfcpci_empty_fifo_trans(struct bchannel *bch, struct bzfifo *rxbz,
 	}
 	maxlen = bchannel_get_rxbuf(bch, fcnt_rx);
 	if (maxlen < 0) {
-		pr_warning("B%d: No bufferspace for %d bytes\n",
-			   bch->nr, fcnt_rx);
+		pr_warn("B%d: No bufferspace for %d bytes\n", bch->nr, fcnt_rx);
 	} else {
 		ptr = skb_put(bch->rx_skb, fcnt_rx);
 		if (le16_to_cpu(*z2r) + fcnt_rx <= B_FIFO_SIZE + B_SUB_VAL)
diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c
index 008a74a1ed44..621364bb6b12 100644
--- a/drivers/isdn/hardware/mISDN/hfcsusb.c
+++ b/drivers/isdn/hardware/mISDN/hfcsusb.c
@@ -841,8 +841,8 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len,
 		if (maxlen < 0) {
 			if (rx_skb)
 				skb_trim(rx_skb, 0);
-			pr_warning("%s.B%d: No bufferspace for %d bytes\n",
-				   hw->name, fifo->bch->nr, len);
+			pr_warn("%s.B%d: No bufferspace for %d bytes\n",
+				hw->name, fifo->bch->nr, len);
 			spin_unlock_irqrestore(&hw->lock, flags);
 			return;
 		}
diff --git a/drivers/isdn/hardware/mISDN/mISDNipac.c b/drivers/isdn/hardware/mISDN/mISDNipac.c
index bca880213e91..ec475087fbf9 100644
--- a/drivers/isdn/hardware/mISDN/mISDNipac.c
+++ b/drivers/isdn/hardware/mISDN/mISDNipac.c
@@ -936,8 +936,8 @@ hscx_empty_fifo(struct hscx_hw *hscx, u8 count)
 		hscx_cmdr(hscx, 0x80); /* RMC */
 		if (hscx->bch.rx_skb)
 			skb_trim(hscx->bch.rx_skb, 0);
-		pr_warning("%s.B%d: No bufferspace for %d bytes\n",
-			   hscx->ip->name, hscx->bch.nr, count);
+		pr_warn("%s.B%d: No bufferspace for %d bytes\n",
+			hscx->ip->name, hscx->bch.nr, count);
 		return;
 	}
 	p = skb_put(hscx->bch.rx_skb, count);
diff --git a/drivers/isdn/hardware/mISDN/mISDNisar.c b/drivers/isdn/hardware/mISDN/mISDNisar.c
index 0303b23c2b02..e325e87c0593 100644
--- a/drivers/isdn/hardware/mISDN/mISDNisar.c
+++ b/drivers/isdn/hardware/mISDN/mISDNisar.c
@@ -221,7 +221,7 @@ load_firmware(struct isar_hw *isar, const u8 *buf, int size)
 			goto reterror;
 		}
 		if (!poll_mbox(isar, 1000)) {
-			pr_warning("ISAR poll_mbox dkey failed\n");
+			pr_warn("ISAR poll_mbox dkey failed\n");
 			ret = -ETIME;
 			goto reterror;
 		}
@@ -431,8 +431,8 @@ isar_rcv_frame(struct isar_ch *ch)
 	case ISDN_P_B_MODEM_ASYNC:
 		maxlen = bchannel_get_rxbuf(&ch->bch, ch->is->clsb);
 		if (maxlen < 0) {
-			pr_warning("%s.B%d: No bufferspace for %d bytes\n",
-				   ch->is->name, ch->bch.nr, ch->is->clsb);
+			pr_warn("%s.B%d: No bufferspace for %d bytes\n",
+				ch->is->name, ch->bch.nr, ch->is->clsb);
 			ch->is->write_reg(ch->is->hw, ISAR_IIA, 0);
 			break;
 		}
@@ -442,8 +442,8 @@ isar_rcv_frame(struct isar_ch *ch)
 	case ISDN_P_B_HDLC:
 		maxlen = bchannel_get_rxbuf(&ch->bch, ch->is->clsb);
 		if (maxlen < 0) {
-			pr_warning("%s.B%d: No bufferspace for %d bytes\n",
-				   ch->is->name, ch->bch.nr, ch->is->clsb);
+			pr_warn("%s.B%d: No bufferspace for %d bytes\n",
+				ch->is->name, ch->bch.nr, ch->is->clsb);
 			ch->is->write_reg(ch->is->hw, ISAR_IIA, 0);
 			break;
 		}
diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c
index 61caa7e50b9a..6aae97e827b7 100644
--- a/drivers/isdn/hardware/mISDN/netjet.c
+++ b/drivers/isdn/hardware/mISDN/netjet.c
@@ -380,8 +380,8 @@ read_dma(struct tiger_ch *bc, u32 idx, int cnt)
 	stat = bchannel_get_rxbuf(&bc->bch, cnt);
 	/* only transparent use the count here, HDLC overun is detected later */
 	if (stat == -ENOMEM) {
-		pr_warning("%s.B%d: No memory for %d bytes\n",
-			   card->name, bc->bch.nr, cnt);
+		pr_warn("%s.B%d: No memory for %d bytes\n",
+			card->name, bc->bch.nr, cnt);
 		return;
 	}
 	if (test_bit(FLG_TRANSPARENT, &bc->bch.Flags))
@@ -420,8 +420,8 @@ read_dma(struct tiger_ch *bc, u32 idx, int cnt)
 			recv_Bchannel(&bc->bch, 0, false);
 			stat = bchannel_get_rxbuf(&bc->bch, bc->bch.maxlen);
 			if (stat < 0) {
-				pr_warning("%s.B%d: No memory for %d bytes\n",
-					   card->name, bc->bch.nr, cnt);
+				pr_warn("%s.B%d: No memory for %d bytes\n",
+					card->name, bc->bch.nr, cnt);
 				return;
 			}
 		} else if (stat == -HDLC_CRC_ERROR) {
diff --git a/drivers/isdn/hardware/mISDN/w6692.c b/drivers/isdn/hardware/mISDN/w6692.c
index bad55fdacd36..f3b8db7b48fe 100644
--- a/drivers/isdn/hardware/mISDN/w6692.c
+++ b/drivers/isdn/hardware/mISDN/w6692.c
@@ -466,8 +466,8 @@ W6692_empty_Bfifo(struct w6692_ch *wch, int count)
 		WriteW6692B(wch, W_B_CMDR, W_B_CMDR_RACK | W_B_CMDR_RACT);
 		if (wch->bch.rx_skb)
 			skb_trim(wch->bch.rx_skb, 0);
-		pr_warning("%s.B%d: No bufferspace for %d bytes\n",
-			   card->name, wch->bch.nr, count);
+		pr_warn("%s.B%d: No bufferspace for %d bytes\n",
+			card->name, wch->bch.nr, count);
 		return;
 	}
 	ptr = skb_put(wch->bch.rx_skb, count);
@@ -729,8 +729,8 @@ W6692B_interrupt(struct w6692_hw *card, int ch)
 				 wch->bch.nr, star);
 		}
 		if (star & W_B_STAR_XDOW) {
-			pr_warning("%s: B%d XDOW proto=%x\n", card->name,
-				   wch->bch.nr, wch->bch.state);
+			pr_warn("%s: B%d XDOW proto=%x\n", card->name,
+				wch->bch.nr, wch->bch.state);
 #ifdef ERROR_STATISTIC
 			wch->bch.err_xdu++;
 #endif
@@ -747,8 +747,8 @@ W6692B_interrupt(struct w6692_hw *card, int ch)
 			return; /* handle XDOW only once */
 	}
 	if (stat & W_B_EXI_XDUN) {
-		pr_warning("%s: B%d XDUN proto=%x\n", card->name,
-			   wch->bch.nr, wch->bch.state);
+		pr_warn("%s: B%d XDUN proto=%x\n", card->name,
+			wch->bch.nr, wch->bch.state);
 #ifdef ERROR_STATISTIC
 		wch->bch.err_xdu++;
 #endif
diff --git a/drivers/isdn/mISDN/hwchannel.c b/drivers/isdn/mISDN/hwchannel.c
index f378173bcf6f..8c93af06ed02 100644
--- a/drivers/isdn/mISDN/hwchannel.c
+++ b/drivers/isdn/mISDN/hwchannel.c
@@ -474,8 +474,8 @@ bchannel_get_rxbuf(struct bchannel *bch, int reqlen)
 	if (bch->rx_skb) {
 		len = skb_tailroom(bch->rx_skb);
 		if (len < reqlen) {
-			pr_warning("B%d no space for %d (only %d) bytes\n",
-				   bch->nr, reqlen, len);
+			pr_warn("B%d no space for %d (only %d) bytes\n",
+				bch->nr, reqlen, len);
 			if (test_bit(FLG_TRANSPARENT, &bch->Flags)) {
 				/* send what we have now and try a new buffer */
 				recv_Bchannel(bch, 0, true);
@@ -508,8 +508,7 @@ bchannel_get_rxbuf(struct bchannel *bch, int reqlen)
 	}
 	bch->rx_skb = mI_alloc_skb(len, GFP_ATOMIC);
 	if (!bch->rx_skb) {
-		pr_warning("B%d receive no memory for %d bytes\n",
-			   bch->nr, len);
+		pr_warn("B%d receive no memory for %d bytes\n", bch->nr, len);
 		len = -ENOMEM;
 	}
 	return len;
diff --git a/drivers/macintosh/windfarm_fcu_controls.c b/drivers/macintosh/windfarm_fcu_controls.c
index 3c971297b6dc..67daeec94b44 100644
--- a/drivers/macintosh/windfarm_fcu_controls.c
+++ b/drivers/macintosh/windfarm_fcu_controls.c
@@ -468,9 +468,7 @@ static void wf_fcu_lookup_fans(struct wf_fcu_priv *pv)
 			else
 				id = ((*reg) - 0x30) / 2;
 			if (id > 7) {
-				pr_warning("wf_fcu: Can't parse "
-				       "fan ID in device-tree for %pOF\n",
-					   np);
+				pr_warn("wf_fcu: Can't parse fan ID in device-tree for %pOF\n", np);
 				break;
 			}
 			wf_fcu_add_fan(pv, name, type, id);
diff --git a/drivers/macintosh/windfarm_lm87_sensor.c b/drivers/macintosh/windfarm_lm87_sensor.c
index e44525b19071..b03a33b803b7 100644
--- a/drivers/macintosh/windfarm_lm87_sensor.c
+++ b/drivers/macintosh/windfarm_lm87_sensor.c
@@ -124,8 +124,8 @@ static int wf_lm87_probe(struct i2c_client *client,
 		}
 	}
 	if (!name) {
-		pr_warning("wf_lm87: Unsupported sensor %pOF\n",
-			   client->dev.of_node);
+		pr_warn("wf_lm87: Unsupported sensor %pOF\n",
+			client->dev.of_node);
 		return -ENODEV;
 	}
 
diff --git a/drivers/macintosh/windfarm_pm72.c b/drivers/macintosh/windfarm_pm72.c
index c5da0fc24884..e81746b87cff 100644
--- a/drivers/macintosh/windfarm_pm72.c
+++ b/drivers/macintosh/windfarm_pm72.c
@@ -285,8 +285,8 @@ static void cpu_fans_tick_split(void)
 		/* Apply result directly to exhaust fan */
 		err = wf_control_set(cpu_rear_fans[cpu], sp->target);
 		if (err) {
-			pr_warning("wf_pm72: Fan %s reports error %d\n",
-			       cpu_rear_fans[cpu]->name, err);
+			pr_warn("wf_pm72: Fan %s reports error %d\n",
+				cpu_rear_fans[cpu]->name, err);
 			failure_state |= FAILURE_FAN;
 			break;
 		}
@@ -296,8 +296,8 @@ static void cpu_fans_tick_split(void)
 		DBG_LOTS("  CPU%d: intake = %d RPM\n", cpu, intake);
 		err = wf_control_set(cpu_front_fans[cpu], intake);
 		if (err) {
-			pr_warning("wf_pm72: Fan %s reports error %d\n",
-			       cpu_front_fans[cpu]->name, err);
+			pr_warn("wf_pm72: Fan %s reports error %d\n",
+				cpu_front_fans[cpu]->name, err);
 			failure_state |= FAILURE_FAN;
 			break;
 		}
@@ -367,22 +367,22 @@ static void cpu_fans_tick_combined(void)
 	for (cpu = 0; cpu < nr_chips; cpu++) {
 		err = wf_control_set(cpu_rear_fans[cpu], sp->target);
 		if (err) {
-			pr_warning("wf_pm72: Fan %s reports error %d\n",
-				   cpu_rear_fans[cpu]->name, err);
+			pr_warn("wf_pm72: Fan %s reports error %d\n",
+				cpu_rear_fans[cpu]->name, err);
 			failure_state |= FAILURE_FAN;
 		}
 		err = wf_control_set(cpu_front_fans[cpu], intake);
 		if (err) {
-			pr_warning("wf_pm72: Fan %s reports error %d\n",
-				   cpu_front_fans[cpu]->name, err);
+			pr_warn("wf_pm72: Fan %s reports error %d\n",
+				cpu_front_fans[cpu]->name, err);
 			failure_state |= FAILURE_FAN;
 		}
 		err = 0;
 		if (cpu_pumps[cpu])
 			err = wf_control_set(cpu_pumps[cpu], pump);
 		if (err) {
-			pr_warning("wf_pm72: Pump %s reports error %d\n",
-				   cpu_pumps[cpu]->name, err);
+			pr_warn("wf_pm72: Pump %s reports error %d\n",
+				cpu_pumps[cpu]->name, err);
 			failure_state |= FAILURE_FAN;
 		}
 	}
@@ -561,7 +561,7 @@ static void drives_fan_tick(void)
 
 	err = wf_sensor_get(drives_temp, &temp);
 	if (err) {
-		pr_warning("wf_pm72: drive bay temp sensor error %d\n", err);
+		pr_warn("wf_pm72: drive bay temp sensor error %d\n", err);
 		failure_state |= FAILURE_SENSOR;
 		wf_control_set_max(drives_fan);
 		return;
diff --git a/drivers/macintosh/windfarm_rm31.c b/drivers/macintosh/windfarm_rm31.c
index 8456eb67184b..7acd1684c451 100644
--- a/drivers/macintosh/windfarm_rm31.c
+++ b/drivers/macintosh/windfarm_rm31.c
@@ -281,8 +281,8 @@ static void cpu_fans_tick(void)
 		for (i = 0; i < 3; i++) {
 			err = wf_control_set(cpu_fans[cpu][i], speed);
 			if (err) {
-				pr_warning("wf_rm31: Fan %s reports error %d\n",
-					   cpu_fans[cpu][i]->name, err);
+				pr_warn("wf_rm31: Fan %s reports error %d\n",
+					cpu_fans[cpu][i]->name, err);
 				failure_state |= FAILURE_FAN;
 			}
 		}
@@ -465,7 +465,7 @@ static void slots_fan_tick(void)
 
 	err = wf_sensor_get(slots_temp, &temp);
 	if (err) {
-		pr_warning("wf_rm31: slots temp sensor error %d\n", err);
+		pr_warn("wf_rm31: slots temp sensor error %d\n", err);
 		failure_state |= FAILURE_SENSOR;
 		wf_control_set_max(slots_fan);
 		return;
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index aa98953f4462..d6d5ab23c088 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -38,9 +38,9 @@ config MD_AUTODETECT
 	default y
 	---help---
 	  If you say Y here, then the kernel will try to autodetect raid
-	  arrays as part of its boot process. 
+	  arrays as part of its boot process.
 
-	  If you don't use raid and say Y, this autodetection can cause 
+	  If you don't use raid and say Y, this autodetection can cause
 	  a several-second delay in the boot time due to various
 	  synchronisation steps that are part of this step.
 
@@ -290,7 +290,7 @@ config DM_SNAPSHOT
        depends on BLK_DEV_DM
        select DM_BUFIO
        ---help---
-         Allow volume managers to take writable snapshots of a device.
+	 Allow volume managers to take writable snapshots of a device.
 
 config DM_THIN_PROVISIONING
        tristate "Thin provisioning target"
@@ -298,7 +298,7 @@ config DM_THIN_PROVISIONING
        select DM_PERSISTENT_DATA
        select DM_BIO_PRISON
        ---help---
-         Provides thin provisioning and snapshots that share a data store.
+	 Provides thin provisioning and snapshots that share a data store.
 
 config DM_CACHE
        tristate "Cache target (EXPERIMENTAL)"
@@ -307,23 +307,23 @@ config DM_CACHE
        select DM_PERSISTENT_DATA
        select DM_BIO_PRISON
        ---help---
-         dm-cache attempts to improve performance of a block device by
-         moving frequently used data to a smaller, higher performance
-         device.  Different 'policy' plugins can be used to change the
-         algorithms used to select which blocks are promoted, demoted,
-         cleaned etc.  It supports writeback and writethrough modes.
+	 dm-cache attempts to improve performance of a block device by
+	 moving frequently used data to a smaller, higher performance
+	 device.  Different 'policy' plugins can be used to change the
+	 algorithms used to select which blocks are promoted, demoted,
+	 cleaned etc.  It supports writeback and writethrough modes.
 
 config DM_CACHE_SMQ
        tristate "Stochastic MQ Cache Policy (EXPERIMENTAL)"
        depends on DM_CACHE
        default y
        ---help---
-         A cache policy that uses a multiqueue ordered by recent hits
-         to select which blocks should be promoted and demoted.
-         This is meant to be a general purpose policy.  It prioritises
-         reads over writes.  This SMQ policy (vs MQ) offers the promise
-         of less memory utilization, improved performance and increased
-         adaptability in the face of changing workloads.
+	 A cache policy that uses a multiqueue ordered by recent hits
+	 to select which blocks should be promoted and demoted.
+	 This is meant to be a general purpose policy.  It prioritises
+	 reads over writes.  This SMQ policy (vs MQ) offers the promise
+	 of less memory utilization, improved performance and increased
+	 adaptability in the face of changing workloads.
 
 config DM_WRITECACHE
 	tristate "Writecache target"
@@ -343,9 +343,9 @@ config DM_ERA
        select DM_PERSISTENT_DATA
        select DM_BIO_PRISON
        ---help---
-         dm-era tracks which parts of a block device are written to
-         over time.  Useful for maintaining cache coherency when using
-         vendor snapshots.
+	 dm-era tracks which parts of a block device are written to
+	 over time.  Useful for maintaining cache coherency when using
+	 vendor snapshots.
 
 config DM_CLONE
        tristate "Clone target (EXPERIMENTAL)"
@@ -353,20 +353,20 @@ config DM_CLONE
        default n
        select DM_PERSISTENT_DATA
        ---help---
-         dm-clone produces a one-to-one copy of an existing, read-only source
-         device into a writable destination device. The cloned device is
-         visible/mountable immediately and the copy of the source device to the
-         destination device happens in the background, in parallel with user
-         I/O.
+	 dm-clone produces a one-to-one copy of an existing, read-only source
+	 device into a writable destination device. The cloned device is
+	 visible/mountable immediately and the copy of the source device to the
+	 destination device happens in the background, in parallel with user
+	 I/O.
 
-         If unsure, say N.
+	 If unsure, say N.
 
 config DM_MIRROR
        tristate "Mirror target"
        depends on BLK_DEV_DM
        ---help---
-         Allow volume managers to mirror logical volumes, also
-         needed for live data migration tools such as 'pvmove'.
+	 Allow volume managers to mirror logical volumes, also
+	 needed for live data migration tools such as 'pvmove'.
 
 config DM_LOG_USERSPACE
 	tristate "Mirror userspace logging"
@@ -483,7 +483,7 @@ config DM_FLAKEY
        tristate "Flakey target"
        depends on BLK_DEV_DM
        ---help---
-         A target that intermittently fails I/O for debugging purposes.
+	 A target that intermittently fails I/O for debugging purposes.
 
 config DM_VERITY
 	tristate "Verity target support"
diff --git a/drivers/md/bcache/Makefile b/drivers/md/bcache/Makefile
index d26b35195825..fd714628da6a 100644
--- a/drivers/md/bcache/Makefile
+++ b/drivers/md/bcache/Makefile
@@ -5,5 +5,3 @@ obj-$(CONFIG_BCACHE)	+= bcache.o
 bcache-y		:= alloc.o bset.o btree.o closure.o debug.o extents.o\
 	io.o journal.o movinggc.o request.o stats.o super.o sysfs.o trace.o\
 	util.o writeback.o
-
-CFLAGS_request.o	+= -Iblock
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 6f776823b9ba..a1df0d95151c 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -377,7 +377,10 @@ retry_invalidate:
 			if (!fifo_full(&ca->free_inc))
 				goto retry_invalidate;
 
-			bch_prio_write(ca);
+			if (bch_prio_write(ca, false) < 0) {
+				ca->invalidate_needs_gc = 1;
+				wake_up_gc(ca->set);
+			}
 		}
 	}
 out:
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 013e35a9e317..9198c1b480d9 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -582,6 +582,7 @@ struct cache_set {
 	 */
 	wait_queue_head_t	btree_cache_wait;
 	struct task_struct	*btree_cache_alloc_lock;
+	spinlock_t		btree_cannibalize_lock;
 
 	/*
 	 * When we free a btree node, we increment the gen of the bucket the
@@ -723,6 +724,7 @@ struct cache_set {
 	unsigned int		gc_always_rewrite:1;
 	unsigned int		shrinker_disabled:1;
 	unsigned int		copy_gc_enabled:1;
+	unsigned int		idle_max_writeback_rate_enabled:1;
 
 #define BUCKET_HASH_BITS	12
 	struct hlist_head	bucket_hash[1 << BUCKET_HASH_BITS];
@@ -977,7 +979,7 @@ bool bch_cached_dev_error(struct cached_dev *dc);
 __printf(2, 3)
 bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...);
 
-void bch_prio_write(struct cache *ca);
+int bch_prio_write(struct cache *ca, bool wait);
 void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent);
 
 extern struct workqueue_struct *bcache_wq;
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 08768796b543..cffcdc9feefb 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -155,6 +155,7 @@ int __bch_keylist_realloc(struct keylist *l, unsigned int u64s)
 	return 0;
 }
 
+/* Pop the top key of keylist by pointing l->top to its previous key */
 struct bkey *bch_keylist_pop(struct keylist *l)
 {
 	struct bkey *k = l->keys;
@@ -168,6 +169,7 @@ struct bkey *bch_keylist_pop(struct keylist *l)
 	return l->top = k;
 }
 
+/* Pop the bottom key of keylist and update l->top_p */
 void bch_keylist_pop_front(struct keylist *l)
 {
 	l->top_p -= bkey_u64s(l->keys);
@@ -309,7 +311,6 @@ void bch_btree_keys_free(struct btree_keys *b)
 	t->tree = NULL;
 	t->data = NULL;
 }
-EXPORT_SYMBOL(bch_btree_keys_free);
 
 int bch_btree_keys_alloc(struct btree_keys *b,
 			 unsigned int page_order,
@@ -342,7 +343,6 @@ err:
 	bch_btree_keys_free(b);
 	return -ENOMEM;
 }
-EXPORT_SYMBOL(bch_btree_keys_alloc);
 
 void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops,
 			 bool *expensive_debug_checks)
@@ -361,7 +361,6 @@ void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops,
 	 * any more.
 	 */
 }
-EXPORT_SYMBOL(bch_btree_keys_init);
 
 /* Binary tree stuff for auxiliary search trees */
 
@@ -678,7 +677,6 @@ void bch_bset_init_next(struct btree_keys *b, struct bset *i, uint64_t magic)
 
 	bch_bset_build_unwritten_tree(b);
 }
-EXPORT_SYMBOL(bch_bset_init_next);
 
 /*
  * Build auxiliary binary tree 'struct bset_tree *t', this tree is used to
@@ -732,7 +730,6 @@ void bch_bset_build_written_tree(struct btree_keys *b)
 	     j = inorder_next(j, t->size))
 		make_bfloat(t, j);
 }
-EXPORT_SYMBOL(bch_bset_build_written_tree);
 
 /* Insert */
 
@@ -780,7 +777,6 @@ fix_right:	do {
 			j = j * 2 + 1;
 		} while (j < t->size);
 }
-EXPORT_SYMBOL(bch_bset_fix_invalidated_key);
 
 static void bch_bset_fix_lookup_table(struct btree_keys *b,
 				      struct bset_tree *t,
@@ -855,7 +851,6 @@ bool bch_bkey_try_merge(struct btree_keys *b, struct bkey *l, struct bkey *r)
 
 	return b->ops->key_merge(b, l, r);
 }
-EXPORT_SYMBOL(bch_bkey_try_merge);
 
 void bch_bset_insert(struct btree_keys *b, struct bkey *where,
 		     struct bkey *insert)
@@ -875,7 +870,6 @@ void bch_bset_insert(struct btree_keys *b, struct bkey *where,
 	bkey_copy(where, insert);
 	bch_bset_fix_lookup_table(b, t, where);
 }
-EXPORT_SYMBOL(bch_bset_insert);
 
 unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
 			      struct bkey *replace_key)
@@ -931,7 +925,6 @@ copy:	bkey_copy(m, k);
 merged:
 	return status;
 }
-EXPORT_SYMBOL(bch_btree_insert_key);
 
 /* Lookup */
 
@@ -1077,7 +1070,6 @@ struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t,
 
 	return i.l;
 }
-EXPORT_SYMBOL(__bch_bset_search);
 
 /* Btree iterator */
 
@@ -1132,7 +1124,6 @@ struct bkey *bch_btree_iter_init(struct btree_keys *b,
 {
 	return __bch_btree_iter_init(b, iter, search, b->set);
 }
-EXPORT_SYMBOL(bch_btree_iter_init);
 
 static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter,
 						 btree_iter_cmp_fn *cmp)
@@ -1165,7 +1156,6 @@ struct bkey *bch_btree_iter_next(struct btree_iter *iter)
 	return __bch_btree_iter_next(iter, btree_iter_cmp);
 
 }
-EXPORT_SYMBOL(bch_btree_iter_next);
 
 struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter,
 					struct btree_keys *b, ptr_filter_fn fn)
@@ -1196,7 +1186,6 @@ int bch_bset_sort_state_init(struct bset_sort_state *state,
 
 	return mempool_init_page_pool(&state->pool, 1, page_order);
 }
-EXPORT_SYMBOL(bch_bset_sort_state_init);
 
 static void btree_mergesort(struct btree_keys *b, struct bset *out,
 			    struct btree_iter *iter,
@@ -1313,7 +1302,6 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
 
 	EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize);
 }
-EXPORT_SYMBOL(bch_btree_sort_partial);
 
 void bch_btree_sort_and_fix_extents(struct btree_keys *b,
 				    struct btree_iter *iter,
@@ -1366,7 +1354,6 @@ void bch_btree_sort_lazy(struct btree_keys *b, struct bset_sort_state *state)
 out:
 	bch_bset_build_written_tree(b);
 }
-EXPORT_SYMBOL(bch_btree_sort_lazy);
 
 void bch_btree_keys_stats(struct btree_keys *b, struct bset_stats *stats)
 {
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index ba434d9ac720..14d6c33b0957 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -543,6 +543,11 @@ static void bch_btree_leaf_dirty(struct btree *b, atomic_t *journal_ref)
 
 	set_btree_node_dirty(b);
 
+	/*
+	 * w->journal is always the oldest journal pin of all bkeys
+	 * in the leaf node, to make sure the oldest jset seq won't
+	 * be increased before this btree node is flushed.
+	 */
 	if (journal_ref) {
 		if (w->journal &&
 		    journal_pin_cmp(b->c, w->journal, journal_ref)) {
@@ -723,6 +728,8 @@ static unsigned long bch_mca_scan(struct shrinker *shrink,
 	 * IO can always make forward progress:
 	 */
 	nr /= c->btree_pages;
+	if (nr == 0)
+		nr = 1;
 	nr = min_t(unsigned long, nr, mca_can_free(c));
 
 	i = 0;
@@ -884,15 +891,17 @@ out:
 
 static int mca_cannibalize_lock(struct cache_set *c, struct btree_op *op)
 {
-	struct task_struct *old;
-
-	old = cmpxchg(&c->btree_cache_alloc_lock, NULL, current);
-	if (old && old != current) {
+	spin_lock(&c->btree_cannibalize_lock);
+	if (likely(c->btree_cache_alloc_lock == NULL)) {
+		c->btree_cache_alloc_lock = current;
+	} else if (c->btree_cache_alloc_lock != current) {
 		if (op)
 			prepare_to_wait(&c->btree_cache_wait, &op->wait,
 					TASK_UNINTERRUPTIBLE);
+		spin_unlock(&c->btree_cannibalize_lock);
 		return -EINTR;
 	}
+	spin_unlock(&c->btree_cannibalize_lock);
 
 	return 0;
 }
@@ -927,10 +936,12 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op,
  */
 static void bch_cannibalize_unlock(struct cache_set *c)
 {
+	spin_lock(&c->btree_cannibalize_lock);
 	if (c->btree_cache_alloc_lock == current) {
 		c->btree_cache_alloc_lock = NULL;
 		wake_up(&c->btree_cache_wait);
 	}
+	spin_unlock(&c->btree_cannibalize_lock);
 }
 
 static struct btree *mca_alloc(struct cache_set *c, struct btree_op *op,
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index c12cd809ab19..0164a1fe94a9 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -45,7 +45,6 @@ void closure_sub(struct closure *cl, int v)
 {
 	closure_put_after_sub(cl, atomic_sub_return(v, &cl->remaining));
 }
-EXPORT_SYMBOL(closure_sub);
 
 /*
  * closure_put - decrement a closure's refcount
@@ -54,7 +53,6 @@ void closure_put(struct closure *cl)
 {
 	closure_put_after_sub(cl, atomic_dec_return(&cl->remaining));
 }
-EXPORT_SYMBOL(closure_put);
 
 /*
  * closure_wake_up - wake up all closures on a wait list, without memory barrier
@@ -76,7 +74,6 @@ void __closure_wake_up(struct closure_waitlist *wait_list)
 		closure_sub(cl, CLOSURE_WAITING + 1);
 	}
 }
-EXPORT_SYMBOL(__closure_wake_up);
 
 /**
  * closure_wait - add a closure to a waitlist
@@ -96,7 +93,6 @@ bool closure_wait(struct closure_waitlist *waitlist, struct closure *cl)
 
 	return true;
 }
-EXPORT_SYMBOL(closure_wait);
 
 struct closure_syncer {
 	struct task_struct	*task;
@@ -131,7 +127,6 @@ void __sched __closure_sync(struct closure *cl)
 
 	__set_current_state(TASK_RUNNING);
 }
-EXPORT_SYMBOL(__closure_sync);
 
 #ifdef CONFIG_BCACHE_CLOSURES_DEBUG
 
@@ -149,7 +144,6 @@ void closure_debug_create(struct closure *cl)
 	list_add(&cl->all, &closure_list);
 	spin_unlock_irqrestore(&closure_list_lock, flags);
 }
-EXPORT_SYMBOL(closure_debug_create);
 
 void closure_debug_destroy(struct closure *cl)
 {
@@ -162,7 +156,6 @@ void closure_debug_destroy(struct closure *cl)
 	list_del(&cl->all);
 	spin_unlock_irqrestore(&closure_list_lock, flags);
 }
-EXPORT_SYMBOL(closure_debug_destroy);
 
 static struct dentry *closure_debug;
 
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 41adcd1546f1..73478a91a342 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -62,18 +62,6 @@ static void bch_data_insert_keys(struct closure *cl)
 	struct bkey *replace_key = op->replace ? &op->replace_key : NULL;
 	int ret;
 
-	/*
-	 * If we're looping, might already be waiting on
-	 * another journal write - can't wait on more than one journal write at
-	 * a time
-	 *
-	 * XXX: this looks wrong
-	 */
-#if 0
-	while (atomic_read(&s->cl.remaining) & CLOSURE_WAITING)
-		closure_sync(&s->cl);
-#endif
-
 	if (!op->replace)
 		journal_ref = bch_journal(op->c, &op->insert_keys,
 					  op->flush_journal ? cl : NULL);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 20ed838e9413..77e9869345e7 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -92,10 +92,11 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 	pr_debug("read sb version %llu, flags %llu, seq %llu, journal size %u",
 		 sb->version, sb->flags, sb->seq, sb->keys);
 
-	err = "Not a bcache superblock";
+	err = "Not a bcache superblock (bad offset)";
 	if (sb->offset != SB_SECTOR)
 		goto err;
 
+	err = "Not a bcache superblock (bad magic)";
 	if (memcmp(sb->magic, bcache_magic, 16))
 		goto err;
 
@@ -529,12 +530,29 @@ static void prio_io(struct cache *ca, uint64_t bucket, int op,
 	closure_sync(cl);
 }
 
-void bch_prio_write(struct cache *ca)
+int bch_prio_write(struct cache *ca, bool wait)
 {
 	int i;
 	struct bucket *b;
 	struct closure cl;
 
+	pr_debug("free_prio=%zu, free_none=%zu, free_inc=%zu",
+		 fifo_used(&ca->free[RESERVE_PRIO]),
+		 fifo_used(&ca->free[RESERVE_NONE]),
+		 fifo_used(&ca->free_inc));
+
+	/*
+	 * Pre-check if there are enough free buckets. In the non-blocking
+	 * scenario it's better to fail early rather than starting to allocate
+	 * buckets and do a cleanup later in case of failure.
+	 */
+	if (!wait) {
+		size_t avail = fifo_used(&ca->free[RESERVE_PRIO]) +
+			       fifo_used(&ca->free[RESERVE_NONE]);
+		if (prio_buckets(ca) > avail)
+			return -ENOMEM;
+	}
+
 	closure_init_stack(&cl);
 
 	lockdep_assert_held(&ca->set->bucket_lock);
@@ -544,9 +562,6 @@ void bch_prio_write(struct cache *ca)
 	atomic_long_add(ca->sb.bucket_size * prio_buckets(ca),
 			&ca->meta_sectors_written);
 
-	//pr_debug("free %zu, free_inc %zu, unused %zu", fifo_used(&ca->free),
-	//	 fifo_used(&ca->free_inc), fifo_used(&ca->unused));
-
 	for (i = prio_buckets(ca) - 1; i >= 0; --i) {
 		long bucket;
 		struct prio_set *p = ca->disk_buckets;
@@ -564,7 +579,7 @@ void bch_prio_write(struct cache *ca)
 		p->magic	= pset_magic(&ca->sb);
 		p->csum		= bch_crc64(&p->magic, bucket_bytes(ca) - 8);
 
-		bucket = bch_bucket_alloc(ca, RESERVE_PRIO, true);
+		bucket = bch_bucket_alloc(ca, RESERVE_PRIO, wait);
 		BUG_ON(bucket == -1);
 
 		mutex_unlock(&ca->set->bucket_lock);
@@ -593,6 +608,7 @@ void bch_prio_write(struct cache *ca)
 
 		ca->prio_last_buckets[i] = ca->prio_buckets[i];
 	}
+	return 0;
 }
 
 static void prio_read(struct cache *ca, uint64_t bucket)
@@ -761,20 +777,28 @@ static inline int idx_to_first_minor(int idx)
 
 static void bcache_device_free(struct bcache_device *d)
 {
+	struct gendisk *disk = d->disk;
+
 	lockdep_assert_held(&bch_register_lock);
 
-	pr_info("%s stopped", d->disk->disk_name);
+	if (disk)
+		pr_info("%s stopped", disk->disk_name);
+	else
+		pr_err("bcache device (NULL gendisk) stopped");
 
 	if (d->c)
 		bcache_device_detach(d);
-	if (d->disk && d->disk->flags & GENHD_FL_UP)
-		del_gendisk(d->disk);
-	if (d->disk && d->disk->queue)
-		blk_cleanup_queue(d->disk->queue);
-	if (d->disk) {
+
+	if (disk) {
+		if (disk->flags & GENHD_FL_UP)
+			del_gendisk(disk);
+
+		if (disk->queue)
+			blk_cleanup_queue(disk->queue);
+
 		ida_simple_remove(&bcache_device_idx,
-				  first_minor_to_idx(d->disk->first_minor));
-		put_disk(d->disk);
+				  first_minor_to_idx(disk->first_minor));
+		put_disk(disk);
 	}
 
 	bioset_exit(&d->bio_split);
@@ -1769,6 +1793,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	sema_init(&c->sb_write_mutex, 1);
 	mutex_init(&c->bucket_lock);
 	init_waitqueue_head(&c->btree_cache_wait);
+	spin_lock_init(&c->btree_cannibalize_lock);
 	init_waitqueue_head(&c->bucket_wait);
 	init_waitqueue_head(&c->gc_wait);
 	sema_init(&c->uuid_write_mutex, 1);
@@ -1809,6 +1834,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	c->congested_read_threshold_us	= 2000;
 	c->congested_write_threshold_us	= 20000;
 	c->error_limit	= DEFAULT_IO_ERROR_LIMIT;
+	c->idle_max_writeback_rate_enabled = 1;
 	WARN_ON(test_and_clear_bit(CACHE_SET_IO_DISABLE, &c->flags));
 
 	return c;
@@ -1954,7 +1980,7 @@ static int run_cache_set(struct cache_set *c)
 
 		mutex_lock(&c->bucket_lock);
 		for_each_cache(ca, c, i)
-			bch_prio_write(ca);
+			bch_prio_write(ca, true);
 		mutex_unlock(&c->bucket_lock);
 
 		err = "cannot allocate new UUID bucket";
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 627dcea0f5b6..733e2ddf3c78 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -134,6 +134,7 @@ rw_attribute(expensive_debug_checks);
 rw_attribute(cache_replacement_policy);
 rw_attribute(btree_shrinker_disabled);
 rw_attribute(copy_gc_enabled);
+rw_attribute(idle_max_writeback_rate);
 rw_attribute(gc_after_writeback);
 rw_attribute(size);
 
@@ -747,6 +748,8 @@ SHOW(__bch_cache_set)
 	sysfs_printf(gc_always_rewrite,		"%i", c->gc_always_rewrite);
 	sysfs_printf(btree_shrinker_disabled,	"%i", c->shrinker_disabled);
 	sysfs_printf(copy_gc_enabled,		"%i", c->copy_gc_enabled);
+	sysfs_printf(idle_max_writeback_rate,	"%i",
+		     c->idle_max_writeback_rate_enabled);
 	sysfs_printf(gc_after_writeback,	"%i", c->gc_after_writeback);
 	sysfs_printf(io_disable,		"%i",
 		     test_bit(CACHE_SET_IO_DISABLE, &c->flags));
@@ -864,6 +867,9 @@ STORE(__bch_cache_set)
 	sysfs_strtoul_bool(gc_always_rewrite,	c->gc_always_rewrite);
 	sysfs_strtoul_bool(btree_shrinker_disabled, c->shrinker_disabled);
 	sysfs_strtoul_bool(copy_gc_enabled,	c->copy_gc_enabled);
+	sysfs_strtoul_bool(idle_max_writeback_rate,
+			   c->idle_max_writeback_rate_enabled);
+
 	/*
 	 * write gc_after_writeback here may overwrite an already set
 	 * BCH_DO_AUTO_GC, it doesn't matter because this flag will be
@@ -954,6 +960,7 @@ static struct attribute *bch_cache_set_internal_files[] = {
 	&sysfs_gc_always_rewrite,
 	&sysfs_btree_shrinker_disabled,
 	&sysfs_copy_gc_enabled,
+	&sysfs_idle_max_writeback_rate,
 	&sysfs_gc_after_writeback,
 	&sysfs_io_disable,
 	&sysfs_cutoff_writeback,
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index d60268fe49e1..4a40f9eadeaf 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -122,6 +122,10 @@ static void __update_writeback_rate(struct cached_dev *dc)
 static bool set_at_max_writeback_rate(struct cache_set *c,
 				       struct cached_dev *dc)
 {
+	/* Don't sst max writeback rate if it is disabled */
+	if (!c->idle_max_writeback_rate_enabled)
+		return false;
+
 	/* Don't set max writeback rate if gc is running */
 	if (!c->gc_mark_valid)
 		return false;
diff --git a/drivers/md/dm-bio-prison-v1.c b/drivers/md/dm-bio-prison-v1.c
index b5389890bbc3..1f8f98efd97a 100644
--- a/drivers/md/dm-bio-prison-v1.c
+++ b/drivers/md/dm-bio-prison-v1.c
@@ -150,11 +150,10 @@ static int bio_detain(struct dm_bio_prison *prison,
 		      struct dm_bio_prison_cell **cell_result)
 {
 	int r;
-	unsigned long flags;
 
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	r = __bio_detain(prison, key, inmate, cell_prealloc, cell_result);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 
 	return r;
 }
@@ -198,11 +197,9 @@ void dm_cell_release(struct dm_bio_prison *prison,
 		     struct dm_bio_prison_cell *cell,
 		     struct bio_list *bios)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	__cell_release(prison, cell, bios);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 }
 EXPORT_SYMBOL_GPL(dm_cell_release);
 
@@ -250,12 +247,10 @@ void dm_cell_visit_release(struct dm_bio_prison *prison,
 			   void *context,
 			   struct dm_bio_prison_cell *cell)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	visit_fn(context, cell);
 	rb_erase(&cell->node, &prison->cells);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 }
 EXPORT_SYMBOL_GPL(dm_cell_visit_release);
 
@@ -275,11 +270,10 @@ int dm_cell_promote_or_release(struct dm_bio_prison *prison,
 			       struct dm_bio_prison_cell *cell)
 {
 	int r;
-	unsigned long flags;
 
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	r = __promote_or_release(prison, cell);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 
 	return r;
 }
@@ -379,10 +373,9 @@ EXPORT_SYMBOL_GPL(dm_deferred_entry_dec);
 int dm_deferred_set_add_work(struct dm_deferred_set *ds, struct list_head *work)
 {
 	int r = 1;
-	unsigned long flags;
 	unsigned next_entry;
 
-	spin_lock_irqsave(&ds->lock, flags);
+	spin_lock_irq(&ds->lock);
 	if ((ds->sweeper == ds->current_entry) &&
 	    !ds->entries[ds->current_entry].count)
 		r = 0;
@@ -392,7 +385,7 @@ int dm_deferred_set_add_work(struct dm_deferred_set *ds, struct list_head *work)
 		if (!ds->entries[next_entry].count)
 			ds->current_entry = next_entry;
 	}
-	spin_unlock_irqrestore(&ds->lock, flags);
+	spin_unlock_irq(&ds->lock);
 
 	return r;
 }
diff --git a/drivers/md/dm-bio-prison-v2.c b/drivers/md/dm-bio-prison-v2.c
index b092cdc8e1ae..8ee019eda32d 100644
--- a/drivers/md/dm-bio-prison-v2.c
+++ b/drivers/md/dm-bio-prison-v2.c
@@ -177,11 +177,10 @@ bool dm_cell_get_v2(struct dm_bio_prison_v2 *prison,
 		    struct dm_bio_prison_cell_v2 **cell_result)
 {
 	int r;
-	unsigned long flags;
 
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	r = __get(prison, key, lock_level, inmate, cell_prealloc, cell_result);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 
 	return r;
 }
@@ -261,11 +260,10 @@ int dm_cell_lock_v2(struct dm_bio_prison_v2 *prison,
 		    struct dm_bio_prison_cell_v2 **cell_result)
 {
 	int r;
-	unsigned long flags;
 
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	r = __lock(prison, key, lock_level, cell_prealloc, cell_result);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 
 	return r;
 }
@@ -285,11 +283,9 @@ void dm_cell_quiesce_v2(struct dm_bio_prison_v2 *prison,
 			struct dm_bio_prison_cell_v2 *cell,
 			struct work_struct *continuation)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	__quiesce(prison, cell, continuation);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 }
 EXPORT_SYMBOL_GPL(dm_cell_quiesce_v2);
 
@@ -309,11 +305,10 @@ int dm_cell_lock_promote_v2(struct dm_bio_prison_v2 *prison,
 			    unsigned new_lock_level)
 {
 	int r;
-	unsigned long flags;
 
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	r = __promote(prison, cell, new_lock_level);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 
 	return r;
 }
@@ -342,11 +337,10 @@ bool dm_cell_unlock_v2(struct dm_bio_prison_v2 *prison,
 		       struct bio_list *bios)
 {
 	bool r;
-	unsigned long flags;
 
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	r = __unlock(prison, cell, bios);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 
 	return r;
 }
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 8346e6d1816c..2d32821b3a5b 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -74,22 +74,19 @@ static bool __iot_idle_for(struct io_tracker *iot, unsigned long jifs)
 static bool iot_idle_for(struct io_tracker *iot, unsigned long jifs)
 {
 	bool r;
-	unsigned long flags;
 
-	spin_lock_irqsave(&iot->lock, flags);
+	spin_lock_irq(&iot->lock);
 	r = __iot_idle_for(iot, jifs);
-	spin_unlock_irqrestore(&iot->lock, flags);
+	spin_unlock_irq(&iot->lock);
 
 	return r;
 }
 
 static void iot_io_begin(struct io_tracker *iot, sector_t len)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&iot->lock, flags);
+	spin_lock_irq(&iot->lock);
 	iot->in_flight += len;
-	spin_unlock_irqrestore(&iot->lock, flags);
+	spin_unlock_irq(&iot->lock);
 }
 
 static void __iot_io_end(struct io_tracker *iot, sector_t len)
@@ -172,7 +169,6 @@ static void __commit(struct work_struct *_ws)
 {
 	struct batcher *b = container_of(_ws, struct batcher, commit_work);
 	blk_status_t r;
-	unsigned long flags;
 	struct list_head work_items;
 	struct work_struct *ws, *tmp;
 	struct continuation *k;
@@ -186,12 +182,12 @@ static void __commit(struct work_struct *_ws)
 	 * We have to grab these before the commit_op to avoid a race
 	 * condition.
 	 */
-	spin_lock_irqsave(&b->lock, flags);
+	spin_lock_irq(&b->lock);
 	list_splice_init(&b->work_items, &work_items);
 	bio_list_merge(&bios, &b->bios);
 	bio_list_init(&b->bios);
 	b->commit_scheduled = false;
-	spin_unlock_irqrestore(&b->lock, flags);
+	spin_unlock_irq(&b->lock);
 
 	r = b->commit_op(b->commit_context);
 
@@ -238,13 +234,12 @@ static void async_commit(struct batcher *b)
 
 static void continue_after_commit(struct batcher *b, struct continuation *k)
 {
-	unsigned long flags;
 	bool commit_scheduled;
 
-	spin_lock_irqsave(&b->lock, flags);
+	spin_lock_irq(&b->lock);
 	commit_scheduled = b->commit_scheduled;
 	list_add_tail(&k->ws.entry, &b->work_items);
-	spin_unlock_irqrestore(&b->lock, flags);
+	spin_unlock_irq(&b->lock);
 
 	if (commit_scheduled)
 		async_commit(b);
@@ -255,13 +250,12 @@ static void continue_after_commit(struct batcher *b, struct continuation *k)
  */
 static void issue_after_commit(struct batcher *b, struct bio *bio)
 {
-       unsigned long flags;
        bool commit_scheduled;
 
-       spin_lock_irqsave(&b->lock, flags);
+       spin_lock_irq(&b->lock);
        commit_scheduled = b->commit_scheduled;
        bio_list_add(&b->bios, bio);
-       spin_unlock_irqrestore(&b->lock, flags);
+       spin_unlock_irq(&b->lock);
 
        if (commit_scheduled)
 	       async_commit(b);
@@ -273,12 +267,11 @@ static void issue_after_commit(struct batcher *b, struct bio *bio)
 static void schedule_commit(struct batcher *b)
 {
 	bool immediate;
-	unsigned long flags;
 
-	spin_lock_irqsave(&b->lock, flags);
+	spin_lock_irq(&b->lock);
 	immediate = !list_empty(&b->work_items) || !bio_list_empty(&b->bios);
 	b->commit_scheduled = true;
-	spin_unlock_irqrestore(&b->lock, flags);
+	spin_unlock_irq(&b->lock);
 
 	if (immediate)
 		async_commit(b);
@@ -630,23 +623,19 @@ static struct per_bio_data *init_per_bio_data(struct bio *bio)
 
 static void defer_bio(struct cache *cache, struct bio *bio)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	bio_list_add(&cache->deferred_bios, bio);
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 
 	wake_deferred_bio_worker(cache);
 }
 
 static void defer_bios(struct cache *cache, struct bio_list *bios)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	bio_list_merge(&cache->deferred_bios, bios);
 	bio_list_init(bios);
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 
 	wake_deferred_bio_worker(cache);
 }
@@ -756,33 +745,27 @@ static dm_dblock_t oblock_to_dblock(struct cache *cache, dm_oblock_t oblock)
 
 static void set_discard(struct cache *cache, dm_dblock_t b)
 {
-	unsigned long flags;
-
 	BUG_ON(from_dblock(b) >= from_dblock(cache->discard_nr_blocks));
 	atomic_inc(&cache->stats.discard_count);
 
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	set_bit(from_dblock(b), cache->discard_bitset);
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 }
 
 static void clear_discard(struct cache *cache, dm_dblock_t b)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	clear_bit(from_dblock(b), cache->discard_bitset);
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 }
 
 static bool is_discarded(struct cache *cache, dm_dblock_t b)
 {
 	int r;
-	unsigned long flags;
-
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	r = test_bit(from_dblock(b), cache->discard_bitset);
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 
 	return r;
 }
@@ -790,12 +773,10 @@ static bool is_discarded(struct cache *cache, dm_dblock_t b)
 static bool is_discarded_oblock(struct cache *cache, dm_oblock_t b)
 {
 	int r;
-	unsigned long flags;
-
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	r = test_bit(from_dblock(oblock_to_dblock(cache, b)),
 		     cache->discard_bitset);
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 
 	return r;
 }
@@ -827,17 +808,16 @@ static void remap_to_cache(struct cache *cache, struct bio *bio,
 
 static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio)
 {
-	unsigned long flags;
 	struct per_bio_data *pb;
 
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	if (cache->need_tick_bio && !op_is_flush(bio->bi_opf) &&
 	    bio_op(bio) != REQ_OP_DISCARD) {
 		pb = get_per_bio_data(bio);
 		pb->tick = true;
 		cache->need_tick_bio = false;
 	}
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 }
 
 static void __remap_to_origin_clear_discard(struct cache *cache, struct bio *bio,
@@ -1889,17 +1869,16 @@ static void process_deferred_bios(struct work_struct *ws)
 {
 	struct cache *cache = container_of(ws, struct cache, deferred_bio_worker);
 
-	unsigned long flags;
 	bool commit_needed = false;
 	struct bio_list bios;
 	struct bio *bio;
 
 	bio_list_init(&bios);
 
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	bio_list_merge(&bios, &cache->deferred_bios);
 	bio_list_init(&cache->deferred_bios);
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 
 	while ((bio = bio_list_pop(&bios))) {
 		if (bio->bi_opf & REQ_PREFLUSH)
diff --git a/drivers/md/dm-clone-metadata.c b/drivers/md/dm-clone-metadata.c
index 6bc8c1d1c351..08c552e5e41b 100644
--- a/drivers/md/dm-clone-metadata.c
+++ b/drivers/md/dm-clone-metadata.c
@@ -712,7 +712,7 @@ static int __metadata_commit(struct dm_clone_metadata *cmd)
 static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap)
 {
 	int r;
-	unsigned long word, flags;
+	unsigned long word;
 
 	word = 0;
 	do {
@@ -736,9 +736,9 @@ static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap)
 		return r;
 
 	/* Update the changed flag */
-	spin_lock_irqsave(&cmd->bitmap_lock, flags);
+	spin_lock_irq(&cmd->bitmap_lock);
 	dmap->changed = 0;
-	spin_unlock_irqrestore(&cmd->bitmap_lock, flags);
+	spin_unlock_irq(&cmd->bitmap_lock);
 
 	return 0;
 }
@@ -746,7 +746,6 @@ static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap)
 int dm_clone_metadata_commit(struct dm_clone_metadata *cmd)
 {
 	int r = -EPERM;
-	unsigned long flags;
 	struct dirty_map *dmap, *next_dmap;
 
 	down_write(&cmd->lock);
@@ -770,9 +769,9 @@ int dm_clone_metadata_commit(struct dm_clone_metadata *cmd)
 	}
 
 	/* Swap dirty bitmaps */
-	spin_lock_irqsave(&cmd->bitmap_lock, flags);
+	spin_lock_irq(&cmd->bitmap_lock);
 	cmd->current_dmap = next_dmap;
-	spin_unlock_irqrestore(&cmd->bitmap_lock, flags);
+	spin_unlock_irq(&cmd->bitmap_lock);
 
 	/*
 	 * No one is accessing the old dirty bitmap anymore, so we can flush
@@ -817,9 +816,9 @@ int dm_clone_cond_set_range(struct dm_clone_metadata *cmd, unsigned long start,
 {
 	int r = 0;
 	struct dirty_map *dmap;
-	unsigned long word, region_nr, flags;
+	unsigned long word, region_nr;
 
-	spin_lock_irqsave(&cmd->bitmap_lock, flags);
+	spin_lock_irq(&cmd->bitmap_lock);
 
 	if (cmd->read_only) {
 		r = -EPERM;
@@ -836,7 +835,7 @@ int dm_clone_cond_set_range(struct dm_clone_metadata *cmd, unsigned long start,
 		}
 	}
 out:
-	spin_unlock_irqrestore(&cmd->bitmap_lock, flags);
+	spin_unlock_irq(&cmd->bitmap_lock);
 
 	return r;
 }
@@ -903,13 +902,11 @@ out:
 
 void dm_clone_metadata_set_read_only(struct dm_clone_metadata *cmd)
 {
-	unsigned long flags;
-
 	down_write(&cmd->lock);
 
-	spin_lock_irqsave(&cmd->bitmap_lock, flags);
+	spin_lock_irq(&cmd->bitmap_lock);
 	cmd->read_only = 1;
-	spin_unlock_irqrestore(&cmd->bitmap_lock, flags);
+	spin_unlock_irq(&cmd->bitmap_lock);
 
 	if (!cmd->fail_io)
 		dm_bm_set_read_only(cmd->bm);
@@ -919,13 +916,11 @@ void dm_clone_metadata_set_read_only(struct dm_clone_metadata *cmd)
 
 void dm_clone_metadata_set_read_write(struct dm_clone_metadata *cmd)
 {
-	unsigned long flags;
-
 	down_write(&cmd->lock);
 
-	spin_lock_irqsave(&cmd->bitmap_lock, flags);
+	spin_lock_irq(&cmd->bitmap_lock);
 	cmd->read_only = 0;
-	spin_unlock_irqrestore(&cmd->bitmap_lock, flags);
+	spin_unlock_irq(&cmd->bitmap_lock);
 
 	if (!cmd->fail_io)
 		dm_bm_set_read_write(cmd->bm);
diff --git a/drivers/md/dm-clone-metadata.h b/drivers/md/dm-clone-metadata.h
index 434bff08508b..3fe50a781c11 100644
--- a/drivers/md/dm-clone-metadata.h
+++ b/drivers/md/dm-clone-metadata.h
@@ -44,7 +44,9 @@ int dm_clone_set_region_hydrated(struct dm_clone_metadata *cmd, unsigned long re
  * @start: Starting region number
  * @nr_regions: Number of regions in the range
  *
- * This function doesn't block, so it's safe to call it from interrupt context.
+ * This function doesn't block, but since it uses spin_lock_irq()/spin_unlock_irq()
+ * it's NOT safe to call it from any context where interrupts are disabled, e.g.,
+ * from interrupt context.
  */
 int dm_clone_cond_set_range(struct dm_clone_metadata *cmd, unsigned long start,
 			    unsigned long nr_regions);
diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c
index 4ca8f1977222..b3d89072d21c 100644
--- a/drivers/md/dm-clone-target.c
+++ b/drivers/md/dm-clone-target.c
@@ -332,8 +332,6 @@ static void submit_bios(struct bio_list *bios)
  */
 static void issue_bio(struct clone *clone, struct bio *bio)
 {
-	unsigned long flags;
-
 	if (!bio_triggers_commit(clone, bio)) {
 		generic_make_request(bio);
 		return;
@@ -352,9 +350,9 @@ static void issue_bio(struct clone *clone, struct bio *bio)
 	 * Batch together any bios that trigger commits and then issue a single
 	 * commit for them in process_deferred_flush_bios().
 	 */
-	spin_lock_irqsave(&clone->lock, flags);
+	spin_lock_irq(&clone->lock);
 	bio_list_add(&clone->deferred_flush_bios, bio);
-	spin_unlock_irqrestore(&clone->lock, flags);
+	spin_unlock_irq(&clone->lock);
 
 	wake_worker(clone);
 }
@@ -469,7 +467,7 @@ static void complete_discard_bio(struct clone *clone, struct bio *bio, bool succ
 
 static void process_discard_bio(struct clone *clone, struct bio *bio)
 {
-	unsigned long rs, re, flags;
+	unsigned long rs, re;
 
 	bio_region_range(clone, bio, &rs, &re);
 	BUG_ON(re > clone->nr_regions);
@@ -501,9 +499,9 @@ static void process_discard_bio(struct clone *clone, struct bio *bio)
 	/*
 	 * Defer discard processing.
 	 */
-	spin_lock_irqsave(&clone->lock, flags);
+	spin_lock_irq(&clone->lock);
 	bio_list_add(&clone->deferred_discard_bios, bio);
-	spin_unlock_irqrestore(&clone->lock, flags);
+	spin_unlock_irq(&clone->lock);
 
 	wake_worker(clone);
 }
@@ -554,6 +552,12 @@ struct hash_table_bucket {
 #define bucket_unlock_irqrestore(bucket, flags) \
 	spin_unlock_irqrestore(&(bucket)->lock, flags)
 
+#define bucket_lock_irq(bucket) \
+	spin_lock_irq(&(bucket)->lock)
+
+#define bucket_unlock_irq(bucket) \
+	spin_unlock_irq(&(bucket)->lock)
+
 static int hash_table_init(struct clone *clone)
 {
 	unsigned int i, sz;
@@ -851,7 +855,6 @@ static void hydration_overwrite(struct dm_clone_region_hydration *hd, struct bio
  */
 static void hydrate_bio_region(struct clone *clone, struct bio *bio)
 {
-	unsigned long flags;
 	unsigned long region_nr;
 	struct hash_table_bucket *bucket;
 	struct dm_clone_region_hydration *hd, *hd2;
@@ -859,19 +862,19 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio)
 	region_nr = bio_to_region(clone, bio);
 	bucket = get_hash_table_bucket(clone, region_nr);
 
-	bucket_lock_irqsave(bucket, flags);
+	bucket_lock_irq(bucket);
 
 	hd = __hash_find(bucket, region_nr);
 	if (hd) {
 		/* Someone else is hydrating the region */
 		bio_list_add(&hd->deferred_bios, bio);
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 		return;
 	}
 
 	if (dm_clone_is_region_hydrated(clone->cmd, region_nr)) {
 		/* The region has been hydrated */
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 		issue_bio(clone, bio);
 		return;
 	}
@@ -880,16 +883,16 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio)
 	 * We must allocate a hydration descriptor and start the hydration of
 	 * the corresponding region.
 	 */
-	bucket_unlock_irqrestore(bucket, flags);
+	bucket_unlock_irq(bucket);
 
 	hd = alloc_hydration(clone);
 	hydration_init(hd, region_nr);
 
-	bucket_lock_irqsave(bucket, flags);
+	bucket_lock_irq(bucket);
 
 	/* Check if the region has been hydrated in the meantime. */
 	if (dm_clone_is_region_hydrated(clone->cmd, region_nr)) {
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 		free_hydration(hd);
 		issue_bio(clone, bio);
 		return;
@@ -899,7 +902,7 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio)
 	if (hd2 != hd) {
 		/* Someone else started the region's hydration. */
 		bio_list_add(&hd2->deferred_bios, bio);
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 		free_hydration(hd);
 		return;
 	}
@@ -911,7 +914,7 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio)
 	 */
 	if (unlikely(get_clone_mode(clone) >= CM_READ_ONLY)) {
 		hlist_del(&hd->h);
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 		free_hydration(hd);
 		bio_io_error(bio);
 		return;
@@ -925,11 +928,11 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio)
 	 * to the destination device.
 	 */
 	if (is_overwrite_bio(clone, bio)) {
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 		hydration_overwrite(hd, bio);
 	} else {
 		bio_list_add(&hd->deferred_bios, bio);
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 		hydration_copy(hd, 1);
 	}
 }
@@ -996,7 +999,6 @@ static unsigned long __start_next_hydration(struct clone *clone,
 					    unsigned long offset,
 					    struct batch_info *batch)
 {
-	unsigned long flags;
 	struct hash_table_bucket *bucket;
 	struct dm_clone_region_hydration *hd;
 	unsigned long nr_regions = clone->nr_regions;
@@ -1010,13 +1012,13 @@ static unsigned long __start_next_hydration(struct clone *clone,
 			break;
 
 		bucket = get_hash_table_bucket(clone, offset);
-		bucket_lock_irqsave(bucket, flags);
+		bucket_lock_irq(bucket);
 
 		if (!dm_clone_is_region_hydrated(clone->cmd, offset) &&
 		    !__hash_find(bucket, offset)) {
 			hydration_init(hd, offset);
 			__insert_region_hydration(bucket, hd);
-			bucket_unlock_irqrestore(bucket, flags);
+			bucket_unlock_irq(bucket);
 
 			/* Batch hydration */
 			__batch_hydration(batch, hd);
@@ -1024,7 +1026,7 @@ static unsigned long __start_next_hydration(struct clone *clone,
 			return (offset + 1);
 		}
 
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 
 	} while (++offset < nr_regions);
 
@@ -1140,13 +1142,13 @@ static void process_deferred_discards(struct clone *clone)
 	int r = -EPERM;
 	struct bio *bio;
 	struct blk_plug plug;
-	unsigned long rs, re, flags;
+	unsigned long rs, re;
 	struct bio_list discards = BIO_EMPTY_LIST;
 
-	spin_lock_irqsave(&clone->lock, flags);
+	spin_lock_irq(&clone->lock);
 	bio_list_merge(&discards, &clone->deferred_discard_bios);
 	bio_list_init(&clone->deferred_discard_bios);
-	spin_unlock_irqrestore(&clone->lock, flags);
+	spin_unlock_irq(&clone->lock);
 
 	if (bio_list_empty(&discards))
 		return;
@@ -1176,13 +1178,12 @@ out:
 
 static void process_deferred_bios(struct clone *clone)
 {
-	unsigned long flags;
 	struct bio_list bios = BIO_EMPTY_LIST;
 
-	spin_lock_irqsave(&clone->lock, flags);
+	spin_lock_irq(&clone->lock);
 	bio_list_merge(&bios, &clone->deferred_bios);
 	bio_list_init(&clone->deferred_bios);
-	spin_unlock_irqrestore(&clone->lock, flags);
+	spin_unlock_irq(&clone->lock);
 
 	if (bio_list_empty(&bios))
 		return;
@@ -1193,7 +1194,6 @@ static void process_deferred_bios(struct clone *clone)
 static void process_deferred_flush_bios(struct clone *clone)
 {
 	struct bio *bio;
-	unsigned long flags;
 	struct bio_list bios = BIO_EMPTY_LIST;
 	struct bio_list bio_completions = BIO_EMPTY_LIST;
 
@@ -1201,13 +1201,13 @@ static void process_deferred_flush_bios(struct clone *clone)
 	 * If there are any deferred flush bios, we must commit the metadata
 	 * before issuing them or signaling their completion.
 	 */
-	spin_lock_irqsave(&clone->lock, flags);
+	spin_lock_irq(&clone->lock);
 	bio_list_merge(&bios, &clone->deferred_flush_bios);
 	bio_list_init(&clone->deferred_flush_bios);
 
 	bio_list_merge(&bio_completions, &clone->deferred_flush_completions);
 	bio_list_init(&clone->deferred_flush_completions);
-	spin_unlock_irqrestore(&clone->lock, flags);
+	spin_unlock_irq(&clone->lock);
 
 	if (bio_list_empty(&bios) && bio_list_empty(&bio_completions) &&
 	    !(dm_clone_changed_this_transaction(clone->cmd) && need_commit_due_to_time(clone)))
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index f87f6495652f..eb9782fc93fe 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -2700,21 +2700,18 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 
 	ret = -ENOMEM;
-	cc->io_queue = alloc_workqueue("kcryptd_io/%s",
-				       WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM,
-				       1, devname);
+	cc->io_queue = alloc_workqueue("kcryptd_io/%s", WQ_MEM_RECLAIM, 1, devname);
 	if (!cc->io_queue) {
 		ti->error = "Couldn't create kcryptd io queue";
 		goto bad;
 	}
 
 	if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags))
-		cc->crypt_queue = alloc_workqueue("kcryptd/%s",
-						  WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM,
+		cc->crypt_queue = alloc_workqueue("kcryptd/%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM,
 						  1, devname);
 	else
 		cc->crypt_queue = alloc_workqueue("kcryptd/%s",
-						  WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND,
+						  WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND,
 						  num_online_cpus(), devname);
 	if (!cc->crypt_queue) {
 		ti->error = "Couldn't create kcryptd queue";
diff --git a/drivers/md/dm-dust.c b/drivers/md/dm-dust.c
index 8288887b7f94..eb37584427a4 100644
--- a/drivers/md/dm-dust.c
+++ b/drivers/md/dm-dust.c
@@ -17,6 +17,7 @@
 struct badblock {
 	struct rb_node node;
 	sector_t bb;
+	unsigned char wr_fail_cnt;
 };
 
 struct dust_device {
@@ -101,7 +102,8 @@ static int dust_remove_block(struct dust_device *dd, unsigned long long block)
 	return 0;
 }
 
-static int dust_add_block(struct dust_device *dd, unsigned long long block)
+static int dust_add_block(struct dust_device *dd, unsigned long long block,
+			  unsigned char wr_fail_cnt)
 {
 	struct badblock *bblock;
 	unsigned long flags;
@@ -115,6 +117,7 @@ static int dust_add_block(struct dust_device *dd, unsigned long long block)
 
 	spin_lock_irqsave(&dd->dust_lock, flags);
 	bblock->bb = block;
+	bblock->wr_fail_cnt = wr_fail_cnt;
 	if (!dust_rb_insert(&dd->badblocklist, bblock)) {
 		if (!dd->quiet_mode) {
 			DMERR("%s: block %llu already in badblocklist",
@@ -126,8 +129,10 @@ static int dust_add_block(struct dust_device *dd, unsigned long long block)
 	}
 
 	dd->badblock_count++;
-	if (!dd->quiet_mode)
-		DMINFO("%s: badblock added at block %llu", __func__, block);
+	if (!dd->quiet_mode) {
+		DMINFO("%s: badblock added at block %llu with write fail count %hhu",
+		       __func__, block, wr_fail_cnt);
+	}
 	spin_unlock_irqrestore(&dd->dust_lock, flags);
 
 	return 0;
@@ -163,22 +168,27 @@ static int dust_map_read(struct dust_device *dd, sector_t thisblock,
 			 bool fail_read_on_bb)
 {
 	unsigned long flags;
-	int ret = DM_MAPIO_REMAPPED;
+	int r = DM_MAPIO_REMAPPED;
 
 	if (fail_read_on_bb) {
 		thisblock >>= dd->sect_per_block_shift;
 		spin_lock_irqsave(&dd->dust_lock, flags);
-		ret = __dust_map_read(dd, thisblock);
+		r = __dust_map_read(dd, thisblock);
 		spin_unlock_irqrestore(&dd->dust_lock, flags);
 	}
 
-	return ret;
+	return r;
 }
 
-static void __dust_map_write(struct dust_device *dd, sector_t thisblock)
+static int __dust_map_write(struct dust_device *dd, sector_t thisblock)
 {
 	struct badblock *bblk = dust_rb_search(&dd->badblocklist, thisblock);
 
+	if (bblk && bblk->wr_fail_cnt > 0) {
+		bblk->wr_fail_cnt--;
+		return DM_MAPIO_KILL;
+	}
+
 	if (bblk) {
 		rb_erase(&bblk->node, &dd->badblocklist);
 		dd->badblock_count--;
@@ -189,37 +199,40 @@ static void __dust_map_write(struct dust_device *dd, sector_t thisblock)
 			       (unsigned long long)thisblock);
 		}
 	}
+
+	return DM_MAPIO_REMAPPED;
 }
 
 static int dust_map_write(struct dust_device *dd, sector_t thisblock,
 			  bool fail_read_on_bb)
 {
 	unsigned long flags;
+	int ret = DM_MAPIO_REMAPPED;
 
 	if (fail_read_on_bb) {
 		thisblock >>= dd->sect_per_block_shift;
 		spin_lock_irqsave(&dd->dust_lock, flags);
-		__dust_map_write(dd, thisblock);
+		ret = __dust_map_write(dd, thisblock);
 		spin_unlock_irqrestore(&dd->dust_lock, flags);
 	}
 
-	return DM_MAPIO_REMAPPED;
+	return ret;
 }
 
 static int dust_map(struct dm_target *ti, struct bio *bio)
 {
 	struct dust_device *dd = ti->private;
-	int ret;
+	int r;
 
 	bio_set_dev(bio, dd->dev->bdev);
 	bio->bi_iter.bi_sector = dd->start + dm_target_offset(ti, bio->bi_iter.bi_sector);
 
 	if (bio_data_dir(bio) == READ)
-		ret = dust_map_read(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb);
+		r = dust_map_read(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb);
 	else
-		ret = dust_map_write(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb);
+		r = dust_map_write(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb);
 
-	return ret;
+	return r;
 }
 
 static bool __dust_clear_badblocks(struct rb_root *tree,
@@ -375,8 +388,10 @@ static int dust_message(struct dm_target *ti, unsigned int argc, char **argv,
 	struct dust_device *dd = ti->private;
 	sector_t size = i_size_read(dd->dev->bdev->bd_inode) >> SECTOR_SHIFT;
 	bool invalid_msg = false;
-	int result = -EINVAL;
+	int r = -EINVAL;
 	unsigned long long tmp, block;
+	unsigned char wr_fail_cnt;
+	unsigned int tmp_ui;
 	unsigned long flags;
 	char dummy;
 
@@ -388,45 +403,69 @@ static int dust_message(struct dm_target *ti, unsigned int argc, char **argv,
 		} else if (!strcasecmp(argv[0], "disable")) {
 			DMINFO("disabling read failures on bad sectors");
 			dd->fail_read_on_bb = false;
-			result = 0;
+			r = 0;
 		} else if (!strcasecmp(argv[0], "enable")) {
 			DMINFO("enabling read failures on bad sectors");
 			dd->fail_read_on_bb = true;
-			result = 0;
+			r = 0;
 		} else if (!strcasecmp(argv[0], "countbadblocks")) {
 			spin_lock_irqsave(&dd->dust_lock, flags);
 			DMINFO("countbadblocks: %llu badblock(s) found",
 			       dd->badblock_count);
 			spin_unlock_irqrestore(&dd->dust_lock, flags);
-			result = 0;
+			r = 0;
 		} else if (!strcasecmp(argv[0], "clearbadblocks")) {
-			result = dust_clear_badblocks(dd);
+			r = dust_clear_badblocks(dd);
 		} else if (!strcasecmp(argv[0], "quiet")) {
 			if (!dd->quiet_mode)
 				dd->quiet_mode = true;
 			else
 				dd->quiet_mode = false;
-			result = 0;
+			r = 0;
 		} else {
 			invalid_msg = true;
 		}
 	} else if (argc == 2) {
 		if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1)
-			return result;
+			return r;
 
 		block = tmp;
 		sector_div(size, dd->sect_per_block);
 		if (block > size) {
 			DMERR("selected block value out of range");
-			return result;
+			return r;
 		}
 
 		if (!strcasecmp(argv[0], "addbadblock"))
-			result = dust_add_block(dd, block);
+			r = dust_add_block(dd, block, 0);
 		else if (!strcasecmp(argv[0], "removebadblock"))
-			result = dust_remove_block(dd, block);
+			r = dust_remove_block(dd, block);
 		else if (!strcasecmp(argv[0], "queryblock"))
-			result = dust_query_block(dd, block);
+			r = dust_query_block(dd, block);
+		else
+			invalid_msg = true;
+
+	} else if (argc == 3) {
+		if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1)
+			return r;
+
+		if (sscanf(argv[2], "%u%c", &tmp_ui, &dummy) != 1)
+			return r;
+
+		block = tmp;
+		if (tmp_ui > 255) {
+			DMERR("selected write fail count out of range");
+			return r;
+		}
+		wr_fail_cnt = tmp_ui;
+		sector_div(size, dd->sect_per_block);
+		if (block > size) {
+			DMERR("selected block value out of range");
+			return r;
+		}
+
+		if (!strcasecmp(argv[0], "addbadblock"))
+			r = dust_add_block(dd, block, wr_fail_cnt);
 		else
 			invalid_msg = true;
 
@@ -436,7 +475,7 @@ static int dust_message(struct dm_target *ti, unsigned int argc, char **argv,
 	if (invalid_msg)
 		DMERR("unrecognized message '%s' received", argv[0]);
 
-	return result;
+	return r;
 }
 
 static void dust_status(struct dm_target *ti, status_type_t type,
@@ -499,12 +538,12 @@ static struct target_type dust_target = {
 
 static int __init dm_dust_init(void)
 {
-	int result = dm_register_target(&dust_target);
+	int r = dm_register_target(&dust_target);
 
-	if (result < 0)
-		DMERR("dm_register_target failed %d", result);
+	if (r < 0)
+		DMERR("dm_register_target failed %d", r);
 
-	return result;
+	return r;
 }
 
 static void __exit dm_dust_exit(void)
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 2900fbde89b3..a2cc9e45cbba 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -280,7 +280,7 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio)
 	struct flakey_c *fc = ti->private;
 
 	bio_set_dev(bio, fc->dev->bdev);
-	if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET)
+	if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio)))
 		bio->bi_iter.bi_sector =
 			flakey_map_sector(ti, bio->bi_iter.bi_sector);
 }
@@ -322,8 +322,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
 	pb->bio_submitted = false;
 
-	/* Do not fail reset zone */
-	if (bio_op(bio) == REQ_OP_ZONE_RESET)
+	if (op_is_zone_mgmt(bio_op(bio)))
 		goto map_bio;
 
 	/* Are we alive ? */
@@ -384,7 +383,7 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio,
 	struct flakey_c *fc = ti->private;
 	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
 
-	if (bio_op(bio) == REQ_OP_ZONE_RESET)
+	if (op_is_zone_mgmt(bio_op(bio)))
 		return DM_ENDIO_DONE;
 
 	if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
@@ -460,21 +459,15 @@ static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
-static int flakey_report_zones(struct dm_target *ti, sector_t sector,
-			       struct blk_zone *zones, unsigned int *nr_zones)
+static int flakey_report_zones(struct dm_target *ti,
+		struct dm_report_zones_args *args, unsigned int nr_zones)
 {
 	struct flakey_c *fc = ti->private;
-	int ret;
+	sector_t sector = flakey_map_sector(ti, args->next_sector);
 
-	/* Do report and remap it */
-	ret = blkdev_report_zones(fc->dev->bdev, flakey_map_sector(ti, sector),
-				  zones, nr_zones);
-	if (ret != 0)
-		return ret;
-
-	if (*nr_zones)
-		dm_remap_zone_report(ti, fc->start, zones, nr_zones);
-	return 0;
+	args->start = fc->start;
+	return blkdev_report_zones(fc->dev->bdev, sector, nr_zones,
+				   dm_report_zones_cb, args);
 }
 #endif
 
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index dab4446fe7d8..b225b3e445fa 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -53,6 +53,7 @@
 #define SB_VERSION_1			1
 #define SB_VERSION_2			2
 #define SB_VERSION_3			3
+#define SB_VERSION_4			4
 #define SB_SECTORS			8
 #define MAX_SECTORS_PER_BLOCK		8
 
@@ -73,6 +74,7 @@ struct superblock {
 #define SB_FLAG_HAVE_JOURNAL_MAC	0x1
 #define SB_FLAG_RECALCULATING		0x2
 #define SB_FLAG_DIRTY_BITMAP		0x4
+#define SB_FLAG_FIXED_PADDING		0x8
 
 #define	JOURNAL_ENTRY_ROUNDUP		8
 
@@ -250,6 +252,7 @@ struct dm_integrity_c {
 	bool journal_uptodate;
 	bool just_formatted;
 	bool recalculate_flag;
+	bool fix_padding;
 
 	struct alg_spec internal_hash_alg;
 	struct alg_spec journal_crypt_alg;
@@ -463,7 +466,9 @@ static void wraparound_section(struct dm_integrity_c *ic, unsigned *sec_ptr)
 
 static void sb_set_version(struct dm_integrity_c *ic)
 {
-	if (ic->mode == 'B' || ic->sb->flags & cpu_to_le32(SB_FLAG_DIRTY_BITMAP))
+	if (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING))
+		ic->sb->version = SB_VERSION_4;
+	else if (ic->mode == 'B' || ic->sb->flags & cpu_to_le32(SB_FLAG_DIRTY_BITMAP))
 		ic->sb->version = SB_VERSION_3;
 	else if (ic->meta_dev || ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING))
 		ic->sb->version = SB_VERSION_2;
@@ -2955,6 +2960,7 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 		arg_count += !!ic->internal_hash_alg.alg_string;
 		arg_count += !!ic->journal_crypt_alg.alg_string;
 		arg_count += !!ic->journal_mac_alg.alg_string;
+		arg_count += (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0;
 		DMEMIT("%s %llu %u %c %u", ic->dev->name, (unsigned long long)ic->start,
 		       ic->tag_size, ic->mode, arg_count);
 		if (ic->meta_dev)
@@ -2974,6 +2980,8 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 			DMEMIT(" sectors_per_bit:%llu", (unsigned long long)ic->sectors_per_block << ic->log2_blocks_per_bitmap_bit);
 			DMEMIT(" bitmap_flush_interval:%u", jiffies_to_msecs(ic->bitmap_flush_interval));
 		}
+		if ((ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0)
+			DMEMIT(" fix_padding");
 
 #define EMIT_ALG(a, n)							\
 		do {							\
@@ -3042,8 +3050,14 @@ static int calculate_device_limits(struct dm_integrity_c *ic)
 	if (!ic->meta_dev) {
 		sector_t last_sector, last_area, last_offset;
 
-		ic->metadata_run = roundup((__u64)ic->tag_size << (ic->sb->log2_interleave_sectors - ic->sb->log2_sectors_per_block),
-					   (__u64)(1 << SECTOR_SHIFT << METADATA_PADDING_SECTORS)) >> SECTOR_SHIFT;
+		/* we have to maintain excessive padding for compatibility with existing volumes */
+		__u64 metadata_run_padding =
+			ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING) ?
+			(__u64)(METADATA_PADDING_SECTORS << SECTOR_SHIFT) :
+			(__u64)(1 << SECTOR_SHIFT << METADATA_PADDING_SECTORS);
+
+		ic->metadata_run = round_up((__u64)ic->tag_size << (ic->sb->log2_interleave_sectors - ic->sb->log2_sectors_per_block),
+					    metadata_run_padding) >> SECTOR_SHIFT;
 		if (!(ic->metadata_run & (ic->metadata_run - 1)))
 			ic->log2_metadata_run = __ffs(ic->metadata_run);
 		else
@@ -3086,6 +3100,8 @@ static int initialize_superblock(struct dm_integrity_c *ic, unsigned journal_sec
 		journal_sections = 1;
 
 	if (!ic->meta_dev) {
+		if (ic->fix_padding)
+			ic->sb->flags |= cpu_to_le32(SB_FLAG_FIXED_PADDING);
 		ic->sb->journal_sections = cpu_to_le32(journal_sections);
 		if (!interleave_sectors)
 			interleave_sectors = DEFAULT_INTERLEAVE_SECTORS;
@@ -3725,6 +3741,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 				goto bad;
 		} else if (!strcmp(opt_string, "recalculate")) {
 			ic->recalculate_flag = true;
+		} else if (!strcmp(opt_string, "fix_padding")) {
+			ic->fix_padding = true;
 		} else {
 			r = -EINVAL;
 			ti->error = "Invalid argument";
@@ -3867,7 +3885,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 			should_write_sb = true;
 	}
 
-	if (!ic->sb->version || ic->sb->version > SB_VERSION_3) {
+	if (!ic->sb->version || ic->sb->version > SB_VERSION_4) {
 		r = -EINVAL;
 		ti->error = "Unknown version";
 		goto bad;
@@ -4182,7 +4200,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
 
 static struct target_type integrity_target = {
 	.name			= "integrity",
-	.version		= {1, 3, 0},
+	.version		= {1, 4, 0},
 	.module			= THIS_MODULE,
 	.features		= DM_TARGET_SINGLETON | DM_TARGET_INTEGRITY,
 	.ctr			= dm_integrity_ctr,
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index ecefe6703736..8d07fdf63a47 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -90,7 +90,7 @@ static void linear_map_bio(struct dm_target *ti, struct bio *bio)
 	struct linear_c *lc = ti->private;
 
 	bio_set_dev(bio, lc->dev->bdev);
-	if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET)
+	if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio)))
 		bio->bi_iter.bi_sector =
 			linear_map_sector(ti, bio->bi_iter.bi_sector);
 }
@@ -136,21 +136,15 @@ static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
-static int linear_report_zones(struct dm_target *ti, sector_t sector,
-			       struct blk_zone *zones, unsigned int *nr_zones)
+static int linear_report_zones(struct dm_target *ti,
+		struct dm_report_zones_args *args, unsigned int nr_zones)
 {
-	struct linear_c *lc = (struct linear_c *) ti->private;
-	int ret;
-
-	/* Do report and remap it */
-	ret = blkdev_report_zones(lc->dev->bdev, linear_map_sector(ti, sector),
-				  zones, nr_zones);
-	if (ret != 0)
-		return ret;
+	struct linear_c *lc = ti->private;
+	sector_t sector = linear_map_sector(ti, args->next_sector);
 
-	if (*nr_zones)
-		dm_remap_zone_report(ti, lc->start, zones, nr_zones);
-	return 0;
+	args->start = lc->start;
+	return blkdev_report_zones(lc->dev->bdev, sector, nr_zones,
+				   dm_report_zones_cb, args);
 }
 #endif
 
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index b0aa595e4375..c412eaa975fc 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -209,6 +209,7 @@ struct raid_dev {
 #define RT_FLAG_RS_SUSPENDED		5
 #define RT_FLAG_RS_IN_SYNC		6
 #define RT_FLAG_RS_RESYNCING		7
+#define RT_FLAG_RS_GROW			8
 
 /* Array elements of 64 bit needed for rebuild/failed disk bits */
 #define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8)
@@ -241,6 +242,9 @@ struct raid_set {
 	struct raid_type *raid_type;
 	struct dm_target_callbacks callbacks;
 
+	sector_t array_sectors;
+	sector_t dev_sectors;
+
 	/* Optional raid4/5/6 journal device */
 	struct journal_dev {
 		struct dm_dev *dev;
@@ -616,7 +620,6 @@ static int raid10_format_to_md_layout(struct raid_set *rs,
 
 	} else if (algorithm == ALGORITHM_RAID10_FAR) {
 		f = copies;
-		r = !RAID10_OFFSET;
 		if (!test_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags))
 			r |= RAID10_USE_FAR_SETS;
 
@@ -1615,13 +1618,12 @@ static int _check_data_dev_sectors(struct raid_set *rs)
 }
 
 /* Calculate the sectors per device and per array used for @rs */
-static int rs_set_dev_and_array_sectors(struct raid_set *rs, bool use_mddev)
+static int rs_set_dev_and_array_sectors(struct raid_set *rs, sector_t sectors, bool use_mddev)
 {
 	int delta_disks;
 	unsigned int data_stripes;
+	sector_t array_sectors = sectors, dev_sectors = sectors;
 	struct mddev *mddev = &rs->md;
-	struct md_rdev *rdev;
-	sector_t array_sectors = rs->ti->len, dev_sectors = rs->ti->len;
 
 	if (use_mddev) {
 		delta_disks = mddev->delta_disks;
@@ -1656,12 +1658,9 @@ static int rs_set_dev_and_array_sectors(struct raid_set *rs, bool use_mddev)
 		/* Striped layouts */
 		array_sectors = (data_stripes + delta_disks) * dev_sectors;
 
-	rdev_for_each(rdev, mddev)
-		if (!test_bit(Journal, &rdev->flags))
-			rdev->sectors = dev_sectors;
-
 	mddev->array_sectors = array_sectors;
 	mddev->dev_sectors = dev_sectors;
+	rs_set_rdev_sectors(rs);
 
 	return _check_data_dev_sectors(rs);
 bad:
@@ -1670,7 +1669,7 @@ bad:
 }
 
 /* Setup recovery on @rs */
-static void __rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors)
+static void rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors)
 {
 	/* raid0 does not recover */
 	if (rs_is_raid0(rs))
@@ -1691,22 +1690,6 @@ static void __rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors)
 				     ? MaxSector : dev_sectors;
 }
 
-/* Setup recovery on @rs based on raid type, device size and 'nosync' flag */
-static void rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors)
-{
-	if (!dev_sectors)
-		/* New raid set or 'sync' flag provided */
-		__rs_setup_recovery(rs, 0);
-	else if (dev_sectors == MaxSector)
-		/* Prevent recovery */
-		__rs_setup_recovery(rs, MaxSector);
-	else if (__rdev_sectors(rs) < dev_sectors)
-		/* Grown raid set */
-		__rs_setup_recovery(rs, __rdev_sectors(rs));
-	else
-		__rs_setup_recovery(rs, MaxSector);
-}
-
 static void do_table_event(struct work_struct *ws)
 {
 	struct raid_set *rs = container_of(ws, struct raid_set, md.event_work);
@@ -2474,7 +2457,7 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev)
 		return -EINVAL;
 	}
 
-	/* Enable bitmap creation for RAID levels != 0 */
+	/* Enable bitmap creation on @rs unless no metadevs or raid0 or journaled raid4/5/6 set. */
 	mddev->bitmap_info.offset = (rt_is_raid0(rs->raid_type) || rs->journal_dev.dev) ? 0 : to_sector(4096);
 	mddev->bitmap_info.default_offset = mddev->bitmap_info.offset;
 
@@ -2911,7 +2894,7 @@ static int rs_setup_reshape(struct raid_set *rs)
 
 	/* Remove disk(s) */
 	} else if (rs->delta_disks < 0) {
-		r = rs_set_dev_and_array_sectors(rs, true);
+		r = rs_set_dev_and_array_sectors(rs, rs->ti->len, true);
 		mddev->reshape_backwards = 1; /* removing disk(s) -> backward reshape */
 
 	/* Change layout and/or chunk size */
@@ -3008,7 +2991,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	bool resize = false;
 	struct raid_type *rt;
 	unsigned int num_raid_params, num_raid_devs;
-	sector_t calculated_dev_sectors, rdev_sectors, reshape_sectors;
+	sector_t sb_array_sectors, rdev_sectors, reshape_sectors;
 	struct raid_set *rs = NULL;
 	const char *arg;
 	struct rs_layout rs_layout;
@@ -3067,11 +3050,13 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	 *
 	 * Any existing superblock will overwrite the array and device sizes
 	 */
-	r = rs_set_dev_and_array_sectors(rs, false);
+	r = rs_set_dev_and_array_sectors(rs, rs->ti->len, false);
 	if (r)
 		goto bad;
 
-	calculated_dev_sectors = rs->md.dev_sectors;
+	/* Memorize just calculated, potentially larger sizes to grow the raid set in preresume */
+	rs->array_sectors = rs->md.array_sectors;
+	rs->dev_sectors = rs->md.dev_sectors;
 
 	/*
 	 * Backup any new raid set level, layout, ...
@@ -3084,6 +3069,8 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	if (r)
 		goto bad;
 
+	/* All in-core metadata now as of current superblocks after calling analyse_superblocks() */
+	sb_array_sectors = rs->md.array_sectors;
 	rdev_sectors = __rdev_sectors(rs);
 	if (!rdev_sectors) {
 		ti->error = "Invalid rdev size";
@@ -3093,8 +3080,11 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 
 	reshape_sectors = _get_reshape_sectors(rs);
-	if (calculated_dev_sectors != rdev_sectors)
-		resize = calculated_dev_sectors != (reshape_sectors ? rdev_sectors - reshape_sectors : rdev_sectors);
+	if (rs->dev_sectors != rdev_sectors) {
+		resize = (rs->dev_sectors != rdev_sectors - reshape_sectors);
+		if (rs->dev_sectors > rdev_sectors - reshape_sectors)
+			set_bit(RT_FLAG_RS_GROW, &rs->runtime_flags);
+	}
 
 	INIT_WORK(&rs->md.event_work, do_table_event);
 	ti->private = rs;
@@ -3121,13 +3111,8 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
 		rs_set_new(rs);
 	} else if (rs_is_recovering(rs)) {
-		/* Rebuild particular devices */
-		if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) {
-			set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
-			rs_setup_recovery(rs, MaxSector);
-		}
 		/* A recovering raid set may be resized */
-		; /* skip setup rs */
+		goto size_check;
 	} else if (rs_is_reshaping(rs)) {
 		/* Have to reject size change request during reshape */
 		if (resize) {
@@ -3171,6 +3156,9 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		rs_setup_recovery(rs, MaxSector);
 		rs_set_new(rs);
 	} else if (rs_reshape_requested(rs)) {
+		/* Only request grow on raid set size extensions, not on reshapes. */
+		clear_bit(RT_FLAG_RS_GROW, &rs->runtime_flags);
+
 		/*
 		 * No need to check for 'ongoing' takeover here, because takeover
 		 * is an instant operation as oposed to an ongoing reshape.
@@ -3201,13 +3189,31 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		}
 		rs_set_cur(rs);
 	} else {
+size_check:
 		/* May not set recovery when a device rebuild is requested */
 		if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) {
-			rs_setup_recovery(rs, MaxSector);
+			clear_bit(RT_FLAG_RS_GROW, &rs->runtime_flags);
 			set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
-		} else
-			rs_setup_recovery(rs, test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags) ?
-					      0 : (resize ? calculated_dev_sectors : MaxSector));
+			rs_setup_recovery(rs, MaxSector);
+		} else if (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags)) {
+			/*
+			 * Set raid set to current size, i.e. size as of
+			 * superblocks to grow to larger size in preresume.
+			 */
+			r = rs_set_dev_and_array_sectors(rs, sb_array_sectors, false);
+			if (r)
+				goto bad;
+
+			rs_setup_recovery(rs, rs->md.recovery_cp < rs->md.dev_sectors ? rs->md.recovery_cp : rs->md.dev_sectors);
+		} else {
+			/* This is no size change or it is shrinking, update size and record in superblocks */
+			r = rs_set_dev_and_array_sectors(rs, rs->ti->len, false);
+			if (r)
+				goto bad;
+
+			if (sb_array_sectors > rs->array_sectors)
+				set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
+		}
 		rs_set_cur(rs);
 	}
 
@@ -3406,10 +3412,9 @@ static const char *__raid_dev_status(struct raid_set *rs, struct md_rdev *rdev)
 
 /* Helper to return resync/reshape progress for @rs and runtime flags for raid set in sync / resynching */
 static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
-				sector_t resync_max_sectors)
+				enum sync_state state, sector_t resync_max_sectors)
 {
 	sector_t r;
-	enum sync_state state;
 	struct mddev *mddev = &rs->md;
 
 	clear_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
@@ -3420,8 +3425,6 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
 		set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
 
 	} else {
-		state = decipher_sync_action(mddev, recovery);
-
 		if (state == st_idle && !test_bit(MD_RECOVERY_INTR, &recovery))
 			r = mddev->recovery_cp;
 		else
@@ -3439,18 +3442,14 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
 			/*
 			 * In case we are recovering, the array is not in sync
 			 * and health chars should show the recovering legs.
+			 *
+			 * Already retrieved recovery offset from curr_resync_completed above.
 			 */
 			;
-		else if (state == st_resync)
-			/*
-			 * If "resync" is occurring, the raid set
-			 * is or may be out of sync hence the health
-			 * characters shall be 'a'.
-			 */
-			set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags);
-		else if (state == st_reshape)
+
+		else if (state == st_resync || state == st_reshape)
 			/*
-			 * If "reshape" is occurring, the raid set
+			 * If "resync/reshape" is occurring, the raid set
 			 * is or may be out of sync hence the health
 			 * characters shall be 'a'.
 			 */
@@ -3464,22 +3463,22 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
 			 */
 			set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
 
-		else {
-			struct md_rdev *rdev;
-
+		else if (test_bit(MD_RECOVERY_NEEDED, &recovery))
 			/*
 			 * We are idle and recovery is needed, prevent 'A' chars race
 			 * caused by components still set to in-sync by constructor.
 			 */
-			if (test_bit(MD_RECOVERY_NEEDED, &recovery))
-				set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags);
+			set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags);
 
+		else {
 			/*
-			 * The raid set may be doing an initial sync, or it may
-			 * be rebuilding individual components.	 If all the
-			 * devices are In_sync, then it is the raid set that is
-			 * being initialized.
+			 * We are idle and the raid set may be doing an initial
+			 * sync, or it may be rebuilding individual components.
+			 * If all the devices are In_sync, then it is the raid set
+			 * that is being initialized.
 			 */
+			struct md_rdev *rdev;
+
 			set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
 			rdev_for_each(rdev, mddev)
 				if (!test_bit(Journal, &rdev->flags) &&
@@ -3512,7 +3511,7 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 	unsigned int rebuild_disks;
 	unsigned int write_mostly_params = 0;
 	sector_t progress, resync_max_sectors, resync_mismatches;
-	const char *sync_action;
+	enum sync_state state;
 	struct raid_type *rt;
 
 	switch (type) {
@@ -3526,14 +3525,14 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 
 		/* Access most recent mddev properties for status output */
 		smp_rmb();
-		recovery = rs->md.recovery;
 		/* Get sensible max sectors even if raid set not yet started */
 		resync_max_sectors = test_bit(RT_FLAG_RS_PRERESUMED, &rs->runtime_flags) ?
 				      mddev->resync_max_sectors : mddev->dev_sectors;
-		progress = rs_get_progress(rs, recovery, resync_max_sectors);
+		recovery = rs->md.recovery;
+		state = decipher_sync_action(mddev, recovery);
+		progress = rs_get_progress(rs, recovery, state, resync_max_sectors);
 		resync_mismatches = (mddev->last_sync_action && !strcasecmp(mddev->last_sync_action, "check")) ?
 				    atomic64_read(&mddev->resync_mismatches) : 0;
-		sync_action = sync_str(decipher_sync_action(&rs->md, recovery));
 
 		/* HM FIXME: do we want another state char for raid0? It shows 'D'/'A'/'-' now */
 		for (i = 0; i < rs->raid_disks; i++)
@@ -3561,7 +3560,7 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 		 *   See Documentation/admin-guide/device-mapper/dm-raid.rst for
 		 *   information on each of these states.
 		 */
-		DMEMIT(" %s", sync_action);
+		DMEMIT(" %s", sync_str(state));
 
 		/*
 		 * v1.5.0+:
@@ -3955,11 +3954,22 @@ static int raid_preresume(struct dm_target *ti)
 	if (r)
 		return r;
 
-	/* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) */
-	if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap &&
-	    mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)) {
-		r = md_bitmap_resize(mddev->bitmap, mddev->dev_sectors,
-				     to_bytes(rs->requested_bitmap_chunk_sectors), 0);
+	/* We are extending the raid set size, adjust mddev/md_rdev sizes and set capacity. */
+	if (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags)) {
+		mddev->array_sectors = rs->array_sectors;
+		mddev->dev_sectors = rs->dev_sectors;
+		rs_set_rdev_sectors(rs);
+		rs_set_capacity(rs);
+	}
+
+	/* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) or grown device size */
+        if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap &&
+	    (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags) ||
+	     (rs->requested_bitmap_chunk_sectors &&
+	       mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)))) {
+		int chunksize = to_bytes(rs->requested_bitmap_chunk_sectors) ?: mddev->bitmap_info.chunksize;
+
+		r = md_bitmap_resize(mddev->bitmap, mddev->dev_sectors, chunksize, 0);
 		if (r)
 			DMERR("Failed to resize bitmap");
 	}
@@ -3968,8 +3978,10 @@ static int raid_preresume(struct dm_target *ti)
 	/* Be prepared for mddev_resume() in raid_resume() */
 	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	if (mddev->recovery_cp && mddev->recovery_cp < MaxSector) {
-		set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+		set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
 		mddev->resync_min = mddev->recovery_cp;
+		if (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags))
+			mddev->resync_max_sectors = mddev->dev_sectors;
 	}
 
 	/* Check for any reshape request unless new raid set */
@@ -4017,7 +4029,7 @@ static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 14, 0},
+	.version = {1, 15, 0},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 8547d7594338..63bbcc20f49a 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -55,19 +55,6 @@ static void trigger_event(struct work_struct *work)
 	dm_table_event(sc->ti->table);
 }
 
-static inline struct stripe_c *alloc_context(unsigned int stripes)
-{
-	size_t len;
-
-	if (dm_array_too_big(sizeof(struct stripe_c), sizeof(struct stripe),
-			     stripes))
-		return NULL;
-
-	len = sizeof(struct stripe_c) + (sizeof(struct stripe) * stripes);
-
-	return kmalloc(len, GFP_KERNEL);
-}
-
 /*
  * Parse a single <dev> <sector> pair
  */
@@ -142,7 +129,7 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		return -EINVAL;
 	}
 
-	sc = alloc_context(stripes);
+	sc = kmalloc(struct_size(sc, stripe, stripes), GFP_KERNEL);
 	if (!sc) {
 		ti->error = "Memory allocation for striped context "
 		    "failed";
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 52e049554f5c..2ae0c1913766 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -918,21 +918,15 @@ bool dm_table_supports_dax(struct dm_table *t,
 
 static bool dm_table_does_not_support_partial_completion(struct dm_table *t);
 
-struct verify_rq_based_data {
-	unsigned sq_count;
-	unsigned mq_count;
-};
-
-static int device_is_rq_based(struct dm_target *ti, struct dm_dev *dev,
-			      sector_t start, sector_t len, void *data)
+static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev,
+				  sector_t start, sector_t len, void *data)
 {
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-	struct verify_rq_based_data *v = data;
+	struct block_device *bdev = dev->bdev;
+	struct request_queue *q = bdev_get_queue(bdev);
 
-	if (queue_is_mq(q))
-		v->mq_count++;
-	else
-		v->sq_count++;
+	/* request-based cannot stack on partitions! */
+	if (bdev != bdev->bd_contains)
+		return false;
 
 	return queue_is_mq(q);
 }
@@ -941,7 +935,6 @@ static int dm_table_determine_type(struct dm_table *t)
 {
 	unsigned i;
 	unsigned bio_based = 0, request_based = 0, hybrid = 0;
-	struct verify_rq_based_data v = {.sq_count = 0, .mq_count = 0};
 	struct dm_target *tgt;
 	struct list_head *devices = dm_table_get_devices(t);
 	enum dm_queue_mode live_md_type = dm_get_md_type(t->md);
@@ -1045,14 +1038,10 @@ verify_rq_based:
 
 	/* Non-request-stackable devices can't be used for request-based dm */
 	if (!tgt->type->iterate_devices ||
-	    !tgt->type->iterate_devices(tgt, device_is_rq_based, &v)) {
+	    !tgt->type->iterate_devices(tgt, device_is_rq_stackable, NULL)) {
 		DMERR("table load rejected: including non-request-stackable devices");
 		return -EINVAL;
 	}
-	if (v.sq_count > 0) {
-		DMERR("table load rejected: not all devices are blk-mq request-stackable");
-		return -EINVAL;
-	}
 
 	return 0;
 }
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index fcd887703f95..5a2c494cb552 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -609,13 +609,12 @@ static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master,
 		blk_status_t error)
 {
 	struct bio_list bios;
-	unsigned long flags;
 
 	bio_list_init(&bios);
 
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 	__merge_bio_list(&bios, master);
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 
 	error_bio_list(&bios, error);
 }
@@ -623,15 +622,14 @@ static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master,
 static void requeue_deferred_cells(struct thin_c *tc)
 {
 	struct pool *pool = tc->pool;
-	unsigned long flags;
 	struct list_head cells;
 	struct dm_bio_prison_cell *cell, *tmp;
 
 	INIT_LIST_HEAD(&cells);
 
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 	list_splice_init(&tc->deferred_cells, &cells);
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 
 	list_for_each_entry_safe(cell, tmp, &cells, user_list)
 		cell_requeue(pool, cell);
@@ -640,14 +638,13 @@ static void requeue_deferred_cells(struct thin_c *tc)
 static void requeue_io(struct thin_c *tc)
 {
 	struct bio_list bios;
-	unsigned long flags;
 
 	bio_list_init(&bios);
 
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 	__merge_bio_list(&bios, &tc->deferred_bio_list);
 	__merge_bio_list(&bios, &tc->retry_on_resume_list);
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 
 	error_bio_list(&bios, BLK_STS_DM_REQUEUE);
 	requeue_deferred_cells(tc);
@@ -756,7 +753,6 @@ static void inc_all_io_entry(struct pool *pool, struct bio *bio)
 static void issue(struct thin_c *tc, struct bio *bio)
 {
 	struct pool *pool = tc->pool;
-	unsigned long flags;
 
 	if (!bio_triggers_commit(tc, bio)) {
 		generic_make_request(bio);
@@ -777,9 +773,9 @@ static void issue(struct thin_c *tc, struct bio *bio)
 	 * Batch together any bios that trigger commits and then issue a
 	 * single commit for them in process_deferred_bios().
 	 */
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	bio_list_add(&pool->deferred_flush_bios, bio);
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 }
 
 static void remap_to_origin_and_issue(struct thin_c *tc, struct bio *bio)
@@ -886,12 +882,15 @@ static void cell_defer_no_holder(struct thin_c *tc, struct dm_bio_prison_cell *c
 {
 	struct pool *pool = tc->pool;
 	unsigned long flags;
+	int has_work;
 
 	spin_lock_irqsave(&tc->lock, flags);
 	cell_release_no_holder(pool, cell, &tc->deferred_bio_list);
+	has_work = !bio_list_empty(&tc->deferred_bio_list);
 	spin_unlock_irqrestore(&tc->lock, flags);
 
-	wake_worker(pool);
+	if (has_work)
+		wake_worker(pool);
 }
 
 static void thin_defer_bio(struct thin_c *tc, struct bio *bio);
@@ -960,7 +959,6 @@ static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m)
 static void complete_overwrite_bio(struct thin_c *tc, struct bio *bio)
 {
 	struct pool *pool = tc->pool;
-	unsigned long flags;
 
 	/*
 	 * If the bio has the REQ_FUA flag set we must commit the metadata
@@ -985,9 +983,9 @@ static void complete_overwrite_bio(struct thin_c *tc, struct bio *bio)
 	 * Batch together any bios that trigger commits and then issue a
 	 * single commit for them in process_deferred_bios().
 	 */
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	bio_list_add(&pool->deferred_flush_completions, bio);
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 }
 
 static void process_prepared_mapping(struct dm_thin_new_mapping *m)
@@ -1226,14 +1224,13 @@ static void process_prepared_discard_passdown_pt2(struct dm_thin_new_mapping *m)
 static void process_prepared(struct pool *pool, struct list_head *head,
 			     process_mapping_fn *fn)
 {
-	unsigned long flags;
 	struct list_head maps;
 	struct dm_thin_new_mapping *m, *tmp;
 
 	INIT_LIST_HEAD(&maps);
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	list_splice_init(head, &maps);
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 
 	list_for_each_entry_safe(m, tmp, &maps, list)
 		(*fn)(m);
@@ -1510,14 +1507,12 @@ static int commit(struct pool *pool)
 
 static void check_low_water_mark(struct pool *pool, dm_block_t free_blocks)
 {
-	unsigned long flags;
-
 	if (free_blocks <= pool->low_water_blocks && !pool->low_water_triggered) {
 		DMWARN("%s: reached low water mark for data device: sending event.",
 		       dm_device_name(pool->pool_md));
-		spin_lock_irqsave(&pool->lock, flags);
+		spin_lock_irq(&pool->lock);
 		pool->low_water_triggered = true;
-		spin_unlock_irqrestore(&pool->lock, flags);
+		spin_unlock_irq(&pool->lock);
 		dm_table_event(pool->ti->table);
 	}
 }
@@ -1593,11 +1588,10 @@ static void retry_on_resume(struct bio *bio)
 {
 	struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
 	struct thin_c *tc = h->tc;
-	unsigned long flags;
 
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 	bio_list_add(&tc->retry_on_resume_list, bio);
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 }
 
 static blk_status_t should_error_unserviceable_bio(struct pool *pool)
@@ -2170,7 +2164,6 @@ static void __sort_thin_deferred_bios(struct thin_c *tc)
 static void process_thin_deferred_bios(struct thin_c *tc)
 {
 	struct pool *pool = tc->pool;
-	unsigned long flags;
 	struct bio *bio;
 	struct bio_list bios;
 	struct blk_plug plug;
@@ -2184,10 +2177,10 @@ static void process_thin_deferred_bios(struct thin_c *tc)
 
 	bio_list_init(&bios);
 
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 
 	if (bio_list_empty(&tc->deferred_bio_list)) {
-		spin_unlock_irqrestore(&tc->lock, flags);
+		spin_unlock_irq(&tc->lock);
 		return;
 	}
 
@@ -2196,7 +2189,7 @@ static void process_thin_deferred_bios(struct thin_c *tc)
 	bio_list_merge(&bios, &tc->deferred_bio_list);
 	bio_list_init(&tc->deferred_bio_list);
 
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 
 	blk_start_plug(&plug);
 	while ((bio = bio_list_pop(&bios))) {
@@ -2206,10 +2199,10 @@ static void process_thin_deferred_bios(struct thin_c *tc)
 		 * prepared mappings to process.
 		 */
 		if (ensure_next_mapping(pool)) {
-			spin_lock_irqsave(&tc->lock, flags);
+			spin_lock_irq(&tc->lock);
 			bio_list_add(&tc->deferred_bio_list, bio);
 			bio_list_merge(&tc->deferred_bio_list, &bios);
-			spin_unlock_irqrestore(&tc->lock, flags);
+			spin_unlock_irq(&tc->lock);
 			break;
 		}
 
@@ -2264,16 +2257,15 @@ static unsigned sort_cells(struct pool *pool, struct list_head *cells)
 static void process_thin_deferred_cells(struct thin_c *tc)
 {
 	struct pool *pool = tc->pool;
-	unsigned long flags;
 	struct list_head cells;
 	struct dm_bio_prison_cell *cell;
 	unsigned i, j, count;
 
 	INIT_LIST_HEAD(&cells);
 
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 	list_splice_init(&tc->deferred_cells, &cells);
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 
 	if (list_empty(&cells))
 		return;
@@ -2294,9 +2286,9 @@ static void process_thin_deferred_cells(struct thin_c *tc)
 				for (j = i; j < count; j++)
 					list_add(&pool->cell_sort_array[j]->user_list, &cells);
 
-				spin_lock_irqsave(&tc->lock, flags);
+				spin_lock_irq(&tc->lock);
 				list_splice(&cells, &tc->deferred_cells);
-				spin_unlock_irqrestore(&tc->lock, flags);
+				spin_unlock_irq(&tc->lock);
 				return;
 			}
 
@@ -2349,7 +2341,6 @@ static struct thin_c *get_next_thin(struct pool *pool, struct thin_c *tc)
 
 static void process_deferred_bios(struct pool *pool)
 {
-	unsigned long flags;
 	struct bio *bio;
 	struct bio_list bios, bio_completions;
 	struct thin_c *tc;
@@ -2368,13 +2359,13 @@ static void process_deferred_bios(struct pool *pool)
 	bio_list_init(&bios);
 	bio_list_init(&bio_completions);
 
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	bio_list_merge(&bios, &pool->deferred_flush_bios);
 	bio_list_init(&pool->deferred_flush_bios);
 
 	bio_list_merge(&bio_completions, &pool->deferred_flush_completions);
 	bio_list_init(&pool->deferred_flush_completions);
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 
 	if (bio_list_empty(&bios) && bio_list_empty(&bio_completions) &&
 	    !(dm_pool_changed_this_transaction(pool->pmd) && need_commit_due_to_time(pool)))
@@ -2657,12 +2648,11 @@ static void metadata_operation_failed(struct pool *pool, const char *op, int r)
  */
 static void thin_defer_bio(struct thin_c *tc, struct bio *bio)
 {
-	unsigned long flags;
 	struct pool *pool = tc->pool;
 
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 	bio_list_add(&tc->deferred_bio_list, bio);
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 
 	wake_worker(pool);
 }
@@ -2678,13 +2668,12 @@ static void thin_defer_bio_with_throttle(struct thin_c *tc, struct bio *bio)
 
 static void thin_defer_cell(struct thin_c *tc, struct dm_bio_prison_cell *cell)
 {
-	unsigned long flags;
 	struct pool *pool = tc->pool;
 
 	throttle_lock(&pool->throttle);
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 	list_add_tail(&cell->user_list, &tc->deferred_cells);
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 	throttle_unlock(&pool->throttle);
 
 	wake_worker(pool);
@@ -2810,15 +2799,14 @@ static int pool_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
 
 static void requeue_bios(struct pool *pool)
 {
-	unsigned long flags;
 	struct thin_c *tc;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(tc, &pool->active_thins, list) {
-		spin_lock_irqsave(&tc->lock, flags);
+		spin_lock_irq(&tc->lock);
 		bio_list_merge(&tc->deferred_bio_list, &tc->retry_on_resume_list);
 		bio_list_init(&tc->retry_on_resume_list);
-		spin_unlock_irqrestore(&tc->lock, flags);
+		spin_unlock_irq(&tc->lock);
 	}
 	rcu_read_unlock();
 }
@@ -3412,15 +3400,14 @@ static int pool_map(struct dm_target *ti, struct bio *bio)
 	int r;
 	struct pool_c *pt = ti->private;
 	struct pool *pool = pt->pool;
-	unsigned long flags;
 
 	/*
 	 * As this is a singleton target, ti->begin is always zero.
 	 */
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	bio_set_dev(bio, pt->data_dev->bdev);
 	r = DM_MAPIO_REMAPPED;
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 
 	return r;
 }
@@ -3591,7 +3578,6 @@ static void pool_resume(struct dm_target *ti)
 {
 	struct pool_c *pt = ti->private;
 	struct pool *pool = pt->pool;
-	unsigned long flags;
 
 	/*
 	 * Must requeue active_thins' bios and then resume
@@ -3600,10 +3586,10 @@ static void pool_resume(struct dm_target *ti)
 	requeue_bios(pool);
 	pool_resume_active_thins(pool);
 
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	pool->low_water_triggered = false;
 	pool->suspended = false;
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 
 	do_waker(&pool->waker.work);
 }
@@ -3612,11 +3598,10 @@ static void pool_presuspend(struct dm_target *ti)
 {
 	struct pool_c *pt = ti->private;
 	struct pool *pool = pt->pool;
-	unsigned long flags;
 
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	pool->suspended = true;
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 
 	pool_suspend_active_thins(pool);
 }
@@ -3625,13 +3610,12 @@ static void pool_presuspend_undo(struct dm_target *ti)
 {
 	struct pool_c *pt = ti->private;
 	struct pool *pool = pt->pool;
-	unsigned long flags;
 
 	pool_resume_active_thins(pool);
 
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	pool->suspended = false;
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 }
 
 static void pool_postsuspend(struct dm_target *ti)
@@ -4110,11 +4094,10 @@ static void thin_put(struct thin_c *tc)
 static void thin_dtr(struct dm_target *ti)
 {
 	struct thin_c *tc = ti->private;
-	unsigned long flags;
 
-	spin_lock_irqsave(&tc->pool->lock, flags);
+	spin_lock_irq(&tc->pool->lock);
 	list_del_rcu(&tc->list);
-	spin_unlock_irqrestore(&tc->pool->lock, flags);
+	spin_unlock_irq(&tc->pool->lock);
 	synchronize_rcu();
 
 	thin_put(tc);
@@ -4150,7 +4133,6 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	struct thin_c *tc;
 	struct dm_dev *pool_dev, *origin_dev;
 	struct mapped_device *pool_md;
-	unsigned long flags;
 
 	mutex_lock(&dm_thin_pool_table.mutex);
 
@@ -4244,9 +4226,9 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 	mutex_unlock(&dm_thin_pool_table.mutex);
 
-	spin_lock_irqsave(&tc->pool->lock, flags);
+	spin_lock_irq(&tc->pool->lock);
 	if (tc->pool->suspended) {
-		spin_unlock_irqrestore(&tc->pool->lock, flags);
+		spin_unlock_irq(&tc->pool->lock);
 		mutex_lock(&dm_thin_pool_table.mutex); /* reacquire for __pool_dec */
 		ti->error = "Unable to activate thin device while pool is suspended";
 		r = -EINVAL;
@@ -4255,7 +4237,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	refcount_set(&tc->refcount, 1);
 	init_completion(&tc->can_destroy);
 	list_add_tail_rcu(&tc->list, &tc->pool->active_thins);
-	spin_unlock_irqrestore(&tc->pool->lock, flags);
+	spin_unlock_irq(&tc->pool->lock);
 	/*
 	 * This synchronize_rcu() call is needed here otherwise we risk a
 	 * wake_worker() call finding no bios to process (because the newly
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index d06b8aa41e26..7d727a72aa13 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -1218,7 +1218,8 @@ bio_copy:
 			}
 		} while (bio->bi_iter.bi_size);
 
-		if (unlikely(wc->uncommitted_blocks >= wc->autocommit_blocks))
+		if (unlikely(bio->bi_opf & REQ_FUA ||
+			     wc->uncommitted_blocks >= wc->autocommit_blocks))
 			writecache_flush(wc);
 		else
 			writecache_schedule_autocommit(wc);
@@ -1561,7 +1562,7 @@ static void writecache_writeback(struct work_struct *work)
 {
 	struct dm_writecache *wc = container_of(work, struct dm_writecache, writeback_work);
 	struct blk_plug plug;
-	struct wc_entry *f, *g, *e = NULL;
+	struct wc_entry *f, *uninitialized_var(g), *e = NULL;
 	struct rb_node *node, *next_node;
 	struct list_head skipped;
 	struct writeback_list wbl;
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index 595a73110e17..22b3cb0050a7 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -554,6 +554,7 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd,
 		       TASK_UNINTERRUPTIBLE);
 	if (test_bit(DMZ_META_ERROR, &mblk->state)) {
 		dmz_release_mblock(zmd, mblk);
+		dmz_check_bdev(zmd->dev);
 		return ERR_PTR(-EIO);
 	}
 
@@ -625,6 +626,8 @@ static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block,
 	ret = submit_bio_wait(bio);
 	bio_put(bio);
 
+	if (ret)
+		dmz_check_bdev(zmd->dev);
 	return ret;
 }
 
@@ -691,6 +694,7 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd,
 			       TASK_UNINTERRUPTIBLE);
 		if (test_bit(DMZ_META_ERROR, &mblk->state)) {
 			clear_bit(DMZ_META_ERROR, &mblk->state);
+			dmz_check_bdev(zmd->dev);
 			ret = -EIO;
 		}
 		nr_mblks_submitted--;
@@ -768,7 +772,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 	/* If there are no dirty metadata blocks, just flush the device cache */
 	if (list_empty(&write_list)) {
 		ret = blkdev_issue_flush(zmd->dev->bdev, GFP_NOIO, NULL);
-		goto out;
+		goto err;
 	}
 
 	/*
@@ -778,7 +782,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 	 */
 	ret = dmz_log_dirty_mblocks(zmd, &write_list);
 	if (ret)
-		goto out;
+		goto err;
 
 	/*
 	 * The log is on disk. It is now safe to update in place
@@ -786,11 +790,11 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 	 */
 	ret = dmz_write_dirty_mblocks(zmd, &write_list, zmd->mblk_primary);
 	if (ret)
-		goto out;
+		goto err;
 
 	ret = dmz_write_sb(zmd, zmd->mblk_primary);
 	if (ret)
-		goto out;
+		goto err;
 
 	while (!list_empty(&write_list)) {
 		mblk = list_first_entry(&write_list, struct dmz_mblock, link);
@@ -805,16 +809,20 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 
 	zmd->sb_gen++;
 out:
-	if (ret && !list_empty(&write_list)) {
-		spin_lock(&zmd->mblk_lock);
-		list_splice(&write_list, &zmd->mblk_dirty_list);
-		spin_unlock(&zmd->mblk_lock);
-	}
-
 	dmz_unlock_flush(zmd);
 	up_write(&zmd->mblk_sem);
 
 	return ret;
+
+err:
+	if (!list_empty(&write_list)) {
+		spin_lock(&zmd->mblk_lock);
+		list_splice(&write_list, &zmd->mblk_dirty_list);
+		spin_unlock(&zmd->mblk_lock);
+	}
+	if (!dmz_check_bdev(zmd->dev))
+		ret = -EIO;
+	goto out;
 }
 
 /*
@@ -1080,9 +1088,10 @@ static int dmz_load_sb(struct dmz_metadata *zmd)
 /*
  * Initialize a zone descriptor.
  */
-static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone,
-			 struct blk_zone *blkz)
+static int dmz_init_zone(struct blk_zone *blkz, unsigned int idx, void *data)
 {
+	struct dmz_metadata *zmd = data;
+	struct dm_zone *zone = &zmd->zones[idx];
 	struct dmz_dev *dev = zmd->dev;
 
 	/* Ignore the eventual last runt (smaller) zone */
@@ -1096,26 +1105,29 @@ static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone,
 	atomic_set(&zone->refcount, 0);
 	zone->chunk = DMZ_MAP_UNMAPPED;
 
-	if (blkz->type == BLK_ZONE_TYPE_CONVENTIONAL) {
+	switch (blkz->type) {
+	case BLK_ZONE_TYPE_CONVENTIONAL:
 		set_bit(DMZ_RND, &zone->flags);
 		zmd->nr_rnd_zones++;
-	} else if (blkz->type == BLK_ZONE_TYPE_SEQWRITE_REQ ||
-		   blkz->type == BLK_ZONE_TYPE_SEQWRITE_PREF) {
+		break;
+	case BLK_ZONE_TYPE_SEQWRITE_REQ:
+	case BLK_ZONE_TYPE_SEQWRITE_PREF:
 		set_bit(DMZ_SEQ, &zone->flags);
-	} else
+		break;
+	default:
 		return -ENXIO;
-
-	if (blkz->cond == BLK_ZONE_COND_OFFLINE)
-		set_bit(DMZ_OFFLINE, &zone->flags);
-	else if (blkz->cond == BLK_ZONE_COND_READONLY)
-		set_bit(DMZ_READ_ONLY, &zone->flags);
+	}
 
 	if (dmz_is_rnd(zone))
 		zone->wp_block = 0;
 	else
 		zone->wp_block = dmz_sect2blk(blkz->wp - blkz->start);
 
-	if (!dmz_is_offline(zone) && !dmz_is_readonly(zone)) {
+	if (blkz->cond == BLK_ZONE_COND_OFFLINE)
+		set_bit(DMZ_OFFLINE, &zone->flags);
+	else if (blkz->cond == BLK_ZONE_COND_READONLY)
+		set_bit(DMZ_READ_ONLY, &zone->flags);
+	else {
 		zmd->nr_useable_zones++;
 		if (dmz_is_rnd(zone)) {
 			zmd->nr_rnd_zones++;
@@ -1139,23 +1151,13 @@ static void dmz_drop_zones(struct dmz_metadata *zmd)
 }
 
 /*
- * The size of a zone report in number of zones.
- * This results in 4096*64B=256KB report zones commands.
- */
-#define DMZ_REPORT_NR_ZONES	4096
-
-/*
  * Allocate and initialize zone descriptors using the zone
  * information from disk.
  */
 static int dmz_init_zones(struct dmz_metadata *zmd)
 {
 	struct dmz_dev *dev = zmd->dev;
-	struct dm_zone *zone;
-	struct blk_zone *blkz;
-	unsigned int nr_blkz;
-	sector_t sector = 0;
-	int i, ret = 0;
+	int ret;
 
 	/* Init */
 	zmd->zone_bitmap_size = dev->zone_nr_blocks >> 3;
@@ -1169,54 +1171,38 @@ static int dmz_init_zones(struct dmz_metadata *zmd)
 	dmz_dev_info(dev, "Using %zu B for zone information",
 		     sizeof(struct dm_zone) * dev->nr_zones);
 
-	/* Get zone information */
-	nr_blkz = DMZ_REPORT_NR_ZONES;
-	blkz = kcalloc(nr_blkz, sizeof(struct blk_zone), GFP_KERNEL);
-	if (!blkz) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
 	/*
-	 * Get zone information and initialize zone descriptors.
-	 * At the same time, determine where the super block
-	 * should be: first block of the first randomly writable
-	 * zone.
+	 * Get zone information and initialize zone descriptors.  At the same
+	 * time, determine where the super block should be: first block of the
+	 * first randomly writable zone.
 	 */
-	zone = zmd->zones;
-	while (sector < dev->capacity) {
-		/* Get zone information */
-		nr_blkz = DMZ_REPORT_NR_ZONES;
-		ret = blkdev_report_zones(dev->bdev, sector, blkz, &nr_blkz);
-		if (ret) {
-			dmz_dev_err(dev, "Report zones failed %d", ret);
-			goto out;
-		}
+	ret = blkdev_report_zones(dev->bdev, 0, BLK_ALL_ZONES, dmz_init_zone,
+				  zmd);
+	if (ret < 0) {
+		dmz_drop_zones(zmd);
+		return ret;
+	}
 
-		if (!nr_blkz)
-			break;
+	return 0;
+}
 
-		/* Process report */
-		for (i = 0; i < nr_blkz; i++) {
-			ret = dmz_init_zone(zmd, zone, &blkz[i]);
-			if (ret)
-				goto out;
-			sector += dev->zone_nr_sectors;
-			zone++;
-		}
-	}
+static int dmz_update_zone_cb(struct blk_zone *blkz, unsigned int idx,
+			      void *data)
+{
+	struct dm_zone *zone = data;
 
-	/* The entire zone configuration of the disk should now be known */
-	if (sector < dev->capacity) {
-		dmz_dev_err(dev, "Failed to get correct zone information");
-		ret = -ENXIO;
-	}
-out:
-	kfree(blkz);
-	if (ret)
-		dmz_drop_zones(zmd);
+	clear_bit(DMZ_OFFLINE, &zone->flags);
+	clear_bit(DMZ_READ_ONLY, &zone->flags);
+	if (blkz->cond == BLK_ZONE_COND_OFFLINE)
+		set_bit(DMZ_OFFLINE, &zone->flags);
+	else if (blkz->cond == BLK_ZONE_COND_READONLY)
+		set_bit(DMZ_READ_ONLY, &zone->flags);
 
-	return ret;
+	if (dmz_is_seq(zone))
+		zone->wp_block = dmz_sect2blk(blkz->wp - blkz->start);
+	else
+		zone->wp_block = 0;
+	return 0;
 }
 
 /*
@@ -1224,9 +1210,7 @@ out:
  */
 static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 {
-	unsigned int nr_blkz = 1;
 	unsigned int noio_flag;
-	struct blk_zone blkz;
 	int ret;
 
 	/*
@@ -1236,29 +1220,19 @@ static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 	 * GFP_NOIO was specified.
 	 */
 	noio_flag = memalloc_noio_save();
-	ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone),
-				  &blkz, &nr_blkz);
+	ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone), 1,
+				  dmz_update_zone_cb, zone);
 	memalloc_noio_restore(noio_flag);
-	if (!nr_blkz)
+
+	if (ret == 0)
 		ret = -EIO;
-	if (ret) {
+	if (ret < 0) {
 		dmz_dev_err(zmd->dev, "Get zone %u report failed",
 			    dmz_id(zmd, zone));
+		dmz_check_bdev(zmd->dev);
 		return ret;
 	}
 
-	clear_bit(DMZ_OFFLINE, &zone->flags);
-	clear_bit(DMZ_READ_ONLY, &zone->flags);
-	if (blkz.cond == BLK_ZONE_COND_OFFLINE)
-		set_bit(DMZ_OFFLINE, &zone->flags);
-	else if (blkz.cond == BLK_ZONE_COND_READONLY)
-		set_bit(DMZ_READ_ONLY, &zone->flags);
-
-	if (dmz_is_seq(zone))
-		zone->wp_block = dmz_sect2blk(blkz.wp - blkz.start);
-	else
-		zone->wp_block = 0;
-
 	return 0;
 }
 
@@ -1312,9 +1286,9 @@ static int dmz_reset_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 	if (!dmz_is_empty(zone) || dmz_seq_write_err(zone)) {
 		struct dmz_dev *dev = zmd->dev;
 
-		ret = blkdev_reset_zones(dev->bdev,
-					 dmz_start_sect(zmd, zone),
-					 dev->zone_nr_sectors, GFP_NOIO);
+		ret = blkdev_zone_mgmt(dev->bdev, REQ_OP_ZONE_RESET,
+				       dmz_start_sect(zmd, zone),
+				       dev->zone_nr_sectors, GFP_NOIO);
 		if (ret) {
 			dmz_dev_err(dev, "Reset zone %u failed %d",
 				    dmz_id(zmd, zone), ret);
diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c
index d240d7ca8a8a..e7ace908a9b7 100644
--- a/drivers/md/dm-zoned-reclaim.c
+++ b/drivers/md/dm-zoned-reclaim.c
@@ -82,6 +82,7 @@ static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone,
 			    "Align zone %u wp %llu to %llu (wp+%u) blocks failed %d",
 			    dmz_id(zmd, zone), (unsigned long long)wp_block,
 			    (unsigned long long)block, nr_blocks, ret);
+		dmz_check_bdev(zrc->dev);
 		return ret;
 	}
 
@@ -489,12 +490,7 @@ static void dmz_reclaim_work(struct work_struct *work)
 	ret = dmz_do_reclaim(zrc);
 	if (ret) {
 		dmz_dev_debug(zrc->dev, "Reclaim error %d\n", ret);
-		if (ret == -EIO)
-			/*
-			 * LLD might be performing some error handling sequence
-			 * at the underlying device. To not interfere, do not
-			 * attempt to schedule the next reclaim run immediately.
-			 */
+		if (!dmz_check_bdev(zrc->dev))
 			return;
 	}
 
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index d3bcc4197f5d..4574e0dedbd6 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -80,6 +80,8 @@ static inline void dmz_bio_endio(struct bio *bio, blk_status_t status)
 
 	if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK)
 		bio->bi_status = status;
+	if (bio->bi_status != BLK_STS_OK)
+		bioctx->target->dev->flags |= DMZ_CHECK_BDEV;
 
 	if (refcount_dec_and_test(&bioctx->ref)) {
 		struct dm_zone *zone = bioctx->zone;
@@ -565,32 +567,52 @@ out:
 }
 
 /*
- * Check the backing device availability. If it's on the way out,
+ * Check if the backing device is being removed. If it's on the way out,
  * start failing I/O. Reclaim and metadata components also call this
  * function to cleanly abort operation in the event of such failure.
  */
 bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev)
 {
-	struct gendisk *disk;
+	if (dmz_dev->flags & DMZ_BDEV_DYING)
+		return true;
 
-	if (!(dmz_dev->flags & DMZ_BDEV_DYING)) {
-		disk = dmz_dev->bdev->bd_disk;
-		if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) {
-			dmz_dev_warn(dmz_dev, "Backing device queue dying");
-			dmz_dev->flags |= DMZ_BDEV_DYING;
-		} else if (disk->fops->check_events) {
-			if (disk->fops->check_events(disk, 0) &
-					DISK_EVENT_MEDIA_CHANGE) {
-				dmz_dev_warn(dmz_dev, "Backing device offline");
-				dmz_dev->flags |= DMZ_BDEV_DYING;
-			}
-		}
+	if (dmz_dev->flags & DMZ_CHECK_BDEV)
+		return !dmz_check_bdev(dmz_dev);
+
+	if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) {
+		dmz_dev_warn(dmz_dev, "Backing device queue dying");
+		dmz_dev->flags |= DMZ_BDEV_DYING;
 	}
 
 	return dmz_dev->flags & DMZ_BDEV_DYING;
 }
 
 /*
+ * Check the backing device availability. This detects such events as
+ * backing device going offline due to errors, media removals, etc.
+ * This check is less efficient than dmz_bdev_is_dying() and should
+ * only be performed as a part of error handling.
+ */
+bool dmz_check_bdev(struct dmz_dev *dmz_dev)
+{
+	struct gendisk *disk;
+
+	dmz_dev->flags &= ~DMZ_CHECK_BDEV;
+
+	if (dmz_bdev_is_dying(dmz_dev))
+		return false;
+
+	disk = dmz_dev->bdev->bd_disk;
+	if (disk->fops->check_events &&
+	    disk->fops->check_events(disk, 0) & DISK_EVENT_MEDIA_CHANGE) {
+		dmz_dev_warn(dmz_dev, "Backing device offline");
+		dmz_dev->flags |= DMZ_BDEV_DYING;
+	}
+
+	return !(dmz_dev->flags & DMZ_BDEV_DYING);
+}
+
+/*
  * Process a new BIO.
  */
 static int dmz_map(struct dm_target *ti, struct bio *bio)
@@ -902,8 +924,8 @@ static int dmz_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
 {
 	struct dmz_target *dmz = ti->private;
 
-	if (dmz_bdev_is_dying(dmz->dev))
-		return -ENODEV;
+	if (!dmz_check_bdev(dmz->dev))
+		return -EIO;
 
 	*bdev = dmz->dev->bdev;
 
diff --git a/drivers/md/dm-zoned.h b/drivers/md/dm-zoned.h
index d8e70b0ade35..5b5e493d479c 100644
--- a/drivers/md/dm-zoned.h
+++ b/drivers/md/dm-zoned.h
@@ -72,6 +72,7 @@ struct dmz_dev {
 
 /* Device flags. */
 #define DMZ_BDEV_DYING		(1 << 0)
+#define DMZ_CHECK_BDEV		(2 << 0)
 
 /*
  * Zone descriptor.
@@ -255,5 +256,6 @@ void dmz_schedule_reclaim(struct dmz_reclaim *zrc);
  * Functions defined in dm-zoned-target.c
  */
 bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev);
+bool dmz_check_bdev(struct dmz_dev *dmz_dev);
 
 #endif /* DM_ZONED_H */
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 1a5e328c443a..e8f9661a10a1 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -440,14 +440,48 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return dm_get_geometry(md, geo);
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data)
+{
+	struct dm_report_zones_args *args = data;
+	sector_t sector_diff = args->tgt->begin - args->start;
+
+	/*
+	 * Ignore zones beyond the target range.
+	 */
+	if (zone->start >= args->start + args->tgt->len)
+		return 0;
+
+	/*
+	 * Remap the start sector and write pointer position of the zone
+	 * to match its position in the target range.
+	 */
+	zone->start += sector_diff;
+	if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) {
+		if (zone->cond == BLK_ZONE_COND_FULL)
+			zone->wp = zone->start + zone->len;
+		else if (zone->cond == BLK_ZONE_COND_EMPTY)
+			zone->wp = zone->start;
+		else
+			zone->wp += sector_diff;
+	}
+
+	args->next_sector = zone->start + zone->len;
+	return args->orig_cb(zone, args->zone_idx++, args->orig_data);
+}
+EXPORT_SYMBOL_GPL(dm_report_zones_cb);
+
 static int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
-			       struct blk_zone *zones, unsigned int *nr_zones)
+		unsigned int nr_zones, report_zones_cb cb, void *data)
 {
-#ifdef CONFIG_BLK_DEV_ZONED
 	struct mapped_device *md = disk->private_data;
-	struct dm_target *tgt;
 	struct dm_table *map;
 	int srcu_idx, ret;
+	struct dm_report_zones_args args = {
+		.next_sector = sector,
+		.orig_data = data,
+		.orig_cb = cb,
+	};
 
 	if (dm_suspended_md(md))
 		return -EAGAIN;
@@ -456,38 +490,30 @@ static int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
 	if (!map)
 		return -EIO;
 
-	tgt = dm_table_find_target(map, sector);
-	if (!tgt) {
-		ret = -EIO;
-		goto out;
-	}
+	do {
+		struct dm_target *tgt;
 
-	/*
-	 * If we are executing this, we already know that the block device
-	 * is a zoned device and so each target should have support for that
-	 * type of drive. A missing report_zones method means that the target
-	 * driver has a problem.
-	 */
-	if (WARN_ON(!tgt->type->report_zones)) {
-		ret = -EIO;
-		goto out;
-	}
+		tgt = dm_table_find_target(map, args.next_sector);
+		if (WARN_ON_ONCE(!tgt->type->report_zones)) {
+			ret = -EIO;
+			goto out;
+		}
 
-	/*
-	 * blkdev_report_zones() will loop and call this again to cover all the
-	 * zones of the target, eventually moving on to the next target.
-	 * So there is no need to loop here trying to fill the entire array
-	 * of zones.
-	 */
-	ret = tgt->type->report_zones(tgt, sector, zones, nr_zones);
+		args.tgt = tgt;
+		ret = tgt->type->report_zones(tgt, &args, nr_zones);
+		if (ret < 0)
+			goto out;
+	} while (args.zone_idx < nr_zones &&
+		 args.next_sector < get_capacity(disk));
 
+	ret = args.zone_idx;
 out:
 	dm_put_live_table(md, srcu_idx);
 	return ret;
-#else
-	return -ENOTSUPP;
-#endif
 }
+#else
+#define dm_blk_report_zones		NULL
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx,
 			    struct block_device **bdev)
@@ -1174,7 +1200,8 @@ static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
- * allowed for all bio types except REQ_PREFLUSH and REQ_OP_ZONE_RESET.
+ * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_RESET,
+ * REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE and REQ_OP_ZONE_FINISH.
  *
  * dm_accept_partial_bio informs the dm that the target only wants to process
  * additional n_sectors sectors of the bio and the rest of the data should be
@@ -1212,54 +1239,6 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
 }
 EXPORT_SYMBOL_GPL(dm_accept_partial_bio);
 
-/*
- * The zone descriptors obtained with a zone report indicate
- * zone positions within the underlying device of the target. The zone
- * descriptors must be remapped to match their position within the dm device.
- * The caller target should obtain the zones information using
- * blkdev_report_zones() to ensure that remapping for partition offset is
- * already handled.
- */
-void dm_remap_zone_report(struct dm_target *ti, sector_t start,
-			  struct blk_zone *zones, unsigned int *nr_zones)
-{
-#ifdef CONFIG_BLK_DEV_ZONED
-	struct blk_zone *zone;
-	unsigned int nrz = *nr_zones;
-	int i;
-
-	/*
-	 * Remap the start sector and write pointer position of the zones in
-	 * the array. Since we may have obtained from the target underlying
-	 * device more zones that the target size, also adjust the number
-	 * of zones.
-	 */
-	for (i = 0; i < nrz; i++) {
-		zone = zones + i;
-		if (zone->start >= start + ti->len) {
-			memset(zone, 0, sizeof(struct blk_zone) * (nrz - i));
-			break;
-		}
-
-		zone->start = zone->start + ti->begin - start;
-		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
-			continue;
-
-		if (zone->cond == BLK_ZONE_COND_FULL)
-			zone->wp = zone->start + zone->len;
-		else if (zone->cond == BLK_ZONE_COND_EMPTY)
-			zone->wp = zone->start;
-		else
-			zone->wp = zone->wp + ti->begin - start;
-	}
-
-	*nr_zones = i;
-#else /* !CONFIG_BLK_DEV_ZONED */
-	*nr_zones = 0;
-#endif
-}
-EXPORT_SYMBOL_GPL(dm_remap_zone_report);
-
 static blk_qc_t __map_bio(struct dm_target_io *tio)
 {
 	int r;
@@ -1627,7 +1606,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 		ci.sector_count = 0;
 		error = __send_empty_flush(&ci);
 		/* dec_pending submits any data associated with flush */
-	} else if (bio_op(bio) == REQ_OP_ZONE_RESET) {
+	} else if (op_is_zone_mgmt(bio_op(bio))) {
 		ci.bio = bio;
 		ci.sector_count = 0;
 		error = __split_and_process_non_flush(&ci);
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index b092c7b5282f..3ad18246fcb3 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -2139,6 +2139,7 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 		memcpy(page_address(store.sb_page),
 		       page_address(bitmap->storage.sb_page),
 		       sizeof(bitmap_super_t));
+	spin_lock_irq(&bitmap->counts.lock);
 	md_bitmap_file_unmap(&bitmap->storage);
 	bitmap->storage = store;
 
@@ -2154,7 +2155,6 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 	blocks = min(old_counts.chunks << old_counts.chunkshift,
 		     chunks << chunkshift);
 
-	spin_lock_irq(&bitmap->counts.lock);
 	/* For cluster raid, need to pre-allocate bitmap */
 	if (mddev_is_clustered(bitmap->mddev)) {
 		unsigned long page;
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index c766c559d36d..26c75c0199fa 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -244,10 +244,9 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 	sector_t start_sector, end_sector, data_offset;
 	sector_t bio_sector = bio->bi_iter.bi_sector;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	tmp_dev = which_dev(mddev, bio_sector);
 	start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c
index 6780938d2991..152f9e65a226 100644
--- a/drivers/md/md-multipath.c
+++ b/drivers/md/md-multipath.c
@@ -104,10 +104,9 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
 	struct multipath_bh * mp_bh;
 	struct multipath_info *multipath;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	mp_bh = mempool_alloc(&conf->pool, GFP_NOIO);
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 1be7abeb24fd..805b33e27496 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -550,7 +550,13 @@ static void md_submit_flush_data(struct work_struct *ws)
 	}
 }
 
-void md_flush_request(struct mddev *mddev, struct bio *bio)
+/*
+ * Manages consolidation of flushes and submitting any flushes needed for
+ * a bio with REQ_PREFLUSH.  Returns true if the bio is finished or is
+ * being finished in another context.  Returns false if the flushing is
+ * complete but still needs the I/O portion of the bio to be processed.
+ */
+bool md_flush_request(struct mddev *mddev, struct bio *bio)
 {
 	ktime_t start = ktime_get_boottime();
 	spin_lock_irq(&mddev->lock);
@@ -575,9 +581,10 @@ void md_flush_request(struct mddev *mddev, struct bio *bio)
 			bio_endio(bio);
 		else {
 			bio->bi_opf &= ~REQ_PREFLUSH;
-			mddev->pers->make_request(mddev, bio);
+			return false;
 		}
 	}
+	return true;
 }
 EXPORT_SYMBOL(md_flush_request);
 
@@ -1098,6 +1105,7 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 	char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
 	mdp_super_t *sb;
 	int ret;
+	bool spare_disk = true;
 
 	/*
 	 * Calculate the position of the superblock (512byte sectors),
@@ -1148,8 +1156,18 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 	else
 		rdev->desc_nr = sb->this_disk.number;
 
+	/* not spare disk, or LEVEL_MULTIPATH */
+	if (sb->level == LEVEL_MULTIPATH ||
+		(rdev->desc_nr >= 0 &&
+		 sb->disks[rdev->desc_nr].state &
+		 ((1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE))))
+		spare_disk = false;
+
 	if (!refdev) {
-		ret = 1;
+		if (!spare_disk)
+			ret = 1;
+		else
+			ret = 0;
 	} else {
 		__u64 ev1, ev2;
 		mdp_super_t *refsb = page_address(refdev->sb_page);
@@ -1165,7 +1183,8 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 		}
 		ev1 = md_event(sb);
 		ev2 = md_event(refsb);
-		if (ev1 > ev2)
+
+		if (!spare_disk && ev1 > ev2)
 			ret = 1;
 		else
 			ret = 0;
@@ -1525,6 +1544,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	sector_t sectors;
 	char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
 	int bmask;
+	bool spare_disk = true;
 
 	/*
 	 * Calculate the position of the superblock in 512byte sectors.
@@ -1658,8 +1678,19 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	    sb->level != 0)
 		return -EINVAL;
 
+	/* not spare disk, or LEVEL_MULTIPATH */
+	if (sb->level == cpu_to_le32(LEVEL_MULTIPATH) ||
+		(rdev->desc_nr >= 0 &&
+		rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
+		(le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX ||
+		 le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL)))
+		spare_disk = false;
+
 	if (!refdev) {
-		ret = 1;
+		if (!spare_disk)
+			ret = 1;
+		else
+			ret = 0;
 	} else {
 		__u64 ev1, ev2;
 		struct mdp_superblock_1 *refsb = page_address(refdev->sb_page);
@@ -1676,7 +1707,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 		ev1 = le64_to_cpu(sb->events);
 		ev2 = le64_to_cpu(refsb->events);
 
-		if (ev1 > ev2)
+		if (!spare_disk && ev1 > ev2)
 			ret = 1;
 		else
 			ret = 0;
@@ -3597,7 +3628,7 @@ abort_free:
  * Check a full RAID array for plausibility
  */
 
-static void analyze_sbs(struct mddev *mddev)
+static int analyze_sbs(struct mddev *mddev)
 {
 	int i;
 	struct md_rdev *rdev, *freshest, *tmp;
@@ -3618,6 +3649,12 @@ static void analyze_sbs(struct mddev *mddev)
 			md_kick_rdev_from_array(rdev);
 		}
 
+	/* Cannot find a valid fresh disk */
+	if (!freshest) {
+		pr_warn("md: cannot find a valid disk\n");
+		return -EINVAL;
+	}
+
 	super_types[mddev->major_version].
 		validate_super(mddev, freshest);
 
@@ -3652,6 +3689,8 @@ static void analyze_sbs(struct mddev *mddev)
 			clear_bit(In_sync, &rdev->flags);
 		}
 	}
+
+	return 0;
 }
 
 /* Read a fixed-point number.
@@ -5570,7 +5609,9 @@ int md_run(struct mddev *mddev)
 	if (!mddev->raid_disks) {
 		if (!mddev->persistent)
 			return -EINVAL;
-		analyze_sbs(mddev);
+		err = analyze_sbs(mddev);
+		if (err)
+			return -EINVAL;
 	}
 
 	if (mddev->level != LEVEL_NONE)
diff --git a/drivers/md/md.h b/drivers/md/md.h
index c5e3ff398b59..5f86f8adb0a4 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -550,7 +550,7 @@ struct md_personality
 	int level;
 	struct list_head list;
 	struct module *owner;
-	bool (*make_request)(struct mddev *mddev, struct bio *bio);
+	bool __must_check (*make_request)(struct mddev *mddev, struct bio *bio);
 	/*
 	 * start up works that do NOT require md_thread. tasks that
 	 * requires md_thread should go into start()
@@ -703,7 +703,7 @@ extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
 extern void md_finish_reshape(struct mddev *mddev);
 
 extern int mddev_congested(struct mddev *mddev, int bits);
-extern void md_flush_request(struct mddev *mddev, struct bio *bio);
+extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 			   sector_t sector, int size, struct page *page);
 extern int md_super_wait(struct mddev *mddev);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 1e772287b1c8..b7c20979bd19 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -575,10 +575,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 	unsigned chunk_sects;
 	unsigned sectors;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) {
 		raid0_handle_discard(mddev, bio);
@@ -615,7 +614,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 		tmp_dev = map_sector(mddev, zone, sector, &sector);
 		break;
 	default:
-		WARN("md/raid0:%s: Invalid layout\n", mdname(mddev));
+		WARN(1, "md/raid0:%s: Invalid layout\n", mdname(mddev));
 		bio_io_error(bio);
 		return true;
 	}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 0466ee2453b4..a409ab6f30bc 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -819,6 +819,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio)
 		else
 			generic_make_request(bio);
 		bio = next;
+		cond_resched();
 	}
 }
 
@@ -1567,10 +1568,9 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 {
 	sector_t sectors;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	/*
 	 * There is a limit to the maximum size, but
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 299c7b1c9718..ec136e44aef7 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -191,7 +191,7 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
 
 out_free_pages:
 	while (--j >= 0)
-		resync_free_pages(&rps[j * 2]);
+		resync_free_pages(&rps[j]);
 
 	j = 0;
 out_free_bio:
@@ -1525,10 +1525,9 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
 	int chunk_sects = chunk_mask + 1;
 	int sectors = bio_sectors(bio);
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	if (!md_write_start(mddev, bio))
 		return false;
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index 18a4064a61a8..cab5b1352892 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -1404,7 +1404,7 @@ int ppl_init_log(struct r5conf *conf)
 	atomic64_set(&ppl_conf->seq, 0);
 	INIT_LIST_HEAD(&ppl_conf->no_mem_stripes);
 	spin_lock_init(&ppl_conf->no_mem_stripes_lock);
-	ppl_conf->write_hint = RWF_WRITE_LIFE_NOT_SET;
+	ppl_conf->write_hint = RWH_WRITE_LIFE_NOT_SET;
 
 	if (!mddev->external) {
 		ppl_conf->signature = ~crc32c_le(~0, mddev->uuid, sizeof(mddev->uuid));
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 223e97ab27e6..f0fc538bfe59 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1134,7 +1134,7 @@ again:
 			bi->bi_iter.bi_size = STRIPE_SIZE;
 			bi->bi_write_hint = sh->dev[i].write_hint;
 			if (!rrdev)
-				sh->dev[i].write_hint = RWF_WRITE_LIFE_NOT_SET;
+				sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET;
 			/*
 			 * If this is discard request, set bi_vcnt 0. We don't
 			 * want to confuse SCSI because SCSI will replace payload
@@ -1187,7 +1187,7 @@ again:
 			rbi->bi_io_vec[0].bv_offset = 0;
 			rbi->bi_iter.bi_size = STRIPE_SIZE;
 			rbi->bi_write_hint = sh->dev[i].write_hint;
-			sh->dev[i].write_hint = RWF_WRITE_LIFE_NOT_SET;
+			sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET;
 			/*
 			 * If this is discard request, set bi_vcnt 0. We don't
 			 * want to confuse SCSI because SCSI will replace payload
@@ -5592,8 +5592,8 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 		if (ret == 0)
 			return true;
 		if (ret == -ENODEV) {
-			md_flush_request(mddev, bi);
-			return true;
+			if (md_flush_request(mddev, bi))
+				return true;
 		}
 		/* ret == -EAGAIN, fallback */
 		/*
diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c
index 79a53cb8507b..00a79489067c 100644
--- a/drivers/mtd/chips/cfi_cmdset_0001.c
+++ b/drivers/mtd/chips/cfi_cmdset_0001.c
@@ -1353,7 +1353,7 @@ static int do_point_onechip (struct map_info *map, struct flchip *chip, loff_t a
 {
 	unsigned long cmd_addr;
 	struct cfi_private *cfi = map->fldrv_priv;
-	int ret = 0;
+	int ret;
 
 	adr += chip->start;
 
@@ -1383,7 +1383,7 @@ static int cfi_intelext_point(struct mtd_info *mtd, loff_t from, size_t len,
 	struct cfi_private *cfi = map->fldrv_priv;
 	unsigned long ofs, last_end = 0;
 	int chipnum;
-	int ret = 0;
+	int ret;
 
 	if (!map->virt)
 		return -EINVAL;
@@ -1550,7 +1550,7 @@ static int __xipram do_write_oneword(struct map_info *map, struct flchip *chip,
 {
 	struct cfi_private *cfi = map->fldrv_priv;
 	map_word status, write_cmd;
-	int ret=0;
+	int ret;
 
 	adr += chip->start;
 
@@ -1624,7 +1624,7 @@ static int cfi_intelext_write_words (struct mtd_info *mtd, loff_t to , size_t le
 {
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
-	int ret = 0;
+	int ret;
 	int chipnum;
 	unsigned long ofs;
 
@@ -1871,7 +1871,7 @@ static int cfi_intelext_writev (struct mtd_info *mtd, const struct kvec *vecs,
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
 	int wbufsize = cfi_interleave(cfi) << cfi->cfiq->MaxBufWriteSize;
-	int ret = 0;
+	int ret;
 	int chipnum;
 	unsigned long ofs, vec_seek, i;
 	size_t len = 0;
diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c
index cf8c8be40a9c..04b383bc3947 100644
--- a/drivers/mtd/chips/cfi_cmdset_0002.c
+++ b/drivers/mtd/chips/cfi_cmdset_0002.c
@@ -123,19 +123,23 @@ static int cfi_use_status_reg(struct cfi_private *cfi)
 		(extp->SoftwareFeatures & poll_mask) == CFI_POLL_STATUS_REG;
 }
 
-static void cfi_check_err_status(struct map_info *map, struct flchip *chip,
-				 unsigned long adr)
+static int cfi_check_err_status(struct map_info *map, struct flchip *chip,
+				unsigned long adr)
 {
 	struct cfi_private *cfi = map->fldrv_priv;
 	map_word status;
 
 	if (!cfi_use_status_reg(cfi))
-		return;
+		return 0;
 
 	cfi_send_gen_cmd(0x70, cfi->addr_unlock1, chip->start, map, cfi,
 			 cfi->device_type, NULL);
 	status = map_read(map, adr);
 
+	/* The error bits are invalid while the chip's busy */
+	if (!map_word_bitsset(map, status, CMD(CFI_SR_DRB)))
+		return 0;
+
 	if (map_word_bitsset(map, status, CMD(0x3a))) {
 		unsigned long chipstatus = MERGESTATUS(status);
 
@@ -151,7 +155,12 @@ static void cfi_check_err_status(struct map_info *map, struct flchip *chip,
 		if (chipstatus & CFI_SR_SLSB)
 			pr_err("%s sector write protected, status %lx\n",
 			       map->name, chipstatus);
+
+		/* Erase/Program status bits are set on the operation failure */
+		if (chipstatus & (CFI_SR_ESB | CFI_SR_PSB))
+			return 1;
 	}
+	return 0;
 }
 
 /* #define DEBUG_CFI_FEATURES */
@@ -785,7 +794,6 @@ static struct mtd_info *cfi_amdstd_setup(struct mtd_info *mtd)
 	kfree(mtd->eraseregions);
 	kfree(mtd);
 	kfree(cfi->cmdset_priv);
-	kfree(cfi->cfiq);
 	return NULL;
 }
 
@@ -848,20 +856,16 @@ static int __xipram chip_good(struct map_info *map, struct flchip *chip,
 
 	if (cfi_use_status_reg(cfi)) {
 		map_word ready = CMD(CFI_SR_DRB);
-		map_word err = CMD(CFI_SR_PSB | CFI_SR_ESB);
+
 		/*
 		 * For chips that support status register, check device
-		 * ready bit and Erase/Program status bit to know if
-		 * operation succeeded.
+		 * ready bit
 		 */
 		cfi_send_gen_cmd(0x70, cfi->addr_unlock1, chip->start, map, cfi,
 				 cfi->device_type, NULL);
 		curd = map_read(map, addr);
 
-		if (map_word_andequal(map, curd, ready, ready))
-			return !map_word_bitsset(map, curd, err);
-
-		return 0;
+		return map_word_andequal(map, curd, ready, ready);
 	}
 
 	oldd = map_read(map, addr);
@@ -1699,8 +1703,11 @@ static int __xipram do_write_oneword_once(struct map_info *map,
 			break;
 		}
 
-		if (chip_good(map, chip, adr, datum))
+		if (chip_good(map, chip, adr, datum)) {
+			if (cfi_check_err_status(map, chip, adr))
+				ret = -EIO;
 			break;
+		}
 
 		/* Latency issues. Drop the lock, wait a while and retry */
 		UDELAY(map, chip, adr, 1);
@@ -1713,7 +1720,7 @@ static int __xipram do_write_oneword_start(struct map_info *map,
 					   struct flchip *chip,
 					   unsigned long adr, int mode)
 {
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&chip->mutex);
 
@@ -1773,7 +1780,6 @@ static int __xipram do_write_oneword_retry(struct map_info *map,
 	ret = do_write_oneword_once(map, chip, adr, datum, mode, cfi);
 	if (ret) {
 		/* reset on all failures. */
-		cfi_check_err_status(map, chip, adr);
 		map_write(map, CMD(0xF0), chip->start);
 		/* FIXME - should have reset delay before continuing */
 
@@ -1791,7 +1797,7 @@ static int __xipram do_write_oneword(struct map_info *map, struct flchip *chip,
 				     unsigned long adr, map_word datum,
 				     int mode)
 {
-	int ret = 0;
+	int ret;
 
 	adr += chip->start;
 
@@ -1815,7 +1821,7 @@ static int cfi_amdstd_write_words(struct mtd_info *mtd, loff_t to, size_t len,
 {
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
-	int ret = 0;
+	int ret;
 	int chipnum;
 	unsigned long ofs, chipstart;
 	DECLARE_WAITQUEUE(wait, current);
@@ -1970,12 +1976,17 @@ static int __xipram do_write_buffer_wait(struct map_info *map,
 		 */
 		if (time_after(jiffies, timeo) &&
 		    !chip_good(map, chip, adr, datum)) {
+			pr_err("MTD %s(): software timeout, address:0x%.8lx.\n",
+			       __func__, adr);
 			ret = -EIO;
 			break;
 		}
 
-		if (chip_good(map, chip, adr, datum))
+		if (chip_good(map, chip, adr, datum)) {
+			if (cfi_check_err_status(map, chip, adr))
+				ret = -EIO;
 			break;
+		}
 
 		/* Latency issues. Drop the lock, wait a while and retry */
 		UDELAY(map, chip, adr, 1);
@@ -2014,7 +2025,7 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip,
 				    int len)
 {
 	struct cfi_private *cfi = map->fldrv_priv;
-	int ret = -EIO;
+	int ret;
 	unsigned long cmd_adr;
 	int z, words;
 	map_word datum;
@@ -2071,12 +2082,8 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip,
 				chip->word_write_time);
 
 	ret = do_write_buffer_wait(map, chip, adr, datum);
-	if (ret) {
-		cfi_check_err_status(map, chip, adr);
+	if (ret)
 		do_write_buffer_reset(map, chip, cfi);
-		pr_err("MTD %s(): software timeout, address:0x%.8lx.\n",
-		       __func__, adr);
-	}
 
 	xip_enable(map, chip, adr);
 
@@ -2095,7 +2102,7 @@ static int cfi_amdstd_write_buffers(struct mtd_info *mtd, loff_t to, size_t len,
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
 	int wbufsize = cfi_interleave(cfi) << cfi->cfiq->MaxBufWriteSize;
-	int ret = 0;
+	int ret;
 	int chipnum;
 	unsigned long ofs;
 
@@ -2232,7 +2239,7 @@ static int do_panic_write_oneword(struct map_info *map, struct flchip *chip,
 	struct cfi_private *cfi = map->fldrv_priv;
 	int retry_cnt = 0;
 	map_word oldd;
-	int ret = 0;
+	int ret;
 	int i;
 
 	adr += chip->start;
@@ -2271,9 +2278,9 @@ retry:
 		udelay(1);
 	}
 
-	if (!chip_good(map, chip, adr, datum)) {
+	if (!chip_good(map, chip, adr, datum) ||
+	    cfi_check_err_status(map, chip, adr)) {
 		/* reset on all failures. */
-		cfi_check_err_status(map, chip, adr);
 		map_write(map, CMD(0xF0), chip->start);
 		/* FIXME - should have reset delay before continuing */
 
@@ -2307,7 +2314,7 @@ static int cfi_amdstd_panic_write(struct mtd_info *mtd, loff_t to, size_t len,
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
 	unsigned long ofs, chipstart;
-	int ret = 0;
+	int ret;
 	int chipnum;
 
 	chipnum = to >> cfi->chipshift;
@@ -2411,7 +2418,7 @@ static int __xipram do_erase_chip(struct map_info *map, struct flchip *chip)
 	unsigned long timeo = jiffies + HZ;
 	unsigned long int adr;
 	DECLARE_WAITQUEUE(wait, current);
-	int ret = 0;
+	int ret;
 	int retry_cnt = 0;
 
 	adr = cfi->addr_unlock1;
@@ -2467,8 +2474,11 @@ static int __xipram do_erase_chip(struct map_info *map, struct flchip *chip)
 			chip->erase_suspended = 0;
 		}
 
-		if (chip_good(map, chip, adr, map_word_ff(map)))
+		if (chip_good(map, chip, adr, map_word_ff(map))) {
+			if (cfi_check_err_status(map, chip, adr))
+				ret = -EIO;
 			break;
+		}
 
 		if (time_after(jiffies, timeo)) {
 			printk(KERN_WARNING "MTD %s(): software timeout\n",
@@ -2483,7 +2493,6 @@ static int __xipram do_erase_chip(struct map_info *map, struct flchip *chip)
 	/* Did we succeed? */
 	if (ret) {
 		/* reset on all failures. */
-		cfi_check_err_status(map, chip, adr);
 		map_write(map, CMD(0xF0), chip->start);
 		/* FIXME - should have reset delay before continuing */
 
@@ -2508,7 +2517,7 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip,
 	struct cfi_private *cfi = map->fldrv_priv;
 	unsigned long timeo = jiffies + HZ;
 	DECLARE_WAITQUEUE(wait, current);
-	int ret = 0;
+	int ret;
 	int retry_cnt = 0;
 
 	adr += chip->start;
@@ -2564,8 +2573,11 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip,
 			chip->erase_suspended = 0;
 		}
 
-		if (chip_good(map, chip, adr, map_word_ff(map)))
+		if (chip_good(map, chip, adr, map_word_ff(map))) {
+			if (cfi_check_err_status(map, chip, adr))
+				ret = -EIO;
 			break;
+		}
 
 		if (time_after(jiffies, timeo)) {
 			printk(KERN_WARNING "MTD %s(): software timeout\n",
@@ -2580,7 +2592,6 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip,
 	/* Did we succeed? */
 	if (ret) {
 		/* reset on all failures. */
-		cfi_check_err_status(map, chip, adr);
 		map_write(map, CMD(0xF0), chip->start);
 		/* FIXME - should have reset delay before continuing */
 
diff --git a/drivers/mtd/chips/cfi_cmdset_0020.c b/drivers/mtd/chips/cfi_cmdset_0020.c
index e752067526a5..54edae63b92d 100644
--- a/drivers/mtd/chips/cfi_cmdset_0020.c
+++ b/drivers/mtd/chips/cfi_cmdset_0020.c
@@ -611,7 +611,7 @@ static int cfi_staa_write_buffers (struct mtd_info *mtd, loff_t to,
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
 	int wbufsize = cfi_interleave(cfi) << cfi->cfiq->MaxBufWriteSize;
-	int ret = 0;
+	int ret;
 	int chipnum;
 	unsigned long ofs;
 
@@ -895,7 +895,7 @@ static int cfi_staa_erase_varsize(struct mtd_info *mtd,
 {	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
 	unsigned long adr, len;
-	int chipnum, ret = 0;
+	int chipnum, ret;
 	int i, first;
 	struct mtd_erase_region_info *regions = mtd->eraseregions;
 
@@ -1132,7 +1132,7 @@ static int cfi_staa_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
 	unsigned long adr;
-	int chipnum, ret = 0;
+	int chipnum, ret;
 #ifdef DEBUG_LOCK_BITS
 	int ofs_factor = cfi->interleave * cfi->device_type;
 #endif
@@ -1279,7 +1279,7 @@ static int cfi_staa_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
 	unsigned long adr;
-	int chipnum, ret = 0;
+	int chipnum, ret;
 #ifdef DEBUG_LOCK_BITS
 	int ofs_factor = cfi->interleave * cfi->device_type;
 #endif
diff --git a/drivers/mtd/chips/cfi_util.c b/drivers/mtd/chips/cfi_util.c
index e3b266ee06af..e2d4db05aeb3 100644
--- a/drivers/mtd/chips/cfi_util.c
+++ b/drivers/mtd/chips/cfi_util.c
@@ -26,7 +26,7 @@
 void cfi_udelay(int us)
 {
 	if (us >= 1000) {
-		msleep((us+999)/1000);
+		msleep(DIV_ROUND_UP(us, 1000));
 	} else {
 		udelay(us);
 		cond_resched();
diff --git a/drivers/mtd/devices/mchp23k256.c b/drivers/mtd/devices/mchp23k256.c
index b20d02b4f830..77c872fd3d83 100644
--- a/drivers/mtd/devices/mchp23k256.c
+++ b/drivers/mtd/devices/mchp23k256.c
@@ -64,15 +64,17 @@ static int mchp23k256_write(struct mtd_info *mtd, loff_t to, size_t len,
 	struct spi_transfer transfer[2] = {};
 	struct spi_message message;
 	unsigned char command[MAX_CMD_SIZE];
-	int ret;
+	int ret, cmd_len;
 
 	spi_message_init(&message);
 
+	cmd_len = mchp23k256_cmdsz(flash);
+
 	command[0] = MCHP23K256_CMD_WRITE;
 	mchp23k256_addr2cmd(flash, to, command);
 
 	transfer[0].tx_buf = command;
-	transfer[0].len = mchp23k256_cmdsz(flash);
+	transfer[0].len = cmd_len;
 	spi_message_add_tail(&transfer[0], &message);
 
 	transfer[1].tx_buf = buf;
@@ -88,8 +90,8 @@ static int mchp23k256_write(struct mtd_info *mtd, loff_t to, size_t len,
 	if (ret)
 		return ret;
 
-	if (retlen && message.actual_length > sizeof(command))
-		*retlen += message.actual_length - sizeof(command);
+	if (retlen && message.actual_length > cmd_len)
+		*retlen += message.actual_length - cmd_len;
 
 	return 0;
 }
@@ -101,16 +103,18 @@ static int mchp23k256_read(struct mtd_info *mtd, loff_t from, size_t len,
 	struct spi_transfer transfer[2] = {};
 	struct spi_message message;
 	unsigned char command[MAX_CMD_SIZE];
-	int ret;
+	int ret, cmd_len;
 
 	spi_message_init(&message);
 
+	cmd_len = mchp23k256_cmdsz(flash);
+
 	memset(&transfer, 0, sizeof(transfer));
 	command[0] = MCHP23K256_CMD_READ;
 	mchp23k256_addr2cmd(flash, from, command);
 
 	transfer[0].tx_buf = command;
-	transfer[0].len = mchp23k256_cmdsz(flash);
+	transfer[0].len = cmd_len;
 	spi_message_add_tail(&transfer[0], &message);
 
 	transfer[1].rx_buf = buf;
@@ -126,8 +130,8 @@ static int mchp23k256_read(struct mtd_info *mtd, loff_t from, size_t len,
 	if (ret)
 		return ret;
 
-	if (retlen && message.actual_length > sizeof(command))
-		*retlen += message.actual_length - sizeof(command);
+	if (retlen && message.actual_length > cmd_len)
+		*retlen += message.actual_length - cmd_len;
 
 	return 0;
 }
diff --git a/drivers/mtd/devices/spear_smi.c b/drivers/mtd/devices/spear_smi.c
index 986f81d2f93e..79dcca16481d 100644
--- a/drivers/mtd/devices/spear_smi.c
+++ b/drivers/mtd/devices/spear_smi.c
@@ -592,6 +592,26 @@ static int spear_mtd_read(struct mtd_info *mtd, loff_t from, size_t len,
 	return 0;
 }
 
+/*
+ * The purpose of this function is to ensure a memcpy_toio() with byte writes
+ * only. Its structure is inspired from the ARM implementation of _memcpy_toio()
+ * which also does single byte writes but cannot be used here as this is just an
+ * implementation detail and not part of the API. Not mentioning the comment
+ * stating that _memcpy_toio() should be optimized.
+ */
+static void spear_smi_memcpy_toio_b(volatile void __iomem *dest,
+				    const void *src, size_t len)
+{
+	const unsigned char *from = src;
+
+	while (len) {
+		len--;
+		writeb(*from, dest);
+		from++;
+		dest++;
+	}
+}
+
 static inline int spear_smi_cpy_toio(struct spear_smi *dev, u32 bank,
 		void __iomem *dest, const void *src, size_t len)
 {
@@ -614,7 +634,23 @@ static inline int spear_smi_cpy_toio(struct spear_smi *dev, u32 bank,
 	ctrlreg1 = readl(dev->io_base + SMI_CR1);
 	writel((ctrlreg1 | WB_MODE) & ~SW_MODE, dev->io_base + SMI_CR1);
 
-	memcpy_toio(dest, src, len);
+	/*
+	 * In Write Burst mode (WB_MODE), the specs states that writes must be:
+	 * - incremental
+	 * - of the same size
+	 * The ARM implementation of memcpy_toio() will optimize the number of
+	 * I/O by using as much 4-byte writes as possible, surrounded by
+	 * 2-byte/1-byte access if:
+	 * - the destination is not 4-byte aligned
+	 * - the length is not a multiple of 4-byte.
+	 * Avoid this alternance of write access size by using our own 'byte
+	 * access' helper if at least one of the two conditions above is true.
+	 */
+	if (IS_ALIGNED(len, sizeof(u32)) &&
+	    IS_ALIGNED((uintptr_t)dest, sizeof(u32)))
+		memcpy_toio(dest, src, len);
+	else
+		spear_smi_memcpy_toio_b(dest, src, len);
 
 	writel(ctrlreg1, dev->io_base + SMI_CR1);
 
@@ -777,9 +813,6 @@ static int spear_smi_probe_config_dt(struct platform_device *pdev,
 
 	/* Fill structs for each subnode (flash device) */
 	while ((pp = of_get_next_child(np, pp))) {
-		struct spear_smi_flash_info *flash_info;
-
-		flash_info = &pdata->board_flash_info[i];
 		pdata->np[i] = pp;
 
 		/* Read base-addr and size from DT */
@@ -933,7 +966,6 @@ static int spear_smi_probe(struct platform_device *pdev)
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
 		ret = -ENODEV;
-		dev_err(&pdev->dev, "invalid smi irq\n");
 		goto err;
 	}
 
diff --git a/drivers/mtd/devices/st_spi_fsm.c b/drivers/mtd/devices/st_spi_fsm.c
index f4d1667daaf9..1888523d9745 100644
--- a/drivers/mtd/devices/st_spi_fsm.c
+++ b/drivers/mtd/devices/st_spi_fsm.c
@@ -255,7 +255,6 @@ struct stfsm_seq {
 struct stfsm {
 	struct device		*dev;
 	void __iomem		*base;
-	struct resource		*region;
 	struct mtd_info		mtd;
 	struct mutex		lock;
 	struct flash_info       *info;
diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig
index bc82305ebb4c..b28225a7c4f3 100644
--- a/drivers/mtd/maps/Kconfig
+++ b/drivers/mtd/maps/Kconfig
@@ -96,6 +96,17 @@ config MTD_PHYSMAP_GEMINI
 	  platforms, some detection and setting up parallel mode on the
 	  external interface.
 
+config MTD_PHYSMAP_IXP4XX
+	bool "Intel IXP4xx OF-based physical memory map handling"
+	depends on MTD_PHYSMAP_OF
+	depends on ARM
+	select MTD_COMPLEX_MAPPINGS
+	select MTD_CFI_BE_BYTE_SWAP if CPU_BIG_ENDIAN
+	default ARCH_IXP4XX
+	help
+	  This provides some extra DT physmap parsing for the Intel IXP4xx
+	  platforms, some elaborate endianness handling in particular.
+
 config MTD_PHYSMAP_GPIO_ADDR
 	bool "GPIO-assisted Flash Chip Support"
 	depends on MTD_PHYSMAP
diff --git a/drivers/mtd/maps/Makefile b/drivers/mtd/maps/Makefile
index 1146009f41df..c0da86a5d26f 100644
--- a/drivers/mtd/maps/Makefile
+++ b/drivers/mtd/maps/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_MTD_PXA2XX)	+= pxa2xx-flash.o
 physmap-objs-y			+= physmap-core.o
 physmap-objs-$(CONFIG_MTD_PHYSMAP_VERSATILE) += physmap-versatile.o
 physmap-objs-$(CONFIG_MTD_PHYSMAP_GEMINI) += physmap-gemini.o
+physmap-objs-$(CONFIG_MTD_PHYSMAP_IXP4XX) += physmap-ixp4xx.o
 physmap-objs			:= $(physmap-objs-y)
 obj-$(CONFIG_MTD_PHYSMAP)	+= physmap.o
 obj-$(CONFIG_MTD_PISMO)		+= pismo.o
diff --git a/drivers/mtd/maps/l440gx.c b/drivers/mtd/maps/l440gx.c
index 876f12f40018..0eeadfeb620d 100644
--- a/drivers/mtd/maps/l440gx.c
+++ b/drivers/mtd/maps/l440gx.c
@@ -86,7 +86,7 @@ static int __init init_l440gx(void)
 		return -ENOMEM;
 	}
 	simple_map_init(&l440gx_map);
-	printk(KERN_NOTICE "window_addr = 0x%08lx\n", (unsigned long)l440gx_map.virt);
+	pr_debug("window_addr = %p\n", l440gx_map.virt);
 
 	/* Setup the pm iobase resource
 	 * This code should move into some kind of generic bridge
diff --git a/drivers/mtd/maps/physmap-core.c b/drivers/mtd/maps/physmap-core.c
index 21b556afc305..a9f7964e2edb 100644
--- a/drivers/mtd/maps/physmap-core.c
+++ b/drivers/mtd/maps/physmap-core.c
@@ -41,6 +41,7 @@
 #include <linux/gpio/consumer.h>
 
 #include "physmap-gemini.h"
+#include "physmap-ixp4xx.h"
 #include "physmap-versatile.h"
 
 struct physmap_flash_info {
@@ -370,6 +371,10 @@ static int physmap_flash_of_init(struct platform_device *dev)
 		if (err)
 			return err;
 
+		err = of_flash_probe_ixp4xx(dev, dp, &info->maps[i]);
+		if (err)
+			return err;
+
 		err = of_flash_probe_versatile(dev, dp, &info->maps[i]);
 		if (err)
 			return err;
diff --git a/drivers/mtd/maps/physmap-ixp4xx.c b/drivers/mtd/maps/physmap-ixp4xx.c
new file mode 100644
index 000000000000..6a054229a8a0
--- /dev/null
+++ b/drivers/mtd/maps/physmap-ixp4xx.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel IXP4xx OF physmap add-on
+ * Copyright (C) 2019 Linus Walleij <linus.walleij@linaro.org>
+ *
+ * Based on the ixp4xx.c map driver, originally written by:
+ * Intel Corporation
+ * Deepak Saxena <dsaxena@mvista.com>
+ * Copyright (C) 2002 Intel Corporation
+ * Copyright (C) 2003-2004 MontaVista Software, Inc.
+ */
+#include <linux/export.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/mtd/map.h>
+#include <linux/mtd/xip.h>
+#include "physmap-ixp4xx.h"
+
+/*
+ * Read/write a 16 bit word from flash address 'addr'.
+ *
+ * When the cpu is in little-endian mode it swizzles the address lines
+ * ('address coherency') so we need to undo the swizzling to ensure commands
+ * and the like end up on the correct flash address.
+ *
+ * To further complicate matters, due to the way the expansion bus controller
+ * handles 32 bit reads, the byte stream ABCD is stored on the flash as:
+ *     D15    D0
+ *     +---+---+
+ *     | A | B | 0
+ *     +---+---+
+ *     | C | D | 2
+ *     +---+---+
+ * This means that on LE systems each 16 bit word must be swapped. Note that
+ * this requires CONFIG_MTD_CFI_BE_BYTE_SWAP to be enabled to 'unswap' the CFI
+ * data and other flash commands which are always in D7-D0.
+ */
+#ifndef CONFIG_CPU_BIG_ENDIAN
+
+static inline u16 flash_read16(void __iomem *addr)
+{
+	return be16_to_cpu(__raw_readw((void __iomem *)((unsigned long)addr ^ 0x2)));
+}
+
+static inline void flash_write16(u16 d, void __iomem *addr)
+{
+	__raw_writew(cpu_to_be16(d), (void __iomem *)((unsigned long)addr ^ 0x2));
+}
+
+#define	BYTE0(h)	((h) & 0xFF)
+#define	BYTE1(h)	(((h) >> 8) & 0xFF)
+
+#else
+
+static inline u16 flash_read16(const void __iomem *addr)
+{
+	return __raw_readw(addr);
+}
+
+static inline void flash_write16(u16 d, void __iomem *addr)
+{
+	__raw_writew(d, addr);
+}
+
+#define	BYTE0(h)	(((h) >> 8) & 0xFF)
+#define	BYTE1(h)	((h) & 0xFF)
+#endif
+
+static map_word ixp4xx_read16(struct map_info *map, unsigned long ofs)
+{
+	map_word val;
+
+	val.x[0] = flash_read16(map->virt + ofs);
+	return val;
+}
+
+/*
+ * The IXP4xx expansion bus only allows 16-bit wide acceses
+ * when attached to a 16-bit wide device (such as the 28F128J3A),
+ * so we can't just memcpy_fromio().
+ */
+static void ixp4xx_copy_from(struct map_info *map, void *to,
+			     unsigned long from, ssize_t len)
+{
+	u8 *dest = (u8 *) to;
+	void __iomem *src = map->virt + from;
+
+	if (len <= 0)
+		return;
+
+	if (from & 1) {
+		*dest++ = BYTE1(flash_read16(src-1));
+		src++;
+		--len;
+	}
+
+	while (len >= 2) {
+		u16 data = flash_read16(src);
+		*dest++ = BYTE0(data);
+		*dest++ = BYTE1(data);
+		src += 2;
+		len -= 2;
+	}
+
+	if (len > 0)
+		*dest++ = BYTE0(flash_read16(src));
+}
+
+static void ixp4xx_write16(struct map_info *map, map_word d, unsigned long adr)
+{
+	flash_write16(d.x[0], map->virt + adr);
+}
+
+int of_flash_probe_ixp4xx(struct platform_device *pdev,
+			  struct device_node *np,
+			  struct map_info *map)
+{
+	struct device *dev = &pdev->dev;
+
+	/* Multiplatform guard */
+	if (!of_device_is_compatible(np, "intel,ixp4xx-flash"))
+		return 0;
+
+	map->read = ixp4xx_read16;
+	map->write = ixp4xx_write16;
+	map->copy_from = ixp4xx_copy_from;
+	map->copy_to = NULL;
+
+	dev_info(dev, "initialized Intel IXP4xx-specific physmap control\n");
+
+	return 0;
+}
diff --git a/drivers/mtd/maps/physmap-ixp4xx.h b/drivers/mtd/maps/physmap-ixp4xx.h
new file mode 100644
index 000000000000..b0fc49b7f3ed
--- /dev/null
+++ b/drivers/mtd/maps/physmap-ixp4xx.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/of.h>
+#include <linux/mtd/map.h>
+
+#ifdef CONFIG_MTD_PHYSMAP_IXP4XX
+int of_flash_probe_ixp4xx(struct platform_device *pdev,
+			  struct device_node *np,
+			  struct map_info *map);
+#else
+static inline
+int of_flash_probe_ixp4xx(struct platform_device *pdev,
+			  struct device_node *np,
+			  struct map_info *map)
+{
+	return 0;
+}
+#endif
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 975aed94f06c..b841008a9eb7 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -174,7 +174,7 @@ static ssize_t mtdchar_read(struct file *file, char __user *buf, size_t count,
 			break;
 		case MTD_FILE_MODE_RAW:
 		{
-			struct mtd_oob_ops ops;
+			struct mtd_oob_ops ops = {};
 
 			ops.mode = MTD_OPS_RAW;
 			ops.datbuf = kbuf;
@@ -268,7 +268,7 @@ static ssize_t mtdchar_write(struct file *file, const char __user *buf, size_t c
 
 		case MTD_FILE_MODE_RAW:
 		{
-			struct mtd_oob_ops ops;
+			struct mtd_oob_ops ops = {};
 
 			ops.mode = MTD_OPS_RAW;
 			ops.datbuf = kbuf;
@@ -350,7 +350,7 @@ static int mtdchar_writeoob(struct file *file, struct mtd_info *mtd,
 	uint32_t __user *retp)
 {
 	struct mtd_file_info *mfi = file->private_data;
-	struct mtd_oob_ops ops;
+	struct mtd_oob_ops ops = {};
 	uint32_t retlen;
 	int ret = 0;
 
@@ -394,7 +394,7 @@ static int mtdchar_readoob(struct file *file, struct mtd_info *mtd,
 	uint32_t __user *retp)
 {
 	struct mtd_file_info *mfi = file->private_data;
-	struct mtd_oob_ops ops;
+	struct mtd_oob_ops ops = {};
 	int ret = 0;
 
 	if (length > 4096)
@@ -587,7 +587,7 @@ static int mtdchar_write_ioctl(struct mtd_info *mtd,
 		struct mtd_write_req __user *argp)
 {
 	struct mtd_write_req req;
-	struct mtd_oob_ops ops;
+	struct mtd_oob_ops ops = {};
 	const void __user *usr_data, *usr_oob;
 	int ret;
 
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 6cc7ecb0c788..5fac4355b9c2 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -382,33 +382,21 @@ static struct dentry *dfs_dir_mtd;
 static void mtd_debugfs_populate(struct mtd_info *mtd)
 {
 	struct device *dev = &mtd->dev;
-	struct dentry *root, *dent;
+	struct dentry *root;
 
 	if (IS_ERR_OR_NULL(dfs_dir_mtd))
 		return;
 
 	root = debugfs_create_dir(dev_name(dev), dfs_dir_mtd);
-	if (IS_ERR_OR_NULL(root)) {
-		dev_dbg(dev, "won't show data in debugfs\n");
-		return;
-	}
-
 	mtd->dbg.dfs_dir = root;
 
-	if (mtd->dbg.partid) {
-		dent = debugfs_create_file("partid", 0400, root, mtd,
-					   &mtd_partid_debug_fops);
-		if (IS_ERR_OR_NULL(dent))
-			dev_err(dev, "can't create debugfs entry for partid\n");
-	}
+	if (mtd->dbg.partid)
+		debugfs_create_file("partid", 0400, root, mtd,
+				    &mtd_partid_debug_fops);
 
-	if (mtd->dbg.partname) {
-		dent = debugfs_create_file("partname", 0400, root, mtd,
-					   &mtd_partname_debug_fops);
-		if (IS_ERR_OR_NULL(dent))
-			dev_err(dev,
-				"can't create debugfs entry for partname\n");
-	}
+	if (mtd->dbg.partname)
+		debugfs_create_file("partname", 0400, root, mtd,
+				    &mtd_partname_debug_fops);
 }
 
 #ifndef CONFIG_MMU
diff --git a/drivers/mtd/mtdswap.c b/drivers/mtd/mtdswap.c
index f92414eb4c86..58eefa43af14 100644
--- a/drivers/mtd/mtdswap.c
+++ b/drivers/mtd/mtdswap.c
@@ -1257,7 +1257,6 @@ DEFINE_SHOW_ATTRIBUTE(mtdswap);
 static int mtdswap_add_debugfs(struct mtdswap_dev *d)
 {
 	struct dentry *root = d->mtd->dbg.dfs_dir;
-	struct dentry *dent;
 
 	if (!IS_ENABLED(CONFIG_DEBUG_FS))
 		return 0;
@@ -1265,12 +1264,7 @@ static int mtdswap_add_debugfs(struct mtdswap_dev *d)
 	if (IS_ERR_OR_NULL(root))
 		return -1;
 
-	dent = debugfs_create_file("mtdswap_stats", S_IRUSR, root, d,
-				&mtdswap_fops);
-	if (!dent) {
-		dev_err(d->dev, "debugfs_create_file failed\n");
-		return -1;
-	}
+	debugfs_create_file("mtdswap_stats", S_IRUSR, root, d, &mtdswap_fops);
 
 	return 0;
 }
diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index e59de3f60cf6..74fb91adeb46 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -450,6 +450,13 @@ config MTD_NAND_PLATFORM
 	  devices. You will need to provide platform-specific functions
 	  via platform_data.
 
+config MTD_NAND_CADENCE
+	tristate "Support Cadence NAND (HPNFC) controller"
+	depends on OF || COMPILE_TEST
+	help
+	  Enable the driver for NAND flash on platforms using a Cadence NAND
+	  controller.
+
 comment "Misc"
 
 config MTD_SM_COMMON
diff --git a/drivers/mtd/nand/raw/Makefile b/drivers/mtd/nand/raw/Makefile
index a98721988e61..2d136b158fb7 100644
--- a/drivers/mtd/nand/raw/Makefile
+++ b/drivers/mtd/nand/raw/Makefile
@@ -57,6 +57,7 @@ obj-$(CONFIG_MTD_NAND_MXIC)		+= mxic_nand.o
 obj-$(CONFIG_MTD_NAND_TEGRA)		+= tegra_nand.o
 obj-$(CONFIG_MTD_NAND_STM32_FMC2)	+= stm32_fmc2_nand.o
 obj-$(CONFIG_MTD_NAND_MESON)		+= meson_nand.o
+obj-$(CONFIG_MTD_NAND_CADENCE)		+= cadence-nand-controller.o
 
 nand-objs := nand_base.o nand_legacy.o nand_bbt.o nand_timings.o nand_ids.o
 nand-objs += nand_onfi.o
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index 15ef30b368a5..1a66b1cd51c0 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -117,6 +117,18 @@ enum flash_dma_reg {
 	FLASH_DMA_CURRENT_DESC_EXT,
 };
 
+/* flash_dma registers v0*/
+static const u16 flash_dma_regs_v0[] = {
+	[FLASH_DMA_REVISION]		= 0x00,
+	[FLASH_DMA_FIRST_DESC]		= 0x04,
+	[FLASH_DMA_CTRL]		= 0x08,
+	[FLASH_DMA_MODE]		= 0x0c,
+	[FLASH_DMA_STATUS]		= 0x10,
+	[FLASH_DMA_INTERRUPT_DESC]	= 0x14,
+	[FLASH_DMA_ERROR_STATUS]	= 0x18,
+	[FLASH_DMA_CURRENT_DESC]	= 0x1c,
+};
+
 /* flash_dma registers v1*/
 static const u16 flash_dma_regs_v1[] = {
 	[FLASH_DMA_REVISION]		= 0x00,
@@ -597,6 +609,8 @@ static void brcmnand_flash_dma_revision_init(struct brcmnand_controller *ctrl)
 	/* flash_dma register offsets */
 	if (ctrl->nand_version >= 0x0703)
 		ctrl->flash_dma_offsets = flash_dma_regs_v4;
+	else if (ctrl->nand_version == 0x0602)
+		ctrl->flash_dma_offsets = flash_dma_regs_v0;
 	else
 		ctrl->flash_dma_offsets = flash_dma_regs_v1;
 }
@@ -918,7 +932,7 @@ static inline void disable_ctrl_irqs(struct brcmnand_controller *ctrl)
 		return;
 
 	if (has_flash_dma(ctrl)) {
-		ctrl->flash_dma_base = 0;
+		ctrl->flash_dma_base = NULL;
 		disable_irq(ctrl->dma_irq);
 	}
 
@@ -1673,8 +1687,11 @@ static void brcmnand_dma_run(struct brcmnand_host *host, dma_addr_t desc)
 
 	flash_dma_writel(ctrl, FLASH_DMA_FIRST_DESC, lower_32_bits(desc));
 	(void)flash_dma_readl(ctrl, FLASH_DMA_FIRST_DESC);
-	flash_dma_writel(ctrl, FLASH_DMA_FIRST_DESC_EXT, upper_32_bits(desc));
-	(void)flash_dma_readl(ctrl, FLASH_DMA_FIRST_DESC_EXT);
+	if (ctrl->nand_version > 0x0602) {
+		flash_dma_writel(ctrl, FLASH_DMA_FIRST_DESC_EXT,
+				 upper_32_bits(desc));
+		(void)flash_dma_readl(ctrl, FLASH_DMA_FIRST_DESC_EXT);
+	}
 
 	/* Start FLASH_DMA engine */
 	ctrl->dma_pending = true;
diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
new file mode 100644
index 000000000000..3a36285a8d8a
--- /dev/null
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -0,0 +1,3030 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Cadence NAND flash controller driver
+ *
+ * Copyright (C) 2019 Cadence
+ *
+ * Author: Piotr Sroka <piotrs@cadence.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/rawnand.h>
+#include <linux/of_device.h>
+#include <linux/iopoll.h>
+
+/*
+ * HPNFC can work in 3 modes:
+ * -  PIO - can work in master or slave DMA
+ * -  CDMA - needs Master DMA for accessing command descriptors.
+ * -  Generic mode - can use only slave DMA.
+ * CDMA and PIO modes can be used to execute only base commands.
+ * Generic mode can be used to execute any command
+ * on NAND flash memory. Driver uses CDMA mode for
+ * block erasing, page reading, page programing.
+ * Generic mode is used for executing rest of commands.
+ */
+
+#define MAX_OOB_SIZE_PER_SECTOR	32
+#define MAX_ADDRESS_CYC		6
+#define MAX_ERASE_ADDRESS_CYC	3
+#define MAX_DATA_SIZE		0xFFFC
+#define DMA_DATA_SIZE_ALIGN	8
+
+/* Register definition. */
+/*
+ * Command register 0.
+ * Writing data to this register will initiate a new transaction
+ * of the NF controller.
+ */
+#define CMD_REG0			0x0000
+/* Command type field mask. */
+#define		CMD_REG0_CT		GENMASK(31, 30)
+/* Command type CDMA. */
+#define		CMD_REG0_CT_CDMA	0uL
+/* Command type generic. */
+#define		CMD_REG0_CT_GEN		3uL
+/* Command thread number field mask. */
+#define		CMD_REG0_TN		GENMASK(27, 24)
+
+/* Command register 2. */
+#define CMD_REG2			0x0008
+/* Command register 3. */
+#define CMD_REG3			0x000C
+/* Pointer register to select which thread status will be selected. */
+#define CMD_STATUS_PTR			0x0010
+/* Command status register for selected thread. */
+#define CMD_STATUS			0x0014
+
+/* Interrupt status register. */
+#define INTR_STATUS			0x0110
+#define		INTR_STATUS_SDMA_ERR	BIT(22)
+#define		INTR_STATUS_SDMA_TRIGG	BIT(21)
+#define		INTR_STATUS_UNSUPP_CMD	BIT(19)
+#define		INTR_STATUS_DDMA_TERR	BIT(18)
+#define		INTR_STATUS_CDMA_TERR	BIT(17)
+#define		INTR_STATUS_CDMA_IDL	BIT(16)
+
+/* Interrupt enable register. */
+#define INTR_ENABLE				0x0114
+#define		INTR_ENABLE_INTR_EN		BIT(31)
+#define		INTR_ENABLE_SDMA_ERR_EN		BIT(22)
+#define		INTR_ENABLE_SDMA_TRIGG_EN	BIT(21)
+#define		INTR_ENABLE_UNSUPP_CMD_EN	BIT(19)
+#define		INTR_ENABLE_DDMA_TERR_EN	BIT(18)
+#define		INTR_ENABLE_CDMA_TERR_EN	BIT(17)
+#define		INTR_ENABLE_CDMA_IDLE_EN	BIT(16)
+
+/* Controller internal state. */
+#define CTRL_STATUS				0x0118
+#define		CTRL_STATUS_INIT_COMP		BIT(9)
+#define		CTRL_STATUS_CTRL_BUSY		BIT(8)
+
+/* Command Engine threads state. */
+#define TRD_STATUS				0x0120
+
+/* Command Engine interrupt thread error status. */
+#define TRD_ERR_INT_STATUS			0x0128
+/* Command Engine interrupt thread error enable. */
+#define TRD_ERR_INT_STATUS_EN			0x0130
+/* Command Engine interrupt thread complete status. */
+#define TRD_COMP_INT_STATUS			0x0138
+
+/*
+ * Transfer config 0 register.
+ * Configures data transfer parameters.
+ */
+#define TRAN_CFG_0				0x0400
+/* Offset value from the beginning of the page. */
+#define		TRAN_CFG_0_OFFSET		GENMASK(31, 16)
+/* Numbers of sectors to transfer within singlNF device's page. */
+#define		TRAN_CFG_0_SEC_CNT		GENMASK(7, 0)
+
+/*
+ * Transfer config 1 register.
+ * Configures data transfer parameters.
+ */
+#define TRAN_CFG_1				0x0404
+/* Size of last data sector. */
+#define		TRAN_CFG_1_LAST_SEC_SIZE	GENMASK(31, 16)
+/* Size of not-last data sector. */
+#define		TRAN_CFG_1_SECTOR_SIZE		GENMASK(15, 0)
+
+/* ECC engine configuration register 0. */
+#define ECC_CONFIG_0				0x0428
+/* Correction strength. */
+#define		ECC_CONFIG_0_CORR_STR		GENMASK(10, 8)
+/* Enable erased pages detection mechanism. */
+#define		ECC_CONFIG_0_ERASE_DET_EN	BIT(1)
+/* Enable controller ECC check bits generation and correction. */
+#define		ECC_CONFIG_0_ECC_EN		BIT(0)
+
+/* ECC engine configuration register 1. */
+#define ECC_CONFIG_1				0x042C
+
+/* Multiplane settings register. */
+#define MULTIPLANE_CFG				0x0434
+/* Cache operation settings. */
+#define CACHE_CFG				0x0438
+
+/* DMA settings register. */
+#define DMA_SETINGS				0x043C
+/* Enable SDMA error report on access unprepared slave DMA interface. */
+#define		DMA_SETINGS_SDMA_ERR_RSP	BIT(17)
+
+/* Transferred data block size for the slave DMA module. */
+#define SDMA_SIZE				0x0440
+
+/* Thread number associated with transferred data block
+ * for the slave DMA module.
+ */
+#define SDMA_TRD_NUM				0x0444
+/* Thread number mask. */
+#define		SDMA_TRD_NUM_SDMA_TRD		GENMASK(2, 0)
+
+#define CONTROL_DATA_CTRL			0x0494
+/* Thread number mask. */
+#define		CONTROL_DATA_CTRL_SIZE		GENMASK(15, 0)
+
+#define CTRL_VERSION				0x800
+#define		CTRL_VERSION_REV		GENMASK(7, 0)
+
+/* Available hardware features of the controller. */
+#define CTRL_FEATURES				0x804
+/* Support for NV-DDR2/3 work mode. */
+#define		CTRL_FEATURES_NVDDR_2_3		BIT(28)
+/* Support for NV-DDR work mode. */
+#define		CTRL_FEATURES_NVDDR		BIT(27)
+/* Support for asynchronous work mode. */
+#define		CTRL_FEATURES_ASYNC		BIT(26)
+/* Support for asynchronous work mode. */
+#define		CTRL_FEATURES_N_BANKS		GENMASK(25, 24)
+/* Slave and Master DMA data width. */
+#define		CTRL_FEATURES_DMA_DWITH64	BIT(21)
+/* Availability of Control Data feature.*/
+#define		CTRL_FEATURES_CONTROL_DATA	BIT(10)
+
+/* BCH Engine identification register 0 - correction strengths. */
+#define BCH_CFG_0				0x838
+#define		BCH_CFG_0_CORR_CAP_0		GENMASK(7, 0)
+#define		BCH_CFG_0_CORR_CAP_1		GENMASK(15, 8)
+#define		BCH_CFG_0_CORR_CAP_2		GENMASK(23, 16)
+#define		BCH_CFG_0_CORR_CAP_3		GENMASK(31, 24)
+
+/* BCH Engine identification register 1 - correction strengths. */
+#define BCH_CFG_1				0x83C
+#define		BCH_CFG_1_CORR_CAP_4		GENMASK(7, 0)
+#define		BCH_CFG_1_CORR_CAP_5		GENMASK(15, 8)
+#define		BCH_CFG_1_CORR_CAP_6		GENMASK(23, 16)
+#define		BCH_CFG_1_CORR_CAP_7		GENMASK(31, 24)
+
+/* BCH Engine identification register 2 - sector sizes. */
+#define BCH_CFG_2				0x840
+#define		BCH_CFG_2_SECT_0		GENMASK(15, 0)
+#define		BCH_CFG_2_SECT_1		GENMASK(31, 16)
+
+/* BCH Engine identification register 3. */
+#define BCH_CFG_3				0x844
+
+/* Ready/Busy# line status. */
+#define RBN_SETINGS				0x1004
+
+/* Common settings. */
+#define COMMON_SET				0x1008
+/* 16 bit device connected to the NAND Flash interface. */
+#define		COMMON_SET_DEVICE_16BIT		BIT(8)
+
+/* Skip_bytes registers. */
+#define SKIP_BYTES_CONF				0x100C
+#define		SKIP_BYTES_MARKER_VALUE		GENMASK(31, 16)
+#define		SKIP_BYTES_NUM_OF_BYTES		GENMASK(7, 0)
+
+#define SKIP_BYTES_OFFSET			0x1010
+#define		 SKIP_BYTES_OFFSET_VALUE	GENMASK(23, 0)
+
+/* Timings configuration. */
+#define ASYNC_TOGGLE_TIMINGS			0x101c
+#define		ASYNC_TOGGLE_TIMINGS_TRH	GENMASK(28, 24)
+#define		ASYNC_TOGGLE_TIMINGS_TRP	GENMASK(20, 16)
+#define		ASYNC_TOGGLE_TIMINGS_TWH	GENMASK(12, 8)
+#define		ASYNC_TOGGLE_TIMINGS_TWP	GENMASK(4, 0)
+
+#define	TIMINGS0				0x1024
+#define		TIMINGS0_TADL			GENMASK(31, 24)
+#define		TIMINGS0_TCCS			GENMASK(23, 16)
+#define		TIMINGS0_TWHR			GENMASK(15, 8)
+#define		TIMINGS0_TRHW			GENMASK(7, 0)
+
+#define	TIMINGS1				0x1028
+#define		TIMINGS1_TRHZ			GENMASK(31, 24)
+#define		TIMINGS1_TWB			GENMASK(23, 16)
+#define		TIMINGS1_TVDLY			GENMASK(7, 0)
+
+#define	TIMINGS2				0x102c
+#define		TIMINGS2_TFEAT			GENMASK(25, 16)
+#define		TIMINGS2_CS_HOLD_TIME		GENMASK(13, 8)
+#define		TIMINGS2_CS_SETUP_TIME		GENMASK(5, 0)
+
+/* Configuration of the resynchronization of slave DLL of PHY. */
+#define DLL_PHY_CTRL				0x1034
+#define		DLL_PHY_CTRL_DLL_RST_N		BIT(24)
+#define		DLL_PHY_CTRL_EXTENDED_WR_MODE	BIT(17)
+#define		DLL_PHY_CTRL_EXTENDED_RD_MODE	BIT(16)
+#define		DLL_PHY_CTRL_RS_HIGH_WAIT_CNT	GENMASK(11, 8)
+#define		DLL_PHY_CTRL_RS_IDLE_CNT	GENMASK(7, 0)
+
+/* Register controlling DQ related timing. */
+#define PHY_DQ_TIMING				0x2000
+/* Register controlling DSQ related timing.  */
+#define PHY_DQS_TIMING				0x2004
+#define		PHY_DQS_TIMING_DQS_SEL_OE_END	GENMASK(3, 0)
+#define		PHY_DQS_TIMING_PHONY_DQS_SEL	BIT(16)
+#define		PHY_DQS_TIMING_USE_PHONY_DQS	BIT(20)
+
+/* Register controlling the gate and loopback control related timing. */
+#define PHY_GATE_LPBK_CTRL			0x2008
+#define		PHY_GATE_LPBK_CTRL_RDS		GENMASK(24, 19)
+
+/* Register holds the control for the master DLL logic. */
+#define PHY_DLL_MASTER_CTRL			0x200C
+#define		PHY_DLL_MASTER_CTRL_BYPASS_MODE	BIT(23)
+
+/* Register holds the control for the slave DLL logic. */
+#define PHY_DLL_SLAVE_CTRL			0x2010
+
+/* This register handles the global control settings for the PHY. */
+#define PHY_CTRL				0x2080
+#define		PHY_CTRL_SDR_DQS		BIT(14)
+#define		PHY_CTRL_PHONY_DQS		GENMASK(9, 4)
+
+/*
+ * This register handles the global control settings
+ * for the termination selects for reads.
+ */
+#define PHY_TSEL				0x2084
+
+/* Generic command layout. */
+#define GCMD_LAY_CS			GENMASK_ULL(11, 8)
+/*
+ * This bit informs the minicotroller if it has to wait for tWB
+ * after sending the last CMD/ADDR/DATA in the sequence.
+ */
+#define GCMD_LAY_TWB			BIT_ULL(6)
+/* Type of generic instruction. */
+#define GCMD_LAY_INSTR			GENMASK_ULL(5, 0)
+
+/* Generic CMD sequence type. */
+#define		GCMD_LAY_INSTR_CMD	0
+/* Generic ADDR sequence type. */
+#define		GCMD_LAY_INSTR_ADDR	1
+/* Generic data transfer sequence type. */
+#define		GCMD_LAY_INSTR_DATA	2
+
+/* Input part of generic command type of input is command. */
+#define GCMD_LAY_INPUT_CMD		GENMASK_ULL(23, 16)
+
+/* Generic command address sequence - address fields. */
+#define GCMD_LAY_INPUT_ADDR		GENMASK_ULL(63, 16)
+/* Generic command address sequence - address size. */
+#define GCMD_LAY_INPUT_ADDR_SIZE	GENMASK_ULL(13, 11)
+
+/* Transfer direction field of generic command data sequence. */
+#define GCMD_DIR			BIT_ULL(11)
+/* Read transfer direction of generic command data sequence. */
+#define		GCMD_DIR_READ		0
+/* Write transfer direction of generic command data sequence. */
+#define		GCMD_DIR_WRITE		1
+
+/* ECC enabled flag of generic command data sequence - ECC enabled. */
+#define GCMD_ECC_EN			BIT_ULL(12)
+/* Generic command data sequence - sector size. */
+#define GCMD_SECT_SIZE			GENMASK_ULL(31, 16)
+/* Generic command data sequence - sector count. */
+#define GCMD_SECT_CNT			GENMASK_ULL(39, 32)
+/* Generic command data sequence - last sector size. */
+#define GCMD_LAST_SIZE			GENMASK_ULL(55, 40)
+
+/* CDMA descriptor fields. */
+/* Erase command type of CDMA descriptor. */
+#define CDMA_CT_ERASE		0x1000
+/* Program page command type of CDMA descriptor. */
+#define CDMA_CT_WR		0x2100
+/* Read page command type of CDMA descriptor. */
+#define CDMA_CT_RD		0x2200
+
+/* Flash pointer memory shift. */
+#define CDMA_CFPTR_MEM_SHIFT	24
+/* Flash pointer memory mask. */
+#define CDMA_CFPTR_MEM		GENMASK(26, 24)
+
+/*
+ * Command DMA descriptor flags. If set causes issue interrupt after
+ * the completion of descriptor processing.
+ */
+#define CDMA_CF_INT		BIT(8)
+/*
+ * Command DMA descriptor flags - the next descriptor
+ * address field is valid and descriptor processing should continue.
+ */
+#define CDMA_CF_CONT		BIT(9)
+/* DMA master flag of command DMA descriptor. */
+#define CDMA_CF_DMA_MASTER	BIT(10)
+
+/* Operation complete status of command descriptor. */
+#define CDMA_CS_COMP		BIT(15)
+/* Operation complete status of command descriptor. */
+/* Command descriptor status - operation fail. */
+#define CDMA_CS_FAIL		BIT(14)
+/* Command descriptor status - page erased. */
+#define CDMA_CS_ERP		BIT(11)
+/* Command descriptor status - timeout occurred. */
+#define CDMA_CS_TOUT		BIT(10)
+/*
+ * Maximum amount of correction applied to one ECC sector.
+ * It is part of command descriptor status.
+ */
+#define CDMA_CS_MAXERR		GENMASK(9, 2)
+/* Command descriptor status - uncorrectable ECC error. */
+#define CDMA_CS_UNCE		BIT(1)
+/* Command descriptor status - descriptor error. */
+#define CDMA_CS_ERR		BIT(0)
+
+/* Status of operation - OK. */
+#define STAT_OK			0
+/* Status of operation - FAIL. */
+#define STAT_FAIL		2
+/* Status of operation - uncorrectable ECC error. */
+#define STAT_ECC_UNCORR		3
+/* Status of operation - page erased. */
+#define STAT_ERASED		5
+/* Status of operation - correctable ECC error. */
+#define STAT_ECC_CORR		6
+/* Status of operation - unsuspected state. */
+#define STAT_UNKNOWN		7
+/* Status of operation - operation is not completed yet. */
+#define STAT_BUSY		0xFF
+
+#define BCH_MAX_NUM_CORR_CAPS		8
+#define BCH_MAX_NUM_SECTOR_SIZES	2
+
+struct cadence_nand_timings {
+	u32 async_toggle_timings;
+	u32 timings0;
+	u32 timings1;
+	u32 timings2;
+	u32 dll_phy_ctrl;
+	u32 phy_ctrl;
+	u32 phy_dqs_timing;
+	u32 phy_gate_lpbk_ctrl;
+};
+
+/* Command DMA descriptor. */
+struct cadence_nand_cdma_desc {
+	/* Next descriptor address. */
+	u64 next_pointer;
+
+	/* Flash address is a 32-bit address comprising of BANK and ROW ADDR. */
+	u32 flash_pointer;
+	/*field appears in HPNFC version 13*/
+	u16 bank;
+	u16 rsvd0;
+
+	/* Operation the controller needs to perform. */
+	u16 command_type;
+	u16 rsvd1;
+	/* Flags for operation of this command. */
+	u16 command_flags;
+	u16 rsvd2;
+
+	/* System/host memory address required for data DMA commands. */
+	u64 memory_pointer;
+
+	/* Status of operation. */
+	u32 status;
+	u32 rsvd3;
+
+	/* Address pointer to sync buffer location. */
+	u64 sync_flag_pointer;
+
+	/* Controls the buffer sync mechanism. */
+	u32 sync_arguments;
+	u32 rsvd4;
+
+	/* Control data pointer. */
+	u64 ctrl_data_ptr;
+};
+
+/* Interrupt status. */
+struct cadence_nand_irq_status {
+	/* Thread operation complete status. */
+	u32 trd_status;
+	/* Thread operation error. */
+	u32 trd_error;
+	/* Controller status. */
+	u32 status;
+};
+
+/* Cadence NAND flash controller capabilities get from driver data. */
+struct cadence_nand_dt_devdata {
+	/* Skew value of the output signals of the NAND Flash interface. */
+	u32 if_skew;
+	/* It informs if slave DMA interface is connected to DMA engine. */
+	unsigned int has_dma:1;
+};
+
+/* Cadence NAND flash controller capabilities read from registers. */
+struct cdns_nand_caps {
+	/* Maximum number of banks supported by hardware. */
+	u8 max_banks;
+	/* Slave and Master DMA data width in bytes (4 or 8). */
+	u8 data_dma_width;
+	/* Control Data feature supported. */
+	bool data_control_supp;
+	/* Is PHY type DLL. */
+	bool is_phy_type_dll;
+};
+
+struct cdns_nand_ctrl {
+	struct device *dev;
+	struct nand_controller controller;
+	struct cadence_nand_cdma_desc *cdma_desc;
+	/* IP capability. */
+	const struct cadence_nand_dt_devdata *caps1;
+	struct cdns_nand_caps caps2;
+	u8 ctrl_rev;
+	dma_addr_t dma_cdma_desc;
+	u8 *buf;
+	u32 buf_size;
+	u8 curr_corr_str_idx;
+
+	/* Register interface. */
+	void __iomem *reg;
+
+	struct {
+		void __iomem *virt;
+		dma_addr_t dma;
+	} io;
+
+	int irq;
+	/* Interrupts that have happened. */
+	struct cadence_nand_irq_status irq_status;
+	/* Interrupts we are waiting for. */
+	struct cadence_nand_irq_status irq_mask;
+	struct completion complete;
+	/* Protect irq_mask and irq_status. */
+	spinlock_t irq_lock;
+
+	int ecc_strengths[BCH_MAX_NUM_CORR_CAPS];
+	struct nand_ecc_step_info ecc_stepinfos[BCH_MAX_NUM_SECTOR_SIZES];
+	struct nand_ecc_caps ecc_caps;
+
+	int curr_trans_type;
+
+	struct dma_chan *dmac;
+
+	u32 nf_clk_rate;
+	/*
+	 * Estimated Board delay. The value includes the total
+	 * round trip delay for the signals and is used for deciding on values
+	 * associated with data read capture.
+	 */
+	u32 board_delay;
+
+	struct nand_chip *selected_chip;
+
+	unsigned long assigned_cs;
+	struct list_head chips;
+};
+
+struct cdns_nand_chip {
+	struct cadence_nand_timings timings;
+	struct nand_chip chip;
+	u8 nsels;
+	struct list_head node;
+
+	/*
+	 * part of oob area of NAND flash memory page.
+	 * This part is available for user to read or write.
+	 */
+	u32 avail_oob_size;
+
+	/* Sector size. There are few sectors per mtd->writesize */
+	u32 sector_size;
+	u32 sector_count;
+
+	/* Offset of BBM. */
+	u8 bbm_offs;
+	/* Number of bytes reserved for BBM. */
+	u8 bbm_len;
+	/* ECC strength index. */
+	u8 corr_str_idx;
+
+	u8 cs[];
+};
+
+struct ecc_info {
+	int (*calc_ecc_bytes)(int step_size, int strength);
+	int max_step_size;
+};
+
+static inline struct
+cdns_nand_chip *to_cdns_nand_chip(struct nand_chip *chip)
+{
+	return container_of(chip, struct cdns_nand_chip, chip);
+}
+
+static inline struct
+cdns_nand_ctrl *to_cdns_nand_ctrl(struct nand_controller *controller)
+{
+	return container_of(controller, struct cdns_nand_ctrl, controller);
+}
+
+static bool
+cadence_nand_dma_buf_ok(struct cdns_nand_ctrl *cdns_ctrl, const void *buf,
+			u32 buf_len)
+{
+	u8 data_dma_width = cdns_ctrl->caps2.data_dma_width;
+
+	return buf && virt_addr_valid(buf) &&
+		likely(IS_ALIGNED((uintptr_t)buf, data_dma_width)) &&
+		likely(IS_ALIGNED(buf_len, DMA_DATA_SIZE_ALIGN));
+}
+
+static int cadence_nand_wait_for_value(struct cdns_nand_ctrl *cdns_ctrl,
+				       u32 reg_offset, u32 timeout_us,
+				       u32 mask, bool is_clear)
+{
+	u32 val;
+	int ret;
+
+	ret = readl_relaxed_poll_timeout(cdns_ctrl->reg + reg_offset,
+					 val, !(val & mask) == is_clear,
+					 10, timeout_us);
+
+	if (ret < 0) {
+		dev_err(cdns_ctrl->dev,
+			"Timeout while waiting for reg %x with mask %x is clear %d\n",
+			reg_offset, mask, is_clear);
+	}
+
+	return ret;
+}
+
+static int cadence_nand_set_ecc_enable(struct cdns_nand_ctrl *cdns_ctrl,
+				       bool enable)
+{
+	u32 reg;
+
+	if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					1000000,
+					CTRL_STATUS_CTRL_BUSY, true))
+		return -ETIMEDOUT;
+
+	reg = readl_relaxed(cdns_ctrl->reg + ECC_CONFIG_0);
+
+	if (enable)
+		reg |= ECC_CONFIG_0_ECC_EN;
+	else
+		reg &= ~ECC_CONFIG_0_ECC_EN;
+
+	writel_relaxed(reg, cdns_ctrl->reg + ECC_CONFIG_0);
+
+	return 0;
+}
+
+static void cadence_nand_set_ecc_strength(struct cdns_nand_ctrl *cdns_ctrl,
+					  u8 corr_str_idx)
+{
+	u32 reg;
+
+	if (cdns_ctrl->curr_corr_str_idx == corr_str_idx)
+		return;
+
+	reg = readl_relaxed(cdns_ctrl->reg + ECC_CONFIG_0);
+	reg &= ~ECC_CONFIG_0_CORR_STR;
+	reg |= FIELD_PREP(ECC_CONFIG_0_CORR_STR, corr_str_idx);
+	writel_relaxed(reg, cdns_ctrl->reg + ECC_CONFIG_0);
+
+	cdns_ctrl->curr_corr_str_idx = corr_str_idx;
+}
+
+static int cadence_nand_get_ecc_strength_idx(struct cdns_nand_ctrl *cdns_ctrl,
+					     u8 strength)
+{
+	int i, corr_str_idx = -1;
+
+	for (i = 0; i < BCH_MAX_NUM_CORR_CAPS; i++) {
+		if (cdns_ctrl->ecc_strengths[i] == strength) {
+			corr_str_idx = i;
+			break;
+		}
+	}
+
+	return corr_str_idx;
+}
+
+static int cadence_nand_set_skip_marker_val(struct cdns_nand_ctrl *cdns_ctrl,
+					    u16 marker_value)
+{
+	u32 reg;
+
+	if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					1000000,
+					CTRL_STATUS_CTRL_BUSY, true))
+		return -ETIMEDOUT;
+
+	reg = readl_relaxed(cdns_ctrl->reg + SKIP_BYTES_CONF);
+	reg &= ~SKIP_BYTES_MARKER_VALUE;
+	reg |= FIELD_PREP(SKIP_BYTES_MARKER_VALUE,
+			  marker_value);
+
+	writel_relaxed(reg, cdns_ctrl->reg + SKIP_BYTES_CONF);
+
+	return 0;
+}
+
+static int cadence_nand_set_skip_bytes_conf(struct cdns_nand_ctrl *cdns_ctrl,
+					    u8 num_of_bytes,
+					    u32 offset_value,
+					    int enable)
+{
+	u32 reg, skip_bytes_offset;
+
+	if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					1000000,
+					CTRL_STATUS_CTRL_BUSY, true))
+		return -ETIMEDOUT;
+
+	if (!enable) {
+		num_of_bytes = 0;
+		offset_value = 0;
+	}
+
+	reg = readl_relaxed(cdns_ctrl->reg + SKIP_BYTES_CONF);
+	reg &= ~SKIP_BYTES_NUM_OF_BYTES;
+	reg |= FIELD_PREP(SKIP_BYTES_NUM_OF_BYTES,
+			  num_of_bytes);
+	skip_bytes_offset = FIELD_PREP(SKIP_BYTES_OFFSET_VALUE,
+				       offset_value);
+
+	writel_relaxed(reg, cdns_ctrl->reg + SKIP_BYTES_CONF);
+	writel_relaxed(skip_bytes_offset, cdns_ctrl->reg + SKIP_BYTES_OFFSET);
+
+	return 0;
+}
+
+/* Functions enables/disables hardware detection of erased data */
+static void cadence_nand_set_erase_detection(struct cdns_nand_ctrl *cdns_ctrl,
+					     bool enable,
+					     u8 bitflips_threshold)
+{
+	u32 reg;
+
+	reg = readl_relaxed(cdns_ctrl->reg + ECC_CONFIG_0);
+
+	if (enable)
+		reg |= ECC_CONFIG_0_ERASE_DET_EN;
+	else
+		reg &= ~ECC_CONFIG_0_ERASE_DET_EN;
+
+	writel_relaxed(reg, cdns_ctrl->reg + ECC_CONFIG_0);
+	writel_relaxed(bitflips_threshold, cdns_ctrl->reg + ECC_CONFIG_1);
+}
+
+static int cadence_nand_set_access_width16(struct cdns_nand_ctrl *cdns_ctrl,
+					   bool bit_bus16)
+{
+	u32 reg;
+
+	if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					1000000,
+					CTRL_STATUS_CTRL_BUSY, true))
+		return -ETIMEDOUT;
+
+	reg = readl_relaxed(cdns_ctrl->reg + COMMON_SET);
+
+	if (!bit_bus16)
+		reg &= ~COMMON_SET_DEVICE_16BIT;
+	else
+		reg |= COMMON_SET_DEVICE_16BIT;
+	writel_relaxed(reg, cdns_ctrl->reg + COMMON_SET);
+
+	return 0;
+}
+
+static void
+cadence_nand_clear_interrupt(struct cdns_nand_ctrl *cdns_ctrl,
+			     struct cadence_nand_irq_status *irq_status)
+{
+	writel_relaxed(irq_status->status, cdns_ctrl->reg + INTR_STATUS);
+	writel_relaxed(irq_status->trd_status,
+		       cdns_ctrl->reg + TRD_COMP_INT_STATUS);
+	writel_relaxed(irq_status->trd_error,
+		       cdns_ctrl->reg + TRD_ERR_INT_STATUS);
+}
+
+static void
+cadence_nand_read_int_status(struct cdns_nand_ctrl *cdns_ctrl,
+			     struct cadence_nand_irq_status *irq_status)
+{
+	irq_status->status = readl_relaxed(cdns_ctrl->reg + INTR_STATUS);
+	irq_status->trd_status = readl_relaxed(cdns_ctrl->reg
+					       + TRD_COMP_INT_STATUS);
+	irq_status->trd_error = readl_relaxed(cdns_ctrl->reg
+					      + TRD_ERR_INT_STATUS);
+}
+
+static u32 irq_detected(struct cdns_nand_ctrl *cdns_ctrl,
+			struct cadence_nand_irq_status *irq_status)
+{
+	cadence_nand_read_int_status(cdns_ctrl, irq_status);
+
+	return irq_status->status || irq_status->trd_status ||
+		irq_status->trd_error;
+}
+
+static void cadence_nand_reset_irq(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cdns_ctrl->irq_lock, flags);
+	memset(&cdns_ctrl->irq_status, 0, sizeof(cdns_ctrl->irq_status));
+	memset(&cdns_ctrl->irq_mask, 0, sizeof(cdns_ctrl->irq_mask));
+	spin_unlock_irqrestore(&cdns_ctrl->irq_lock, flags);
+}
+
+/*
+ * This is the interrupt service routine. It handles all interrupts
+ * sent to this device.
+ */
+static irqreturn_t cadence_nand_isr(int irq, void *dev_id)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = dev_id;
+	struct cadence_nand_irq_status irq_status;
+	irqreturn_t result = IRQ_NONE;
+
+	spin_lock(&cdns_ctrl->irq_lock);
+
+	if (irq_detected(cdns_ctrl, &irq_status)) {
+		/* Handle interrupt. */
+		/* First acknowledge it. */
+		cadence_nand_clear_interrupt(cdns_ctrl, &irq_status);
+		/* Status in the device context for someone to read. */
+		cdns_ctrl->irq_status.status |= irq_status.status;
+		cdns_ctrl->irq_status.trd_status |= irq_status.trd_status;
+		cdns_ctrl->irq_status.trd_error |= irq_status.trd_error;
+		/* Notify anyone who cares that it happened. */
+		complete(&cdns_ctrl->complete);
+		/* Tell the OS that we've handled this. */
+		result = IRQ_HANDLED;
+	}
+	spin_unlock(&cdns_ctrl->irq_lock);
+
+	return result;
+}
+
+static void cadence_nand_set_irq_mask(struct cdns_nand_ctrl *cdns_ctrl,
+				      struct cadence_nand_irq_status *irq_mask)
+{
+	writel_relaxed(INTR_ENABLE_INTR_EN | irq_mask->status,
+		       cdns_ctrl->reg + INTR_ENABLE);
+
+	writel_relaxed(irq_mask->trd_error,
+		       cdns_ctrl->reg + TRD_ERR_INT_STATUS_EN);
+}
+
+static void
+cadence_nand_wait_for_irq(struct cdns_nand_ctrl *cdns_ctrl,
+			  struct cadence_nand_irq_status *irq_mask,
+			  struct cadence_nand_irq_status *irq_status)
+{
+	unsigned long timeout = msecs_to_jiffies(10000);
+	unsigned long time_left;
+
+	time_left = wait_for_completion_timeout(&cdns_ctrl->complete,
+						timeout);
+
+	*irq_status = cdns_ctrl->irq_status;
+	if (time_left == 0) {
+		/* Timeout error. */
+		dev_err(cdns_ctrl->dev, "timeout occurred:\n");
+		dev_err(cdns_ctrl->dev, "\tstatus = 0x%x, mask = 0x%x\n",
+			irq_status->status, irq_mask->status);
+		dev_err(cdns_ctrl->dev,
+			"\ttrd_status = 0x%x, trd_status mask = 0x%x\n",
+			irq_status->trd_status, irq_mask->trd_status);
+		dev_err(cdns_ctrl->dev,
+			"\t trd_error = 0x%x, trd_error mask = 0x%x\n",
+			irq_status->trd_error, irq_mask->trd_error);
+	}
+}
+
+/* Execute generic command on NAND controller. */
+static int cadence_nand_generic_cmd_send(struct cdns_nand_ctrl *cdns_ctrl,
+					 u8 chip_nr,
+					 u64 mini_ctrl_cmd)
+{
+	u32 mini_ctrl_cmd_l, mini_ctrl_cmd_h, reg;
+
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_CS, chip_nr);
+	mini_ctrl_cmd_l = mini_ctrl_cmd & 0xFFFFFFFF;
+	mini_ctrl_cmd_h = mini_ctrl_cmd >> 32;
+
+	if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					1000000,
+					CTRL_STATUS_CTRL_BUSY, true))
+		return -ETIMEDOUT;
+
+	cadence_nand_reset_irq(cdns_ctrl);
+
+	writel_relaxed(mini_ctrl_cmd_l, cdns_ctrl->reg + CMD_REG2);
+	writel_relaxed(mini_ctrl_cmd_h, cdns_ctrl->reg + CMD_REG3);
+
+	/* Select generic command. */
+	reg = FIELD_PREP(CMD_REG0_CT, CMD_REG0_CT_GEN);
+	/* Thread number. */
+	reg |= FIELD_PREP(CMD_REG0_TN, 0);
+
+	/* Issue command. */
+	writel_relaxed(reg, cdns_ctrl->reg + CMD_REG0);
+
+	return 0;
+}
+
+/* Wait for data on slave DMA interface. */
+static int cadence_nand_wait_on_sdma(struct cdns_nand_ctrl *cdns_ctrl,
+				     u8 *out_sdma_trd,
+				     u32 *out_sdma_size)
+{
+	struct cadence_nand_irq_status irq_mask, irq_status;
+
+	irq_mask.trd_status = 0;
+	irq_mask.trd_error = 0;
+	irq_mask.status = INTR_STATUS_SDMA_TRIGG
+		| INTR_STATUS_SDMA_ERR
+		| INTR_STATUS_UNSUPP_CMD;
+
+	cadence_nand_set_irq_mask(cdns_ctrl, &irq_mask);
+	cadence_nand_wait_for_irq(cdns_ctrl, &irq_mask, &irq_status);
+	if (irq_status.status == 0) {
+		dev_err(cdns_ctrl->dev, "Timeout while waiting for SDMA\n");
+		return -ETIMEDOUT;
+	}
+
+	if (irq_status.status & INTR_STATUS_SDMA_TRIGG) {
+		*out_sdma_size = readl_relaxed(cdns_ctrl->reg + SDMA_SIZE);
+		*out_sdma_trd  = readl_relaxed(cdns_ctrl->reg + SDMA_TRD_NUM);
+		*out_sdma_trd =
+			FIELD_GET(SDMA_TRD_NUM_SDMA_TRD, *out_sdma_trd);
+	} else {
+		dev_err(cdns_ctrl->dev, "SDMA error - irq_status %x\n",
+			irq_status.status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static void cadence_nand_get_caps(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	u32  reg;
+
+	reg = readl_relaxed(cdns_ctrl->reg + CTRL_FEATURES);
+
+	cdns_ctrl->caps2.max_banks = 1 << FIELD_GET(CTRL_FEATURES_N_BANKS, reg);
+
+	if (FIELD_GET(CTRL_FEATURES_DMA_DWITH64, reg))
+		cdns_ctrl->caps2.data_dma_width = 8;
+	else
+		cdns_ctrl->caps2.data_dma_width = 4;
+
+	if (reg & CTRL_FEATURES_CONTROL_DATA)
+		cdns_ctrl->caps2.data_control_supp = true;
+
+	if (reg & (CTRL_FEATURES_NVDDR_2_3
+		   | CTRL_FEATURES_NVDDR))
+		cdns_ctrl->caps2.is_phy_type_dll = true;
+}
+
+/* Prepare CDMA descriptor. */
+static void
+cadence_nand_cdma_desc_prepare(struct cdns_nand_ctrl *cdns_ctrl,
+			       char nf_mem, u32 flash_ptr, char *mem_ptr,
+			       char *ctrl_data_ptr, u16 ctype)
+{
+	struct cadence_nand_cdma_desc *cdma_desc = cdns_ctrl->cdma_desc;
+
+	memset(cdma_desc, 0, sizeof(struct cadence_nand_cdma_desc));
+
+	/* Set fields for one descriptor. */
+	cdma_desc->flash_pointer = flash_ptr;
+	if (cdns_ctrl->ctrl_rev >= 13)
+		cdma_desc->bank = nf_mem;
+	else
+		cdma_desc->flash_pointer |= (nf_mem << CDMA_CFPTR_MEM_SHIFT);
+
+	cdma_desc->command_flags |= CDMA_CF_DMA_MASTER;
+	cdma_desc->command_flags  |= CDMA_CF_INT;
+
+	cdma_desc->memory_pointer = (uintptr_t)mem_ptr;
+	cdma_desc->status = 0;
+	cdma_desc->sync_flag_pointer = 0;
+	cdma_desc->sync_arguments = 0;
+
+	cdma_desc->command_type = ctype;
+	cdma_desc->ctrl_data_ptr = (uintptr_t)ctrl_data_ptr;
+}
+
+static u8 cadence_nand_check_desc_error(struct cdns_nand_ctrl *cdns_ctrl,
+					u32 desc_status)
+{
+	if (desc_status & CDMA_CS_ERP)
+		return STAT_ERASED;
+
+	if (desc_status & CDMA_CS_UNCE)
+		return STAT_ECC_UNCORR;
+
+	if (desc_status & CDMA_CS_ERR) {
+		dev_err(cdns_ctrl->dev, ":CDMA desc error flag detected.\n");
+		return STAT_FAIL;
+	}
+
+	if (FIELD_GET(CDMA_CS_MAXERR, desc_status))
+		return STAT_ECC_CORR;
+
+	return STAT_FAIL;
+}
+
+static int cadence_nand_cdma_finish(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	struct cadence_nand_cdma_desc *desc_ptr = cdns_ctrl->cdma_desc;
+	u8 status = STAT_BUSY;
+
+	if (desc_ptr->status & CDMA_CS_FAIL) {
+		status = cadence_nand_check_desc_error(cdns_ctrl,
+						       desc_ptr->status);
+		dev_err(cdns_ctrl->dev, ":CDMA error %x\n", desc_ptr->status);
+	} else if (desc_ptr->status & CDMA_CS_COMP) {
+		/* Descriptor finished with no errors. */
+		if (desc_ptr->command_flags & CDMA_CF_CONT) {
+			dev_info(cdns_ctrl->dev, "DMA unsupported flag is set");
+			status = STAT_UNKNOWN;
+		} else {
+			/* Last descriptor.  */
+			status = STAT_OK;
+		}
+	}
+
+	return status;
+}
+
+static int cadence_nand_cdma_send(struct cdns_nand_ctrl *cdns_ctrl,
+				  u8 thread)
+{
+	u32 reg;
+	int status;
+
+	/* Wait for thread ready. */
+	status = cadence_nand_wait_for_value(cdns_ctrl, TRD_STATUS,
+					     1000000,
+					     BIT(thread), true);
+	if (status)
+		return status;
+
+	cadence_nand_reset_irq(cdns_ctrl);
+
+	writel_relaxed((u32)cdns_ctrl->dma_cdma_desc,
+		       cdns_ctrl->reg + CMD_REG2);
+	writel_relaxed(0, cdns_ctrl->reg + CMD_REG3);
+
+	/* Select CDMA mode. */
+	reg = FIELD_PREP(CMD_REG0_CT, CMD_REG0_CT_CDMA);
+	/* Thread number. */
+	reg |= FIELD_PREP(CMD_REG0_TN, thread);
+	/* Issue command. */
+	writel_relaxed(reg, cdns_ctrl->reg + CMD_REG0);
+
+	return 0;
+}
+
+/* Send SDMA command and wait for finish. */
+static u32
+cadence_nand_cdma_send_and_wait(struct cdns_nand_ctrl *cdns_ctrl,
+				u8 thread)
+{
+	struct cadence_nand_irq_status irq_mask, irq_status = {0};
+	int status;
+
+	irq_mask.trd_status = BIT(thread);
+	irq_mask.trd_error = BIT(thread);
+	irq_mask.status = INTR_STATUS_CDMA_TERR;
+
+	cadence_nand_set_irq_mask(cdns_ctrl, &irq_mask);
+
+	status = cadence_nand_cdma_send(cdns_ctrl, thread);
+	if (status)
+		return status;
+
+	cadence_nand_wait_for_irq(cdns_ctrl, &irq_mask, &irq_status);
+
+	if (irq_status.status == 0 && irq_status.trd_status == 0 &&
+	    irq_status.trd_error == 0) {
+		dev_err(cdns_ctrl->dev, "CDMA command timeout\n");
+		return -ETIMEDOUT;
+	}
+	if (irq_status.status & irq_mask.status) {
+		dev_err(cdns_ctrl->dev, "CDMA command failed\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/*
+ * ECC size depends on configured ECC strength and on maximum supported
+ * ECC step size.
+ */
+static int cadence_nand_calc_ecc_bytes(int max_step_size, int strength)
+{
+	int nbytes = DIV_ROUND_UP(fls(8 * max_step_size) * strength, 8);
+
+	return ALIGN(nbytes, 2);
+}
+
+#define CADENCE_NAND_CALC_ECC_BYTES(max_step_size) \
+	static int \
+	cadence_nand_calc_ecc_bytes_##max_step_size(int step_size, \
+						    int strength)\
+	{\
+		return cadence_nand_calc_ecc_bytes(max_step_size, strength);\
+	}
+
+CADENCE_NAND_CALC_ECC_BYTES(256)
+CADENCE_NAND_CALC_ECC_BYTES(512)
+CADENCE_NAND_CALC_ECC_BYTES(1024)
+CADENCE_NAND_CALC_ECC_BYTES(2048)
+CADENCE_NAND_CALC_ECC_BYTES(4096)
+
+/* Function reads BCH capabilities. */
+static int cadence_nand_read_bch_caps(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	struct nand_ecc_caps *ecc_caps = &cdns_ctrl->ecc_caps;
+	int max_step_size = 0, nstrengths, i;
+	u32 reg;
+
+	reg = readl_relaxed(cdns_ctrl->reg + BCH_CFG_0);
+	cdns_ctrl->ecc_strengths[0] = FIELD_GET(BCH_CFG_0_CORR_CAP_0, reg);
+	cdns_ctrl->ecc_strengths[1] = FIELD_GET(BCH_CFG_0_CORR_CAP_1, reg);
+	cdns_ctrl->ecc_strengths[2] = FIELD_GET(BCH_CFG_0_CORR_CAP_2, reg);
+	cdns_ctrl->ecc_strengths[3] = FIELD_GET(BCH_CFG_0_CORR_CAP_3, reg);
+
+	reg = readl_relaxed(cdns_ctrl->reg + BCH_CFG_1);
+	cdns_ctrl->ecc_strengths[4] = FIELD_GET(BCH_CFG_1_CORR_CAP_4, reg);
+	cdns_ctrl->ecc_strengths[5] = FIELD_GET(BCH_CFG_1_CORR_CAP_5, reg);
+	cdns_ctrl->ecc_strengths[6] = FIELD_GET(BCH_CFG_1_CORR_CAP_6, reg);
+	cdns_ctrl->ecc_strengths[7] = FIELD_GET(BCH_CFG_1_CORR_CAP_7, reg);
+
+	reg = readl_relaxed(cdns_ctrl->reg + BCH_CFG_2);
+	cdns_ctrl->ecc_stepinfos[0].stepsize =
+		FIELD_GET(BCH_CFG_2_SECT_0, reg);
+
+	cdns_ctrl->ecc_stepinfos[1].stepsize =
+		FIELD_GET(BCH_CFG_2_SECT_1, reg);
+
+	nstrengths = 0;
+	for (i = 0; i < BCH_MAX_NUM_CORR_CAPS; i++) {
+		if (cdns_ctrl->ecc_strengths[i] != 0)
+			nstrengths++;
+	}
+
+	ecc_caps->nstepinfos = 0;
+	for (i = 0; i < BCH_MAX_NUM_SECTOR_SIZES; i++) {
+		/* ECC strengths are common for all step infos. */
+		cdns_ctrl->ecc_stepinfos[i].nstrengths = nstrengths;
+		cdns_ctrl->ecc_stepinfos[i].strengths =
+			cdns_ctrl->ecc_strengths;
+
+		if (cdns_ctrl->ecc_stepinfos[i].stepsize != 0)
+			ecc_caps->nstepinfos++;
+
+		if (cdns_ctrl->ecc_stepinfos[i].stepsize > max_step_size)
+			max_step_size = cdns_ctrl->ecc_stepinfos[i].stepsize;
+	}
+	ecc_caps->stepinfos = &cdns_ctrl->ecc_stepinfos[0];
+
+	switch (max_step_size) {
+	case 256:
+		ecc_caps->calc_ecc_bytes = &cadence_nand_calc_ecc_bytes_256;
+		break;
+	case 512:
+		ecc_caps->calc_ecc_bytes = &cadence_nand_calc_ecc_bytes_512;
+		break;
+	case 1024:
+		ecc_caps->calc_ecc_bytes = &cadence_nand_calc_ecc_bytes_1024;
+		break;
+	case 2048:
+		ecc_caps->calc_ecc_bytes = &cadence_nand_calc_ecc_bytes_2048;
+		break;
+	case 4096:
+		ecc_caps->calc_ecc_bytes = &cadence_nand_calc_ecc_bytes_4096;
+		break;
+	default:
+		dev_err(cdns_ctrl->dev,
+			"Unsupported sector size(ecc step size) %d\n",
+			max_step_size);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/* Hardware initialization. */
+static int cadence_nand_hw_init(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	int status;
+	u32 reg;
+
+	status = cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					     1000000,
+					     CTRL_STATUS_INIT_COMP, false);
+	if (status)
+		return status;
+
+	reg = readl_relaxed(cdns_ctrl->reg + CTRL_VERSION);
+	cdns_ctrl->ctrl_rev = FIELD_GET(CTRL_VERSION_REV, reg);
+
+	dev_info(cdns_ctrl->dev,
+		 "%s: cadence nand controller version reg %x\n",
+		 __func__, reg);
+
+	/* Disable cache and multiplane. */
+	writel_relaxed(0, cdns_ctrl->reg + MULTIPLANE_CFG);
+	writel_relaxed(0, cdns_ctrl->reg + CACHE_CFG);
+
+	/* Clear all interrupts. */
+	writel_relaxed(0xFFFFFFFF, cdns_ctrl->reg + INTR_STATUS);
+
+	cadence_nand_get_caps(cdns_ctrl);
+	cadence_nand_read_bch_caps(cdns_ctrl);
+
+	/*
+	 * Set IO width access to 8.
+	 * It is because during SW device discovering width access
+	 * is expected to be 8.
+	 */
+	status = cadence_nand_set_access_width16(cdns_ctrl, false);
+
+	return status;
+}
+
+#define TT_MAIN_OOB_AREAS	2
+#define TT_RAW_PAGE		3
+#define TT_BBM			4
+#define TT_MAIN_OOB_AREA_EXT	5
+
+/* Prepare size of data to transfer. */
+static void
+cadence_nand_prepare_data_size(struct nand_chip *chip,
+			       int transfer_type)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	u32 sec_size = 0, offset = 0, sec_cnt = 1;
+	u32 last_sec_size = cdns_chip->sector_size;
+	u32 data_ctrl_size = 0;
+	u32 reg = 0;
+
+	if (cdns_ctrl->curr_trans_type == transfer_type)
+		return;
+
+	switch (transfer_type) {
+	case TT_MAIN_OOB_AREA_EXT:
+		sec_cnt = cdns_chip->sector_count;
+		sec_size = cdns_chip->sector_size;
+		data_ctrl_size = cdns_chip->avail_oob_size;
+		break;
+	case TT_MAIN_OOB_AREAS:
+		sec_cnt = cdns_chip->sector_count;
+		last_sec_size = cdns_chip->sector_size
+			+ cdns_chip->avail_oob_size;
+		sec_size = cdns_chip->sector_size;
+		break;
+	case TT_RAW_PAGE:
+		last_sec_size = mtd->writesize + mtd->oobsize;
+		break;
+	case TT_BBM:
+		offset = mtd->writesize + cdns_chip->bbm_offs;
+		last_sec_size = 8;
+		break;
+	}
+
+	reg = 0;
+	reg |= FIELD_PREP(TRAN_CFG_0_OFFSET, offset);
+	reg |= FIELD_PREP(TRAN_CFG_0_SEC_CNT, sec_cnt);
+	writel_relaxed(reg, cdns_ctrl->reg + TRAN_CFG_0);
+
+	reg = 0;
+	reg |= FIELD_PREP(TRAN_CFG_1_LAST_SEC_SIZE, last_sec_size);
+	reg |= FIELD_PREP(TRAN_CFG_1_SECTOR_SIZE, sec_size);
+	writel_relaxed(reg, cdns_ctrl->reg + TRAN_CFG_1);
+
+	if (cdns_ctrl->caps2.data_control_supp) {
+		reg = readl_relaxed(cdns_ctrl->reg + CONTROL_DATA_CTRL);
+		reg &= ~CONTROL_DATA_CTRL_SIZE;
+		reg |= FIELD_PREP(CONTROL_DATA_CTRL_SIZE, data_ctrl_size);
+		writel_relaxed(reg, cdns_ctrl->reg + CONTROL_DATA_CTRL);
+	}
+
+	cdns_ctrl->curr_trans_type = transfer_type;
+}
+
+static int
+cadence_nand_cdma_transfer(struct cdns_nand_ctrl *cdns_ctrl, u8 chip_nr,
+			   int page, void *buf, void *ctrl_dat, u32 buf_size,
+			   u32 ctrl_dat_size, enum dma_data_direction dir,
+			   bool with_ecc)
+{
+	dma_addr_t dma_buf, dma_ctrl_dat = 0;
+	u8 thread_nr = chip_nr;
+	int status;
+	u16 ctype;
+
+	if (dir == DMA_FROM_DEVICE)
+		ctype = CDMA_CT_RD;
+	else
+		ctype = CDMA_CT_WR;
+
+	cadence_nand_set_ecc_enable(cdns_ctrl, with_ecc);
+
+	dma_buf = dma_map_single(cdns_ctrl->dev, buf, buf_size, dir);
+	if (dma_mapping_error(cdns_ctrl->dev, dma_buf)) {
+		dev_err(cdns_ctrl->dev, "Failed to map DMA buffer\n");
+		return -EIO;
+	}
+
+	if (ctrl_dat && ctrl_dat_size) {
+		dma_ctrl_dat = dma_map_single(cdns_ctrl->dev, ctrl_dat,
+					      ctrl_dat_size, dir);
+		if (dma_mapping_error(cdns_ctrl->dev, dma_ctrl_dat)) {
+			dma_unmap_single(cdns_ctrl->dev, dma_buf,
+					 buf_size, dir);
+			dev_err(cdns_ctrl->dev, "Failed to map DMA buffer\n");
+			return -EIO;
+		}
+	}
+
+	cadence_nand_cdma_desc_prepare(cdns_ctrl, chip_nr, page,
+				       (void *)dma_buf, (void *)dma_ctrl_dat,
+				       ctype);
+
+	status = cadence_nand_cdma_send_and_wait(cdns_ctrl, thread_nr);
+
+	dma_unmap_single(cdns_ctrl->dev, dma_buf,
+			 buf_size, dir);
+
+	if (ctrl_dat && ctrl_dat_size)
+		dma_unmap_single(cdns_ctrl->dev, dma_ctrl_dat,
+				 ctrl_dat_size, dir);
+	if (status)
+		return status;
+
+	return cadence_nand_cdma_finish(cdns_ctrl);
+}
+
+static void cadence_nand_set_timings(struct cdns_nand_ctrl *cdns_ctrl,
+				     struct cadence_nand_timings *t)
+{
+	writel_relaxed(t->async_toggle_timings,
+		       cdns_ctrl->reg + ASYNC_TOGGLE_TIMINGS);
+	writel_relaxed(t->timings0, cdns_ctrl->reg + TIMINGS0);
+	writel_relaxed(t->timings1, cdns_ctrl->reg + TIMINGS1);
+	writel_relaxed(t->timings2, cdns_ctrl->reg + TIMINGS2);
+
+	if (cdns_ctrl->caps2.is_phy_type_dll)
+		writel_relaxed(t->dll_phy_ctrl, cdns_ctrl->reg + DLL_PHY_CTRL);
+
+	writel_relaxed(t->phy_ctrl, cdns_ctrl->reg + PHY_CTRL);
+
+	if (cdns_ctrl->caps2.is_phy_type_dll) {
+		writel_relaxed(0, cdns_ctrl->reg + PHY_TSEL);
+		writel_relaxed(2, cdns_ctrl->reg + PHY_DQ_TIMING);
+		writel_relaxed(t->phy_dqs_timing,
+			       cdns_ctrl->reg + PHY_DQS_TIMING);
+		writel_relaxed(t->phy_gate_lpbk_ctrl,
+			       cdns_ctrl->reg + PHY_GATE_LPBK_CTRL);
+		writel_relaxed(PHY_DLL_MASTER_CTRL_BYPASS_MODE,
+			       cdns_ctrl->reg + PHY_DLL_MASTER_CTRL);
+		writel_relaxed(0, cdns_ctrl->reg + PHY_DLL_SLAVE_CTRL);
+	}
+}
+
+static int cadence_nand_select_target(struct nand_chip *chip)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+
+	if (chip == cdns_ctrl->selected_chip)
+		return 0;
+
+	if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					1000000,
+					CTRL_STATUS_CTRL_BUSY, true))
+		return -ETIMEDOUT;
+
+	cadence_nand_set_timings(cdns_ctrl, &cdns_chip->timings);
+
+	cadence_nand_set_ecc_strength(cdns_ctrl,
+				      cdns_chip->corr_str_idx);
+
+	cadence_nand_set_erase_detection(cdns_ctrl, true,
+					 chip->ecc.strength);
+
+	cdns_ctrl->curr_trans_type = -1;
+	cdns_ctrl->selected_chip = chip;
+
+	return 0;
+}
+
+static int cadence_nand_erase(struct nand_chip *chip, u32 page)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	int status;
+	u8 thread_nr = cdns_chip->cs[chip->cur_cs];
+
+	cadence_nand_cdma_desc_prepare(cdns_ctrl,
+				       cdns_chip->cs[chip->cur_cs],
+				       page, NULL, NULL,
+				       CDMA_CT_ERASE);
+	status = cadence_nand_cdma_send_and_wait(cdns_ctrl, thread_nr);
+	if (status) {
+		dev_err(cdns_ctrl->dev, "erase operation failed\n");
+		return -EIO;
+	}
+
+	status = cadence_nand_cdma_finish(cdns_ctrl);
+	if (status)
+		return status;
+
+	return 0;
+}
+
+static int cadence_nand_read_bbm(struct nand_chip *chip, int page, u8 *buf)
+{
+	int status;
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	cadence_nand_prepare_data_size(chip, TT_BBM);
+
+	cadence_nand_set_skip_bytes_conf(cdns_ctrl, 0, 0, 0);
+
+	/*
+	 * Read only bad block marker from offset
+	 * defined by a memory manufacturer.
+	 */
+	status = cadence_nand_cdma_transfer(cdns_ctrl,
+					    cdns_chip->cs[chip->cur_cs],
+					    page, cdns_ctrl->buf, NULL,
+					    mtd->oobsize,
+					    0, DMA_FROM_DEVICE, false);
+	if (status) {
+		dev_err(cdns_ctrl->dev, "read BBM failed\n");
+		return -EIO;
+	}
+
+	memcpy(buf + cdns_chip->bbm_offs, cdns_ctrl->buf, cdns_chip->bbm_len);
+
+	return 0;
+}
+
+static int cadence_nand_write_page(struct nand_chip *chip,
+				   const u8 *buf, int oob_required,
+				   int page)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int status;
+	u16 marker_val = 0xFFFF;
+
+	status = cadence_nand_select_target(chip);
+	if (status)
+		return status;
+
+	cadence_nand_set_skip_bytes_conf(cdns_ctrl, cdns_chip->bbm_len,
+					 mtd->writesize
+					 + cdns_chip->bbm_offs,
+					 1);
+
+	if (oob_required) {
+		marker_val = *(u16 *)(chip->oob_poi
+				      + cdns_chip->bbm_offs);
+	} else {
+		/* Set oob data to 0xFF. */
+		memset(cdns_ctrl->buf + mtd->writesize, 0xFF,
+		       cdns_chip->avail_oob_size);
+	}
+
+	cadence_nand_set_skip_marker_val(cdns_ctrl, marker_val);
+
+	cadence_nand_prepare_data_size(chip, TT_MAIN_OOB_AREA_EXT);
+
+	if (cadence_nand_dma_buf_ok(cdns_ctrl, buf, mtd->writesize) &&
+	    cdns_ctrl->caps2.data_control_supp) {
+		u8 *oob;
+
+		if (oob_required)
+			oob = chip->oob_poi;
+		else
+			oob = cdns_ctrl->buf + mtd->writesize;
+
+		status = cadence_nand_cdma_transfer(cdns_ctrl,
+						    cdns_chip->cs[chip->cur_cs],
+						    page, (void *)buf, oob,
+						    mtd->writesize,
+						    cdns_chip->avail_oob_size,
+						    DMA_TO_DEVICE, true);
+		if (status) {
+			dev_err(cdns_ctrl->dev, "write page failed\n");
+			return -EIO;
+		}
+
+		return 0;
+	}
+
+	if (oob_required) {
+		/* Transfer the data to the oob area. */
+		memcpy(cdns_ctrl->buf + mtd->writesize, chip->oob_poi,
+		       cdns_chip->avail_oob_size);
+	}
+
+	memcpy(cdns_ctrl->buf, buf, mtd->writesize);
+
+	cadence_nand_prepare_data_size(chip, TT_MAIN_OOB_AREAS);
+
+	return cadence_nand_cdma_transfer(cdns_ctrl,
+					  cdns_chip->cs[chip->cur_cs],
+					  page, cdns_ctrl->buf, NULL,
+					  mtd->writesize
+					  + cdns_chip->avail_oob_size,
+					  0, DMA_TO_DEVICE, true);
+}
+
+static int cadence_nand_write_oob(struct nand_chip *chip, int page)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	memset(cdns_ctrl->buf, 0xFF, mtd->writesize);
+
+	return cadence_nand_write_page(chip, cdns_ctrl->buf, 1, page);
+}
+
+static int cadence_nand_write_page_raw(struct nand_chip *chip,
+				       const u8 *buf, int oob_required,
+				       int page)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int writesize = mtd->writesize;
+	int oobsize = mtd->oobsize;
+	int ecc_steps = chip->ecc.steps;
+	int ecc_size = chip->ecc.size;
+	int ecc_bytes = chip->ecc.bytes;
+	void *tmp_buf = cdns_ctrl->buf;
+	int oob_skip = cdns_chip->bbm_len;
+	size_t size = writesize + oobsize;
+	int i, pos, len;
+	int status = 0;
+
+	status = cadence_nand_select_target(chip);
+	if (status)
+		return status;
+
+	/*
+	 * Fill the buffer with 0xff first except the full page transfer.
+	 * This simplifies the logic.
+	 */
+	if (!buf || !oob_required)
+		memset(tmp_buf, 0xff, size);
+
+	cadence_nand_set_skip_bytes_conf(cdns_ctrl, 0, 0, 0);
+
+	/* Arrange the buffer for syndrome payload/ecc layout. */
+	if (buf) {
+		for (i = 0; i < ecc_steps; i++) {
+			pos = i * (ecc_size + ecc_bytes);
+			len = ecc_size;
+
+			if (pos >= writesize)
+				pos += oob_skip;
+			else if (pos + len > writesize)
+				len = writesize - pos;
+
+			memcpy(tmp_buf + pos, buf, len);
+			buf += len;
+			if (len < ecc_size) {
+				len = ecc_size - len;
+				memcpy(tmp_buf + writesize + oob_skip, buf,
+				       len);
+				buf += len;
+			}
+		}
+	}
+
+	if (oob_required) {
+		const u8 *oob = chip->oob_poi;
+		u32 oob_data_offset = (cdns_chip->sector_count - 1) *
+			(cdns_chip->sector_size + chip->ecc.bytes)
+			+ cdns_chip->sector_size + oob_skip;
+
+		/* BBM at the beginning of the OOB area. */
+		memcpy(tmp_buf + writesize, oob, oob_skip);
+
+		/* OOB free. */
+		memcpy(tmp_buf + oob_data_offset, oob,
+		       cdns_chip->avail_oob_size);
+		oob += cdns_chip->avail_oob_size;
+
+		/* OOB ECC. */
+		for (i = 0; i < ecc_steps; i++) {
+			pos = ecc_size + i * (ecc_size + ecc_bytes);
+			if (i == (ecc_steps - 1))
+				pos += cdns_chip->avail_oob_size;
+
+			len = ecc_bytes;
+
+			if (pos >= writesize)
+				pos += oob_skip;
+			else if (pos + len > writesize)
+				len = writesize - pos;
+
+			memcpy(tmp_buf + pos, oob, len);
+			oob += len;
+			if (len < ecc_bytes) {
+				len = ecc_bytes - len;
+				memcpy(tmp_buf + writesize + oob_skip, oob,
+				       len);
+				oob += len;
+			}
+		}
+	}
+
+	cadence_nand_prepare_data_size(chip, TT_RAW_PAGE);
+
+	return cadence_nand_cdma_transfer(cdns_ctrl,
+					  cdns_chip->cs[chip->cur_cs],
+					  page, cdns_ctrl->buf, NULL,
+					  mtd->writesize +
+					  mtd->oobsize,
+					  0, DMA_TO_DEVICE, false);
+}
+
+static int cadence_nand_write_oob_raw(struct nand_chip *chip,
+				      int page)
+{
+	return cadence_nand_write_page_raw(chip, NULL, true, page);
+}
+
+static int cadence_nand_read_page(struct nand_chip *chip,
+				  u8 *buf, int oob_required, int page)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int status = 0;
+	int ecc_err_count = 0;
+
+	status = cadence_nand_select_target(chip);
+	if (status)
+		return status;
+
+	cadence_nand_set_skip_bytes_conf(cdns_ctrl, cdns_chip->bbm_len,
+					 mtd->writesize
+					 + cdns_chip->bbm_offs, 1);
+
+	/*
+	 * If data buffer can be accessed by DMA and data_control feature
+	 * is supported then transfer data and oob directly.
+	 */
+	if (cadence_nand_dma_buf_ok(cdns_ctrl, buf, mtd->writesize) &&
+	    cdns_ctrl->caps2.data_control_supp) {
+		u8 *oob;
+
+		if (oob_required)
+			oob = chip->oob_poi;
+		else
+			oob = cdns_ctrl->buf + mtd->writesize;
+
+		cadence_nand_prepare_data_size(chip, TT_MAIN_OOB_AREA_EXT);
+		status = cadence_nand_cdma_transfer(cdns_ctrl,
+						    cdns_chip->cs[chip->cur_cs],
+						    page, buf, oob,
+						    mtd->writesize,
+						    cdns_chip->avail_oob_size,
+						    DMA_FROM_DEVICE, true);
+	/* Otherwise use bounce buffer. */
+	} else {
+		cadence_nand_prepare_data_size(chip, TT_MAIN_OOB_AREAS);
+		status = cadence_nand_cdma_transfer(cdns_ctrl,
+						    cdns_chip->cs[chip->cur_cs],
+						    page, cdns_ctrl->buf,
+						    NULL, mtd->writesize
+						    + cdns_chip->avail_oob_size,
+						    0, DMA_FROM_DEVICE, true);
+
+		memcpy(buf, cdns_ctrl->buf, mtd->writesize);
+		if (oob_required)
+			memcpy(chip->oob_poi,
+			       cdns_ctrl->buf + mtd->writesize,
+			       mtd->oobsize);
+	}
+
+	switch (status) {
+	case STAT_ECC_UNCORR:
+		mtd->ecc_stats.failed++;
+		ecc_err_count++;
+		break;
+	case STAT_ECC_CORR:
+		ecc_err_count = FIELD_GET(CDMA_CS_MAXERR,
+					  cdns_ctrl->cdma_desc->status);
+		mtd->ecc_stats.corrected += ecc_err_count;
+		break;
+	case STAT_ERASED:
+	case STAT_OK:
+		break;
+	default:
+		dev_err(cdns_ctrl->dev, "read page failed\n");
+		return -EIO;
+	}
+
+	if (oob_required)
+		if (cadence_nand_read_bbm(chip, page, chip->oob_poi))
+			return -EIO;
+
+	return ecc_err_count;
+}
+
+/* Reads OOB data from the device. */
+static int cadence_nand_read_oob(struct nand_chip *chip, int page)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+
+	return cadence_nand_read_page(chip, cdns_ctrl->buf, 1, page);
+}
+
+static int cadence_nand_read_page_raw(struct nand_chip *chip,
+				      u8 *buf, int oob_required, int page)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int oob_skip = cdns_chip->bbm_len;
+	int writesize = mtd->writesize;
+	int ecc_steps = chip->ecc.steps;
+	int ecc_size = chip->ecc.size;
+	int ecc_bytes = chip->ecc.bytes;
+	void *tmp_buf = cdns_ctrl->buf;
+	int i, pos, len;
+	int status = 0;
+
+	status = cadence_nand_select_target(chip);
+	if (status)
+		return status;
+
+	cadence_nand_set_skip_bytes_conf(cdns_ctrl, 0, 0, 0);
+
+	cadence_nand_prepare_data_size(chip, TT_RAW_PAGE);
+	status = cadence_nand_cdma_transfer(cdns_ctrl,
+					    cdns_chip->cs[chip->cur_cs],
+					    page, cdns_ctrl->buf, NULL,
+					    mtd->writesize
+					    + mtd->oobsize,
+					    0, DMA_FROM_DEVICE, false);
+
+	switch (status) {
+	case STAT_ERASED:
+	case STAT_OK:
+		break;
+	default:
+		dev_err(cdns_ctrl->dev, "read raw page failed\n");
+		return -EIO;
+	}
+
+	/* Arrange the buffer for syndrome payload/ecc layout. */
+	if (buf) {
+		for (i = 0; i < ecc_steps; i++) {
+			pos = i * (ecc_size + ecc_bytes);
+			len = ecc_size;
+
+			if (pos >= writesize)
+				pos += oob_skip;
+			else if (pos + len > writesize)
+				len = writesize - pos;
+
+			memcpy(buf, tmp_buf + pos, len);
+			buf += len;
+			if (len < ecc_size) {
+				len = ecc_size - len;
+				memcpy(buf, tmp_buf + writesize + oob_skip,
+				       len);
+				buf += len;
+			}
+		}
+	}
+
+	if (oob_required) {
+		u8 *oob = chip->oob_poi;
+		u32 oob_data_offset = (cdns_chip->sector_count - 1) *
+			(cdns_chip->sector_size + chip->ecc.bytes)
+			+ cdns_chip->sector_size + oob_skip;
+
+		/* OOB free. */
+		memcpy(oob, tmp_buf + oob_data_offset,
+		       cdns_chip->avail_oob_size);
+
+		/* BBM at the beginning of the OOB area. */
+		memcpy(oob, tmp_buf + writesize, oob_skip);
+
+		oob += cdns_chip->avail_oob_size;
+
+		/* OOB ECC */
+		for (i = 0; i < ecc_steps; i++) {
+			pos = ecc_size + i * (ecc_size + ecc_bytes);
+			len = ecc_bytes;
+
+			if (i == (ecc_steps - 1))
+				pos += cdns_chip->avail_oob_size;
+
+			if (pos >= writesize)
+				pos += oob_skip;
+			else if (pos + len > writesize)
+				len = writesize - pos;
+
+			memcpy(oob, tmp_buf + pos, len);
+			oob += len;
+			if (len < ecc_bytes) {
+				len = ecc_bytes - len;
+				memcpy(oob, tmp_buf + writesize + oob_skip,
+				       len);
+				oob += len;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int cadence_nand_read_oob_raw(struct nand_chip *chip,
+				     int page)
+{
+	return cadence_nand_read_page_raw(chip, NULL, true, page);
+}
+
+static void cadence_nand_slave_dma_transfer_finished(void *data)
+{
+	struct completion *finished = data;
+
+	complete(finished);
+}
+
+static int cadence_nand_slave_dma_transfer(struct cdns_nand_ctrl *cdns_ctrl,
+					   void *buf,
+					   dma_addr_t dev_dma, size_t len,
+					   enum dma_data_direction dir)
+{
+	DECLARE_COMPLETION_ONSTACK(finished);
+	struct dma_chan *chan;
+	struct dma_device *dma_dev;
+	dma_addr_t src_dma, dst_dma, buf_dma;
+	struct dma_async_tx_descriptor *tx;
+	dma_cookie_t cookie;
+
+	chan = cdns_ctrl->dmac;
+	dma_dev = chan->device;
+
+	buf_dma = dma_map_single(dma_dev->dev, buf, len, dir);
+	if (dma_mapping_error(dma_dev->dev, buf_dma)) {
+		dev_err(cdns_ctrl->dev, "Failed to map DMA buffer\n");
+		goto err;
+	}
+
+	if (dir == DMA_FROM_DEVICE) {
+		src_dma = cdns_ctrl->io.dma;
+		dst_dma = buf_dma;
+	} else {
+		src_dma = buf_dma;
+		dst_dma = cdns_ctrl->io.dma;
+	}
+
+	tx = dmaengine_prep_dma_memcpy(cdns_ctrl->dmac, dst_dma, src_dma, len,
+				       DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
+	if (!tx) {
+		dev_err(cdns_ctrl->dev, "Failed to prepare DMA memcpy\n");
+		goto err_unmap;
+	}
+
+	tx->callback = cadence_nand_slave_dma_transfer_finished;
+	tx->callback_param = &finished;
+
+	cookie = dmaengine_submit(tx);
+	if (dma_submit_error(cookie)) {
+		dev_err(cdns_ctrl->dev, "Failed to do DMA tx_submit\n");
+		goto err_unmap;
+	}
+
+	dma_async_issue_pending(cdns_ctrl->dmac);
+	wait_for_completion(&finished);
+
+	dma_unmap_single(cdns_ctrl->dev, buf_dma, len, dir);
+
+	return 0;
+
+err_unmap:
+	dma_unmap_single(cdns_ctrl->dev, buf_dma, len, dir);
+
+err:
+	dev_dbg(cdns_ctrl->dev, "Fall back to CPU I/O\n");
+
+	return -EIO;
+}
+
+static int cadence_nand_read_buf(struct cdns_nand_ctrl *cdns_ctrl,
+				 u8 *buf, int len)
+{
+	u8 thread_nr = 0;
+	u32 sdma_size;
+	int status;
+
+	/* Wait until slave DMA interface is ready to data transfer. */
+	status = cadence_nand_wait_on_sdma(cdns_ctrl, &thread_nr, &sdma_size);
+	if (status)
+		return status;
+
+	if (!cdns_ctrl->caps1->has_dma) {
+		int len_in_words = len >> 2;
+
+		/* read alingment data */
+		ioread32_rep(cdns_ctrl->io.virt, buf, len_in_words);
+		if (sdma_size > len) {
+			/* read rest data from slave DMA interface if any */
+			ioread32_rep(cdns_ctrl->io.virt, cdns_ctrl->buf,
+				     sdma_size / 4 - len_in_words);
+			/* copy rest of data */
+			memcpy(buf + (len_in_words << 2), cdns_ctrl->buf,
+			       len - (len_in_words << 2));
+		}
+		return 0;
+	}
+
+	if (cadence_nand_dma_buf_ok(cdns_ctrl, buf, len)) {
+		status = cadence_nand_slave_dma_transfer(cdns_ctrl, buf,
+							 cdns_ctrl->io.dma,
+							 len, DMA_FROM_DEVICE);
+		if (status == 0)
+			return 0;
+
+		dev_warn(cdns_ctrl->dev,
+			 "Slave DMA transfer failed. Try again using bounce buffer.");
+	}
+
+	/* If DMA transfer is not possible or failed then use bounce buffer. */
+	status = cadence_nand_slave_dma_transfer(cdns_ctrl, cdns_ctrl->buf,
+						 cdns_ctrl->io.dma,
+						 sdma_size, DMA_FROM_DEVICE);
+
+	if (status) {
+		dev_err(cdns_ctrl->dev, "Slave DMA transfer failed");
+		return status;
+	}
+
+	memcpy(buf, cdns_ctrl->buf, len);
+
+	return 0;
+}
+
+static int cadence_nand_write_buf(struct cdns_nand_ctrl *cdns_ctrl,
+				  const u8 *buf, int len)
+{
+	u8 thread_nr = 0;
+	u32 sdma_size;
+	int status;
+
+	/* Wait until slave DMA interface is ready to data transfer. */
+	status = cadence_nand_wait_on_sdma(cdns_ctrl, &thread_nr, &sdma_size);
+	if (status)
+		return status;
+
+	if (!cdns_ctrl->caps1->has_dma) {
+		int len_in_words = len >> 2;
+
+		iowrite32_rep(cdns_ctrl->io.virt, buf, len_in_words);
+		if (sdma_size > len) {
+			/* copy rest of data */
+			memcpy(cdns_ctrl->buf, buf + (len_in_words << 2),
+			       len - (len_in_words << 2));
+			/* write all expected by nand controller data */
+			iowrite32_rep(cdns_ctrl->io.virt, cdns_ctrl->buf,
+				      sdma_size / 4 - len_in_words);
+		}
+
+		return 0;
+	}
+
+	if (cadence_nand_dma_buf_ok(cdns_ctrl, buf, len)) {
+		status = cadence_nand_slave_dma_transfer(cdns_ctrl, (void *)buf,
+							 cdns_ctrl->io.dma,
+							 len, DMA_TO_DEVICE);
+		if (status == 0)
+			return 0;
+
+		dev_warn(cdns_ctrl->dev,
+			 "Slave DMA transfer failed. Try again using bounce buffer.");
+	}
+
+	/* If DMA transfer is not possible or failed then use bounce buffer. */
+	memcpy(cdns_ctrl->buf, buf, len);
+
+	status = cadence_nand_slave_dma_transfer(cdns_ctrl, cdns_ctrl->buf,
+						 cdns_ctrl->io.dma,
+						 sdma_size, DMA_TO_DEVICE);
+
+	if (status)
+		dev_err(cdns_ctrl->dev, "Slave DMA transfer failed");
+
+	return status;
+}
+
+static int cadence_nand_force_byte_access(struct nand_chip *chip,
+					  bool force_8bit)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	int status;
+
+	/*
+	 * Callers of this function do not verify if the NAND is using a 16-bit
+	 * an 8-bit bus for normal operations, so we need to take care of that
+	 * here by leaving the configuration unchanged if the NAND does not have
+	 * the NAND_BUSWIDTH_16 flag set.
+	 */
+	if (!(chip->options & NAND_BUSWIDTH_16))
+		return 0;
+
+	status = cadence_nand_set_access_width16(cdns_ctrl, !force_8bit);
+
+	return status;
+}
+
+static int cadence_nand_cmd_opcode(struct nand_chip *chip,
+				   const struct nand_subop *subop)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	const struct nand_op_instr *instr;
+	unsigned int op_id = 0;
+	u64 mini_ctrl_cmd = 0;
+	int ret;
+
+	instr = &subop->instrs[op_id];
+
+	if (instr->delay_ns > 0)
+		mini_ctrl_cmd |= GCMD_LAY_TWB;
+
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INSTR,
+				    GCMD_LAY_INSTR_CMD);
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INPUT_CMD,
+				    instr->ctx.cmd.opcode);
+
+	ret = cadence_nand_generic_cmd_send(cdns_ctrl,
+					    cdns_chip->cs[chip->cur_cs],
+					    mini_ctrl_cmd);
+	if (ret)
+		dev_err(cdns_ctrl->dev, "send cmd %x failed\n",
+			instr->ctx.cmd.opcode);
+
+	return ret;
+}
+
+static int cadence_nand_cmd_address(struct nand_chip *chip,
+				    const struct nand_subop *subop)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	const struct nand_op_instr *instr;
+	unsigned int op_id = 0;
+	u64 mini_ctrl_cmd = 0;
+	unsigned int offset, naddrs;
+	u64 address = 0;
+	const u8 *addrs;
+	int ret;
+	int i;
+
+	instr = &subop->instrs[op_id];
+
+	if (instr->delay_ns > 0)
+		mini_ctrl_cmd |= GCMD_LAY_TWB;
+
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INSTR,
+				    GCMD_LAY_INSTR_ADDR);
+
+	offset = nand_subop_get_addr_start_off(subop, op_id);
+	naddrs = nand_subop_get_num_addr_cyc(subop, op_id);
+	addrs = &instr->ctx.addr.addrs[offset];
+
+	for (i = 0; i < naddrs; i++)
+		address |= (u64)addrs[i] << (8 * i);
+
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INPUT_ADDR,
+				    address);
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INPUT_ADDR_SIZE,
+				    naddrs - 1);
+
+	ret = cadence_nand_generic_cmd_send(cdns_ctrl,
+					    cdns_chip->cs[chip->cur_cs],
+					    mini_ctrl_cmd);
+	if (ret)
+		dev_err(cdns_ctrl->dev, "send address %llx failed\n", address);
+
+	return ret;
+}
+
+static int cadence_nand_cmd_erase(struct nand_chip *chip,
+				  const struct nand_subop *subop)
+{
+	unsigned int op_id;
+
+	if (subop->instrs[0].ctx.cmd.opcode == NAND_CMD_ERASE1) {
+		int i;
+		const struct nand_op_instr *instr = NULL;
+		unsigned int offset, naddrs;
+		const u8 *addrs;
+		u32 page = 0;
+
+		instr = &subop->instrs[1];
+		offset = nand_subop_get_addr_start_off(subop, 1);
+		naddrs = nand_subop_get_num_addr_cyc(subop, 1);
+		addrs = &instr->ctx.addr.addrs[offset];
+
+		for (i = 0; i < naddrs; i++)
+			page |= (u32)addrs[i] << (8 * i);
+
+		return cadence_nand_erase(chip, page);
+	}
+
+	/*
+	 * If it is not an erase operation then handle operation
+	 * by calling exec_op function.
+	 */
+	for (op_id = 0; op_id < subop->ninstrs; op_id++) {
+		int ret;
+		const struct nand_operation nand_op = {
+			.cs = chip->cur_cs,
+			.instrs =  &subop->instrs[op_id],
+			.ninstrs = 1};
+		ret = chip->controller->ops->exec_op(chip, &nand_op, false);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int cadence_nand_cmd_data(struct nand_chip *chip,
+				 const struct nand_subop *subop)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	const struct nand_op_instr *instr;
+	unsigned int offset, op_id = 0;
+	u64 mini_ctrl_cmd = 0;
+	int len = 0;
+	int ret;
+
+	instr = &subop->instrs[op_id];
+
+	if (instr->delay_ns > 0)
+		mini_ctrl_cmd |= GCMD_LAY_TWB;
+
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INSTR,
+				    GCMD_LAY_INSTR_DATA);
+
+	if (instr->type == NAND_OP_DATA_OUT_INSTR)
+		mini_ctrl_cmd |= FIELD_PREP(GCMD_DIR,
+					    GCMD_DIR_WRITE);
+
+	len = nand_subop_get_data_len(subop, op_id);
+	offset = nand_subop_get_data_start_off(subop, op_id);
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_SECT_CNT, 1);
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAST_SIZE, len);
+	if (instr->ctx.data.force_8bit) {
+		ret = cadence_nand_force_byte_access(chip, true);
+		if (ret) {
+			dev_err(cdns_ctrl->dev,
+				"cannot change byte access generic data cmd failed\n");
+			return ret;
+		}
+	}
+
+	ret = cadence_nand_generic_cmd_send(cdns_ctrl,
+					    cdns_chip->cs[chip->cur_cs],
+					    mini_ctrl_cmd);
+	if (ret) {
+		dev_err(cdns_ctrl->dev, "send generic data cmd failed\n");
+		return ret;
+	}
+
+	if (instr->type == NAND_OP_DATA_IN_INSTR) {
+		void *buf = instr->ctx.data.buf.in + offset;
+
+		ret = cadence_nand_read_buf(cdns_ctrl, buf, len);
+	} else {
+		const void *buf = instr->ctx.data.buf.out + offset;
+
+		ret = cadence_nand_write_buf(cdns_ctrl, buf, len);
+	}
+
+	if (ret) {
+		dev_err(cdns_ctrl->dev, "data transfer failed for generic command\n");
+		return ret;
+	}
+
+	if (instr->ctx.data.force_8bit) {
+		ret = cadence_nand_force_byte_access(chip, false);
+		if (ret) {
+			dev_err(cdns_ctrl->dev,
+				"cannot change byte access generic data cmd failed\n");
+		}
+	}
+
+	return ret;
+}
+
+static int cadence_nand_cmd_waitrdy(struct nand_chip *chip,
+				    const struct nand_subop *subop)
+{
+	int status;
+	unsigned int op_id = 0;
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	const struct nand_op_instr *instr = &subop->instrs[op_id];
+	u32 timeout_us = instr->ctx.waitrdy.timeout_ms * 1000;
+
+	status = cadence_nand_wait_for_value(cdns_ctrl, RBN_SETINGS,
+					     timeout_us,
+					     BIT(cdns_chip->cs[chip->cur_cs]),
+					     false);
+	return status;
+}
+
+static const struct nand_op_parser cadence_nand_op_parser = NAND_OP_PARSER(
+	NAND_OP_PARSER_PATTERN(
+		cadence_nand_cmd_erase,
+		NAND_OP_PARSER_PAT_CMD_ELEM(false),
+		NAND_OP_PARSER_PAT_ADDR_ELEM(false, MAX_ERASE_ADDRESS_CYC),
+		NAND_OP_PARSER_PAT_CMD_ELEM(false),
+		NAND_OP_PARSER_PAT_WAITRDY_ELEM(false)),
+	NAND_OP_PARSER_PATTERN(
+		cadence_nand_cmd_opcode,
+		NAND_OP_PARSER_PAT_CMD_ELEM(false)),
+	NAND_OP_PARSER_PATTERN(
+		cadence_nand_cmd_address,
+		NAND_OP_PARSER_PAT_ADDR_ELEM(false, MAX_ADDRESS_CYC)),
+	NAND_OP_PARSER_PATTERN(
+		cadence_nand_cmd_data,
+		NAND_OP_PARSER_PAT_DATA_IN_ELEM(false, MAX_DATA_SIZE)),
+	NAND_OP_PARSER_PATTERN(
+		cadence_nand_cmd_data,
+		NAND_OP_PARSER_PAT_DATA_OUT_ELEM(false, MAX_DATA_SIZE)),
+	NAND_OP_PARSER_PATTERN(
+		cadence_nand_cmd_waitrdy,
+		NAND_OP_PARSER_PAT_WAITRDY_ELEM(false))
+	);
+
+static int cadence_nand_exec_op(struct nand_chip *chip,
+				const struct nand_operation *op,
+				bool check_only)
+{
+	int status = cadence_nand_select_target(chip);
+
+	if (status)
+		return status;
+
+	return nand_op_parser_exec_op(chip, &cadence_nand_op_parser, op,
+				      check_only);
+}
+
+static int cadence_nand_ooblayout_free(struct mtd_info *mtd, int section,
+				       struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+
+	if (section)
+		return -ERANGE;
+
+	oobregion->offset = cdns_chip->bbm_len;
+	oobregion->length = cdns_chip->avail_oob_size
+		- cdns_chip->bbm_len;
+
+	return 0;
+}
+
+static int cadence_nand_ooblayout_ecc(struct mtd_info *mtd, int section,
+				      struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+
+	if (section)
+		return -ERANGE;
+
+	oobregion->offset = cdns_chip->avail_oob_size;
+	oobregion->length = chip->ecc.total;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops cadence_nand_ooblayout_ops = {
+	.free = cadence_nand_ooblayout_free,
+	.ecc = cadence_nand_ooblayout_ecc,
+};
+
+static int calc_cycl(u32 timing, u32 clock)
+{
+	if (timing == 0 || clock == 0)
+		return 0;
+
+	if ((timing % clock) > 0)
+		return timing / clock;
+	else
+		return timing / clock - 1;
+}
+
+/* Calculate max data valid window. */
+static inline u32 calc_tdvw_max(u32 trp_cnt, u32 clk_period, u32 trhoh_min,
+				u32 board_delay_skew_min, u32 ext_mode)
+{
+	if (ext_mode == 0)
+		clk_period /= 2;
+
+	return (trp_cnt + 1) * clk_period + trhoh_min +
+		board_delay_skew_min;
+}
+
+/* Calculate data valid window. */
+static inline u32 calc_tdvw(u32 trp_cnt, u32 clk_period, u32 trhoh_min,
+			    u32 trea_max, u32 ext_mode)
+{
+	if (ext_mode == 0)
+		clk_period /= 2;
+
+	return (trp_cnt + 1) * clk_period + trhoh_min - trea_max;
+}
+
+static int
+cadence_nand_setup_data_interface(struct nand_chip *chip, int chipnr,
+				  const struct nand_data_interface *conf)
+{
+	const struct nand_sdr_timings *sdr;
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	struct cadence_nand_timings *t = &cdns_chip->timings;
+	u32 reg;
+	u32 board_delay = cdns_ctrl->board_delay;
+	u32 clk_period = DIV_ROUND_DOWN_ULL(1000000000000ULL,
+					    cdns_ctrl->nf_clk_rate);
+	u32 tceh_cnt, tcs_cnt, tadl_cnt, tccs_cnt;
+	u32 tfeat_cnt, trhz_cnt, tvdly_cnt;
+	u32 trhw_cnt, twb_cnt, twh_cnt = 0, twhr_cnt;
+	u32 twp_cnt = 0, trp_cnt = 0, trh_cnt = 0;
+	u32 if_skew = cdns_ctrl->caps1->if_skew;
+	u32 board_delay_skew_min = board_delay - if_skew;
+	u32 board_delay_skew_max = board_delay + if_skew;
+	u32 dqs_sampl_res, phony_dqs_mod;
+	u32 tdvw, tdvw_min, tdvw_max;
+	u32 ext_rd_mode, ext_wr_mode;
+	u32 dll_phy_dqs_timing = 0, phony_dqs_timing = 0, rd_del_sel = 0;
+	u32 sampling_point;
+
+	sdr = nand_get_sdr_timings(conf);
+	if (IS_ERR(sdr))
+		return PTR_ERR(sdr);
+
+	memset(t, 0, sizeof(*t));
+	/* Sampling point calculation. */
+
+	if (cdns_ctrl->caps2.is_phy_type_dll)
+		phony_dqs_mod = 2;
+	else
+		phony_dqs_mod = 1;
+
+	dqs_sampl_res = clk_period / phony_dqs_mod;
+
+	tdvw_min = sdr->tREA_max + board_delay_skew_max;
+	/*
+	 * The idea of those calculation is to get the optimum value
+	 * for tRP and tRH timings. If it is NOT possible to sample data
+	 * with optimal tRP/tRH settings, the parameters will be extended.
+	 * If clk_period is 50ns (the lowest value) this condition is met
+	 * for asynchronous timing modes 1, 2, 3, 4 and 5.
+	 * If clk_period is 20ns the condition is met only
+	 * for asynchronous timing mode 5.
+	 */
+	if (sdr->tRC_min <= clk_period &&
+	    sdr->tRP_min <= (clk_period / 2) &&
+	    sdr->tREH_min <= (clk_period / 2)) {
+		/* Performance mode. */
+		ext_rd_mode = 0;
+		tdvw = calc_tdvw(trp_cnt, clk_period, sdr->tRHOH_min,
+				 sdr->tREA_max, ext_rd_mode);
+		tdvw_max = calc_tdvw_max(trp_cnt, clk_period, sdr->tRHOH_min,
+					 board_delay_skew_min,
+					 ext_rd_mode);
+		/*
+		 * Check if data valid window and sampling point can be found
+		 * and is not on the edge (ie. we have hold margin).
+		 * If not extend the tRP timings.
+		 */
+		if (tdvw > 0) {
+			if (tdvw_max <= tdvw_min ||
+			    (tdvw_max % dqs_sampl_res) == 0) {
+				/*
+				 * No valid sampling point so the RE pulse need
+				 * to be widen widening by half clock cycle.
+				 */
+				ext_rd_mode = 1;
+			}
+		} else {
+			/*
+			 * There is no valid window
+			 * to be able to sample data the tRP need to be widen.
+			 * Very safe calculations are performed here.
+			 */
+			trp_cnt = (sdr->tREA_max + board_delay_skew_max
+				   + dqs_sampl_res) / clk_period;
+			ext_rd_mode = 1;
+		}
+
+	} else {
+		/* Extended read mode. */
+		u32 trh;
+
+		ext_rd_mode = 1;
+		trp_cnt = calc_cycl(sdr->tRP_min, clk_period);
+		trh = sdr->tRC_min - ((trp_cnt + 1) * clk_period);
+		if (sdr->tREH_min >= trh)
+			trh_cnt = calc_cycl(sdr->tREH_min, clk_period);
+		else
+			trh_cnt = calc_cycl(trh, clk_period);
+
+		tdvw = calc_tdvw(trp_cnt, clk_period, sdr->tRHOH_min,
+				 sdr->tREA_max, ext_rd_mode);
+		/*
+		 * Check if data valid window and sampling point can be found
+		 * or if it is at the edge check if previous is valid
+		 * - if not extend the tRP timings.
+		 */
+		if (tdvw > 0) {
+			tdvw_max = calc_tdvw_max(trp_cnt, clk_period,
+						 sdr->tRHOH_min,
+						 board_delay_skew_min,
+						 ext_rd_mode);
+
+			if ((((tdvw_max / dqs_sampl_res)
+			      * dqs_sampl_res) <= tdvw_min) ||
+			    (((tdvw_max % dqs_sampl_res) == 0) &&
+			     (((tdvw_max / dqs_sampl_res - 1)
+			       * dqs_sampl_res) <= tdvw_min))) {
+				/*
+				 * Data valid window width is lower than
+				 * sampling resolution and do not hit any
+				 * sampling point to be sure the sampling point
+				 * will be found the RE low pulse width will be
+				 *  extended by one clock cycle.
+				 */
+				trp_cnt = trp_cnt + 1;
+			}
+		} else {
+			/*
+			 * There is no valid window to be able to sample data.
+			 * The tRP need to be widen.
+			 * Very safe calculations are performed here.
+			 */
+			trp_cnt = (sdr->tREA_max + board_delay_skew_max
+				   + dqs_sampl_res) / clk_period;
+		}
+	}
+
+	tdvw_max = calc_tdvw_max(trp_cnt, clk_period,
+				 sdr->tRHOH_min,
+				 board_delay_skew_min, ext_rd_mode);
+
+	if (sdr->tWC_min <= clk_period &&
+	    (sdr->tWP_min + if_skew) <= (clk_period / 2) &&
+	    (sdr->tWH_min + if_skew) <= (clk_period / 2)) {
+		ext_wr_mode = 0;
+	} else {
+		u32 twh;
+
+		ext_wr_mode = 1;
+		twp_cnt = calc_cycl(sdr->tWP_min + if_skew, clk_period);
+		if ((twp_cnt + 1) * clk_period < (sdr->tALS_min + if_skew))
+			twp_cnt = calc_cycl(sdr->tALS_min + if_skew,
+					    clk_period);
+
+		twh = (sdr->tWC_min - (twp_cnt + 1) * clk_period);
+		if (sdr->tWH_min >= twh)
+			twh = sdr->tWH_min;
+
+		twh_cnt = calc_cycl(twh + if_skew, clk_period);
+	}
+
+	reg = FIELD_PREP(ASYNC_TOGGLE_TIMINGS_TRH, trh_cnt);
+	reg |= FIELD_PREP(ASYNC_TOGGLE_TIMINGS_TRP, trp_cnt);
+	reg |= FIELD_PREP(ASYNC_TOGGLE_TIMINGS_TWH, twh_cnt);
+	reg |= FIELD_PREP(ASYNC_TOGGLE_TIMINGS_TWP, twp_cnt);
+	t->async_toggle_timings = reg;
+	dev_dbg(cdns_ctrl->dev, "ASYNC_TOGGLE_TIMINGS_SDR\t%x\n", reg);
+
+	tadl_cnt = calc_cycl((sdr->tADL_min + if_skew), clk_period);
+	tccs_cnt = calc_cycl((sdr->tCCS_min + if_skew), clk_period);
+	twhr_cnt = calc_cycl((sdr->tWHR_min + if_skew), clk_period);
+	trhw_cnt = calc_cycl((sdr->tRHW_min + if_skew), clk_period);
+	reg = FIELD_PREP(TIMINGS0_TADL, tadl_cnt);
+
+	/*
+	 * If timing exceeds delay field in timing register
+	 * then use maximum value.
+	 */
+	if (FIELD_FIT(TIMINGS0_TCCS, tccs_cnt))
+		reg |= FIELD_PREP(TIMINGS0_TCCS, tccs_cnt);
+	else
+		reg |= TIMINGS0_TCCS;
+
+	reg |= FIELD_PREP(TIMINGS0_TWHR, twhr_cnt);
+	reg |= FIELD_PREP(TIMINGS0_TRHW, trhw_cnt);
+	t->timings0 = reg;
+	dev_dbg(cdns_ctrl->dev, "TIMINGS0_SDR\t%x\n", reg);
+
+	/* The following is related to single signal so skew is not needed. */
+	trhz_cnt = calc_cycl(sdr->tRHZ_max, clk_period);
+	trhz_cnt = trhz_cnt + 1;
+	twb_cnt = calc_cycl((sdr->tWB_max + board_delay), clk_period);
+	/*
+	 * Because of the two stage syncflop the value must be increased by 3
+	 * first value is related with sync, second value is related
+	 * with output if delay.
+	 */
+	twb_cnt = twb_cnt + 3 + 5;
+	/*
+	 * The following is related to the we edge of the random data input
+	 * sequence so skew is not needed.
+	 */
+	tvdly_cnt = calc_cycl(500000 + if_skew, clk_period);
+	reg = FIELD_PREP(TIMINGS1_TRHZ, trhz_cnt);
+	reg |= FIELD_PREP(TIMINGS1_TWB, twb_cnt);
+	reg |= FIELD_PREP(TIMINGS1_TVDLY, tvdly_cnt);
+	t->timings1 = reg;
+	dev_dbg(cdns_ctrl->dev, "TIMINGS1_SDR\t%x\n", reg);
+
+	tfeat_cnt = calc_cycl(sdr->tFEAT_max, clk_period);
+	if (tfeat_cnt < twb_cnt)
+		tfeat_cnt = twb_cnt;
+
+	tceh_cnt = calc_cycl(sdr->tCEH_min, clk_period);
+	tcs_cnt = calc_cycl((sdr->tCS_min + if_skew), clk_period);
+
+	reg = FIELD_PREP(TIMINGS2_TFEAT, tfeat_cnt);
+	reg |= FIELD_PREP(TIMINGS2_CS_HOLD_TIME, tceh_cnt);
+	reg |= FIELD_PREP(TIMINGS2_CS_SETUP_TIME, tcs_cnt);
+	t->timings2 = reg;
+	dev_dbg(cdns_ctrl->dev, "TIMINGS2_SDR\t%x\n", reg);
+
+	if (cdns_ctrl->caps2.is_phy_type_dll) {
+		reg = DLL_PHY_CTRL_DLL_RST_N;
+		if (ext_wr_mode)
+			reg |= DLL_PHY_CTRL_EXTENDED_WR_MODE;
+		if (ext_rd_mode)
+			reg |= DLL_PHY_CTRL_EXTENDED_RD_MODE;
+
+		reg |= FIELD_PREP(DLL_PHY_CTRL_RS_HIGH_WAIT_CNT, 7);
+		reg |= FIELD_PREP(DLL_PHY_CTRL_RS_IDLE_CNT, 7);
+		t->dll_phy_ctrl = reg;
+		dev_dbg(cdns_ctrl->dev, "DLL_PHY_CTRL_SDR\t%x\n", reg);
+	}
+
+	/* Sampling point calculation. */
+	if ((tdvw_max % dqs_sampl_res) > 0)
+		sampling_point = tdvw_max / dqs_sampl_res;
+	else
+		sampling_point = (tdvw_max / dqs_sampl_res - 1);
+
+	if (sampling_point * dqs_sampl_res > tdvw_min) {
+		dll_phy_dqs_timing =
+			FIELD_PREP(PHY_DQS_TIMING_DQS_SEL_OE_END, 4);
+		dll_phy_dqs_timing |= PHY_DQS_TIMING_USE_PHONY_DQS;
+		phony_dqs_timing = sampling_point / phony_dqs_mod;
+
+		if ((sampling_point % 2) > 0) {
+			dll_phy_dqs_timing |= PHY_DQS_TIMING_PHONY_DQS_SEL;
+			if ((tdvw_max % dqs_sampl_res) == 0)
+				/*
+				 * Calculation for sampling point at the edge
+				 * of data and being odd number.
+				 */
+				phony_dqs_timing = (tdvw_max / dqs_sampl_res)
+					/ phony_dqs_mod - 1;
+
+			if (!cdns_ctrl->caps2.is_phy_type_dll)
+				phony_dqs_timing--;
+
+		} else {
+			phony_dqs_timing--;
+		}
+		rd_del_sel = phony_dqs_timing + 3;
+	} else {
+		dev_warn(cdns_ctrl->dev,
+			 "ERROR : cannot find valid sampling point\n");
+	}
+
+	reg = FIELD_PREP(PHY_CTRL_PHONY_DQS, phony_dqs_timing);
+	if (cdns_ctrl->caps2.is_phy_type_dll)
+		reg  |= PHY_CTRL_SDR_DQS;
+	t->phy_ctrl = reg;
+	dev_dbg(cdns_ctrl->dev, "PHY_CTRL_REG_SDR\t%x\n", reg);
+
+	if (cdns_ctrl->caps2.is_phy_type_dll) {
+		dev_dbg(cdns_ctrl->dev, "PHY_TSEL_REG_SDR\t%x\n", 0);
+		dev_dbg(cdns_ctrl->dev, "PHY_DQ_TIMING_REG_SDR\t%x\n", 2);
+		dev_dbg(cdns_ctrl->dev, "PHY_DQS_TIMING_REG_SDR\t%x\n",
+			dll_phy_dqs_timing);
+		t->phy_dqs_timing = dll_phy_dqs_timing;
+
+		reg = FIELD_PREP(PHY_GATE_LPBK_CTRL_RDS, rd_del_sel);
+		dev_dbg(cdns_ctrl->dev, "PHY_GATE_LPBK_CTRL_REG_SDR\t%x\n",
+			reg);
+		t->phy_gate_lpbk_ctrl = reg;
+
+		dev_dbg(cdns_ctrl->dev, "PHY_DLL_MASTER_CTRL_REG_SDR\t%lx\n",
+			PHY_DLL_MASTER_CTRL_BYPASS_MODE);
+		dev_dbg(cdns_ctrl->dev, "PHY_DLL_SLAVE_CTRL_REG_SDR\t%x\n", 0);
+	}
+
+	return 0;
+}
+
+int cadence_nand_attach_chip(struct nand_chip *chip)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	u32 ecc_size = cdns_chip->sector_count * chip->ecc.bytes;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	u32 max_oob_data_size;
+	int ret;
+
+	if (chip->options & NAND_BUSWIDTH_16) {
+		ret = cadence_nand_set_access_width16(cdns_ctrl, true);
+		if (ret)
+			return ret;
+	}
+
+	chip->bbt_options |= NAND_BBT_USE_FLASH;
+	chip->bbt_options |= NAND_BBT_NO_OOB;
+	chip->ecc.mode = NAND_ECC_HW;
+
+	chip->options |= NAND_NO_SUBPAGE_WRITE;
+
+	cdns_chip->bbm_offs = chip->badblockpos;
+	if (chip->options & NAND_BUSWIDTH_16) {
+		cdns_chip->bbm_offs &= ~0x01;
+		cdns_chip->bbm_len = 2;
+	} else {
+		cdns_chip->bbm_len = 1;
+	}
+
+	ret = nand_ecc_choose_conf(chip,
+				   &cdns_ctrl->ecc_caps,
+				   mtd->oobsize - cdns_chip->bbm_len);
+	if (ret) {
+		dev_err(cdns_ctrl->dev, "ECC configuration failed\n");
+		return ret;
+	}
+
+	dev_dbg(cdns_ctrl->dev,
+		"chosen ECC settings: step=%d, strength=%d, bytes=%d\n",
+		chip->ecc.size, chip->ecc.strength, chip->ecc.bytes);
+
+	/* Error correction configuration. */
+	cdns_chip->sector_size = chip->ecc.size;
+	cdns_chip->sector_count = mtd->writesize / cdns_chip->sector_size;
+
+	cdns_chip->avail_oob_size = mtd->oobsize - ecc_size;
+
+	max_oob_data_size = MAX_OOB_SIZE_PER_SECTOR;
+
+	if (cdns_chip->avail_oob_size > max_oob_data_size)
+		cdns_chip->avail_oob_size = max_oob_data_size;
+
+	if ((cdns_chip->avail_oob_size + cdns_chip->bbm_len + ecc_size)
+	    > mtd->oobsize)
+		cdns_chip->avail_oob_size -= 4;
+
+	ret = cadence_nand_get_ecc_strength_idx(cdns_ctrl, chip->ecc.strength);
+	if (ret < 0)
+		return -EINVAL;
+
+	cdns_chip->corr_str_idx = (u8)ret;
+
+	if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					1000000,
+					CTRL_STATUS_CTRL_BUSY, true))
+		return -ETIMEDOUT;
+
+	cadence_nand_set_ecc_strength(cdns_ctrl,
+				      cdns_chip->corr_str_idx);
+
+	cadence_nand_set_erase_detection(cdns_ctrl, true,
+					 chip->ecc.strength);
+
+	/* Override the default read operations. */
+	chip->ecc.read_page = cadence_nand_read_page;
+	chip->ecc.read_page_raw = cadence_nand_read_page_raw;
+	chip->ecc.write_page = cadence_nand_write_page;
+	chip->ecc.write_page_raw = cadence_nand_write_page_raw;
+	chip->ecc.read_oob = cadence_nand_read_oob;
+	chip->ecc.write_oob = cadence_nand_write_oob;
+	chip->ecc.read_oob_raw = cadence_nand_read_oob_raw;
+	chip->ecc.write_oob_raw = cadence_nand_write_oob_raw;
+
+	if ((mtd->writesize + mtd->oobsize) > cdns_ctrl->buf_size)
+		cdns_ctrl->buf_size = mtd->writesize + mtd->oobsize;
+
+	/* Is 32-bit DMA supported? */
+	ret = dma_set_mask(cdns_ctrl->dev, DMA_BIT_MASK(32));
+	if (ret) {
+		dev_err(cdns_ctrl->dev, "no usable DMA configuration\n");
+		return ret;
+	}
+
+	mtd_set_ooblayout(mtd, &cadence_nand_ooblayout_ops);
+
+	return 0;
+}
+
+static const struct nand_controller_ops cadence_nand_controller_ops = {
+	.attach_chip = cadence_nand_attach_chip,
+	.exec_op = cadence_nand_exec_op,
+	.setup_data_interface = cadence_nand_setup_data_interface,
+};
+
+static int cadence_nand_chip_init(struct cdns_nand_ctrl *cdns_ctrl,
+				  struct device_node *np)
+{
+	struct cdns_nand_chip *cdns_chip;
+	struct mtd_info *mtd;
+	struct nand_chip *chip;
+	int nsels, ret, i;
+	u32 cs;
+
+	nsels = of_property_count_elems_of_size(np, "reg", sizeof(u32));
+	if (nsels <= 0) {
+		dev_err(cdns_ctrl->dev, "missing/invalid reg property\n");
+		return -EINVAL;
+	}
+
+	/* Allocate the nand chip structure. */
+	cdns_chip = devm_kzalloc(cdns_ctrl->dev, sizeof(*cdns_chip) +
+				 (nsels * sizeof(u8)),
+				 GFP_KERNEL);
+	if (!cdns_chip) {
+		dev_err(cdns_ctrl->dev, "could not allocate chip structure\n");
+		return -ENOMEM;
+	}
+
+	cdns_chip->nsels = nsels;
+
+	for (i = 0; i < nsels; i++) {
+		/* Retrieve CS id. */
+		ret = of_property_read_u32_index(np, "reg", i, &cs);
+		if (ret) {
+			dev_err(cdns_ctrl->dev,
+				"could not retrieve reg property: %d\n",
+				ret);
+			return ret;
+		}
+
+		if (cs >= cdns_ctrl->caps2.max_banks) {
+			dev_err(cdns_ctrl->dev,
+				"invalid reg value: %u (max CS = %d)\n",
+				cs, cdns_ctrl->caps2.max_banks);
+			return -EINVAL;
+		}
+
+		if (test_and_set_bit(cs, &cdns_ctrl->assigned_cs)) {
+			dev_err(cdns_ctrl->dev,
+				"CS %d already assigned\n", cs);
+			return -EINVAL;
+		}
+
+		cdns_chip->cs[i] = cs;
+	}
+
+	chip = &cdns_chip->chip;
+	chip->controller = &cdns_ctrl->controller;
+	nand_set_flash_node(chip, np);
+
+	mtd = nand_to_mtd(chip);
+	mtd->dev.parent = cdns_ctrl->dev;
+
+	/*
+	 * Default to HW ECC engine mode. If the nand-ecc-mode property is given
+	 * in the DT node, this entry will be overwritten in nand_scan_ident().
+	 */
+	chip->ecc.mode = NAND_ECC_HW;
+
+	ret = nand_scan(chip, cdns_chip->nsels);
+	if (ret) {
+		dev_err(cdns_ctrl->dev, "could not scan the nand chip\n");
+		return ret;
+	}
+
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret) {
+		dev_err(cdns_ctrl->dev,
+			"failed to register mtd device: %d\n", ret);
+		nand_cleanup(chip);
+		return ret;
+	}
+
+	list_add_tail(&cdns_chip->node, &cdns_ctrl->chips);
+
+	return 0;
+}
+
+static void cadence_nand_chips_cleanup(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	struct cdns_nand_chip *entry, *temp;
+
+	list_for_each_entry_safe(entry, temp, &cdns_ctrl->chips, node) {
+		nand_release(&entry->chip);
+		list_del(&entry->node);
+	}
+}
+
+static int cadence_nand_chips_init(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	struct device_node *np = cdns_ctrl->dev->of_node;
+	struct device_node *nand_np;
+	int max_cs = cdns_ctrl->caps2.max_banks;
+	int nchips, ret;
+
+	nchips = of_get_child_count(np);
+
+	if (nchips > max_cs) {
+		dev_err(cdns_ctrl->dev,
+			"too many NAND chips: %d (max = %d CS)\n",
+			nchips, max_cs);
+		return -EINVAL;
+	}
+
+	for_each_child_of_node(np, nand_np) {
+		ret = cadence_nand_chip_init(cdns_ctrl, nand_np);
+		if (ret) {
+			of_node_put(nand_np);
+			cadence_nand_chips_cleanup(cdns_ctrl);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void
+cadence_nand_irq_cleanup(int irqnum, struct cdns_nand_ctrl *cdns_ctrl)
+{
+	/* Disable interrupts. */
+	writel_relaxed(INTR_ENABLE_INTR_EN, cdns_ctrl->reg + INTR_ENABLE);
+}
+
+static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	dma_cap_mask_t mask;
+	int ret;
+
+	cdns_ctrl->cdma_desc = dma_alloc_coherent(cdns_ctrl->dev,
+						  sizeof(*cdns_ctrl->cdma_desc),
+						  &cdns_ctrl->dma_cdma_desc,
+						  GFP_KERNEL);
+	if (!cdns_ctrl->dma_cdma_desc)
+		return -ENOMEM;
+
+	cdns_ctrl->buf_size = SZ_16K;
+	cdns_ctrl->buf = kmalloc(cdns_ctrl->buf_size, GFP_KERNEL);
+	if (!cdns_ctrl->buf) {
+		ret = -ENOMEM;
+		goto free_buf_desc;
+	}
+
+	if (devm_request_irq(cdns_ctrl->dev, cdns_ctrl->irq, cadence_nand_isr,
+			     IRQF_SHARED, "cadence-nand-controller",
+			     cdns_ctrl)) {
+		dev_err(cdns_ctrl->dev, "Unable to allocate IRQ\n");
+		ret = -ENODEV;
+		goto free_buf;
+	}
+
+	spin_lock_init(&cdns_ctrl->irq_lock);
+	init_completion(&cdns_ctrl->complete);
+
+	ret = cadence_nand_hw_init(cdns_ctrl);
+	if (ret)
+		goto disable_irq;
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_MEMCPY, mask);
+
+	if (cdns_ctrl->caps1->has_dma) {
+		cdns_ctrl->dmac = dma_request_channel(mask, NULL, NULL);
+		if (!cdns_ctrl->dmac) {
+			dev_err(cdns_ctrl->dev,
+				"Unable to get a DMA channel\n");
+			ret = -EBUSY;
+			goto disable_irq;
+		}
+	}
+
+	nand_controller_init(&cdns_ctrl->controller);
+	INIT_LIST_HEAD(&cdns_ctrl->chips);
+
+	cdns_ctrl->controller.ops = &cadence_nand_controller_ops;
+	cdns_ctrl->curr_corr_str_idx = 0xFF;
+
+	ret = cadence_nand_chips_init(cdns_ctrl);
+	if (ret) {
+		dev_err(cdns_ctrl->dev, "Failed to register MTD: %d\n",
+			ret);
+		goto dma_release_chnl;
+	}
+
+	kfree(cdns_ctrl->buf);
+	cdns_ctrl->buf = kzalloc(cdns_ctrl->buf_size, GFP_KERNEL);
+	if (!cdns_ctrl->buf) {
+		ret = -ENOMEM;
+		goto dma_release_chnl;
+	}
+
+	return 0;
+
+dma_release_chnl:
+	if (cdns_ctrl->dmac)
+		dma_release_channel(cdns_ctrl->dmac);
+
+disable_irq:
+	cadence_nand_irq_cleanup(cdns_ctrl->irq, cdns_ctrl);
+
+free_buf:
+	kfree(cdns_ctrl->buf);
+
+free_buf_desc:
+	dma_free_coherent(cdns_ctrl->dev, sizeof(struct cadence_nand_cdma_desc),
+			  cdns_ctrl->cdma_desc, cdns_ctrl->dma_cdma_desc);
+
+	return ret;
+}
+
+/* Driver exit point. */
+static void cadence_nand_remove(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	cadence_nand_chips_cleanup(cdns_ctrl);
+	cadence_nand_irq_cleanup(cdns_ctrl->irq, cdns_ctrl);
+	kfree(cdns_ctrl->buf);
+	dma_free_coherent(cdns_ctrl->dev, sizeof(struct cadence_nand_cdma_desc),
+			  cdns_ctrl->cdma_desc, cdns_ctrl->dma_cdma_desc);
+
+	if (cdns_ctrl->dmac)
+		dma_release_channel(cdns_ctrl->dmac);
+}
+
+struct cadence_nand_dt {
+	struct cdns_nand_ctrl cdns_ctrl;
+	struct clk *clk;
+};
+
+static const struct cadence_nand_dt_devdata cadence_nand_default = {
+	.if_skew = 0,
+	.has_dma = 1,
+};
+
+static const struct of_device_id cadence_nand_dt_ids[] = {
+	{
+		.compatible = "cdns,hp-nfc",
+		.data = &cadence_nand_default
+	}, {}
+};
+
+MODULE_DEVICE_TABLE(of, cadence_nand_dt_ids);
+
+static int cadence_nand_dt_probe(struct platform_device *ofdev)
+{
+	struct resource *res;
+	struct cadence_nand_dt *dt;
+	struct cdns_nand_ctrl *cdns_ctrl;
+	int ret;
+	const struct of_device_id *of_id;
+	const struct cadence_nand_dt_devdata *devdata;
+	u32 val;
+
+	of_id = of_match_device(cadence_nand_dt_ids, &ofdev->dev);
+	if (of_id) {
+		ofdev->id_entry = of_id->data;
+		devdata = of_id->data;
+	} else {
+		pr_err("Failed to find the right device id.\n");
+		return -ENOMEM;
+	}
+
+	dt = devm_kzalloc(&ofdev->dev, sizeof(*dt), GFP_KERNEL);
+	if (!dt)
+		return -ENOMEM;
+
+	cdns_ctrl = &dt->cdns_ctrl;
+	cdns_ctrl->caps1 = devdata;
+
+	cdns_ctrl->dev = &ofdev->dev;
+	cdns_ctrl->irq = platform_get_irq(ofdev, 0);
+	if (cdns_ctrl->irq < 0)
+		return cdns_ctrl->irq;
+
+	dev_info(cdns_ctrl->dev, "IRQ: nr %d\n", cdns_ctrl->irq);
+
+	cdns_ctrl->reg = devm_platform_ioremap_resource(ofdev, 0);
+	if (IS_ERR(cdns_ctrl->reg)) {
+		dev_err(&ofdev->dev, "devm_ioremap_resource res 0 failed\n");
+		return PTR_ERR(cdns_ctrl->reg);
+	}
+
+	res = platform_get_resource(ofdev, IORESOURCE_MEM, 1);
+	cdns_ctrl->io.dma = res->start;
+	cdns_ctrl->io.virt = devm_ioremap_resource(&ofdev->dev, res);
+	if (IS_ERR(cdns_ctrl->io.virt)) {
+		dev_err(cdns_ctrl->dev, "devm_ioremap_resource res 1 failed\n");
+		return PTR_ERR(cdns_ctrl->io.virt);
+	}
+
+	dt->clk = devm_clk_get(cdns_ctrl->dev, "nf_clk");
+	if (IS_ERR(dt->clk))
+		return PTR_ERR(dt->clk);
+
+	cdns_ctrl->nf_clk_rate = clk_get_rate(dt->clk);
+
+	ret = of_property_read_u32(ofdev->dev.of_node,
+				   "cdns,board-delay-ps", &val);
+	if (ret) {
+		val = 4830;
+		dev_info(cdns_ctrl->dev,
+			 "missing cdns,board-delay-ps property, %d was set\n",
+			 val);
+	}
+	cdns_ctrl->board_delay = val;
+
+	ret = cadence_nand_init(cdns_ctrl);
+	if (ret)
+		return ret;
+
+	platform_set_drvdata(ofdev, dt);
+	return 0;
+}
+
+static int cadence_nand_dt_remove(struct platform_device *ofdev)
+{
+	struct cadence_nand_dt *dt = platform_get_drvdata(ofdev);
+
+	cadence_nand_remove(&dt->cdns_ctrl);
+
+	return 0;
+}
+
+static struct platform_driver cadence_nand_dt_driver = {
+	.probe		= cadence_nand_dt_probe,
+	.remove		= cadence_nand_dt_remove,
+	.driver		= {
+		.name	= "cadence-nand-controller",
+		.of_match_table = cadence_nand_dt_ids,
+	},
+};
+
+module_platform_driver(cadence_nand_dt_driver);
+
+MODULE_AUTHOR("Piotr Sroka <piotrs@cadence.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Driver for Cadence NAND flash controller");
+
diff --git a/drivers/mtd/nand/raw/denali_dt.c b/drivers/mtd/nand/raw/denali_dt.c
index 5e14836f6bd5..8b779a899dcf 100644
--- a/drivers/mtd/nand/raw/denali_dt.c
+++ b/drivers/mtd/nand/raw/denali_dt.c
@@ -102,47 +102,6 @@ static int denali_dt_chip_init(struct denali_controller *denali,
 	return denali_chip_init(denali, dchip);
 }
 
-/* Backward compatibility for old platforms */
-static int denali_dt_legacy_chip_init(struct denali_controller *denali)
-{
-	struct denali_chip *dchip;
-	int nsels, i;
-
-	nsels = denali->nbanks;
-
-	dchip = devm_kzalloc(denali->dev, struct_size(dchip, sels, nsels),
-			     GFP_KERNEL);
-	if (!dchip)
-		return -ENOMEM;
-
-	dchip->nsels = nsels;
-
-	for (i = 0; i < nsels; i++)
-		dchip->sels[i].bank = i;
-
-	nand_set_flash_node(&dchip->chip, denali->dev->of_node);
-
-	return denali_chip_init(denali, dchip);
-}
-
-/*
- * Check the DT binding.
- * The new binding expects chip subnodes in the controller node.
- * So, #address-cells = <1>; #size-cells = <0>; are required.
- * Check the #size-cells to distinguish the binding.
- */
-static bool denali_dt_is_legacy_binding(struct device_node *np)
-{
-	u32 cells;
-	int ret;
-
-	ret = of_property_read_u32(np, "#size-cells", &cells);
-	if (ret)
-		return true;
-
-	return cells != 0;
-}
-
 static int denali_dt_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -167,10 +126,8 @@ static int denali_dt_probe(struct platform_device *pdev)
 
 	denali->dev = dev;
 	denali->irq = platform_get_irq(pdev, 0);
-	if (denali->irq < 0) {
-		dev_err(dev, "no irq defined\n");
+	if (denali->irq < 0)
 		return denali->irq;
-	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "denali_reg");
 	denali->reg = devm_ioremap_resource(dev, res);
@@ -213,17 +170,11 @@ static int denali_dt_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_disable_clk_ecc;
 
-	if (denali_dt_is_legacy_binding(dev->of_node)) {
-		ret = denali_dt_legacy_chip_init(denali);
-		if (ret)
+	for_each_child_of_node(dev->of_node, np) {
+		ret = denali_dt_chip_init(denali, np);
+		if (ret) {
+			of_node_put(np);
 			goto out_remove_denali;
-	} else {
-		for_each_child_of_node(dev->of_node, np) {
-			ret = denali_dt_chip_init(denali, np);
-			if (ret) {
-				of_node_put(np);
-				goto out_remove_denali;
-			}
 		}
 	}
 
diff --git a/drivers/mtd/nand/raw/hisi504_nand.c b/drivers/mtd/nand/raw/hisi504_nand.c
index 6a4626a8bf95..0b48be54ba6f 100644
--- a/drivers/mtd/nand/raw/hisi504_nand.c
+++ b/drivers/mtd/nand/raw/hisi504_nand.c
@@ -751,10 +751,8 @@ static int hisi_nfc_probe(struct platform_device *pdev)
 	mtd  = nand_to_mtd(chip);
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "no IRQ resource defined\n");
+	if (irq < 0)
 		return -ENXIO;
-	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	host->iobase = devm_ioremap_resource(dev, res);
diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c
index 78b31f845c50..241b58b83240 100644
--- a/drivers/mtd/nand/raw/lpc32xx_mlc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c
@@ -773,7 +773,6 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 
 	host->irq = platform_get_irq(pdev, 0);
 	if (host->irq < 0) {
-		dev_err(&pdev->dev, "failed to get platform irq\n");
 		res = -EINVAL;
 		goto release_dma_chan;
 	}
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index fc49e13d81ec..fb5abdcfb007 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -2862,10 +2862,8 @@ static int marvell_nfc_probe(struct platform_device *pdev)
 		return PTR_ERR(nfc->regs);
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "failed to retrieve irq\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	nfc->core_clk = devm_clk_get(&pdev->dev, "core");
 
diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c
index 1b82b687e5a5..9f17b5b8efbf 100644
--- a/drivers/mtd/nand/raw/meson_nand.c
+++ b/drivers/mtd/nand/raw/meson_nand.c
@@ -1399,10 +1399,8 @@ static int meson_nfc_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "no NFC IRQ resource\n");
+	if (irq < 0)
 		return -EINVAL;
-	}
 
 	ret = meson_nfc_clk_init(nfc);
 	if (ret) {
diff --git a/drivers/mtd/nand/raw/mtk_ecc.c b/drivers/mtd/nand/raw/mtk_ecc.c
index 74595b644b7c..75f1fa3d4d35 100644
--- a/drivers/mtd/nand/raw/mtk_ecc.c
+++ b/drivers/mtd/nand/raw/mtk_ecc.c
@@ -527,10 +527,8 @@ static int mtk_ecc_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "failed to get irq: %d\n", irq);
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = dma_set_mask(dev, DMA_BIT_MASK(32));
 	if (ret) {
diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c
index 373d47d1ba4c..b8305e39ab51 100644
--- a/drivers/mtd/nand/raw/mtk_nand.c
+++ b/drivers/mtd/nand/raw/mtk_nand.c
@@ -1540,7 +1540,6 @@ static int mtk_nfc_probe(struct platform_device *pdev)
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
-		dev_err(dev, "no nfi irq resource\n");
 		ret = -EINVAL;
 		goto clk_disable;
 	}
diff --git a/drivers/mtd/nand/raw/mxic_nand.c b/drivers/mtd/nand/raw/mxic_nand.c
index 9d49e6c845e1..ed7a4e021bf5 100644
--- a/drivers/mtd/nand/raw/mxic_nand.c
+++ b/drivers/mtd/nand/raw/mxic_nand.c
@@ -524,10 +524,8 @@ static int mxic_nfc_probe(struct platform_device *pdev)
 	nand_chip->controller = &nfc->controller;
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "failed to retrieve irq\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	mxic_nfc_hw_init(nfc);
 
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 5c2c30a7dffa..f64e3b6605c6 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -292,12 +292,16 @@ int nand_bbm_get_next_page(struct nand_chip *chip, int page)
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	int last_page = ((mtd->erasesize - mtd->writesize) >>
 			 chip->page_shift) & chip->pagemask;
+	unsigned int bbm_flags = NAND_BBM_FIRSTPAGE | NAND_BBM_SECONDPAGE
+		| NAND_BBM_LASTPAGE;
 
+	if (page == 0 && !(chip->options & bbm_flags))
+		return 0;
 	if (page == 0 && chip->options & NAND_BBM_FIRSTPAGE)
 		return 0;
-	else if (page <= 1 && chip->options & NAND_BBM_SECONDPAGE)
+	if (page <= 1 && chip->options & NAND_BBM_SECONDPAGE)
 		return 1;
-	else if (page <= last_page && chip->options & NAND_BBM_LASTPAGE)
+	if (page <= last_page && chip->options & NAND_BBM_LASTPAGE)
 		return last_page;
 
 	return -EINVAL;
diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index 8ca9fad6e6ad..56654030ec7f 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -446,8 +446,10 @@ static int micron_nand_init(struct nand_chip *chip)
 	if (ret)
 		goto err_free_manuf_data;
 
+	chip->options |= NAND_BBM_FIRSTPAGE;
+
 	if (mtd->writesize == 2048)
-		chip->options |= NAND_BBM_FIRSTPAGE | NAND_BBM_SECONDPAGE;
+		chip->options |= NAND_BBM_SECONDPAGE;
 
 	ondie = micron_supports_on_die_ecc(chip);
 
diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c
index 6ec65f48501c..ad77c112a78a 100644
--- a/drivers/mtd/nand/raw/omap2.c
+++ b/drivers/mtd/nand/raw/omap2.c
@@ -1967,10 +1967,8 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 
 	case NAND_OMAP_PREFETCH_IRQ:
 		info->gpmc_irq_fifo = platform_get_irq(info->pdev, 0);
-		if (info->gpmc_irq_fifo <= 0) {
-			dev_err(dev, "Error getting fifo IRQ\n");
+		if (info->gpmc_irq_fifo <= 0)
 			return -ENODEV;
-		}
 		err = devm_request_irq(dev, info->gpmc_irq_fifo,
 				       omap_nand_irq, IRQF_SHARED,
 				       "gpmc-nand-fifo", info);
@@ -1982,10 +1980,8 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 		}
 
 		info->gpmc_irq_count = platform_get_irq(info->pdev, 1);
-		if (info->gpmc_irq_count <= 0) {
-			dev_err(dev, "Error getting IRQ count\n");
+		if (info->gpmc_irq_count <= 0)
 			return -ENODEV;
-		}
 		err = devm_request_irq(dev, info->gpmc_irq_count,
 				       omap_nand_irq, IRQF_SHARED,
 				       "gpmc-nand-count", info);
diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c
index e509c93737c4..058e99d0cbcf 100644
--- a/drivers/mtd/nand/raw/sh_flctl.c
+++ b/drivers/mtd/nand/raw/sh_flctl.c
@@ -1129,10 +1129,8 @@ static int flctl_probe(struct platform_device *pdev)
 	flctl->fifo = res->start + 0x24; /* FLDTFIFO */
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "failed to get flste irq data: %d\n", irq);
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = devm_request_irq(&pdev->dev, irq, flctl_handle_flste, IRQF_SHARED,
 			       "flste", flctl);
diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
index 8cc852dc7d54..9e63800f768a 100644
--- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c
+++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
@@ -1880,11 +1880,8 @@ static int stm32_fmc2_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		if (irq != -EPROBE_DEFER)
-			dev_err(dev, "IRQ error missing or invalid\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = devm_request_irq(dev, irq, stm32_fmc2_irq, 0,
 			       dev_name(dev), fmc2);
diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index 89773293c64d..37a4ac0dd85b 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -2071,10 +2071,8 @@ static int sunxi_nfc_probe(struct platform_device *pdev)
 		return PTR_ERR(nfc->regs);
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "failed to retrieve irq\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	nfc->ahb_clk = devm_clk_get(dev, "ahb");
 	if (IS_ERR(nfc->ahb_clk)) {
diff --git a/drivers/mtd/spi-nor/aspeed-smc.c b/drivers/mtd/spi-nor/aspeed-smc.c
index 009c1da8574c..2b7cabbb680c 100644
--- a/drivers/mtd/spi-nor/aspeed-smc.c
+++ b/drivers/mtd/spi-nor/aspeed-smc.c
@@ -320,7 +320,8 @@ static void aspeed_smc_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
 	mutex_unlock(&chip->controller->mutex);
 }
 
-static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
+			       size_t len)
 {
 	struct aspeed_smc_chip *chip = nor->priv;
 
@@ -331,8 +332,8 @@ static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 	return 0;
 }
 
-static int aspeed_smc_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
-				int len)
+static int aspeed_smc_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf,
+				size_t len)
 {
 	struct aspeed_smc_chip *chip = nor->priv;
 
@@ -746,6 +747,15 @@ static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip)
 	return 0;
 }
 
+static const struct spi_nor_controller_ops aspeed_smc_controller_ops = {
+	.prepare = aspeed_smc_prep,
+	.unprepare = aspeed_smc_unprep,
+	.read_reg = aspeed_smc_read_reg,
+	.write_reg = aspeed_smc_write_reg,
+	.read = aspeed_smc_read_user,
+	.write = aspeed_smc_write_user,
+};
+
 static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller,
 				  struct device_node *np, struct resource *r)
 {
@@ -805,12 +815,7 @@ static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller,
 		nor->dev = dev;
 		nor->priv = chip;
 		spi_nor_set_flash_node(nor, child);
-		nor->read = aspeed_smc_read_user;
-		nor->write = aspeed_smc_write_user;
-		nor->read_reg = aspeed_smc_read_reg;
-		nor->write_reg = aspeed_smc_write_reg;
-		nor->prepare = aspeed_smc_prep;
-		nor->unprepare = aspeed_smc_unprep;
+		nor->controller_ops = &aspeed_smc_controller_ops;
 
 		ret = aspeed_smc_chip_setup_init(chip, r);
 		if (ret)
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index 7bef63947b29..06f997247d0f 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -285,7 +285,7 @@ static irqreturn_t cqspi_irq_handler(int this_irq, void *dev)
 	return IRQ_HANDLED;
 }
 
-static unsigned int cqspi_calc_rdreg(struct spi_nor *nor, const u8 opcode)
+static unsigned int cqspi_calc_rdreg(struct spi_nor *nor)
 {
 	struct cqspi_flash_pdata *f_pdata = nor->priv;
 	u32 rdreg = 0;
@@ -354,27 +354,27 @@ static int cqspi_exec_flash_cmd(struct cqspi_st *cqspi, unsigned int reg)
 	return cqspi_wait_idle(cqspi);
 }
 
-static int cqspi_command_read(struct spi_nor *nor,
-			      const u8 *txbuf, const unsigned n_tx,
-			      u8 *rxbuf, const unsigned n_rx)
+static int cqspi_command_read(struct spi_nor *nor, u8 opcode,
+			      u8 *rxbuf, size_t n_rx)
 {
 	struct cqspi_flash_pdata *f_pdata = nor->priv;
 	struct cqspi_st *cqspi = f_pdata->cqspi;
 	void __iomem *reg_base = cqspi->iobase;
 	unsigned int rdreg;
 	unsigned int reg;
-	unsigned int read_len;
+	size_t read_len;
 	int status;
 
 	if (!n_rx || n_rx > CQSPI_STIG_DATA_LEN_MAX || !rxbuf) {
-		dev_err(nor->dev, "Invalid input argument, len %d rxbuf 0x%p\n",
+		dev_err(nor->dev,
+			"Invalid input argument, len %zu rxbuf 0x%p\n",
 			n_rx, rxbuf);
 		return -EINVAL;
 	}
 
-	reg = txbuf[0] << CQSPI_REG_CMDCTRL_OPCODE_LSB;
+	reg = opcode << CQSPI_REG_CMDCTRL_OPCODE_LSB;
 
-	rdreg = cqspi_calc_rdreg(nor, txbuf[0]);
+	rdreg = cqspi_calc_rdreg(nor);
 	writel(rdreg, reg_base + CQSPI_REG_RD_INSTR);
 
 	reg |= (0x1 << CQSPI_REG_CMDCTRL_RD_EN_LSB);
@@ -404,19 +404,19 @@ static int cqspi_command_read(struct spi_nor *nor,
 }
 
 static int cqspi_command_write(struct spi_nor *nor, const u8 opcode,
-			       const u8 *txbuf, const unsigned n_tx)
+			       const u8 *txbuf, size_t n_tx)
 {
 	struct cqspi_flash_pdata *f_pdata = nor->priv;
 	struct cqspi_st *cqspi = f_pdata->cqspi;
 	void __iomem *reg_base = cqspi->iobase;
 	unsigned int reg;
 	unsigned int data;
-	u32 write_len;
+	size_t write_len;
 	int ret;
 
 	if (n_tx > CQSPI_STIG_DATA_LEN_MAX || (n_tx && !txbuf)) {
 		dev_err(nor->dev,
-			"Invalid input argument, cmdlen %d txbuf 0x%p\n",
+			"Invalid input argument, cmdlen %zu txbuf 0x%p\n",
 			n_tx, txbuf);
 		return -EINVAL;
 	}
@@ -470,7 +470,7 @@ static int cqspi_read_setup(struct spi_nor *nor)
 	unsigned int reg;
 
 	reg = nor->read_opcode << CQSPI_REG_RD_INSTR_OPCODE_LSB;
-	reg |= cqspi_calc_rdreg(nor, nor->read_opcode);
+	reg |= cqspi_calc_rdreg(nor);
 
 	/* Setup dummy clock cycles */
 	dummy_clk = nor->read_dummy;
@@ -603,7 +603,7 @@ static int cqspi_write_setup(struct spi_nor *nor)
 	/* Set opcode. */
 	reg = nor->program_opcode << CQSPI_REG_WR_INSTR_OPCODE_LSB;
 	writel(reg, reg_base + CQSPI_REG_WR_INSTR);
-	reg = cqspi_calc_rdreg(nor, nor->program_opcode);
+	reg = cqspi_calc_rdreg(nor);
 	writel(reg, reg_base + CQSPI_REG_RD_INSTR);
 
 	reg = readl(reg_base + CQSPI_REG_SIZE);
@@ -1050,7 +1050,7 @@ static int cqspi_erase(struct spi_nor *nor, loff_t offs)
 		return ret;
 
 	/* Send write enable, then erase commands. */
-	ret = nor->write_reg(nor, SPINOR_OP_WREN, NULL, 0);
+	ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WREN, NULL, 0);
 	if (ret)
 		return ret;
 
@@ -1080,18 +1080,19 @@ static void cqspi_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
 	mutex_unlock(&cqspi->bus_mutex);
 }
 
-static int cqspi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int cqspi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, size_t len)
 {
 	int ret;
 
 	ret = cqspi_set_protocol(nor, 0);
 	if (!ret)
-		ret = cqspi_command_read(nor, &opcode, 1, buf, len);
+		ret = cqspi_command_read(nor, opcode, buf, len);
 
 	return ret;
 }
 
-static int cqspi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int cqspi_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf,
+			   size_t len)
 {
 	int ret;
 
@@ -1216,6 +1217,16 @@ static void cqspi_request_mmap_dma(struct cqspi_st *cqspi)
 	init_completion(&cqspi->rx_dma_complete);
 }
 
+static const struct spi_nor_controller_ops cqspi_controller_ops = {
+	.prepare = cqspi_prep,
+	.unprepare = cqspi_unprep,
+	.read_reg = cqspi_read_reg,
+	.write_reg = cqspi_write_reg,
+	.read = cqspi_read,
+	.write = cqspi_write,
+	.erase = cqspi_erase,
+};
+
 static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np)
 {
 	struct platform_device *pdev = cqspi->pdev;
@@ -1265,14 +1276,7 @@ static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np)
 		nor->dev = dev;
 		spi_nor_set_flash_node(nor, np);
 		nor->priv = f_pdata;
-
-		nor->read_reg = cqspi_read_reg;
-		nor->write_reg = cqspi_write_reg;
-		nor->read = cqspi_read;
-		nor->write = cqspi_write;
-		nor->erase = cqspi_erase;
-		nor->prepare = cqspi_prep;
-		nor->unprepare = cqspi_unprep;
+		nor->controller_ops = &cqspi_controller_ops;
 
 		mtd->name = devm_kasprintf(dev, GFP_KERNEL, "%s.%d",
 					   dev_name(dev), cs);
@@ -1366,10 +1370,8 @@ static int cqspi_probe(struct platform_device *pdev)
 
 	/* Obtain IRQ line. */
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "Cannot obtain IRQ.\n");
+	if (irq < 0)
 		return -ENXIO;
-	}
 
 	pm_runtime_enable(dev);
 	ret = pm_runtime_get_sync(dev);
diff --git a/drivers/mtd/spi-nor/hisi-sfc.c b/drivers/mtd/spi-nor/hisi-sfc.c
index 6dac9dd8bf42..a1258216f89d 100644
--- a/drivers/mtd/spi-nor/hisi-sfc.c
+++ b/drivers/mtd/spi-nor/hisi-sfc.c
@@ -177,7 +177,7 @@ static void hisi_spi_nor_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
 }
 
 static int hisi_spi_nor_op_reg(struct spi_nor *nor,
-				u8 opcode, int len, u8 optype)
+				u8 opcode, size_t len, u8 optype)
 {
 	struct hifmc_priv *priv = nor->priv;
 	struct hifmc_host *host = priv->host;
@@ -200,7 +200,7 @@ static int hisi_spi_nor_op_reg(struct spi_nor *nor,
 }
 
 static int hisi_spi_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
-		int len)
+				 size_t len)
 {
 	struct hifmc_priv *priv = nor->priv;
 	struct hifmc_host *host = priv->host;
@@ -215,7 +215,7 @@ static int hisi_spi_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
 }
 
 static int hisi_spi_nor_write_reg(struct spi_nor *nor, u8 opcode,
-				u8 *buf, int len)
+				  const u8 *buf, size_t len)
 {
 	struct hifmc_priv *priv = nor->priv;
 	struct hifmc_host *host = priv->host;
@@ -311,6 +311,15 @@ static ssize_t hisi_spi_nor_write(struct spi_nor *nor, loff_t to,
 	return len;
 }
 
+static const struct spi_nor_controller_ops hisi_controller_ops = {
+	.prepare = hisi_spi_nor_prep,
+	.unprepare = hisi_spi_nor_unprep,
+	.read_reg = hisi_spi_nor_read_reg,
+	.write_reg = hisi_spi_nor_write_reg,
+	.read = hisi_spi_nor_read,
+	.write = hisi_spi_nor_write,
+};
+
 /**
  * Get spi flash device information and register it as a mtd device.
  */
@@ -357,14 +366,8 @@ static int hisi_spi_nor_register(struct device_node *np,
 	}
 	priv->host = host;
 	nor->priv = priv;
+	nor->controller_ops = &hisi_controller_ops;
 
-	nor->prepare = hisi_spi_nor_prep;
-	nor->unprepare = hisi_spi_nor_unprep;
-	nor->read_reg = hisi_spi_nor_read_reg;
-	nor->write_reg = hisi_spi_nor_write_reg;
-	nor->read = hisi_spi_nor_read;
-	nor->write = hisi_spi_nor_write;
-	nor->erase = NULL;
 	ret = spi_nor_scan(nor, NULL, &hwcaps);
 	if (ret)
 		return ret;
diff --git a/drivers/mtd/spi-nor/intel-spi-pci.c b/drivers/mtd/spi-nor/intel-spi-pci.c
index 3cda8e7a68f8..3d8987baea2a 100644
--- a/drivers/mtd/spi-nor/intel-spi-pci.c
+++ b/drivers/mtd/spi-nor/intel-spi-pci.c
@@ -20,6 +20,10 @@ static const struct intel_spi_boardinfo bxt_info = {
 	.type = INTEL_SPI_BXT,
 };
 
+static const struct intel_spi_boardinfo cnl_info = {
+	.type = INTEL_SPI_CNL,
+};
+
 static int intel_spi_pci_probe(struct pci_dev *pdev,
 			       const struct pci_device_id *id)
 {
@@ -61,6 +65,7 @@ static void intel_spi_pci_remove(struct pci_dev *pdev)
 
 static const struct pci_device_id intel_spi_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0x02a4), (unsigned long)&bxt_info },
+	{ PCI_VDEVICE(INTEL, 0x06a4), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0x18e0), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0x19e0), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0x34a4), (unsigned long)&bxt_info },
@@ -68,6 +73,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0xa0a4), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0xa1a4), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0xa224), (unsigned long)&bxt_info },
+	{ PCI_VDEVICE(INTEL, 0xa324), (unsigned long)&cnl_info },
 	{ },
 };
 MODULE_DEVICE_TABLE(pci, intel_spi_pci_ids);
diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c
index 43e55a2e9b27..61d2a0ad2131 100644
--- a/drivers/mtd/spi-nor/intel-spi.c
+++ b/drivers/mtd/spi-nor/intel-spi.c
@@ -108,6 +108,10 @@
 #define BXT_FREG_NUM			12
 #define BXT_PR_NUM			6
 
+#define CNL_PR				0x84
+#define CNL_FREG_NUM			6
+#define CNL_PR_NUM			5
+
 #define LVSCC				0xc4
 #define UVSCC				0xc8
 #define ERASE_OPCODE_SHIFT		8
@@ -187,12 +191,16 @@ static void intel_spi_dump_regs(struct intel_spi *ispi)
 		dev_dbg(ispi->dev, "PR(%d)=0x%08x\n", i,
 			readl(ispi->pregs + PR(i)));
 
-	value = readl(ispi->sregs + SSFSTS_CTL);
-	dev_dbg(ispi->dev, "SSFSTS_CTL=0x%08x\n", value);
-	dev_dbg(ispi->dev, "PREOP_OPTYPE=0x%08x\n",
-		readl(ispi->sregs + PREOP_OPTYPE));
-	dev_dbg(ispi->dev, "OPMENU0=0x%08x\n", readl(ispi->sregs + OPMENU0));
-	dev_dbg(ispi->dev, "OPMENU1=0x%08x\n", readl(ispi->sregs + OPMENU1));
+	if (ispi->sregs) {
+		value = readl(ispi->sregs + SSFSTS_CTL);
+		dev_dbg(ispi->dev, "SSFSTS_CTL=0x%08x\n", value);
+		dev_dbg(ispi->dev, "PREOP_OPTYPE=0x%08x\n",
+			readl(ispi->sregs + PREOP_OPTYPE));
+		dev_dbg(ispi->dev, "OPMENU0=0x%08x\n",
+			readl(ispi->sregs + OPMENU0));
+		dev_dbg(ispi->dev, "OPMENU1=0x%08x\n",
+			readl(ispi->sregs + OPMENU1));
+	}
 
 	if (ispi->info->type == INTEL_SPI_BYT)
 		dev_dbg(ispi->dev, "BCR=0x%08x\n", readl(ispi->base + BYT_BCR));
@@ -340,6 +348,13 @@ static int intel_spi_init(struct intel_spi *ispi)
 		ispi->erase_64k = true;
 		break;
 
+	case INTEL_SPI_CNL:
+		ispi->sregs = NULL;
+		ispi->pregs = ispi->base + CNL_PR;
+		ispi->nregions = CNL_FREG_NUM;
+		ispi->pr_num = CNL_PR_NUM;
+		break;
+
 	default:
 		return -EINVAL;
 	}
@@ -367,6 +382,11 @@ static int intel_spi_init(struct intel_spi *ispi)
 		    !(uvscc & ERASE_64K_OPCODE_MASK))
 			ispi->erase_64k = false;
 
+	if (ispi->sregs == NULL && (ispi->swseq_reg || ispi->swseq_erase)) {
+		dev_err(ispi->dev, "software sequencer not supported, but required\n");
+		return -EINVAL;
+	}
+
 	/*
 	 * Some controllers can only do basic operations using hardware
 	 * sequencer. All other operations are supposed to be carried out
@@ -383,7 +403,7 @@ static int intel_spi_init(struct intel_spi *ispi)
 	val = readl(ispi->base + HSFSTS_CTL);
 	ispi->locked = !!(val & HSFSTS_CTL_FLOCKDN);
 
-	if (ispi->locked) {
+	if (ispi->locked && ispi->sregs) {
 		/*
 		 * BIOS programs allowed opcodes and then locks down the
 		 * register. So read back what opcodes it decided to support.
@@ -426,7 +446,7 @@ static int intel_spi_opcode_index(struct intel_spi *ispi, u8 opcode, int optype)
 	return 0;
 }
 
-static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, int len)
+static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, size_t len)
 {
 	u32 val, status;
 	int ret;
@@ -469,7 +489,7 @@ static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, int len)
 	return 0;
 }
 
-static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, int len,
+static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, size_t len,
 			      int optype)
 {
 	u32 val = 0, status;
@@ -535,7 +555,8 @@ static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, int len,
 	return 0;
 }
 
-static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
+			      size_t len)
 {
 	struct intel_spi *ispi = nor->priv;
 	int ret;
@@ -555,7 +576,8 @@ static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 	return intel_spi_read_block(ispi, buf, len);
 }
 
-static int intel_spi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int intel_spi_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf,
+			       size_t len)
 {
 	struct intel_spi *ispi = nor->priv;
 	int ret;
@@ -864,6 +886,14 @@ static void intel_spi_fill_partition(struct intel_spi *ispi,
 	}
 }
 
+static const struct spi_nor_controller_ops intel_spi_controller_ops = {
+	.read_reg = intel_spi_read_reg,
+	.write_reg = intel_spi_write_reg,
+	.read = intel_spi_read,
+	.write = intel_spi_write,
+	.erase = intel_spi_erase,
+};
+
 struct intel_spi *intel_spi_probe(struct device *dev,
 	struct resource *mem, const struct intel_spi_boardinfo *info)
 {
@@ -897,11 +927,7 @@ struct intel_spi *intel_spi_probe(struct device *dev,
 
 	ispi->nor.dev = ispi->dev;
 	ispi->nor.priv = ispi;
-	ispi->nor.read_reg = intel_spi_read_reg;
-	ispi->nor.write_reg = intel_spi_write_reg;
-	ispi->nor.read = intel_spi_read;
-	ispi->nor.write = intel_spi_write;
-	ispi->nor.erase = intel_spi_erase;
+	ispi->nor.controller_ops = &intel_spi_controller_ops;
 
 	ret = spi_nor_scan(&ispi->nor, NULL, &hwcaps);
 	if (ret) {
diff --git a/drivers/mtd/spi-nor/mtk-quadspi.c b/drivers/mtd/spi-nor/mtk-quadspi.c
index 34db01ab6cab..b1691680d174 100644
--- a/drivers/mtd/spi-nor/mtk-quadspi.c
+++ b/drivers/mtd/spi-nor/mtk-quadspi.c
@@ -151,9 +151,9 @@ static int mtk_nor_execute_cmd(struct mtk_nor *mtk_nor, u8 cmdval)
 }
 
 static int mtk_nor_do_tx_rx(struct mtk_nor *mtk_nor, u8 op,
-			    u8 *tx, int txlen, u8 *rx, int rxlen)
+			    const u8 *tx, size_t txlen, u8 *rx, size_t rxlen)
 {
-	int len = 1 + txlen + rxlen;
+	size_t len = 1 + txlen + rxlen;
 	int i, ret, idx;
 
 	if (len > MTK_NOR_MAX_SHIFT)
@@ -193,7 +193,7 @@ static int mtk_nor_do_tx_rx(struct mtk_nor *mtk_nor, u8 op,
 }
 
 /* Do a WRSR (Write Status Register) command */
-static int mtk_nor_wr_sr(struct mtk_nor *mtk_nor, u8 sr)
+static int mtk_nor_wr_sr(struct mtk_nor *mtk_nor, const u8 sr)
 {
 	writeb(sr, mtk_nor->base + MTK_NOR_PRGDATA5_REG);
 	writeb(8, mtk_nor->base + MTK_NOR_CNT_REG);
@@ -354,7 +354,7 @@ static ssize_t mtk_nor_write(struct spi_nor *nor, loff_t to, size_t len,
 	return len;
 }
 
-static int mtk_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int mtk_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, size_t len)
 {
 	int ret;
 	struct mtk_nor *mtk_nor = nor->priv;
@@ -376,8 +376,8 @@ static int mtk_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 	return ret;
 }
 
-static int mtk_nor_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
-			     int len)
+static int mtk_nor_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf,
+			     size_t len)
 {
 	int ret;
 	struct mtk_nor *mtk_nor = nor->priv;
@@ -419,6 +419,13 @@ static int mtk_nor_enable_clk(struct mtk_nor *mtk_nor)
 	return 0;
 }
 
+static const struct spi_nor_controller_ops mtk_controller_ops = {
+	.read_reg = mtk_nor_read_reg,
+	.write_reg = mtk_nor_write_reg,
+	.read = mtk_nor_read,
+	.write = mtk_nor_write,
+};
+
 static int mtk_nor_init(struct mtk_nor *mtk_nor,
 			struct device_node *flash_node)
 {
@@ -438,12 +445,8 @@ static int mtk_nor_init(struct mtk_nor *mtk_nor,
 	nor->dev = mtk_nor->dev;
 	nor->priv = mtk_nor;
 	spi_nor_set_flash_node(nor, flash_node);
+	nor->controller_ops = &mtk_controller_ops;
 
-	/* fill the hooks to spi nor */
-	nor->read = mtk_nor_read;
-	nor->read_reg = mtk_nor_read_reg;
-	nor->write = mtk_nor_write;
-	nor->write_reg = mtk_nor_write_reg;
 	nor->mtd.name = "mtk_nor";
 	/* initialized with NULL */
 	ret = spi_nor_scan(nor, NULL, &hwcaps);
diff --git a/drivers/mtd/spi-nor/nxp-spifi.c b/drivers/mtd/spi-nor/nxp-spifi.c
index 4a871587392b..9a5b1a7c636a 100644
--- a/drivers/mtd/spi-nor/nxp-spifi.c
+++ b/drivers/mtd/spi-nor/nxp-spifi.c
@@ -123,7 +123,8 @@ static int nxp_spifi_set_memory_mode_on(struct nxp_spifi *spifi)
 	return ret;
 }
 
-static int nxp_spifi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int nxp_spifi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
+			      size_t len)
 {
 	struct nxp_spifi *spifi = nor->priv;
 	u32 cmd;
@@ -145,7 +146,8 @@ static int nxp_spifi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 	return nxp_spifi_wait_for_cmd(spifi);
 }
 
-static int nxp_spifi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int nxp_spifi_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf,
+			       size_t len)
 {
 	struct nxp_spifi *spifi = nor->priv;
 	u32 cmd;
@@ -263,9 +265,18 @@ static int nxp_spifi_setup_memory_cmd(struct nxp_spifi *spifi)
 static void nxp_spifi_dummy_id_read(struct spi_nor *nor)
 {
 	u8 id[SPI_NOR_MAX_ID_LEN];
-	nor->read_reg(nor, SPINOR_OP_RDID, id, SPI_NOR_MAX_ID_LEN);
+	nor->controller_ops->read_reg(nor, SPINOR_OP_RDID, id,
+				      SPI_NOR_MAX_ID_LEN);
 }
 
+static const struct spi_nor_controller_ops nxp_spifi_controller_ops = {
+	.read_reg  = nxp_spifi_read_reg,
+	.write_reg = nxp_spifi_write_reg,
+	.read  = nxp_spifi_read,
+	.write = nxp_spifi_write,
+	.erase = nxp_spifi_erase,
+};
+
 static int nxp_spifi_setup_flash(struct nxp_spifi *spifi,
 				 struct device_node *np)
 {
@@ -332,11 +343,7 @@ static int nxp_spifi_setup_flash(struct nxp_spifi *spifi,
 	spifi->nor.dev   = spifi->dev;
 	spi_nor_set_flash_node(&spifi->nor, np);
 	spifi->nor.priv  = spifi;
-	spifi->nor.read  = nxp_spifi_read;
-	spifi->nor.write = nxp_spifi_write;
-	spifi->nor.erase = nxp_spifi_erase;
-	spifi->nor.read_reg  = nxp_spifi_read_reg;
-	spifi->nor.write_reg = nxp_spifi_write_reg;
+	spifi->nor.controller_ops = &nxp_spifi_controller_ops;
 
 	/*
 	 * The first read on a hard reset isn't reliable so do a
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 7acf4a93b592..f4afe123e9dc 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -338,7 +338,7 @@ static ssize_t spi_nor_read_data(struct spi_nor *nor, loff_t from, size_t len,
 	if (nor->spimem)
 		return spi_nor_spimem_read_data(nor, from, len, buf);
 
-	return nor->read(nor, from, len, buf);
+	return nor->controller_ops->read(nor, from, len, buf);
 }
 
 /**
@@ -385,239 +385,172 @@ static ssize_t spi_nor_write_data(struct spi_nor *nor, loff_t to, size_t len,
 	if (nor->spimem)
 		return spi_nor_spimem_write_data(nor, to, len, buf);
 
-	return nor->write(nor, to, len, buf);
+	return nor->controller_ops->write(nor, to, len, buf);
 }
 
-/*
- * Read the status register, returning its value in the location
- * Return the status register value.
- * Returns negative if error occurred.
+/**
+ * spi_nor_write_enable() - Set write enable latch with Write Enable command.
+ * @nor:	pointer to 'struct spi_nor'.
+ *
+ * Return: 0 on success, -errno otherwise.
  */
-static int read_sr(struct spi_nor *nor)
+static int spi_nor_write_enable(struct spi_nor *nor)
 {
 	int ret;
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WREN, 1),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_IN(1, nor->bouncebuf, 1));
+				   SPI_MEM_OP_NO_DATA);
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
-		ret = nor->read_reg(nor, SPINOR_OP_RDSR, nor->bouncebuf, 1);
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WREN,
+						     NULL, 0);
 	}
 
-	if (ret < 0) {
-		pr_err("error %d reading SR\n", (int) ret);
-		return ret;
-	}
+	if (ret)
+		dev_dbg(nor->dev, "error %d on Write Enable\n", ret);
 
-	return nor->bouncebuf[0];
+	return ret;
 }
 
-/*
- * Read the flag status register, returning its value in the location
- * Return the status register value.
- * Returns negative if error occurred.
+/**
+ * spi_nor_write_disable() - Send Write Disable instruction to the chip.
+ * @nor:	pointer to 'struct spi_nor'.
+ *
+ * Return: 0 on success, -errno otherwise.
  */
-static int read_fsr(struct spi_nor *nor)
+static int spi_nor_write_disable(struct spi_nor *nor)
 {
 	int ret;
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDFSR, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRDI, 1),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_IN(1, nor->bouncebuf, 1));
+				   SPI_MEM_OP_NO_DATA);
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
-		ret = nor->read_reg(nor, SPINOR_OP_RDFSR, nor->bouncebuf, 1);
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WRDI,
+						     NULL, 0);
 	}
 
-	if (ret < 0) {
-		pr_err("error %d reading FSR\n", ret);
-		return ret;
-	}
+	if (ret)
+		dev_dbg(nor->dev, "error %d on Write Disable\n", ret);
 
-	return nor->bouncebuf[0];
+	return ret;
 }
 
-/*
- * Read configuration register, returning its value in the
- * location. Return the configuration register value.
- * Returns negative if error occurred.
+/**
+ * spi_nor_read_sr() - Read the Status Register.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @sr:		pointer to a DMA-able buffer where the value of the
+ *              Status Register will be written.
+ *
+ * Return: 0 on success, -errno otherwise.
  */
-static int read_cr(struct spi_nor *nor)
+static int spi_nor_read_sr(struct spi_nor *nor, u8 *sr)
 {
 	int ret;
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDCR, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR, 1),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_IN(1, nor->bouncebuf, 1));
+				   SPI_MEM_OP_DATA_IN(1, sr, 1));
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
-		ret = nor->read_reg(nor, SPINOR_OP_RDCR, nor->bouncebuf, 1);
+		ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDSR,
+						    sr, 1);
 	}
 
-	if (ret < 0) {
-		dev_err(nor->dev, "error %d reading CR\n", ret);
-		return ret;
-	}
+	if (ret)
+		dev_dbg(nor->dev, "error %d reading SR\n", ret);
 
-	return nor->bouncebuf[0];
+	return ret;
 }
 
-/*
- * Write status register 1 byte
- * Returns negative if error occurred.
+/**
+ * spi_nor_read_fsr() - Read the Flag Status Register.
+ * @nor:	pointer to 'struct spi_nor'
+ * @fsr:	pointer to a DMA-able buffer where the value of the
+ *              Flag Status Register will be written.
+ *
+ * Return: 0 on success, -errno otherwise.
  */
-static int write_sr(struct spi_nor *nor, u8 val)
+static int spi_nor_read_fsr(struct spi_nor *nor, u8 *fsr)
 {
-	nor->bouncebuf[0] = val;
-	if (nor->spimem) {
-		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR, 1),
-				   SPI_MEM_OP_NO_ADDR,
-				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 1));
-
-		return spi_mem_exec_op(nor->spimem, &op);
-	}
-
-	return nor->write_reg(nor, SPINOR_OP_WRSR, nor->bouncebuf, 1);
-}
+	int ret;
 
-/*
- * Set write enable latch with Write Enable command.
- * Returns negative if error occurred.
- */
-static int write_enable(struct spi_nor *nor)
-{
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WREN, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDFSR, 1),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_NO_DATA);
+				   SPI_MEM_OP_DATA_IN(1, fsr, 1));
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDFSR,
+						    fsr, 1);
 	}
 
-	return nor->write_reg(nor, SPINOR_OP_WREN, NULL, 0);
+	if (ret)
+		dev_dbg(nor->dev, "error %d reading FSR\n", ret);
+
+	return ret;
 }
 
-/*
- * Send write disable instruction to the chip.
+/**
+ * spi_nor_read_cr() - Read the Configuration Register using the
+ * SPINOR_OP_RDCR (35h) command.
+ * @nor:	pointer to 'struct spi_nor'
+ * @cr:		pointer to a DMA-able buffer where the value of the
+ *              Configuration Register will be written.
+ *
+ * Return: 0 on success, -errno otherwise.
  */
-static int write_disable(struct spi_nor *nor)
+static int spi_nor_read_cr(struct spi_nor *nor, u8 *cr)
 {
+	int ret;
+
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRDI, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDCR, 1),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_NO_DATA);
+				   SPI_MEM_OP_DATA_IN(1, cr, 1));
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDCR, cr, 1);
 	}
 
-	return nor->write_reg(nor, SPINOR_OP_WRDI, NULL, 0);
-}
-
-static struct spi_nor *mtd_to_spi_nor(struct mtd_info *mtd)
-{
-	return mtd->priv;
-}
-
-
-static u8 spi_nor_convert_opcode(u8 opcode, const u8 table[][2], size_t size)
-{
-	size_t i;
-
-	for (i = 0; i < size; i++)
-		if (table[i][0] == opcode)
-			return table[i][1];
-
-	/* No conversion found, keep input op code. */
-	return opcode;
-}
-
-static u8 spi_nor_convert_3to4_read(u8 opcode)
-{
-	static const u8 spi_nor_3to4_read[][2] = {
-		{ SPINOR_OP_READ,	SPINOR_OP_READ_4B },
-		{ SPINOR_OP_READ_FAST,	SPINOR_OP_READ_FAST_4B },
-		{ SPINOR_OP_READ_1_1_2,	SPINOR_OP_READ_1_1_2_4B },
-		{ SPINOR_OP_READ_1_2_2,	SPINOR_OP_READ_1_2_2_4B },
-		{ SPINOR_OP_READ_1_1_4,	SPINOR_OP_READ_1_1_4_4B },
-		{ SPINOR_OP_READ_1_4_4,	SPINOR_OP_READ_1_4_4_4B },
-		{ SPINOR_OP_READ_1_1_8,	SPINOR_OP_READ_1_1_8_4B },
-		{ SPINOR_OP_READ_1_8_8,	SPINOR_OP_READ_1_8_8_4B },
-
-		{ SPINOR_OP_READ_1_1_1_DTR,	SPINOR_OP_READ_1_1_1_DTR_4B },
-		{ SPINOR_OP_READ_1_2_2_DTR,	SPINOR_OP_READ_1_2_2_DTR_4B },
-		{ SPINOR_OP_READ_1_4_4_DTR,	SPINOR_OP_READ_1_4_4_DTR_4B },
-	};
-
-	return spi_nor_convert_opcode(opcode, spi_nor_3to4_read,
-				      ARRAY_SIZE(spi_nor_3to4_read));
-}
-
-static u8 spi_nor_convert_3to4_program(u8 opcode)
-{
-	static const u8 spi_nor_3to4_program[][2] = {
-		{ SPINOR_OP_PP,		SPINOR_OP_PP_4B },
-		{ SPINOR_OP_PP_1_1_4,	SPINOR_OP_PP_1_1_4_4B },
-		{ SPINOR_OP_PP_1_4_4,	SPINOR_OP_PP_1_4_4_4B },
-		{ SPINOR_OP_PP_1_1_8,	SPINOR_OP_PP_1_1_8_4B },
-		{ SPINOR_OP_PP_1_8_8,	SPINOR_OP_PP_1_8_8_4B },
-	};
-
-	return spi_nor_convert_opcode(opcode, spi_nor_3to4_program,
-				      ARRAY_SIZE(spi_nor_3to4_program));
-}
-
-static u8 spi_nor_convert_3to4_erase(u8 opcode)
-{
-	static const u8 spi_nor_3to4_erase[][2] = {
-		{ SPINOR_OP_BE_4K,	SPINOR_OP_BE_4K_4B },
-		{ SPINOR_OP_BE_32K,	SPINOR_OP_BE_32K_4B },
-		{ SPINOR_OP_SE,		SPINOR_OP_SE_4B },
-	};
-
-	return spi_nor_convert_opcode(opcode, spi_nor_3to4_erase,
-				      ARRAY_SIZE(spi_nor_3to4_erase));
-}
-
-static void spi_nor_set_4byte_opcodes(struct spi_nor *nor)
-{
-	nor->read_opcode = spi_nor_convert_3to4_read(nor->read_opcode);
-	nor->program_opcode = spi_nor_convert_3to4_program(nor->program_opcode);
-	nor->erase_opcode = spi_nor_convert_3to4_erase(nor->erase_opcode);
-
-	if (!spi_nor_has_uniform_erase(nor)) {
-		struct spi_nor_erase_map *map = &nor->params.erase_map;
-		struct spi_nor_erase_type *erase;
-		int i;
+	if (ret)
+		dev_dbg(nor->dev, "error %d reading CR\n", ret);
 
-		for (i = 0; i < SNOR_ERASE_TYPE_MAX; i++) {
-			erase = &map->erase_type[i];
-			erase->opcode =
-				spi_nor_convert_3to4_erase(erase->opcode);
-		}
-	}
+	return ret;
 }
 
+/**
+ * macronix_set_4byte() - Set 4-byte address mode for Macronix flashes.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @enable:	true to enter the 4-byte address mode, false to exit the 4-byte
+ *		address mode.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int macronix_set_4byte(struct spi_nor *nor, bool enable)
 {
+	int ret;
+
 	if (nor->spimem) {
 		struct spi_mem_op op =
 			SPI_MEM_OP(SPI_MEM_OP_CMD(enable ?
@@ -628,26 +561,55 @@ static int macronix_set_4byte(struct spi_nor *nor, bool enable)
 				  SPI_MEM_OP_NO_DUMMY,
 				  SPI_MEM_OP_NO_DATA);
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor,
+						     enable ? SPINOR_OP_EN4B :
+							      SPINOR_OP_EX4B,
+						     NULL, 0);
 	}
 
-	return nor->write_reg(nor, enable ? SPINOR_OP_EN4B : SPINOR_OP_EX4B,
-			      NULL, 0);
+	if (ret)
+		dev_dbg(nor->dev, "error %d setting 4-byte mode\n", ret);
+
+	return ret;
 }
 
+/**
+ * st_micron_set_4byte() - Set 4-byte address mode for ST and Micron flashes.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @enable:	true to enter the 4-byte address mode, false to exit the 4-byte
+ *		address mode.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int st_micron_set_4byte(struct spi_nor *nor, bool enable)
 {
 	int ret;
 
-	write_enable(nor);
+	ret = spi_nor_write_enable(nor);
+	if (ret)
+		return ret;
+
 	ret = macronix_set_4byte(nor, enable);
-	write_disable(nor);
+	if (ret)
+		return ret;
 
-	return ret;
+	return spi_nor_write_disable(nor);
 }
 
+/**
+ * spansion_set_4byte() - Set 4-byte address mode for Spansion flashes.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @enable:	true to enter the 4-byte address mode, false to exit the 4-byte
+ *		address mode.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int spansion_set_4byte(struct spi_nor *nor, bool enable)
 {
+	int ret;
+
 	nor->bouncebuf[0] = enable << 7;
 
 	if (nor->spimem) {
@@ -657,14 +619,29 @@ static int spansion_set_4byte(struct spi_nor *nor, bool enable)
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 1));
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_BRWR,
+						     nor->bouncebuf, 1);
 	}
 
-	return nor->write_reg(nor, SPINOR_OP_BRWR, nor->bouncebuf, 1);
+	if (ret)
+		dev_dbg(nor->dev, "error %d setting 4-byte mode\n", ret);
+
+	return ret;
 }
 
+/**
+ * spi_nor_write_ear() - Write Extended Address Register.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @ear:	value to write to the Extended Address Register.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int spi_nor_write_ear(struct spi_nor *nor, u8 ear)
 {
+	int ret;
+
 	nor->bouncebuf[0] = ear;
 
 	if (nor->spimem) {
@@ -674,12 +651,26 @@ static int spi_nor_write_ear(struct spi_nor *nor, u8 ear)
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 1));
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WREAR,
+						     nor->bouncebuf, 1);
 	}
 
-	return nor->write_reg(nor, SPINOR_OP_WREAR, nor->bouncebuf, 1);
+	if (ret)
+		dev_dbg(nor->dev, "error %d writing EAR\n", ret);
+
+	return ret;
 }
 
+/**
+ * winbond_set_4byte() - Set 4-byte address mode for Winbond flashes.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @enable:	true to enter the 4-byte address mode, false to exit the 4-byte
+ *		address mode.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int winbond_set_4byte(struct spi_nor *nor, bool enable)
 {
 	int ret;
@@ -693,15 +684,29 @@ static int winbond_set_4byte(struct spi_nor *nor, bool enable)
 	 * Register to be set to 1, so all 3-byte-address reads come from the
 	 * second 16M. We must clear the register to enable normal behavior.
 	 */
-	write_enable(nor);
+	ret = spi_nor_write_enable(nor);
+	if (ret)
+		return ret;
+
 	ret = spi_nor_write_ear(nor, 0);
-	write_disable(nor);
+	if (ret)
+		return ret;
 
-	return ret;
+	return spi_nor_write_disable(nor);
 }
 
+/**
+ * spi_nor_xread_sr() - Read the Status Register on S3AN flashes.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @sr:		pointer to a DMA-able buffer where the value of the
+ *              Status Register will be written.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int spi_nor_xread_sr(struct spi_nor *nor, u8 *sr)
 {
+	int ret;
+
 	if (nor->spimem) {
 		struct spi_mem_op op =
 			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_XRDSR, 1),
@@ -709,27 +714,44 @@ static int spi_nor_xread_sr(struct spi_nor *nor, u8 *sr)
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_DATA_IN(1, sr, 1));
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->read_reg(nor, SPINOR_OP_XRDSR,
+						    sr, 1);
 	}
 
-	return nor->read_reg(nor, SPINOR_OP_XRDSR, sr, 1);
+	if (ret)
+		dev_dbg(nor->dev, "error %d reading XRDSR\n", ret);
+
+	return ret;
 }
 
+/**
+ * s3an_sr_ready() - Query the Status Register of the S3AN flash to see if the
+ * flash is ready for new commands.
+ * @nor:	pointer to 'struct spi_nor'.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int s3an_sr_ready(struct spi_nor *nor)
 {
 	int ret;
 
 	ret = spi_nor_xread_sr(nor, nor->bouncebuf);
-	if (ret < 0) {
-		dev_err(nor->dev, "error %d reading XRDSR\n", (int) ret);
+	if (ret)
 		return ret;
-	}
 
 	return !!(nor->bouncebuf[0] & XSR_RDY);
 }
 
-static int spi_nor_clear_sr(struct spi_nor *nor)
+/**
+ * spi_nor_clear_sr() - Clear the Status Register.
+ * @nor:	pointer to 'struct spi_nor'.
+ */
+static void spi_nor_clear_sr(struct spi_nor *nor)
 {
+	int ret;
+
 	if (nor->spimem) {
 		struct spi_mem_op op =
 			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CLSR, 1),
@@ -737,20 +759,33 @@ static int spi_nor_clear_sr(struct spi_nor *nor)
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_NO_DATA);
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_CLSR,
+						     NULL, 0);
 	}
 
-	return nor->write_reg(nor, SPINOR_OP_CLSR, NULL, 0);
+	if (ret)
+		dev_dbg(nor->dev, "error %d clearing SR\n", ret);
 }
 
+/**
+ * spi_nor_sr_ready() - Query the Status Register to see if the flash is ready
+ * for new commands.
+ * @nor:	pointer to 'struct spi_nor'.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int spi_nor_sr_ready(struct spi_nor *nor)
 {
-	int sr = read_sr(nor);
-	if (sr < 0)
-		return sr;
+	int ret = spi_nor_read_sr(nor, nor->bouncebuf);
+
+	if (ret)
+		return ret;
 
-	if (nor->flags & SNOR_F_USE_CLSR && sr & (SR_E_ERR | SR_P_ERR)) {
-		if (sr & SR_E_ERR)
+	if (nor->flags & SNOR_F_USE_CLSR &&
+	    nor->bouncebuf[0] & (SR_E_ERR | SR_P_ERR)) {
+		if (nor->bouncebuf[0] & SR_E_ERR)
 			dev_err(nor->dev, "Erase Error occurred\n");
 		else
 			dev_err(nor->dev, "Programming Error occurred\n");
@@ -759,11 +794,17 @@ static int spi_nor_sr_ready(struct spi_nor *nor)
 		return -EIO;
 	}
 
-	return !(sr & SR_WIP);
+	return !(nor->bouncebuf[0] & SR_WIP);
 }
 
-static int spi_nor_clear_fsr(struct spi_nor *nor)
+/**
+ * spi_nor_clear_fsr() - Clear the Flag Status Register.
+ * @nor:	pointer to 'struct spi_nor'.
+ */
+static void spi_nor_clear_fsr(struct spi_nor *nor)
 {
+	int ret;
+
 	if (nor->spimem) {
 		struct spi_mem_op op =
 			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CLFSR, 1),
@@ -771,25 +812,37 @@ static int spi_nor_clear_fsr(struct spi_nor *nor)
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_NO_DATA);
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_CLFSR,
+						     NULL, 0);
 	}
 
-	return nor->write_reg(nor, SPINOR_OP_CLFSR, NULL, 0);
+	if (ret)
+		dev_dbg(nor->dev, "error %d clearing FSR\n", ret);
 }
 
+/**
+ * spi_nor_fsr_ready() - Query the Flag Status Register to see if the flash is
+ * ready for new commands.
+ * @nor:	pointer to 'struct spi_nor'.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int spi_nor_fsr_ready(struct spi_nor *nor)
 {
-	int fsr = read_fsr(nor);
-	if (fsr < 0)
-		return fsr;
+	int ret = spi_nor_read_fsr(nor, nor->bouncebuf);
 
-	if (fsr & (FSR_E_ERR | FSR_P_ERR)) {
-		if (fsr & FSR_E_ERR)
+	if (ret)
+		return ret;
+
+	if (nor->bouncebuf[0] & (FSR_E_ERR | FSR_P_ERR)) {
+		if (nor->bouncebuf[0] & FSR_E_ERR)
 			dev_err(nor->dev, "Erase operation failed.\n");
 		else
 			dev_err(nor->dev, "Program operation failed.\n");
 
-		if (fsr & FSR_PT_ERR)
+		if (nor->bouncebuf[0] & FSR_PT_ERR)
 			dev_err(nor->dev,
 			"Attempted to modify a protected sector.\n");
 
@@ -797,9 +850,15 @@ static int spi_nor_fsr_ready(struct spi_nor *nor)
 		return -EIO;
 	}
 
-	return fsr & FSR_READY;
+	return nor->bouncebuf[0] & FSR_READY;
 }
 
+/**
+ * spi_nor_ready() - Query the flash to see if it is ready for new commands.
+ * @nor:	pointer to 'struct spi_nor'.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int spi_nor_ready(struct spi_nor *nor)
 {
 	int sr, fsr;
@@ -816,9 +875,13 @@ static int spi_nor_ready(struct spi_nor *nor)
 	return sr && fsr;
 }
 
-/*
- * Service routine to read status register until ready, or timeout occurs.
- * Returns non-zero if error.
+/**
+ * spi_nor_wait_till_ready_with_timeout() - Service routine to read the
+ * Status Register until ready, or timeout occurs.
+ * @nor:		pointer to "struct spi_nor".
+ * @timeout_jiffies:	jiffies to wait until timeout.
+ *
+ * Return: 0 on success, -errno otherwise.
  */
 static int spi_nor_wait_till_ready_with_timeout(struct spi_nor *nor,
 						unsigned long timeout_jiffies)
@@ -841,24 +904,305 @@ static int spi_nor_wait_till_ready_with_timeout(struct spi_nor *nor,
 		cond_resched();
 	}
 
-	dev_err(nor->dev, "flash operation timed out\n");
+	dev_dbg(nor->dev, "flash operation timed out\n");
 
 	return -ETIMEDOUT;
 }
 
+/**
+ * spi_nor_wait_till_ready() - Wait for a predefined amount of time for the
+ * flash to be ready, or timeout occurs.
+ * @nor:	pointer to "struct spi_nor".
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int spi_nor_wait_till_ready(struct spi_nor *nor)
 {
 	return spi_nor_wait_till_ready_with_timeout(nor,
 						    DEFAULT_READY_WAIT_JIFFIES);
 }
 
-/*
- * Erase the whole flash memory
+/**
+ * spi_nor_write_sr() - Write the Status Register.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @sr:		pointer to DMA-able buffer to write to the Status Register.
+ * @len:	number of bytes to write to the Status Register.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int spi_nor_write_sr(struct spi_nor *nor, const u8 *sr, size_t len)
+{
+	int ret;
+
+	ret = spi_nor_write_enable(nor);
+	if (ret)
+		return ret;
+
+	if (nor->spimem) {
+		struct spi_mem_op op =
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR, 1),
+				   SPI_MEM_OP_NO_ADDR,
+				   SPI_MEM_OP_NO_DUMMY,
+				   SPI_MEM_OP_DATA_OUT(len, sr, 1));
+
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WRSR,
+						     sr, len);
+	}
+
+	if (ret) {
+		dev_dbg(nor->dev, "error %d writing SR\n", ret);
+		return ret;
+	}
+
+	return spi_nor_wait_till_ready(nor);
+}
+
+/**
+ * spi_nor_write_sr1_and_check() - Write one byte to the Status Register 1 and
+ * ensure that the byte written match the received value.
+ * @nor:	pointer to a 'struct spi_nor'.
+ * @sr1:	byte value to be written to the Status Register.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int spi_nor_write_sr1_and_check(struct spi_nor *nor, u8 sr1)
+{
+	int ret;
+
+	nor->bouncebuf[0] = sr1;
+
+	ret = spi_nor_write_sr(nor, nor->bouncebuf, 1);
+	if (ret)
+		return ret;
+
+	ret = spi_nor_read_sr(nor, nor->bouncebuf);
+	if (ret)
+		return ret;
+
+	if (nor->bouncebuf[0] != sr1) {
+		dev_dbg(nor->dev, "SR1: read back test failed\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * spi_nor_write_16bit_sr_and_check() - Write the Status Register 1 and the
+ * Status Register 2 in one shot. Ensure that the byte written in the Status
+ * Register 1 match the received value, and that the 16-bit Write did not
+ * affect what was already in the Status Register 2.
+ * @nor:	pointer to a 'struct spi_nor'.
+ * @sr1:	byte value to be written to the Status Register 1.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int spi_nor_write_16bit_sr_and_check(struct spi_nor *nor, u8 sr1)
+{
+	int ret;
+	u8 *sr_cr = nor->bouncebuf;
+	u8 cr_written;
+
+	/* Make sure we don't overwrite the contents of Status Register 2. */
+	if (!(nor->flags & SNOR_F_NO_READ_CR)) {
+		ret = spi_nor_read_cr(nor, &sr_cr[1]);
+		if (ret)
+			return ret;
+	} else if (nor->params.quad_enable) {
+		/*
+		 * If the Status Register 2 Read command (35h) is not
+		 * supported, we should at least be sure we don't
+		 * change the value of the SR2 Quad Enable bit.
+		 *
+		 * We can safely assume that when the Quad Enable method is
+		 * set, the value of the QE bit is one, as a consequence of the
+		 * nor->params.quad_enable() call.
+		 *
+		 * We can safely assume that the Quad Enable bit is present in
+		 * the Status Register 2 at BIT(1). According to the JESD216
+		 * revB standard, BFPT DWORDS[15], bits 22:20, the 16-bit
+		 * Write Status (01h) command is available just for the cases
+		 * in which the QE bit is described in SR2 at BIT(1).
+		 */
+		sr_cr[1] = SR2_QUAD_EN_BIT1;
+	} else {
+		sr_cr[1] = 0;
+	}
+
+	sr_cr[0] = sr1;
+
+	ret = spi_nor_write_sr(nor, sr_cr, 2);
+	if (ret)
+		return ret;
+
+	if (nor->flags & SNOR_F_NO_READ_CR)
+		return 0;
+
+	cr_written = sr_cr[1];
+
+	ret = spi_nor_read_cr(nor, &sr_cr[1]);
+	if (ret)
+		return ret;
+
+	if (cr_written != sr_cr[1]) {
+		dev_dbg(nor->dev, "CR: read back test failed\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * spi_nor_write_16bit_cr_and_check() - Write the Status Register 1 and the
+ * Configuration Register in one shot. Ensure that the byte written in the
+ * Configuration Register match the received value, and that the 16-bit Write
+ * did not affect what was already in the Status Register 1.
+ * @nor:	pointer to a 'struct spi_nor'.
+ * @cr:		byte value to be written to the Configuration Register.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int spi_nor_write_16bit_cr_and_check(struct spi_nor *nor, u8 cr)
+{
+	int ret;
+	u8 *sr_cr = nor->bouncebuf;
+	u8 sr_written;
+
+	/* Keep the current value of the Status Register 1. */
+	ret = spi_nor_read_sr(nor, sr_cr);
+	if (ret)
+		return ret;
+
+	sr_cr[1] = cr;
+
+	ret = spi_nor_write_sr(nor, sr_cr, 2);
+	if (ret)
+		return ret;
+
+	sr_written = sr_cr[0];
+
+	ret = spi_nor_read_sr(nor, sr_cr);
+	if (ret)
+		return ret;
+
+	if (sr_written != sr_cr[0]) {
+		dev_dbg(nor->dev, "SR: Read back test failed\n");
+		return -EIO;
+	}
+
+	if (nor->flags & SNOR_F_NO_READ_CR)
+		return 0;
+
+	ret = spi_nor_read_cr(nor, &sr_cr[1]);
+	if (ret)
+		return ret;
+
+	if (cr != sr_cr[1]) {
+		dev_dbg(nor->dev, "CR: read back test failed\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * spi_nor_write_sr_and_check() - Write the Status Register 1 and ensure that
+ * the byte written match the received value without affecting other bits in the
+ * Status Register 1 and 2.
+ * @nor:	pointer to a 'struct spi_nor'.
+ * @sr1:	byte value to be written to the Status Register.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int spi_nor_write_sr_and_check(struct spi_nor *nor, u8 sr1)
+{
+	if (nor->flags & SNOR_F_HAS_16BIT_SR)
+		return spi_nor_write_16bit_sr_and_check(nor, sr1);
+
+	return spi_nor_write_sr1_and_check(nor, sr1);
+}
+
+/**
+ * spi_nor_write_sr2() - Write the Status Register 2 using the
+ * SPINOR_OP_WRSR2 (3eh) command.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @sr2:	pointer to DMA-able buffer to write to the Status Register 2.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int spi_nor_write_sr2(struct spi_nor *nor, const u8 *sr2)
+{
+	int ret;
+
+	ret = spi_nor_write_enable(nor);
+	if (ret)
+		return ret;
+
+	if (nor->spimem) {
+		struct spi_mem_op op =
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR2, 1),
+				   SPI_MEM_OP_NO_ADDR,
+				   SPI_MEM_OP_NO_DUMMY,
+				   SPI_MEM_OP_DATA_OUT(1, sr2, 1));
+
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WRSR2,
+						     sr2, 1);
+	}
+
+	if (ret) {
+		dev_dbg(nor->dev, "error %d writing SR2\n", ret);
+		return ret;
+	}
+
+	return spi_nor_wait_till_ready(nor);
+}
+
+/**
+ * spi_nor_read_sr2() - Read the Status Register 2 using the
+ * SPINOR_OP_RDSR2 (3fh) command.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @sr2:	pointer to DMA-able buffer where the value of the
+ *		Status Register 2 will be written.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int spi_nor_read_sr2(struct spi_nor *nor, u8 *sr2)
+{
+	int ret;
+
+	if (nor->spimem) {
+		struct spi_mem_op op =
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR2, 1),
+				   SPI_MEM_OP_NO_ADDR,
+				   SPI_MEM_OP_NO_DUMMY,
+				   SPI_MEM_OP_DATA_IN(1, sr2, 1));
+
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDSR2,
+						    sr2, 1);
+	}
+
+	if (ret)
+		dev_dbg(nor->dev, "error %d reading SR2\n", ret);
+
+	return ret;
+}
+
+/**
+ * spi_nor_erase_chip() - Erase the entire flash memory.
+ * @nor:	pointer to 'struct spi_nor'.
  *
- * Returns 0 if successful, non-zero otherwise.
+ * Return: 0 on success, -errno otherwise.
  */
-static int erase_chip(struct spi_nor *nor)
+static int spi_nor_erase_chip(struct spi_nor *nor)
 {
+	int ret;
+
 	dev_dbg(nor->dev, " %lldKiB\n", (long long)(nor->mtd.size >> 10));
 
 	if (nor->spimem) {
@@ -868,10 +1212,99 @@ static int erase_chip(struct spi_nor *nor)
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_NO_DATA);
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_CHIP_ERASE,
+						     NULL, 0);
 	}
 
-	return nor->write_reg(nor, SPINOR_OP_CHIP_ERASE, NULL, 0);
+	if (ret)
+		dev_dbg(nor->dev, "error %d erasing chip\n", ret);
+
+	return ret;
+}
+
+static struct spi_nor *mtd_to_spi_nor(struct mtd_info *mtd)
+{
+	return mtd->priv;
+}
+
+static u8 spi_nor_convert_opcode(u8 opcode, const u8 table[][2], size_t size)
+{
+	size_t i;
+
+	for (i = 0; i < size; i++)
+		if (table[i][0] == opcode)
+			return table[i][1];
+
+	/* No conversion found, keep input op code. */
+	return opcode;
+}
+
+static u8 spi_nor_convert_3to4_read(u8 opcode)
+{
+	static const u8 spi_nor_3to4_read[][2] = {
+		{ SPINOR_OP_READ,	SPINOR_OP_READ_4B },
+		{ SPINOR_OP_READ_FAST,	SPINOR_OP_READ_FAST_4B },
+		{ SPINOR_OP_READ_1_1_2,	SPINOR_OP_READ_1_1_2_4B },
+		{ SPINOR_OP_READ_1_2_2,	SPINOR_OP_READ_1_2_2_4B },
+		{ SPINOR_OP_READ_1_1_4,	SPINOR_OP_READ_1_1_4_4B },
+		{ SPINOR_OP_READ_1_4_4,	SPINOR_OP_READ_1_4_4_4B },
+		{ SPINOR_OP_READ_1_1_8,	SPINOR_OP_READ_1_1_8_4B },
+		{ SPINOR_OP_READ_1_8_8,	SPINOR_OP_READ_1_8_8_4B },
+
+		{ SPINOR_OP_READ_1_1_1_DTR,	SPINOR_OP_READ_1_1_1_DTR_4B },
+		{ SPINOR_OP_READ_1_2_2_DTR,	SPINOR_OP_READ_1_2_2_DTR_4B },
+		{ SPINOR_OP_READ_1_4_4_DTR,	SPINOR_OP_READ_1_4_4_DTR_4B },
+	};
+
+	return spi_nor_convert_opcode(opcode, spi_nor_3to4_read,
+				      ARRAY_SIZE(spi_nor_3to4_read));
+}
+
+static u8 spi_nor_convert_3to4_program(u8 opcode)
+{
+	static const u8 spi_nor_3to4_program[][2] = {
+		{ SPINOR_OP_PP,		SPINOR_OP_PP_4B },
+		{ SPINOR_OP_PP_1_1_4,	SPINOR_OP_PP_1_1_4_4B },
+		{ SPINOR_OP_PP_1_4_4,	SPINOR_OP_PP_1_4_4_4B },
+		{ SPINOR_OP_PP_1_1_8,	SPINOR_OP_PP_1_1_8_4B },
+		{ SPINOR_OP_PP_1_8_8,	SPINOR_OP_PP_1_8_8_4B },
+	};
+
+	return spi_nor_convert_opcode(opcode, spi_nor_3to4_program,
+				      ARRAY_SIZE(spi_nor_3to4_program));
+}
+
+static u8 spi_nor_convert_3to4_erase(u8 opcode)
+{
+	static const u8 spi_nor_3to4_erase[][2] = {
+		{ SPINOR_OP_BE_4K,	SPINOR_OP_BE_4K_4B },
+		{ SPINOR_OP_BE_32K,	SPINOR_OP_BE_32K_4B },
+		{ SPINOR_OP_SE,		SPINOR_OP_SE_4B },
+	};
+
+	return spi_nor_convert_opcode(opcode, spi_nor_3to4_erase,
+				      ARRAY_SIZE(spi_nor_3to4_erase));
+}
+
+static void spi_nor_set_4byte_opcodes(struct spi_nor *nor)
+{
+	nor->read_opcode = spi_nor_convert_3to4_read(nor->read_opcode);
+	nor->program_opcode = spi_nor_convert_3to4_program(nor->program_opcode);
+	nor->erase_opcode = spi_nor_convert_3to4_erase(nor->erase_opcode);
+
+	if (!spi_nor_has_uniform_erase(nor)) {
+		struct spi_nor_erase_map *map = &nor->params.erase_map;
+		struct spi_nor_erase_type *erase;
+		int i;
+
+		for (i = 0; i < SNOR_ERASE_TYPE_MAX; i++) {
+			erase = &map->erase_type[i];
+			erase->opcode =
+				spi_nor_convert_3to4_erase(erase->opcode);
+		}
+	}
 }
 
 static int spi_nor_lock_and_prep(struct spi_nor *nor, enum spi_nor_ops ops)
@@ -880,10 +1313,9 @@ static int spi_nor_lock_and_prep(struct spi_nor *nor, enum spi_nor_ops ops)
 
 	mutex_lock(&nor->lock);
 
-	if (nor->prepare) {
-		ret = nor->prepare(nor, ops);
+	if (nor->controller_ops &&  nor->controller_ops->prepare) {
+		ret = nor->controller_ops->prepare(nor, ops);
 		if (ret) {
-			dev_err(nor->dev, "failed in the preparation.\n");
 			mutex_unlock(&nor->lock);
 			return ret;
 		}
@@ -893,8 +1325,8 @@ static int spi_nor_lock_and_prep(struct spi_nor *nor, enum spi_nor_ops ops)
 
 static void spi_nor_unlock_and_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
 {
-	if (nor->unprepare)
-		nor->unprepare(nor, ops);
+	if (nor->controller_ops && nor->controller_ops->unprepare)
+		nor->controller_ops->unprepare(nor, ops);
 	mutex_unlock(&nor->lock);
 }
 
@@ -935,9 +1367,6 @@ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr)
 
 	addr = spi_nor_convert_addr(nor, addr);
 
-	if (nor->erase)
-		return nor->erase(nor, addr);
-
 	if (nor->spimem) {
 		struct spi_mem_op op =
 			SPI_MEM_OP(SPI_MEM_OP_CMD(nor->erase_opcode, 1),
@@ -946,6 +1375,8 @@ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr)
 				   SPI_MEM_OP_NO_DATA);
 
 		return spi_mem_exec_op(nor->spimem, &op);
+	} else if (nor->controller_ops->erase) {
+		return nor->controller_ops->erase(nor, addr);
 	}
 
 	/*
@@ -957,8 +1388,8 @@ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr)
 		addr >>= 8;
 	}
 
-	return nor->write_reg(nor, nor->erase_opcode, nor->bouncebuf,
-			      nor->addr_width);
+	return nor->controller_ops->write_reg(nor, nor->erase_opcode,
+					      nor->bouncebuf, nor->addr_width);
 }
 
 /**
@@ -1208,7 +1639,9 @@ static int spi_nor_erase_multi_sectors(struct spi_nor *nor, u64 addr, u32 len)
 	list_for_each_entry_safe(cmd, next, &erase_list, list) {
 		nor->erase_opcode = cmd->opcode;
 		while (cmd->count) {
-			write_enable(nor);
+			ret = spi_nor_write_enable(nor);
+			if (ret)
+				goto destroy_erase_cmd_list;
 
 			ret = spi_nor_erase_sector(nor, addr);
 			if (ret)
@@ -1263,12 +1696,13 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr)
 	if (len == mtd->size && !(nor->flags & SNOR_F_NO_OP_CHIP_ERASE)) {
 		unsigned long timeout;
 
-		write_enable(nor);
+		ret = spi_nor_write_enable(nor);
+		if (ret)
+			goto erase_err;
 
-		if (erase_chip(nor)) {
-			ret = -EIO;
+		ret = spi_nor_erase_chip(nor);
+		if (ret)
 			goto erase_err;
-		}
 
 		/*
 		 * Scale the timeout linearly with the size of the flash, with
@@ -1291,7 +1725,9 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr)
 	/* "sector"-at-a-time erase */
 	} else if (spi_nor_has_uniform_erase(nor)) {
 		while (len) {
-			write_enable(nor);
+			ret = spi_nor_write_enable(nor);
+			if (ret)
+				goto erase_err;
 
 			ret = spi_nor_erase_sector(nor, addr);
 			if (ret)
@@ -1312,7 +1748,7 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr)
 			goto erase_err;
 	}
 
-	write_disable(nor);
+	ret = spi_nor_write_disable(nor);
 
 erase_err:
 	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_ERASE);
@@ -1320,27 +1756,6 @@ erase_err:
 	return ret;
 }
 
-/* Write status register and ensure bits in mask match written values */
-static int write_sr_and_check(struct spi_nor *nor, u8 status_new, u8 mask)
-{
-	int ret;
-
-	write_enable(nor);
-	ret = write_sr(nor, status_new);
-	if (ret)
-		return ret;
-
-	ret = spi_nor_wait_till_ready(nor);
-	if (ret)
-		return ret;
-
-	ret = read_sr(nor);
-	if (ret < 0)
-		return ret;
-
-	return ((ret & mask) != (status_new & mask)) ? -EIO : 0;
-}
-
 static void stm_get_locked_range(struct spi_nor *nor, u8 sr, loff_t *ofs,
 				 uint64_t *len)
 {
@@ -1433,16 +1848,18 @@ static int stm_is_unlocked_sr(struct spi_nor *nor, loff_t ofs, uint64_t len,
 static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 {
 	struct mtd_info *mtd = &nor->mtd;
-	int status_old, status_new;
+	int ret, status_old, status_new;
 	u8 mask = SR_BP2 | SR_BP1 | SR_BP0;
 	u8 shift = ffs(mask) - 1, pow, val;
 	loff_t lock_len;
 	bool can_be_top = true, can_be_bottom = nor->flags & SNOR_F_HAS_SR_TB;
 	bool use_top;
 
-	status_old = read_sr(nor);
-	if (status_old < 0)
-		return status_old;
+	ret = spi_nor_read_sr(nor, nor->bouncebuf);
+	if (ret)
+		return ret;
+
+	status_old = nor->bouncebuf[0];
 
 	/* If nothing in our range is unlocked, we don't need to do anything */
 	if (stm_is_locked_sr(nor, ofs, len, status_old))
@@ -1502,7 +1919,7 @@ static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	if ((status_new & mask) < (status_old & mask))
 		return -EINVAL;
 
-	return write_sr_and_check(nor, status_new, mask);
+	return spi_nor_write_sr_and_check(nor, status_new);
 }
 
 /*
@@ -1513,16 +1930,18 @@ static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 {
 	struct mtd_info *mtd = &nor->mtd;
-	int status_old, status_new;
+	int ret, status_old, status_new;
 	u8 mask = SR_BP2 | SR_BP1 | SR_BP0;
 	u8 shift = ffs(mask) - 1, pow, val;
 	loff_t lock_len;
 	bool can_be_top = true, can_be_bottom = nor->flags & SNOR_F_HAS_SR_TB;
 	bool use_top;
 
-	status_old = read_sr(nor);
-	if (status_old < 0)
-		return status_old;
+	ret = spi_nor_read_sr(nor, nor->bouncebuf);
+	if (ret)
+		return ret;
+
+	status_old = nor->bouncebuf[0];
 
 	/* If nothing in our range is locked, we don't need to do anything */
 	if (stm_is_unlocked_sr(nor, ofs, len, status_old))
@@ -1585,7 +2004,7 @@ static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	if ((status_new & mask) > (status_old & mask))
 		return -EINVAL;
 
-	return write_sr_and_check(nor, status_new, mask);
+	return spi_nor_write_sr_and_check(nor, status_new);
 }
 
 /*
@@ -1597,13 +2016,13 @@ static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
  */
 static int stm_is_locked(struct spi_nor *nor, loff_t ofs, uint64_t len)
 {
-	int status;
+	int ret;
 
-	status = read_sr(nor);
-	if (status < 0)
-		return status;
+	ret = spi_nor_read_sr(nor, nor->bouncebuf);
+	if (ret)
+		return ret;
 
-	return stm_is_locked_sr(nor, ofs, len, status);
+	return stm_is_locked_sr(nor, ofs, len, nor->bouncebuf[0]);
 }
 
 static const struct spi_nor_locking_ops stm_locking_ops = {
@@ -1657,242 +2076,59 @@ static int spi_nor_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	return ret;
 }
 
-/*
- * Write status Register and configuration register with 2 bytes
- * The first byte will be written to the status register, while the
- * second byte will be written to the configuration register.
- * Return negative if error occurred.
- */
-static int write_sr_cr(struct spi_nor *nor, u8 *sr_cr)
-{
-	int ret;
-
-	write_enable(nor);
-
-	if (nor->spimem) {
-		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR, 1),
-				   SPI_MEM_OP_NO_ADDR,
-				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_OUT(2, sr_cr, 1));
-
-		ret = spi_mem_exec_op(nor->spimem, &op);
-	} else {
-		ret = nor->write_reg(nor, SPINOR_OP_WRSR, sr_cr, 2);
-	}
-
-	if (ret < 0) {
-		dev_err(nor->dev,
-			"error while writing configuration register\n");
-		return -EINVAL;
-	}
-
-	ret = spi_nor_wait_till_ready(nor);
-	if (ret) {
-		dev_err(nor->dev,
-			"timeout while writing configuration register\n");
-		return ret;
-	}
-
-	return 0;
-}
-
-/**
- * macronix_quad_enable() - set QE bit in Status Register.
- * @nor:	pointer to a 'struct spi_nor'
- *
- * Set the Quad Enable (QE) bit in the Status Register.
- *
- * bit 6 of the Status Register is the QE bit for Macronix like QSPI memories.
- *
- * Return: 0 on success, -errno otherwise.
- */
-static int macronix_quad_enable(struct spi_nor *nor)
-{
-	int ret, val;
-
-	val = read_sr(nor);
-	if (val < 0)
-		return val;
-	if (val & SR_QUAD_EN_MX)
-		return 0;
-
-	write_enable(nor);
-
-	write_sr(nor, val | SR_QUAD_EN_MX);
-
-	ret = spi_nor_wait_till_ready(nor);
-	if (ret)
-		return ret;
-
-	ret = read_sr(nor);
-	if (!(ret > 0 && (ret & SR_QUAD_EN_MX))) {
-		dev_err(nor->dev, "Macronix Quad bit not set\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 /**
- * spansion_quad_enable() - set QE bit in Configuraiton Register.
+ * spi_nor_sr1_bit6_quad_enable() - Set the Quad Enable BIT(6) in the Status
+ * Register 1.
  * @nor:	pointer to a 'struct spi_nor'
  *
- * Set the Quad Enable (QE) bit in the Configuration Register.
- * This function is kept for legacy purpose because it has been used for a
- * long time without anybody complaining but it should be considered as
- * deprecated and maybe buggy.
- * First, this function doesn't care about the previous values of the Status
- * and Configuration Registers when it sets the QE bit (bit 1) in the
- * Configuration Register: all other bits are cleared, which may have unwanted
- * side effects like removing some block protections.
- * Secondly, it uses the Read Configuration Register (35h) instruction though
- * some very old and few memories don't support this instruction. If a pull-up
- * resistor is present on the MISO/IO1 line, we might still be able to pass the
- * "read back" test because the QSPI memory doesn't recognize the command,
- * so leaves the MISO/IO1 line state unchanged, hence read_cr() returns 0xFF.
- *
- * bit 1 of the Configuration Register is the QE bit for Spansion like QSPI
- * memories.
+ * Bit 6 of the Status Register 1 is the QE bit for Macronix like QSPI memories.
  *
  * Return: 0 on success, -errno otherwise.
  */
-static int spansion_quad_enable(struct spi_nor *nor)
+static int spi_nor_sr1_bit6_quad_enable(struct spi_nor *nor)
 {
-	u8 *sr_cr = nor->bouncebuf;
 	int ret;
 
-	sr_cr[0] = 0;
-	sr_cr[1] = CR_QUAD_EN_SPAN;
-	ret = write_sr_cr(nor, sr_cr);
+	ret = spi_nor_read_sr(nor, nor->bouncebuf);
 	if (ret)
 		return ret;
 
-	/* read back and check it */
-	ret = read_cr(nor);
-	if (!(ret > 0 && (ret & CR_QUAD_EN_SPAN))) {
-		dev_err(nor->dev, "Spansion Quad bit not set\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-/**
- * spansion_no_read_cr_quad_enable() - set QE bit in Configuration Register.
- * @nor:	pointer to a 'struct spi_nor'
- *
- * Set the Quad Enable (QE) bit in the Configuration Register.
- * This function should be used with QSPI memories not supporting the Read
- * Configuration Register (35h) instruction.
- *
- * bit 1 of the Configuration Register is the QE bit for Spansion like QSPI
- * memories.
- *
- * Return: 0 on success, -errno otherwise.
- */
-static int spansion_no_read_cr_quad_enable(struct spi_nor *nor)
-{
-	u8 *sr_cr = nor->bouncebuf;
-	int ret;
+	if (nor->bouncebuf[0] & SR1_QUAD_EN_BIT6)
+		return 0;
 
-	/* Keep the current value of the Status Register. */
-	ret = read_sr(nor);
-	if (ret < 0) {
-		dev_err(nor->dev, "error while reading status register\n");
-		return -EINVAL;
-	}
-	sr_cr[0] = ret;
-	sr_cr[1] = CR_QUAD_EN_SPAN;
+	nor->bouncebuf[0] |= SR1_QUAD_EN_BIT6;
 
-	return write_sr_cr(nor, sr_cr);
+	return spi_nor_write_sr1_and_check(nor, nor->bouncebuf[0]);
 }
 
 /**
- * spansion_read_cr_quad_enable() - set QE bit in Configuration Register.
- * @nor:	pointer to a 'struct spi_nor'
- *
- * Set the Quad Enable (QE) bit in the Configuration Register.
- * This function should be used with QSPI memories supporting the Read
- * Configuration Register (35h) instruction.
+ * spi_nor_sr2_bit1_quad_enable() - set the Quad Enable BIT(1) in the Status
+ * Register 2.
+ * @nor:       pointer to a 'struct spi_nor'.
  *
- * bit 1 of the Configuration Register is the QE bit for Spansion like QSPI
- * memories.
+ * Bit 1 of the Status Register 2 is the QE bit for Spansion like QSPI memories.
  *
  * Return: 0 on success, -errno otherwise.
  */
-static int spansion_read_cr_quad_enable(struct spi_nor *nor)
+static int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor)
 {
-	struct device *dev = nor->dev;
-	u8 *sr_cr = nor->bouncebuf;
 	int ret;
 
-	/* Check current Quad Enable bit value. */
-	ret = read_cr(nor);
-	if (ret < 0) {
-		dev_err(dev, "error while reading configuration register\n");
-		return -EINVAL;
-	}
-
-	if (ret & CR_QUAD_EN_SPAN)
-		return 0;
+	if (nor->flags & SNOR_F_NO_READ_CR)
+		return spi_nor_write_16bit_cr_and_check(nor, SR2_QUAD_EN_BIT1);
 
-	sr_cr[1] = ret | CR_QUAD_EN_SPAN;
-
-	/* Keep the current value of the Status Register. */
-	ret = read_sr(nor);
-	if (ret < 0) {
-		dev_err(dev, "error while reading status register\n");
-		return -EINVAL;
-	}
-	sr_cr[0] = ret;
-
-	ret = write_sr_cr(nor, sr_cr);
+	ret = spi_nor_read_cr(nor, nor->bouncebuf);
 	if (ret)
 		return ret;
 
-	/* Read back and check it. */
-	ret = read_cr(nor);
-	if (!(ret > 0 && (ret & CR_QUAD_EN_SPAN))) {
-		dev_err(nor->dev, "Spansion Quad bit not set\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int spi_nor_write_sr2(struct spi_nor *nor, u8 *sr2)
-{
-	if (nor->spimem) {
-		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR2, 1),
-				   SPI_MEM_OP_NO_ADDR,
-				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_OUT(1, sr2, 1));
-
-		return spi_mem_exec_op(nor->spimem, &op);
-	}
-
-	return nor->write_reg(nor, SPINOR_OP_WRSR2, sr2, 1);
-}
-
-static int spi_nor_read_sr2(struct spi_nor *nor, u8 *sr2)
-{
-	if (nor->spimem) {
-		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR2, 1),
-				   SPI_MEM_OP_NO_ADDR,
-				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_IN(1, sr2, 1));
-
-		return spi_mem_exec_op(nor->spimem, &op);
-	}
+	if (nor->bouncebuf[0] & SR2_QUAD_EN_BIT1)
+		return 0;
 
-	return nor->read_reg(nor, SPINOR_OP_RDSR2, sr2, 1);
+	return spi_nor_write_16bit_cr_and_check(nor, nor->bouncebuf[0]);
 }
 
 /**
- * sr2_bit7_quad_enable() - set QE bit in Status Register 2.
+ * spi_nor_sr2_bit7_quad_enable() - set QE bit in Status Register 2.
  * @nor:	pointer to a 'struct spi_nor'
  *
  * Set the Quad Enable (QE) bit in the Status Register 2.
@@ -1903,10 +2139,11 @@ static int spi_nor_read_sr2(struct spi_nor *nor, u8 *sr2)
  *
  * Return: 0 on success, -errno otherwise.
  */
-static int sr2_bit7_quad_enable(struct spi_nor *nor)
+static int spi_nor_sr2_bit7_quad_enable(struct spi_nor *nor)
 {
 	u8 *sr2 = nor->bouncebuf;
 	int ret;
+	u8 sr2_written;
 
 	/* Check current Quad Enable bit value. */
 	ret = spi_nor_read_sr2(nor, sr2);
@@ -1918,117 +2155,23 @@ static int sr2_bit7_quad_enable(struct spi_nor *nor)
 	/* Update the Quad Enable bit. */
 	*sr2 |= SR2_QUAD_EN_BIT7;
 
-	write_enable(nor);
-
 	ret = spi_nor_write_sr2(nor, sr2);
-	if (ret < 0) {
-		dev_err(nor->dev, "error while writing status register 2\n");
-		return -EINVAL;
-	}
-
-	ret = spi_nor_wait_till_ready(nor);
-	if (ret < 0) {
-		dev_err(nor->dev, "timeout while writing status register 2\n");
+	if (ret)
 		return ret;
-	}
+
+	sr2_written = *sr2;
 
 	/* Read back and check it. */
 	ret = spi_nor_read_sr2(nor, sr2);
-	if (!(ret > 0 && (*sr2 & SR2_QUAD_EN_BIT7))) {
-		dev_err(nor->dev, "SR2 Quad bit not set\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-/**
- * spi_nor_clear_sr_bp() - clear the Status Register Block Protection bits.
- * @nor:        pointer to a 'struct spi_nor'
- *
- * Read-modify-write function that clears the Block Protection bits from the
- * Status Register without affecting other bits.
- *
- * Return: 0 on success, -errno otherwise.
- */
-static int spi_nor_clear_sr_bp(struct spi_nor *nor)
-{
-	int ret;
-	u8 mask = SR_BP2 | SR_BP1 | SR_BP0;
-
-	ret = read_sr(nor);
-	if (ret < 0) {
-		dev_err(nor->dev, "error while reading status register\n");
-		return ret;
-	}
-
-	write_enable(nor);
-
-	ret = write_sr(nor, ret & ~mask);
-	if (ret) {
-		dev_err(nor->dev, "write to status register failed\n");
-		return ret;
-	}
-
-	ret = spi_nor_wait_till_ready(nor);
 	if (ret)
-		dev_err(nor->dev, "timeout while writing status register\n");
-	return ret;
-}
-
-/**
- * spi_nor_spansion_clear_sr_bp() - clear the Status Register Block Protection
- * bits on spansion flashes.
- * @nor:        pointer to a 'struct spi_nor'
- *
- * Read-modify-write function that clears the Block Protection bits from the
- * Status Register without affecting other bits. The function is tightly
- * coupled with the spansion_quad_enable() function. Both assume that the Write
- * Register with 16 bits, together with the Read Configuration Register (35h)
- * instructions are supported.
- *
- * Return: 0 on success, -errno otherwise.
- */
-static int spi_nor_spansion_clear_sr_bp(struct spi_nor *nor)
-{
-	int ret;
-	u8 mask = SR_BP2 | SR_BP1 | SR_BP0;
-	u8 *sr_cr =  nor->bouncebuf;
-
-	/* Check current Quad Enable bit value. */
-	ret = read_cr(nor);
-	if (ret < 0) {
-		dev_err(nor->dev,
-			"error while reading configuration register\n");
 		return ret;
-	}
-
-	/*
-	 * When the configuration register Quad Enable bit is one, only the
-	 * Write Status (01h) command with two data bytes may be used.
-	 */
-	if (ret & CR_QUAD_EN_SPAN) {
-		sr_cr[1] = ret;
 
-		ret = read_sr(nor);
-		if (ret < 0) {
-			dev_err(nor->dev,
-				"error while reading status register\n");
-			return ret;
-		}
-		sr_cr[0] = ret & ~mask;
-
-		ret = write_sr_cr(nor, sr_cr);
-		if (ret)
-			dev_err(nor->dev, "16-bit write register failed\n");
-		return ret;
+	if (*sr2 != sr2_written) {
+		dev_dbg(nor->dev, "SR2: Read back test failed\n");
+		return -EIO;
 	}
 
-	/*
-	 * If the Quad Enable bit is zero, use the Write Status (01h) command
-	 * with one data byte.
-	 */
-	return spi_nor_clear_sr_bp(nor);
+	return 0;
 }
 
 /* Used when the "_ext_id" is two bytes at most */
@@ -2136,7 +2279,7 @@ static void gd25q256_default_init(struct spi_nor *nor)
 	 * indicate the quad_enable method for this case, we need
 	 * to set it in the default_init fixup hook.
 	 */
-	nor->params.quad_enable = macronix_quad_enable;
+	nor->params.quad_enable = spi_nor_sr1_bit6_quad_enable;
 }
 
 static struct spi_nor_fixups gd25q256_fixups = {
@@ -2179,6 +2322,8 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "en25q64",    INFO(0x1c3017, 0, 64 * 1024,  128, SECT_4K) },
 	{ "en25q80a",   INFO(0x1c3014, 0, 64 * 1024,   16,
 			SECT_4K | SPI_NOR_DUAL_READ) },
+	{ "en25qh16",   INFO(0x1c7015, 0, 64 * 1024,   32,
+			SECT_4K | SPI_NOR_DUAL_READ) },
 	{ "en25qh32",   INFO(0x1c7016, 0, 64 * 1024,   64, 0) },
 	{ "en25qh64",   INFO(0x1c7017, 0, 64 * 1024,  128,
 			SECT_4K | SPI_NOR_DUAL_READ) },
@@ -2267,6 +2412,10 @@ static const struct flash_info spi_nor_ids[] = {
 			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "is25wp128",  INFO(0x9d7018, 0, 64 * 1024, 256,
 			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+	{ "is25wp256", INFO(0x9d7019, 0, 64 * 1024, 512,
+			    SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			    SPI_NOR_4B_OPCODES)
+		       .fixups = &is25lp256_fixups },
 
 	/* Macronix */
 	{ "mx25l512e",   INFO(0xc22010, 0, 64 * 1024,   1, SECT_4K) },
@@ -2482,6 +2631,8 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "w25q256", INFO(0xef4019, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "w25q256jvm", INFO(0xef7019, 0, 64 * 1024, 512,
 			     SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+	{ "w25q256jw", INFO(0xef6019, 0, 64 * 1024, 512,
+			     SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "w25m512jv", INFO(0xef7119, 0, 64 * 1024, 1024,
 			SECT_4K | SPI_NOR_QUAD_READ | SPI_NOR_DUAL_READ) },
 
@@ -2520,11 +2671,11 @@ static const struct flash_info *spi_nor_read_id(struct spi_nor *nor)
 
 		tmp = spi_mem_exec_op(nor->spimem, &op);
 	} else {
-		tmp = nor->read_reg(nor, SPINOR_OP_RDID, id,
-				    SPI_NOR_MAX_ID_LEN);
+		tmp = nor->controller_ops->read_reg(nor, SPINOR_OP_RDID, id,
+						    SPI_NOR_MAX_ID_LEN);
 	}
-	if (tmp < 0) {
-		dev_err(nor->dev, "error %d reading JEDEC ID\n", tmp);
+	if (tmp) {
+		dev_dbg(nor->dev, "error %d reading JEDEC ID\n", tmp);
 		return ERR_PTR(tmp);
 	}
 
@@ -2544,7 +2695,7 @@ static int spi_nor_read(struct mtd_info *mtd, loff_t from, size_t len,
 			size_t *retlen, u_char *buf)
 {
 	struct spi_nor *nor = mtd_to_spi_nor(mtd);
-	int ret;
+	ssize_t ret;
 
 	dev_dbg(nor->dev, "from 0x%08x, len %zd\n", (u32)from, len);
 
@@ -2583,7 +2734,7 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 		size_t *retlen, const u_char *buf)
 {
 	struct spi_nor *nor = mtd_to_spi_nor(mtd);
-	size_t actual;
+	size_t actual = 0;
 	int ret;
 
 	dev_dbg(nor->dev, "to 0x%08x, len %zd\n", (u32)to, len);
@@ -2592,26 +2743,28 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 	if (ret)
 		return ret;
 
-	write_enable(nor);
+	ret = spi_nor_write_enable(nor);
+	if (ret)
+		goto out;
 
 	nor->sst_write_second = false;
 
-	actual = to % 2;
 	/* Start write from odd address. */
-	if (actual) {
+	if (to % 2) {
 		nor->program_opcode = SPINOR_OP_BP;
 
 		/* write one byte. */
 		ret = spi_nor_write_data(nor, to, 1, buf);
 		if (ret < 0)
-			goto sst_write_err;
-		WARN(ret != 1, "While writing 1 byte written %i bytes\n",
-		     (int)ret);
+			goto out;
+		WARN(ret != 1, "While writing 1 byte written %i bytes\n", ret);
 		ret = spi_nor_wait_till_ready(nor);
 		if (ret)
-			goto sst_write_err;
+			goto out;
+
+		to++;
+		actual++;
 	}
-	to += actual;
 
 	/* Write out most of the data here. */
 	for (; actual < len - 1; actual += 2) {
@@ -2620,39 +2773,44 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 		/* write two bytes. */
 		ret = spi_nor_write_data(nor, to, 2, buf + actual);
 		if (ret < 0)
-			goto sst_write_err;
-		WARN(ret != 2, "While writing 2 bytes written %i bytes\n",
-		     (int)ret);
+			goto out;
+		WARN(ret != 2, "While writing 2 bytes written %i bytes\n", ret);
 		ret = spi_nor_wait_till_ready(nor);
 		if (ret)
-			goto sst_write_err;
+			goto out;
 		to += 2;
 		nor->sst_write_second = true;
 	}
 	nor->sst_write_second = false;
 
-	write_disable(nor);
+	ret = spi_nor_write_disable(nor);
+	if (ret)
+		goto out;
+
 	ret = spi_nor_wait_till_ready(nor);
 	if (ret)
-		goto sst_write_err;
+		goto out;
 
 	/* Write out trailing byte if it exists. */
 	if (actual != len) {
-		write_enable(nor);
+		ret = spi_nor_write_enable(nor);
+		if (ret)
+			goto out;
 
 		nor->program_opcode = SPINOR_OP_BP;
 		ret = spi_nor_write_data(nor, to, 1, buf + actual);
 		if (ret < 0)
-			goto sst_write_err;
-		WARN(ret != 1, "While writing 1 byte written %i bytes\n",
-		     (int)ret);
+			goto out;
+		WARN(ret != 1, "While writing 1 byte written %i bytes\n", ret);
 		ret = spi_nor_wait_till_ready(nor);
 		if (ret)
-			goto sst_write_err;
-		write_disable(nor);
+			goto out;
+
 		actual += 1;
+
+		ret = spi_nor_write_disable(nor);
 	}
-sst_write_err:
+out:
 	*retlen += actual;
 	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_WRITE);
 	return ret;
@@ -2701,7 +2859,10 @@ static int spi_nor_write(struct mtd_info *mtd, loff_t to, size_t len,
 
 		addr = spi_nor_convert_addr(nor, addr);
 
-		write_enable(nor);
+		ret = spi_nor_write_enable(nor);
+		if (ret)
+			goto write_err;
+
 		ret = spi_nor_write_data(nor, addr, page_remain, buf + i);
 		if (ret < 0)
 			goto write_err;
@@ -2722,13 +2883,21 @@ write_err:
 static int spi_nor_check(struct spi_nor *nor)
 {
 	if (!nor->dev ||
-	    (!nor->spimem &&
-	    (!nor->read || !nor->write || !nor->read_reg ||
-	      !nor->write_reg))) {
+	    (!nor->spimem && !nor->controller_ops) ||
+	    (!nor->spimem && nor->controller_ops &&
+	    (!nor->controller_ops->read ||
+	     !nor->controller_ops->write ||
+	     !nor->controller_ops->read_reg ||
+	     !nor->controller_ops->write_reg))) {
 		pr_err("spi-nor: please fill all the necessary fields!\n");
 		return -EINVAL;
 	}
 
+	if (nor->spimem && nor->controller_ops) {
+		dev_err(nor->dev, "nor->spimem and nor->controller_ops are mutually exclusive, please set just one of them.\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -2738,10 +2907,8 @@ static int s3an_nor_setup(struct spi_nor *nor,
 	int ret;
 
 	ret = spi_nor_xread_sr(nor, nor->bouncebuf);
-	if (ret < 0) {
-		dev_err(nor->dev, "error %d reading XRDSR\n", (int) ret);
+	if (ret)
 		return ret;
-	}
 
 	nor->erase_opcode = SPINOR_OP_XSE;
 	nor->program_opcode = SPINOR_OP_XPP;
@@ -2865,7 +3032,7 @@ static int spi_nor_hwcaps_pp2cmd(u32 hwcaps)
  */
 static int spi_nor_read_raw(struct spi_nor *nor, u32 addr, size_t len, u8 *buf)
 {
-	int ret;
+	ssize_t ret;
 
 	while (len) {
 		ret = spi_nor_read_data(nor, addr, len, buf);
@@ -3489,20 +3656,39 @@ static int spi_nor_parse_bfpt(struct spi_nor *nor,
 		break;
 
 	case BFPT_DWORD15_QER_SR2_BIT1_BUGGY:
+		/*
+		 * Writing only one byte to the Status Register has the
+		 * side-effect of clearing Status Register 2.
+		 */
 	case BFPT_DWORD15_QER_SR2_BIT1_NO_RD:
-		params->quad_enable = spansion_no_read_cr_quad_enable;
+		/*
+		 * Read Configuration Register (35h) instruction is not
+		 * supported.
+		 */
+		nor->flags |= SNOR_F_HAS_16BIT_SR | SNOR_F_NO_READ_CR;
+		params->quad_enable = spi_nor_sr2_bit1_quad_enable;
 		break;
 
 	case BFPT_DWORD15_QER_SR1_BIT6:
-		params->quad_enable = macronix_quad_enable;
+		nor->flags &= ~SNOR_F_HAS_16BIT_SR;
+		params->quad_enable = spi_nor_sr1_bit6_quad_enable;
 		break;
 
 	case BFPT_DWORD15_QER_SR2_BIT7:
-		params->quad_enable = sr2_bit7_quad_enable;
+		nor->flags &= ~SNOR_F_HAS_16BIT_SR;
+		params->quad_enable = spi_nor_sr2_bit7_quad_enable;
 		break;
 
 	case BFPT_DWORD15_QER_SR2_BIT1:
-		params->quad_enable = spansion_read_cr_quad_enable;
+		/*
+		 * JESD216 rev B or later does not specify if writing only one
+		 * byte to the Status Register clears or not the Status
+		 * Register 2, so let's be cautious and keep the default
+		 * assumption of a 16-bit Write Status (01h) command.
+		 */
+		nor->flags |= SNOR_F_HAS_16BIT_SR;
+
+		params->quad_enable = spi_nor_sr2_bit1_quad_enable;
 		break;
 
 	default:
@@ -4101,7 +4287,7 @@ static int spi_nor_parse_sfdp(struct spi_nor *nor,
 		err = spi_nor_read_sfdp(nor, sizeof(header),
 					psize, param_headers);
 		if (err < 0) {
-			dev_err(dev, "failed to read SFDP parameter headers\n");
+			dev_dbg(dev, "failed to read SFDP parameter headers\n");
 			goto exit;
 		}
 	}
@@ -4348,7 +4534,7 @@ static int spi_nor_default_setup(struct spi_nor *nor,
 	/* Select the (Fast) Read command. */
 	err = spi_nor_select_read(nor, shared_mask);
 	if (err) {
-		dev_err(nor->dev,
+		dev_dbg(nor->dev,
 			"can't select read settings supported by both the SPI controller and memory.\n");
 		return err;
 	}
@@ -4356,7 +4542,7 @@ static int spi_nor_default_setup(struct spi_nor *nor,
 	/* Select the Page Program command. */
 	err = spi_nor_select_pp(nor, shared_mask);
 	if (err) {
-		dev_err(nor->dev,
+		dev_dbg(nor->dev,
 			"can't select write settings supported by both the SPI controller and memory.\n");
 		return err;
 	}
@@ -4364,7 +4550,7 @@ static int spi_nor_default_setup(struct spi_nor *nor,
 	/* Select the Sector Erase command. */
 	err = spi_nor_select_erase(nor);
 	if (err) {
-		dev_err(nor->dev,
+		dev_dbg(nor->dev,
 			"can't select erase settings supported by both the SPI controller and memory.\n");
 		return err;
 	}
@@ -4381,12 +4567,32 @@ static int spi_nor_setup(struct spi_nor *nor,
 	return nor->params.setup(nor, hwcaps);
 }
 
+static void atmel_set_default_init(struct spi_nor *nor)
+{
+	nor->flags |= SNOR_F_HAS_LOCK;
+}
+
+static void intel_set_default_init(struct spi_nor *nor)
+{
+	nor->flags |= SNOR_F_HAS_LOCK;
+}
+
+static void issi_set_default_init(struct spi_nor *nor)
+{
+	nor->params.quad_enable = spi_nor_sr1_bit6_quad_enable;
+}
+
 static void macronix_set_default_init(struct spi_nor *nor)
 {
-	nor->params.quad_enable = macronix_quad_enable;
+	nor->params.quad_enable = spi_nor_sr1_bit6_quad_enable;
 	nor->params.set_4byte = macronix_set_4byte;
 }
 
+static void sst_set_default_init(struct spi_nor *nor)
+{
+	nor->flags |= SNOR_F_HAS_LOCK;
+}
+
 static void st_micron_set_default_init(struct spi_nor *nor)
 {
 	nor->flags |= SNOR_F_HAS_LOCK;
@@ -4408,6 +4614,18 @@ static void spi_nor_manufacturer_init_params(struct spi_nor *nor)
 {
 	/* Init flash parameters based on MFR */
 	switch (JEDEC_MFR(nor->info)) {
+	case SNOR_MFR_ATMEL:
+		atmel_set_default_init(nor);
+		break;
+
+	case SNOR_MFR_INTEL:
+		intel_set_default_init(nor);
+		break;
+
+	case SNOR_MFR_ISSI:
+		issi_set_default_init(nor);
+		break;
+
 	case SNOR_MFR_MACRONIX:
 		macronix_set_default_init(nor);
 		break;
@@ -4417,6 +4635,10 @@ static void spi_nor_manufacturer_init_params(struct spi_nor *nor)
 		st_micron_set_default_init(nor);
 		break;
 
+	case SNOR_MFR_SST:
+		sst_set_default_init(nor);
+		break;
+
 	case SNOR_MFR_WINBOND:
 		winbond_set_default_init(nor);
 		break;
@@ -4465,9 +4687,11 @@ static void spi_nor_info_init_params(struct spi_nor *nor)
 	u8 i, erase_mask;
 
 	/* Initialize legacy flash parameters and settings. */
-	params->quad_enable = spansion_quad_enable;
+	params->quad_enable = spi_nor_sr2_bit1_quad_enable;
 	params->set_4byte = spansion_set_4byte;
 	params->setup = spi_nor_default_setup;
+	/* Default to 16-bit Write Status (01h) Command */
+	nor->flags |= SNOR_F_HAS_16BIT_SR;
 
 	/* Set SPI NOR sizes. */
 	params->size = (u64)info->sector_size * info->n_sectors;
@@ -4675,25 +4899,36 @@ static int spi_nor_quad_enable(struct spi_nor *nor)
 	return nor->params.quad_enable(nor);
 }
 
+/**
+ * spi_nor_unlock_all() - Unlocks the entire flash memory array.
+ * @nor:	pointer to a 'struct spi_nor'.
+ *
+ * Some SPI NOR flashes are write protected by default after a power-on reset
+ * cycle, in order to avoid inadvertent writes during power-up. Backward
+ * compatibility imposes to unlock the entire flash memory array at power-up
+ * by default.
+ */
+static int spi_nor_unlock_all(struct spi_nor *nor)
+{
+	if (nor->flags & SNOR_F_HAS_LOCK)
+		return spi_nor_unlock(&nor->mtd, 0, nor->params.size);
+
+	return 0;
+}
+
 static int spi_nor_init(struct spi_nor *nor)
 {
 	int err;
 
-	if (nor->clear_sr_bp) {
-		if (nor->params.quad_enable == spansion_quad_enable)
-			nor->clear_sr_bp = spi_nor_spansion_clear_sr_bp;
-
-		err = nor->clear_sr_bp(nor);
-		if (err) {
-			dev_err(nor->dev,
-				"fail to clear block protection bits\n");
-			return err;
-		}
+	err = spi_nor_quad_enable(nor);
+	if (err) {
+		dev_dbg(nor->dev, "quad mode not supported\n");
+		return err;
 	}
 
-	err = spi_nor_quad_enable(nor);
+	err = spi_nor_unlock_all(nor);
 	if (err) {
-		dev_err(nor->dev, "quad mode not supported\n");
+		dev_dbg(nor->dev, "Failed to unlock the entire flash memory array\n");
 		return err;
 	}
 
@@ -4761,7 +4996,7 @@ static int spi_nor_set_addr_width(struct spi_nor *nor)
 	}
 
 	if (nor->addr_width > SPI_NOR_MAX_ADDR_WIDTH) {
-		dev_err(nor->dev, "address width is too large: %u\n",
+		dev_dbg(nor->dev, "address width is too large: %u\n",
 			nor->addr_width);
 		return -EINVAL;
 	}
@@ -4879,16 +5114,6 @@ int spi_nor_scan(struct spi_nor *nor, const char *name,
 	if (info->flags & SPI_NOR_HAS_LOCK)
 		nor->flags |= SNOR_F_HAS_LOCK;
 
-	/*
-	 * Atmel, SST, Intel/Numonyx, and others serial NOR tend to power up
-	 * with the software protection bits set.
-	 */
-	if (JEDEC_MFR(nor->info) == SNOR_MFR_ATMEL ||
-	    JEDEC_MFR(nor->info) == SNOR_MFR_INTEL ||
-	    JEDEC_MFR(nor->info) == SNOR_MFR_SST ||
-	    nor->info->flags & SPI_NOR_HAS_LOCK)
-		nor->clear_sr_bp = spi_nor_clear_sr_bp;
-
 	/* Init flash parameters based on flash_info struct and SFDP */
 	spi_nor_init_params(nor);
 
diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c
index a1dff92ceedf..0f847d510950 100644
--- a/drivers/mtd/ubi/debug.c
+++ b/drivers/mtd/ubi/debug.c
@@ -509,11 +509,9 @@ static const struct file_operations eraseblk_count_fops = {
  */
 int ubi_debugfs_init_dev(struct ubi_device *ubi)
 {
-	int err, n;
 	unsigned long ubi_num = ubi->ubi_num;
-	const char *fname;
-	struct dentry *dent;
 	struct ubi_debug_info *d = &ubi->dbg;
+	int n;
 
 	if (!IS_ENABLED(CONFIG_DEBUG_FS))
 		return 0;
@@ -522,95 +520,52 @@ int ubi_debugfs_init_dev(struct ubi_device *ubi)
 		     ubi->ubi_num);
 	if (n == UBI_DFS_DIR_LEN) {
 		/* The array size is too small */
-		fname = UBI_DFS_DIR_NAME;
-		dent = ERR_PTR(-EINVAL);
-		goto out;
+		return -EINVAL;
 	}
 
-	fname = d->dfs_dir_name;
-	dent = debugfs_create_dir(fname, dfs_rootdir);
-	if (IS_ERR_OR_NULL(dent))
-		goto out;
-	d->dfs_dir = dent;
-
-	fname = "chk_gen";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_chk_gen = dent;
-
-	fname = "chk_io";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_chk_io = dent;
-
-	fname = "chk_fastmap";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_chk_fastmap = dent;
-
-	fname = "tst_disable_bgt";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_disable_bgt = dent;
-
-	fname = "tst_emulate_bitflips";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_emulate_bitflips = dent;
-
-	fname = "tst_emulate_io_failures";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_emulate_io_failures = dent;
-
-	fname = "tst_emulate_power_cut";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_emulate_power_cut = dent;
-
-	fname = "tst_emulate_power_cut_min";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_power_cut_min = dent;
-
-	fname = "tst_emulate_power_cut_max";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_power_cut_max = dent;
-
-	fname = "detailed_erase_block_info";
-	dent = debugfs_create_file(fname, S_IRUSR, d->dfs_dir, (void *)ubi_num,
-				   &eraseblk_count_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
+	d->dfs_dir = debugfs_create_dir(d->dfs_dir_name, dfs_rootdir);
 
-	return 0;
+	d->dfs_chk_gen = debugfs_create_file("chk_gen", S_IWUSR, d->dfs_dir,
+					     (void *)ubi_num, &dfs_fops);
 
-out_remove:
-	debugfs_remove_recursive(d->dfs_dir);
-out:
-	err = dent ? PTR_ERR(dent) : -ENODEV;
-	ubi_err(ubi, "cannot create \"%s\" debugfs file or directory, error %d\n",
-		fname, err);
-	return err;
+	d->dfs_chk_io = debugfs_create_file("chk_io", S_IWUSR, d->dfs_dir,
+					    (void *)ubi_num, &dfs_fops);
+
+	d->dfs_chk_fastmap = debugfs_create_file("chk_fastmap", S_IWUSR,
+						 d->dfs_dir, (void *)ubi_num,
+						 &dfs_fops);
+
+	d->dfs_disable_bgt = debugfs_create_file("tst_disable_bgt", S_IWUSR,
+						 d->dfs_dir, (void *)ubi_num,
+						 &dfs_fops);
+
+	d->dfs_emulate_bitflips = debugfs_create_file("tst_emulate_bitflips",
+						      S_IWUSR, d->dfs_dir,
+						      (void *)ubi_num,
+						      &dfs_fops);
+
+	d->dfs_emulate_io_failures = debugfs_create_file("tst_emulate_io_failures",
+							 S_IWUSR, d->dfs_dir,
+							 (void *)ubi_num,
+							 &dfs_fops);
+
+	d->dfs_emulate_power_cut = debugfs_create_file("tst_emulate_power_cut",
+						       S_IWUSR, d->dfs_dir,
+						       (void *)ubi_num,
+						       &dfs_fops);
+
+	d->dfs_power_cut_min = debugfs_create_file("tst_emulate_power_cut_min",
+						   S_IWUSR, d->dfs_dir,
+						   (void *)ubi_num, &dfs_fops);
+
+	d->dfs_power_cut_max = debugfs_create_file("tst_emulate_power_cut_max",
+						   S_IWUSR, d->dfs_dir,
+						   (void *)ubi_num, &dfs_fops);
+
+	debugfs_create_file("detailed_erase_block_info", S_IRUSR, d->dfs_dir,
+			    (void *)ubi_num, &eraseblk_count_fops);
+
+	return 0;
 }
 
 /**
diff --git a/drivers/net/wireless/cisco/Kconfig b/drivers/net/wireless/cisco/Kconfig
index 01e173ede894..7a3b3bb2ce15 100644
--- a/drivers/net/wireless/cisco/Kconfig
+++ b/drivers/net/wireless/cisco/Kconfig
@@ -17,7 +17,7 @@ config AIRO
 	depends on CFG80211 && ISA_DMA_API && (PCI || BROKEN)
 	select WIRELESS_EXT
 	select CRYPTO
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select WEXT_SPY
 	select WEXT_PRIV
 	---help---
diff --git a/drivers/nubus/nubus.c b/drivers/nubus/nubus.c
index bb0d63a44f41..f70ba58dbc55 100644
--- a/drivers/nubus/nubus.c
+++ b/drivers/nubus/nubus.c
@@ -163,7 +163,7 @@ unsigned char *nubus_dirptr(const struct nubus_dirent *nd)
 void nubus_get_rsrc_mem(void *dest, const struct nubus_dirent *dirent,
 			unsigned int len)
 {
-	unsigned char *t = (unsigned char *)dest;
+	unsigned char *t = dest;
 	unsigned char *p = nubus_dirptr(dirent);
 
 	while (len) {
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index 2b36f052bfb9..c6439638a419 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -23,6 +23,16 @@ config NVME_MULTIPATH
 	   /dev/nvmeXnY device will show up for each NVMe namespaces,
 	   even if it is accessible through multiple controllers.
 
+config NVME_HWMON
+	bool "NVMe hardware monitoring"
+	depends on (NVME_CORE=y && HWMON=y) || (NVME_CORE=m && HWMON)
+	help
+	  This provides support for NVMe hardware monitoring. If enabled,
+	  a hardware monitoring device will be created for each NVMe drive
+	  in the system.
+
+	  If unsure, say N.
+
 config NVME_FABRICS
 	tristate
 
diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile
index 8a4b671c5f0c..fc7b26be692d 100644
--- a/drivers/nvme/host/Makefile
+++ b/drivers/nvme/host/Makefile
@@ -14,6 +14,7 @@ nvme-core-$(CONFIG_TRACING)		+= trace.o
 nvme-core-$(CONFIG_NVME_MULTIPATH)	+= multipath.o
 nvme-core-$(CONFIG_NVM)			+= lightnvm.o
 nvme-core-$(CONFIG_FAULT_INJECTION_DEBUG_FS)	+= fault_inject.o
+nvme-core-$(CONFIG_NVME_HWMON)		+= hwmon.o
 
 nvme-y					+= pci.o
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index fa7ba09dca77..8e8527408db3 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -283,6 +283,8 @@ void nvme_complete_rq(struct request *req)
 
 	trace_nvme_complete_rq(req);
 
+	nvme_cleanup_cmd(req);
+
 	if (nvme_req(req)->ctrl->kas)
 		nvme_req(req)->ctrl->comp_seen = true;
 
@@ -313,7 +315,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved)
 	if (blk_mq_request_completed(req))
 		return true;
 
-	nvme_req(req)->status = NVME_SC_HOST_PATH_ERROR;
+	nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD;
 	blk_mq_complete_request(req);
 	return true;
 }
@@ -611,8 +613,14 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 	struct nvme_dsm_range *range;
 	struct bio *bio;
 
-	range = kmalloc_array(segments, sizeof(*range),
-				GFP_ATOMIC | __GFP_NOWARN);
+	/*
+	 * Some devices do not consider the DSM 'Number of Ranges' field when
+	 * determining how much data to DMA. Always allocate memory for maximum
+	 * number of segments to prevent device reading beyond end of buffer.
+	 */
+	static const size_t alloc_size = sizeof(*range) * NVME_DSM_MAX_RANGES;
+
+	range = kzalloc(alloc_size, GFP_ATOMIC | __GFP_NOWARN);
 	if (!range) {
 		/*
 		 * If we fail allocation our range, fallback to the controller
@@ -626,7 +634,7 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 	}
 
 	__rq_for_each_bio(bio, req) {
-		u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector);
+		u64 slba = nvme_sect_to_lba(ns, bio->bi_iter.bi_sector);
 		u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift;
 
 		if (n < segments) {
@@ -652,7 +660,7 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 
 	req->special_vec.bv_page = virt_to_page(range);
 	req->special_vec.bv_offset = offset_in_page(range);
-	req->special_vec.bv_len = sizeof(*range) * segments;
+	req->special_vec.bv_len = alloc_size;
 	req->rq_flags |= RQF_SPECIAL_PAYLOAD;
 
 	return BLK_STS_OK;
@@ -667,7 +675,7 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
 	cmnd->write_zeroes.opcode = nvme_cmd_write_zeroes;
 	cmnd->write_zeroes.nsid = cpu_to_le32(ns->head->ns_id);
 	cmnd->write_zeroes.slba =
-		cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
+		cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
 	cmnd->write_zeroes.length =
 		cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
 	cmnd->write_zeroes.control = 0;
@@ -691,7 +699,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 
 	cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
 	cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id);
-	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
+	cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
 	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
 
 	if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams)
@@ -1647,7 +1655,7 @@ static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type)
 
 static void nvme_set_chunk_size(struct nvme_ns *ns)
 {
-	u32 chunk_size = (((u32)ns->noiob) << (ns->lba_shift - 9));
+	u32 chunk_size = nvme_lba_to_sect(ns, ns->noiob);
 	blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size));
 }
 
@@ -1684,8 +1692,7 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
 
 static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns)
 {
-	u32 max_sectors;
-	unsigned short bs = 1 << ns->lba_shift;
+	u64 max_blocks;
 
 	if (!(ns->ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES) ||
 	    (ns->ctrl->quirks & NVME_QUIRK_DISABLE_WRITE_ZEROES))
@@ -1701,11 +1708,12 @@ static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns)
 	 * nvme_init_identify() if available.
 	 */
 	if (ns->ctrl->max_hw_sectors == UINT_MAX)
-		max_sectors = ((u32)(USHRT_MAX + 1) * bs) >> 9;
+		max_blocks = (u64)USHRT_MAX + 1;
 	else
-		max_sectors = ((u32)(ns->ctrl->max_hw_sectors + 1) * bs) >> 9;
+		max_blocks = ns->ctrl->max_hw_sectors + 1;
 
-	blk_queue_max_write_zeroes_sectors(disk->queue, max_sectors);
+	blk_queue_max_write_zeroes_sectors(disk->queue,
+					   nvme_lba_to_sect(ns, max_blocks));
 }
 
 static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid,
@@ -1748,7 +1756,7 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
 static void nvme_update_disk_info(struct gendisk *disk,
 		struct nvme_ns *ns, struct nvme_id_ns *id)
 {
-	sector_t capacity = le64_to_cpu(id->nsze) << (ns->lba_shift - 9);
+	sector_t capacity = nvme_lba_to_sect(ns, le64_to_cpu(id->nsze));
 	unsigned short bs = 1 << ns->lba_shift;
 	u32 atomic_bs, phys_bs, io_opt;
 
@@ -2796,6 +2804,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	ctrl->oncs = le16_to_cpu(id->oncs);
 	ctrl->mtfa = le16_to_cpu(id->mtfa);
 	ctrl->oaes = le32_to_cpu(id->oaes);
+	ctrl->wctemp = le16_to_cpu(id->wctemp);
+	ctrl->cctemp = le16_to_cpu(id->cctemp);
+
 	atomic_set(&ctrl->abort_limit, id->acl + 1);
 	ctrl->vwc = id->vwc;
 	if (id->mdts)
@@ -2895,6 +2906,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	if (ret < 0)
 		return ret;
 
+	if (!ctrl->identified)
+		nvme_hwmon_init(ctrl);
+
 	ctrl->identified = true;
 
 	return 0;
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 265f89e11d8b..679a721ae229 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1224,7 +1224,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl,
 	lsreq->rqstlen = sizeof(*assoc_rqst);
 	lsreq->rspaddr = assoc_acc;
 	lsreq->rsplen = sizeof(*assoc_acc);
-	lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC;
+	lsreq->timeout = NVME_FC_LS_TIMEOUT_SEC;
 
 	ret = nvme_fc_send_ls_req(ctrl->rport, lsop);
 	if (ret)
@@ -1264,7 +1264,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl,
 	if (fcret) {
 		ret = -EBADF;
 		dev_err(ctrl->dev,
-			"q %d connect failed: %s\n",
+			"q %d Create Association LS failed: %s\n",
 			queue->qnum, validation_errors[fcret]);
 	} else {
 		ctrl->association_id =
@@ -1332,7 +1332,7 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 	lsreq->rqstlen = sizeof(*conn_rqst);
 	lsreq->rspaddr = conn_acc;
 	lsreq->rsplen = sizeof(*conn_acc);
-	lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC;
+	lsreq->timeout = NVME_FC_LS_TIMEOUT_SEC;
 
 	ret = nvme_fc_send_ls_req(ctrl->rport, lsop);
 	if (ret)
@@ -1363,7 +1363,7 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 	if (fcret) {
 		ret = -EBADF;
 		dev_err(ctrl->dev,
-			"q %d connect failed: %s\n",
+			"q %d Create I/O Connection LS failed: %s\n",
 			queue->qnum, validation_errors[fcret]);
 	} else {
 		queue->connection_id =
@@ -1376,7 +1376,7 @@ out_free_buffer:
 out_no_memory:
 	if (ret)
 		dev_err(ctrl->dev,
-			"queue %d connect command failed (%d).\n",
+			"queue %d connect I/O queue failed (%d).\n",
 			queue->qnum, ret);
 	return ret;
 }
@@ -1413,8 +1413,8 @@ nvme_fc_disconnect_assoc_done(struct nvmefc_ls_req *lsreq, int status)
 static void
 nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl)
 {
-	struct fcnvme_ls_disconnect_rqst *discon_rqst;
-	struct fcnvme_ls_disconnect_acc *discon_acc;
+	struct fcnvme_ls_disconnect_assoc_rqst *discon_rqst;
+	struct fcnvme_ls_disconnect_assoc_acc *discon_acc;
 	struct nvmefc_ls_req_op *lsop;
 	struct nvmefc_ls_req *lsreq;
 	int ret;
@@ -1430,11 +1430,11 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl)
 	lsreq = &lsop->ls_req;
 
 	lsreq->private = (void *)&lsop[1];
-	discon_rqst = (struct fcnvme_ls_disconnect_rqst *)
+	discon_rqst = (struct fcnvme_ls_disconnect_assoc_rqst *)
 			(lsreq->private + ctrl->lport->ops->lsrqst_priv_sz);
-	discon_acc = (struct fcnvme_ls_disconnect_acc *)&discon_rqst[1];
+	discon_acc = (struct fcnvme_ls_disconnect_assoc_acc *)&discon_rqst[1];
 
-	discon_rqst->w0.ls_cmd = FCNVME_LS_DISCONNECT;
+	discon_rqst->w0.ls_cmd = FCNVME_LS_DISCONNECT_ASSOC;
 	discon_rqst->desc_list_len = cpu_to_be32(
 				sizeof(struct fcnvme_lsdesc_assoc_id) +
 				sizeof(struct fcnvme_lsdesc_disconn_cmd));
@@ -1451,22 +1451,17 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl)
 	discon_rqst->discon_cmd.desc_len =
 			fcnvme_lsdesc_len(
 				sizeof(struct fcnvme_lsdesc_disconn_cmd));
-	discon_rqst->discon_cmd.scope = FCNVME_DISCONN_ASSOCIATION;
-	discon_rqst->discon_cmd.id = cpu_to_be64(ctrl->association_id);
 
 	lsreq->rqstaddr = discon_rqst;
 	lsreq->rqstlen = sizeof(*discon_rqst);
 	lsreq->rspaddr = discon_acc;
 	lsreq->rsplen = sizeof(*discon_acc);
-	lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC;
+	lsreq->timeout = NVME_FC_LS_TIMEOUT_SEC;
 
 	ret = nvme_fc_send_ls_req_async(ctrl->rport, lsop,
 				nvme_fc_disconnect_assoc_done);
 	if (ret)
 		kfree(lsop);
-
-	/* only meaningful part to terminating the association */
-	ctrl->association_id = 0;
 }
 
 
@@ -1662,7 +1657,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 					(freq->rcv_rsplen / 4) ||
 			     be32_to_cpu(op->rsp_iu.xfrd_len) !=
 					freq->transferred_length ||
-			     op->rsp_iu.status_code ||
+			     op->rsp_iu.ersp_result ||
 			     sqe->common.command_id != cqe->command_id)) {
 			status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
 			dev_info(ctrl->ctrl.device,
@@ -1672,7 +1667,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 				ctrl->cnum, be16_to_cpu(op->rsp_iu.iu_len),
 				be32_to_cpu(op->rsp_iu.xfrd_len),
 				freq->transferred_length,
-				op->rsp_iu.status_code,
+				op->rsp_iu.ersp_result,
 				sqe->common.command_id,
 				cqe->command_id);
 			goto done;
@@ -1731,9 +1726,14 @@ __nvme_fc_init_request(struct nvme_fc_ctrl *ctrl,
 	op->rq = rq;
 	op->rqno = rqno;
 
-	cmdiu->scsi_id = NVME_CMD_SCSI_ID;
+	cmdiu->format_id = NVME_CMD_FORMAT_ID;
 	cmdiu->fc_id = NVME_CMD_FC_ID;
 	cmdiu->iu_len = cpu_to_be16(sizeof(*cmdiu) / sizeof(u32));
+	if (queue->qnum)
+		cmdiu->rsv_cat = fccmnd_set_cat_css(0,
+					(NVME_CC_CSS_NVM >> NVME_CC_CSS_SHIFT));
+	else
+		cmdiu->rsv_cat = fccmnd_set_cat_admin(0);
 
 	op->fcp_req.cmddma = fc_dma_map_single(ctrl->lport->dev,
 				&op->cmd_iu, sizeof(op->cmd_iu), DMA_TO_DEVICE);
@@ -2173,8 +2173,6 @@ nvme_fc_unmap_data(struct nvme_fc_ctrl *ctrl, struct request *rq,
 	fc_dma_unmap_sg(ctrl->lport->dev, freq->sg_table.sgl, op->nents,
 			rq_dma_dir(rq));
 
-	nvme_cleanup_cmd(rq);
-
 	sg_free_table_chained(&freq->sg_table, SG_CHUNK_SIZE);
 
 	freq->sg_cnt = 0;
@@ -2305,6 +2303,7 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 		if (!(op->flags & FCOP_FLAGS_AEN))
 			nvme_fc_unmap_data(ctrl, op->rq, op);
 
+		nvme_cleanup_cmd(op->rq);
 		nvme_fc_ctrl_put(ctrl);
 
 		if (ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE &&
@@ -2695,7 +2694,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 		/* warn if maxcmd is lower than queue_size */
 		dev_warn(ctrl->ctrl.device,
 			"queue_size %zu > ctrl maxcmd %u, reducing "
-			"to queue_size\n",
+			"to maxcmd\n",
 			opts->queue_size, ctrl->ctrl.maxcmd);
 		opts->queue_size = ctrl->ctrl.maxcmd;
 	}
@@ -2703,7 +2702,8 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	if (opts->queue_size > ctrl->ctrl.sqsize + 1) {
 		/* warn if sqsize is lower than queue_size */
 		dev_warn(ctrl->ctrl.device,
-			"queue_size %zu > ctrl sqsize %u, clamping down\n",
+			"queue_size %zu > ctrl sqsize %u, reducing "
+			"to sqsize\n",
 			opts->queue_size, ctrl->ctrl.sqsize + 1);
 		opts->queue_size = ctrl->ctrl.sqsize + 1;
 	}
@@ -2739,6 +2739,7 @@ out_term_aen_ops:
 out_disconnect_admin_queue:
 	/* send a Disconnect(association) LS to fc-nvme target */
 	nvme_fc_xmt_disconnect_assoc(ctrl);
+	ctrl->association_id = 0;
 out_delete_hw_queue:
 	__nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[0], 0);
 out_free_queue:
@@ -2830,6 +2831,8 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl)
 	if (ctrl->association_id)
 		nvme_fc_xmt_disconnect_assoc(ctrl);
 
+	ctrl->association_id = 0;
+
 	if (ctrl->ctrl.tagset) {
 		nvme_fc_delete_hw_io_queues(ctrl);
 		nvme_fc_free_io_queues(ctrl);
diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c
new file mode 100644
index 000000000000..a5af21f5d370
--- /dev/null
+++ b/drivers/nvme/host/hwmon.c
@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVM Express hardware monitoring support
+ * Copyright (c) 2019, Guenter Roeck
+ */
+
+#include <linux/hwmon.h>
+#include <asm/unaligned.h>
+
+#include "nvme.h"
+
+/* These macros should be moved to linux/temperature.h */
+#define MILLICELSIUS_TO_KELVIN(t) DIV_ROUND_CLOSEST((t) + 273150, 1000)
+#define KELVIN_TO_MILLICELSIUS(t) ((t) * 1000L - 273150)
+
+struct nvme_hwmon_data {
+	struct nvme_ctrl *ctrl;
+	struct nvme_smart_log log;
+	struct mutex read_lock;
+};
+
+static int nvme_get_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under,
+				long *temp)
+{
+	unsigned int threshold = sensor << NVME_TEMP_THRESH_SELECT_SHIFT;
+	u32 status;
+	int ret;
+
+	if (under)
+		threshold |= NVME_TEMP_THRESH_TYPE_UNDER;
+
+	ret = nvme_get_features(ctrl, NVME_FEAT_TEMP_THRESH, threshold, NULL, 0,
+				&status);
+	if (ret > 0)
+		return -EIO;
+	if (ret < 0)
+		return ret;
+	*temp = KELVIN_TO_MILLICELSIUS(status & NVME_TEMP_THRESH_MASK);
+
+	return 0;
+}
+
+static int nvme_set_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under,
+				long temp)
+{
+	unsigned int threshold = sensor << NVME_TEMP_THRESH_SELECT_SHIFT;
+	int ret;
+
+	temp = MILLICELSIUS_TO_KELVIN(temp);
+	threshold |= clamp_val(temp, 0, NVME_TEMP_THRESH_MASK);
+
+	if (under)
+		threshold |= NVME_TEMP_THRESH_TYPE_UNDER;
+
+	ret = nvme_set_features(ctrl, NVME_FEAT_TEMP_THRESH, threshold, NULL, 0,
+				NULL);
+	if (ret > 0)
+		return -EIO;
+
+	return ret;
+}
+
+static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data)
+{
+	int ret;
+
+	ret = nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0,
+			   &data->log, sizeof(data->log), 0);
+
+	return ret <= 0 ? ret : -EIO;
+}
+
+static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+			   u32 attr, int channel, long *val)
+{
+	struct nvme_hwmon_data *data = dev_get_drvdata(dev);
+	struct nvme_smart_log *log = &data->log;
+	int temp;
+	int err;
+
+	/*
+	 * First handle attributes which don't require us to read
+	 * the smart log.
+	 */
+	switch (attr) {
+	case hwmon_temp_max:
+		return nvme_get_temp_thresh(data->ctrl, channel, false, val);
+	case hwmon_temp_min:
+		return nvme_get_temp_thresh(data->ctrl, channel, true, val);
+	case hwmon_temp_crit:
+		*val = KELVIN_TO_MILLICELSIUS(data->ctrl->cctemp);
+		return 0;
+	default:
+		break;
+	}
+
+	mutex_lock(&data->read_lock);
+	err = nvme_hwmon_get_smart_log(data);
+	if (err)
+		goto unlock;
+
+	switch (attr) {
+	case hwmon_temp_input:
+		if (!channel)
+			temp = get_unaligned_le16(log->temperature);
+		else
+			temp = le16_to_cpu(log->temp_sensor[channel - 1]);
+		*val = KELVIN_TO_MILLICELSIUS(temp);
+		break;
+	case hwmon_temp_alarm:
+		*val = !!(log->critical_warning & NVME_SMART_CRIT_TEMPERATURE);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+unlock:
+	mutex_unlock(&data->read_lock);
+	return err;
+}
+
+static int nvme_hwmon_write(struct device *dev, enum hwmon_sensor_types type,
+			    u32 attr, int channel, long val)
+{
+	struct nvme_hwmon_data *data = dev_get_drvdata(dev);
+
+	switch (attr) {
+	case hwmon_temp_max:
+		return nvme_set_temp_thresh(data->ctrl, channel, false, val);
+	case hwmon_temp_min:
+		return nvme_set_temp_thresh(data->ctrl, channel, true, val);
+	default:
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static const char * const nvme_hwmon_sensor_names[] = {
+	"Composite",
+	"Sensor 1",
+	"Sensor 2",
+	"Sensor 3",
+	"Sensor 4",
+	"Sensor 5",
+	"Sensor 6",
+	"Sensor 7",
+	"Sensor 8",
+};
+
+static int nvme_hwmon_read_string(struct device *dev,
+				  enum hwmon_sensor_types type, u32 attr,
+				  int channel, const char **str)
+{
+	*str = nvme_hwmon_sensor_names[channel];
+	return 0;
+}
+
+static umode_t nvme_hwmon_is_visible(const void *_data,
+				     enum hwmon_sensor_types type,
+				     u32 attr, int channel)
+{
+	const struct nvme_hwmon_data *data = _data;
+
+	switch (attr) {
+	case hwmon_temp_crit:
+		if (!channel && data->ctrl->cctemp)
+			return 0444;
+		break;
+	case hwmon_temp_max:
+	case hwmon_temp_min:
+		if ((!channel && data->ctrl->wctemp) ||
+		    (channel && data->log.temp_sensor[channel - 1])) {
+			if (data->ctrl->quirks &
+			    NVME_QUIRK_NO_TEMP_THRESH_CHANGE)
+				return 0444;
+			return 0644;
+		}
+		break;
+	case hwmon_temp_alarm:
+		if (!channel)
+			return 0444;
+		break;
+	case hwmon_temp_input:
+	case hwmon_temp_label:
+		if (!channel || data->log.temp_sensor[channel - 1])
+			return 0444;
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static const struct hwmon_channel_info *nvme_hwmon_info[] = {
+	HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ),
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_CRIT | HWMON_T_LABEL | HWMON_T_ALARM,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL),
+	NULL
+};
+
+static const struct hwmon_ops nvme_hwmon_ops = {
+	.is_visible	= nvme_hwmon_is_visible,
+	.read		= nvme_hwmon_read,
+	.read_string	= nvme_hwmon_read_string,
+	.write		= nvme_hwmon_write,
+};
+
+static const struct hwmon_chip_info nvme_hwmon_chip_info = {
+	.ops	= &nvme_hwmon_ops,
+	.info	= nvme_hwmon_info,
+};
+
+void nvme_hwmon_init(struct nvme_ctrl *ctrl)
+{
+	struct device *dev = ctrl->dev;
+	struct nvme_hwmon_data *data;
+	struct device *hwmon;
+	int err;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return;
+
+	data->ctrl = ctrl;
+	mutex_init(&data->read_lock);
+
+	err = nvme_hwmon_get_smart_log(data);
+	if (err) {
+		dev_warn(dev, "Failed to read smart log (error %d)\n", err);
+		devm_kfree(dev, data);
+		return;
+	}
+
+	hwmon = devm_hwmon_device_register_with_info(dev, "nvme", data,
+						     &nvme_hwmon_chip_info,
+						     NULL);
+	if (IS_ERR(hwmon)) {
+		dev_warn(dev, "Failed to instantiate hwmon device\n");
+		devm_kfree(dev, data);
+	}
+}
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index e0f064dcbd02..797c18337d96 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -95,6 +95,7 @@ void nvme_failover_req(struct request *req)
 		}
 		break;
 	case NVME_SC_HOST_PATH_ERROR:
+	case NVME_SC_HOST_ABORTED_CMD:
 		/*
 		 * Temporary transport disruption in talking to the controller.
 		 * Try to send on a new path.
@@ -446,8 +447,14 @@ static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
 
 	for (i = 0; i < le16_to_cpu(ctrl->ana_log_buf->ngrps); i++) {
 		struct nvme_ana_group_desc *desc = base + offset;
-		u32 nr_nsids = le32_to_cpu(desc->nnsids);
-		size_t nsid_buf_size = nr_nsids * sizeof(__le32);
+		u32 nr_nsids;
+		size_t nsid_buf_size;
+
+		if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc)))
+			return -EINVAL;
+
+		nr_nsids = le32_to_cpu(desc->nnsids);
+		nsid_buf_size = nr_nsids * sizeof(__le32);
 
 		if (WARN_ON_ONCE(desc->grpid == 0))
 			return -EINVAL;
@@ -467,8 +474,6 @@ static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
 			return error;
 
 		offset += nsid_buf_size;
-		if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc)))
-			return -EINVAL;
 	}
 
 	return 0;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 22e8401352c2..3b9cbe0668fa 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -115,6 +115,11 @@ enum nvme_quirks {
 	 * Prevent tag overlap between queues
 	 */
 	NVME_QUIRK_SHARED_TAGS                  = (1 << 13),
+
+	/*
+	 * Don't change the value of the temperature threshold feature
+	 */
+	NVME_QUIRK_NO_TEMP_THRESH_CHANGE	= (1 << 14),
 };
 
 /*
@@ -231,6 +236,8 @@ struct nvme_ctrl {
 	u16 kas;
 	u8 npss;
 	u8 apsta;
+	u16 wctemp;
+	u16 cctemp;
 	u32 oaes;
 	u32 aen_result;
 	u32 ctratt;
@@ -419,9 +426,20 @@ static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl)
 	return ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, 0x4E564D65);
 }
 
-static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector)
+/*
+ * Convert a 512B sector number to a device logical block number.
+ */
+static inline u64 nvme_sect_to_lba(struct nvme_ns *ns, sector_t sector)
+{
+	return sector >> (ns->lba_shift - SECTOR_SHIFT);
+}
+
+/*
+ * Convert a device logical block number to a 512B sector number.
+ */
+static inline sector_t nvme_lba_to_sect(struct nvme_ns *ns, u64 lba)
 {
-	return (sector >> (ns->lba_shift - 9));
+	return lba << (ns->lba_shift - SECTOR_SHIFT);
 }
 
 static inline void nvme_end_request(struct request *req, __le16 status,
@@ -446,6 +464,11 @@ static inline void nvme_put_ctrl(struct nvme_ctrl *ctrl)
 	put_device(ctrl->device);
 }
 
+static inline bool nvme_is_aen_req(u16 qid, __u16 command_id)
+{
+	return !qid && command_id >= NVME_AQ_BLK_MQ_DEPTH;
+}
+
 void nvme_complete_rq(struct request *req);
 bool nvme_cancel_request(struct request *req, void *data, bool reserved);
 bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
@@ -652,4 +675,10 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
 	return dev_to_disk(dev)->private_data;
 }
 
+#ifdef CONFIG_NVME_HWMON
+void nvme_hwmon_init(struct nvme_ctrl *ctrl);
+#else
+static inline void nvme_hwmon_init(struct nvme_ctrl *ctrl) { }
+#endif
+
 #endif /* _NVME_H */
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 869f462e6b6e..dcaad5831cee 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -925,7 +925,6 @@ static void nvme_pci_complete_rq(struct request *req)
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct nvme_dev *dev = iod->nvmeq->dev;
 
-	nvme_cleanup_cmd(req);
 	if (blk_integrity_rq(req))
 		dma_unmap_page(dev->dev, iod->meta_dma,
 			       rq_integrity_vec(req)->bv_len, rq_data_dir(req));
@@ -968,8 +967,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 	 * aborts.  We don't even bother to allocate a struct request
 	 * for them but rather special case them here.
 	 */
-	if (unlikely(nvmeq->qid == 0 &&
-			cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) {
+	if (unlikely(nvme_is_aen_req(nvmeq->qid, cqe->command_id))) {
 		nvme_complete_async_event(&nvmeq->dev->ctrl,
 				cqe->status, &cqe->result);
 		return;
@@ -2982,7 +2980,7 @@ static int nvme_suspend(struct device *dev)
 
 		/*
 		 * Clearing npss forces a controller reset on resume. The
-		 * correct value will be resdicovered then.
+		 * correct value will be rediscovered then.
 		 */
 		ret = nvme_disable_prepare_reset(ndev, true);
 		ctrl->npss = 0;
@@ -3082,7 +3080,8 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0xf1a5),	/* Intel 600P/P3100 */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
-				NVME_QUIRK_MEDIUM_PRIO_SQ },
+				NVME_QUIRK_MEDIUM_PRIO_SQ |
+				NVME_QUIRK_NO_TEMP_THRESH_CHANGE },
 	{ PCI_VDEVICE(INTEL, 0xf1a6),	/* Intel 760p/Pro 7600p */
 		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index cb4c3000a57e..dce59459ed41 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1160,8 +1160,6 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue,
 	}
 
 	ib_dma_unmap_sg(ibdev, req->sg_table.sgl, req->nents, rq_dma_dir(rq));
-
-	nvme_cleanup_cmd(rq);
 	sg_free_table_chained(&req->sg_table, SG_CHUNK_SIZE);
 }
 
@@ -1501,8 +1499,8 @@ static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	 * aborts.  We don't even bother to allocate a struct request
 	 * for them but rather special case them here.
 	 */
-	if (unlikely(nvme_rdma_queue_idx(queue) == 0 &&
-			cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH))
+	if (unlikely(nvme_is_aen_req(nvme_rdma_queue_idx(queue),
+				     cqe->command_id)))
 		nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status,
 				&cqe->result);
 	else
@@ -1768,7 +1766,6 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (unlikely(err < 0)) {
 		dev_err(queue->ctrl->ctrl.device,
 			     "Failed to map data (%d)\n", err);
-		nvme_cleanup_cmd(rq);
 		goto err;
 	}
 
@@ -1779,18 +1776,19 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	err = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge,
 			req->mr ? &req->reg_wr.wr : NULL);
-	if (unlikely(err)) {
-		nvme_rdma_unmap_data(queue, rq);
-		goto err;
-	}
+	if (unlikely(err))
+		goto err_unmap;
 
 	return BLK_STS_OK;
 
+err_unmap:
+	nvme_rdma_unmap_data(queue, rq);
 err:
 	if (err == -ENOMEM || err == -EAGAIN)
 		ret = BLK_STS_RESOURCE;
 	else
 		ret = BLK_STS_IOERR;
+	nvme_cleanup_cmd(rq);
 unmap_qe:
 	ib_dma_unmap_single(dev, req->sqe.dma, sizeof(struct nvme_command),
 			    DMA_TO_DEVICE);
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 7544be84ab35..6d43b23a0fc8 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -491,8 +491,8 @@ static int nvme_tcp_handle_comp(struct nvme_tcp_queue *queue,
 	 * aborts.  We don't even bother to allocate a struct request
 	 * for them but rather special case them here.
 	 */
-	if (unlikely(nvme_tcp_queue_id(queue) == 0 &&
-	    cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH))
+	if (unlikely(nvme_is_aen_req(nvme_tcp_queue_id(queue),
+				     cqe->command_id)))
 		nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status,
 				&cqe->result);
 	else
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 831a062d27cb..56c21b501185 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -31,7 +31,7 @@ u64 nvmet_get_log_page_offset(struct nvme_command *cmd)
 
 static void nvmet_execute_get_log_page_noop(struct nvmet_req *req)
 {
-	nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->data_len));
+	nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->transfer_len));
 }
 
 static void nvmet_execute_get_log_page_error(struct nvmet_req *req)
@@ -134,7 +134,7 @@ static void nvmet_execute_get_log_page_smart(struct nvmet_req *req)
 	u16 status = NVME_SC_INTERNAL;
 	unsigned long flags;
 
-	if (req->data_len != sizeof(*log))
+	if (req->transfer_len != sizeof(*log))
 		goto out;
 
 	log = kzalloc(sizeof(*log), GFP_KERNEL);
@@ -196,7 +196,7 @@ static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
 	u16 status = NVME_SC_INTERNAL;
 	size_t len;
 
-	if (req->data_len != NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32))
+	if (req->transfer_len != NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32))
 		goto out;
 
 	mutex_lock(&ctrl->lock);
@@ -206,7 +206,7 @@ static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
 		len = ctrl->nr_changed_ns * sizeof(__le32);
 	status = nvmet_copy_to_sgl(req, 0, ctrl->changed_ns_list, len);
 	if (!status)
-		status = nvmet_zero_sgl(req, len, req->data_len - len);
+		status = nvmet_zero_sgl(req, len, req->transfer_len - len);
 	ctrl->nr_changed_ns = 0;
 	nvmet_clear_aen_bit(req, NVME_AEN_BIT_NS_ATTR);
 	mutex_unlock(&ctrl->lock);
@@ -282,6 +282,36 @@ out:
 	nvmet_req_complete(req, status);
 }
 
+static void nvmet_execute_get_log_page(struct nvmet_req *req)
+{
+	if (!nvmet_check_data_len(req, nvmet_get_log_page_len(req->cmd)))
+		return;
+
+	switch (req->cmd->get_log_page.lid) {
+	case NVME_LOG_ERROR:
+		return nvmet_execute_get_log_page_error(req);
+	case NVME_LOG_SMART:
+		return nvmet_execute_get_log_page_smart(req);
+	case NVME_LOG_FW_SLOT:
+		/*
+		 * We only support a single firmware slot which always is
+		 * active, so we can zero out the whole firmware slot log and
+		 * still claim to fully implement this mandatory log page.
+		 */
+		return nvmet_execute_get_log_page_noop(req);
+	case NVME_LOG_CHANGED_NS:
+		return nvmet_execute_get_log_changed_ns(req);
+	case NVME_LOG_CMD_EFFECTS:
+		return nvmet_execute_get_log_cmd_effects_ns(req);
+	case NVME_LOG_ANA:
+		return nvmet_execute_get_log_page_ana(req);
+	}
+	pr_err("unhandled lid %d on qid %d\n",
+	       req->cmd->get_log_page.lid, req->sq->qid);
+	req->error_loc = offsetof(struct nvme_get_log_page_command, lid);
+	nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
+}
+
 static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -565,6 +595,28 @@ out:
 	nvmet_req_complete(req, status);
 }
 
+static void nvmet_execute_identify(struct nvmet_req *req)
+{
+	if (!nvmet_check_data_len(req, NVME_IDENTIFY_DATA_SIZE))
+		return;
+
+	switch (req->cmd->identify.cns) {
+	case NVME_ID_CNS_NS:
+		return nvmet_execute_identify_ns(req);
+	case NVME_ID_CNS_CTRL:
+		return nvmet_execute_identify_ctrl(req);
+	case NVME_ID_CNS_NS_ACTIVE_LIST:
+		return nvmet_execute_identify_nslist(req);
+	case NVME_ID_CNS_NS_DESC_LIST:
+		return nvmet_execute_identify_desclist(req);
+	}
+
+	pr_err("unhandled identify cns %d on qid %d\n",
+	       req->cmd->identify.cns, req->sq->qid);
+	req->error_loc = offsetof(struct nvme_identify, cns);
+	nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
+}
+
 /*
  * A "minimum viable" abort implementation: the command is mandatory in the
  * spec, but we are not required to do any useful work.  We couldn't really
@@ -574,6 +626,8 @@ out:
  */
 static void nvmet_execute_abort(struct nvmet_req *req)
 {
+	if (!nvmet_check_data_len(req, 0))
+		return;
 	nvmet_set_result(req, 1);
 	nvmet_req_complete(req, 0);
 }
@@ -658,6 +712,9 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
 	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
 	u16 status = 0;
 
+	if (!nvmet_check_data_len(req, 0))
+		return;
+
 	switch (cdw10 & 0xff) {
 	case NVME_FEAT_NUM_QUEUES:
 		nvmet_set_result(req,
@@ -721,6 +778,9 @@ static void nvmet_execute_get_features(struct nvmet_req *req)
 	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
 	u16 status = 0;
 
+	if (!nvmet_check_data_len(req, 0))
+		return;
+
 	switch (cdw10 & 0xff) {
 	/*
 	 * These features are mandatory in the spec, but we don't
@@ -785,6 +845,9 @@ void nvmet_execute_async_event(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
 
+	if (!nvmet_check_data_len(req, 0))
+		return;
+
 	mutex_lock(&ctrl->lock);
 	if (ctrl->nr_async_event_cmds >= NVMET_ASYNC_EVENTS) {
 		mutex_unlock(&ctrl->lock);
@@ -801,6 +864,9 @@ void nvmet_execute_keep_alive(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
 
+	if (!nvmet_check_data_len(req, 0))
+		return;
+
 	pr_debug("ctrl %d update keep-alive timer for %d secs\n",
 		ctrl->cntlid, ctrl->kato);
 
@@ -813,77 +879,36 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 	struct nvme_command *cmd = req->cmd;
 	u16 ret;
 
+	if (nvme_is_fabrics(cmd))
+		return nvmet_parse_fabrics_cmd(req);
+	if (req->sq->ctrl->subsys->type == NVME_NQN_DISC)
+		return nvmet_parse_discovery_cmd(req);
+
 	ret = nvmet_check_ctrl_status(req, cmd);
 	if (unlikely(ret))
 		return ret;
 
 	switch (cmd->common.opcode) {
 	case nvme_admin_get_log_page:
-		req->data_len = nvmet_get_log_page_len(cmd);
-
-		switch (cmd->get_log_page.lid) {
-		case NVME_LOG_ERROR:
-			req->execute = nvmet_execute_get_log_page_error;
-			return 0;
-		case NVME_LOG_SMART:
-			req->execute = nvmet_execute_get_log_page_smart;
-			return 0;
-		case NVME_LOG_FW_SLOT:
-			/*
-			 * We only support a single firmware slot which always
-			 * is active, so we can zero out the whole firmware slot
-			 * log and still claim to fully implement this mandatory
-			 * log page.
-			 */
-			req->execute = nvmet_execute_get_log_page_noop;
-			return 0;
-		case NVME_LOG_CHANGED_NS:
-			req->execute = nvmet_execute_get_log_changed_ns;
-			return 0;
-		case NVME_LOG_CMD_EFFECTS:
-			req->execute = nvmet_execute_get_log_cmd_effects_ns;
-			return 0;
-		case NVME_LOG_ANA:
-			req->execute = nvmet_execute_get_log_page_ana;
-			return 0;
-		}
-		break;
+		req->execute = nvmet_execute_get_log_page;
+		return 0;
 	case nvme_admin_identify:
-		req->data_len = NVME_IDENTIFY_DATA_SIZE;
-		switch (cmd->identify.cns) {
-		case NVME_ID_CNS_NS:
-			req->execute = nvmet_execute_identify_ns;
-			return 0;
-		case NVME_ID_CNS_CTRL:
-			req->execute = nvmet_execute_identify_ctrl;
-			return 0;
-		case NVME_ID_CNS_NS_ACTIVE_LIST:
-			req->execute = nvmet_execute_identify_nslist;
-			return 0;
-		case NVME_ID_CNS_NS_DESC_LIST:
-			req->execute = nvmet_execute_identify_desclist;
-			return 0;
-		}
-		break;
+		req->execute = nvmet_execute_identify;
+		return 0;
 	case nvme_admin_abort_cmd:
 		req->execute = nvmet_execute_abort;
-		req->data_len = 0;
 		return 0;
 	case nvme_admin_set_features:
 		req->execute = nvmet_execute_set_features;
-		req->data_len = 0;
 		return 0;
 	case nvme_admin_get_features:
 		req->execute = nvmet_execute_get_features;
-		req->data_len = 0;
 		return 0;
 	case nvme_admin_async_event:
 		req->execute = nvmet_execute_async_event;
-		req->data_len = 0;
 		return 0;
 	case nvme_admin_keep_alive:
 		req->execute = nvmet_execute_keep_alive;
-		req->data_len = 0;
 		return 0;
 	}
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 3a67e244e568..28438b833c1b 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -892,14 +892,10 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 	}
 
 	if (unlikely(!req->sq->ctrl))
-		/* will return an error for any Non-connect command: */
+		/* will return an error for any non-connect command: */
 		status = nvmet_parse_connect_cmd(req);
 	else if (likely(req->sq->qid != 0))
 		status = nvmet_parse_io_cmd(req);
-	else if (nvme_is_fabrics(req->cmd))
-		status = nvmet_parse_fabrics_cmd(req);
-	else if (req->sq->ctrl->subsys->type == NVME_NQN_DISC)
-		status = nvmet_parse_discovery_cmd(req);
 	else
 		status = nvmet_parse_admin_cmd(req);
 
@@ -930,15 +926,17 @@ void nvmet_req_uninit(struct nvmet_req *req)
 }
 EXPORT_SYMBOL_GPL(nvmet_req_uninit);
 
-void nvmet_req_execute(struct nvmet_req *req)
+bool nvmet_check_data_len(struct nvmet_req *req, size_t data_len)
 {
-	if (unlikely(req->data_len != req->transfer_len)) {
+	if (unlikely(data_len != req->transfer_len)) {
 		req->error_loc = offsetof(struct nvme_common_command, dptr);
 		nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR);
-	} else
-		req->execute(req);
+		return false;
+	}
+
+	return true;
 }
-EXPORT_SYMBOL_GPL(nvmet_req_execute);
+EXPORT_SYMBOL_GPL(nvmet_check_data_len);
 
 int nvmet_req_alloc_sgl(struct nvmet_req *req)
 {
@@ -966,7 +964,7 @@ int nvmet_req_alloc_sgl(struct nvmet_req *req)
 	}
 
 	req->sg = sgl_alloc(req->transfer_len, GFP_KERNEL, &req->sg_cnt);
-	if (!req->sg)
+	if (unlikely(!req->sg))
 		return -ENOMEM;
 
 	return 0;
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 3764a8900850..0c2274b21e15 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -157,7 +157,7 @@ static size_t discovery_log_entries(struct nvmet_req *req)
 	return entries;
 }
 
-static void nvmet_execute_get_disc_log_page(struct nvmet_req *req)
+static void nvmet_execute_disc_get_log_page(struct nvmet_req *req)
 {
 	const int entry_size = sizeof(struct nvmf_disc_rsp_page_entry);
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -171,6 +171,16 @@ static void nvmet_execute_get_disc_log_page(struct nvmet_req *req)
 	u16 status = 0;
 	void *buffer;
 
+	if (!nvmet_check_data_len(req, data_len))
+		return;
+
+	if (req->cmd->get_log_page.lid != NVME_LOG_DISC) {
+		req->error_loc =
+			offsetof(struct nvme_get_log_page_command, lid);
+		status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+		goto out;
+	}
+
 	/* Spec requires dword aligned offsets */
 	if (offset & 0x3) {
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
@@ -227,20 +237,35 @@ out:
 	nvmet_req_complete(req, status);
 }
 
-static void nvmet_execute_identify_disc_ctrl(struct nvmet_req *req)
+static void nvmet_execute_disc_identify(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
 	struct nvme_id_ctrl *id;
+	const char model[] = "Linux";
 	u16 status = 0;
 
+	if (!nvmet_check_data_len(req, NVME_IDENTIFY_DATA_SIZE))
+		return;
+
+	if (req->cmd->identify.cns != NVME_ID_CNS_CTRL) {
+		req->error_loc = offsetof(struct nvme_identify, cns);
+		status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+		goto out;
+	}
+
 	id = kzalloc(sizeof(*id), GFP_KERNEL);
 	if (!id) {
 		status = NVME_SC_INTERNAL;
 		goto out;
 	}
 
+	memset(id->sn, ' ', sizeof(id->sn));
+	bin2hex(id->sn, &ctrl->subsys->serial,
+		min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2));
 	memset(id->fr, ' ', sizeof(id->fr));
-	strncpy((char *)id->fr, UTS_RELEASE, sizeof(id->fr));
+	memcpy_and_pad(id->mn, sizeof(id->mn), model, sizeof(model) - 1, ' ');
+	memcpy_and_pad(id->fr, sizeof(id->fr),
+		       UTS_RELEASE, strlen(UTS_RELEASE), ' ');
 
 	/* no limit on data transfer sizes for now */
 	id->mdts = 0;
@@ -273,6 +298,9 @@ static void nvmet_execute_disc_set_features(struct nvmet_req *req)
 	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
 	u16 stat;
 
+	if (!nvmet_check_data_len(req, 0))
+		return;
+
 	switch (cdw10 & 0xff) {
 	case NVME_FEAT_KATO:
 		stat = nvmet_set_feat_kato(req);
@@ -296,6 +324,9 @@ static void nvmet_execute_disc_get_features(struct nvmet_req *req)
 	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
 	u16 stat = 0;
 
+	if (!nvmet_check_data_len(req, 0))
+		return;
+
 	switch (cdw10 & 0xff) {
 	case NVME_FEAT_KATO:
 		nvmet_get_feat_kato(req);
@@ -328,47 +359,22 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
 	switch (cmd->common.opcode) {
 	case nvme_admin_set_features:
 		req->execute = nvmet_execute_disc_set_features;
-		req->data_len = 0;
 		return 0;
 	case nvme_admin_get_features:
 		req->execute = nvmet_execute_disc_get_features;
-		req->data_len = 0;
 		return 0;
 	case nvme_admin_async_event:
 		req->execute = nvmet_execute_async_event;
-		req->data_len = 0;
 		return 0;
 	case nvme_admin_keep_alive:
 		req->execute = nvmet_execute_keep_alive;
-		req->data_len = 0;
 		return 0;
 	case nvme_admin_get_log_page:
-		req->data_len = nvmet_get_log_page_len(cmd);
-
-		switch (cmd->get_log_page.lid) {
-		case NVME_LOG_DISC:
-			req->execute = nvmet_execute_get_disc_log_page;
-			return 0;
-		default:
-			pr_err("unsupported get_log_page lid %d\n",
-			       cmd->get_log_page.lid);
-			req->error_loc =
-				offsetof(struct nvme_get_log_page_command, lid);
-			return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
-		}
+		req->execute = nvmet_execute_disc_get_log_page;
+		return 0;
 	case nvme_admin_identify:
-		req->data_len = NVME_IDENTIFY_DATA_SIZE;
-		switch (cmd->identify.cns) {
-		case NVME_ID_CNS_CTRL:
-			req->execute =
-				nvmet_execute_identify_disc_ctrl;
-			return 0;
-		default:
-			pr_err("unsupported identify cns %d\n",
-			       cmd->identify.cns);
-			req->error_loc = offsetof(struct nvme_identify, cns);
-			return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
-		}
+		req->execute = nvmet_execute_disc_identify;
+		return 0;
 	default:
 		pr_err("unhandled cmd %d\n", cmd->common.opcode);
 		req->error_loc = offsetof(struct nvme_common_command, opcode);
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index d16b55ffe79f..f7297473d9eb 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -12,6 +12,9 @@ static void nvmet_execute_prop_set(struct nvmet_req *req)
 	u64 val = le64_to_cpu(req->cmd->prop_set.value);
 	u16 status = 0;
 
+	if (!nvmet_check_data_len(req, 0))
+		return;
+
 	if (req->cmd->prop_set.attrib & 1) {
 		req->error_loc =
 			offsetof(struct nvmf_property_set_command, attrib);
@@ -38,6 +41,9 @@ static void nvmet_execute_prop_get(struct nvmet_req *req)
 	u16 status = 0;
 	u64 val = 0;
 
+	if (!nvmet_check_data_len(req, 0))
+		return;
+
 	if (req->cmd->prop_get.attrib & 1) {
 		switch (le32_to_cpu(req->cmd->prop_get.offset)) {
 		case NVME_REG_CAP:
@@ -82,11 +88,9 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req)
 
 	switch (cmd->fabrics.fctype) {
 	case nvme_fabrics_type_property_set:
-		req->data_len = 0;
 		req->execute = nvmet_execute_prop_set;
 		break;
 	case nvme_fabrics_type_property_get:
-		req->data_len = 0;
 		req->execute = nvmet_execute_prop_get;
 		break;
 	default:
@@ -147,6 +151,9 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 	struct nvmet_ctrl *ctrl = NULL;
 	u16 status = 0;
 
+	if (!nvmet_check_data_len(req, sizeof(struct nvmf_connect_data)))
+		return;
+
 	d = kmalloc(sizeof(*d), GFP_KERNEL);
 	if (!d) {
 		status = NVME_SC_INTERNAL;
@@ -211,6 +218,9 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
 	u16 qid = le16_to_cpu(c->qid);
 	u16 status = 0;
 
+	if (!nvmet_check_data_len(req, sizeof(struct nvmf_connect_data)))
+		return;
+
 	d = kmalloc(sizeof(*d), GFP_KERNEL);
 	if (!d) {
 		status = NVME_SC_INTERNAL;
@@ -281,7 +291,6 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req)
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 
-	req->data_len = sizeof(struct nvmf_connect_data);
 	if (cmd->connect.qid == 0)
 		req->execute = nvmet_execute_admin_connect;
 	else
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index ce8d819f86cc..a0db6371b43e 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -1495,20 +1495,20 @@ static void
 nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 			struct nvmet_fc_ls_iod *iod)
 {
-	struct fcnvme_ls_disconnect_rqst *rqst =
-			(struct fcnvme_ls_disconnect_rqst *)iod->rqstbuf;
-	struct fcnvme_ls_disconnect_acc *acc =
-			(struct fcnvme_ls_disconnect_acc *)iod->rspbuf;
+	struct fcnvme_ls_disconnect_assoc_rqst *rqst =
+			(struct fcnvme_ls_disconnect_assoc_rqst *)iod->rqstbuf;
+	struct fcnvme_ls_disconnect_assoc_acc *acc =
+			(struct fcnvme_ls_disconnect_assoc_acc *)iod->rspbuf;
 	struct nvmet_fc_tgt_assoc *assoc;
 	int ret = 0;
 
 	memset(acc, 0, sizeof(*acc));
 
-	if (iod->rqstdatalen < sizeof(struct fcnvme_ls_disconnect_rqst))
+	if (iod->rqstdatalen < sizeof(struct fcnvme_ls_disconnect_assoc_rqst))
 		ret = VERR_DISCONN_LEN;
 	else if (rqst->desc_list_len !=
 			fcnvme_lsdesc_len(
-				sizeof(struct fcnvme_ls_disconnect_rqst)))
+				sizeof(struct fcnvme_ls_disconnect_assoc_rqst)))
 		ret = VERR_DISCONN_RQST_LEN;
 	else if (rqst->associd.desc_tag != cpu_to_be32(FCNVME_LSDESC_ASSOC_ID))
 		ret = VERR_ASSOC_ID;
@@ -1523,8 +1523,11 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 			fcnvme_lsdesc_len(
 				sizeof(struct fcnvme_lsdesc_disconn_cmd)))
 		ret = VERR_DISCONN_CMD_LEN;
-	else if ((rqst->discon_cmd.scope != FCNVME_DISCONN_ASSOCIATION) &&
-			(rqst->discon_cmd.scope != FCNVME_DISCONN_CONNECTION))
+	/*
+	 * As the standard changed on the LS, check if old format and scope
+	 * something other than Association (e.g. 0).
+	 */
+	else if (rqst->discon_cmd.rsvd8[0])
 		ret = VERR_DISCONN_SCOPE;
 	else {
 		/* match an active association */
@@ -1556,8 +1559,8 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 
 	nvmet_fc_format_rsp_hdr(acc, FCNVME_LS_ACC,
 			fcnvme_lsdesc_len(
-				sizeof(struct fcnvme_ls_disconnect_acc)),
-			FCNVME_LS_DISCONNECT);
+				sizeof(struct fcnvme_ls_disconnect_assoc_acc)),
+			FCNVME_LS_DISCONNECT_ASSOC);
 
 	/* release get taken in nvmet_fc_find_target_assoc */
 	nvmet_fc_tgt_a_put(iod->assoc);
@@ -1632,7 +1635,7 @@ nvmet_fc_handle_ls_rqst(struct nvmet_fc_tgtport *tgtport,
 		/* Creates an IO Queue/Connection */
 		nvmet_fc_ls_create_connection(tgtport, iod);
 		break;
-	case FCNVME_LS_DISCONNECT:
+	case FCNVME_LS_DISCONNECT_ASSOC:
 		/* Terminate a Queue/Connection or the Association */
 		nvmet_fc_ls_disconnect(tgtport, iod);
 		break;
@@ -2015,7 +2018,7 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod)
 		}
 
 		/* data transfer complete, resume with nvmet layer */
-		nvmet_req_execute(&fod->req);
+		fod->req.execute(&fod->req);
 		break;
 
 	case NVMET_FCOP_READDATA:
@@ -2231,7 +2234,7 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 	 * can invoke the nvmet_layer now. If read data, cmd completion will
 	 * push the data
 	 */
-	nvmet_req_execute(&fod->req);
+	fod->req.execute(&fod->req);
 	return;
 
 transport_error:
@@ -2299,7 +2302,7 @@ nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *target_port,
 
 	/* validate iu, so the connection id can be used to find the queue */
 	if ((cmdiubuf_len != sizeof(*cmdiu)) ||
-			(cmdiu->scsi_id != NVME_CMD_SCSI_ID) ||
+			(cmdiu->format_id != NVME_CMD_FORMAT_ID) ||
 			(cmdiu->fc_id != NVME_CMD_FC_ID) ||
 			(be16_to_cpu(cmdiu->iu_len) != (sizeof(*cmdiu)/4)))
 		return -EIO;
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index 32008d85172b..b6fca0e421ef 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -147,8 +147,12 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req)
 	int sg_cnt = req->sg_cnt;
 	struct bio *bio;
 	struct scatterlist *sg;
+	struct blk_plug plug;
 	sector_t sector;
-	int op, op_flags = 0, i;
+	int op, i;
+
+	if (!nvmet_check_data_len(req, nvmet_rw_len(req)))
+		return;
 
 	if (!req->sg_cnt) {
 		nvmet_req_complete(req, 0);
@@ -156,21 +160,20 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req)
 	}
 
 	if (req->cmd->rw.opcode == nvme_cmd_write) {
-		op = REQ_OP_WRITE;
-		op_flags = REQ_SYNC | REQ_IDLE;
+		op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
 		if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA))
-			op_flags |= REQ_FUA;
+			op |= REQ_FUA;
 	} else {
 		op = REQ_OP_READ;
 	}
 
 	if (is_pci_p2pdma_page(sg_page(req->sg)))
-		op_flags |= REQ_NOMERGE;
+		op |= REQ_NOMERGE;
 
 	sector = le64_to_cpu(req->cmd->rw.slba);
 	sector <<= (req->ns->blksize_shift - 9);
 
-	if (req->data_len <= NVMET_MAX_INLINE_DATA_LEN) {
+	if (req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN) {
 		bio = &req->b.inline_bio;
 		bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec));
 	} else {
@@ -180,8 +183,9 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req)
 	bio->bi_iter.bi_sector = sector;
 	bio->bi_private = req;
 	bio->bi_end_io = nvmet_bio_done;
-	bio_set_op_attrs(bio, op, op_flags);
+	bio->bi_opf = op;
 
+	blk_start_plug(&plug);
 	for_each_sg(req->sg, sg, req->sg_cnt, i) {
 		while (bio_add_page(bio, sg_page(sg), sg->length, sg->offset)
 				!= sg->length) {
@@ -190,7 +194,7 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req)
 			bio = bio_alloc(GFP_KERNEL, min(sg_cnt, BIO_MAX_PAGES));
 			bio_set_dev(bio, req->ns->bdev);
 			bio->bi_iter.bi_sector = sector;
-			bio_set_op_attrs(bio, op, op_flags);
+			bio->bi_opf = op;
 
 			bio_chain(bio, prev);
 			submit_bio(prev);
@@ -201,12 +205,16 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req)
 	}
 
 	submit_bio(bio);
+	blk_finish_plug(&plug);
 }
 
 static void nvmet_bdev_execute_flush(struct nvmet_req *req)
 {
 	struct bio *bio = &req->b.inline_bio;
 
+	if (!nvmet_check_data_len(req, 0))
+		return;
+
 	bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec));
 	bio_set_dev(bio, req->ns->bdev);
 	bio->bi_private = req;
@@ -261,12 +269,10 @@ static void nvmet_bdev_execute_discard(struct nvmet_req *req)
 	if (bio) {
 		bio->bi_private = req;
 		bio->bi_end_io = nvmet_bio_done;
-		if (status) {
-			bio->bi_status = BLK_STS_IOERR;
-			bio_endio(bio);
-		} else {
+		if (status)
+			bio_io_error(bio);
+		else
 			submit_bio(bio);
-		}
 	} else {
 		nvmet_req_complete(req, status);
 	}
@@ -274,6 +280,9 @@ static void nvmet_bdev_execute_discard(struct nvmet_req *req)
 
 static void nvmet_bdev_execute_dsm(struct nvmet_req *req)
 {
+	if (!nvmet_check_data_len(req, nvmet_dsm_len(req)))
+		return;
+
 	switch (le32_to_cpu(req->cmd->dsm.attributes)) {
 	case NVME_DSMGMT_AD:
 		nvmet_bdev_execute_discard(req);
@@ -295,6 +304,9 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req)
 	sector_t nr_sector;
 	int ret;
 
+	if (!nvmet_check_data_len(req, 0))
+		return;
+
 	sector = le64_to_cpu(write_zeroes->slba) <<
 		(req->ns->blksize_shift - 9);
 	nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) <<
@@ -319,20 +331,15 @@ u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req)
 	case nvme_cmd_read:
 	case nvme_cmd_write:
 		req->execute = nvmet_bdev_execute_rw;
-		req->data_len = nvmet_rw_len(req);
 		return 0;
 	case nvme_cmd_flush:
 		req->execute = nvmet_bdev_execute_flush;
-		req->data_len = 0;
 		return 0;
 	case nvme_cmd_dsm:
 		req->execute = nvmet_bdev_execute_dsm;
-		req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) *
-			sizeof(struct nvme_dsm_range);
 		return 0;
 	case nvme_cmd_write_zeroes:
 		req->execute = nvmet_bdev_execute_write_zeroes;
-		req->data_len = 0;
 		return 0;
 	default:
 		pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index 05453f5d1448..caebfce06605 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -126,7 +126,7 @@ static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2)
 			mempool_free(req->f.bvec, req->ns->bvec_pool);
 	}
 
-	if (unlikely(ret != req->data_len))
+	if (unlikely(ret != req->transfer_len))
 		status = errno_to_nvme_status(req, ret);
 	nvmet_req_complete(req, status);
 }
@@ -146,7 +146,7 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags)
 		is_sync = true;
 
 	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
-	if (unlikely(pos + req->data_len > req->ns->size)) {
+	if (unlikely(pos + req->transfer_len > req->ns->size)) {
 		nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC));
 		return true;
 	}
@@ -173,7 +173,7 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags)
 		nr_bvec--;
 	}
 
-	if (WARN_ON_ONCE(total_len != req->data_len)) {
+	if (WARN_ON_ONCE(total_len != req->transfer_len)) {
 		ret = -EIO;
 		goto complete;
 	}
@@ -232,6 +232,9 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 {
 	ssize_t nr_bvec = req->sg_cnt;
 
+	if (!nvmet_check_data_len(req, nvmet_rw_len(req)))
+		return;
+
 	if (!req->sg_cnt || !nr_bvec) {
 		nvmet_req_complete(req, 0);
 		return;
@@ -273,6 +276,8 @@ static void nvmet_file_flush_work(struct work_struct *w)
 
 static void nvmet_file_execute_flush(struct nvmet_req *req)
 {
+	if (!nvmet_check_data_len(req, 0))
+		return;
 	INIT_WORK(&req->f.work, nvmet_file_flush_work);
 	schedule_work(&req->f.work);
 }
@@ -331,6 +336,8 @@ static void nvmet_file_dsm_work(struct work_struct *w)
 
 static void nvmet_file_execute_dsm(struct nvmet_req *req)
 {
+	if (!nvmet_check_data_len(req, nvmet_dsm_len(req)))
+		return;
 	INIT_WORK(&req->f.work, nvmet_file_dsm_work);
 	schedule_work(&req->f.work);
 }
@@ -359,6 +366,8 @@ static void nvmet_file_write_zeroes_work(struct work_struct *w)
 
 static void nvmet_file_execute_write_zeroes(struct nvmet_req *req)
 {
+	if (!nvmet_check_data_len(req, 0))
+		return;
 	INIT_WORK(&req->f.work, nvmet_file_write_zeroes_work);
 	schedule_work(&req->f.work);
 }
@@ -371,20 +380,15 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
 	case nvme_cmd_read:
 	case nvme_cmd_write:
 		req->execute = nvmet_file_execute_rw;
-		req->data_len = nvmet_rw_len(req);
 		return 0;
 	case nvme_cmd_flush:
 		req->execute = nvmet_file_execute_flush;
-		req->data_len = 0;
 		return 0;
 	case nvme_cmd_dsm:
 		req->execute = nvmet_file_execute_dsm;
-		req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) *
-			sizeof(struct nvme_dsm_range);
 		return 0;
 	case nvme_cmd_write_zeroes:
 		req->execute = nvmet_file_execute_write_zeroes;
-		req->data_len = 0;
 		return 0;
 	default:
 		pr_err("unhandled cmd for file ns %d on qid %d\n",
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 11f5aea97d1b..a758bb3d5dd4 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -76,7 +76,6 @@ static void nvme_loop_complete_rq(struct request *req)
 {
 	struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
 
-	nvme_cleanup_cmd(req);
 	sg_free_table_chained(&iod->sg_table, SG_CHUNK_SIZE);
 	nvme_complete_rq(req);
 }
@@ -102,8 +101,8 @@ static void nvme_loop_queue_response(struct nvmet_req *req)
 	 * aborts.  We don't even bother to allocate a struct request
 	 * for them but rather special case them here.
 	 */
-	if (unlikely(nvme_loop_queue_idx(queue) == 0 &&
-			cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) {
+	if (unlikely(nvme_is_aen_req(nvme_loop_queue_idx(queue),
+				     cqe->command_id))) {
 		nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status,
 				&cqe->result);
 	} else {
@@ -126,7 +125,7 @@ static void nvme_loop_execute_work(struct work_struct *work)
 	struct nvme_loop_iod *iod =
 		container_of(work, struct nvme_loop_iod, work);
 
-	nvmet_req_execute(&iod->req);
+	iod->req.execute(&iod->req);
 }
 
 static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index c51f8dd01dc4..46df45e837c9 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -304,8 +304,6 @@ struct nvmet_req {
 		} f;
 	};
 	int			sg_cnt;
-	/* data length as parsed from the command: */
-	size_t			data_len;
 	/* data length as parsed from the SGL descriptor: */
 	size_t			transfer_len;
 
@@ -375,7 +373,7 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req);
 bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 		struct nvmet_sq *sq, const struct nvmet_fabrics_ops *ops);
 void nvmet_req_uninit(struct nvmet_req *req);
-void nvmet_req_execute(struct nvmet_req *req);
+bool nvmet_check_data_len(struct nvmet_req *req, size_t data_len);
 void nvmet_req_complete(struct nvmet_req *req, u16 status);
 int nvmet_req_alloc_sgl(struct nvmet_req *req);
 void nvmet_req_free_sgl(struct nvmet_req *req);
@@ -495,6 +493,12 @@ static inline u32 nvmet_rw_len(struct nvmet_req *req)
 			req->ns->blksize_shift;
 }
 
+static inline u32 nvmet_dsm_len(struct nvmet_req *req)
+{
+	return (le32_to_cpu(req->cmd->dsm.nr) + 1) *
+		sizeof(struct nvme_dsm_range);
+}
+
 u16 errno_to_nvme_status(struct nvmet_req *req, int errno);
 
 /* Convert a 32-bit number to a 16-bit 0's based number */
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 36d906a7f70d..37d262a65877 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -603,7 +603,7 @@ static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc)
 		return;
 	}
 
-	nvmet_req_execute(&rsp->req);
+	rsp->req.execute(&rsp->req);
 }
 
 static void nvmet_rdma_use_inline_sg(struct nvmet_rdma_rsp *rsp, u32 len,
@@ -672,13 +672,13 @@ static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp,
 		return 0;
 
 	ret = nvmet_req_alloc_sgl(&rsp->req);
-	if (ret < 0)
+	if (unlikely(ret < 0))
 		goto error_out;
 
 	ret = rdma_rw_ctx_init(&rsp->rw, cm_id->qp, cm_id->port_num,
 			rsp->req.sg, rsp->req.sg_cnt, 0, addr, key,
 			nvmet_data_dir(&rsp->req));
-	if (ret < 0)
+	if (unlikely(ret < 0))
 		goto error_out;
 	rsp->n_rdma += ret;
 
@@ -746,7 +746,7 @@ static bool nvmet_rdma_execute_command(struct nvmet_rdma_rsp *rsp)
 				queue->cm_id->port_num, &rsp->read_cqe, NULL))
 			nvmet_req_complete(&rsp->req, NVME_SC_DATA_XFER_ERROR);
 	} else {
-		nvmet_req_execute(&rsp->req);
+		rsp->req.execute(&rsp->req);
 	}
 
 	return true;
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index d535080b781f..af674fc0bb1e 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -320,7 +320,7 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd)
 	struct nvme_sgl_desc *sgl = &cmd->req.cmd->common.dptr.sgl;
 	u32 len = le32_to_cpu(sgl->length);
 
-	if (!cmd->req.data_len)
+	if (!len)
 		return 0;
 
 	if (sgl->type == ((NVME_SGL_FMT_DATA_DESC << 4) |
@@ -813,13 +813,11 @@ free_crypto:
 static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue,
 		struct nvmet_tcp_cmd *cmd, struct nvmet_req *req)
 {
+	size_t data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length);
 	int ret;
 
-	/* recover the expected data transfer length */
-	req->data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length);
-
 	if (!nvme_is_write(cmd->req.cmd) ||
-	    req->data_len > cmd->req.port->inline_data_size) {
+	    data_len > cmd->req.port->inline_data_size) {
 		nvmet_prepare_receive_pdu(queue);
 		return;
 	}
@@ -932,7 +930,7 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue)
 		goto out;
 	}
 
-	nvmet_req_execute(&queue->cmd->req);
+	queue->cmd->req.execute(&queue->cmd->req);
 out:
 	nvmet_prepare_receive_pdu(queue);
 	return ret;
@@ -1052,7 +1050,7 @@ static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue)
 			nvmet_tcp_prep_recv_ddgst(cmd);
 			return 0;
 		}
-		nvmet_req_execute(&cmd->req);
+		cmd->req.execute(&cmd->req);
 	}
 
 	nvmet_prepare_receive_pdu(queue);
@@ -1092,7 +1090,7 @@ static int nvmet_tcp_try_recv_ddgst(struct nvmet_tcp_queue *queue)
 
 	if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED) &&
 	    cmd->rbytes_done == cmd->req.transfer_len)
-		nvmet_req_execute(&cmd->req);
+		cmd->req.execute(&cmd->req);
 	ret = 0;
 out:
 	nvmet_prepare_receive_pdu(queue);
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 057d1ff87d5d..9f1ee9c766ec 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -76,33 +76,6 @@ static struct bus_type nvmem_bus_type = {
 	.name		= "nvmem",
 };
 
-static struct nvmem_device *of_nvmem_find(struct device_node *nvmem_np)
-{
-	struct device *d;
-
-	if (!nvmem_np)
-		return NULL;
-
-	d = bus_find_device_by_of_node(&nvmem_bus_type, nvmem_np);
-
-	if (!d)
-		return NULL;
-
-	return to_nvmem_device(d);
-}
-
-static struct nvmem_device *nvmem_find(const char *name)
-{
-	struct device *d;
-
-	d = bus_find_device_by_name(&nvmem_bus_type, NULL, name);
-
-	if (!d)
-		return NULL;
-
-	return to_nvmem_device(d);
-}
-
 static void nvmem_cell_drop(struct nvmem_cell *cell)
 {
 	blocking_notifier_call_chain(&nvmem_notifier, NVMEM_CELL_REMOVE, cell);
@@ -532,13 +505,16 @@ int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem)
 }
 EXPORT_SYMBOL(devm_nvmem_unregister);
 
-static struct nvmem_device *__nvmem_device_get(struct device_node *np,
-					       const char *nvmem_name)
+static struct nvmem_device *__nvmem_device_get(void *data,
+			int (*match)(struct device *dev, const void *data))
 {
 	struct nvmem_device *nvmem = NULL;
+	struct device *dev;
 
 	mutex_lock(&nvmem_mutex);
-	nvmem = np ? of_nvmem_find(np) : nvmem_find(nvmem_name);
+	dev = bus_find_device(&nvmem_bus_type, NULL, data, match);
+	if (dev)
+		nvmem = to_nvmem_device(dev);
 	mutex_unlock(&nvmem_mutex);
 	if (!nvmem)
 		return ERR_PTR(-EPROBE_DEFER);
@@ -587,7 +563,7 @@ struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *id)
 	if (!nvmem_np)
 		return ERR_PTR(-ENOENT);
 
-	return __nvmem_device_get(nvmem_np, NULL);
+	return __nvmem_device_get(nvmem_np, device_match_of_node);
 }
 EXPORT_SYMBOL_GPL(of_nvmem_device_get);
 #endif
@@ -613,10 +589,26 @@ struct nvmem_device *nvmem_device_get(struct device *dev, const char *dev_name)
 
 	}
 
-	return __nvmem_device_get(NULL, dev_name);
+	return __nvmem_device_get((void *)dev_name, device_match_name);
 }
 EXPORT_SYMBOL_GPL(nvmem_device_get);
 
+/**
+ * nvmem_device_find() - Find nvmem device with matching function
+ *
+ * @data: Data to pass to match function
+ * @match: Callback function to check device
+ *
+ * Return: ERR_PTR() on error or a valid pointer to a struct nvmem_device
+ * on success.
+ */
+struct nvmem_device *nvmem_device_find(void *data,
+			int (*match)(struct device *dev, const void *data))
+{
+	return __nvmem_device_get(data, match);
+}
+EXPORT_SYMBOL_GPL(nvmem_device_find);
+
 static int devm_nvmem_device_match(struct device *dev, void *res, void *data)
 {
 	struct nvmem_device **nvmem = res;
@@ -710,7 +702,8 @@ nvmem_cell_get_from_lookup(struct device *dev, const char *con_id)
 		if ((strcmp(lookup->dev_id, dev_id) == 0) &&
 		    (strcmp(lookup->con_id, con_id) == 0)) {
 			/* This is the right entry. */
-			nvmem = __nvmem_device_get(NULL, lookup->nvmem_name);
+			nvmem = __nvmem_device_get((void *)lookup->nvmem_name,
+						   device_match_name);
 			if (IS_ERR(nvmem)) {
 				/* Provider may not be registered yet. */
 				cell = ERR_CAST(nvmem);
@@ -780,7 +773,7 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id)
 	if (!nvmem_np)
 		return ERR_PTR(-EINVAL);
 
-	nvmem = __nvmem_device_get(nvmem_np, NULL);
+	nvmem = __nvmem_device_get(nvmem_np, device_match_of_node);
 	of_node_put(nvmem_np);
 	if (IS_ERR(nvmem))
 		return ERR_CAST(nvmem);
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 223d617ecfe1..f1c23aad951e 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -412,8 +412,8 @@ void *__unflatten_device_tree(const void *blob,
 	/* Second pass, do actual unflattening */
 	unflatten_dt_nodes(blob, mem, dad, mynodes);
 	if (be32_to_cpup(mem + size) != 0xdeadbeef)
-		pr_warning("End of tree marker overwritten: %08x\n",
-			   be32_to_cpup(mem + size));
+		pr_warn("End of tree marker overwritten: %08x\n",
+			be32_to_cpup(mem + size));
 
 	if (detached && mynodes) {
 		of_node_set_flag(*mynodes, OF_DETACHED);
@@ -1120,25 +1120,25 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
 	size &= PAGE_MASK;
 
 	if (base > MAX_MEMBLOCK_ADDR) {
-		pr_warning("Ignoring memory block 0x%llx - 0x%llx\n",
-				base, base + size);
+		pr_warn("Ignoring memory block 0x%llx - 0x%llx\n",
+			base, base + size);
 		return;
 	}
 
 	if (base + size - 1 > MAX_MEMBLOCK_ADDR) {
-		pr_warning("Ignoring memory range 0x%llx - 0x%llx\n",
-				((u64)MAX_MEMBLOCK_ADDR) + 1, base + size);
+		pr_warn("Ignoring memory range 0x%llx - 0x%llx\n",
+			((u64)MAX_MEMBLOCK_ADDR) + 1, base + size);
 		size = MAX_MEMBLOCK_ADDR - base + 1;
 	}
 
 	if (base + size < phys_offset) {
-		pr_warning("Ignoring memory block 0x%llx - 0x%llx\n",
-			   base, base + size);
+		pr_warn("Ignoring memory block 0x%llx - 0x%llx\n",
+			base, base + size);
 		return;
 	}
 	if (base < phys_offset) {
-		pr_warning("Ignoring memory range 0x%llx - 0x%llx\n",
-			   base, phys_offset);
+		pr_warn("Ignoring memory range 0x%llx - 0x%llx\n",
+			base, phys_offset);
 		size -= phys_offset - base;
 		base = phys_offset;
 	}
diff --git a/drivers/oprofile/oprofile_perf.c b/drivers/oprofile/oprofile_perf.c
index 4b150a754890..98a63a5f8763 100644
--- a/drivers/oprofile/oprofile_perf.c
+++ b/drivers/oprofile/oprofile_perf.c
@@ -46,8 +46,8 @@ static void op_overflow_handler(struct perf_event *event,
 	if (id != num_counters)
 		oprofile_add_sample(regs, id);
 	else
-		pr_warning("oprofile: ignoring spurious overflow "
-				"on cpu %u\n", cpu);
+		pr_warn("oprofile: ignoring spurious overflow on cpu %u\n",
+			cpu);
 }
 
 /*
@@ -88,8 +88,8 @@ static int op_create_counter(int cpu, int event)
 
 	if (pevent->state != PERF_EVENT_STATE_ACTIVE) {
 		perf_event_release_kernel(pevent);
-		pr_warning("oprofile: failed to enable event %d "
-				"on CPU %d\n", event, cpu);
+		pr_warn("oprofile: failed to enable event %d on CPU %d\n",
+			event, cpu);
 		return -EBUSY;
 	}
 
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index 8f8606b9bc9e..1b8e337a29ca 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -1642,7 +1642,6 @@ static struct cci_pmu *cci_pmu_alloc(struct device *dev)
 
 static int cci_pmu_probe(struct platform_device *pdev)
 {
-	struct resource *res;
 	struct cci_pmu *cci_pmu;
 	int i, ret, irq;
 
@@ -1650,8 +1649,7 @@ static int cci_pmu_probe(struct platform_device *pdev)
 	if (IS_ERR(cci_pmu))
 		return PTR_ERR(cci_pmu);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	cci_pmu->base = devm_ioremap_resource(&pdev->dev, res);
+	cci_pmu->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(cci_pmu->base))
 		return -ENOMEM;
 
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 6fc0273b6129..fea354d6fb29 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -1477,8 +1477,7 @@ static int arm_ccn_probe(struct platform_device *pdev)
 	ccn->dev = &pdev->dev;
 	platform_set_drvdata(pdev, ccn);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	ccn->base = devm_ioremap_resource(ccn->dev, res);
+	ccn->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(ccn->base))
 		return PTR_ERR(ccn->base);
 
@@ -1537,6 +1536,7 @@ static int arm_ccn_remove(struct platform_device *pdev)
 static const struct of_device_id arm_ccn_match[] = {
 	{ .compatible = "arm,ccn-502", },
 	{ .compatible = "arm,ccn-504", },
+	{ .compatible = "arm,ccn-512", },
 	{},
 };
 MODULE_DEVICE_TABLE(of, arm_ccn_match);
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
index abcf54f7d19c..773128f411f1 100644
--- a/drivers/perf/arm_smmuv3_pmu.c
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -727,7 +727,7 @@ static void smmu_pmu_get_acpi_options(struct smmu_pmu *smmu_pmu)
 static int smmu_pmu_probe(struct platform_device *pdev)
 {
 	struct smmu_pmu *smmu_pmu;
-	struct resource *res_0, *res_1;
+	struct resource *res_0;
 	u32 cfgr, reg_size;
 	u64 ceid_64[2];
 	int irq, err;
@@ -764,8 +764,7 @@ static int smmu_pmu_probe(struct platform_device *pdev)
 
 	/* Determine if page 1 is present */
 	if (cfgr & SMMU_PMCG_CFGR_RELOC_CTRS) {
-		res_1 = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-		smmu_pmu->reloc_base = devm_ioremap_resource(dev, res_1);
+		smmu_pmu->reloc_base = devm_platform_ioremap_resource(pdev, 1);
 		if (IS_ERR(smmu_pmu->reloc_base))
 			return PTR_ERR(smmu_pmu->reloc_base);
 	} else {
diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c
index ce7345745b42..55083c67b2bb 100644
--- a/drivers/perf/fsl_imx8_ddr_perf.c
+++ b/drivers/perf/fsl_imx8_ddr_perf.c
@@ -45,7 +45,8 @@
 static DEFINE_IDA(ddr_ida);
 
 /* DDR Perf hardware feature */
-#define DDR_CAP_AXI_ID_FILTER          0x1     /* support AXI ID filter */
+#define DDR_CAP_AXI_ID_FILTER			0x1     /* support AXI ID filter */
+#define DDR_CAP_AXI_ID_FILTER_ENHANCED		0x3     /* support enhanced AXI ID filter */
 
 struct fsl_ddr_devtype_data {
 	unsigned int quirks;    /* quirks needed for different DDR Perf core */
@@ -57,9 +58,14 @@ static const struct fsl_ddr_devtype_data imx8m_devtype_data = {
 	.quirks = DDR_CAP_AXI_ID_FILTER,
 };
 
+static const struct fsl_ddr_devtype_data imx8mp_devtype_data = {
+	.quirks = DDR_CAP_AXI_ID_FILTER_ENHANCED,
+};
+
 static const struct of_device_id imx_ddr_pmu_dt_ids[] = {
 	{ .compatible = "fsl,imx8-ddr-pmu", .data = &imx8_devtype_data},
 	{ .compatible = "fsl,imx8m-ddr-pmu", .data = &imx8m_devtype_data},
+	{ .compatible = "fsl,imx8mp-ddr-pmu", .data = &imx8mp_devtype_data},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, imx_ddr_pmu_dt_ids);
@@ -78,6 +84,61 @@ struct ddr_pmu {
 	int id;
 };
 
+enum ddr_perf_filter_capabilities {
+	PERF_CAP_AXI_ID_FILTER = 0,
+	PERF_CAP_AXI_ID_FILTER_ENHANCED,
+	PERF_CAP_AXI_ID_FEAT_MAX,
+};
+
+static u32 ddr_perf_filter_cap_get(struct ddr_pmu *pmu, int cap)
+{
+	u32 quirks = pmu->devtype_data->quirks;
+
+	switch (cap) {
+	case PERF_CAP_AXI_ID_FILTER:
+		return !!(quirks & DDR_CAP_AXI_ID_FILTER);
+	case PERF_CAP_AXI_ID_FILTER_ENHANCED:
+		quirks &= DDR_CAP_AXI_ID_FILTER_ENHANCED;
+		return quirks == DDR_CAP_AXI_ID_FILTER_ENHANCED;
+	default:
+		WARN(1, "unknown filter cap %d\n", cap);
+	}
+
+	return 0;
+}
+
+static ssize_t ddr_perf_filter_cap_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct ddr_pmu *pmu = dev_get_drvdata(dev);
+	struct dev_ext_attribute *ea =
+		container_of(attr, struct dev_ext_attribute, attr);
+	int cap = (long)ea->var;
+
+	return snprintf(buf, PAGE_SIZE, "%u\n",
+			ddr_perf_filter_cap_get(pmu, cap));
+}
+
+#define PERF_EXT_ATTR_ENTRY(_name, _func, _var)				\
+	(&((struct dev_ext_attribute) {					\
+		__ATTR(_name, 0444, _func, NULL), (void *)_var		\
+	}).attr.attr)
+
+#define PERF_FILTER_EXT_ATTR_ENTRY(_name, _var)				\
+	PERF_EXT_ATTR_ENTRY(_name, ddr_perf_filter_cap_show, _var)
+
+static struct attribute *ddr_perf_filter_cap_attr[] = {
+	PERF_FILTER_EXT_ATTR_ENTRY(filter, PERF_CAP_AXI_ID_FILTER),
+	PERF_FILTER_EXT_ATTR_ENTRY(enhanced_filter, PERF_CAP_AXI_ID_FILTER_ENHANCED),
+	NULL,
+};
+
+static struct attribute_group ddr_perf_filter_cap_attr_group = {
+	.name = "caps",
+	.attrs = ddr_perf_filter_cap_attr,
+};
+
 static ssize_t ddr_perf_cpumask_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
@@ -175,9 +236,40 @@ static const struct attribute_group *attr_groups[] = {
 	&ddr_perf_events_attr_group,
 	&ddr_perf_format_attr_group,
 	&ddr_perf_cpumask_attr_group,
+	&ddr_perf_filter_cap_attr_group,
 	NULL,
 };
 
+static bool ddr_perf_is_filtered(struct perf_event *event)
+{
+	return event->attr.config == 0x41 || event->attr.config == 0x42;
+}
+
+static u32 ddr_perf_filter_val(struct perf_event *event)
+{
+	return event->attr.config1;
+}
+
+static bool ddr_perf_filters_compatible(struct perf_event *a,
+					struct perf_event *b)
+{
+	if (!ddr_perf_is_filtered(a))
+		return true;
+	if (!ddr_perf_is_filtered(b))
+		return true;
+	return ddr_perf_filter_val(a) == ddr_perf_filter_val(b);
+}
+
+static bool ddr_perf_is_enhanced_filtered(struct perf_event *event)
+{
+	unsigned int filt;
+	struct ddr_pmu *pmu = to_ddr_pmu(event->pmu);
+
+	filt = pmu->devtype_data->quirks & DDR_CAP_AXI_ID_FILTER_ENHANCED;
+	return (filt == DDR_CAP_AXI_ID_FILTER_ENHANCED) &&
+		ddr_perf_is_filtered(event);
+}
+
 static u32 ddr_perf_alloc_counter(struct ddr_pmu *pmu, int event)
 {
 	int i;
@@ -209,27 +301,17 @@ static void ddr_perf_free_counter(struct ddr_pmu *pmu, int counter)
 
 static u32 ddr_perf_read_counter(struct ddr_pmu *pmu, int counter)
 {
-	return readl_relaxed(pmu->base + COUNTER_READ + counter * 4);
-}
-
-static bool ddr_perf_is_filtered(struct perf_event *event)
-{
-	return event->attr.config == 0x41 || event->attr.config == 0x42;
-}
+	struct perf_event *event = pmu->events[counter];
+	void __iomem *base = pmu->base;
 
-static u32 ddr_perf_filter_val(struct perf_event *event)
-{
-	return event->attr.config1;
-}
-
-static bool ddr_perf_filters_compatible(struct perf_event *a,
-					struct perf_event *b)
-{
-	if (!ddr_perf_is_filtered(a))
-		return true;
-	if (!ddr_perf_is_filtered(b))
-		return true;
-	return ddr_perf_filter_val(a) == ddr_perf_filter_val(b);
+	/*
+	 * return bytes instead of bursts from ddr transaction for
+	 * axid-read and axid-write event if PMU core supports enhanced
+	 * filter.
+	 */
+	base += ddr_perf_is_enhanced_filtered(event) ? COUNTER_DPCR1 :
+						       COUNTER_READ;
+	return readl_relaxed(base + counter * 4);
 }
 
 static int ddr_perf_event_init(struct perf_event *event)
diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
index e42d4464c2cf..453f1c6a16ca 100644
--- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
@@ -243,8 +243,6 @@ MODULE_DEVICE_TABLE(acpi, hisi_ddrc_pmu_acpi_match);
 static int hisi_ddrc_pmu_init_data(struct platform_device *pdev,
 				   struct hisi_pmu *ddrc_pmu)
 {
-	struct resource *res;
-
 	/*
 	 * Use the SCCL_ID and DDRC channel ID to identify the
 	 * DDRC PMU, while SCCL_ID is in MPIDR[aff2].
@@ -263,8 +261,7 @@ static int hisi_ddrc_pmu_init_data(struct platform_device *pdev,
 	/* DDRC PMUs only share the same SCCL */
 	ddrc_pmu->ccl_id = -1;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	ddrc_pmu->base = devm_ioremap_resource(&pdev->dev, res);
+	ddrc_pmu->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(ddrc_pmu->base)) {
 		dev_err(&pdev->dev, "ioremap failed for ddrc_pmu resource\n");
 		return PTR_ERR(ddrc_pmu->base);
diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
index f28063873e11..6a1dd72d8abb 100644
--- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
@@ -234,7 +234,6 @@ static int hisi_hha_pmu_init_data(struct platform_device *pdev,
 				  struct hisi_pmu *hha_pmu)
 {
 	unsigned long long id;
-	struct resource *res;
 	acpi_status status;
 
 	status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev),
@@ -256,8 +255,7 @@ static int hisi_hha_pmu_init_data(struct platform_device *pdev,
 	/* HHA PMUs only share the same SCCL */
 	hha_pmu->ccl_id = -1;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	hha_pmu->base = devm_ioremap_resource(&pdev->dev, res);
+	hha_pmu->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(hha_pmu->base)) {
 		dev_err(&pdev->dev, "ioremap failed for hha_pmu resource\n");
 		return PTR_ERR(hha_pmu->base);
diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
index 078b8dc57250..1151e99b241c 100644
--- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
@@ -233,7 +233,6 @@ static int hisi_l3c_pmu_init_data(struct platform_device *pdev,
 				  struct hisi_pmu *l3c_pmu)
 {
 	unsigned long long id;
-	struct resource *res;
 	acpi_status status;
 
 	status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev),
@@ -259,8 +258,7 @@ static int hisi_l3c_pmu_init_data(struct platform_device *pdev,
 		return -EINVAL;
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	l3c_pmu->base = devm_ioremap_resource(&pdev->dev, res);
+	l3c_pmu->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(l3c_pmu->base)) {
 		dev_err(&pdev->dev, "ioremap failed for l3c_pmu resource\n");
 		return PTR_ERR(l3c_pmu->base);
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c
index 79f76f8dda8e..96183e31b96a 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c
@@ -15,6 +15,7 @@
 #include <linux/errno.h>
 #include <linux/interrupt.h>
 
+#include <asm/cputype.h>
 #include <asm/local64.h>
 
 #include "hisi_uncore_pmu.h"
@@ -338,8 +339,10 @@ void hisi_uncore_pmu_disable(struct pmu *pmu)
 
 /*
  * Read Super CPU cluster and CPU cluster ID from MPIDR_EL1.
- * If multi-threading is supported, CCL_ID is the low 3-bits in MPIDR[Aff2]
- * and SCCL_ID is the upper 5-bits of Aff2 field; if not, SCCL_ID
+ * If multi-threading is supported, On Huawei Kunpeng 920 SoC whose cpu
+ * core is tsv110, CCL_ID is the low 3-bits in MPIDR[Aff2] and SCCL_ID
+ * is the upper 5-bits of Aff2 field; while for other cpu types, SCCL_ID
+ * is in MPIDR[Aff3] and CCL_ID is in MPIDR[Aff2], if not, SCCL_ID
  * is in MPIDR[Aff2] and CCL_ID is in MPIDR[Aff1].
  */
 static void hisi_read_sccl_and_ccl_id(int *sccl_id, int *ccl_id)
@@ -347,12 +350,19 @@ static void hisi_read_sccl_and_ccl_id(int *sccl_id, int *ccl_id)
 	u64 mpidr = read_cpuid_mpidr();
 
 	if (mpidr & MPIDR_MT_BITMASK) {
-		int aff2 = MPIDR_AFFINITY_LEVEL(mpidr, 2);
-
-		if (sccl_id)
-			*sccl_id = aff2 >> 3;
-		if (ccl_id)
-			*ccl_id = aff2 & 0x7;
+		if (read_cpuid_part_number() == HISI_CPU_PART_TSV110) {
+			int aff2 = MPIDR_AFFINITY_LEVEL(mpidr, 2);
+
+			if (sccl_id)
+				*sccl_id = aff2 >> 3;
+			if (ccl_id)
+				*ccl_id = aff2 & 0x7;
+		} else {
+			if (sccl_id)
+				*sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 3);
+			if (ccl_id)
+				*ccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
+		}
 	} else {
 		if (sccl_id)
 			*sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
diff --git a/drivers/perf/thunderx2_pmu.c b/drivers/perf/thunderx2_pmu.c
index 43d76c85da56..51b31d6ff2c4 100644
--- a/drivers/perf/thunderx2_pmu.c
+++ b/drivers/perf/thunderx2_pmu.c
@@ -16,23 +16,36 @@
  * they need to be sampled before overflow(i.e, at every 2 seconds).
  */
 
-#define TX2_PMU_MAX_COUNTERS		4
+#define TX2_PMU_DMC_L3C_MAX_COUNTERS	4
+#define TX2_PMU_CCPI2_MAX_COUNTERS	8
+#define TX2_PMU_MAX_COUNTERS		TX2_PMU_CCPI2_MAX_COUNTERS
+
+
 #define TX2_PMU_DMC_CHANNELS		8
 #define TX2_PMU_L3_TILES		16
 
 #define TX2_PMU_HRTIMER_INTERVAL	(2 * NSEC_PER_SEC)
-#define GET_EVENTID(ev)			((ev->hw.config) & 0x1f)
-#define GET_COUNTERID(ev)		((ev->hw.idx) & 0x3)
+#define GET_EVENTID(ev, mask)		((ev->hw.config) & mask)
+#define GET_COUNTERID(ev, mask)		((ev->hw.idx) & mask)
  /* 1 byte per counter(4 counters).
   * Event id is encoded in bits [5:1] of a byte,
   */
 #define DMC_EVENT_CFG(idx, val)		((val) << (((idx) * 8) + 1))
 
+/* bits[3:0] to select counters, are indexed from 8 to 15. */
+#define CCPI2_COUNTER_OFFSET		8
+
 #define L3C_COUNTER_CTL			0xA8
 #define L3C_COUNTER_DATA		0xAC
 #define DMC_COUNTER_CTL			0x234
 #define DMC_COUNTER_DATA		0x240
 
+#define CCPI2_PERF_CTL			0x108
+#define CCPI2_COUNTER_CTL		0x10C
+#define CCPI2_COUNTER_SEL		0x12c
+#define CCPI2_COUNTER_DATA_L		0x130
+#define CCPI2_COUNTER_DATA_H		0x134
+
 /* L3C event IDs */
 #define L3_EVENT_READ_REQ		0xD
 #define L3_EVENT_WRITEBACK_REQ		0xE
@@ -51,15 +64,28 @@
 #define DMC_EVENT_READ_TXNS		0xF
 #define DMC_EVENT_MAX			0x10
 
+#define CCPI2_EVENT_REQ_PKT_SENT	0x3D
+#define CCPI2_EVENT_SNOOP_PKT_SENT	0x65
+#define CCPI2_EVENT_DATA_PKT_SENT	0x105
+#define CCPI2_EVENT_GIC_PKT_SENT	0x12D
+#define CCPI2_EVENT_MAX			0x200
+
+#define CCPI2_PERF_CTL_ENABLE		BIT(0)
+#define CCPI2_PERF_CTL_START		BIT(1)
+#define CCPI2_PERF_CTL_RESET		BIT(4)
+#define CCPI2_EVENT_LEVEL_RISING_EDGE	BIT(10)
+#define CCPI2_EVENT_TYPE_EDGE_SENSITIVE	BIT(11)
+
 enum tx2_uncore_type {
 	PMU_TYPE_L3C,
 	PMU_TYPE_DMC,
+	PMU_TYPE_CCPI2,
 	PMU_TYPE_INVALID,
 };
 
 /*
- * pmu on each socket has 2 uncore devices(dmc and l3c),
- * each device has 4 counters.
+ * Each socket has 3 uncore devices associated with a PMU. The DMC and
+ * L3C have 4 32-bit counters and the CCPI2 has 8 64-bit counters.
  */
 struct tx2_uncore_pmu {
 	struct hlist_node hpnode;
@@ -69,8 +95,10 @@ struct tx2_uncore_pmu {
 	int node;
 	int cpu;
 	u32 max_counters;
+	u32 counters_mask;
 	u32 prorate_factor;
 	u32 max_events;
+	u32 events_mask;
 	u64 hrtimer_interval;
 	void __iomem *base;
 	DECLARE_BITMAP(active_counters, TX2_PMU_MAX_COUNTERS);
@@ -79,6 +107,7 @@ struct tx2_uncore_pmu {
 	struct hrtimer hrtimer;
 	const struct attribute_group **attr_groups;
 	enum tx2_uncore_type type;
+	enum hrtimer_restart (*hrtimer_callback)(struct hrtimer *cb);
 	void (*init_cntr_base)(struct perf_event *event,
 			struct tx2_uncore_pmu *tx2_pmu);
 	void (*stop_event)(struct perf_event *event);
@@ -92,7 +121,21 @@ static inline struct tx2_uncore_pmu *pmu_to_tx2_pmu(struct pmu *pmu)
 	return container_of(pmu, struct tx2_uncore_pmu, pmu);
 }
 
-PMU_FORMAT_ATTR(event,	"config:0-4");
+#define TX2_PMU_FORMAT_ATTR(_var, _name, _format)			\
+static ssize_t								\
+__tx2_pmu_##_var##_show(struct device *dev,				\
+			       struct device_attribute *attr,		\
+			       char *page)				\
+{									\
+	BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE);			\
+	return sprintf(page, _format "\n");				\
+}									\
+									\
+static struct device_attribute format_attr_##_var =			\
+	__ATTR(_name, 0444, __tx2_pmu_##_var##_show, NULL)
+
+TX2_PMU_FORMAT_ATTR(event, event, "config:0-4");
+TX2_PMU_FORMAT_ATTR(event_ccpi2, event, "config:0-9");
 
 static struct attribute *l3c_pmu_format_attrs[] = {
 	&format_attr_event.attr,
@@ -104,6 +147,11 @@ static struct attribute *dmc_pmu_format_attrs[] = {
 	NULL,
 };
 
+static struct attribute *ccpi2_pmu_format_attrs[] = {
+	&format_attr_event_ccpi2.attr,
+	NULL,
+};
+
 static const struct attribute_group l3c_pmu_format_attr_group = {
 	.name = "format",
 	.attrs = l3c_pmu_format_attrs,
@@ -114,6 +162,11 @@ static const struct attribute_group dmc_pmu_format_attr_group = {
 	.attrs = dmc_pmu_format_attrs,
 };
 
+static const struct attribute_group ccpi2_pmu_format_attr_group = {
+	.name = "format",
+	.attrs = ccpi2_pmu_format_attrs,
+};
+
 /*
  * sysfs event attributes
  */
@@ -164,6 +217,19 @@ static struct attribute *dmc_pmu_events_attrs[] = {
 	NULL,
 };
 
+TX2_EVENT_ATTR(req_pktsent, CCPI2_EVENT_REQ_PKT_SENT);
+TX2_EVENT_ATTR(snoop_pktsent, CCPI2_EVENT_SNOOP_PKT_SENT);
+TX2_EVENT_ATTR(data_pktsent, CCPI2_EVENT_DATA_PKT_SENT);
+TX2_EVENT_ATTR(gic_pktsent, CCPI2_EVENT_GIC_PKT_SENT);
+
+static struct attribute *ccpi2_pmu_events_attrs[] = {
+	&tx2_pmu_event_attr_req_pktsent.attr.attr,
+	&tx2_pmu_event_attr_snoop_pktsent.attr.attr,
+	&tx2_pmu_event_attr_data_pktsent.attr.attr,
+	&tx2_pmu_event_attr_gic_pktsent.attr.attr,
+	NULL,
+};
+
 static const struct attribute_group l3c_pmu_events_attr_group = {
 	.name = "events",
 	.attrs = l3c_pmu_events_attrs,
@@ -174,6 +240,11 @@ static const struct attribute_group dmc_pmu_events_attr_group = {
 	.attrs = dmc_pmu_events_attrs,
 };
 
+static const struct attribute_group ccpi2_pmu_events_attr_group = {
+	.name = "events",
+	.attrs = ccpi2_pmu_events_attrs,
+};
+
 /*
  * sysfs cpumask attributes
  */
@@ -213,6 +284,13 @@ static const struct attribute_group *dmc_pmu_attr_groups[] = {
 	NULL
 };
 
+static const struct attribute_group *ccpi2_pmu_attr_groups[] = {
+	&ccpi2_pmu_format_attr_group,
+	&pmu_cpumask_attr_group,
+	&ccpi2_pmu_events_attr_group,
+	NULL
+};
+
 static inline u32 reg_readl(unsigned long addr)
 {
 	return readl((void __iomem *)addr);
@@ -245,33 +323,58 @@ static void init_cntr_base_l3c(struct perf_event *event,
 		struct tx2_uncore_pmu *tx2_pmu)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	u32 cmask;
+
+	tx2_pmu = pmu_to_tx2_pmu(event->pmu);
+	cmask = tx2_pmu->counters_mask;
 
 	/* counter ctrl/data reg offset at 8 */
 	hwc->config_base = (unsigned long)tx2_pmu->base
-		+ L3C_COUNTER_CTL + (8 * GET_COUNTERID(event));
+		+ L3C_COUNTER_CTL + (8 * GET_COUNTERID(event, cmask));
 	hwc->event_base =  (unsigned long)tx2_pmu->base
-		+ L3C_COUNTER_DATA + (8 * GET_COUNTERID(event));
+		+ L3C_COUNTER_DATA + (8 * GET_COUNTERID(event, cmask));
 }
 
 static void init_cntr_base_dmc(struct perf_event *event,
 		struct tx2_uncore_pmu *tx2_pmu)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	u32 cmask;
+
+	tx2_pmu = pmu_to_tx2_pmu(event->pmu);
+	cmask = tx2_pmu->counters_mask;
 
 	hwc->config_base = (unsigned long)tx2_pmu->base
 		+ DMC_COUNTER_CTL;
 	/* counter data reg offset at 0xc */
 	hwc->event_base = (unsigned long)tx2_pmu->base
-		+ DMC_COUNTER_DATA + (0xc * GET_COUNTERID(event));
+		+ DMC_COUNTER_DATA + (0xc * GET_COUNTERID(event, cmask));
+}
+
+static void init_cntr_base_ccpi2(struct perf_event *event,
+		struct tx2_uncore_pmu *tx2_pmu)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	u32 cmask;
+
+	cmask = tx2_pmu->counters_mask;
+
+	hwc->config_base = (unsigned long)tx2_pmu->base
+		+ CCPI2_COUNTER_CTL + (4 * GET_COUNTERID(event, cmask));
+	hwc->event_base =  (unsigned long)tx2_pmu->base;
 }
 
 static void uncore_start_event_l3c(struct perf_event *event, int flags)
 {
-	u32 val;
+	u32 val, emask;
 	struct hw_perf_event *hwc = &event->hw;
+	struct tx2_uncore_pmu *tx2_pmu;
+
+	tx2_pmu = pmu_to_tx2_pmu(event->pmu);
+	emask = tx2_pmu->events_mask;
 
 	/* event id encoded in bits [07:03] */
-	val = GET_EVENTID(event) << 3;
+	val = GET_EVENTID(event, emask) << 3;
 	reg_writel(val, hwc->config_base);
 	local64_set(&hwc->prev_count, 0);
 	reg_writel(0, hwc->event_base);
@@ -284,10 +387,17 @@ static inline void uncore_stop_event_l3c(struct perf_event *event)
 
 static void uncore_start_event_dmc(struct perf_event *event, int flags)
 {
-	u32 val;
+	u32 val, cmask, emask;
 	struct hw_perf_event *hwc = &event->hw;
-	int idx = GET_COUNTERID(event);
-	int event_id = GET_EVENTID(event);
+	struct tx2_uncore_pmu *tx2_pmu;
+	int idx, event_id;
+
+	tx2_pmu = pmu_to_tx2_pmu(event->pmu);
+	cmask = tx2_pmu->counters_mask;
+	emask = tx2_pmu->events_mask;
+
+	idx = GET_COUNTERID(event, cmask);
+	event_id = GET_EVENTID(event, emask);
 
 	/* enable and start counters.
 	 * 8 bits for each counter, bits[05:01] of a counter to set event type.
@@ -302,9 +412,14 @@ static void uncore_start_event_dmc(struct perf_event *event, int flags)
 
 static void uncore_stop_event_dmc(struct perf_event *event)
 {
-	u32 val;
+	u32 val, cmask;
 	struct hw_perf_event *hwc = &event->hw;
-	int idx = GET_COUNTERID(event);
+	struct tx2_uncore_pmu *tx2_pmu;
+	int idx;
+
+	tx2_pmu = pmu_to_tx2_pmu(event->pmu);
+	cmask = tx2_pmu->counters_mask;
+	idx = GET_COUNTERID(event, cmask);
 
 	/* clear event type(bits[05:01]) to stop counter */
 	val = reg_readl(hwc->config_base);
@@ -312,27 +427,72 @@ static void uncore_stop_event_dmc(struct perf_event *event)
 	reg_writel(val, hwc->config_base);
 }
 
+static void uncore_start_event_ccpi2(struct perf_event *event, int flags)
+{
+	u32 emask;
+	struct hw_perf_event *hwc = &event->hw;
+	struct tx2_uncore_pmu *tx2_pmu;
+
+	tx2_pmu = pmu_to_tx2_pmu(event->pmu);
+	emask = tx2_pmu->events_mask;
+
+	/* Bit [09:00] to set event id.
+	 * Bits [10], set level to rising edge.
+	 * Bits [11], set type to edge sensitive.
+	 */
+	reg_writel((CCPI2_EVENT_TYPE_EDGE_SENSITIVE |
+			CCPI2_EVENT_LEVEL_RISING_EDGE |
+			GET_EVENTID(event, emask)), hwc->config_base);
+
+	/* reset[4], enable[0] and start[1] counters */
+	reg_writel(CCPI2_PERF_CTL_RESET |
+			CCPI2_PERF_CTL_START |
+			CCPI2_PERF_CTL_ENABLE,
+			hwc->event_base + CCPI2_PERF_CTL);
+	local64_set(&event->hw.prev_count, 0ULL);
+}
+
+static void uncore_stop_event_ccpi2(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/* disable and stop counter */
+	reg_writel(0, hwc->event_base + CCPI2_PERF_CTL);
+}
+
 static void tx2_uncore_event_update(struct perf_event *event)
 {
-	s64 prev, delta, new = 0;
+	u64 prev, delta, new = 0;
 	struct hw_perf_event *hwc = &event->hw;
 	struct tx2_uncore_pmu *tx2_pmu;
 	enum tx2_uncore_type type;
 	u32 prorate_factor;
+	u32 cmask, emask;
 
 	tx2_pmu = pmu_to_tx2_pmu(event->pmu);
 	type = tx2_pmu->type;
+	cmask = tx2_pmu->counters_mask;
+	emask = tx2_pmu->events_mask;
 	prorate_factor = tx2_pmu->prorate_factor;
-
-	new = reg_readl(hwc->event_base);
-	prev = local64_xchg(&hwc->prev_count, new);
-
-	/* handles rollover of 32 bit counter */
-	delta = (u32)(((1UL << 32) - prev) + new);
+	if (type == PMU_TYPE_CCPI2) {
+		reg_writel(CCPI2_COUNTER_OFFSET +
+				GET_COUNTERID(event, cmask),
+				hwc->event_base + CCPI2_COUNTER_SEL);
+		new = reg_readl(hwc->event_base + CCPI2_COUNTER_DATA_H);
+		new = (new << 32) +
+			reg_readl(hwc->event_base + CCPI2_COUNTER_DATA_L);
+		prev = local64_xchg(&hwc->prev_count, new);
+		delta = new - prev;
+	} else {
+		new = reg_readl(hwc->event_base);
+		prev = local64_xchg(&hwc->prev_count, new);
+		/* handles rollover of 32 bit counter */
+		delta = (u32)(((1UL << 32) - prev) + new);
+	}
 
 	/* DMC event data_transfers granularity is 16 Bytes, convert it to 64 */
 	if (type == PMU_TYPE_DMC &&
-			GET_EVENTID(event) == DMC_EVENT_DATA_TRANSFERS)
+			GET_EVENTID(event, emask) == DMC_EVENT_DATA_TRANSFERS)
 		delta = delta/4;
 
 	/* L3C and DMC has 16 and 8 interleave channels respectively.
@@ -351,6 +511,7 @@ static enum tx2_uncore_type get_tx2_pmu_type(struct acpi_device *adev)
 	} devices[] = {
 		{"CAV901D", PMU_TYPE_L3C},
 		{"CAV901F", PMU_TYPE_DMC},
+		{"CAV901E", PMU_TYPE_CCPI2},
 		{"", PMU_TYPE_INVALID}
 	};
 
@@ -380,7 +541,8 @@ static bool tx2_uncore_validate_event(struct pmu *pmu,
  * Make sure the group of events can be scheduled at once
  * on the PMU.
  */
-static bool tx2_uncore_validate_event_group(struct perf_event *event)
+static bool tx2_uncore_validate_event_group(struct perf_event *event,
+		int max_counters)
 {
 	struct perf_event *sibling, *leader = event->group_leader;
 	int counters = 0;
@@ -403,7 +565,7 @@ static bool tx2_uncore_validate_event_group(struct perf_event *event)
 	 * If the group requires more counters than the HW has,
 	 * it cannot ever be scheduled.
 	 */
-	return counters <= TX2_PMU_MAX_COUNTERS;
+	return counters <= max_counters;
 }
 
 
@@ -439,7 +601,7 @@ static int tx2_uncore_event_init(struct perf_event *event)
 	hwc->config = event->attr.config;
 
 	/* Validate the group */
-	if (!tx2_uncore_validate_event_group(event))
+	if (!tx2_uncore_validate_event_group(event, tx2_pmu->max_counters))
 		return -EINVAL;
 
 	return 0;
@@ -456,6 +618,10 @@ static void tx2_uncore_event_start(struct perf_event *event, int flags)
 	tx2_pmu->start_event(event, flags);
 	perf_event_update_userpage(event);
 
+	/* No hrtimer needed for CCPI2, 64-bit counters */
+	if (!tx2_pmu->hrtimer_callback)
+		return;
+
 	/* Start timer for first event */
 	if (bitmap_weight(tx2_pmu->active_counters,
 				tx2_pmu->max_counters) == 1) {
@@ -510,15 +676,23 @@ static void tx2_uncore_event_del(struct perf_event *event, int flags)
 {
 	struct tx2_uncore_pmu *tx2_pmu = pmu_to_tx2_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
+	u32 cmask;
 
+	cmask = tx2_pmu->counters_mask;
 	tx2_uncore_event_stop(event, PERF_EF_UPDATE);
 
 	/* clear the assigned counter */
-	free_counter(tx2_pmu, GET_COUNTERID(event));
+	free_counter(tx2_pmu, GET_COUNTERID(event, cmask));
 
 	perf_event_update_userpage(event);
 	tx2_pmu->events[hwc->idx] = NULL;
 	hwc->idx = -1;
+
+	if (!tx2_pmu->hrtimer_callback)
+		return;
+
+	if (bitmap_empty(tx2_pmu->active_counters, tx2_pmu->max_counters))
+		hrtimer_cancel(&tx2_pmu->hrtimer);
 }
 
 static void tx2_uncore_event_read(struct perf_event *event)
@@ -580,8 +754,12 @@ static int tx2_uncore_pmu_add_dev(struct tx2_uncore_pmu *tx2_pmu)
 			cpu_online_mask);
 
 	tx2_pmu->cpu = cpu;
-	hrtimer_init(&tx2_pmu->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	tx2_pmu->hrtimer.function = tx2_hrtimer_callback;
+
+	if (tx2_pmu->hrtimer_callback) {
+		hrtimer_init(&tx2_pmu->hrtimer,
+				CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+		tx2_pmu->hrtimer.function = tx2_pmu->hrtimer_callback;
+	}
 
 	ret = tx2_uncore_pmu_register(tx2_pmu);
 	if (ret) {
@@ -653,10 +831,13 @@ static struct tx2_uncore_pmu *tx2_uncore_pmu_init_dev(struct device *dev,
 
 	switch (tx2_pmu->type) {
 	case PMU_TYPE_L3C:
-		tx2_pmu->max_counters = TX2_PMU_MAX_COUNTERS;
+		tx2_pmu->max_counters = TX2_PMU_DMC_L3C_MAX_COUNTERS;
+		tx2_pmu->counters_mask = 0x3;
 		tx2_pmu->prorate_factor = TX2_PMU_L3_TILES;
 		tx2_pmu->max_events = L3_EVENT_MAX;
+		tx2_pmu->events_mask = 0x1f;
 		tx2_pmu->hrtimer_interval = TX2_PMU_HRTIMER_INTERVAL;
+		tx2_pmu->hrtimer_callback = tx2_hrtimer_callback;
 		tx2_pmu->attr_groups = l3c_pmu_attr_groups;
 		tx2_pmu->name = devm_kasprintf(dev, GFP_KERNEL,
 				"uncore_l3c_%d", tx2_pmu->node);
@@ -665,10 +846,13 @@ static struct tx2_uncore_pmu *tx2_uncore_pmu_init_dev(struct device *dev,
 		tx2_pmu->stop_event = uncore_stop_event_l3c;
 		break;
 	case PMU_TYPE_DMC:
-		tx2_pmu->max_counters = TX2_PMU_MAX_COUNTERS;
+		tx2_pmu->max_counters = TX2_PMU_DMC_L3C_MAX_COUNTERS;
+		tx2_pmu->counters_mask = 0x3;
 		tx2_pmu->prorate_factor = TX2_PMU_DMC_CHANNELS;
 		tx2_pmu->max_events = DMC_EVENT_MAX;
+		tx2_pmu->events_mask = 0x1f;
 		tx2_pmu->hrtimer_interval = TX2_PMU_HRTIMER_INTERVAL;
+		tx2_pmu->hrtimer_callback = tx2_hrtimer_callback;
 		tx2_pmu->attr_groups = dmc_pmu_attr_groups;
 		tx2_pmu->name = devm_kasprintf(dev, GFP_KERNEL,
 				"uncore_dmc_%d", tx2_pmu->node);
@@ -676,6 +860,21 @@ static struct tx2_uncore_pmu *tx2_uncore_pmu_init_dev(struct device *dev,
 		tx2_pmu->start_event = uncore_start_event_dmc;
 		tx2_pmu->stop_event = uncore_stop_event_dmc;
 		break;
+	case PMU_TYPE_CCPI2:
+		/* CCPI2 has 8 counters */
+		tx2_pmu->max_counters = TX2_PMU_CCPI2_MAX_COUNTERS;
+		tx2_pmu->counters_mask = 0x7;
+		tx2_pmu->prorate_factor = 1;
+		tx2_pmu->max_events = CCPI2_EVENT_MAX;
+		tx2_pmu->events_mask = 0x1ff;
+		tx2_pmu->attr_groups = ccpi2_pmu_attr_groups;
+		tx2_pmu->name = devm_kasprintf(dev, GFP_KERNEL,
+				"uncore_ccpi2_%d", tx2_pmu->node);
+		tx2_pmu->init_cntr_base = init_cntr_base_ccpi2;
+		tx2_pmu->start_event = uncore_start_event_ccpi2;
+		tx2_pmu->stop_event = uncore_stop_event_ccpi2;
+		tx2_pmu->hrtimer_callback = NULL;
+		break;
 	case PMU_TYPE_INVALID:
 		devm_kfree(dev, tx2_pmu);
 		return NULL;
@@ -744,7 +943,9 @@ static int tx2_uncore_pmu_offline_cpu(unsigned int cpu,
 	if (cpu != tx2_pmu->cpu)
 		return 0;
 
-	hrtimer_cancel(&tx2_pmu->hrtimer);
+	if (tx2_pmu->hrtimer_callback)
+		hrtimer_cancel(&tx2_pmu->hrtimer);
+
 	cpumask_copy(&cpu_online_mask_temp, cpu_online_mask);
 	cpumask_clear_cpu(cpu, &cpu_online_mask_temp);
 	new_cpu = cpumask_any_and(
diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index 7e328d6385c3..46ee6807d533 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -1282,25 +1282,21 @@ static int acpi_pmu_probe_active_mcb_mcu_l3c(struct xgene_pmu *xgene_pmu,
 					     struct platform_device *pdev)
 {
 	void __iomem *csw_csr, *mcba_csr, *mcbb_csr;
-	struct resource *res;
 	unsigned int reg;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	csw_csr = devm_ioremap_resource(&pdev->dev, res);
+	csw_csr = devm_platform_ioremap_resource(pdev, 1);
 	if (IS_ERR(csw_csr)) {
 		dev_err(&pdev->dev, "ioremap failed for CSW CSR resource\n");
 		return PTR_ERR(csw_csr);
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
-	mcba_csr = devm_ioremap_resource(&pdev->dev, res);
+	mcba_csr = devm_platform_ioremap_resource(pdev, 2);
 	if (IS_ERR(mcba_csr)) {
 		dev_err(&pdev->dev, "ioremap failed for MCBA CSR resource\n");
 		return PTR_ERR(mcba_csr);
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 3);
-	mcbb_csr = devm_ioremap_resource(&pdev->dev, res);
+	mcbb_csr = devm_platform_ioremap_resource(pdev, 3);
 	if (IS_ERR(mcbb_csr)) {
 		dev_err(&pdev->dev, "ioremap failed for MCBB CSR resource\n");
 		return PTR_ERR(mcbb_csr);
@@ -1332,13 +1328,11 @@ static int acpi_pmu_v3_probe_active_mcb_mcu_l3c(struct xgene_pmu *xgene_pmu,
 						struct platform_device *pdev)
 {
 	void __iomem *csw_csr;
-	struct resource *res;
 	unsigned int reg;
 	u32 mcb0routing;
 	u32 mcb1routing;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	csw_csr = devm_ioremap_resource(&pdev->dev, res);
+	csw_csr = devm_platform_ioremap_resource(pdev, 1);
 	if (IS_ERR(csw_csr)) {
 		dev_err(&pdev->dev, "ioremap failed for CSW CSR resource\n");
 		return PTR_ERR(csw_csr);
diff --git a/drivers/platform/mips/Kconfig b/drivers/platform/mips/Kconfig
index 62ea1934fb6a..f4d0a86c00d0 100644
--- a/drivers/platform/mips/Kconfig
+++ b/drivers/platform/mips/Kconfig
@@ -17,8 +17,8 @@ menuconfig MIPS_PLATFORM_DEVICES
 if MIPS_PLATFORM_DEVICES
 
 config CPU_HWMON
-	tristate "Loongson CPU HWMon Driver"
-	depends on LOONGSON_MACH3X
+	tristate "Loongson-3 CPU HWMon Driver"
+	depends on CONFIG_MACH_LOONGSON64
 	select HWMON
 	default y
 	help
diff --git a/drivers/platform/mips/cpu_hwmon.c b/drivers/platform/mips/cpu_hwmon.c
index a7f184bb47e0..0d27cb7a9e3c 100644
--- a/drivers/platform/mips/cpu_hwmon.c
+++ b/drivers/platform/mips/cpu_hwmon.c
@@ -9,6 +9,9 @@
 #include <loongson.h>
 #include <boot_param.h>
 #include <loongson_hwmon.h>
+#include <loongson_regs.h>
+
+static int csr_temp_enable = 0;
 
 /*
  * Loongson-3 series cpu has two sensors inside,
@@ -20,8 +23,14 @@ int loongson3_cpu_temp(int cpu)
 {
 	u32 reg, prid_rev;
 
+	if (csr_temp_enable) {
+		reg = (csr_readl(LOONGSON_CSR_CPUTEMP) & 0xff);
+		goto out;
+	}
+
 	reg = LOONGSON_CHIPTEMP(cpu);
 	prid_rev = read_c0_prid() & PRID_REV_MASK;
+
 	switch (prid_rev) {
 	case PRID_REV_LOONGSON3A_R1:
 		reg = (reg >> 8) & 0xff;
@@ -34,9 +43,12 @@ int loongson3_cpu_temp(int cpu)
 		break;
 	case PRID_REV_LOONGSON3A_R3_0:
 	case PRID_REV_LOONGSON3A_R3_1:
+	default:
 		reg = (reg & 0xffff)*731/0x4000 - 273;
 		break;
 	}
+
+out:
 	return (int)reg * 1000;
 }
 
@@ -159,9 +171,12 @@ static int __init loongson_hwmon_init(void)
 
 	pr_info("Loongson Hwmon Enter...\n");
 
+	if (cpu_has_csr())
+		csr_temp_enable = csr_readl(LOONGSON_CSR_FEATURES) & LOONGSON_CSRF_TEMP;
+
 	cpu_hwmon_dev = hwmon_device_register(NULL);
 	if (IS_ERR(cpu_hwmon_dev)) {
-		ret = -ENOMEM;
+		ret = PTR_ERR(cpu_hwmon_dev);
 		pr_err("hwmon_device_register fail!\n");
 		goto fail_hwmon_device_register;
 	}
diff --git a/drivers/platform/x86/asus-laptop.c b/drivers/platform/x86/asus-laptop.c
index 472af7edf0af..ca65e1039f92 100644
--- a/drivers/platform/x86/asus-laptop.c
+++ b/drivers/platform/x86/asus-laptop.c
@@ -1148,7 +1148,7 @@ static void asus_als_switch(struct asus_laptop *asus, int value)
 		ret = write_acpi_int(asus->handle, METHOD_ALS_CONTROL, value);
 	}
 	if (ret)
-		pr_warning("Error setting light sensor switch\n");
+		pr_warn("Error setting light sensor switch\n");
 
 	asus->light_switch = value;
 }
diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c
index f3f74a9c109e..776868d5e458 100644
--- a/drivers/platform/x86/eeepc-laptop.c
+++ b/drivers/platform/x86/eeepc-laptop.c
@@ -578,7 +578,7 @@ static void eeepc_rfkill_hotplug(struct eeepc_laptop *eeepc, acpi_handle handle)
 
 	port = acpi_get_pci_dev(handle);
 	if (!port) {
-		pr_warning("Unable to find port\n");
+		pr_warn("Unable to find port\n");
 		goto out_unlock;
 	}
 
diff --git a/drivers/platform/x86/intel_oaktrail.c b/drivers/platform/x86/intel_oaktrail.c
index 3c0438ba385e..1a09a75bd16d 100644
--- a/drivers/platform/x86/intel_oaktrail.c
+++ b/drivers/platform/x86/intel_oaktrail.c
@@ -243,7 +243,7 @@ static int oaktrail_backlight_init(void)
 
 	if (IS_ERR(bd)) {
 		oaktrail_bl_device = NULL;
-		pr_warning("Unable to register backlight device\n");
+		pr_warn("Unable to register backlight device\n");
 		return PTR_ERR(bd);
 	}
 
@@ -313,20 +313,20 @@ static int __init oaktrail_init(void)
 
 	ret = platform_driver_register(&oaktrail_driver);
 	if (ret) {
-		pr_warning("Unable to register platform driver\n");
+		pr_warn("Unable to register platform driver\n");
 		goto err_driver_reg;
 	}
 
 	oaktrail_device = platform_device_alloc(DRIVER_NAME, -1);
 	if (!oaktrail_device) {
-		pr_warning("Unable to allocate platform device\n");
+		pr_warn("Unable to allocate platform device\n");
 		ret = -ENOMEM;
 		goto err_device_alloc;
 	}
 
 	ret = platform_device_add(oaktrail_device);
 	if (ret) {
-		pr_warning("Unable to add platform device\n");
+		pr_warn("Unable to add platform device\n");
 		goto err_device_add;
 	}
 
@@ -338,7 +338,7 @@ static int __init oaktrail_init(void)
 
 	ret = oaktrail_rfkill_init();
 	if (ret) {
-		pr_warning("Setup rfkill failed\n");
+		pr_warn("Setup rfkill failed\n");
 		goto err_rfkill;
 	}
 
diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c
index 5542d9eadfe0..7d079154f849 100644
--- a/drivers/s390/block/dasd_genhd.c
+++ b/drivers/s390/block/dasd_genhd.c
@@ -116,7 +116,9 @@ int dasd_scan_partitions(struct dasd_block *block)
 		return -ENODEV;
 	}
 
-	rc = blkdev_reread_part(bdev);
+	mutex_lock(&bdev->bd_mutex);
+	rc = bdev_disk_changed(bdev, false);
+	mutex_unlock(&bdev->bd_mutex);
 	if (rc)
 		DBF_DEV_EVENT(DBF_ERR, block->base,
 				"scan partitions error, rc %d", rc);
diff --git a/drivers/s390/cio/Makefile b/drivers/s390/cio/Makefile
index f6a8db04177c..23eae4188876 100644
--- a/drivers/s390/cio/Makefile
+++ b/drivers/s390/cio/Makefile
@@ -5,7 +5,7 @@
 
 # The following is required for define_trace.h to find ./trace.h
 CFLAGS_trace.o := -I$(src)
-CFLAGS_vfio_ccw_fsm.o := -I$(src)
+CFLAGS_vfio_ccw_trace.o := -I$(src)
 
 obj-y += airq.o blacklist.o chsc.o cio.o css.o chp.o idset.o isc.o \
 	fcx.o itcw.o crw.o ccwreq.o trace.o ioasm.o
@@ -21,5 +21,5 @@ qdio-objs := qdio_main.o qdio_thinint.o qdio_debug.o qdio_setup.o
 obj-$(CONFIG_QDIO) += qdio.o
 
 vfio_ccw-objs += vfio_ccw_drv.o vfio_ccw_cp.o vfio_ccw_ops.o vfio_ccw_fsm.o \
-	vfio_ccw_async.o
+	vfio_ccw_async.o vfio_ccw_trace.o
 obj-$(CONFIG_VFIO_CCW) += vfio_ccw.o
diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h
index 2a34a2ab9bf7..4b0798472643 100644
--- a/drivers/s390/cio/qdio.h
+++ b/drivers/s390/cio/qdio.h
@@ -253,9 +253,6 @@ struct qdio_q {
 	/* input or output queue */
 	int is_input_q;
 
-	/* list of thinint input queues */
-	struct list_head entry;
-
 	/* upper-layer program handler */
 	qdio_handler_t (*handler);
 
@@ -273,6 +270,7 @@ struct qdio_irq {
 	struct qib qib;
 	u32 *dsci;		/* address of device state change indicator */
 	struct ccw_device *cdev;
+	struct list_head entry;		/* list of thinint devices */
 	struct dentry *debugfs_dev;
 	struct dentry *debugfs_perf;
 
@@ -318,13 +316,15 @@ struct qdio_irq {
 
 #define qperf(__qdev, __attr)	((__qdev)->perf_stat.(__attr))
 
-#define qperf_inc(__q, __attr)						\
+#define QDIO_PERF_STAT_INC(__irq, __attr)				\
 ({									\
-	struct qdio_irq *qdev = (__q)->irq_ptr;				\
+	struct qdio_irq *qdev = __irq;					\
 	if (qdev->perf_stat_enabled)					\
 		(qdev->perf_stat.__attr)++;				\
 })
 
+#define qperf_inc(__q, __attr)	QDIO_PERF_STAT_INC((__q)->irq_ptr, __attr)
+
 static inline void account_sbals_error(struct qdio_q *q, int count)
 {
 	q->q_stats.nr_sbal_error += count;
@@ -356,14 +356,10 @@ static inline int multicast_outbound(struct qdio_q *q)
 	for (i = 0; i < irq_ptr->nr_output_qs &&	\
 		({ q = irq_ptr->output_qs[i]; 1; }); i++)
 
-#define prev_buf(bufnr)	\
-	((bufnr + QDIO_MAX_BUFFERS_MASK) & QDIO_MAX_BUFFERS_MASK)
-#define next_buf(bufnr)	\
-	((bufnr + 1) & QDIO_MAX_BUFFERS_MASK)
-#define add_buf(bufnr, inc) \
-	((bufnr + inc) & QDIO_MAX_BUFFERS_MASK)
-#define sub_buf(bufnr, dec) \
-	((bufnr - dec) & QDIO_MAX_BUFFERS_MASK)
+#define add_buf(bufnr, inc)	QDIO_BUFNR((bufnr) + (inc))
+#define next_buf(bufnr)		add_buf(bufnr, 1)
+#define sub_buf(bufnr, dec)	QDIO_BUFNR((bufnr) - (dec))
+#define prev_buf(bufnr)		sub_buf(bufnr, 1)
 
 #define queue_irqs_enabled(q)			\
 	(test_bit(QDIO_QUEUE_IRQS_DISABLED, &q->u.in.queue_irq_state) == 0)
@@ -376,8 +372,8 @@ extern u64 last_ai_time;
 void qdio_setup_thinint(struct qdio_irq *irq_ptr);
 int qdio_establish_thinint(struct qdio_irq *irq_ptr);
 void qdio_shutdown_thinint(struct qdio_irq *irq_ptr);
-void tiqdio_add_input_queues(struct qdio_irq *irq_ptr);
-void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr);
+void tiqdio_add_device(struct qdio_irq *irq_ptr);
+void tiqdio_remove_device(struct qdio_irq *irq_ptr);
 void tiqdio_inbound_processing(unsigned long q);
 int tiqdio_allocate_memory(void);
 void tiqdio_free_memory(void);
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 7368407030b0..f8b897b7e78b 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -131,7 +131,7 @@ again:
 	case 96:
 		/* not all buffers processed */
 		qperf_inc(q, eqbs_partial);
-		DBF_DEV_EVENT(DBF_WARN, q->irq_ptr, "EQBS part:%02x",
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "EQBS part:%02x",
 			tmp_count);
 		return count - tmp_count;
 	case 97:
@@ -424,9 +424,6 @@ static inline void account_sbals(struct qdio_q *q, unsigned int count)
 static void process_buffer_error(struct qdio_q *q, unsigned int start,
 				 int count)
 {
-	unsigned char state = (q->is_input_q) ? SLSB_P_INPUT_NOT_INIT :
-					SLSB_P_OUTPUT_NOT_INIT;
-
 	q->qdio_error = QDIO_ERROR_SLSB_STATE;
 
 	/* special handling for no target buffer empty */
@@ -434,7 +431,7 @@ static void process_buffer_error(struct qdio_q *q, unsigned int start,
 	    q->sbal[start]->element[15].sflags == 0x10) {
 		qperf_inc(q, target_full);
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "OUTFULL FTC:%02x", start);
-		goto set;
+		return;
 	}
 
 	DBF_ERROR("%4x BUF ERROR", SCH_NO(q));
@@ -443,13 +440,6 @@ static void process_buffer_error(struct qdio_q *q, unsigned int start,
 	DBF_ERROR("F14:%2x F15:%2x",
 		  q->sbal[start]->element[14].sflags,
 		  q->sbal[start]->element[15].sflags);
-
-set:
-	/*
-	 * Interrupts may be avoided as long as the error is present
-	 * so change the buffer state immediately to avoid starvation.
-	 */
-	set_buf_states(q, start, state, count);
 }
 
 static inline void inbound_primed(struct qdio_q *q, unsigned int start,
@@ -531,6 +521,11 @@ static int get_inbound_buffer_frontier(struct qdio_q *q, unsigned int start)
 		return count;
 	case SLSB_P_INPUT_ERROR:
 		process_buffer_error(q, start, count);
+		/*
+		 * Interrupts may be avoided as long as the error is present
+		 * so change the buffer state immediately to avoid starvation.
+		 */
+		set_buf_states(q, start, SLSB_P_INPUT_NOT_INIT, count);
 		if (atomic_sub_return(count, &q->nr_buf_used) == 0)
 			qperf_inc(q, inbound_queue_full);
 		if (q->irq_ptr->perf_stat_enabled)
@@ -965,7 +960,7 @@ static void qdio_int_handler_pci(struct qdio_irq *irq_ptr)
 			/* skip if polling is enabled or already in work */
 			if (test_and_set_bit(QDIO_QUEUE_IRQS_DISABLED,
 				     &q->u.in.queue_irq_state)) {
-				qperf_inc(q, int_discarded);
+				QDIO_PERF_STAT_INC(irq_ptr, int_discarded);
 				continue;
 			}
 			q->u.in.queue_start_poll(q->irq_ptr->cdev, q->nr,
@@ -1164,7 +1159,7 @@ int qdio_shutdown(struct ccw_device *cdev, int how)
 	 */
 	qdio_set_state(irq_ptr, QDIO_IRQ_STATE_STOPPED);
 
-	tiqdio_remove_input_queues(irq_ptr);
+	tiqdio_remove_device(irq_ptr);
 	qdio_shutdown_queues(cdev);
 	qdio_shutdown_debug_entries(irq_ptr);
 
@@ -1286,6 +1281,7 @@ int qdio_allocate(struct qdio_initialize *init_data)
 			     init_data->no_output_qs))
 		goto out_rel;
 
+	INIT_LIST_HEAD(&irq_ptr->entry);
 	init_data->cdev->private->qdio_data = irq_ptr;
 	qdio_set_state(irq_ptr, QDIO_IRQ_STATE_INACTIVE);
 	return 0;
@@ -1430,7 +1426,7 @@ int qdio_activate(struct ccw_device *cdev)
 	}
 
 	if (is_thinint_irq(irq_ptr))
-		tiqdio_add_input_queues(irq_ptr);
+		tiqdio_add_device(irq_ptr);
 
 	/* wait for subchannel to become active */
 	msleep(5);
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index cd164886132f..dc430bd86ade 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -150,7 +150,6 @@ static int __qdio_allocate_qs(struct qdio_q **irq_ptr_qs, int nr_queues)
 			return -ENOMEM;
 		}
 		irq_ptr_qs[i] = q;
-		INIT_LIST_HEAD(&q->entry);
 	}
 	return 0;
 }
@@ -179,7 +178,6 @@ static void setup_queues_misc(struct qdio_q *q, struct qdio_irq *irq_ptr,
 	q->mask = 1 << (31 - i);
 	q->nr = i;
 	q->handler = handler;
-	INIT_LIST_HEAD(&q->entry);
 }
 
 static void setup_storage_lists(struct qdio_q *q, struct qdio_irq *irq_ptr,
diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c
index 93ee067c10ca..7c4e4ec08a12 100644
--- a/drivers/s390/cio/qdio_thinint.c
+++ b/drivers/s390/cio/qdio_thinint.c
@@ -39,14 +39,6 @@ struct indicator_t {
 static LIST_HEAD(tiq_list);
 static DEFINE_MUTEX(tiq_list_lock);
 
-/* Adapter interrupt definitions */
-static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating);
-
-static struct airq_struct tiqdio_airq = {
-	.handler = tiqdio_thinint_handler,
-	.isc = QDIO_AIRQ_ISC,
-};
-
 static struct indicator_t *q_indicators;
 
 u64 last_ai_time;
@@ -74,26 +66,20 @@ static void put_indicator(u32 *addr)
 	atomic_dec(&ind->count);
 }
 
-void tiqdio_add_input_queues(struct qdio_irq *irq_ptr)
+void tiqdio_add_device(struct qdio_irq *irq_ptr)
 {
 	mutex_lock(&tiq_list_lock);
-	list_add_rcu(&irq_ptr->input_qs[0]->entry, &tiq_list);
+	list_add_rcu(&irq_ptr->entry, &tiq_list);
 	mutex_unlock(&tiq_list_lock);
 }
 
-void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr)
+void tiqdio_remove_device(struct qdio_irq *irq_ptr)
 {
-	struct qdio_q *q;
-
-	q = irq_ptr->input_qs[0];
-	if (!q)
-		return;
-
 	mutex_lock(&tiq_list_lock);
-	list_del_rcu(&q->entry);
+	list_del_rcu(&irq_ptr->entry);
 	mutex_unlock(&tiq_list_lock);
 	synchronize_rcu();
-	INIT_LIST_HEAD(&q->entry);
+	INIT_LIST_HEAD(&irq_ptr->entry);
 }
 
 static inline int has_multiple_inq_on_dsci(struct qdio_irq *irq_ptr)
@@ -154,7 +140,7 @@ static inline void tiqdio_call_inq_handlers(struct qdio_irq *irq)
 			/* skip if polling is enabled or already in work */
 			if (test_and_set_bit(QDIO_QUEUE_IRQS_DISABLED,
 					     &q->u.in.queue_irq_state)) {
-				qperf_inc(q, int_discarded);
+				QDIO_PERF_STAT_INC(irq, int_discarded);
 				continue;
 			}
 
@@ -182,7 +168,7 @@ static inline void tiqdio_call_inq_handlers(struct qdio_irq *irq)
 static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating)
 {
 	u32 si_used = clear_shared_ind();
-	struct qdio_q *q;
+	struct qdio_irq *irq;
 
 	last_ai_time = S390_lowcore.int_clock;
 	inc_irq_stat(IRQIO_QAI);
@@ -190,12 +176,8 @@ static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating)
 	/* protect tiq_list entries, only changed in activate or shutdown */
 	rcu_read_lock();
 
-	/* check for work on all inbound thinint queues */
-	list_for_each_entry_rcu(q, &tiq_list, entry) {
-		struct qdio_irq *irq;
-
+	list_for_each_entry_rcu(irq, &tiq_list, entry) {
 		/* only process queues from changed sets */
-		irq = q->irq_ptr;
 		if (unlikely(references_shared_dsci(irq))) {
 			if (!si_used)
 				continue;
@@ -204,11 +186,16 @@ static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating)
 
 		tiqdio_call_inq_handlers(irq);
 
-		qperf_inc(q, adapter_int);
+		QDIO_PERF_STAT_INC(irq, adapter_int);
 	}
 	rcu_read_unlock();
 }
 
+static struct airq_struct tiqdio_airq = {
+	.handler = tiqdio_thinint_handler,
+	.isc = QDIO_AIRQ_ISC,
+};
+
 static int set_subchannel_ind(struct qdio_irq *irq_ptr, int reset)
 {
 	struct chsc_scssc_area *scssc = (void *)irq_ptr->chsc_page;
diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h
index 7cdc38049033..ba31240ce965 100644
--- a/drivers/s390/cio/vfio_ccw_cp.h
+++ b/drivers/s390/cio/vfio_ccw_cp.h
@@ -15,6 +15,7 @@
 #include <asm/scsw.h>
 
 #include "orb.h"
+#include "vfio_ccw_trace.h"
 
 /*
  * Max length for ccw chain.
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index 4a1e727c62d9..23e61aa638e4 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -15,9 +15,6 @@
 #include "ioasm.h"
 #include "vfio_ccw_private.h"
 
-#define CREATE_TRACE_POINTS
-#include "vfio_ccw_trace.h"
-
 static int fsm_io_helper(struct vfio_ccw_private *private)
 {
 	struct subchannel *sch;
@@ -321,8 +318,8 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 	}
 
 err_out:
-	trace_vfio_ccw_io_fctl(scsw->cmd.fctl, schid,
-			       io_region->ret_code, errstr);
+	trace_vfio_ccw_fsm_io_request(scsw->cmd.fctl, schid,
+				      io_region->ret_code, errstr);
 }
 
 /*
@@ -344,6 +341,10 @@ static void fsm_async_request(struct vfio_ccw_private *private,
 		/* should not happen? */
 		cmd_region->ret_code = -EINVAL;
 	}
+
+	trace_vfio_ccw_fsm_async_request(get_schid(private),
+					 cmd_region->command,
+					 cmd_region->ret_code);
 }
 
 /*
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index bbe9babf767b..9b9bb4982972 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -135,6 +135,7 @@ extern fsm_func_t *vfio_ccw_jumptable[NR_VFIO_CCW_STATES][NR_VFIO_CCW_EVENTS];
 static inline void vfio_ccw_fsm_event(struct vfio_ccw_private *private,
 				     int event)
 {
+	trace_vfio_ccw_fsm_event(private->sch->schid, private->state, event);
 	vfio_ccw_jumptable[private->state][event](private, event);
 }
 
diff --git a/drivers/s390/cio/vfio_ccw_trace.c b/drivers/s390/cio/vfio_ccw_trace.c
new file mode 100644
index 000000000000..8c671d2519f6
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_trace.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Tracepoint definitions for vfio_ccw
+ *
+ * Copyright IBM Corp. 2019
+ * Author(s): Eric Farman <farman@linux.ibm.com>
+ */
+
+#define CREATE_TRACE_POINTS
+#include "vfio_ccw_trace.h"
+
+EXPORT_TRACEPOINT_SYMBOL(vfio_ccw_fsm_async_request);
+EXPORT_TRACEPOINT_SYMBOL(vfio_ccw_fsm_event);
+EXPORT_TRACEPOINT_SYMBOL(vfio_ccw_fsm_io_request);
diff --git a/drivers/s390/cio/vfio_ccw_trace.h b/drivers/s390/cio/vfio_ccw_trace.h
index b1da53ddec1f..30162a318a8a 100644
--- a/drivers/s390/cio/vfio_ccw_trace.h
+++ b/drivers/s390/cio/vfio_ccw_trace.h
@@ -7,6 +7,8 @@
  *            Halil Pasic <pasic@linux.vnet.ibm.com>
  */
 
+#include "cio.h"
+
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM vfio_ccw
 
@@ -15,28 +17,88 @@
 
 #include <linux/tracepoint.h>
 
-TRACE_EVENT(vfio_ccw_io_fctl,
+TRACE_EVENT(vfio_ccw_fsm_async_request,
+	TP_PROTO(struct subchannel_id schid,
+		 int command,
+		 int errno),
+	TP_ARGS(schid, command, errno),
+
+	TP_STRUCT__entry(
+		__field(u8, cssid)
+		__field(u8, ssid)
+		__field(u16, sch_no)
+		__field(int, command)
+		__field(int, errno)
+	),
+
+	TP_fast_assign(
+		__entry->cssid = schid.cssid;
+		__entry->ssid = schid.ssid;
+		__entry->sch_no = schid.sch_no;
+		__entry->command = command;
+		__entry->errno = errno;
+	),
+
+	TP_printk("schid=%x.%x.%04x command=0x%x errno=%d",
+		  __entry->cssid,
+		  __entry->ssid,
+		  __entry->sch_no,
+		  __entry->command,
+		  __entry->errno)
+);
+
+TRACE_EVENT(vfio_ccw_fsm_event,
+	TP_PROTO(struct subchannel_id schid, int state, int event),
+	TP_ARGS(schid, state, event),
+
+	TP_STRUCT__entry(
+		__field(u8, cssid)
+		__field(u8, ssid)
+		__field(u16, schno)
+		__field(int, state)
+		__field(int, event)
+	),
+
+	TP_fast_assign(
+		__entry->cssid = schid.cssid;
+		__entry->ssid = schid.ssid;
+		__entry->schno = schid.sch_no;
+		__entry->state = state;
+		__entry->event = event;
+	),
+
+	TP_printk("schid=%x.%x.%04x state=%d event=%d",
+		__entry->cssid, __entry->ssid, __entry->schno,
+		__entry->state,
+		__entry->event)
+);
+
+TRACE_EVENT(vfio_ccw_fsm_io_request,
 	TP_PROTO(int fctl, struct subchannel_id schid, int errno, char *errstr),
 	TP_ARGS(fctl, schid, errno, errstr),
 
 	TP_STRUCT__entry(
+		__field(u8, cssid)
+		__field(u8, ssid)
+		__field(u16, sch_no)
 		__field(int, fctl)
-		__field_struct(struct subchannel_id, schid)
 		__field(int, errno)
 		__field(char*, errstr)
 	),
 
 	TP_fast_assign(
+		__entry->cssid = schid.cssid;
+		__entry->ssid = schid.ssid;
+		__entry->sch_no = schid.sch_no;
 		__entry->fctl = fctl;
-		__entry->schid = schid;
 		__entry->errno = errno;
 		__entry->errstr = errstr;
 	),
 
-	TP_printk("schid=%x.%x.%04x fctl=%x errno=%d info=%s",
-		  __entry->schid.cssid,
-		  __entry->schid.ssid,
-		  __entry->schid.sch_no,
+	TP_printk("schid=%x.%x.%04x fctl=0x%x errno=%d info=%s",
+		  __entry->cssid,
+		  __entry->ssid,
+		  __entry->sch_no,
 		  __entry->fctl,
 		  __entry->errno,
 		  __entry->errstr)
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index 9de3d46b3253..d78d77686d7b 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -715,36 +715,18 @@ out:
 
 static void *_copy_key_from_user(void __user *ukey, size_t keylen)
 {
-	void *kkey;
-
 	if (!ukey || keylen < MINKEYBLOBSIZE || keylen > KEYBLOBBUFSIZE)
 		return ERR_PTR(-EINVAL);
-	kkey = kmalloc(keylen, GFP_KERNEL);
-	if (!kkey)
-		return ERR_PTR(-ENOMEM);
-	if (copy_from_user(kkey, ukey, keylen)) {
-		kfree(kkey);
-		return ERR_PTR(-EFAULT);
-	}
 
-	return kkey;
+	return memdup_user(ukey, keylen);
 }
 
 static void *_copy_apqns_from_user(void __user *uapqns, size_t nr_apqns)
 {
-	void *kapqns = NULL;
-	size_t nbytes;
-
-	if (uapqns && nr_apqns > 0) {
-		nbytes = nr_apqns * sizeof(struct pkey_apqn);
-		kapqns = kmalloc(nbytes, GFP_KERNEL);
-		if (!kapqns)
-			return ERR_PTR(-ENOMEM);
-		if (copy_from_user(kapqns, uapqns, nbytes))
-			return ERR_PTR(-EFAULT);
-	}
+	if (!uapqns || nr_apqns == 0)
+		return NULL;
 
-	return kapqns;
+	return memdup_user(uapqns, nr_apqns * sizeof(struct pkey_apqn));
 }
 
 static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h
index 2421f29021c1..5db04fe472c0 100644
--- a/drivers/s390/net/qeth_l3.h
+++ b/drivers/s390/net/qeth_l3.h
@@ -13,8 +13,6 @@
 #include "qeth_core.h"
 #include <linux/hashtable.h>
 
-#define QETH_SNIFF_AVAIL	0x0008
-
 enum qeth_ip_types {
 	QETH_IP_TYPE_NORMAL,
 	QETH_IP_TYPE_VIPA,
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index b6b38b69a5f4..f9067ed6c7d3 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -204,7 +204,7 @@ static ssize_t qeth_l3_dev_sniffer_store(struct device *dev,
 		break;
 	case 1:
 		qdio_get_ssqd_desc(CARD_DDEV(card), &card->ssqd);
-		if (card->ssqd.qdioac2 & QETH_SNIFF_AVAIL) {
+		if (card->ssqd.qdioac2 & CHSC_AC2_SNIFFER_AVAILABLE) {
 			card->options.sniffer = i;
 			if (card->qdio.init_pool.buf_count !=
 					QETH_IN_BUF_COUNT_MAX)
diff --git a/drivers/scsi/a3000.c b/drivers/scsi/a3000.c
index 222c77c9621f..b6a0432f305a 100644
--- a/drivers/scsi/a3000.c
+++ b/drivers/scsi/a3000.c
@@ -39,7 +39,7 @@ static irqreturn_t a3000_intr(int irq, void *data)
 		spin_unlock_irqrestore(instance->host_lock, flags);
 		return IRQ_HANDLED;
 	}
-	pr_warning("Non-serviced A3000 SCSI-interrupt? ISTR = %02x\n", status);
+	pr_warn("Non-serviced A3000 SCSI-interrupt? ISTR = %02x\n", status);
 	return IRQ_NONE;
 }
 
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index ebb40160539f..470ee6dc3f7e 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1291,9 +1291,17 @@ static blk_status_t sd_init_command(struct scsi_cmnd *cmd)
 	case REQ_OP_WRITE:
 		return sd_setup_read_write_cmnd(cmd);
 	case REQ_OP_ZONE_RESET:
-		return sd_zbc_setup_reset_cmnd(cmd, false);
+		return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER,
+						   false);
 	case REQ_OP_ZONE_RESET_ALL:
-		return sd_zbc_setup_reset_cmnd(cmd, true);
+		return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER,
+						   true);
+	case REQ_OP_ZONE_OPEN:
+		return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_OPEN_ZONE, false);
+	case REQ_OP_ZONE_CLOSE:
+		return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_CLOSE_ZONE, false);
+	case REQ_OP_ZONE_FINISH:
+		return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_FINISH_ZONE, false);
 	default:
 		WARN_ON_ONCE(1);
 		return BLK_STS_NOTSUPP;
@@ -1961,6 +1969,9 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 	case REQ_OP_WRITE_SAME:
 	case REQ_OP_ZONE_RESET:
 	case REQ_OP_ZONE_RESET_ALL:
+	case REQ_OP_ZONE_OPEN:
+	case REQ_OP_ZONE_CLOSE:
+	case REQ_OP_ZONE_FINISH:
 		if (!result) {
 			good_bytes = blk_rq_bytes(req);
 			scsi_set_resid(SCpnt, 0);
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 1eab779f812b..42fd3f00e4a5 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -209,11 +209,12 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp)
 
 extern int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer);
 extern void sd_zbc_print_zones(struct scsi_disk *sdkp);
-extern blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all);
+blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
+					 unsigned char op, bool all);
 extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 			    struct scsi_sense_hdr *sshdr);
-extern int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
-			       struct blk_zone *zones, unsigned int *nr_zones);
+int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
+		unsigned int nr_zones, report_zones_cb cb, void *data);
 
 #else /* CONFIG_BLK_DEV_ZONED */
 
@@ -225,8 +226,9 @@ static inline int sd_zbc_read_zones(struct scsi_disk *sdkp,
 
 static inline void sd_zbc_print_zones(struct scsi_disk *sdkp) {}
 
-static inline blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd,
-						   bool all)
+static inline blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
+						       unsigned char op,
+						       bool all)
 {
 	return BLK_STS_TARGET;
 }
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 1efc69e194f8..0e5ede48f045 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -19,34 +19,27 @@
 
 #include "sd.h"
 
-/**
- * sd_zbc_parse_report - Convert a zone descriptor to a struct blk_zone,
- * @sdkp: The disk the report originated from
- * @buf: Address of the report zone descriptor
- * @zone: the destination zone structure
- *
- * All LBA sized values are converted to 512B sectors unit.
- */
-static void sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf,
-				struct blk_zone *zone)
+static int sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf,
+			       unsigned int idx, report_zones_cb cb, void *data)
 {
 	struct scsi_device *sdp = sdkp->device;
+	struct blk_zone zone = { 0 };
 
-	memset(zone, 0, sizeof(struct blk_zone));
-
-	zone->type = buf[0] & 0x0f;
-	zone->cond = (buf[1] >> 4) & 0xf;
+	zone.type = buf[0] & 0x0f;
+	zone.cond = (buf[1] >> 4) & 0xf;
 	if (buf[1] & 0x01)
-		zone->reset = 1;
+		zone.reset = 1;
 	if (buf[1] & 0x02)
-		zone->non_seq = 1;
-
-	zone->len = logical_to_sectors(sdp, get_unaligned_be64(&buf[8]));
-	zone->start = logical_to_sectors(sdp, get_unaligned_be64(&buf[16]));
-	zone->wp = logical_to_sectors(sdp, get_unaligned_be64(&buf[24]));
-	if (zone->type != ZBC_ZONE_TYPE_CONV &&
-	    zone->cond == ZBC_ZONE_COND_FULL)
-		zone->wp = zone->start + zone->len;
+		zone.non_seq = 1;
+
+	zone.len = logical_to_sectors(sdp, get_unaligned_be64(&buf[8]));
+	zone.start = logical_to_sectors(sdp, get_unaligned_be64(&buf[16]));
+	zone.wp = logical_to_sectors(sdp, get_unaligned_be64(&buf[24]));
+	if (zone.type != ZBC_ZONE_TYPE_CONV &&
+	    zone.cond == ZBC_ZONE_COND_FULL)
+		zone.wp = zone.start + zone.len;
+
+	return cb(&zone, idx, data);
 }
 
 /**
@@ -104,11 +97,6 @@ static int sd_zbc_do_report_zones(struct scsi_disk *sdkp, unsigned char *buf,
 	return 0;
 }
 
-/*
- * Maximum number of zones to get with one report zones command.
- */
-#define SD_ZBC_REPORT_MAX_ZONES		8192U
-
 /**
  * Allocate a buffer for report zones reply.
  * @sdkp: The target disk
@@ -138,82 +126,94 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp,
 	 * sure that the allocated buffer can always be mapped by limiting the
 	 * number of pages allocated to the HBA max segments limit.
 	 */
-	nr_zones = min(nr_zones, SD_ZBC_REPORT_MAX_ZONES);
-	bufsize = roundup((nr_zones + 1) * 64, 512);
+	nr_zones = min(nr_zones, sdkp->nr_zones);
+	bufsize = roundup((nr_zones + 1) * 64, SECTOR_SIZE);
 	bufsize = min_t(size_t, bufsize,
 			queue_max_hw_sectors(q) << SECTOR_SHIFT);
 	bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT);
 
-	buf = vzalloc(bufsize);
-	if (buf)
-		*buflen = bufsize;
+	while (bufsize >= SECTOR_SIZE) {
+		buf = __vmalloc(bufsize,
+				GFP_KERNEL | __GFP_ZERO | __GFP_NORETRY,
+				PAGE_KERNEL);
+		if (buf) {
+			*buflen = bufsize;
+			return buf;
+		}
+		bufsize >>= 1;
+	}
 
-	return buf;
+	return NULL;
 }
 
 /**
- * sd_zbc_report_zones - Disk report zones operation.
- * @disk: The target disk
- * @sector: Start 512B sector of the report
- * @zones: Array of zone descriptors
- * @nr_zones: Number of descriptors in the array
- *
- * Execute a report zones command on the target disk.
+ * sd_zbc_zone_sectors - Get the device zone size in number of 512B sectors.
+ * @sdkp: The target disk
  */
+static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp)
+{
+	return logical_to_sectors(sdkp->device, sdkp->zone_blocks);
+}
+
 int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
-			struct blk_zone *zones, unsigned int *nr_zones)
+			unsigned int nr_zones, report_zones_cb cb, void *data)
 {
 	struct scsi_disk *sdkp = scsi_disk(disk);
-	unsigned int i, nrz = *nr_zones;
+	unsigned int nr, i;
 	unsigned char *buf;
-	size_t buflen = 0, offset = 0;
-	int ret = 0;
+	size_t offset, buflen = 0;
+	int zone_idx = 0;
+	int ret;
 
 	if (!sd_is_zoned(sdkp))
 		/* Not a zoned device */
 		return -EOPNOTSUPP;
 
-	buf = sd_zbc_alloc_report_buffer(sdkp, nrz, &buflen);
+	buf = sd_zbc_alloc_report_buffer(sdkp, nr_zones, &buflen);
 	if (!buf)
 		return -ENOMEM;
 
-	ret = sd_zbc_do_report_zones(sdkp, buf, buflen,
-			sectors_to_logical(sdkp->device, sector), true);
-	if (ret)
-		goto out;
+	while (zone_idx < nr_zones && sector < get_capacity(disk)) {
+		ret = sd_zbc_do_report_zones(sdkp, buf, buflen,
+				sectors_to_logical(sdkp->device, sector), true);
+		if (ret)
+			goto out;
+
+		offset = 0;
+		nr = min(nr_zones, get_unaligned_be32(&buf[0]) / 64);
+		if (!nr)
+			break;
+
+		for (i = 0; i < nr && zone_idx < nr_zones; i++) {
+			offset += 64;
+			ret = sd_zbc_parse_report(sdkp, buf + offset, zone_idx,
+						  cb, data);
+			if (ret)
+				goto out;
+			zone_idx++;
+		}
 
-	nrz = min(nrz, get_unaligned_be32(&buf[0]) / 64);
-	for (i = 0; i < nrz; i++) {
-		offset += 64;
-		sd_zbc_parse_report(sdkp, buf + offset, zones);
-		zones++;
+		sector += sd_zbc_zone_sectors(sdkp) * i;
 	}
 
-	*nr_zones = nrz;
-
+	ret = zone_idx;
 out:
 	kvfree(buf);
-
 	return ret;
 }
 
 /**
- * sd_zbc_zone_sectors - Get the device zone size in number of 512B sectors.
- * @sdkp: The target disk
- */
-static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp)
-{
-	return logical_to_sectors(sdkp->device, sdkp->zone_blocks);
-}
-
-/**
- * sd_zbc_setup_reset_cmnd - Prepare a RESET WRITE POINTER scsi command.
+ * sd_zbc_setup_zone_mgmt_cmnd - Prepare a zone ZBC_OUT command. The operations
+ *			can be RESET WRITE POINTER, OPEN, CLOSE or FINISH.
  * @cmd: the command to setup
- * @all: Reset all zones control.
+ * @op: Operation to be performed
+ * @all: All zones control
  *
- * Called from sd_init_command() for a REQ_OP_ZONE_RESET request.
+ * Called from sd_init_command() for REQ_OP_ZONE_RESET, REQ_OP_ZONE_RESET_ALL,
+ * REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE or REQ_OP_ZONE_FINISH requests.
  */
-blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all)
+blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
+					 unsigned char op, bool all)
 {
 	struct request *rq = cmd->request;
 	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
@@ -234,7 +234,7 @@ blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all)
 	cmd->cmd_len = 16;
 	memset(cmd->cmnd, 0, cmd->cmd_len);
 	cmd->cmnd[0] = ZBC_OUT;
-	cmd->cmnd[1] = ZO_RESET_WRITE_POINTER;
+	cmd->cmnd[1] = op;
 	if (all)
 		cmd->cmnd[14] = 0x1;
 	else
@@ -263,14 +263,14 @@ void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 	int result = cmd->result;
 	struct request *rq = cmd->request;
 
-	if (req_op(rq) == REQ_OP_ZONE_RESET &&
+	if (op_is_zone_mgmt(req_op(rq)) &&
 	    result &&
 	    sshdr->sense_key == ILLEGAL_REQUEST &&
 	    sshdr->asc == 0x24) {
 		/*
-		 * INVALID FIELD IN CDB error: reset of a conventional
-		 * zone was attempted. Nothing to worry about, so be
-		 * quiet about the error.
+		 * INVALID FIELD IN CDB error: a zone management command was
+		 * attempted on a conventional zone. Nothing to worry about,
+		 * so be quiet about the error.
 		 */
 		rq->rq_flags |= RQF_QUIET;
 	}
@@ -335,32 +335,18 @@ static int sd_zbc_check_zoned_characteristics(struct scsi_disk *sdkp,
  * Returns the zone size in number of blocks upon success or an error code
  * upon failure.
  */
-static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks)
+static int sd_zbc_check_zones(struct scsi_disk *sdkp, unsigned char *buf,
+			      u32 *zblocks)
 {
-	size_t bufsize, buflen;
-	unsigned int noio_flag;
 	u64 zone_blocks = 0;
-	sector_t max_lba, block = 0;
-	unsigned char *buf;
+	sector_t max_lba;
 	unsigned char *rec;
 	int ret;
-	u8 same;
 
-	/* Do all memory allocations as if GFP_NOIO was specified */
-	noio_flag = memalloc_noio_save();
-
-	/* Get a buffer */
-	buf = sd_zbc_alloc_report_buffer(sdkp, SD_ZBC_REPORT_MAX_ZONES,
-					 &bufsize);
-	if (!buf) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	/* Do a report zone to get max_lba and the same field */
-	ret = sd_zbc_do_report_zones(sdkp, buf, bufsize, 0, false);
+	/* Do a report zone to get max_lba and the size of the first zone */
+	ret = sd_zbc_do_report_zones(sdkp, buf, SD_BUF_SIZE, 0, false);
 	if (ret)
-		goto out_free;
+		return ret;
 
 	if (sdkp->rc_basis == 0) {
 		/* The max_lba field is the capacity of this device */
@@ -375,82 +361,27 @@ static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks)
 		}
 	}
 
-	/*
-	 * Check same field: for any value other than 0, we know that all zones
-	 * have the same size.
-	 */
-	same = buf[4] & 0x0f;
-	if (same > 0) {
-		rec = &buf[64];
-		zone_blocks = get_unaligned_be64(&rec[8]);
-		goto out;
-	}
-
-	/*
-	 * Check the size of all zones: all zones must be of
-	 * equal size, except the last zone which can be smaller
-	 * than other zones.
-	 */
-	do {
-
-		/* Parse REPORT ZONES header */
-		buflen = min_t(size_t, get_unaligned_be32(&buf[0]) + 64,
-			       bufsize);
-		rec = buf + 64;
-
-		/* Parse zone descriptors */
-		while (rec < buf + buflen) {
-			u64 this_zone_blocks = get_unaligned_be64(&rec[8]);
-
-			if (zone_blocks == 0) {
-				zone_blocks = this_zone_blocks;
-			} else if (this_zone_blocks != zone_blocks &&
-				   (block + this_zone_blocks < sdkp->capacity
-				    || this_zone_blocks > zone_blocks)) {
-				zone_blocks = 0;
-				goto out;
-			}
-			block += this_zone_blocks;
-			rec += 64;
-		}
-
-		if (block < sdkp->capacity) {
-			ret = sd_zbc_do_report_zones(sdkp, buf, bufsize, block,
-						     true);
-			if (ret)
-				goto out_free;
-		}
-
-	} while (block < sdkp->capacity);
-
-out:
-	if (!zone_blocks) {
-		if (sdkp->first_scan)
-			sd_printk(KERN_NOTICE, sdkp,
-				  "Devices with non constant zone "
-				  "size are not supported\n");
-		ret = -ENODEV;
-	} else if (!is_power_of_2(zone_blocks)) {
+	/* Parse REPORT ZONES header */
+	rec = buf + 64;
+	zone_blocks = get_unaligned_be64(&rec[8]);
+	if (!zone_blocks || !is_power_of_2(zone_blocks)) {
 		if (sdkp->first_scan)
 			sd_printk(KERN_NOTICE, sdkp,
 				  "Devices with non power of 2 zone "
 				  "size are not supported\n");
-		ret = -ENODEV;
-	} else if (logical_to_sectors(sdkp->device, zone_blocks) > UINT_MAX) {
+		return -ENODEV;
+	}
+
+	if (logical_to_sectors(sdkp->device, zone_blocks) > UINT_MAX) {
 		if (sdkp->first_scan)
 			sd_printk(KERN_NOTICE, sdkp,
 				  "Zone size too large\n");
-		ret = -EFBIG;
-	} else {
-		*zblocks = zone_blocks;
-		ret = 0;
+		return -EFBIG;
 	}
 
-out_free:
-	memalloc_noio_restore(noio_flag);
-	kvfree(buf);
+	*zblocks = zone_blocks;
 
-	return ret;
+	return 0;
 }
 
 int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
@@ -476,7 +407,7 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 	 * Check zone size: only devices with a constant zone size (except
 	 * an eventual last runt zone) that is a power of 2 are supported.
 	 */
-	ret = sd_zbc_check_zones(sdkp, &zone_blocks);
+	ret = sd_zbc_check_zones(sdkp, buf, &zone_blocks);
 	if (ret != 0)
 		goto err;
 
diff --git a/drivers/sh/intc/core.c b/drivers/sh/intc/core.c
index 46f0f322d4d8..8485e812d9b2 100644
--- a/drivers/sh/intc/core.c
+++ b/drivers/sh/intc/core.c
@@ -100,8 +100,8 @@ static void __init intc_register_irq(struct intc_desc *desc,
 		primary = 1;
 
 	if (!data[0] && !data[1])
-		pr_warning("missing unique irq mask for irq %d (vect 0x%04x)\n",
-			   irq, irq2evt(irq));
+		pr_warn("missing unique irq mask for irq %d (vect 0x%04x)\n",
+			irq, irq2evt(irq));
 
 	data[0] = data[0] ? data[0] : intc_get_mask_handle(desc, d, enum_id, 1);
 	data[1] = data[1] ? data[1] : intc_get_prio_handle(desc, d, enum_id, 1);
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index c6b3bdbbdbc9..de7b8382aba9 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -113,9 +113,9 @@ static int __init text_mode(char *str)
 {
 	vgacon_text_mode_force = true;
 
-	pr_warning("You have booted with nomodeset. This means your GPU drivers are DISABLED\n");
-	pr_warning("Any video related functionality will be severely degraded, and you may not even be able to suspend the system properly\n");
-	pr_warning("Unless you actually understand what nomodeset does, you should reboot without enabling it\n");
+	pr_warn("You have booted with nomodeset. This means your GPU drivers are DISABLED\n");
+	pr_warn("Any video related functionality will be severely degraded, and you may not even be able to suspend the system properly\n");
+	pr_warn("Unless you actually understand what nomodeset does, you should reboot without enabling it\n");
 
 	return 1;
 }
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 226fbb995fb0..e05679c478e2 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -772,6 +772,13 @@ static unsigned long shrink_free_pages(struct virtio_balloon *vb,
 	return blocks_freed << VIRTIO_BALLOON_FREE_PAGE_ORDER;
 }
 
+static unsigned long leak_balloon_pages(struct virtio_balloon *vb,
+                                          unsigned long pages_to_free)
+{
+	return leak_balloon(vb, pages_to_free * VIRTIO_BALLOON_PAGES_PER_PAGE) /
+		VIRTIO_BALLOON_PAGES_PER_PAGE;
+}
+
 static unsigned long shrink_balloon_pages(struct virtio_balloon *vb,
 					  unsigned long pages_to_free)
 {
@@ -782,11 +789,10 @@ static unsigned long shrink_balloon_pages(struct virtio_balloon *vb,
 	 * VIRTIO_BALLOON_ARRAY_PFNS_MAX balloon pages, so we call it
 	 * multiple times to deflate pages till reaching pages_to_free.
 	 */
-	while (vb->num_pages && pages_to_free) {
-		pages_freed += leak_balloon(vb, pages_to_free) /
-					VIRTIO_BALLOON_PAGES_PER_PAGE;
-		pages_to_free -= pages_freed;
-	}
+	while (vb->num_pages && pages_freed < pages_to_free)
+		pages_freed += leak_balloon_pages(vb,
+						  pages_to_free - pages_freed);
+
 	update_balloon_size(vb);
 
 	return pages_freed;
@@ -799,7 +805,7 @@ static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker,
 	struct virtio_balloon *vb = container_of(shrinker,
 					struct virtio_balloon, shrinker);
 
-	pages_to_free = sc->nr_to_scan * VIRTIO_BALLOON_PAGES_PER_PAGE;
+	pages_to_free = sc->nr_to_scan;
 
 	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
 		pages_freed = shrink_free_pages(vb, pages_to_free);
@@ -820,7 +826,7 @@ static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker,
 	unsigned long count;
 
 	count = vb->num_pages / VIRTIO_BALLOON_PAGES_PER_PAGE;
-	count += vb->num_free_page_blocks >> VIRTIO_BALLOON_FREE_PAGE_ORDER;
+	count += vb->num_free_page_blocks << VIRTIO_BALLOON_FREE_PAGE_ORDER;
 
 	return count;
 }
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index a8041e451e9e..867c7ebd3f10 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -583,7 +583,7 @@ unmap_release:
 		kfree(desc);
 
 	END_USE(vq);
-	return -EIO;
+	return -ENOMEM;
 }
 
 static bool virtqueue_kick_prepare_split(struct virtqueue *_vq)
@@ -1085,7 +1085,7 @@ unmap_release:
 	kfree(desc);
 
 	END_USE(vq);
-	return -EIO;
+	return -ENOMEM;
 }
 
 static inline int virtqueue_add_packed(struct virtqueue *_vq,
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 79cc75096f42..61212fc7f0c7 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -106,27 +106,27 @@ config XENFS
 	  If in doubt, say yes.
 
 config XEN_COMPAT_XENFS
-       bool "Create compatibility mount point /proc/xen"
-       depends on XENFS
-       default y
-       help
-         The old xenstore userspace tools expect to find "xenbus"
-         under /proc/xen, but "xenbus" is now found at the root of the
-         xenfs filesystem.  Selecting this causes the kernel to create
-         the compatibility mount point /proc/xen if it is running on
-         a xen platform.
-         If in doubt, say yes.
+	bool "Create compatibility mount point /proc/xen"
+	depends on XENFS
+	default y
+	help
+	  The old xenstore userspace tools expect to find "xenbus"
+	  under /proc/xen, but "xenbus" is now found at the root of the
+	  xenfs filesystem.  Selecting this causes the kernel to create
+	  the compatibility mount point /proc/xen if it is running on
+	  a xen platform.
+	  If in doubt, say yes.
 
 config XEN_SYS_HYPERVISOR
-       bool "Create xen entries under /sys/hypervisor"
-       depends on SYSFS
-       select SYS_HYPERVISOR
-       default y
-       help
-         Create entries under /sys/hypervisor describing the Xen
-	 hypervisor environment.  When running native or in another
-	 virtual environment, /sys/hypervisor will still be present,
-	 but will have no xen contents.
+	bool "Create xen entries under /sys/hypervisor"
+	depends on SYSFS
+	select SYS_HYPERVISOR
+	default y
+	help
+	  Create entries under /sys/hypervisor describing the Xen
+	  hypervisor environment.  When running native or in another
+	  virtual environment, /sys/hypervisor will still be present,
+	  but will have no xen contents.
 
 config XEN_XENBUS_FRONTEND
 	tristate
@@ -141,7 +141,8 @@ config XEN_GNTDEV
 
 config XEN_GNTDEV_DMABUF
 	bool "Add support for dma-buf grant access device driver extension"
-	depends on XEN_GNTDEV && XEN_GRANT_DMA_ALLOC && DMA_SHARED_BUFFER
+	depends on XEN_GNTDEV && XEN_GRANT_DMA_ALLOC
+	select DMA_SHARED_BUFFER
 	help
 	  Allows userspace processes and kernel modules to use Xen backed
 	  dma-buf implementation. With this extension grant references to
@@ -270,7 +271,7 @@ config XEN_ACPI_PROCESSOR
 	depends on XEN && XEN_DOM0 && X86 && ACPI_PROCESSOR && CPU_FREQ
 	default m
 	help
-          This ACPI processor uploads Power Management information to the Xen
+	  This ACPI processor uploads Power Management information to the Xen
 	  hypervisor.
 
 	  To do that the driver parses the Power Management data and uploads
@@ -279,19 +280,19 @@ config XEN_ACPI_PROCESSOR
 	  SMM so that other drivers (such as ACPI cpufreq scaling driver) will
 	  not load.
 
-          To compile this driver as a module, choose M here: the module will be
+	  To compile this driver as a module, choose M here: the module will be
 	  called xen_acpi_processor  If you do not know what to choose, select
 	  M here. If the CPUFREQ drivers are built in, select Y here.
 
 config XEN_MCE_LOG
 	bool "Xen platform mcelog"
-	depends on XEN_DOM0 && X86_64 && X86_MCE
+	depends on XEN_DOM0 && X86_MCE
 	help
 	  Allow kernel fetching MCE error from Xen platform and
 	  converting it into Linux mcelog format for mcelog tools
 
 config XEN_HAVE_PVMMU
-       bool
+	bool
 
 config XEN_EFI
 	def_bool y
@@ -308,15 +309,15 @@ config XEN_ACPI
 	depends on X86 && ACPI
 
 config XEN_SYMS
-       bool "Xen symbols"
-       depends on X86 && XEN_DOM0 && XENFS
-       default y if KALLSYMS
-       help
-          Exports hypervisor symbols (along with their types and addresses) via
-          /proc/xen/xensyms file, similar to /proc/kallsyms
+	bool "Xen symbols"
+	depends on X86 && XEN_DOM0 && XENFS
+	default y if KALLSYMS
+	help
+	  Exports hypervisor symbols (along with their types and addresses) via
+	  /proc/xen/xensyms file, similar to /proc/kallsyms
 
 config XEN_HAVE_VPMU
-       bool
+	bool
 
 config XEN_FRONT_PGDIR_SHBUF
 	tristate
diff --git a/drivers/xen/mcelog.c b/drivers/xen/mcelog.c
index b8bf61abb65b..e9ac3b8c4167 100644
--- a/drivers/xen/mcelog.c
+++ b/drivers/xen/mcelog.c
@@ -222,7 +222,7 @@ static int convert_log(struct mc_info *mi)
 	struct mcinfo_global *mc_global;
 	struct mcinfo_bank *mc_bank;
 	struct xen_mce m;
-	uint32_t i;
+	unsigned int i, j;
 
 	mic = NULL;
 	x86_mcinfo_lookup(&mic, mi, MC_TYPE_GLOBAL);
@@ -248,7 +248,17 @@ static int convert_log(struct mc_info *mi)
 	m.socketid = g_physinfo[i].mc_chipid;
 	m.cpu = m.extcpu = g_physinfo[i].mc_cpunr;
 	m.cpuvendor = (__u8)g_physinfo[i].mc_vendor;
-	m.mcgcap = g_physinfo[i].mc_msrvalues[__MC_MSR_MCGCAP].value;
+	for (j = 0; j < g_physinfo[i].mc_nmsrvals; ++j)
+		switch (g_physinfo[i].mc_msrvalues[j].reg) {
+		case MSR_IA32_MCG_CAP:
+			m.mcgcap = g_physinfo[i].mc_msrvalues[j].value;
+			break;
+
+		case MSR_PPIN:
+		case MSR_AMD_PPIN:
+			m.ppin = g_physinfo[i].mc_msrvalues[j].value;
+			break;
+		}
 
 	mic = NULL;
 	x86_mcinfo_lookup(&mic, mi, MC_TYPE_BANK);
diff --git a/fs/Kconfig b/fs/Kconfig
index 2501e6f1f965..7b623e9fc1b0 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -322,4 +322,7 @@ source "fs/nls/Kconfig"
 source "fs/dlm/Kconfig"
 source "fs/unicode/Kconfig"
 
+config IO_WQ
+	bool
+
 endmenu
diff --git a/fs/Makefile b/fs/Makefile
index 14231b4cf383..1148c555c4d3 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -32,6 +32,7 @@ obj-$(CONFIG_EVENTFD)		+= eventfd.o
 obj-$(CONFIG_USERFAULTFD)	+= userfaultfd.o
 obj-$(CONFIG_AIO)               += aio.o
 obj-$(CONFIG_IO_URING)		+= io_uring.o
+obj-$(CONFIG_IO_WQ)		+= io-wq.o
 obj-$(CONFIG_FS_DAX)		+= dax.o
 obj-$(CONFIG_FS_ENCRYPTION)	+= crypto/
 obj-$(CONFIG_FS_VERITY)		+= verity/
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index a92eb6ae2ae2..a755bef7c4c7 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -43,8 +43,8 @@ struct affs_ext_key {
  */
 struct affs_inode_info {
 	atomic_t i_opencnt;
-	struct semaphore i_link_lock;		/* Protects internal inode access. */
-	struct semaphore i_ext_lock;		/* Protects internal inode access. */
+	struct mutex i_link_lock;		/* Protects internal inode access. */
+	struct mutex i_ext_lock;		/* Protects internal inode access. */
 #define i_hash_lock i_ext_lock
 	u32	 i_blkcnt;			/* block count */
 	u32	 i_extcnt;			/* extended block count */
@@ -293,30 +293,30 @@ affs_adjust_bitmapchecksum(struct buffer_head *bh, u32 val)
 static inline void
 affs_lock_link(struct inode *inode)
 {
-	down(&AFFS_I(inode)->i_link_lock);
+	mutex_lock(&AFFS_I(inode)->i_link_lock);
 }
 static inline void
 affs_unlock_link(struct inode *inode)
 {
-	up(&AFFS_I(inode)->i_link_lock);
+	mutex_unlock(&AFFS_I(inode)->i_link_lock);
 }
 static inline void
 affs_lock_dir(struct inode *inode)
 {
-	down(&AFFS_I(inode)->i_hash_lock);
+	mutex_lock_nested(&AFFS_I(inode)->i_hash_lock, SINGLE_DEPTH_NESTING);
 }
 static inline void
 affs_unlock_dir(struct inode *inode)
 {
-	up(&AFFS_I(inode)->i_hash_lock);
+	mutex_unlock(&AFFS_I(inode)->i_hash_lock);
 }
 static inline void
 affs_lock_ext(struct inode *inode)
 {
-	down(&AFFS_I(inode)->i_ext_lock);
+	mutex_lock(&AFFS_I(inode)->i_ext_lock);
 }
 static inline void
 affs_unlock_ext(struct inode *inode)
 {
-	up(&AFFS_I(inode)->i_ext_lock);
+	mutex_unlock(&AFFS_I(inode)->i_ext_lock);
 }
diff --git a/fs/affs/super.c b/fs/affs/super.c
index cc463ae47c12..47107c6712a6 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -121,8 +121,8 @@ static void init_once(void *foo)
 {
 	struct affs_inode_info *ei = (struct affs_inode_info *) foo;
 
-	sema_init(&ei->i_link_lock, 1);
-	sema_init(&ei->i_ext_lock, 1);
+	mutex_init(&ei->i_link_lock);
+	mutex_init(&ei->i_ext_lock);
 	inode_init_once(&ei->vfs_inode);
 }
 
@@ -561,14 +561,9 @@ affs_remount(struct super_block *sb, int *flags, char *data)
 	int			 root_block;
 	unsigned long		 mount_flags;
 	int			 res = 0;
-	char			*new_opts;
 	char			 volume[32];
 	char			*prefix = NULL;
 
-	new_opts = kstrdup(data, GFP_KERNEL);
-	if (data && !new_opts)
-		return -ENOMEM;
-
 	pr_debug("%s(flags=0x%x,opts=\"%s\")\n", __func__, *flags, data);
 
 	sync_filesystem(sb);
@@ -579,7 +574,6 @@ affs_remount(struct super_block *sb, int *flags, char *data)
 			   &blocksize, &prefix, volume,
 			   &mount_flags)) {
 		kfree(prefix);
-		kfree(new_opts);
 		return -EINVAL;
 	}
 
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index d5e5a6ddc847..0f2a94ba73cb 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -346,8 +346,8 @@ again:
 		if (ret < 0) {
 			trace_afs_flock_ev(vnode, NULL, afs_flock_extend_fail,
 					   ret);
-			pr_warning("AFS: Failed to extend lock on {%llx:%llx} error %d\n",
-				   vnode->fid.vid, vnode->fid.vnode, ret);
+			pr_warn("AFS: Failed to extend lock on {%llx:%llx} error %d\n",
+				vnode->fid.vid, vnode->fid.vnode, ret);
 		}
 
 		spin_lock(&vnode->lock);
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 46d2d7cb461d..281470fe1183 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -34,8 +34,7 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren
 {
 	static unsigned long once_only;
 
-	pr_warn("kAFS: AFS vnode with undefined type %u\n",
-		vnode->status.type);
+	pr_warn("kAFS: AFS vnode with undefined type %u\n", vnode->status.type);
 	pr_warn("kAFS: A=%d m=%o s=%llx v=%llx\n",
 		vnode->status.abort_code,
 		vnode->status.mode,
@@ -175,11 +174,11 @@ static void afs_apply_status(struct afs_fs_cursor *fc,
 	BUG_ON(test_bit(AFS_VNODE_UNSET, &vnode->flags));
 
 	if (status->type != vnode->status.type) {
-		pr_warning("Vnode %llx:%llx:%x changed type %u to %u\n",
-			   vnode->fid.vid,
-			   vnode->fid.vnode,
-			   vnode->fid.unique,
-			   status->type, vnode->status.type);
+		pr_warn("Vnode %llx:%llx:%x changed type %u to %u\n",
+			vnode->fid.vid,
+			vnode->fid.vnode,
+			vnode->fid.unique,
+			status->type, vnode->status.type);
 		afs_protocol_error(NULL, -EBADMSG, afs_eproto_bad_status);
 		return;
 	}
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 3ee7abf4b2d0..9ac035c17dc4 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -152,8 +152,8 @@ static void yfs_check_req(struct afs_call *call, __be32 *bp)
 		pr_err("kAFS: %s: Request buffer overflow (%zu>%u)\n",
 		       call->type->name, len, call->request_size);
 	else if (len < call->request_size)
-		pr_warning("kAFS: %s: Request buffer underflow (%zu<%u)\n",
-			   call->type->name, len, call->request_size);
+		pr_warn("kAFS: %s: Request buffer underflow (%zu<%u)\n",
+			call->type->name, len, call->request_size);
 }
 
 /*
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9c073dbdc1b0..ee63c2732fa2 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1403,11 +1403,7 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty)
 		       "resized disk %s\n",
 		       bdev->bd_disk ? bdev->bd_disk->disk_name : "");
 	}
-
-	if (!bdev->bd_disk)
-		return;
-	if (disk_part_scan_enabled(bdev->bd_disk))
-		bdev->bd_invalidated = 1;
+	bdev->bd_invalidated = 1;
 }
 
 /**
@@ -1420,8 +1416,8 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty)
  * and adjusts it if it differs. When shrinking the bdev size, its all caches
  * are freed.
  */
-void check_disk_size_change(struct gendisk *disk, struct block_device *bdev,
-		bool verbose)
+static void check_disk_size_change(struct gendisk *disk,
+		struct block_device *bdev, bool verbose)
 {
 	loff_t disk_size, bdev_size;
 
@@ -1437,6 +1433,7 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev,
 		if (bdev_size > disk_size)
 			flush_disk(bdev, false);
 	}
+	bdev->bd_invalidated = 0;
 }
 
 /**
@@ -1466,7 +1463,6 @@ int revalidate_disk(struct gendisk *disk)
 
 		mutex_lock(&bdev->bd_mutex);
 		check_disk_size_change(disk, bdev, ret == 0);
-		bdev->bd_invalidated = 0;
 		mutex_unlock(&bdev->bd_mutex);
 		bdput(bdev);
 	}
@@ -1512,6 +1508,45 @@ EXPORT_SYMBOL(bd_set_size);
 
 static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
+int bdev_disk_changed(struct block_device *bdev, bool invalidate)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	int ret;
+
+	lockdep_assert_held(&bdev->bd_mutex);
+
+rescan:
+	ret = blk_drop_partitions(disk, bdev);
+	if (ret)
+		return ret;
+
+	if (invalidate)
+		set_capacity(disk, 0);
+	else if (disk->fops->revalidate_disk)
+		disk->fops->revalidate_disk(disk);
+
+	check_disk_size_change(disk, bdev, !invalidate);
+
+	if (get_capacity(disk)) {
+		ret = blk_add_partitions(disk, bdev);
+		if (ret == -EAGAIN)
+			goto rescan;
+	} else {
+		/*
+		 * Tell userspace that the media / partition table may have
+		 * changed.
+		 */
+		kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
+	}
+
+	return ret;
+}
+/*
+ * Only exported for for loop and dasd for historic reasons.  Don't use in new
+ * code!
+ */
+EXPORT_SYMBOL_GPL(bdev_disk_changed);
+
 /*
  * bd_mutex locking:
  *
@@ -1594,12 +1629,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			 * The latter is necessary to prevent ghost
 			 * partitions on a removed medium.
 			 */
-			if (bdev->bd_invalidated) {
-				if (!ret)
-					rescan_partitions(disk, bdev);
-				else if (ret == -ENOMEDIUM)
-					invalidate_partitions(disk, bdev);
-			}
+			if (bdev->bd_invalidated &&
+			    (!ret || ret == -ENOMEDIUM))
+				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 
 			if (ret)
 				goto out_clear;
@@ -1632,12 +1664,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			if (bdev->bd_disk->fops->open)
 				ret = bdev->bd_disk->fops->open(bdev, mode);
 			/* the same as first opener case, read comment there */
-			if (bdev->bd_invalidated) {
-				if (!ret)
-					rescan_partitions(bdev->bd_disk, bdev);
-				else if (ret == -ENOMEDIUM)
-					invalidate_partitions(bdev->bd_disk, bdev);
-			}
+			if (bdev->bd_invalidated &&
+			    (!ret || ret == -ENOMEDIUM))
+				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 			if (ret)
 				goto out_unlock_bdev;
 		}
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index 38651fae7f21..75b6d10c9845 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -5,6 +5,8 @@ config BTRFS_FS
 	select CRYPTO
 	select CRYPTO_CRC32C
 	select LIBCRC32C
+	select CRYPTO_XXHASH
+	select CRYPTO_SHA256
 	select ZLIB_INFLATE
 	select ZLIB_DEFLATE
 	select LZO_COMPRESS
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 2e9e13ffbd08..1d32a07bb2d1 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -53,24 +53,12 @@ struct btrfs_workqueue {
 	struct __btrfs_workqueue *high;
 };
 
-static void normal_work_helper(struct btrfs_work *work);
-
-#define BTRFS_WORK_HELPER(name)					\
-noinline_for_stack void btrfs_##name(struct work_struct *arg)		\
-{									\
-	struct btrfs_work *work = container_of(arg, struct btrfs_work,	\
-					       normal_work);		\
-	normal_work_helper(work);					\
-}
-
-struct btrfs_fs_info *
-btrfs_workqueue_owner(const struct __btrfs_workqueue *wq)
+struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq)
 {
 	return wq->fs_info;
 }
 
-struct btrfs_fs_info *
-btrfs_work_owner(const struct btrfs_work *work)
+struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work)
 {
 	return work->wq->fs_info;
 }
@@ -89,29 +77,6 @@ bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq)
 	return atomic_read(&wq->normal->pending) > wq->normal->thresh * 2;
 }
 
-BTRFS_WORK_HELPER(worker_helper);
-BTRFS_WORK_HELPER(delalloc_helper);
-BTRFS_WORK_HELPER(flush_delalloc_helper);
-BTRFS_WORK_HELPER(cache_helper);
-BTRFS_WORK_HELPER(submit_helper);
-BTRFS_WORK_HELPER(fixup_helper);
-BTRFS_WORK_HELPER(endio_helper);
-BTRFS_WORK_HELPER(endio_meta_helper);
-BTRFS_WORK_HELPER(endio_meta_write_helper);
-BTRFS_WORK_HELPER(endio_raid56_helper);
-BTRFS_WORK_HELPER(endio_repair_helper);
-BTRFS_WORK_HELPER(rmw_helper);
-BTRFS_WORK_HELPER(endio_write_helper);
-BTRFS_WORK_HELPER(freespace_write_helper);
-BTRFS_WORK_HELPER(delayed_meta_helper);
-BTRFS_WORK_HELPER(readahead_helper);
-BTRFS_WORK_HELPER(qgroup_rescan_helper);
-BTRFS_WORK_HELPER(extent_refs_helper);
-BTRFS_WORK_HELPER(scrub_helper);
-BTRFS_WORK_HELPER(scrubwrc_helper);
-BTRFS_WORK_HELPER(scrubnc_helper);
-BTRFS_WORK_HELPER(scrubparity_helper);
-
 static struct __btrfs_workqueue *
 __btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name,
 			unsigned int flags, int limit_active, int thresh)
@@ -252,16 +217,16 @@ out:
 	}
 }
 
-static void run_ordered_work(struct __btrfs_workqueue *wq)
+static void run_ordered_work(struct __btrfs_workqueue *wq,
+			     struct btrfs_work *self)
 {
 	struct list_head *list = &wq->ordered_list;
 	struct btrfs_work *work;
 	spinlock_t *lock = &wq->list_lock;
 	unsigned long flags;
+	bool free_self = false;
 
 	while (1) {
-		void *wtag;
-
 		spin_lock_irqsave(lock, flags);
 		if (list_empty(list))
 			break;
@@ -287,22 +252,53 @@ static void run_ordered_work(struct __btrfs_workqueue *wq)
 		list_del(&work->ordered_list);
 		spin_unlock_irqrestore(lock, flags);
 
-		/*
-		 * We don't want to call the ordered free functions with the
-		 * lock held though. Save the work as tag for the trace event,
-		 * because the callback could free the structure.
-		 */
-		wtag = work;
-		work->ordered_free(work);
-		trace_btrfs_all_work_done(wq->fs_info, wtag);
+		if (work == self) {
+			/*
+			 * This is the work item that the worker is currently
+			 * executing.
+			 *
+			 * The kernel workqueue code guarantees non-reentrancy
+			 * of work items. I.e., if a work item with the same
+			 * address and work function is queued twice, the second
+			 * execution is blocked until the first one finishes. A
+			 * work item may be freed and recycled with the same
+			 * work function; the workqueue code assumes that the
+			 * original work item cannot depend on the recycled work
+			 * item in that case (see find_worker_executing_work()).
+			 *
+			 * Note that different types of Btrfs work can depend on
+			 * each other, and one type of work on one Btrfs
+			 * filesystem may even depend on the same type of work
+			 * on another Btrfs filesystem via, e.g., a loop device.
+			 * Therefore, we must not allow the current work item to
+			 * be recycled until we are really done, otherwise we
+			 * break the above assumption and can deadlock.
+			 */
+			free_self = true;
+		} else {
+			/*
+			 * We don't want to call the ordered free functions with
+			 * the lock held.
+			 */
+			work->ordered_free(work);
+			/* NB: work must not be dereferenced past this point. */
+			trace_btrfs_all_work_done(wq->fs_info, work);
+		}
 	}
 	spin_unlock_irqrestore(lock, flags);
+
+	if (free_self) {
+		self->ordered_free(self);
+		/* NB: self must not be dereferenced past this point. */
+		trace_btrfs_all_work_done(wq->fs_info, self);
+	}
 }
 
-static void normal_work_helper(struct btrfs_work *work)
+static void btrfs_work_helper(struct work_struct *normal_work)
 {
+	struct btrfs_work *work = container_of(normal_work, struct btrfs_work,
+					       normal_work);
 	struct __btrfs_workqueue *wq;
-	void *wtag;
 	int need_order = 0;
 
 	/*
@@ -316,29 +312,26 @@ static void normal_work_helper(struct btrfs_work *work)
 	if (work->ordered_func)
 		need_order = 1;
 	wq = work->wq;
-	/* Safe for tracepoints in case work gets freed by the callback */
-	wtag = work;
 
 	trace_btrfs_work_sched(work);
 	thresh_exec_hook(wq);
 	work->func(work);
 	if (need_order) {
 		set_bit(WORK_DONE_BIT, &work->flags);
-		run_ordered_work(wq);
+		run_ordered_work(wq, work);
+	} else {
+		/* NB: work must not be dereferenced past this point. */
+		trace_btrfs_all_work_done(wq->fs_info, work);
 	}
-	if (!need_order)
-		trace_btrfs_all_work_done(wq->fs_info, wtag);
 }
 
-void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func,
-		     btrfs_func_t func,
-		     btrfs_func_t ordered_func,
-		     btrfs_func_t ordered_free)
+void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func,
+		     btrfs_func_t ordered_func, btrfs_func_t ordered_free)
 {
 	work->func = func;
 	work->ordered_func = ordered_func;
 	work->ordered_free = ordered_free;
-	INIT_WORK(&work->normal_work, uniq_func);
+	INIT_WORK(&work->normal_work, btrfs_work_helper);
 	INIT_LIST_HEAD(&work->ordered_list);
 	work->flags = 0;
 }
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 7861c9feba5f..a4434301d84d 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -29,49 +29,20 @@ struct btrfs_work {
 	unsigned long flags;
 };
 
-#define BTRFS_WORK_HELPER_PROTO(name)					\
-void btrfs_##name(struct work_struct *arg)
-
-BTRFS_WORK_HELPER_PROTO(worker_helper);
-BTRFS_WORK_HELPER_PROTO(delalloc_helper);
-BTRFS_WORK_HELPER_PROTO(flush_delalloc_helper);
-BTRFS_WORK_HELPER_PROTO(cache_helper);
-BTRFS_WORK_HELPER_PROTO(submit_helper);
-BTRFS_WORK_HELPER_PROTO(fixup_helper);
-BTRFS_WORK_HELPER_PROTO(endio_helper);
-BTRFS_WORK_HELPER_PROTO(endio_meta_helper);
-BTRFS_WORK_HELPER_PROTO(endio_meta_write_helper);
-BTRFS_WORK_HELPER_PROTO(endio_raid56_helper);
-BTRFS_WORK_HELPER_PROTO(endio_repair_helper);
-BTRFS_WORK_HELPER_PROTO(rmw_helper);
-BTRFS_WORK_HELPER_PROTO(endio_write_helper);
-BTRFS_WORK_HELPER_PROTO(freespace_write_helper);
-BTRFS_WORK_HELPER_PROTO(delayed_meta_helper);
-BTRFS_WORK_HELPER_PROTO(readahead_helper);
-BTRFS_WORK_HELPER_PROTO(qgroup_rescan_helper);
-BTRFS_WORK_HELPER_PROTO(extent_refs_helper);
-BTRFS_WORK_HELPER_PROTO(scrub_helper);
-BTRFS_WORK_HELPER_PROTO(scrubwrc_helper);
-BTRFS_WORK_HELPER_PROTO(scrubnc_helper);
-BTRFS_WORK_HELPER_PROTO(scrubparity_helper);
-
-
 struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info,
 					      const char *name,
 					      unsigned int flags,
 					      int limit_active,
 					      int thresh);
-void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t helper,
-		     btrfs_func_t func,
-		     btrfs_func_t ordered_func,
-		     btrfs_func_t ordered_free);
+void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func,
+		     btrfs_func_t ordered_func, btrfs_func_t ordered_free);
 void btrfs_queue_work(struct btrfs_workqueue *wq,
 		      struct btrfs_work *work);
 void btrfs_destroy_workqueue(struct btrfs_workqueue *wq);
 void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max);
 void btrfs_set_work_high_priority(struct btrfs_work *work);
-struct btrfs_fs_info *btrfs_work_owner(const struct btrfs_work *work);
-struct btrfs_fs_info *btrfs_workqueue_owner(const struct __btrfs_workqueue *wq);
+struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work);
+struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq);
 bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq);
 
 #endif
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 670700cb1110..6934a5b8708f 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -120,12 +120,12 @@ u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags)
 	return get_alloc_profile(fs_info, orig_flags);
 }
 
-void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
+void btrfs_get_block_group(struct btrfs_block_group *cache)
 {
 	atomic_inc(&cache->count);
 }
 
-void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
+void btrfs_put_block_group(struct btrfs_block_group *cache)
 {
 	if (atomic_dec_and_test(&cache->count)) {
 		WARN_ON(cache->pinned > 0);
@@ -149,22 +149,21 @@ void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
  * This adds the block group to the fs_info rb tree for the block group cache
  */
 static int btrfs_add_block_group_cache(struct btrfs_fs_info *info,
-				struct btrfs_block_group_cache *block_group)
+				       struct btrfs_block_group *block_group)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 
 	spin_lock(&info->block_group_cache_lock);
 	p = &info->block_group_cache_tree.rb_node;
 
 	while (*p) {
 		parent = *p;
-		cache = rb_entry(parent, struct btrfs_block_group_cache,
-				 cache_node);
-		if (block_group->key.objectid < cache->key.objectid) {
+		cache = rb_entry(parent, struct btrfs_block_group, cache_node);
+		if (block_group->start < cache->start) {
 			p = &(*p)->rb_left;
-		} else if (block_group->key.objectid > cache->key.objectid) {
+		} else if (block_group->start > cache->start) {
 			p = &(*p)->rb_right;
 		} else {
 			spin_unlock(&info->block_group_cache_lock);
@@ -176,8 +175,8 @@ static int btrfs_add_block_group_cache(struct btrfs_fs_info *info,
 	rb_insert_color(&block_group->cache_node,
 			&info->block_group_cache_tree);
 
-	if (info->first_logical_byte > block_group->key.objectid)
-		info->first_logical_byte = block_group->key.objectid;
+	if (info->first_logical_byte > block_group->start)
+		info->first_logical_byte = block_group->start;
 
 	spin_unlock(&info->block_group_cache_lock);
 
@@ -188,10 +187,10 @@ static int btrfs_add_block_group_cache(struct btrfs_fs_info *info,
  * This will return the block group at or after bytenr if contains is 0, else
  * it will return the block group that contains the bytenr
  */
-static struct btrfs_block_group_cache *block_group_cache_tree_search(
+static struct btrfs_block_group *block_group_cache_tree_search(
 		struct btrfs_fs_info *info, u64 bytenr, int contains)
 {
-	struct btrfs_block_group_cache *cache, *ret = NULL;
+	struct btrfs_block_group *cache, *ret = NULL;
 	struct rb_node *n;
 	u64 end, start;
 
@@ -199,13 +198,12 @@ static struct btrfs_block_group_cache *block_group_cache_tree_search(
 	n = info->block_group_cache_tree.rb_node;
 
 	while (n) {
-		cache = rb_entry(n, struct btrfs_block_group_cache,
-				 cache_node);
-		end = cache->key.objectid + cache->key.offset - 1;
-		start = cache->key.objectid;
+		cache = rb_entry(n, struct btrfs_block_group, cache_node);
+		end = cache->start + cache->length - 1;
+		start = cache->start;
 
 		if (bytenr < start) {
-			if (!contains && (!ret || start < ret->key.objectid))
+			if (!contains && (!ret || start < ret->start))
 				ret = cache;
 			n = n->rb_left;
 		} else if (bytenr > start) {
@@ -221,8 +219,8 @@ static struct btrfs_block_group_cache *block_group_cache_tree_search(
 	}
 	if (ret) {
 		btrfs_get_block_group(ret);
-		if (bytenr == 0 && info->first_logical_byte > ret->key.objectid)
-			info->first_logical_byte = ret->key.objectid;
+		if (bytenr == 0 && info->first_logical_byte > ret->start)
+			info->first_logical_byte = ret->start;
 	}
 	spin_unlock(&info->block_group_cache_lock);
 
@@ -232,7 +230,7 @@ static struct btrfs_block_group_cache *block_group_cache_tree_search(
 /*
  * Return the block group that starts at or after bytenr
  */
-struct btrfs_block_group_cache *btrfs_lookup_first_block_group(
+struct btrfs_block_group *btrfs_lookup_first_block_group(
 		struct btrfs_fs_info *info, u64 bytenr)
 {
 	return block_group_cache_tree_search(info, bytenr, 0);
@@ -241,14 +239,14 @@ struct btrfs_block_group_cache *btrfs_lookup_first_block_group(
 /*
  * Return the block group that contains the given bytenr
  */
-struct btrfs_block_group_cache *btrfs_lookup_block_group(
+struct btrfs_block_group *btrfs_lookup_block_group(
 		struct btrfs_fs_info *info, u64 bytenr)
 {
 	return block_group_cache_tree_search(info, bytenr, 1);
 }
 
-struct btrfs_block_group_cache *btrfs_next_block_group(
-		struct btrfs_block_group_cache *cache)
+struct btrfs_block_group *btrfs_next_block_group(
+		struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct rb_node *node;
@@ -257,7 +255,7 @@ struct btrfs_block_group_cache *btrfs_next_block_group(
 
 	/* If our block group was removed, we need a full search. */
 	if (RB_EMPTY_NODE(&cache->cache_node)) {
-		const u64 next_bytenr = cache->key.objectid + cache->key.offset;
+		const u64 next_bytenr = cache->start + cache->length;
 
 		spin_unlock(&fs_info->block_group_cache_lock);
 		btrfs_put_block_group(cache);
@@ -266,8 +264,7 @@ struct btrfs_block_group_cache *btrfs_next_block_group(
 	node = rb_next(&cache->cache_node);
 	btrfs_put_block_group(cache);
 	if (node) {
-		cache = rb_entry(node, struct btrfs_block_group_cache,
-				 cache_node);
+		cache = rb_entry(node, struct btrfs_block_group, cache_node);
 		btrfs_get_block_group(cache);
 	} else
 		cache = NULL;
@@ -277,7 +274,7 @@ struct btrfs_block_group_cache *btrfs_next_block_group(
 
 bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
 {
-	struct btrfs_block_group_cache *bg;
+	struct btrfs_block_group *bg;
 	bool ret = true;
 
 	bg = btrfs_lookup_block_group(fs_info, bytenr);
@@ -300,7 +297,7 @@ bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
 
 void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
 {
-	struct btrfs_block_group_cache *bg;
+	struct btrfs_block_group *bg;
 
 	bg = btrfs_lookup_block_group(fs_info, bytenr);
 	ASSERT(bg);
@@ -314,7 +311,7 @@ void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
 	btrfs_put_block_group(bg);
 }
 
-void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg)
+void btrfs_wait_nocow_writers(struct btrfs_block_group *bg)
 {
 	wait_var_event(&bg->nocow_writers, !atomic_read(&bg->nocow_writers));
 }
@@ -322,7 +319,7 @@ void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg)
 void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
 					const u64 start)
 {
-	struct btrfs_block_group_cache *bg;
+	struct btrfs_block_group *bg;
 
 	bg = btrfs_lookup_block_group(fs_info, start);
 	ASSERT(bg);
@@ -331,7 +328,7 @@ void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
 	btrfs_put_block_group(bg);
 }
 
-void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg)
+void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg)
 {
 	struct btrfs_space_info *space_info = bg->space_info;
 
@@ -357,7 +354,7 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg)
 }
 
 struct btrfs_caching_control *btrfs_get_caching_control(
-		struct btrfs_block_group_cache *cache)
+		struct btrfs_block_group *cache)
 {
 	struct btrfs_caching_control *ctl;
 
@@ -392,7 +389,7 @@ void btrfs_put_caching_control(struct btrfs_caching_control *ctl)
  * Callers of this must check if cache->cached == BTRFS_CACHE_ERROR before using
  * any of the information in this block group.
  */
-void btrfs_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache,
+void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
 					   u64 num_bytes)
 {
 	struct btrfs_caching_control *caching_ctl;
@@ -401,13 +398,13 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache
 	if (!caching_ctl)
 		return;
 
-	wait_event(caching_ctl->wait, btrfs_block_group_cache_done(cache) ||
+	wait_event(caching_ctl->wait, btrfs_block_group_done(cache) ||
 		   (cache->free_space_ctl->free_space >= num_bytes));
 
 	btrfs_put_caching_control(caching_ctl);
 }
 
-int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
+int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache)
 {
 	struct btrfs_caching_control *caching_ctl;
 	int ret = 0;
@@ -416,7 +413,7 @@ int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
 	if (!caching_ctl)
 		return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0;
 
-	wait_event(caching_ctl->wait, btrfs_block_group_cache_done(cache));
+	wait_event(caching_ctl->wait, btrfs_block_group_done(cache));
 	if (cache->cached == BTRFS_CACHE_ERROR)
 		ret = -EIO;
 	btrfs_put_caching_control(caching_ctl);
@@ -424,11 +421,11 @@ int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
 }
 
 #ifdef CONFIG_BTRFS_DEBUG
-static void fragment_free_space(struct btrfs_block_group_cache *block_group)
+static void fragment_free_space(struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
-	u64 start = block_group->key.objectid;
-	u64 len = block_group->key.offset;
+	u64 start = block_group->start;
+	u64 len = block_group->length;
 	u64 chunk = block_group->flags & BTRFS_BLOCK_GROUP_METADATA ?
 		fs_info->nodesize : fs_info->sectorsize;
 	u64 step = chunk << 1;
@@ -450,8 +447,7 @@ static void fragment_free_space(struct btrfs_block_group_cache *block_group)
  * used yet since their free space will be released as soon as the transaction
  * commits.
  */
-u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
-		       u64 start, u64 end)
+u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end)
 {
 	struct btrfs_fs_info *info = block_group->fs_info;
 	u64 extent_start, extent_end, size, total_added = 0;
@@ -491,7 +487,7 @@ u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
 
 static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
 {
-	struct btrfs_block_group_cache *block_group = caching_ctl->block_group;
+	struct btrfs_block_group *block_group = caching_ctl->block_group;
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	struct btrfs_root *extent_root = fs_info->extent_root;
 	struct btrfs_path *path;
@@ -507,7 +503,7 @@ static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
 	if (!path)
 		return -ENOMEM;
 
-	last = max_t(u64, block_group->key.objectid, BTRFS_SUPER_INFO_OFFSET);
+	last = max_t(u64, block_group->start, BTRFS_SUPER_INFO_OFFSET);
 
 #ifdef CONFIG_BTRFS_DEBUG
 	/*
@@ -587,13 +583,12 @@ next:
 			goto next;
 		}
 
-		if (key.objectid < block_group->key.objectid) {
+		if (key.objectid < block_group->start) {
 			path->slots[0]++;
 			continue;
 		}
 
-		if (key.objectid >= block_group->key.objectid +
-		    block_group->key.offset)
+		if (key.objectid >= block_group->start + block_group->length)
 			break;
 
 		if (key.type == BTRFS_EXTENT_ITEM_KEY ||
@@ -617,8 +612,7 @@ next:
 	ret = 0;
 
 	total_found += add_new_free_space(block_group, last,
-					  block_group->key.objectid +
-					  block_group->key.offset);
+				block_group->start + block_group->length);
 	caching_ctl->progress = (u64)-1;
 
 out:
@@ -628,7 +622,7 @@ out:
 
 static noinline void caching_thread(struct btrfs_work *work)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_fs_info *fs_info;
 	struct btrfs_caching_control *caching_ctl;
 	int ret;
@@ -656,8 +650,7 @@ static noinline void caching_thread(struct btrfs_work *work)
 
 		spin_lock(&block_group->space_info->lock);
 		spin_lock(&block_group->lock);
-		bytes_used = block_group->key.offset -
-			btrfs_block_group_used(&block_group->item);
+		bytes_used = block_group->length - block_group->used;
 		block_group->space_info->bytes_used += bytes_used >> 1;
 		spin_unlock(&block_group->lock);
 		spin_unlock(&block_group->space_info->lock);
@@ -677,8 +670,7 @@ static noinline void caching_thread(struct btrfs_work *work)
 	btrfs_put_block_group(block_group);
 }
 
-int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
-			    int load_cache_only)
+int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only)
 {
 	DEFINE_WAIT(wait);
 	struct btrfs_fs_info *fs_info = cache->fs_info;
@@ -693,10 +685,9 @@ int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
 	mutex_init(&caching_ctl->mutex);
 	init_waitqueue_head(&caching_ctl->wait);
 	caching_ctl->block_group = cache;
-	caching_ctl->progress = cache->key.objectid;
+	caching_ctl->progress = cache->start;
 	refcount_set(&caching_ctl->count, 1);
-	btrfs_init_work(&caching_ctl->work, btrfs_cache_helper,
-			caching_thread, NULL, NULL);
+	btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL);
 
 	spin_lock(&cache->lock);
 	/*
@@ -763,8 +754,7 @@ int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
 
 			spin_lock(&cache->space_info->lock);
 			spin_lock(&cache->lock);
-			bytes_used = cache->key.offset -
-				btrfs_block_group_used(&cache->item);
+			bytes_used = cache->length - cache->used;
 			cache->space_info->bytes_used += bytes_used >> 1;
 			spin_unlock(&cache->lock);
 			spin_unlock(&cache->space_info->lock);
@@ -833,27 +823,36 @@ static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
  *
  * - RAID56 - in case there's neither RAID5 nor RAID6 profile block group
  *            in the whole filesystem
+ *
+ * - RAID1C34 - same as above for RAID1C3 and RAID1C4 block groups
  */
 static void clear_incompat_bg_bits(struct btrfs_fs_info *fs_info, u64 flags)
 {
-	if (flags & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+	bool found_raid56 = false;
+	bool found_raid1c34 = false;
+
+	if ((flags & BTRFS_BLOCK_GROUP_RAID56_MASK) ||
+	    (flags & BTRFS_BLOCK_GROUP_RAID1C3) ||
+	    (flags & BTRFS_BLOCK_GROUP_RAID1C4)) {
 		struct list_head *head = &fs_info->space_info;
 		struct btrfs_space_info *sinfo;
 
 		list_for_each_entry_rcu(sinfo, head, list) {
-			bool found = false;
-
 			down_read(&sinfo->groups_sem);
 			if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID5]))
-				found = true;
+				found_raid56 = true;
 			if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID6]))
-				found = true;
+				found_raid56 = true;
+			if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID1C3]))
+				found_raid1c34 = true;
+			if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID1C4]))
+				found_raid1c34 = true;
 			up_read(&sinfo->groups_sem);
-
-			if (found)
-				return;
 		}
-		btrfs_clear_fs_incompat(fs_info, RAID56);
+		if (found_raid56)
+			btrfs_clear_fs_incompat(fs_info, RAID56);
+		if (found_raid1c34)
+			btrfs_clear_fs_incompat(fs_info, RAID1C34);
 	}
 }
 
@@ -863,7 +862,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_path *path;
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_free_cluster *cluster;
 	struct btrfs_root *tree_root = fs_info->tree_root;
 	struct btrfs_key key;
@@ -886,10 +885,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 * remove it.
 	 */
 	btrfs_free_excluded_extents(block_group);
-	btrfs_free_ref_tree_range(fs_info, block_group->key.objectid,
-				  block_group->key.offset);
+	btrfs_free_ref_tree_range(fs_info, block_group->start,
+				  block_group->length);
 
-	memcpy(&key, &block_group->key, sizeof(key));
 	index = btrfs_bg_flags_to_raid_index(block_group->flags);
 	factor = btrfs_bg_type_to_factor(block_group->flags);
 
@@ -967,8 +965,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	}
 
 	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
-	key.offset = block_group->key.objectid;
 	key.type = 0;
+	key.offset = block_group->start;
 
 	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
 	if (ret < 0)
@@ -987,7 +985,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		 &fs_info->block_group_cache_tree);
 	RB_CLEAR_NODE(&block_group->cache_node);
 
-	if (fs_info->first_logical_byte == block_group->key.objectid)
+	if (fs_info->first_logical_byte == block_group->start)
 		fs_info->first_logical_byte = (u64)-1;
 	spin_unlock(&fs_info->block_group_cache_lock);
 
@@ -1048,19 +1046,21 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	if (btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
 		WARN_ON(block_group->space_info->total_bytes
-			< block_group->key.offset);
+			< block_group->length);
 		WARN_ON(block_group->space_info->bytes_readonly
-			< block_group->key.offset);
+			< block_group->length);
 		WARN_ON(block_group->space_info->disk_total
-			< block_group->key.offset * factor);
+			< block_group->length * factor);
 	}
-	block_group->space_info->total_bytes -= block_group->key.offset;
-	block_group->space_info->bytes_readonly -= block_group->key.offset;
-	block_group->space_info->disk_total -= block_group->key.offset * factor;
+	block_group->space_info->total_bytes -= block_group->length;
+	block_group->space_info->bytes_readonly -= block_group->length;
+	block_group->space_info->disk_total -= block_group->length * factor;
 
 	spin_unlock(&block_group->space_info->lock);
 
-	memcpy(&key, &block_group->key, sizeof(key));
+	key.objectid = block_group->start;
+	key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+	key.offset = block_group->length;
 
 	mutex_lock(&fs_info->chunk_mutex);
 	spin_lock(&block_group->lock);
@@ -1180,7 +1180,7 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
  * data in this block group. That check should be done by relocation routine,
  * not this function.
  */
-static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
+static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
 {
 	struct btrfs_space_info *sinfo = cache->space_info;
 	u64 num_bytes;
@@ -1209,8 +1209,8 @@ static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
 		goto out;
 	}
 
-	num_bytes = cache->key.offset - cache->reserved - cache->pinned -
-		    cache->bytes_super - btrfs_block_group_used(&cache->item);
+	num_bytes = cache->length - cache->reserved - cache->pinned -
+		    cache->bytes_super - cache->used;
 	sinfo_used = btrfs_space_info_used(sinfo, true);
 
 	/*
@@ -1231,8 +1231,7 @@ out:
 	spin_unlock(&sinfo->lock);
 	if (ret == -ENOSPC && btrfs_test_opt(cache->fs_info, ENOSPC_DEBUG)) {
 		btrfs_info(cache->fs_info,
-			"unable to make block group %llu ro",
-			cache->key.objectid);
+			"unable to make block group %llu ro", cache->start);
 		btrfs_info(cache->fs_info,
 			"sinfo_used=%llu bg_num_bytes=%llu min_allocable=%llu",
 			sinfo_used, num_bytes, min_allocable_bytes);
@@ -1247,7 +1246,7 @@ out:
  */
 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_space_info *space_info;
 	struct btrfs_trans_handle *trans;
 	int ret = 0;
@@ -1261,7 +1260,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		int trimming;
 
 		block_group = list_first_entry(&fs_info->unused_bgs,
-					       struct btrfs_block_group_cache,
+					       struct btrfs_block_group,
 					       bg_list);
 		list_del_init(&block_group->bg_list);
 
@@ -1279,8 +1278,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		down_write(&space_info->groups_sem);
 		spin_lock(&block_group->lock);
 		if (block_group->reserved || block_group->pinned ||
-		    btrfs_block_group_used(&block_group->item) ||
-		    block_group->ro ||
+		    block_group->used || block_group->ro ||
 		    list_is_singular(&block_group->list)) {
 			/*
 			 * We want to bail if we made new allocations or have
@@ -1308,7 +1306,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * properly if we fail to join the transaction.
 		 */
 		trans = btrfs_start_trans_remove_block_group(fs_info,
-						     block_group->key.objectid);
+						     block_group->start);
 		if (IS_ERR(trans)) {
 			btrfs_dec_block_group_ro(block_group);
 			ret = PTR_ERR(trans);
@@ -1319,8 +1317,8 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * We could have pending pinned extents for this block group,
 		 * just delete them, we don't care about them anymore.
 		 */
-		start = block_group->key.objectid;
-		end = start + block_group->key.offset - 1;
+		start = block_group->start;
+		end = start + block_group->length - 1;
 		/*
 		 * Hold the unused_bg_unpin_mutex lock to avoid racing with
 		 * btrfs_finish_extent_commit(). If we are at transaction N,
@@ -1375,7 +1373,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * Btrfs_remove_chunk will abort the transaction if things go
 		 * horribly wrong.
 		 */
-		ret = btrfs_remove_chunk(trans, block_group->key.objectid);
+		ret = btrfs_remove_chunk(trans, block_group->start);
 
 		if (ret) {
 			if (trimming)
@@ -1410,7 +1408,7 @@ next:
 	spin_unlock(&fs_info->unused_bgs_lock);
 }
 
-void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg)
+void btrfs_mark_bg_unused(struct btrfs_block_group *bg)
 {
 	struct btrfs_fs_info *fs_info = bg->fs_info;
 
@@ -1478,7 +1476,7 @@ static int find_first_block_group(struct btrfs_fs_info *fs_info,
 				read_extent_buffer(leaf, &bg,
 					btrfs_item_ptr_offset(leaf, slot),
 					sizeof(bg));
-				flags = btrfs_block_group_flags(&bg) &
+				flags = btrfs_stack_block_group_flags(&bg) &
 					BTRFS_BLOCK_GROUP_TYPE_MASK;
 
 				if (flags != (em->map_lookup->type &
@@ -1518,7 +1516,7 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 	write_sequnlock(&fs_info->profiles_lock);
 }
 
-static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
+static int exclude_super_stripes(struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	u64 bytenr;
@@ -1526,10 +1524,10 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
 	int stripe_len;
 	int i, nr, ret;
 
-	if (cache->key.objectid < BTRFS_SUPER_INFO_OFFSET) {
-		stripe_len = BTRFS_SUPER_INFO_OFFSET - cache->key.objectid;
+	if (cache->start < BTRFS_SUPER_INFO_OFFSET) {
+		stripe_len = BTRFS_SUPER_INFO_OFFSET - cache->start;
 		cache->bytes_super += stripe_len;
-		ret = btrfs_add_excluded_extent(fs_info, cache->key.objectid,
+		ret = btrfs_add_excluded_extent(fs_info, cache->start,
 						stripe_len);
 		if (ret)
 			return ret;
@@ -1537,7 +1535,7 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
 
 	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
 		bytenr = btrfs_sb_offset(i);
-		ret = btrfs_rmap_block(fs_info, cache->key.objectid,
+		ret = btrfs_rmap_block(fs_info, cache->start,
 				       bytenr, &logical, &nr, &stripe_len);
 		if (ret)
 			return ret;
@@ -1545,21 +1543,19 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
 		while (nr--) {
 			u64 start, len;
 
-			if (logical[nr] > cache->key.objectid +
-			    cache->key.offset)
+			if (logical[nr] > cache->start + cache->length)
 				continue;
 
-			if (logical[nr] + stripe_len <= cache->key.objectid)
+			if (logical[nr] + stripe_len <= cache->start)
 				continue;
 
 			start = logical[nr];
-			if (start < cache->key.objectid) {
-				start = cache->key.objectid;
+			if (start < cache->start) {
+				start = cache->start;
 				len = (logical[nr] + stripe_len) - start;
 			} else {
 				len = min_t(u64, stripe_len,
-					    cache->key.objectid +
-					    cache->key.offset - start);
+					    cache->start + cache->length - start);
 			}
 
 			cache->bytes_super += len;
@@ -1575,7 +1571,7 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
 	return 0;
 }
 
-static void link_block_group(struct btrfs_block_group_cache *cache)
+static void link_block_group(struct btrfs_block_group *cache)
 {
 	struct btrfs_space_info *space_info = cache->space_info;
 	int index = btrfs_bg_flags_to_raid_index(cache->flags);
@@ -1591,10 +1587,10 @@ static void link_block_group(struct btrfs_block_group_cache *cache)
 		btrfs_sysfs_add_block_group_type(cache);
 }
 
-static struct btrfs_block_group_cache *btrfs_create_block_group_cache(
+static struct btrfs_block_group *btrfs_create_block_group_cache(
 		struct btrfs_fs_info *fs_info, u64 start, u64 size)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 
 	cache = kzalloc(sizeof(*cache), GFP_NOFS);
 	if (!cache)
@@ -1607,9 +1603,8 @@ static struct btrfs_block_group_cache *btrfs_create_block_group_cache(
 		return NULL;
 	}
 
-	cache->key.objectid = start;
-	cache->key.offset = size;
-	cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+	cache->start = start;
+	cache->length = size;
 
 	cache->fs_info = fs_info;
 	cache->full_stripe_len = btrfs_full_stripe_len(fs_info, start);
@@ -1640,7 +1635,7 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
 {
 	struct extent_map_tree *map_tree = &fs_info->mapping_tree;
 	struct extent_map *em;
-	struct btrfs_block_group_cache *bg;
+	struct btrfs_block_group *bg;
 	u64 start = 0;
 	int ret = 0;
 
@@ -1665,15 +1660,14 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
 			free_extent_map(em);
 			break;
 		}
-		if (bg->key.objectid != em->start ||
-		    bg->key.offset != em->len ||
+		if (bg->start != em->start || bg->length != em->len ||
 		    (bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) !=
 		    (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
 			btrfs_err(fs_info,
 "chunk start=%llu len=%llu flags=0x%llx doesn't match block group start=%llu len=%llu flags=0x%llx",
 				em->start, em->len,
 				em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK,
-				bg->key.objectid, bg->key.offset,
+				bg->start, bg->length,
 				bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
 			ret = -EUCLEAN;
 			free_extent_map(em);
@@ -1687,22 +1681,117 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
 	return ret;
 }
 
+static int read_one_block_group(struct btrfs_fs_info *info,
+				struct btrfs_path *path,
+				const struct btrfs_key *key,
+				int need_clear)
+{
+	struct extent_buffer *leaf = path->nodes[0];
+	struct btrfs_block_group *cache;
+	struct btrfs_space_info *space_info;
+	struct btrfs_block_group_item bgi;
+	const bool mixed = btrfs_fs_incompat(info, MIXED_GROUPS);
+	int slot = path->slots[0];
+	int ret;
+
+	ASSERT(key->type == BTRFS_BLOCK_GROUP_ITEM_KEY);
+
+	cache = btrfs_create_block_group_cache(info, key->objectid, key->offset);
+	if (!cache)
+		return -ENOMEM;
+
+	if (need_clear) {
+		/*
+		 * When we mount with old space cache, we need to
+		 * set BTRFS_DC_CLEAR and set dirty flag.
+		 *
+		 * a) Setting 'BTRFS_DC_CLEAR' makes sure that we
+		 *    truncate the old free space cache inode and
+		 *    setup a new one.
+		 * b) Setting 'dirty flag' makes sure that we flush
+		 *    the new space cache info onto disk.
+		 */
+		if (btrfs_test_opt(info, SPACE_CACHE))
+			cache->disk_cache_state = BTRFS_DC_CLEAR;
+	}
+	read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
+			   sizeof(bgi));
+	cache->used = btrfs_stack_block_group_used(&bgi);
+	cache->flags = btrfs_stack_block_group_flags(&bgi);
+	if (!mixed && ((cache->flags & BTRFS_BLOCK_GROUP_METADATA) &&
+	    (cache->flags & BTRFS_BLOCK_GROUP_DATA))) {
+			btrfs_err(info,
+"bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups",
+				  cache->start);
+			ret = -EINVAL;
+			goto error;
+	}
+
+	/*
+	 * We need to exclude the super stripes now so that the space info has
+	 * super bytes accounted for, otherwise we'll think we have more space
+	 * than we actually do.
+	 */
+	ret = exclude_super_stripes(cache);
+	if (ret) {
+		/* We may have excluded something, so call this just in case. */
+		btrfs_free_excluded_extents(cache);
+		goto error;
+	}
+
+	/*
+	 * Check for two cases, either we are full, and therefore don't need
+	 * to bother with the caching work since we won't find any space, or we
+	 * are empty, and we can just add all the space in and be done with it.
+	 * This saves us _a_lot_ of time, particularly in the full case.
+	 */
+	if (key->offset == cache->used) {
+		cache->last_byte_to_unpin = (u64)-1;
+		cache->cached = BTRFS_CACHE_FINISHED;
+		btrfs_free_excluded_extents(cache);
+	} else if (cache->used == 0) {
+		cache->last_byte_to_unpin = (u64)-1;
+		cache->cached = BTRFS_CACHE_FINISHED;
+		add_new_free_space(cache, key->objectid,
+				   key->objectid + key->offset);
+		btrfs_free_excluded_extents(cache);
+	}
+
+	ret = btrfs_add_block_group_cache(info, cache);
+	if (ret) {
+		btrfs_remove_free_space_cache(cache);
+		goto error;
+	}
+	trace_btrfs_add_block_group(info, cache, 0);
+	btrfs_update_space_info(info, cache->flags, key->offset,
+				cache->used, cache->bytes_super, &space_info);
+
+	cache->space_info = space_info;
+
+	link_block_group(cache);
+
+	set_avail_alloc_bits(info, cache->flags);
+	if (btrfs_chunk_readonly(info, cache->start)) {
+		inc_block_group_ro(cache, 1);
+	} else if (cache->used == 0) {
+		ASSERT(list_empty(&cache->bg_list));
+		btrfs_mark_bg_unused(cache);
+	}
+	return 0;
+error:
+	btrfs_put_block_group(cache);
+	return ret;
+}
+
 int btrfs_read_block_groups(struct btrfs_fs_info *info)
 {
 	struct btrfs_path *path;
 	int ret;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	struct btrfs_space_info *space_info;
 	struct btrfs_key key;
-	struct btrfs_key found_key;
-	struct extent_buffer *leaf;
 	int need_clear = 0;
 	u64 cache_gen;
-	u64 feature;
-	int mixed;
-
-	feature = btrfs_super_incompat_flags(info->super_copy);
-	mixed = !!(feature & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS);
 
 	key.objectid = 0;
 	key.offset = 0;
@@ -1726,108 +1815,13 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 		if (ret != 0)
 			goto error;
 
-		leaf = path->nodes[0];
-		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
-
-		cache = btrfs_create_block_group_cache(info, found_key.objectid,
-						       found_key.offset);
-		if (!cache) {
-			ret = -ENOMEM;
-			goto error;
-		}
-
-		if (need_clear) {
-			/*
-			 * When we mount with old space cache, we need to
-			 * set BTRFS_DC_CLEAR and set dirty flag.
-			 *
-			 * a) Setting 'BTRFS_DC_CLEAR' makes sure that we
-			 *    truncate the old free space cache inode and
-			 *    setup a new one.
-			 * b) Setting 'dirty flag' makes sure that we flush
-			 *    the new space cache info onto disk.
-			 */
-			if (btrfs_test_opt(info, SPACE_CACHE))
-				cache->disk_cache_state = BTRFS_DC_CLEAR;
-		}
-
-		read_extent_buffer(leaf, &cache->item,
-				   btrfs_item_ptr_offset(leaf, path->slots[0]),
-				   sizeof(cache->item));
-		cache->flags = btrfs_block_group_flags(&cache->item);
-		if (!mixed &&
-		    ((cache->flags & BTRFS_BLOCK_GROUP_METADATA) &&
-		    (cache->flags & BTRFS_BLOCK_GROUP_DATA))) {
-			btrfs_err(info,
-"bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups",
-				  cache->key.objectid);
-			btrfs_put_block_group(cache);
-			ret = -EINVAL;
+		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+		ret = read_one_block_group(info, path, &key, need_clear);
+		if (ret < 0)
 			goto error;
-		}
-
-		key.objectid = found_key.objectid + found_key.offset;
+		key.objectid += key.offset;
+		key.offset = 0;
 		btrfs_release_path(path);
-
-		/*
-		 * We need to exclude the super stripes now so that the space
-		 * info has super bytes accounted for, otherwise we'll think
-		 * we have more space than we actually do.
-		 */
-		ret = exclude_super_stripes(cache);
-		if (ret) {
-			/*
-			 * We may have excluded something, so call this just in
-			 * case.
-			 */
-			btrfs_free_excluded_extents(cache);
-			btrfs_put_block_group(cache);
-			goto error;
-		}
-
-		/*
-		 * Check for two cases, either we are full, and therefore
-		 * don't need to bother with the caching work since we won't
-		 * find any space, or we are empty, and we can just add all
-		 * the space in and be done with it.  This saves us _a_lot_ of
-		 * time, particularly in the full case.
-		 */
-		if (found_key.offset == btrfs_block_group_used(&cache->item)) {
-			cache->last_byte_to_unpin = (u64)-1;
-			cache->cached = BTRFS_CACHE_FINISHED;
-			btrfs_free_excluded_extents(cache);
-		} else if (btrfs_block_group_used(&cache->item) == 0) {
-			cache->last_byte_to_unpin = (u64)-1;
-			cache->cached = BTRFS_CACHE_FINISHED;
-			add_new_free_space(cache, found_key.objectid,
-					   found_key.objectid +
-					   found_key.offset);
-			btrfs_free_excluded_extents(cache);
-		}
-
-		ret = btrfs_add_block_group_cache(info, cache);
-		if (ret) {
-			btrfs_remove_free_space_cache(cache);
-			btrfs_put_block_group(cache);
-			goto error;
-		}
-
-		trace_btrfs_add_block_group(info, cache, 0);
-		btrfs_update_space_info(info, cache->flags, found_key.offset,
-					btrfs_block_group_used(&cache->item),
-					cache->bytes_super, &space_info);
-
-		cache->space_info = space_info;
-
-		link_block_group(cache);
-
-		set_avail_alloc_bits(info, cache->flags);
-		if (btrfs_chunk_readonly(info, cache->key.objectid)) {
-			inc_block_group_ro(cache, 1);
-		} else if (btrfs_block_group_used(&cache->item) == 0) {
-			ASSERT(list_empty(&cache->bg_list));
-			btrfs_mark_bg_unused(cache);
-		}
 	}
 
 	list_for_each_entry_rcu(space_info, &info->space_info, list) {
@@ -1861,7 +1855,7 @@ error:
 void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_root *extent_root = fs_info->extent_root;
 	struct btrfs_block_group_item item;
 	struct btrfs_key key;
@@ -1872,14 +1866,19 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
 
 	while (!list_empty(&trans->new_bgs)) {
 		block_group = list_first_entry(&trans->new_bgs,
-					       struct btrfs_block_group_cache,
+					       struct btrfs_block_group,
 					       bg_list);
 		if (ret)
 			goto next;
 
 		spin_lock(&block_group->lock);
-		memcpy(&item, &block_group->item, sizeof(item));
-		memcpy(&key, &block_group->key, sizeof(key));
+		btrfs_set_stack_block_group_used(&item, block_group->used);
+		btrfs_set_stack_block_group_chunk_objectid(&item,
+				BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+		btrfs_set_stack_block_group_flags(&item, block_group->flags);
+		key.objectid = block_group->start;
+		key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+		key.offset = block_group->length;
 		spin_unlock(&block_group->lock);
 
 		ret = btrfs_insert_item(trans, extent_root, &key, &item,
@@ -1902,7 +1901,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 			   u64 type, u64 chunk_offset, u64 size)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	int ret;
 
 	btrfs_set_log_full_commit(trans);
@@ -1911,11 +1910,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 	if (!cache)
 		return -ENOMEM;
 
-	btrfs_set_block_group_used(&cache->item, bytes_used);
-	btrfs_set_block_group_chunk_objectid(&cache->item,
-					     BTRFS_FIRST_CHUNK_TREE_OBJECTID);
-	btrfs_set_block_group_flags(&cache->item, type);
-
+	cache->used = bytes_used;
 	cache->flags = type;
 	cache->last_byte_to_unpin = (u64)-1;
 	cache->cached = BTRFS_CACHE_FINISHED;
@@ -2022,8 +2017,17 @@ static u64 update_block_group_flags(struct btrfs_fs_info *fs_info, u64 flags)
 	return flags;
 }
 
-int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache)
-
+/*
+ * Mark one block group RO, can be called several times for the same block
+ * group.
+ *
+ * @cache:		the destination block group
+ * @do_chunk_alloc:	whether need to do chunk pre-allocation, this is to
+ * 			ensure we still have some free space after marking this
+ * 			block group RO.
+ */
+int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
+			     bool do_chunk_alloc)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_trans_handle *trans;
@@ -2053,25 +2057,29 @@ again:
 		goto again;
 	}
 
-	/*
-	 * if we are changing raid levels, try to allocate a corresponding
-	 * block group with the new raid level.
-	 */
-	alloc_flags = update_block_group_flags(fs_info, cache->flags);
-	if (alloc_flags != cache->flags) {
-		ret = btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
+	if (do_chunk_alloc) {
 		/*
-		 * ENOSPC is allowed here, we may have enough space
-		 * already allocated at the new raid level to
-		 * carry on
+		 * If we are changing raid levels, try to allocate a
+		 * corresponding block group with the new raid level.
 		 */
-		if (ret == -ENOSPC)
-			ret = 0;
-		if (ret < 0)
-			goto out;
+		alloc_flags = update_block_group_flags(fs_info, cache->flags);
+		if (alloc_flags != cache->flags) {
+			ret = btrfs_chunk_alloc(trans, alloc_flags,
+						CHUNK_ALLOC_FORCE);
+			/*
+			 * ENOSPC is allowed here, we may have enough space
+			 * already allocated at the new raid level to carry on
+			 */
+			if (ret == -ENOSPC)
+				ret = 0;
+			if (ret < 0)
+				goto out;
+		}
 	}
 
-	ret = inc_block_group_ro(cache, 0);
+	ret = inc_block_group_ro(cache, !do_chunk_alloc);
+	if (!do_chunk_alloc)
+		goto unlock_out;
 	if (!ret)
 		goto out;
 	alloc_flags = btrfs_get_alloc_profile(fs_info, cache->space_info->flags);
@@ -2086,13 +2094,14 @@ out:
 		check_system_chunk(trans, alloc_flags);
 		mutex_unlock(&fs_info->chunk_mutex);
 	}
+unlock_out:
 	mutex_unlock(&fs_info->ro_block_group_mutex);
 
 	btrfs_end_transaction(trans);
 	return ret;
 }
 
-void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache)
+void btrfs_dec_block_group_ro(struct btrfs_block_group *cache)
 {
 	struct btrfs_space_info *sinfo = cache->space_info;
 	u64 num_bytes;
@@ -2102,9 +2111,8 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache)
 	spin_lock(&sinfo->lock);
 	spin_lock(&cache->lock);
 	if (!--cache->ro) {
-		num_bytes = cache->key.offset - cache->reserved -
-			    cache->pinned - cache->bytes_super -
-			    btrfs_block_group_used(&cache->item);
+		num_bytes = cache->length - cache->reserved -
+			    cache->pinned - cache->bytes_super - cache->used;
 		sinfo->bytes_readonly -= num_bytes;
 		list_del_init(&cache->ro_list);
 	}
@@ -2114,15 +2122,21 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache)
 
 static int write_one_cache_group(struct btrfs_trans_handle *trans,
 				 struct btrfs_path *path,
-				 struct btrfs_block_group_cache *cache)
+				 struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret;
 	struct btrfs_root *extent_root = fs_info->extent_root;
 	unsigned long bi;
 	struct extent_buffer *leaf;
+	struct btrfs_block_group_item bgi;
+	struct btrfs_key key;
+
+	key.objectid = cache->start;
+	key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+	key.offset = cache->length;
 
-	ret = btrfs_search_slot(trans, extent_root, &cache->key, path, 0, 1);
+	ret = btrfs_search_slot(trans, extent_root, &key, path, 0, 1);
 	if (ret) {
 		if (ret > 0)
 			ret = -ENOENT;
@@ -2131,7 +2145,11 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
 
 	leaf = path->nodes[0];
 	bi = btrfs_item_ptr_offset(leaf, path->slots[0]);
-	write_extent_buffer(leaf, &cache->item, bi, sizeof(cache->item));
+	btrfs_set_stack_block_group_used(&bgi, cache->used);
+	btrfs_set_stack_block_group_chunk_objectid(&bgi,
+			BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+	btrfs_set_stack_block_group_flags(&bgi, cache->flags);
+	write_extent_buffer(leaf, &bgi, bi, sizeof(bgi));
 	btrfs_mark_buffer_dirty(leaf);
 fail:
 	btrfs_release_path(path);
@@ -2139,7 +2157,7 @@ fail:
 
 }
 
-static int cache_save_setup(struct btrfs_block_group_cache *block_group,
+static int cache_save_setup(struct btrfs_block_group *block_group,
 			    struct btrfs_trans_handle *trans,
 			    struct btrfs_path *path)
 {
@@ -2157,7 +2175,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
 	 * If this block group is smaller than 100 megs don't bother caching the
 	 * block group.
 	 */
-	if (block_group->key.offset < (100 * SZ_1M)) {
+	if (block_group->length < (100 * SZ_1M)) {
 		spin_lock(&block_group->lock);
 		block_group->disk_cache_state = BTRFS_DC_WRITTEN;
 		spin_unlock(&block_group->lock);
@@ -2258,7 +2276,7 @@ again:
 	 * taking up quite a bit since it's not folded into the other space
 	 * cache.
 	 */
-	num_pages = div_u64(block_group->key.offset, SZ_256M);
+	num_pages = div_u64(block_group->length, SZ_256M);
 	if (!num_pages)
 		num_pages = 1;
 
@@ -2303,7 +2321,7 @@ out:
 int btrfs_setup_space_cache(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_block_group_cache *cache, *tmp;
+	struct btrfs_block_group *cache, *tmp;
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	struct btrfs_path *path;
 
@@ -2341,7 +2359,7 @@ int btrfs_setup_space_cache(struct btrfs_trans_handle *trans)
 int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	int ret = 0;
 	int should_put;
@@ -2378,8 +2396,7 @@ again:
 	while (!list_empty(&dirty)) {
 		bool drop_reserve = true;
 
-		cache = list_first_entry(&dirty,
-					 struct btrfs_block_group_cache,
+		cache = list_first_entry(&dirty, struct btrfs_block_group,
 					 dirty_list);
 		/*
 		 * This can happen if something re-dirties a block group that
@@ -2504,7 +2521,7 @@ again:
 int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	int ret = 0;
 	int should_put;
@@ -2534,7 +2551,7 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
 	spin_lock(&cur_trans->dirty_bgs_lock);
 	while (!list_empty(&cur_trans->dirty_bgs)) {
 		cache = list_first_entry(&cur_trans->dirty_bgs,
-					 struct btrfs_block_group_cache,
+					 struct btrfs_block_group,
 					 dirty_list);
 
 		/*
@@ -2616,7 +2633,7 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
 	 * to use it without any locking
 	 */
 	while (!list_empty(io)) {
-		cache = list_first_entry(io, struct btrfs_block_group_cache,
+		cache = list_first_entry(io, struct btrfs_block_group,
 					 io_list);
 		list_del_init(&cache->io_list);
 		btrfs_wait_cache_io(trans, cache, path);
@@ -2631,7 +2648,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 			     u64 bytenr, u64 num_bytes, int alloc)
 {
 	struct btrfs_fs_info *info = trans->fs_info;
-	struct btrfs_block_group_cache *cache = NULL;
+	struct btrfs_block_group *cache = NULL;
 	u64 total = num_bytes;
 	u64 old_val;
 	u64 byte_in_group;
@@ -2662,11 +2679,11 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 		 * is because we need the unpinning stage to actually add the
 		 * space back to the block group, otherwise we will leak space.
 		 */
-		if (!alloc && cache->cached == BTRFS_CACHE_NO)
+		if (!alloc && !btrfs_block_group_done(cache))
 			btrfs_cache_block_group(cache, 1);
 
-		byte_in_group = bytenr - cache->key.objectid;
-		WARN_ON(byte_in_group > cache->key.offset);
+		byte_in_group = bytenr - cache->start;
+		WARN_ON(byte_in_group > cache->length);
 
 		spin_lock(&cache->space_info->lock);
 		spin_lock(&cache->lock);
@@ -2675,11 +2692,11 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 		    cache->disk_cache_state < BTRFS_DC_CLEAR)
 			cache->disk_cache_state = BTRFS_DC_CLEAR;
 
-		old_val = btrfs_block_group_used(&cache->item);
-		num_bytes = min(total, cache->key.offset - byte_in_group);
+		old_val = cache->used;
+		num_bytes = min(total, cache->length - byte_in_group);
 		if (alloc) {
 			old_val += num_bytes;
-			btrfs_set_block_group_used(&cache->item, old_val);
+			cache->used = old_val;
 			cache->reserved -= num_bytes;
 			cache->space_info->bytes_reserved -= num_bytes;
 			cache->space_info->bytes_used += num_bytes;
@@ -2688,7 +2705,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 			spin_unlock(&cache->space_info->lock);
 		} else {
 			old_val -= num_bytes;
-			btrfs_set_block_group_used(&cache->item, old_val);
+			cache->used = old_val;
 			cache->pinned += num_bytes;
 			btrfs_space_info_update_bytes_pinned(info,
 					cache->space_info, num_bytes);
@@ -2746,7 +2763,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
  * reservation and the block group has become read only we cannot make the
  * reservation and return -EAGAIN, otherwise this function always succeeds.
  */
-int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
+int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
 			     u64 ram_bytes, u64 num_bytes, int delalloc)
 {
 	struct btrfs_space_info *space_info = cache->space_info;
@@ -2782,7 +2799,7 @@ int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
  * A and before transaction A commits you free that leaf, you call this with
  * reserve set to 0 in order to clear the reservation.
  */
-void btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
+void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
 			       u64 num_bytes, int delalloc)
 {
 	struct btrfs_space_info *space_info = cache->space_info;
@@ -2988,9 +3005,7 @@ static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type)
 }
 
 /*
- * If @is_allocation is true, reserve space in the system space info necessary
- * for allocating a chunk, otherwise if it's false, reserve space necessary for
- * removing a chunk.
+ * Reserve space in the system space for allocating or removing a chunk
  */
 void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
 {
@@ -3047,7 +3062,7 @@ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
 
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	u64 last = 0;
 
 	while (1) {
@@ -3075,7 +3090,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
 		spin_unlock(&block_group->lock);
 		ASSERT(block_group->io_ctl.inode == NULL);
 		iput(inode);
-		last = block_group->key.objectid + block_group->key.offset;
+		last = block_group->start + block_group->length;
 		btrfs_put_block_group(block_group);
 	}
 }
@@ -3087,7 +3102,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
  */
 int btrfs_free_block_groups(struct btrfs_fs_info *info)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_space_info *space_info;
 	struct btrfs_caching_control *caching_ctl;
 	struct rb_node *n;
@@ -3104,7 +3119,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 	spin_lock(&info->unused_bgs_lock);
 	while (!list_empty(&info->unused_bgs)) {
 		block_group = list_first_entry(&info->unused_bgs,
-					       struct btrfs_block_group_cache,
+					       struct btrfs_block_group,
 					       bg_list);
 		list_del_init(&block_group->bg_list);
 		btrfs_put_block_group(block_group);
@@ -3113,7 +3128,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 
 	spin_lock(&info->block_group_cache_lock);
 	while ((n = rb_last(&info->block_group_cache_tree)) != NULL) {
-		block_group = rb_entry(n, struct btrfs_block_group_cache,
+		block_group = rb_entry(n, struct btrfs_block_group,
 				       cache_node);
 		rb_erase(&block_group->cache_node,
 			 &info->block_group_cache_tree);
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index c391800388dd..9b409676c4b2 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -34,7 +34,7 @@ struct btrfs_caching_control {
 	struct mutex mutex;
 	wait_queue_head_t wait;
 	struct btrfs_work work;
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	u64 progress;
 	refcount_t count;
 };
@@ -42,14 +42,15 @@ struct btrfs_caching_control {
 /* Once caching_thread() finds this much free space, it will wake up waiters. */
 #define CACHING_CTL_WAKE_UP SZ_2M
 
-struct btrfs_block_group_cache {
-	struct btrfs_key key;
-	struct btrfs_block_group_item item;
+struct btrfs_block_group {
 	struct btrfs_fs_info *fs_info;
 	struct inode *inode;
 	spinlock_t lock;
+	u64 start;
+	u64 length;
 	u64 pinned;
 	u64 reserved;
+	u64 used;
 	u64 delalloc_bytes;
 	u64 bytes_super;
 	u64 flags;
@@ -159,7 +160,7 @@ struct btrfs_block_group_cache {
 
 #ifdef CONFIG_BTRFS_DEBUG
 static inline int btrfs_should_fragment_free_space(
-		struct btrfs_block_group_cache *block_group)
+		struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 
@@ -170,29 +171,29 @@ static inline int btrfs_should_fragment_free_space(
 }
 #endif
 
-struct btrfs_block_group_cache *btrfs_lookup_first_block_group(
+struct btrfs_block_group *btrfs_lookup_first_block_group(
 		struct btrfs_fs_info *info, u64 bytenr);
-struct btrfs_block_group_cache *btrfs_lookup_block_group(
+struct btrfs_block_group *btrfs_lookup_block_group(
 		struct btrfs_fs_info *info, u64 bytenr);
-struct btrfs_block_group_cache *btrfs_next_block_group(
-		struct btrfs_block_group_cache *cache);
-void btrfs_get_block_group(struct btrfs_block_group_cache *cache);
-void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
+struct btrfs_block_group *btrfs_next_block_group(
+		struct btrfs_block_group *cache);
+void btrfs_get_block_group(struct btrfs_block_group *cache);
+void btrfs_put_block_group(struct btrfs_block_group *cache);
 void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
 					const u64 start);
-void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg);
+void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg);
 bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
 void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
-void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg);
-void btrfs_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache,
+void btrfs_wait_nocow_writers(struct btrfs_block_group *bg);
+void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
 				           u64 num_bytes);
-int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache);
-int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
+int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache);
+int btrfs_cache_block_group(struct btrfs_block_group *cache,
 			    int load_cache_only);
 void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
 struct btrfs_caching_control *btrfs_get_caching_control(
-		struct btrfs_block_group_cache *cache);
-u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
+		struct btrfs_block_group *cache);
+u64 add_new_free_space(struct btrfs_block_group *block_group,
 		       u64 start, u64 end);
 struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 				struct btrfs_fs_info *fs_info,
@@ -200,21 +201,22 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 			     u64 group_start, struct extent_map *em);
 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
-void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg);
+void btrfs_mark_bg_unused(struct btrfs_block_group *bg);
 int btrfs_read_block_groups(struct btrfs_fs_info *info);
 int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 			   u64 type, u64 chunk_offset, u64 size);
 void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
-int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache);
-void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache);
+int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
+			     bool do_chunk_alloc);
+void btrfs_dec_block_group_ro(struct btrfs_block_group *cache);
 int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans);
 int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans);
 int btrfs_setup_space_cache(struct btrfs_trans_handle *trans);
 int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 			     u64 bytenr, u64 num_bytes, int alloc);
-int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
+int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
 			     u64 ram_bytes, u64 num_bytes, int delalloc);
-void btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
+void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
 			       u64 num_bytes, int delalloc);
 int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 		      enum btrfs_chunk_alloc_enum force);
@@ -239,8 +241,7 @@ static inline u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info)
 	return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
 }
 
-static inline int btrfs_block_group_cache_done(
-		struct btrfs_block_group_cache *cache)
+static inline int btrfs_block_group_done(struct btrfs_block_group *cache)
 {
 	smp_mb();
 	return cache->cached == BTRFS_CACHE_FINISHED ||
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index f853835c409c..4e12a477d32e 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -63,9 +63,6 @@ struct btrfs_inode {
 	/* held while logging the inode in tree-log.c */
 	struct mutex log_mutex;
 
-	/* held while doing delalloc reservations */
-	struct mutex delalloc_mutex;
-
 	/* used to order data wrt metadata */
 	struct btrfs_ordered_inode_tree ordered_tree;
 
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b05b361e2062..ee834ef7beb4 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -29,6 +29,41 @@
 #include "extent_io.h"
 #include "extent_map.h"
 
+int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
+		u64 start, struct page **pages, unsigned long *out_pages,
+		unsigned long *total_in, unsigned long *total_out);
+int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
+int zlib_decompress(struct list_head *ws, unsigned char *data_in,
+		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		size_t destlen);
+struct list_head *zlib_alloc_workspace(unsigned int level);
+void zlib_free_workspace(struct list_head *ws);
+struct list_head *zlib_get_workspace(unsigned int level);
+
+int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
+		u64 start, struct page **pages, unsigned long *out_pages,
+		unsigned long *total_in, unsigned long *total_out);
+int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
+int lzo_decompress(struct list_head *ws, unsigned char *data_in,
+		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		size_t destlen);
+struct list_head *lzo_alloc_workspace(unsigned int level);
+void lzo_free_workspace(struct list_head *ws);
+
+int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
+		u64 start, struct page **pages, unsigned long *out_pages,
+		unsigned long *total_in, unsigned long *total_out);
+int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
+int zstd_decompress(struct list_head *ws, unsigned char *data_in,
+		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		size_t destlen);
+void zstd_init_workspace_manager(void);
+void zstd_cleanup_workspace_manager(void);
+struct list_head *zstd_alloc_workspace(unsigned int level);
+void zstd_free_workspace(struct list_head *ws);
+struct list_head *zstd_get_workspace(unsigned int level);
+void zstd_put_workspace(struct list_head *ws);
+
 static const char* const btrfs_compress_types[] = { "", "zlib", "lzo", "zstd" };
 
 const char* btrfs_compress_type2str(enum btrfs_compression_type type)
@@ -39,6 +74,8 @@ const char* btrfs_compress_type2str(enum btrfs_compression_type type)
 	case BTRFS_COMPRESS_ZSTD:
 	case BTRFS_COMPRESS_NONE:
 		return btrfs_compress_types[type];
+	default:
+		break;
 	}
 
 	return NULL;
@@ -60,6 +97,70 @@ bool btrfs_compress_is_valid_type(const char *str, size_t len)
 	return false;
 }
 
+static int compression_compress_pages(int type, struct list_head *ws,
+               struct address_space *mapping, u64 start, struct page **pages,
+               unsigned long *out_pages, unsigned long *total_in,
+               unsigned long *total_out)
+{
+	switch (type) {
+	case BTRFS_COMPRESS_ZLIB:
+		return zlib_compress_pages(ws, mapping, start, pages,
+				out_pages, total_in, total_out);
+	case BTRFS_COMPRESS_LZO:
+		return lzo_compress_pages(ws, mapping, start, pages,
+				out_pages, total_in, total_out);
+	case BTRFS_COMPRESS_ZSTD:
+		return zstd_compress_pages(ws, mapping, start, pages,
+				out_pages, total_in, total_out);
+	case BTRFS_COMPRESS_NONE:
+	default:
+		/*
+		 * This can't happen, the type is validated several times
+		 * before we get here. As a sane fallback, return what the
+		 * callers will understand as 'no compression happened'.
+		 */
+		return -E2BIG;
+	}
+}
+
+static int compression_decompress_bio(int type, struct list_head *ws,
+		struct compressed_bio *cb)
+{
+	switch (type) {
+	case BTRFS_COMPRESS_ZLIB: return zlib_decompress_bio(ws, cb);
+	case BTRFS_COMPRESS_LZO:  return lzo_decompress_bio(ws, cb);
+	case BTRFS_COMPRESS_ZSTD: return zstd_decompress_bio(ws, cb);
+	case BTRFS_COMPRESS_NONE:
+	default:
+		/*
+		 * This can't happen, the type is validated several times
+		 * before we get here.
+		 */
+		BUG();
+	}
+}
+
+static int compression_decompress(int type, struct list_head *ws,
+               unsigned char *data_in, struct page *dest_page,
+               unsigned long start_byte, size_t srclen, size_t destlen)
+{
+	switch (type) {
+	case BTRFS_COMPRESS_ZLIB: return zlib_decompress(ws, data_in, dest_page,
+						start_byte, srclen, destlen);
+	case BTRFS_COMPRESS_LZO:  return lzo_decompress(ws, data_in, dest_page,
+						start_byte, srclen, destlen);
+	case BTRFS_COMPRESS_ZSTD: return zstd_decompress(ws, data_in, dest_page,
+						start_byte, srclen, destlen);
+	case BTRFS_COMPRESS_NONE:
+	default:
+		/*
+		 * This can't happen, the type is validated several times
+		 * before we get here.
+		 */
+		BUG();
+	}
+}
+
 static int btrfs_decompress_bio(struct compressed_bio *cb);
 
 static inline int compressed_bio_size(struct btrfs_fs_info *fs_info,
@@ -311,7 +412,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				 unsigned long compressed_len,
 				 struct page **compressed_pages,
 				 unsigned long nr_pages,
-				 unsigned int write_flags)
+				 unsigned int write_flags,
+				 struct cgroup_subsys_state *blkcg_css)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct bio *bio = NULL;
@@ -320,7 +422,6 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	int pg_index = 0;
 	struct page *page;
 	u64 first_byte = disk_start;
-	struct block_device *bdev;
 	blk_status_t ret;
 	int skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 
@@ -339,13 +440,15 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	cb->orig_bio = NULL;
 	cb->nr_pages = nr_pages;
 
-	bdev = fs_info->fs_devices->latest_bdev;
-
 	bio = btrfs_bio_alloc(first_byte);
-	bio_set_dev(bio, bdev);
 	bio->bi_opf = REQ_OP_WRITE | write_flags;
 	bio->bi_private = cb;
 	bio->bi_end_io = end_compressed_bio_write;
+
+	if (blkcg_css) {
+		bio->bi_opf |= REQ_CGROUP_PUNT;
+		bio_associate_blkg_from_css(bio, blkcg_css);
+	}
 	refcount_set(&cb->pending_bios, 1);
 
 	/* create and submit bios for the compressed pages */
@@ -378,14 +481,13 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				BUG_ON(ret); /* -ENOMEM */
 			}
 
-			ret = btrfs_map_bio(fs_info, bio, 0, 1);
+			ret = btrfs_map_bio(fs_info, bio, 0);
 			if (ret) {
 				bio->bi_status = ret;
 				bio_endio(bio);
 			}
 
 			bio = btrfs_bio_alloc(first_byte);
-			bio_set_dev(bio, bdev);
 			bio->bi_opf = REQ_OP_WRITE | write_flags;
 			bio->bi_private = cb;
 			bio->bi_end_io = end_compressed_bio_write;
@@ -409,7 +511,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 		BUG_ON(ret); /* -ENOMEM */
 	}
 
-	ret = btrfs_map_bio(fs_info, bio, 0, 1);
+	ret = btrfs_map_bio(fs_info, bio, 0);
 	if (ret) {
 		bio->bi_status = ret;
 		bio_endio(bio);
@@ -553,7 +655,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	unsigned long nr_pages;
 	unsigned long pg_index;
 	struct page *page;
-	struct block_device *bdev;
 	struct bio *comp_bio;
 	u64 cur_disk_byte = (u64)bio->bi_iter.bi_sector << 9;
 	u64 em_len;
@@ -604,8 +705,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	if (!cb->compressed_pages)
 		goto fail1;
 
-	bdev = fs_info->fs_devices->latest_bdev;
-
 	for (pg_index = 0; pg_index < nr_pages; pg_index++) {
 		cb->compressed_pages[pg_index] = alloc_page(GFP_NOFS |
 							      __GFP_HIGHMEM);
@@ -624,7 +723,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	cb->len = bio->bi_iter.bi_size;
 
 	comp_bio = btrfs_bio_alloc(cur_disk_byte);
-	bio_set_dev(comp_bio, bdev);
 	comp_bio->bi_opf = REQ_OP_READ;
 	comp_bio->bi_private = cb;
 	comp_bio->bi_end_io = end_compressed_bio_read;
@@ -668,14 +766,13 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 						  fs_info->sectorsize);
 			sums += csum_size * nr_sectors;
 
-			ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0);
+			ret = btrfs_map_bio(fs_info, comp_bio, mirror_num);
 			if (ret) {
 				comp_bio->bi_status = ret;
 				bio_endio(comp_bio);
 			}
 
 			comp_bio = btrfs_bio_alloc(cur_disk_byte);
-			bio_set_dev(comp_bio, bdev);
 			comp_bio->bi_opf = REQ_OP_READ;
 			comp_bio->bi_private = cb;
 			comp_bio->bi_end_io = end_compressed_bio_read;
@@ -693,7 +790,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		BUG_ON(ret); /* -ENOMEM */
 	}
 
-	ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0);
+	ret = btrfs_map_bio(fs_info, comp_bio, mirror_num);
 	if (ret) {
 		comp_bio->bi_status = ret;
 		bio_endio(comp_bio);
@@ -764,26 +861,6 @@ struct heuristic_ws {
 
 static struct workspace_manager heuristic_wsm;
 
-static void heuristic_init_workspace_manager(void)
-{
-	btrfs_init_workspace_manager(&heuristic_wsm, &btrfs_heuristic_compress);
-}
-
-static void heuristic_cleanup_workspace_manager(void)
-{
-	btrfs_cleanup_workspace_manager(&heuristic_wsm);
-}
-
-static struct list_head *heuristic_get_workspace(unsigned int level)
-{
-	return btrfs_get_workspace(&heuristic_wsm, level);
-}
-
-static void heuristic_put_workspace(struct list_head *ws)
-{
-	btrfs_put_workspace(&heuristic_wsm, ws);
-}
-
 static void free_heuristic_ws(struct list_head *ws)
 {
 	struct heuristic_ws *workspace;
@@ -824,12 +901,7 @@ fail:
 }
 
 const struct btrfs_compress_op btrfs_heuristic_compress = {
-	.init_workspace_manager = heuristic_init_workspace_manager,
-	.cleanup_workspace_manager = heuristic_cleanup_workspace_manager,
-	.get_workspace = heuristic_get_workspace,
-	.put_workspace = heuristic_put_workspace,
-	.alloc_workspace = alloc_heuristic_ws,
-	.free_workspace = free_heuristic_ws,
+	.workspace_manager = &heuristic_wsm,
 };
 
 static const struct btrfs_compress_op * const btrfs_compress_op[] = {
@@ -840,13 +912,44 @@ static const struct btrfs_compress_op * const btrfs_compress_op[] = {
 	&btrfs_zstd_compress,
 };
 
-void btrfs_init_workspace_manager(struct workspace_manager *wsm,
-				  const struct btrfs_compress_op *ops)
+static struct list_head *alloc_workspace(int type, unsigned int level)
 {
-	struct list_head *workspace;
+	switch (type) {
+	case BTRFS_COMPRESS_NONE: return alloc_heuristic_ws(level);
+	case BTRFS_COMPRESS_ZLIB: return zlib_alloc_workspace(level);
+	case BTRFS_COMPRESS_LZO:  return lzo_alloc_workspace(level);
+	case BTRFS_COMPRESS_ZSTD: return zstd_alloc_workspace(level);
+	default:
+		/*
+		 * This can't happen, the type is validated several times
+		 * before we get here.
+		 */
+		BUG();
+	}
+}
 
-	wsm->ops = ops;
+static void free_workspace(int type, struct list_head *ws)
+{
+	switch (type) {
+	case BTRFS_COMPRESS_NONE: return free_heuristic_ws(ws);
+	case BTRFS_COMPRESS_ZLIB: return zlib_free_workspace(ws);
+	case BTRFS_COMPRESS_LZO:  return lzo_free_workspace(ws);
+	case BTRFS_COMPRESS_ZSTD: return zstd_free_workspace(ws);
+	default:
+		/*
+		 * This can't happen, the type is validated several times
+		 * before we get here.
+		 */
+		BUG();
+	}
+}
+
+static void btrfs_init_workspace_manager(int type)
+{
+	struct workspace_manager *wsm;
+	struct list_head *workspace;
 
+	wsm = btrfs_compress_op[type]->workspace_manager;
 	INIT_LIST_HEAD(&wsm->idle_ws);
 	spin_lock_init(&wsm->ws_lock);
 	atomic_set(&wsm->total_ws, 0);
@@ -856,7 +959,7 @@ void btrfs_init_workspace_manager(struct workspace_manager *wsm,
 	 * Preallocate one workspace for each compression type so we can
 	 * guarantee forward progress in the worst case
 	 */
-	workspace = wsm->ops->alloc_workspace(0);
+	workspace = alloc_workspace(type, 0);
 	if (IS_ERR(workspace)) {
 		pr_warn(
 	"BTRFS: cannot preallocate compression workspace, will try later\n");
@@ -867,14 +970,16 @@ void btrfs_init_workspace_manager(struct workspace_manager *wsm,
 	}
 }
 
-void btrfs_cleanup_workspace_manager(struct workspace_manager *wsman)
+static void btrfs_cleanup_workspace_manager(int type)
 {
+	struct workspace_manager *wsman;
 	struct list_head *ws;
 
+	wsman = btrfs_compress_op[type]->workspace_manager;
 	while (!list_empty(&wsman->idle_ws)) {
 		ws = wsman->idle_ws.next;
 		list_del(ws);
-		wsman->ops->free_workspace(ws);
+		free_workspace(type, ws);
 		atomic_dec(&wsman->total_ws);
 	}
 }
@@ -885,9 +990,9 @@ void btrfs_cleanup_workspace_manager(struct workspace_manager *wsman)
  * Preallocation makes a forward progress guarantees and we do not return
  * errors.
  */
-struct list_head *btrfs_get_workspace(struct workspace_manager *wsm,
-				      unsigned int level)
+struct list_head *btrfs_get_workspace(int type, unsigned int level)
 {
+	struct workspace_manager *wsm;
 	struct list_head *workspace;
 	int cpus = num_online_cpus();
 	unsigned nofs_flag;
@@ -897,6 +1002,7 @@ struct list_head *btrfs_get_workspace(struct workspace_manager *wsm,
 	wait_queue_head_t *ws_wait;
 	int *free_ws;
 
+	wsm = btrfs_compress_op[type]->workspace_manager;
 	idle_ws	 = &wsm->idle_ws;
 	ws_lock	 = &wsm->ws_lock;
 	total_ws = &wsm->total_ws;
@@ -932,7 +1038,7 @@ again:
 	 * context of btrfs_compress_bio/btrfs_compress_pages
 	 */
 	nofs_flag = memalloc_nofs_save();
-	workspace = wsm->ops->alloc_workspace(level);
+	workspace = alloc_workspace(type, level);
 	memalloc_nofs_restore(nofs_flag);
 
 	if (IS_ERR(workspace)) {
@@ -965,21 +1071,34 @@ again:
 
 static struct list_head *get_workspace(int type, int level)
 {
-	return btrfs_compress_op[type]->get_workspace(level);
+	switch (type) {
+	case BTRFS_COMPRESS_NONE: return btrfs_get_workspace(type, level);
+	case BTRFS_COMPRESS_ZLIB: return zlib_get_workspace(level);
+	case BTRFS_COMPRESS_LZO:  return btrfs_get_workspace(type, level);
+	case BTRFS_COMPRESS_ZSTD: return zstd_get_workspace(level);
+	default:
+		/*
+		 * This can't happen, the type is validated several times
+		 * before we get here.
+		 */
+		BUG();
+	}
 }
 
 /*
  * put a workspace struct back on the list or free it if we have enough
  * idle ones sitting around
  */
-void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws)
+void btrfs_put_workspace(int type, struct list_head *ws)
 {
+	struct workspace_manager *wsm;
 	struct list_head *idle_ws;
 	spinlock_t *ws_lock;
 	atomic_t *total_ws;
 	wait_queue_head_t *ws_wait;
 	int *free_ws;
 
+	wsm = btrfs_compress_op[type]->workspace_manager;
 	idle_ws	 = &wsm->idle_ws;
 	ws_lock	 = &wsm->ws_lock;
 	total_ws = &wsm->total_ws;
@@ -995,7 +1114,7 @@ void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws)
 	}
 	spin_unlock(ws_lock);
 
-	wsm->ops->free_workspace(ws);
+	free_workspace(type, ws);
 	atomic_dec(total_ws);
 wake:
 	cond_wake_up(ws_wait);
@@ -1003,7 +1122,18 @@ wake:
 
 static void put_workspace(int type, struct list_head *ws)
 {
-	return btrfs_compress_op[type]->put_workspace(ws);
+	switch (type) {
+	case BTRFS_COMPRESS_NONE: return btrfs_put_workspace(type, ws);
+	case BTRFS_COMPRESS_ZLIB: return btrfs_put_workspace(type, ws);
+	case BTRFS_COMPRESS_LZO:  return btrfs_put_workspace(type, ws);
+	case BTRFS_COMPRESS_ZSTD: return zstd_put_workspace(ws);
+	default:
+		/*
+		 * This can't happen, the type is validated several times
+		 * before we get here.
+		 */
+		BUG();
+	}
 }
 
 /*
@@ -1042,10 +1172,8 @@ int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping,
 
 	level = btrfs_compress_set_level(type, level);
 	workspace = get_workspace(type, level);
-	ret = btrfs_compress_op[type]->compress_pages(workspace, mapping,
-						      start, pages,
-						      out_pages,
-						      total_in, total_out);
+	ret = compression_compress_pages(type, workspace, mapping, start, pages,
+					 out_pages, total_in, total_out);
 	put_workspace(type, workspace);
 	return ret;
 }
@@ -1071,7 +1199,7 @@ static int btrfs_decompress_bio(struct compressed_bio *cb)
 	int type = cb->compress_type;
 
 	workspace = get_workspace(type, 0);
-	ret = btrfs_compress_op[type]->decompress_bio(workspace, cb);
+	ret = compression_decompress_bio(type, workspace, cb);
 	put_workspace(type, workspace);
 
 	return ret;
@@ -1089,9 +1217,8 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
 	int ret;
 
 	workspace = get_workspace(type, 0);
-	ret = btrfs_compress_op[type]->decompress(workspace, data_in,
-						  dest_page, start_byte,
-						  srclen, destlen);
+	ret = compression_decompress(type, workspace, data_in, dest_page,
+				     start_byte, srclen, destlen);
 	put_workspace(type, workspace);
 
 	return ret;
@@ -1099,18 +1226,18 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
 
 void __init btrfs_init_compress(void)
 {
-	int i;
-
-	for (i = 0; i < BTRFS_NR_WORKSPACE_MANAGERS; i++)
-		btrfs_compress_op[i]->init_workspace_manager();
+	btrfs_init_workspace_manager(BTRFS_COMPRESS_NONE);
+	btrfs_init_workspace_manager(BTRFS_COMPRESS_ZLIB);
+	btrfs_init_workspace_manager(BTRFS_COMPRESS_LZO);
+	zstd_init_workspace_manager();
 }
 
 void __cold btrfs_exit_compress(void)
 {
-	int i;
-
-	for (i = 0; i < BTRFS_NR_WORKSPACE_MANAGERS; i++)
-		btrfs_compress_op[i]->cleanup_workspace_manager();
+	btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_NONE);
+	btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_ZLIB);
+	btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_LZO);
+	zstd_cleanup_workspace_manager();
 }
 
 /*
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 4cb8be9ff88b..d253f7aa8ed5 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -93,7 +93,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				  unsigned long compressed_len,
 				  struct page **compressed_pages,
 				  unsigned long nr_pages,
-				  unsigned int write_flags);
+				  unsigned int write_flags,
+				  struct cgroup_subsys_state *blkcg_css);
 blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags);
 
@@ -104,11 +105,10 @@ enum btrfs_compression_type {
 	BTRFS_COMPRESS_ZLIB  = 1,
 	BTRFS_COMPRESS_LZO   = 2,
 	BTRFS_COMPRESS_ZSTD  = 3,
-	BTRFS_COMPRESS_TYPES = 3,
+	BTRFS_NR_COMPRESS_TYPES = 4,
 };
 
 struct workspace_manager {
-	const struct btrfs_compress_op *ops;
 	struct list_head idle_ws;
 	spinlock_t ws_lock;
 	/* Number of free workspaces */
@@ -119,50 +119,18 @@ struct workspace_manager {
 	wait_queue_head_t ws_wait;
 };
 
-void btrfs_init_workspace_manager(struct workspace_manager *wsm,
-				  const struct btrfs_compress_op *ops);
-struct list_head *btrfs_get_workspace(struct workspace_manager *wsm,
-				      unsigned int level);
-void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws);
-void btrfs_cleanup_workspace_manager(struct workspace_manager *wsm);
+struct list_head *btrfs_get_workspace(int type, unsigned int level);
+void btrfs_put_workspace(int type, struct list_head *ws);
 
 struct btrfs_compress_op {
-	void (*init_workspace_manager)(void);
-
-	void (*cleanup_workspace_manager)(void);
-
-	struct list_head *(*get_workspace)(unsigned int level);
-
-	void (*put_workspace)(struct list_head *ws);
-
-	struct list_head *(*alloc_workspace)(unsigned int level);
-
-	void (*free_workspace)(struct list_head *workspace);
-
-	int (*compress_pages)(struct list_head *workspace,
-			      struct address_space *mapping,
-			      u64 start,
-			      struct page **pages,
-			      unsigned long *out_pages,
-			      unsigned long *total_in,
-			      unsigned long *total_out);
-
-	int (*decompress_bio)(struct list_head *workspace,
-				struct compressed_bio *cb);
-
-	int (*decompress)(struct list_head *workspace,
-			  unsigned char *data_in,
-			  struct page *dest_page,
-			  unsigned long start_byte,
-			  size_t srclen, size_t destlen);
-
+	struct workspace_manager *workspace_manager;
 	/* Maximum level supported by the compression algorithm */
 	unsigned int max_level;
 	unsigned int default_level;
 };
 
 /* The heuristic workspaces are managed via the 0th workspace manager */
-#define BTRFS_NR_WORKSPACE_MANAGERS	(BTRFS_COMPRESS_TYPES + 1)
+#define BTRFS_NR_WORKSPACE_MANAGERS	BTRFS_NR_COMPRESS_TYPES
 
 extern const struct btrfs_compress_op btrfs_heuristic_compress;
 extern const struct btrfs_compress_op btrfs_zlib_compress;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index e59cde204b2f..5b6e86aaf2e1 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -32,8 +32,13 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
 static const struct btrfs_csums {
 	u16		size;
 	const char	*name;
+	const char	*driver;
 } btrfs_csums[] = {
 	[BTRFS_CSUM_TYPE_CRC32] = { .size = 4, .name = "crc32c" },
+	[BTRFS_CSUM_TYPE_XXHASH] = { .size = 8, .name = "xxhash64" },
+	[BTRFS_CSUM_TYPE_SHA256] = { .size = 32, .name = "sha256" },
+	[BTRFS_CSUM_TYPE_BLAKE2] = { .size = 32, .name = "blake2b",
+				     .driver = "blake2b-256" },
 };
 
 int btrfs_super_csum_size(const struct btrfs_super_block *s)
@@ -51,34 +56,25 @@ const char *btrfs_super_csum_name(u16 csum_type)
 	return btrfs_csums[csum_type].name;
 }
 
-struct btrfs_path *btrfs_alloc_path(void)
+/*
+ * Return driver name if defined, otherwise the name that's also a valid driver
+ * name
+ */
+const char *btrfs_super_csum_driver(u16 csum_type)
 {
-	return kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS);
+	/* csum type is validated at mount time */
+	return btrfs_csums[csum_type].driver ?:
+		btrfs_csums[csum_type].name;
 }
 
-/*
- * set all locked nodes in the path to blocking locks.  This should
- * be done before scheduling
- */
-noinline void btrfs_set_path_blocking(struct btrfs_path *p)
+size_t __const btrfs_get_num_csums(void)
 {
-	int i;
-	for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
-		if (!p->nodes[i] || !p->locks[i])
-			continue;
-		/*
-		 * If we currently have a spinning reader or writer lock this
-		 * will bump the count of blocking holders and drop the
-		 * spinlock.
-		 */
-		if (p->locks[i] == BTRFS_READ_LOCK) {
-			btrfs_set_lock_blocking_read(p->nodes[i]);
-			p->locks[i] = BTRFS_READ_LOCK_BLOCKING;
-		} else if (p->locks[i] == BTRFS_WRITE_LOCK) {
-			btrfs_set_lock_blocking_write(p->nodes[i]);
-			p->locks[i] = BTRFS_WRITE_LOCK_BLOCKING;
-		}
-	}
+	return ARRAY_SIZE(btrfs_csums);
+}
+
+struct btrfs_path *btrfs_alloc_path(void)
+{
+	return kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS);
 }
 
 /* this also releases the path */
@@ -1125,7 +1121,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 		    btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
 			parent_start = buf->start;
 
-		extent_buffer_get(cow);
+		atomic_inc(&cow->refs);
 		ret = tree_mod_log_insert_root(root->node, cow, 1);
 		BUG_ON(ret < 0);
 		rcu_assign_pointer(root->node, cow);
@@ -1563,7 +1559,7 @@ static int comp_keys(const struct btrfs_disk_key *disk,
 /*
  * same as comp_keys only with two btrfs_key's
  */
-int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2)
+int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2)
 {
 	if (k1->objectid > k2->objectid)
 		return 1;
@@ -2036,7 +2032,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 	/* update the path */
 	if (left) {
 		if (btrfs_header_nritems(left) > orig_slot) {
-			extent_buffer_get(left);
+			atomic_inc(&left->refs);
 			/* left was locked after cow */
 			path->nodes[level] = left;
 			path->slots[level + 1] -= 1;
@@ -2379,32 +2375,6 @@ static noinline void unlock_up(struct btrfs_path *path, int level,
 }
 
 /*
- * This releases any locks held in the path starting at level and
- * going all the way up to the root.
- *
- * btrfs_search_slot will keep the lock held on higher nodes in a few
- * corner cases, such as COW of the block at slot zero in the node.  This
- * ignores those rules, and it should only be called when there are no
- * more updates to be done higher up in the tree.
- */
-noinline void btrfs_unlock_up_safe(struct btrfs_path *path, int level)
-{
-	int i;
-
-	if (path->keep_locks)
-		return;
-
-	for (i = level; i < BTRFS_MAX_LEVEL; i++) {
-		if (!path->nodes[i])
-			continue;
-		if (!path->locks[i])
-			continue;
-		btrfs_tree_unlock_rw(path->nodes[i], path->locks[i]);
-		path->locks[i] = 0;
-	}
-}
-
-/*
  * helper function for btrfs_search_slot.  The goal is to find a block
  * in cache without setting the path to blocking.  If we find the block
  * we return zero and the path is unchanged.
@@ -2652,7 +2622,7 @@ static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root,
 
 		} else {
 			b = root->commit_root;
-			extent_buffer_get(b);
+			atomic_inc(&b->refs);
 		}
 		level = btrfs_header_level(b);
 		/*
@@ -2785,12 +2755,10 @@ again:
 	}
 
 	while (b) {
+		int dec = 0;
+
 		level = btrfs_header_level(b);
 
-		/*
-		 * setup the path here so we can release it under lock
-		 * contention with the cow code
-		 */
 		if (cow) {
 			bool last_level = (level == (BTRFS_MAX_LEVEL - 1));
 
@@ -2861,73 +2829,7 @@ cow_done:
 		if (ret < 0)
 			goto done;
 
-		if (level != 0) {
-			int dec = 0;
-			if (ret && slot > 0) {
-				dec = 1;
-				slot -= 1;
-			}
-			p->slots[level] = slot;
-			err = setup_nodes_for_search(trans, root, p, b, level,
-					     ins_len, &write_lock_level);
-			if (err == -EAGAIN)
-				goto again;
-			if (err) {
-				ret = err;
-				goto done;
-			}
-			b = p->nodes[level];
-			slot = p->slots[level];
-
-			/*
-			 * slot 0 is special, if we change the key
-			 * we have to update the parent pointer
-			 * which means we must have a write lock
-			 * on the parent
-			 */
-			if (slot == 0 && ins_len &&
-			    write_lock_level < level + 1) {
-				write_lock_level = level + 1;
-				btrfs_release_path(p);
-				goto again;
-			}
-
-			unlock_up(p, level, lowest_unlock,
-				  min_write_lock_level, &write_lock_level);
-
-			if (level == lowest_level) {
-				if (dec)
-					p->slots[level]++;
-				goto done;
-			}
-
-			err = read_block_for_search(root, p, &b, level,
-						    slot, key);
-			if (err == -EAGAIN)
-				goto again;
-			if (err) {
-				ret = err;
-				goto done;
-			}
-
-			if (!p->skip_locking) {
-				level = btrfs_header_level(b);
-				if (level <= write_lock_level) {
-					if (!btrfs_try_tree_write_lock(b)) {
-						btrfs_set_path_blocking(p);
-						btrfs_tree_lock(b);
-					}
-					p->locks[level] = BTRFS_WRITE_LOCK;
-				} else {
-					if (!btrfs_tree_read_lock_atomic(b)) {
-						btrfs_set_path_blocking(p);
-						btrfs_tree_read_lock(b);
-					}
-					p->locks[level] = BTRFS_READ_LOCK;
-				}
-				p->nodes[level] = b;
-			}
-		} else {
+		if (level == 0) {
 			p->slots[level] = slot;
 			if (ins_len > 0 &&
 			    btrfs_leaf_free_space(b) < ins_len) {
@@ -2952,6 +2854,67 @@ cow_done:
 					  min_write_lock_level, NULL);
 			goto done;
 		}
+		if (ret && slot > 0) {
+			dec = 1;
+			slot--;
+		}
+		p->slots[level] = slot;
+		err = setup_nodes_for_search(trans, root, p, b, level, ins_len,
+					     &write_lock_level);
+		if (err == -EAGAIN)
+			goto again;
+		if (err) {
+			ret = err;
+			goto done;
+		}
+		b = p->nodes[level];
+		slot = p->slots[level];
+
+		/*
+		 * Slot 0 is special, if we change the key we have to update
+		 * the parent pointer which means we must have a write lock on
+		 * the parent
+		 */
+		if (slot == 0 && ins_len && write_lock_level < level + 1) {
+			write_lock_level = level + 1;
+			btrfs_release_path(p);
+			goto again;
+		}
+
+		unlock_up(p, level, lowest_unlock, min_write_lock_level,
+			  &write_lock_level);
+
+		if (level == lowest_level) {
+			if (dec)
+				p->slots[level]++;
+			goto done;
+		}
+
+		err = read_block_for_search(root, p, &b, level, slot, key);
+		if (err == -EAGAIN)
+			goto again;
+		if (err) {
+			ret = err;
+			goto done;
+		}
+
+		if (!p->skip_locking) {
+			level = btrfs_header_level(b);
+			if (level <= write_lock_level) {
+				if (!btrfs_try_tree_write_lock(b)) {
+					btrfs_set_path_blocking(p);
+					btrfs_tree_lock(b);
+				}
+				p->locks[level] = BTRFS_WRITE_LOCK;
+			} else {
+				if (!btrfs_tree_read_lock_atomic(b)) {
+					btrfs_set_path_blocking(p);
+					btrfs_tree_read_lock(b);
+				}
+				p->locks[level] = BTRFS_READ_LOCK;
+			}
+			p->nodes[level] = b;
+		}
 	}
 	ret = 1;
 done:
@@ -3008,6 +2971,8 @@ again:
 	p->locks[level] = BTRFS_READ_LOCK;
 
 	while (b) {
+		int dec = 0;
+
 		level = btrfs_header_level(b);
 		p->nodes[level] = b;
 
@@ -3028,47 +2993,45 @@ again:
 		if (ret < 0)
 			goto done;
 
-		if (level != 0) {
-			int dec = 0;
-			if (ret && slot > 0) {
-				dec = 1;
-				slot -= 1;
-			}
+		if (level == 0) {
 			p->slots[level] = slot;
 			unlock_up(p, level, lowest_unlock, 0, NULL);
+			goto done;
+		}
 
-			if (level == lowest_level) {
-				if (dec)
-					p->slots[level]++;
-				goto done;
-			}
+		if (ret && slot > 0) {
+			dec = 1;
+			slot--;
+		}
+		p->slots[level] = slot;
+		unlock_up(p, level, lowest_unlock, 0, NULL);
 
-			err = read_block_for_search(root, p, &b, level,
-						    slot, key);
-			if (err == -EAGAIN)
-				goto again;
-			if (err) {
-				ret = err;
-				goto done;
-			}
+		if (level == lowest_level) {
+			if (dec)
+				p->slots[level]++;
+			goto done;
+		}
 
-			level = btrfs_header_level(b);
-			if (!btrfs_tree_read_lock_atomic(b)) {
-				btrfs_set_path_blocking(p);
-				btrfs_tree_read_lock(b);
-			}
-			b = tree_mod_log_rewind(fs_info, p, b, time_seq);
-			if (!b) {
-				ret = -ENOMEM;
-				goto done;
-			}
-			p->locks[level] = BTRFS_READ_LOCK;
-			p->nodes[level] = b;
-		} else {
-			p->slots[level] = slot;
-			unlock_up(p, level, lowest_unlock, 0, NULL);
+		err = read_block_for_search(root, p, &b, level, slot, key);
+		if (err == -EAGAIN)
+			goto again;
+		if (err) {
+			ret = err;
+			goto done;
+		}
+
+		level = btrfs_header_level(b);
+		if (!btrfs_tree_read_lock_atomic(b)) {
+			btrfs_set_path_blocking(p);
+			btrfs_tree_read_lock(b);
+		}
+		b = tree_mod_log_rewind(fs_info, p, b, time_seq);
+		if (!b) {
+			ret = -ENOMEM;
 			goto done;
 		}
+		p->locks[level] = BTRFS_READ_LOCK;
+		p->nodes[level] = b;
 	}
 	ret = 1;
 done:
@@ -3433,7 +3396,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 	free_extent_buffer(old);
 
 	add_root_to_dirty_list(root);
-	extent_buffer_get(c);
+	atomic_inc(&c->refs);
 	path->nodes[level] = c;
 	path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
 	path->slots[level] = 0;
@@ -4966,7 +4929,7 @@ static noinline void btrfs_del_leaf(struct btrfs_trans_handle *trans,
 
 	root_sub_used(root, leaf->len);
 
-	extent_buffer_get(leaf);
+	atomic_inc(&leaf->refs);
 	btrfs_free_tree_block(trans, root, leaf, 0, 1);
 	free_extent_buffer_stale(leaf);
 }
@@ -5047,7 +5010,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 			 * for possible call to del_ptr below
 			 */
 			slot = path->slots[1];
-			extent_buffer_get(leaf);
+			atomic_inc(&leaf->refs);
 
 			btrfs_set_path_blocking(path);
 			wret = push_leaf_left(trans, root, path, 1, 1,
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index fe2b8765d9e6..b2e8fd8a8e59 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -28,6 +28,7 @@
 #include <linux/dynamic_debug.h>
 #include <linux/refcount.h>
 #include <linux/crc32c.h>
+#include "extent-io-tree.h"
 #include "extent_io.h"
 #include "extent_map.h"
 #include "async-thread.h"
@@ -38,7 +39,7 @@ struct btrfs_transaction;
 struct btrfs_pending_snapshot;
 struct btrfs_delayed_ref_root;
 struct btrfs_space_info;
-struct btrfs_block_group_cache;
+struct btrfs_block_group;
 extern struct kmem_cache *btrfs_trans_handle_cachep;
 extern struct kmem_cache *btrfs_bit_radix_cachep;
 extern struct kmem_cache *btrfs_path_cachep;
@@ -56,9 +57,9 @@ struct btrfs_ref;
  * filesystem data as well that can be used to read data in order to repair
  * read errors on other disks.
  *
- * Current value is derived from RAID1 with 2 copies.
+ * Current value is derived from RAID1C4 with 4 copies.
  */
-#define BTRFS_MAX_MIRRORS (2 + 1)
+#define BTRFS_MAX_MIRRORS (4 + 1)
 
 #define BTRFS_MAX_LEVEL 8
 
@@ -291,7 +292,8 @@ struct btrfs_super_block {
 	 BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF |		\
 	 BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA |	\
 	 BTRFS_FEATURE_INCOMPAT_NO_HOLES	|	\
-	 BTRFS_FEATURE_INCOMPAT_METADATA_UUID)
+	 BTRFS_FEATURE_INCOMPAT_METADATA_UUID	|	\
+	 BTRFS_FEATURE_INCOMPAT_RAID1C34)
 
 #define BTRFS_FEATURE_INCOMPAT_SAFE_SET			\
 	(BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF)
@@ -413,7 +415,7 @@ struct btrfs_free_cluster {
 	/* We did a full search and couldn't create a cluster */
 	bool fragmented;
 
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	/*
 	 * when a cluster is allocated from a block group, we put the
 	 * cluster onto a list in the block group so that it can
@@ -476,8 +478,8 @@ struct btrfs_swapfile_pin {
 	void *ptr;
 	struct inode *inode;
 	/*
-	 * If true, ptr points to a struct btrfs_block_group_cache. Otherwise,
-	 * ptr points to a struct btrfs_device.
+	 * If true, ptr points to a struct btrfs_block_group. Otherwise, ptr
+	 * points to a struct btrfs_device.
 	 */
 	bool is_block_group;
 };
@@ -722,7 +724,6 @@ struct btrfs_fs_info {
 	struct btrfs_workqueue *endio_meta_write_workers;
 	struct btrfs_workqueue *endio_write_workers;
 	struct btrfs_workqueue *endio_freespace_worker;
-	struct btrfs_workqueue *submit_workers;
 	struct btrfs_workqueue *caching_workers;
 	struct btrfs_workqueue *readahead_workers;
 
@@ -1519,18 +1520,18 @@ static inline u64 btrfs_stripe_devid_nr(struct extent_buffer *eb,
 }
 
 /* struct btrfs_block_group_item */
-BTRFS_SETGET_STACK_FUNCS(block_group_used, struct btrfs_block_group_item,
+BTRFS_SETGET_STACK_FUNCS(stack_block_group_used, struct btrfs_block_group_item,
 			 used, 64);
-BTRFS_SETGET_FUNCS(disk_block_group_used, struct btrfs_block_group_item,
+BTRFS_SETGET_FUNCS(block_group_used, struct btrfs_block_group_item,
 			 used, 64);
-BTRFS_SETGET_STACK_FUNCS(block_group_chunk_objectid,
+BTRFS_SETGET_STACK_FUNCS(stack_block_group_chunk_objectid,
 			struct btrfs_block_group_item, chunk_objectid, 64);
 
-BTRFS_SETGET_FUNCS(disk_block_group_chunk_objectid,
+BTRFS_SETGET_FUNCS(block_group_chunk_objectid,
 		   struct btrfs_block_group_item, chunk_objectid, 64);
-BTRFS_SETGET_FUNCS(disk_block_group_flags,
+BTRFS_SETGET_FUNCS(block_group_flags,
 		   struct btrfs_block_group_item, flags, 64);
-BTRFS_SETGET_STACK_FUNCS(block_group_flags,
+BTRFS_SETGET_STACK_FUNCS(stack_block_group_flags,
 			struct btrfs_block_group_item, flags, 64);
 
 /* struct btrfs_free_space_info */
@@ -2163,6 +2164,9 @@ BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block,
 
 int btrfs_super_csum_size(const struct btrfs_super_block *s);
 const char *btrfs_super_csum_name(u16 csum_type);
+const char *btrfs_super_csum_driver(u16 csum_type);
+size_t __const btrfs_get_num_csums(void);
+
 
 /*
  * The leaf data grows from end-to-front in the node.
@@ -2397,7 +2401,7 @@ static inline u64 btrfs_calc_metadata_size(struct btrfs_fs_info *fs_info,
 
 int btrfs_add_excluded_extent(struct btrfs_fs_info *fs_info,
 			      u64 start, u64 num_bytes);
-void btrfs_free_excluded_extents(struct btrfs_block_group_cache *cache);
+void btrfs_free_excluded_extents(struct btrfs_block_group *cache);
 int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 			   unsigned long count);
 void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
@@ -2453,8 +2457,8 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			 struct btrfs_ref *generic_ref);
 
 int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr);
-void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache);
-void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *cache);
+void btrfs_get_block_group_trimming(struct btrfs_block_group *cache);
+void btrfs_put_block_group_trimming(struct btrfs_block_group *cache);
 void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
 
 enum btrfs_reserve_flush_enum {
@@ -2507,7 +2511,7 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
 		     int level, int *slot);
-int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2);
+int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2);
 int btrfs_previous_item(struct btrfs_root *root,
 			struct btrfs_path *path, u64 min_objectid,
 			int type);
@@ -2567,8 +2571,6 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 void btrfs_release_path(struct btrfs_path *p);
 struct btrfs_path *btrfs_alloc_path(void);
 void btrfs_free_path(struct btrfs_path *p);
-void btrfs_set_path_blocking(struct btrfs_path *p);
-void btrfs_unlock_up_safe(struct btrfs_path *p, int level);
 
 int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		   struct btrfs_path *path, int slot, int nr);
@@ -2870,10 +2872,9 @@ int btrfs_drop_inode(struct inode *inode);
 int __init btrfs_init_cachep(void);
 void __cold btrfs_destroy_cachep(void);
 struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
-			      struct btrfs_root *root, int *new,
-			      struct btrfs_path *path);
+			      struct btrfs_root *root, struct btrfs_path *path);
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
-			 struct btrfs_root *root, int *was_new);
+			 struct btrfs_root *root);
 struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 				    struct page *page, size_t pg_offset,
 				    u64 start, u64 end, int create);
@@ -2909,7 +2910,7 @@ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 int btrfs_ioctl_get_supported_features(void __user *arg);
 void btrfs_sync_inode_flags_to_i_flags(struct inode *inode);
-int btrfs_is_empty_uuid(u8 *uuid);
+int __pure btrfs_is_empty_uuid(u8 *uuid);
 int btrfs_defrag_file(struct inode *inode, struct file *file,
 		      struct btrfs_ioctl_defrag_range_args *range,
 		      u64 newer_than, unsigned long max_pages);
@@ -3143,7 +3144,7 @@ __cold
 void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
 		     unsigned int line, int errno, const char *fmt, ...);
 
-const char *btrfs_decode_error(int errno);
+const char * __attribute_const__ btrfs_decode_error(int errno);
 
 __cold
 void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index db9f2c58eb4a..4cdac4d834f5 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -307,7 +307,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	unsigned nr_extents;
 	enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL;
 	int ret = 0;
-	bool delalloc_lock = true;
 
 	/*
 	 * If we are a free space inode we need to not flush since we will be in
@@ -320,7 +319,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	 */
 	if (btrfs_is_free_space_inode(inode)) {
 		flush = BTRFS_RESERVE_NO_FLUSH;
-		delalloc_lock = false;
 	} else {
 		if (current->journal_info)
 			flush = BTRFS_RESERVE_FLUSH_LIMIT;
@@ -329,9 +327,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 			schedule_timeout(1);
 	}
 
-	if (delalloc_lock)
-		mutex_lock(&inode->delalloc_mutex);
-
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
 
 	/*
@@ -348,10 +343,12 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 				&qgroup_reserve);
 	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true);
 	if (ret)
-		goto out_fail;
+		return ret;
 	ret = btrfs_reserve_metadata_bytes(root, block_rsv, meta_reserve, flush);
-	if (ret)
-		goto out_qgroup;
+	if (ret) {
+		btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve);
+		return ret;
+	}
 
 	/*
 	 * Now we need to update our outstanding extents and csum bytes _first_
@@ -375,15 +372,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	block_rsv->qgroup_rsv_reserved += qgroup_reserve;
 	spin_unlock(&block_rsv->lock);
 
-	if (delalloc_lock)
-		mutex_unlock(&inode->delalloc_mutex);
 	return 0;
-out_qgroup:
-	btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve);
-out_fail:
-	if (delalloc_lock)
-		mutex_unlock(&inode->delalloc_mutex);
-	return ret;
 }
 
 /**
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 1f7f39b10bd0..d3e15e1d4a91 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -12,6 +12,7 @@
 #include "transaction.h"
 #include "ctree.h"
 #include "qgroup.h"
+#include "locking.h"
 
 #define BTRFS_DELAYED_WRITEBACK		512
 #define BTRFS_DELAYED_BACKGROUND	128
@@ -1367,8 +1368,8 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
 		return -ENOMEM;
 
 	async_work->delayed_root = delayed_root;
-	btrfs_init_work(&async_work->work, btrfs_delayed_meta_helper,
-			btrfs_async_run_delayed_root, NULL, NULL);
+	btrfs_init_work(&async_work->work, btrfs_async_run_delayed_root, NULL,
+			NULL);
 	async_work->nr = nr;
 
 	btrfs_queue_work(fs_info->delayed_workers, &async_work->work);
@@ -1949,12 +1950,19 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root)
 		}
 
 		inode_id = delayed_nodes[n - 1]->inode_id + 1;
-
-		for (i = 0; i < n; i++)
-			refcount_inc(&delayed_nodes[i]->refs);
+		for (i = 0; i < n; i++) {
+			/*
+			 * Don't increase refs in case the node is dead and
+			 * about to be removed from the tree in the loop below
+			 */
+			if (!refcount_inc_not_zero(&delayed_nodes[i]->refs))
+				delayed_nodes[i] = NULL;
+		}
 		spin_unlock(&root->inode_lock);
 
 		for (i = 0; i < n; i++) {
+			if (!delayed_nodes[i])
+				continue;
 			__btrfs_kill_delayed_node(delayed_nodes[i]);
 			btrfs_release_delayed_node(delayed_nodes[i]);
 		}
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 48890826b5e6..f639dde2a679 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -986,7 +986,7 @@ static int btrfs_dev_replace_kthread(void *data)
 	return 0;
 }
 
-int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
+int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
 {
 	if (!dev_replace->is_valid)
 		return 0;
diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h
index 78c5d8f1adda..60b70dacc299 100644
--- a/fs/btrfs/dev-replace.h
+++ b/fs/btrfs/dev-replace.h
@@ -17,6 +17,6 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info);
 void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info);
 int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info);
-int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace);
+int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace);
 
 #endif
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 402b61bf345c..e0edfdc9c82b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -205,7 +205,6 @@ struct extent_map *btree_get_extent(struct btrfs_inode *inode,
 		struct page *page, size_t pg_offset, u64 start, u64 len,
 		int create)
 {
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
 	int ret;
@@ -213,7 +212,6 @@ struct extent_map *btree_get_extent(struct btrfs_inode *inode,
 	read_lock(&em_tree->lock);
 	em = lookup_extent_mapping(em_tree, start, len);
 	if (em) {
-		em->bdev = fs_info->fs_devices->latest_bdev;
 		read_unlock(&em_tree->lock);
 		goto out;
 	}
@@ -228,7 +226,6 @@ struct extent_map *btree_get_extent(struct btrfs_inode *inode,
 	em->len = (u64)-1;
 	em->block_len = (u64)-1;
 	em->block_start = 0;
-	em->bdev = fs_info->fs_devices->latest_bdev;
 
 	write_lock(&em_tree->lock);
 	ret = add_extent_mapping(em_tree, em, 0);
@@ -352,6 +349,9 @@ static bool btrfs_supported_super_csum(u16 csum_type)
 {
 	switch (csum_type) {
 	case BTRFS_CSUM_TYPE_CRC32:
+	case BTRFS_CSUM_TYPE_XXHASH:
+	case BTRFS_CSUM_TYPE_SHA256:
+	case BTRFS_CSUM_TYPE_BLAKE2:
 		return true;
 	default:
 		return false;
@@ -545,9 +545,11 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
 		ret = btrfs_check_leaf_full(eb);
 
 	if (ret < 0) {
+		btrfs_print_tree(eb, 0);
 		btrfs_err(fs_info,
 		"block=%llu write time tree block corruption detected",
 			  eb->start);
+		WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
 		return ret;
 	}
 	write_extent_buffer(eb, result, 0, csum_size);
@@ -608,7 +610,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 	/* the pending IO might have been the only thing that kept this buffer
 	 * in memory.  Make sure we have a ref for all this other checks
 	 */
-	extent_buffer_get(eb);
+	atomic_inc(&eb->refs);
 
 	reads_done = atomic_dec_and_test(&eb->io_pages);
 	if (!reads_done)
@@ -706,43 +708,31 @@ static void end_workqueue_bio(struct bio *bio)
 	struct btrfs_end_io_wq *end_io_wq = bio->bi_private;
 	struct btrfs_fs_info *fs_info;
 	struct btrfs_workqueue *wq;
-	btrfs_work_func_t func;
 
 	fs_info = end_io_wq->info;
 	end_io_wq->status = bio->bi_status;
 
 	if (bio_op(bio) == REQ_OP_WRITE) {
-		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) {
+		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
 			wq = fs_info->endio_meta_write_workers;
-			func = btrfs_endio_meta_write_helper;
-		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) {
+		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
 			wq = fs_info->endio_freespace_worker;
-			func = btrfs_freespace_write_helper;
-		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
 			wq = fs_info->endio_raid56_workers;
-			func = btrfs_endio_raid56_helper;
-		} else {
+		else
 			wq = fs_info->endio_write_workers;
-			func = btrfs_endio_write_helper;
-		}
 	} else {
-		if (unlikely(end_io_wq->metadata ==
-			     BTRFS_WQ_ENDIO_DIO_REPAIR)) {
+		if (unlikely(end_io_wq->metadata == BTRFS_WQ_ENDIO_DIO_REPAIR))
 			wq = fs_info->endio_repair_workers;
-			func = btrfs_endio_repair_helper;
-		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
 			wq = fs_info->endio_raid56_workers;
-			func = btrfs_endio_raid56_helper;
-		} else if (end_io_wq->metadata) {
+		else if (end_io_wq->metadata)
 			wq = fs_info->endio_meta_workers;
-			func = btrfs_endio_meta_helper;
-		} else {
+		else
 			wq = fs_info->endio_workers;
-			func = btrfs_endio_helper;
-		}
 	}
 
-	btrfs_init_work(&end_io_wq->work, func, end_workqueue_fn, NULL, NULL);
+	btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);
 	btrfs_queue_work(wq, &end_io_wq->work);
 }
 
@@ -803,8 +793,13 @@ static void run_one_async_done(struct btrfs_work *work)
 		return;
 	}
 
-	ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio,
-			async->mirror_num, 1);
+	/*
+	 * All of the bios that pass through here are from async helpers.
+	 * Use REQ_CGROUP_PUNT to issue them from the owning cgroup's context.
+	 * This changes nothing when cgroups aren't in use.
+	 */
+	async->bio->bi_opf |= REQ_CGROUP_PUNT;
+	ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio, async->mirror_num);
 	if (ret) {
 		async->bio->bi_status = ret;
 		bio_endio(async->bio);
@@ -835,8 +830,8 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 	async->mirror_num = mirror_num;
 	async->submit_bio_start = submit_bio_start;
 
-	btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start,
-			run_one_async_done, run_one_async_free);
+	btrfs_init_work(&async->work, run_one_async_start, run_one_async_done,
+			run_one_async_free);
 
 	async->bio_offset = bio_offset;
 
@@ -904,12 +899,12 @@ static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio,
 					  BTRFS_WQ_ENDIO_METADATA);
 		if (ret)
 			goto out_w_error;
-		ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
+		ret = btrfs_map_bio(fs_info, bio, mirror_num);
 	} else if (!async) {
 		ret = btree_csum_one_bio(bio);
 		if (ret)
 			goto out_w_error;
-		ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
+		ret = btrfs_map_bio(fs_info, bio, mirror_num);
 	} else {
 		/*
 		 * kthread helpers are used to submit writes so that
@@ -1657,8 +1652,8 @@ static void end_workqueue_fn(struct btrfs_work *work)
 	bio->bi_status = end_io_wq->status;
 	bio->bi_private = end_io_wq->private;
 	bio->bi_end_io = end_io_wq->end_io;
-	kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
 	bio_endio(bio);
+	kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
 }
 
 static int cleaner_kthread(void *arg)
@@ -1753,7 +1748,7 @@ static int transaction_kthread(void *arg)
 		}
 
 		now = ktime_get_seconds();
-		if (cur->state < TRANS_STATE_BLOCKED &&
+		if (cur->state < TRANS_STATE_COMMIT_START &&
 		    !test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) &&
 		    (now < cur->start_time ||
 		     now - cur->start_time < fs_info->commit_interval)) {
@@ -1792,18 +1787,18 @@ sleep:
 }
 
 /*
- * this will find the highest generation in the array of
- * root backups.  The index of the highest array is returned,
- * or -1 if we can't find anything.
+ * This will find the highest generation in the array of root backups.  The
+ * index of the highest array is returned, or -EINVAL if we can't find
+ * anything.
  *
  * We check to make sure the array is valid by comparing the
  * generation of the latest  root in the array with the generation
  * in the super block.  If they don't match we pitch it.
  */
-static int find_newest_super_backup(struct btrfs_fs_info *info, u64 newest_gen)
+static int find_newest_super_backup(struct btrfs_fs_info *info)
 {
+	const u64 newest_gen = btrfs_super_generation(info->super_copy);
 	u64 cur;
-	int newest_index = -1;
 	struct btrfs_root_backup *root_backup;
 	int i;
 
@@ -1811,37 +1806,10 @@ static int find_newest_super_backup(struct btrfs_fs_info *info, u64 newest_gen)
 		root_backup = info->super_copy->super_roots + i;
 		cur = btrfs_backup_tree_root_gen(root_backup);
 		if (cur == newest_gen)
-			newest_index = i;
+			return i;
 	}
 
-	/* check to see if we actually wrapped around */
-	if (newest_index == BTRFS_NUM_BACKUP_ROOTS - 1) {
-		root_backup = info->super_copy->super_roots;
-		cur = btrfs_backup_tree_root_gen(root_backup);
-		if (cur == newest_gen)
-			newest_index = 0;
-	}
-	return newest_index;
-}
-
-
-/*
- * find the oldest backup so we know where to store new entries
- * in the backup array.  This will set the backup_root_index
- * field in the fs_info struct
- */
-static void find_oldest_super_backup(struct btrfs_fs_info *info,
-				     u64 newest_gen)
-{
-	int newest_index = -1;
-
-	newest_index = find_newest_super_backup(info, newest_gen);
-	/* if there was garbage in there, just move along */
-	if (newest_index == -1) {
-		info->backup_root_index = 0;
-	} else {
-		info->backup_root_index = (newest_index + 1) % BTRFS_NUM_BACKUP_ROOTS;
-	}
+	return -EINVAL;
 }
 
 /*
@@ -1851,22 +1819,8 @@ static void find_oldest_super_backup(struct btrfs_fs_info *info,
  */
 static void backup_super_roots(struct btrfs_fs_info *info)
 {
-	int next_backup;
+	const int next_backup = info->backup_root_index;
 	struct btrfs_root_backup *root_backup;
-	int last_backup;
-
-	next_backup = info->backup_root_index;
-	last_backup = (next_backup + BTRFS_NUM_BACKUP_ROOTS - 1) %
-		BTRFS_NUM_BACKUP_ROOTS;
-
-	/*
-	 * just overwrite the last backup if we're at the same generation
-	 * this happens only at umount
-	 */
-	root_backup = info->super_for_commit->super_roots + last_backup;
-	if (btrfs_backup_tree_root_gen(root_backup) ==
-	    btrfs_header_generation(info->tree_root->node))
-		next_backup = last_backup;
 
 	root_backup = info->super_for_commit->super_roots + next_backup;
 
@@ -1939,40 +1893,31 @@ static void backup_super_roots(struct btrfs_fs_info *info)
 }
 
 /*
- * this copies info out of the root backup array and back into
- * the in-memory super block.  It is meant to help iterate through
- * the array, so you send it the number of backups you've already
- * tried and the last backup index you used.
+ * read_backup_root - Reads a backup root based on the passed priority. Prio 0
+ * is the newest, prio 1/2/3 are 2nd newest/3rd newest/4th (oldest) backup roots
  *
- * this returns -1 when it has tried all the backups
+ * fs_info - filesystem whose backup roots need to be read
+ * priority - priority of backup root required
+ *
+ * Returns backup root index on success and -EINVAL otherwise.
  */
-static noinline int next_root_backup(struct btrfs_fs_info *info,
-				     struct btrfs_super_block *super,
-				     int *num_backups_tried, int *backup_index)
+static int read_backup_root(struct btrfs_fs_info *fs_info, u8 priority)
 {
+	int backup_index = find_newest_super_backup(fs_info);
+	struct btrfs_super_block *super = fs_info->super_copy;
 	struct btrfs_root_backup *root_backup;
-	int newest = *backup_index;
-
-	if (*num_backups_tried == 0) {
-		u64 gen = btrfs_super_generation(super);
 
-		newest = find_newest_super_backup(info, gen);
-		if (newest == -1)
-			return -1;
+	if (priority < BTRFS_NUM_BACKUP_ROOTS && backup_index >= 0) {
+		if (priority == 0)
+			return backup_index;
 
-		*backup_index = newest;
-		*num_backups_tried = 1;
-	} else if (*num_backups_tried == BTRFS_NUM_BACKUP_ROOTS) {
-		/* we've tried all the backups, all done */
-		return -1;
+		backup_index = backup_index + BTRFS_NUM_BACKUP_ROOTS - priority;
+		backup_index %= BTRFS_NUM_BACKUP_ROOTS;
 	} else {
-		/* jump to the next oldest backup */
-		newest = (*backup_index + BTRFS_NUM_BACKUP_ROOTS - 1) %
-			BTRFS_NUM_BACKUP_ROOTS;
-		*backup_index = newest;
-		*num_backups_tried += 1;
+		return -EINVAL;
 	}
-	root_backup = super->super_roots + newest;
+
+	root_backup = super->super_roots + backup_index;
 
 	btrfs_set_super_generation(super,
 				   btrfs_backup_tree_root_gen(root_backup));
@@ -1982,12 +1927,13 @@ static noinline int next_root_backup(struct btrfs_fs_info *info,
 	btrfs_set_super_bytes_used(super, btrfs_backup_bytes_used(root_backup));
 
 	/*
-	 * fixme: the total bytes and num_devices need to match or we should
+	 * Fixme: the total bytes and num_devices need to match or we should
 	 * need a fsck
 	 */
 	btrfs_set_super_total_bytes(super, btrfs_backup_total_bytes(root_backup));
 	btrfs_set_super_num_devices(super, btrfs_backup_num_devices(root_backup));
-	return 0;
+
+	return backup_index;
 }
 
 /* helper to cleanup workers */
@@ -2002,7 +1948,6 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_workqueue(fs_info->rmw_workers);
 	btrfs_destroy_workqueue(fs_info->endio_write_workers);
 	btrfs_destroy_workqueue(fs_info->endio_freespace_worker);
-	btrfs_destroy_workqueue(fs_info->submit_workers);
 	btrfs_destroy_workqueue(fs_info->delayed_workers);
 	btrfs_destroy_workqueue(fs_info->caching_workers);
 	btrfs_destroy_workqueue(fs_info->readahead_workers);
@@ -2028,7 +1973,7 @@ static void free_root_extent_buffers(struct btrfs_root *root)
 }
 
 /* helper to cleanup tree roots */
-static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
+static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root)
 {
 	free_root_extent_buffers(info->tree_root);
 
@@ -2037,7 +1982,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
 	free_root_extent_buffers(info->csum_root);
 	free_root_extent_buffers(info->quota_root);
 	free_root_extent_buffers(info->uuid_root);
-	if (chunk_root)
+	if (free_chunk_root)
 		free_root_extent_buffers(info->chunk_root);
 	free_root_extent_buffers(info->free_space_root);
 }
@@ -2167,16 +2112,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
 	fs_info->caching_workers =
 		btrfs_alloc_workqueue(fs_info, "cache", flags, max_active, 0);
 
-	/*
-	 * a higher idle thresh on the submit workers makes it much more
-	 * likely that bios will be send down in a sane order to the
-	 * devices
-	 */
-	fs_info->submit_workers =
-		btrfs_alloc_workqueue(fs_info, "submit", flags,
-				      min_t(u64, fs_devices->num_devices,
-					    max_active), 64);
-
 	fs_info->fixup_workers =
 		btrfs_alloc_workqueue(fs_info, "fixup", flags, 1, 0);
 
@@ -2215,7 +2150,7 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
 		btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0);
 
 	if (!(fs_info->workers && fs_info->delalloc_workers &&
-	      fs_info->submit_workers && fs_info->flush_workers &&
+	      fs_info->flush_workers &&
 	      fs_info->endio_workers && fs_info->endio_meta_workers &&
 	      fs_info->endio_meta_write_workers &&
 	      fs_info->endio_repair_workers &&
@@ -2233,13 +2168,13 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
 static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type)
 {
 	struct crypto_shash *csum_shash;
-	const char *csum_name = btrfs_super_csum_name(csum_type);
+	const char *csum_driver = btrfs_super_csum_driver(csum_type);
 
-	csum_shash = crypto_alloc_shash(csum_name, 0, 0);
+	csum_shash = crypto_alloc_shash(csum_driver, 0, 0);
 
 	if (IS_ERR(csum_shash)) {
 		btrfs_err(fs_info, "error allocating %s hash for checksum",
-			  csum_name);
+			  csum_driver);
 		return PTR_ERR(csum_shash);
 	}
 
@@ -2589,7 +2524,101 @@ out:
 	return ret;
 }
 
-int open_ctree(struct super_block *sb,
+static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
+{
+	int backup_index = find_newest_super_backup(fs_info);
+	struct btrfs_super_block *sb = fs_info->super_copy;
+	struct btrfs_root *tree_root = fs_info->tree_root;
+	bool handle_error = false;
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) {
+		u64 generation;
+		int level;
+
+		if (handle_error) {
+			if (!IS_ERR(tree_root->node))
+				free_extent_buffer(tree_root->node);
+			tree_root->node = NULL;
+
+			if (!btrfs_test_opt(fs_info, USEBACKUPROOT))
+				break;
+
+			free_root_pointers(fs_info, 0);
+
+			/*
+			 * Don't use the log in recovery mode, it won't be
+			 * valid
+			 */
+			btrfs_set_super_log_root(sb, 0);
+
+			/* We can't trust the free space cache either */
+			btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE);
+
+			ret = read_backup_root(fs_info, i);
+			backup_index = ret;
+			if (ret < 0)
+				return ret;
+		}
+		generation = btrfs_super_generation(sb);
+		level = btrfs_super_root_level(sb);
+		tree_root->node = read_tree_block(fs_info, btrfs_super_root(sb),
+						  generation, level, NULL);
+		if (IS_ERR(tree_root->node) ||
+		    !extent_buffer_uptodate(tree_root->node)) {
+			handle_error = true;
+
+			if (IS_ERR(tree_root->node))
+				ret = PTR_ERR(tree_root->node);
+			else if (!extent_buffer_uptodate(tree_root->node))
+				ret = -EUCLEAN;
+
+			btrfs_warn(fs_info, "failed to read tree root");
+			continue;
+		}
+
+		btrfs_set_root_node(&tree_root->root_item, tree_root->node);
+		tree_root->commit_root = btrfs_root_node(tree_root);
+		btrfs_set_root_refs(&tree_root->root_item, 1);
+
+		/*
+		 * No need to hold btrfs_root::objectid_mutex since the fs
+		 * hasn't been fully initialised and we are the only user
+		 */
+		ret = btrfs_find_highest_objectid(tree_root,
+						&tree_root->highest_objectid);
+		if (ret < 0) {
+			handle_error = true;
+			continue;
+		}
+
+		ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+		ret = btrfs_read_roots(fs_info);
+		if (ret < 0) {
+			handle_error = true;
+			continue;
+		}
+
+		/* All successful */
+		fs_info->generation = generation;
+		fs_info->last_trans_committed = generation;
+
+		/* Always begin writing backup roots after the one being used */
+		if (backup_index < 0) {
+			fs_info->backup_root_index = 0;
+		} else {
+			fs_info->backup_root_index = backup_index + 1;
+			fs_info->backup_root_index %= BTRFS_NUM_BACKUP_ROOTS;
+		}
+		break;
+	}
+
+	return ret;
+}
+
+int __cold open_ctree(struct super_block *sb,
 	       struct btrfs_fs_devices *fs_devices,
 	       char *options)
 {
@@ -2607,8 +2636,6 @@ int open_ctree(struct super_block *sb,
 	struct btrfs_root *chunk_root;
 	int ret;
 	int err = -EINVAL;
-	int num_backups_tried = 0;
-	int backup_index = 0;
 	int clear_free_space_tree = 0;
 	int level;
 
@@ -2879,13 +2906,6 @@ int open_ctree(struct super_block *sb,
 		set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
 
 	/*
-	 * run through our array of backup supers and setup
-	 * our ring pointer to the oldest one
-	 */
-	generation = btrfs_super_generation(disk_super);
-	find_oldest_super_backup(fs_info, generation);
-
-	/*
 	 * In the long term, we'll store the compression type in the super
 	 * block, and it'll be used for per file compression control.
 	 */
@@ -3031,44 +3051,9 @@ int open_ctree(struct super_block *sb,
 		goto fail_tree_roots;
 	}
 
-retry_root_backup:
-	generation = btrfs_super_generation(disk_super);
-	level = btrfs_super_root_level(disk_super);
-
-	tree_root->node = read_tree_block(fs_info,
-					  btrfs_super_root(disk_super),
-					  generation, level, NULL);
-	if (IS_ERR(tree_root->node) ||
-	    !extent_buffer_uptodate(tree_root->node)) {
-		btrfs_warn(fs_info, "failed to read tree root");
-		if (!IS_ERR(tree_root->node))
-			free_extent_buffer(tree_root->node);
-		tree_root->node = NULL;
-		goto recovery_tree_root;
-	}
-
-	btrfs_set_root_node(&tree_root->root_item, tree_root->node);
-	tree_root->commit_root = btrfs_root_node(tree_root);
-	btrfs_set_root_refs(&tree_root->root_item, 1);
-
-	mutex_lock(&tree_root->objectid_mutex);
-	ret = btrfs_find_highest_objectid(tree_root,
-					&tree_root->highest_objectid);
-	if (ret) {
-		mutex_unlock(&tree_root->objectid_mutex);
-		goto recovery_tree_root;
-	}
-
-	ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
-
-	mutex_unlock(&tree_root->objectid_mutex);
-
-	ret = btrfs_read_roots(fs_info);
+	ret = init_tree_roots(fs_info);
 	if (ret)
-		goto recovery_tree_root;
-
-	fs_info->generation = generation;
-	fs_info->last_trans_committed = generation;
+		goto fail_tree_roots;
 
 	ret = btrfs_verify_dev_extents(fs_info);
 	if (ret) {
@@ -3336,7 +3321,7 @@ fail_block_groups:
 	btrfs_put_block_group_cache(fs_info);
 
 fail_tree_roots:
-	free_root_pointers(fs_info, 1);
+	free_root_pointers(fs_info, true);
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 
 fail_sb_buffer:
@@ -3363,24 +3348,6 @@ fail:
 	btrfs_free_stripe_hash_table(fs_info);
 	btrfs_close_devices(fs_info->fs_devices);
 	return err;
-
-recovery_tree_root:
-	if (!btrfs_test_opt(fs_info, USEBACKUPROOT))
-		goto fail_tree_roots;
-
-	free_root_pointers(fs_info, 0);
-
-	/* don't use the log in recovery mode, it won't be valid */
-	btrfs_set_super_log_root(disk_super, 0);
-
-	/* we can't trust the free space cache either */
-	btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE);
-
-	ret = next_root_backup(fs_info, fs_info->super_copy,
-			       &num_backups_tried, &backup_index);
-	if (ret == -1)
-		goto fail_block_groups;
-	goto retry_root_backup;
 }
 ALLOW_ERROR_INJECTION(open_ctree, ERRNO);
 
@@ -3974,7 +3941,7 @@ int btrfs_commit_super(struct btrfs_fs_info *fs_info)
 	return btrfs_commit_transaction(trans);
 }
 
-void close_ctree(struct btrfs_fs_info *fs_info)
+void __cold close_ctree(struct btrfs_fs_info *fs_info)
 {
 	int ret;
 
@@ -4062,7 +4029,7 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	btrfs_free_block_groups(fs_info);
 
 	clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
-	free_root_pointers(fs_info, 1);
+	free_root_pointers(fs_info, true);
 
 	iput(fs_info->btree_inode);
 
@@ -4439,7 +4406,7 @@ again:
 	return 0;
 }
 
-static void btrfs_cleanup_bg_io(struct btrfs_block_group_cache *cache)
+static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache)
 {
 	struct inode *inode;
 
@@ -4456,12 +4423,12 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group_cache *cache)
 void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans,
 			     struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 
 	spin_lock(&cur_trans->dirty_bgs_lock);
 	while (!list_empty(&cur_trans->dirty_bgs)) {
 		cache = list_first_entry(&cur_trans->dirty_bgs,
-					 struct btrfs_block_group_cache,
+					 struct btrfs_block_group,
 					 dirty_list);
 
 		if (!list_empty(&cache->io_list)) {
@@ -4489,7 +4456,7 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans,
 	 */
 	while (!list_empty(&cur_trans->io_bgs)) {
 		cache = list_first_entry(&cur_trans->io_bgs,
-					 struct btrfs_block_group_cache,
+					 struct btrfs_block_group,
 					 io_list);
 
 		list_del_init(&cache->io_list);
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index a6958103d87e..76f123ebb292 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -49,10 +49,10 @@ struct extent_buffer *btrfs_find_create_tree_block(
 						struct btrfs_fs_info *fs_info,
 						u64 bytenr);
 void btrfs_clean_tree_block(struct extent_buffer *buf);
-int open_ctree(struct super_block *sb,
+int __cold open_ctree(struct super_block *sb,
 	       struct btrfs_fs_devices *fs_devices,
 	       char *options);
-void close_ctree(struct btrfs_fs_info *fs_info);
+void __cold close_ctree(struct btrfs_fs_info *fs_info);
 int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors);
 struct buffer_head *btrfs_read_dev_super(struct block_device *bdev);
 int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num,
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index ddf28ecf17f9..72e312cae69d 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -87,7 +87,7 @@ static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
-	inode = btrfs_iget(sb, &key, root, NULL);
+	inode = btrfs_iget(sb, &key, root);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto fail;
@@ -214,7 +214,7 @@ static struct dentry *btrfs_get_parent(struct dentry *child)
 
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
-	return d_obtain_alias(btrfs_iget(fs_info->sb, &key, root, NULL));
+	return d_obtain_alias(btrfs_iget(fs_info->sb, &key, root));
 fail:
 	btrfs_free_path(path);
 	return ERR_PTR(ret);
diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h
new file mode 100644
index 000000000000..a3febe746c79
--- /dev/null
+++ b/fs/btrfs/extent-io-tree.h
@@ -0,0 +1,248 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef BTRFS_EXTENT_IO_TREE_H
+#define BTRFS_EXTENT_IO_TREE_H
+
+struct extent_changeset;
+struct io_failure_record;
+
+/* Bits for the extent state */
+#define EXTENT_DIRTY		(1U << 0)
+#define EXTENT_UPTODATE		(1U << 1)
+#define EXTENT_LOCKED		(1U << 2)
+#define EXTENT_NEW		(1U << 3)
+#define EXTENT_DELALLOC		(1U << 4)
+#define EXTENT_DEFRAG		(1U << 5)
+#define EXTENT_BOUNDARY		(1U << 6)
+#define EXTENT_NODATASUM	(1U << 7)
+#define EXTENT_CLEAR_META_RESV	(1U << 8)
+#define EXTENT_NEED_WAIT	(1U << 9)
+#define EXTENT_DAMAGED		(1U << 10)
+#define EXTENT_NORESERVE	(1U << 11)
+#define EXTENT_QGROUP_RESERVED	(1U << 12)
+#define EXTENT_CLEAR_DATA_RESV	(1U << 13)
+#define EXTENT_DELALLOC_NEW	(1U << 14)
+#define EXTENT_DO_ACCOUNTING    (EXTENT_CLEAR_META_RESV | \
+				 EXTENT_CLEAR_DATA_RESV)
+#define EXTENT_CTLBITS		(EXTENT_DO_ACCOUNTING)
+
+/*
+ * Redefined bits above which are used only in the device allocation tree,
+ * shouldn't be using EXTENT_LOCKED / EXTENT_BOUNDARY / EXTENT_CLEAR_META_RESV
+ * / EXTENT_CLEAR_DATA_RESV because they have special meaning to the bit
+ * manipulation functions
+ */
+#define CHUNK_ALLOCATED				EXTENT_DIRTY
+#define CHUNK_TRIMMED				EXTENT_DEFRAG
+
+enum {
+	IO_TREE_FS_INFO_FREED_EXTENTS0,
+	IO_TREE_FS_INFO_FREED_EXTENTS1,
+	IO_TREE_INODE_IO,
+	IO_TREE_INODE_IO_FAILURE,
+	IO_TREE_RELOC_BLOCKS,
+	IO_TREE_TRANS_DIRTY_PAGES,
+	IO_TREE_ROOT_DIRTY_LOG_PAGES,
+	IO_TREE_SELFTEST,
+};
+
+struct extent_io_tree {
+	struct rb_root state;
+	struct btrfs_fs_info *fs_info;
+	void *private_data;
+	u64 dirty_bytes;
+	bool track_uptodate;
+
+	/* Who owns this io tree, should be one of IO_TREE_* */
+	u8 owner;
+
+	spinlock_t lock;
+	const struct extent_io_ops *ops;
+};
+
+struct extent_state {
+	u64 start;
+	u64 end; /* inclusive */
+	struct rb_node rb_node;
+
+	/* ADD NEW ELEMENTS AFTER THIS */
+	wait_queue_head_t wq;
+	refcount_t refs;
+	unsigned state;
+
+	struct io_failure_record *failrec;
+
+#ifdef CONFIG_BTRFS_DEBUG
+	struct list_head leak_list;
+#endif
+};
+
+int __init extent_state_cache_init(void);
+void __cold extent_state_cache_exit(void);
+
+void extent_io_tree_init(struct btrfs_fs_info *fs_info,
+			 struct extent_io_tree *tree, unsigned int owner,
+			 void *private_data);
+void extent_io_tree_release(struct extent_io_tree *tree);
+
+int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+		     struct extent_state **cached);
+
+static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
+{
+	return lock_extent_bits(tree, start, end, NULL);
+}
+
+int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
+
+int __init extent_io_init(void);
+void __cold extent_io_exit(void);
+
+u64 count_range_bits(struct extent_io_tree *tree,
+		     u64 *start, u64 search_end,
+		     u64 max_bytes, unsigned bits, int contig);
+
+void free_extent_state(struct extent_state *state);
+int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		   unsigned bits, int filled,
+		   struct extent_state *cached_state);
+int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+		unsigned bits, struct extent_changeset *changeset);
+int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		     unsigned bits, int wake, int delete,
+		     struct extent_state **cached);
+int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		     unsigned bits, int wake, int delete,
+		     struct extent_state **cached, gfp_t mask,
+		     struct extent_changeset *changeset);
+
+static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
+{
+	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL);
+}
+
+static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached)
+{
+	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
+				GFP_NOFS, NULL);
+}
+
+static inline int unlock_extent_cached_atomic(struct extent_io_tree *tree,
+		u64 start, u64 end, struct extent_state **cached)
+{
+	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
+				GFP_ATOMIC, NULL);
+}
+
+static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
+		u64 end, unsigned bits)
+{
+	int wake = 0;
+
+	if (bits & EXTENT_LOCKED)
+		wake = 1;
+
+	return clear_extent_bit(tree, start, end, bits, wake, 0, NULL);
+}
+
+int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+			   unsigned bits, struct extent_changeset *changeset);
+int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		   unsigned bits, u64 *failed_start,
+		   struct extent_state **cached_state, gfp_t mask);
+int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end,
+			   unsigned bits);
+
+static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
+		u64 end, unsigned bits)
+{
+	return set_extent_bit(tree, start, end, bits, NULL, NULL, GFP_NOFS);
+}
+
+static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached_state)
+{
+	return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
+				cached_state, GFP_NOFS, NULL);
+}
+
+static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
+		u64 end, gfp_t mask)
+{
+	return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL,
+			      NULL, mask);
+}
+
+static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
+				     u64 end, struct extent_state **cached)
+{
+	return clear_extent_bit(tree, start, end,
+				EXTENT_DIRTY | EXTENT_DELALLOC |
+				EXTENT_DO_ACCOUNTING, 0, 0, cached);
+}
+
+int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		       unsigned bits, unsigned clear_bits,
+		       struct extent_state **cached_state);
+
+static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
+				      u64 end, unsigned int extra_bits,
+				      struct extent_state **cached_state)
+{
+	return set_extent_bit(tree, start, end,
+			      EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits,
+			      NULL, cached_state, GFP_NOFS);
+}
+
+static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached_state)
+{
+	return set_extent_bit(tree, start, end,
+			      EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
+			      NULL, cached_state, GFP_NOFS);
+}
+
+static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
+		u64 end)
+{
+	return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL,
+			GFP_NOFS);
+}
+
+static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached_state, gfp_t mask)
+{
+	return set_extent_bit(tree, start, end, EXTENT_UPTODATE, NULL,
+			      cached_state, mask);
+}
+
+int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
+			  u64 *start_ret, u64 *end_ret, unsigned bits,
+			  struct extent_state **cached_state);
+void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
+				 u64 *start_ret, u64 *end_ret, unsigned bits);
+int extent_invalidatepage(struct extent_io_tree *tree,
+			  struct page *page, unsigned long offset);
+bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start,
+			       u64 *end, u64 max_bytes,
+			       struct extent_state **cached_state);
+
+/* This should be reworked in the future and put elsewhere. */
+int get_state_failrec(struct extent_io_tree *tree, u64 start,
+		      struct io_failure_record **failrec);
+int set_state_failrec(struct extent_io_tree *tree, u64 start,
+		      struct io_failure_record *failrec);
+void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
+		u64 end);
+int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
+				struct io_failure_record **failrec_ret);
+int free_io_failure(struct extent_io_tree *failure_tree,
+		    struct extent_io_tree *io_tree,
+		    struct io_failure_record *rec);
+int clean_io_failure(struct btrfs_fs_info *fs_info,
+		     struct extent_io_tree *failure_tree,
+		     struct extent_io_tree *io_tree, u64 start,
+		     struct page *page, u64 ino, unsigned int pg_offset);
+
+#endif /* BTRFS_EXTENT_IO_TREE_H */
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 49cb26fa7c63..153f71a5bba9 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -54,7 +54,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 static int find_next_key(struct btrfs_path *path, int level,
 			 struct btrfs_key *key);
 
-static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits)
+static int block_group_bits(struct btrfs_block_group *cache, u64 bits)
 {
 	return (cache->flags & bits) == bits;
 }
@@ -70,13 +70,13 @@ int btrfs_add_excluded_extent(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
-void btrfs_free_excluded_extents(struct btrfs_block_group_cache *cache)
+void btrfs_free_excluded_extents(struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	u64 start, end;
 
-	start = cache->key.objectid;
-	end = start + cache->key.offset - 1;
+	start = cache->start;
+	end = start + cache->length - 1;
 
 	clear_extent_bits(&fs_info->freed_extents[0],
 			  start, end, EXTENT_UPTODATE);
@@ -1306,8 +1306,10 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
 int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 			 u64 num_bytes, u64 *actual_bytes)
 {
-	int ret;
+	int ret = 0;
 	u64 discarded_bytes = 0;
+	u64 end = bytenr + num_bytes;
+	u64 cur = bytenr;
 	struct btrfs_bio *bbio = NULL;
 
 
@@ -1316,15 +1318,23 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 	 * associated to its stripes that don't go away while we are discarding.
 	 */
 	btrfs_bio_counter_inc_blocked(fs_info);
-	/* Tell the block device(s) that the sectors can be discarded */
-	ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, bytenr, &num_bytes,
-			      &bbio, 0);
-	/* Error condition is -ENOMEM */
-	if (!ret) {
-		struct btrfs_bio_stripe *stripe = bbio->stripes;
+	while (cur < end) {
+		struct btrfs_bio_stripe *stripe;
 		int i;
 
+		num_bytes = end - cur;
+		/* Tell the block device(s) that the sectors can be discarded */
+		ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, cur,
+				      &num_bytes, &bbio, 0);
+		/*
+		 * Error can be -ENOMEM, -ENOENT (no such chunk mapping) or
+		 * -EOPNOTSUPP. For any such error, @num_bytes is not updated,
+		 * thus we can't continue anyway.
+		 */
+		if (ret < 0)
+			goto out;
 
+		stripe = bbio->stripes;
 		for (i = 0; i < bbio->num_stripes; i++, stripe++) {
 			u64 bytes;
 			struct request_queue *req_q;
@@ -1341,10 +1351,19 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 						  stripe->physical,
 						  stripe->length,
 						  &bytes);
-			if (!ret)
+			if (!ret) {
 				discarded_bytes += bytes;
-			else if (ret != -EOPNOTSUPP)
-				break; /* Logic errors or -ENOMEM, or -EIO but I don't know how that could happen JDM */
+			} else if (ret != -EOPNOTSUPP) {
+				/*
+				 * Logic errors or -ENOMEM, or -EIO, but
+				 * unlikely to happen.
+				 *
+				 * And since there are two loops, explicitly
+				 * go to out to avoid confusion.
+				 */
+				btrfs_put_bbio(bbio);
+				goto out;
+			}
 
 			/*
 			 * Just in case we get back EOPNOTSUPP for some reason,
@@ -1354,7 +1373,9 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 			ret = 0;
 		}
 		btrfs_put_bbio(bbio);
+		cur += num_bytes;
 	}
+out:
 	btrfs_bio_counter_dec(fs_info);
 
 	if (actual_bytes)
@@ -2516,7 +2537,7 @@ int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 
 int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	int readonly = 0;
 
 	block_group = btrfs_lookup_block_group(fs_info, bytenr);
@@ -2546,7 +2567,7 @@ static u64 get_alloc_profile_by_root(struct btrfs_root *root, int data)
 
 static u64 first_logical_byte(struct btrfs_fs_info *fs_info, u64 search_start)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	u64 bytenr;
 
 	spin_lock(&fs_info->block_group_cache_lock);
@@ -2560,13 +2581,13 @@ static u64 first_logical_byte(struct btrfs_fs_info *fs_info, u64 search_start)
 	if (!cache)
 		return 0;
 
-	bytenr = cache->key.objectid;
+	bytenr = cache->start;
 	btrfs_put_block_group(cache);
 
 	return bytenr;
 }
 
-static int pin_down_extent(struct btrfs_block_group_cache *cache,
+static int pin_down_extent(struct btrfs_block_group *cache,
 			   u64 bytenr, u64 num_bytes, int reserved)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
@@ -2590,13 +2611,12 @@ static int pin_down_extent(struct btrfs_block_group_cache *cache,
 	return 0;
 }
 
-/*
- * this function must be called within transaction
- */
 int btrfs_pin_extent(struct btrfs_fs_info *fs_info,
 		     u64 bytenr, u64 num_bytes, int reserved)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
+
+	ASSERT(fs_info->running_transaction);
 
 	cache = btrfs_lookup_block_group(fs_info, bytenr);
 	BUG_ON(!cache); /* Logic error */
@@ -2613,7 +2633,7 @@ int btrfs_pin_extent(struct btrfs_fs_info *fs_info,
 int btrfs_pin_extent_for_log_replay(struct btrfs_fs_info *fs_info,
 				    u64 bytenr, u64 num_bytes)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	int ret;
 
 	cache = btrfs_lookup_block_group(fs_info, bytenr);
@@ -2640,7 +2660,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
 				   u64 start, u64 num_bytes)
 {
 	int ret;
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_caching_control *caching_ctl;
 
 	block_group = btrfs_lookup_block_group(fs_info, start);
@@ -2652,7 +2672,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
 
 	if (!caching_ctl) {
 		/* Logic error */
-		BUG_ON(!btrfs_block_group_cache_done(block_group));
+		BUG_ON(!btrfs_block_group_done(block_group));
 		ret = btrfs_remove_free_space(block_group, start, num_bytes);
 	} else {
 		mutex_lock(&caching_ctl->mutex);
@@ -2717,7 +2737,7 @@ int btrfs_exclude_logged_extents(struct extent_buffer *eb)
 }
 
 static void
-btrfs_inc_block_group_reservations(struct btrfs_block_group_cache *bg)
+btrfs_inc_block_group_reservations(struct btrfs_block_group *bg)
 {
 	atomic_inc(&bg->reservations);
 }
@@ -2726,14 +2746,14 @@ void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_caching_control *next;
 	struct btrfs_caching_control *caching_ctl;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 
 	down_write(&fs_info->commit_root_sem);
 
 	list_for_each_entry_safe(caching_ctl, next,
 				 &fs_info->caching_block_groups, list) {
 		cache = caching_ctl->block_group;
-		if (btrfs_block_group_cache_done(cache)) {
+		if (btrfs_block_group_done(cache)) {
 			cache->last_byte_to_unpin = (u64)-1;
 			list_del_init(&caching_ctl->list);
 			btrfs_put_caching_control(caching_ctl);
@@ -2785,7 +2805,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 			      u64 start, u64 end,
 			      const bool return_free_space)
 {
-	struct btrfs_block_group_cache *cache = NULL;
+	struct btrfs_block_group *cache = NULL;
 	struct btrfs_space_info *space_info;
 	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
 	struct btrfs_free_cluster *cluster = NULL;
@@ -2797,7 +2817,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 	while (start <= end) {
 		readonly = false;
 		if (!cache ||
-		    start >= cache->key.objectid + cache->key.offset) {
+		    start >= cache->start + cache->length) {
 			if (cache)
 				btrfs_put_block_group(cache);
 			total_unpinned = 0;
@@ -2810,7 +2830,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 			empty_cluster <<= 1;
 		}
 
-		len = cache->key.objectid + cache->key.offset - start;
+		len = cache->start + cache->length - start;
 		len = min(len, end + 1 - start);
 
 		if (start < cache->last_byte_to_unpin) {
@@ -2880,7 +2900,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_block_group_cache *block_group, *tmp;
+	struct btrfs_block_group *block_group, *tmp;
 	struct list_head *deleted_bgs;
 	struct extent_io_tree *unpin;
 	u64 start;
@@ -2926,8 +2946,8 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
 		ret = -EROFS;
 		if (!trans->aborted)
 			ret = btrfs_discard_extent(fs_info,
-						   block_group->key.objectid,
-						   block_group->key.offset,
+						   block_group->start,
+						   block_group->length,
 						   &trimmed);
 
 		list_del_init(&block_group->bg_list);
@@ -3262,7 +3282,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 	}
 
 	if (last_ref && btrfs_header_generation(buf) == trans->transid) {
-		struct btrfs_block_group_cache *cache;
+		struct btrfs_block_group *cache;
 
 		if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
 			ret = check_ref_cleanup(trans, buf->start);
@@ -3349,15 +3369,14 @@ enum btrfs_loop_type {
 };
 
 static inline void
-btrfs_lock_block_group(struct btrfs_block_group_cache *cache,
+btrfs_lock_block_group(struct btrfs_block_group *cache,
 		       int delalloc)
 {
 	if (delalloc)
 		down_read(&cache->data_rwsem);
 }
 
-static inline void
-btrfs_grab_block_group(struct btrfs_block_group_cache *cache,
+static inline void btrfs_grab_block_group(struct btrfs_block_group *cache,
 		       int delalloc)
 {
 	btrfs_get_block_group(cache);
@@ -3365,12 +3384,12 @@ btrfs_grab_block_group(struct btrfs_block_group_cache *cache,
 		down_read(&cache->data_rwsem);
 }
 
-static struct btrfs_block_group_cache *
-btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
+static struct btrfs_block_group *btrfs_lock_cluster(
+		   struct btrfs_block_group *block_group,
 		   struct btrfs_free_cluster *cluster,
 		   int delalloc)
 {
-	struct btrfs_block_group_cache *used_bg = NULL;
+	struct btrfs_block_group *used_bg = NULL;
 
 	spin_lock(&cluster->refill_lock);
 	while (1) {
@@ -3404,7 +3423,7 @@ btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
 }
 
 static inline void
-btrfs_release_block_group(struct btrfs_block_group_cache *cache,
+btrfs_release_block_group(struct btrfs_block_group *cache,
 			 int delalloc)
 {
 	if (delalloc)
@@ -3475,12 +3494,12 @@ struct find_free_extent_ctl {
  * Return >0 to inform caller that we find nothing
  * Return 0 means we have found a location and set ffe_ctl->found_offset.
  */
-static int find_free_extent_clustered(struct btrfs_block_group_cache *bg,
+static int find_free_extent_clustered(struct btrfs_block_group *bg,
 		struct btrfs_free_cluster *last_ptr,
 		struct find_free_extent_ctl *ffe_ctl,
-		struct btrfs_block_group_cache **cluster_bg_ret)
+		struct btrfs_block_group **cluster_bg_ret)
 {
-	struct btrfs_block_group_cache *cluster_bg;
+	struct btrfs_block_group *cluster_bg;
 	u64 aligned_cluster;
 	u64 offset;
 	int ret;
@@ -3493,7 +3512,7 @@ static int find_free_extent_clustered(struct btrfs_block_group_cache *bg,
 		goto release_cluster;
 
 	offset = btrfs_alloc_from_cluster(cluster_bg, last_ptr,
-			ffe_ctl->num_bytes, cluster_bg->key.objectid,
+			ffe_ctl->num_bytes, cluster_bg->start,
 			&ffe_ctl->max_extent_size);
 	if (offset) {
 		/* We have a block, we're done */
@@ -3579,7 +3598,7 @@ refill_cluster:
  * Return 0 when we found an free extent and set ffe_ctrl->found_offset
  * Return -EAGAIN to inform caller that we need to re-search this block group
  */
-static int find_free_extent_unclustered(struct btrfs_block_group_cache *bg,
+static int find_free_extent_unclustered(struct btrfs_block_group *bg,
 		struct btrfs_free_cluster *last_ptr,
 		struct find_free_extent_ctl *ffe_ctl)
 {
@@ -3781,7 +3800,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
 {
 	int ret = 0;
 	struct btrfs_free_cluster *last_ptr = NULL;
-	struct btrfs_block_group_cache *block_group = NULL;
+	struct btrfs_block_group *block_group = NULL;
 	struct find_free_extent_ctl ffe_ctl = {0};
 	struct btrfs_space_info *space_info;
 	bool use_cluster = true;
@@ -3904,7 +3923,7 @@ search:
 			continue;
 
 		btrfs_grab_block_group(block_group, delalloc);
-		ffe_ctl.search_start = block_group->key.objectid;
+		ffe_ctl.search_start = block_group->start;
 
 		/*
 		 * this can happen if we end up cycling through all the
@@ -3935,7 +3954,7 @@ search:
 		}
 
 have_block_group:
-		ffe_ctl.cached = btrfs_block_group_cache_done(block_group);
+		ffe_ctl.cached = btrfs_block_group_done(block_group);
 		if (unlikely(!ffe_ctl.cached)) {
 			ffe_ctl.have_caching_bg = true;
 			ret = btrfs_cache_block_group(block_group, 0);
@@ -3951,7 +3970,7 @@ have_block_group:
 		 * lets look there
 		 */
 		if (last_ptr && use_cluster) {
-			struct btrfs_block_group_cache *cluster_bg = NULL;
+			struct btrfs_block_group *cluster_bg = NULL;
 
 			ret = find_free_extent_clustered(block_group, last_ptr,
 							 &ffe_ctl, &cluster_bg);
@@ -3984,7 +4003,7 @@ checks:
 
 		/* move on to the next group */
 		if (ffe_ctl.search_start + num_bytes >
-		    block_group->key.objectid + block_group->key.offset) {
+		    block_group->start + block_group->length) {
 			btrfs_add_free_space(block_group, ffe_ctl.found_offset,
 					     num_bytes);
 			goto loop;
@@ -4133,7 +4152,7 @@ static int __btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
 					u64 start, u64 len,
 					int pin, int delalloc)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	int ret = 0;
 
 	cache = btrfs_lookup_block_group(fs_info, start);
@@ -4366,7 +4385,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret;
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_space_info *space_info;
 
 	/*
@@ -5436,7 +5455,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 
 	btrfs_assert_tree_locked(parent);
 	parent_level = btrfs_header_level(parent);
-	extent_buffer_get(parent);
+	atomic_inc(&parent->refs);
 	path->nodes[parent_level] = parent;
 	path->slots[parent_level] = btrfs_header_nritems(parent);
 
@@ -5480,7 +5499,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
  */
 u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	u64 free_bytes = 0;
 	int factor;
 
@@ -5498,9 +5517,8 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
 		}
 
 		factor = btrfs_bg_type_to_factor(block_group->flags);
-		free_bytes += (block_group->key.offset -
-			       btrfs_block_group_used(&block_group->item)) *
-			       factor;
+		free_bytes += (block_group->length -
+			       block_group->used) * factor;
 
 		spin_unlock(&block_group->lock);
 	}
@@ -5623,7 +5641,7 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed)
  */
 int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 {
-	struct btrfs_block_group_cache *cache = NULL;
+	struct btrfs_block_group *cache = NULL;
 	struct btrfs_device *device;
 	struct list_head *devices;
 	u64 group_trimmed;
@@ -5647,16 +5665,16 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 
 	cache = btrfs_lookup_first_block_group(fs_info, range->start);
 	for (; cache; cache = btrfs_next_block_group(cache)) {
-		if (cache->key.objectid >= range_end) {
+		if (cache->start >= range_end) {
 			btrfs_put_block_group(cache);
 			break;
 		}
 
-		start = max(range->start, cache->key.objectid);
-		end = min(range_end, cache->key.objectid + cache->key.offset);
+		start = max(range->start, cache->start);
+		end = min(range_end, cache->start + cache->length);
 
 		if (end - start >= range->minlen) {
-			if (!btrfs_block_group_cache_done(cache)) {
+			if (!btrfs_block_group_done(cache)) {
 				ret = btrfs_cache_block_group(cache, 0);
 				if (ret) {
 					bg_failed++;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index cceaf05aada2..eb8bd0258360 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -14,6 +14,7 @@
 #include <linux/prefetch.h>
 #include <linux/cleancache.h>
 #include "extent_io.h"
+#include "extent-io-tree.h"
 #include "extent_map.h"
 #include "ctree.h"
 #include "btrfs_inode.h"
@@ -59,12 +60,23 @@ void btrfs_leak_debug_del(struct list_head *entry)
 	spin_unlock_irqrestore(&leak_lock, flags);
 }
 
-static inline
-void btrfs_leak_debug_check(void)
+static inline void btrfs_extent_buffer_leak_debug_check(void)
 {
-	struct extent_state *state;
 	struct extent_buffer *eb;
 
+	while (!list_empty(&buffers)) {
+		eb = list_entry(buffers.next, struct extent_buffer, leak_list);
+		pr_err("BTRFS: buffer leak start %llu len %lu refs %d bflags %lu\n",
+		       eb->start, eb->len, atomic_read(&eb->refs), eb->bflags);
+		list_del(&eb->leak_list);
+		kmem_cache_free(extent_buffer_cache, eb);
+	}
+}
+
+static inline void btrfs_extent_state_leak_debug_check(void)
+{
+	struct extent_state *state;
+
 	while (!list_empty(&states)) {
 		state = list_entry(states.next, struct extent_state, leak_list);
 		pr_err("BTRFS: state leak: start %llu end %llu state %u in tree %d refs %d\n",
@@ -74,14 +86,6 @@ void btrfs_leak_debug_check(void)
 		list_del(&state->leak_list);
 		kmem_cache_free(extent_state_cache, state);
 	}
-
-	while (!list_empty(&buffers)) {
-		eb = list_entry(buffers.next, struct extent_buffer, leak_list);
-		pr_err("BTRFS: buffer leak start %llu len %lu refs %d bflags %lu\n",
-		       eb->start, eb->len, atomic_read(&eb->refs), eb->bflags);
-		list_del(&eb->leak_list);
-		kmem_cache_free(extent_buffer_cache, eb);
-	}
 }
 
 #define btrfs_debug_check_extent_io_range(tree, start, end)		\
@@ -105,7 +109,8 @@ static inline void __btrfs_debug_check_extent_io_range(const char *caller,
 #else
 #define btrfs_leak_debug_add(new, head)	do {} while (0)
 #define btrfs_leak_debug_del(entry)	do {} while (0)
-#define btrfs_leak_debug_check()	do {} while (0)
+#define btrfs_extent_buffer_leak_debug_check()	do {} while (0)
+#define btrfs_extent_state_leak_debug_check()	do {} while (0)
 #define btrfs_debug_check_extent_io_range(c, s, e)	do {} while (0)
 #endif
 
@@ -196,19 +201,23 @@ static int __must_check flush_write_bio(struct extent_page_data *epd)
 	return ret;
 }
 
-int __init extent_io_init(void)
+int __init extent_state_cache_init(void)
 {
 	extent_state_cache = kmem_cache_create("btrfs_extent_state",
 			sizeof(struct extent_state), 0,
 			SLAB_MEM_SPREAD, NULL);
 	if (!extent_state_cache)
 		return -ENOMEM;
+	return 0;
+}
 
+int __init extent_io_init(void)
+{
 	extent_buffer_cache = kmem_cache_create("btrfs_extent_buffer",
 			sizeof(struct extent_buffer), 0,
 			SLAB_MEM_SPREAD, NULL);
 	if (!extent_buffer_cache)
-		goto free_state_cache;
+		return -ENOMEM;
 
 	if (bioset_init(&btrfs_bioset, BIO_POOL_SIZE,
 			offsetof(struct btrfs_io_bio, bio),
@@ -226,23 +235,24 @@ free_bioset:
 free_buffer_cache:
 	kmem_cache_destroy(extent_buffer_cache);
 	extent_buffer_cache = NULL;
+	return -ENOMEM;
+}
 
-free_state_cache:
+void __cold extent_state_cache_exit(void)
+{
+	btrfs_extent_state_leak_debug_check();
 	kmem_cache_destroy(extent_state_cache);
-	extent_state_cache = NULL;
-	return -ENOMEM;
 }
 
 void __cold extent_io_exit(void)
 {
-	btrfs_leak_debug_check();
+	btrfs_extent_buffer_leak_debug_check();
 
 	/*
 	 * Make sure all delayed rcu free are flushed before we
 	 * destroy caches.
 	 */
 	rcu_barrier();
-	kmem_cache_destroy(extent_state_cache);
 	kmem_cache_destroy(extent_buffer_cache);
 	bioset_exit(&btrfs_bioset);
 }
@@ -1676,9 +1686,9 @@ out:
  *
  * true is returned if we find something, false if nothing was in the tree
  */
-static noinline bool find_delalloc_range(struct extent_io_tree *tree,
-					u64 *start, u64 *end, u64 max_bytes,
-					struct extent_state **cached_state)
+bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start,
+			       u64 *end, u64 max_bytes,
+			       struct extent_state **cached_state)
 {
 	struct rb_node *node;
 	struct extent_state *state;
@@ -1796,8 +1806,8 @@ again:
 	/* step one, find a bunch of delalloc bytes starting at start */
 	delalloc_start = *start;
 	delalloc_end = 0;
-	found = find_delalloc_range(tree, &delalloc_start, &delalloc_end,
-				    max_bytes, &cached_state);
+	found = btrfs_find_delalloc_range(tree, &delalloc_start, &delalloc_end,
+					  max_bytes, &cached_state);
 	if (!found || delalloc_end <= *start) {
 		*start = delalloc_start;
 		*end = delalloc_end;
@@ -1899,7 +1909,7 @@ static int __process_pages_contig(struct address_space *mapping,
 			if (page_ops & PAGE_SET_PRIVATE2)
 				SetPagePrivate2(pages[i]);
 
-			if (pages[i] == locked_page) {
+			if (locked_page && pages[i] == locked_page) {
 				put_page(pages[i]);
 				pages_locked++;
 				continue;
@@ -2014,8 +2024,8 @@ out:
  * set the private field for a given byte offset in the tree.  If there isn't
  * an extent_state there already, this does nothing.
  */
-static noinline int set_state_failrec(struct extent_io_tree *tree, u64 start,
-		struct io_failure_record *failrec)
+int set_state_failrec(struct extent_io_tree *tree, u64 start,
+		      struct io_failure_record *failrec)
 {
 	struct rb_node *node;
 	struct extent_state *state;
@@ -2042,8 +2052,8 @@ out:
 	return ret;
 }
 
-static noinline int get_state_failrec(struct extent_io_tree *tree, u64 start,
-		struct io_failure_record **failrec)
+int get_state_failrec(struct extent_io_tree *tree, u64 start,
+		      struct io_failure_record **failrec)
 {
 	struct rb_node *node;
 	struct extent_state *state;
@@ -2534,7 +2544,6 @@ struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
 	bio = btrfs_io_bio_alloc(1);
 	bio->bi_end_io = endio_func;
 	bio->bi_iter.bi_sector = failrec->logical >> 9;
-	bio_set_dev(bio, fs_info->fs_devices->latest_bdev);
 	bio->bi_iter.bi_size = 0;
 	bio->bi_private = data;
 
@@ -2920,7 +2929,6 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size)
  *              a contiguous page to the previous one
  * @size:	portion of page that we want to write
  * @offset:	starting offset in the page
- * @bdev:	attach newly created bios to this bdev
  * @bio_ret:	must be valid pointer, newly allocated bio will be stored there
  * @end_io_func:     end_io callback for new bio
  * @mirror_num:	     desired mirror to read/write
@@ -2931,7 +2939,6 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 			      struct writeback_control *wbc,
 			      struct page *page, u64 offset,
 			      size_t size, unsigned long pg_offset,
-			      struct block_device *bdev,
 			      struct bio **bio_ret,
 			      bio_end_io_t end_io_func,
 			      int mirror_num,
@@ -2977,13 +2984,16 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 	}
 
 	bio = btrfs_bio_alloc(offset);
-	bio_set_dev(bio, bdev);
 	bio_add_page(bio, page, page_size, pg_offset);
 	bio->bi_end_io = end_io_func;
 	bio->bi_private = tree;
 	bio->bi_write_hint = page->mapping->host->i_write_hint;
 	bio->bi_opf = opf;
 	if (wbc) {
+		struct block_device *bdev;
+
+		bdev = BTRFS_I(page->mapping->host)->root->fs_info->fs_devices->latest_bdev;
+		bio_set_dev(bio, bdev);
 		wbc_init_bio(wbc, bio);
 		wbc_account_cgroup_owner(wbc, page, page_size);
 	}
@@ -3065,7 +3075,6 @@ static int __do_readpage(struct extent_io_tree *tree,
 	u64 block_start;
 	u64 cur_end;
 	struct extent_map *em;
-	struct block_device *bdev;
 	int ret = 0;
 	int nr = 0;
 	size_t pg_offset = 0;
@@ -3142,7 +3151,6 @@ static int __do_readpage(struct extent_io_tree *tree,
 			offset = em->block_start + extent_offset;
 			disk_io_size = iosize;
 		}
-		bdev = em->bdev;
 		block_start = em->block_start;
 		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 			block_start = EXTENT_MAP_HOLE;
@@ -3232,7 +3240,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 
 		ret = submit_extent_page(REQ_OP_READ | read_flags, tree, NULL,
 					 page, offset, disk_io_size,
-					 pg_offset, bdev, bio,
+					 pg_offset, bio,
 					 end_bio_extent_readpage, mirror_num,
 					 *bio_flags,
 					 this_bio_flag,
@@ -3409,7 +3417,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 				 struct extent_page_data *epd,
 				 loff_t i_size,
 				 unsigned long nr_written,
-				 unsigned int write_flags, int *nr_ret)
+				 int *nr_ret)
 {
 	struct extent_io_tree *tree = epd->tree;
 	u64 start = page_offset(page);
@@ -3420,11 +3428,11 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 	u64 block_start;
 	u64 iosize;
 	struct extent_map *em;
-	struct block_device *bdev;
 	size_t pg_offset = 0;
 	size_t blocksize;
 	int ret = 0;
 	int nr = 0;
+	const unsigned int write_flags = wbc_to_write_flags(wbc);
 	bool compressed;
 
 	ret = btrfs_writepage_cow_fixup(page, start, page_end);
@@ -3478,7 +3486,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 		iosize = min(em_end - cur, end - cur + 1);
 		iosize = ALIGN(iosize, blocksize);
 		offset = em->block_start + extent_offset;
-		bdev = em->bdev;
 		block_start = em->block_start;
 		compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
 		free_extent_map(em);
@@ -3520,7 +3527,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 
 		ret = submit_extent_page(REQ_OP_WRITE | write_flags, tree, wbc,
 					 page, offset, iosize, pg_offset,
-					 bdev, &epd->bio,
+					 &epd->bio,
 					 end_bio_extent_writepage,
 					 0, 0, 0, false);
 		if (ret) {
@@ -3558,11 +3565,8 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	size_t pg_offset = 0;
 	loff_t i_size = i_size_read(inode);
 	unsigned long end_index = i_size >> PAGE_SHIFT;
-	unsigned int write_flags = 0;
 	unsigned long nr_written = 0;
 
-	write_flags = wbc_to_write_flags(wbc);
-
 	trace___extent_writepage(page, inode, wbc);
 
 	WARN_ON(!PageLocked(page));
@@ -3600,7 +3604,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	}
 
 	ret = __extent_writepage_io(inode, page, wbc, epd,
-				    i_size, nr_written, write_flags, &nr);
+				    i_size, nr_written, &nr);
 	if (ret == 1)
 		goto done_unlocked;
 
@@ -3849,7 +3853,6 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 			struct extent_page_data *epd)
 {
 	struct btrfs_fs_info *fs_info = eb->fs_info;
-	struct block_device *bdev = fs_info->fs_devices->latest_bdev;
 	struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
 	u64 offset = eb->start;
 	u32 nritems;
@@ -3884,7 +3887,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 		clear_page_dirty_for_io(p);
 		set_page_writeback(p);
 		ret = submit_extent_page(REQ_OP_WRITE | write_flags, tree, wbc,
-					 p, offset, PAGE_SIZE, 0, bdev,
+					 p, offset, PAGE_SIZE, 0,
 					 &epd->bio,
 					 end_bio_extent_buffer_writepage,
 					 0, 0, 0, false);
@@ -4121,7 +4124,7 @@ retry:
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
-			done_index = page->index;
+			done_index = page->index + 1;
 			/*
 			 * At this point we hold neither the i_pages lock nor
 			 * the page lock: the page may be truncated or
@@ -4156,16 +4159,6 @@ retry:
 
 			ret = __extent_writepage(page, wbc, epd);
 			if (ret < 0) {
-				/*
-				 * done_index is set past this page,
-				 * so media errors will not choke
-				 * background writeout for the entire
-				 * file. This has consequences for
-				 * range_cyclic semantics (ie. it may
-				 * not be suitable for data integrity
-				 * writeout).
-				 */
-				done_index = page->index + 1;
 				done = 1;
 				break;
 			}
@@ -4240,8 +4233,12 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
 		.nr_to_write	= nr_pages * 2,
 		.range_start	= start,
 		.range_end	= end + 1,
+		/* We're called from an async helper function */
+		.punt_to_cgroup	= 1,
+		.no_cgroup_owner = 1,
 	};
 
+	wbc_attach_fdatawrite_inode(&wbc_writepages, inode);
 	while (start <= end) {
 		page = find_get_page(mapping, start >> PAGE_SHIFT);
 		if (clear_page_dirty_for_io(page))
@@ -4256,11 +4253,12 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
 	}
 
 	ASSERT(ret <= 0);
-	if (ret < 0) {
+	if (ret == 0)
+		ret = flush_write_bio(&epd);
+	else
 		end_write_bio(&epd, ret);
-		return ret;
-	}
-	ret = flush_write_bio(&epd);
+
+	wbc_detach_inode(&wbc_writepages);
 	return ret;
 }
 
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index cf3424d58fec..a8551a1f56e2 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -7,35 +7,6 @@
 #include <linux/refcount.h>
 #include "ulist.h"
 
-/* bits for the extent state */
-#define EXTENT_DIRTY		(1U << 0)
-#define EXTENT_UPTODATE		(1U << 1)
-#define EXTENT_LOCKED		(1U << 2)
-#define EXTENT_NEW		(1U << 3)
-#define EXTENT_DELALLOC		(1U << 4)
-#define EXTENT_DEFRAG		(1U << 5)
-#define EXTENT_BOUNDARY		(1U << 6)
-#define EXTENT_NODATASUM	(1U << 7)
-#define EXTENT_CLEAR_META_RESV	(1U << 8)
-#define EXTENT_NEED_WAIT	(1U << 9)
-#define EXTENT_DAMAGED		(1U << 10)
-#define EXTENT_NORESERVE	(1U << 11)
-#define EXTENT_QGROUP_RESERVED	(1U << 12)
-#define EXTENT_CLEAR_DATA_RESV	(1U << 13)
-#define EXTENT_DELALLOC_NEW	(1U << 14)
-#define EXTENT_DO_ACCOUNTING    (EXTENT_CLEAR_META_RESV | \
-				 EXTENT_CLEAR_DATA_RESV)
-#define EXTENT_CTLBITS		(EXTENT_DO_ACCOUNTING)
-
-/*
- * Redefined bits above which are used only in the device allocation tree,
- * shouldn't be using EXTENT_LOCKED / EXTENT_BOUNDARY / EXTENT_CLEAR_META_RESV
- * / EXTENT_CLEAR_DATA_RESV because they have special meaning to the bit
- * manipulation functions
- */
-#define CHUNK_ALLOCATED EXTENT_DIRTY
-#define CHUNK_TRIMMED   EXTENT_DEFRAG
-
 /*
  * flags for bio submission. The high bits indicate the compression
  * type for this bio
@@ -89,12 +60,11 @@ enum {
 #define BITMAP_LAST_BYTE_MASK(nbits) \
 	(BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
 
-struct extent_state;
 struct btrfs_root;
 struct btrfs_inode;
 struct btrfs_io_bio;
 struct io_failure_record;
-
+struct extent_io_tree;
 
 typedef blk_status_t (extent_submit_bio_start_t)(void *private_data,
 		struct bio *bio, u64 bio_offset);
@@ -111,47 +81,6 @@ struct extent_io_ops {
 				    int mirror);
 };
 
-enum {
-	IO_TREE_FS_INFO_FREED_EXTENTS0,
-	IO_TREE_FS_INFO_FREED_EXTENTS1,
-	IO_TREE_INODE_IO,
-	IO_TREE_INODE_IO_FAILURE,
-	IO_TREE_RELOC_BLOCKS,
-	IO_TREE_TRANS_DIRTY_PAGES,
-	IO_TREE_ROOT_DIRTY_LOG_PAGES,
-	IO_TREE_SELFTEST,
-};
-
-struct extent_io_tree {
-	struct rb_root state;
-	struct btrfs_fs_info *fs_info;
-	void *private_data;
-	u64 dirty_bytes;
-	bool track_uptodate;
-
-	/* Who owns this io tree, should be one of IO_TREE_* */
-	u8 owner;
-
-	spinlock_t lock;
-	const struct extent_io_ops *ops;
-};
-
-struct extent_state {
-	u64 start;
-	u64 end; /* inclusive */
-	struct rb_node rb_node;
-
-	/* ADD NEW ELEMENTS AFTER THIS */
-	wait_queue_head_t wq;
-	refcount_t refs;
-	unsigned state;
-
-	struct io_failure_record *failrec;
-
-#ifdef CONFIG_BTRFS_DEBUG
-	struct list_head leak_list;
-#endif
-};
 
 #define INLINE_EXTENT_BUFFER_PAGES 16
 #define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_SIZE)
@@ -259,152 +188,11 @@ typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode,
 					  u64 start, u64 len,
 					  int create);
 
-void extent_io_tree_init(struct btrfs_fs_info *fs_info,
-			 struct extent_io_tree *tree, unsigned int owner,
-			 void *private_data);
-void extent_io_tree_release(struct extent_io_tree *tree);
 int try_release_extent_mapping(struct page *page, gfp_t mask);
 int try_release_extent_buffer(struct page *page);
-int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		     struct extent_state **cached);
 
-static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
-{
-	return lock_extent_bits(tree, start, end, NULL);
-}
-
-int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 			  get_extent_t *get_extent, int mirror_num);
-int __init extent_io_init(void);
-void __cold extent_io_exit(void);
-
-u64 count_range_bits(struct extent_io_tree *tree,
-		     u64 *start, u64 search_end,
-		     u64 max_bytes, unsigned bits, int contig);
-
-void free_extent_state(struct extent_state *state);
-int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   unsigned bits, int filled,
-		   struct extent_state *cached_state);
-int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		unsigned bits, struct extent_changeset *changeset);
-int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		     unsigned bits, int wake, int delete,
-		     struct extent_state **cached);
-int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		     unsigned bits, int wake, int delete,
-		     struct extent_state **cached, gfp_t mask,
-		     struct extent_changeset *changeset);
-
-static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
-{
-	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL);
-}
-
-static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start,
-		u64 end, struct extent_state **cached)
-{
-	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
-				GFP_NOFS, NULL);
-}
-
-static inline int unlock_extent_cached_atomic(struct extent_io_tree *tree,
-		u64 start, u64 end, struct extent_state **cached)
-{
-	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
-				GFP_ATOMIC, NULL);
-}
-
-static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
-		u64 end, unsigned bits)
-{
-	int wake = 0;
-
-	if (bits & EXTENT_LOCKED)
-		wake = 1;
-
-	return clear_extent_bit(tree, start, end, bits, wake, 0, NULL);
-}
-
-int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-			   unsigned bits, struct extent_changeset *changeset);
-int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   unsigned bits, u64 *failed_start,
-		   struct extent_state **cached_state, gfp_t mask);
-int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end,
-			   unsigned bits);
-
-static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
-		u64 end, unsigned bits)
-{
-	return set_extent_bit(tree, start, end, bits, NULL, NULL, GFP_NOFS);
-}
-
-static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
-		u64 end, struct extent_state **cached_state)
-{
-	return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
-				cached_state, GFP_NOFS, NULL);
-}
-
-static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
-		u64 end, gfp_t mask)
-{
-	return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL,
-			      NULL, mask);
-}
-
-static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
-				     u64 end, struct extent_state **cached)
-{
-	return clear_extent_bit(tree, start, end,
-				EXTENT_DIRTY | EXTENT_DELALLOC |
-				EXTENT_DO_ACCOUNTING, 0, 0, cached);
-}
-
-int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		       unsigned bits, unsigned clear_bits,
-		       struct extent_state **cached_state);
-
-static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
-				      u64 end, unsigned int extra_bits,
-				      struct extent_state **cached_state)
-{
-	return set_extent_bit(tree, start, end,
-			      EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits,
-			      NULL, cached_state, GFP_NOFS);
-}
-
-static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
-		u64 end, struct extent_state **cached_state)
-{
-	return set_extent_bit(tree, start, end,
-			      EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
-			      NULL, cached_state, GFP_NOFS);
-}
-
-static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
-		u64 end)
-{
-	return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL,
-			GFP_NOFS);
-}
-
-static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start,
-		u64 end, struct extent_state **cached_state, gfp_t mask)
-{
-	return set_extent_bit(tree, start, end, EXTENT_UPTODATE, NULL,
-			      cached_state, mask);
-}
-
-int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
-			  u64 *start_ret, u64 *end_ret, unsigned bits,
-			  struct extent_state **cached_state);
-void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
-				 u64 *start_ret, u64 *end_ret, unsigned bits);
-int extent_invalidatepage(struct extent_io_tree *tree,
-			  struct page *page, unsigned long offset);
 int extent_write_full_page(struct page *page, struct writeback_control *wbc);
 int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
 			      int mode);
@@ -442,11 +230,6 @@ static inline int num_extent_pages(const struct extent_buffer *eb)
 	       (eb->start >> PAGE_SHIFT);
 }
 
-static inline void extent_buffer_get(struct extent_buffer *eb)
-{
-	atomic_inc(&eb->refs);
-}
-
 static inline int extent_buffer_uptodate(struct extent_buffer *eb)
 {
 	return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
@@ -508,10 +291,6 @@ struct btrfs_inode;
 int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 		      u64 length, u64 logical, struct page *page,
 		      unsigned int pg_offset, int mirror_num);
-int clean_io_failure(struct btrfs_fs_info *fs_info,
-		     struct extent_io_tree *failure_tree,
-		     struct extent_io_tree *io_tree, u64 start,
-		     struct page *page, u64 ino, unsigned int pg_offset);
 void end_extent_writepage(struct page *page, int err, u64 start, u64 end);
 int btrfs_repair_eb_io_failure(struct extent_buffer *eb, int mirror_num);
 
@@ -535,19 +314,12 @@ struct io_failure_record {
 };
 
 
-void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
-		u64 end);
-int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
-				struct io_failure_record **failrec_ret);
 bool btrfs_check_repairable(struct inode *inode, unsigned failed_bio_pages,
 			    struct io_failure_record *failrec, int fail_mirror);
 struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
 				    struct io_failure_record *failrec,
 				    struct page *page, int pg_offset, int icsum,
 				    bio_end_io_t *endio_func, void *data);
-int free_io_failure(struct extent_io_tree *failure_tree,
-		    struct extent_io_tree *io_tree,
-		    struct io_failure_record *rec);
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 bool find_lock_delalloc_range(struct inode *inode,
 			     struct page *locked_page, u64 *start,
@@ -555,5 +327,4 @@ bool find_lock_delalloc_range(struct inode *inode,
 #endif
 struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
 					       u64 start);
-
 #endif
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 9d30acca55e1..6f417ff68980 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -214,9 +214,13 @@ static int mergable_maps(struct extent_map *prev, struct extent_map *next)
 	ASSERT(next->block_start != EXTENT_MAP_DELALLOC &&
 	       prev->block_start != EXTENT_MAP_DELALLOC);
 
+	if (prev->map_lookup || next->map_lookup)
+		ASSERT(test_bit(EXTENT_FLAG_FS_MAPPING, &prev->flags) &&
+		       test_bit(EXTENT_FLAG_FS_MAPPING, &next->flags));
+
 	if (extent_map_end(prev) == next->start &&
 	    prev->flags == next->flags &&
-	    prev->bdev == next->bdev &&
+	    prev->map_lookup == next->map_lookup &&
 	    ((next->block_start == EXTENT_MAP_HOLE &&
 	      prev->block_start == EXTENT_MAP_HOLE) ||
 	     (next->block_start == EXTENT_MAP_INLINE &&
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index 473f039fcd7c..8e217337dff9 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -42,15 +42,8 @@ struct extent_map {
 	u64 block_len;
 	u64 generation;
 	unsigned long flags;
-	union {
-		struct block_device *bdev;
-
-		/*
-		 * used for chunk mappings
-		 * flags & EXTENT_FLAG_FS_MAPPING must be set
-		 */
-		struct map_lookup *map_lookup;
-	};
+	/* Used for chunk mappings, flag EXTENT_FLAG_FS_MAPPING must be set */
+	struct map_lookup *map_lookup;
 	refcount_t refs;
 	unsigned int compress_type;
 	struct list_head list;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 1a599f50837b..3270a40b0777 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -945,7 +945,6 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 	u8 type = btrfs_file_extent_type(leaf, fi);
 	int compress_type = btrfs_file_extent_compression(leaf, fi);
 
-	em->bdev = fs_info->fs_devices->latest_bdev;
 	btrfs_item_key_to_cpu(leaf, &key, slot);
 	extent_start = key.offset;
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 435a502a3226..0cb43b682789 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -296,7 +296,7 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 	key.objectid = defrag->ino;
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
-	inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, inode_root);
 	if (IS_ERR(inode)) {
 		ret = PTR_ERR(inode);
 		goto cleanup;
@@ -667,7 +667,6 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
 			}
 
 			split->generation = gen;
-			split->bdev = em->bdev;
 			split->flags = flags;
 			split->compress_type = em->compress_type;
 			replace_extent_mapping(em_tree, em, split, modified);
@@ -680,7 +679,6 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
 
 			split->start = start + len;
 			split->len = em->start + em->len - (start + len);
-			split->bdev = em->bdev;
 			split->flags = flags;
 			split->compress_type = em->compress_type;
 			split->generation = gen;
@@ -1636,6 +1634,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
 			break;
 		}
 
+		only_release_metadata = false;
 		sector_offset = pos & (fs_info->sectorsize - 1);
 		reserve_bytes = round_up(write_bytes + sector_offset,
 				fs_info->sectorsize);
@@ -1791,7 +1790,6 @@ again:
 			set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
 				       lockend, EXTENT_NORESERVE, NULL,
 				       NULL, GFP_NOFS);
-			only_release_metadata = false;
 		}
 
 		btrfs_drop_pages(pages, num_pages);
@@ -1903,9 +1901,10 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	    (iocb->ki_flags & IOCB_NOWAIT))
 		return -EOPNOTSUPP;
 
-	if (!inode_trylock(inode)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock(inode))
 			return -EAGAIN;
+	} else {
 		inode_lock(inode);
 	}
 
@@ -2359,7 +2358,6 @@ out:
 		hole_em->block_start = EXTENT_MAP_HOLE;
 		hole_em->block_len = 0;
 		hole_em->orig_block_len = 0;
-		hole_em->bdev = fs_info->fs_devices->latest_bdev;
 		hole_em->compress_type = BTRFS_COMPRESS_NONE;
 		hole_em->generation = trans->transid;
 
@@ -3350,29 +3348,30 @@ out:
 	return ret;
 }
 
-static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
+static loff_t find_desired_extent(struct inode *inode, loff_t offset,
+				  int whence)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct extent_map *em = NULL;
 	struct extent_state *cached_state = NULL;
+	loff_t i_size = inode->i_size;
 	u64 lockstart;
 	u64 lockend;
 	u64 start;
 	u64 len;
 	int ret = 0;
 
-	if (inode->i_size == 0)
+	if (i_size == 0 || offset >= i_size)
 		return -ENXIO;
 
 	/*
-	 * *offset can be negative, in this case we start finding DATA/HOLE from
+	 * offset can be negative, in this case we start finding DATA/HOLE from
 	 * the very start of the file.
 	 */
-	start = max_t(loff_t, 0, *offset);
+	start = max_t(loff_t, 0, offset);
 
 	lockstart = round_down(start, fs_info->sectorsize);
-	lockend = round_up(i_size_read(inode),
-			   fs_info->sectorsize);
+	lockend = round_up(i_size, fs_info->sectorsize);
 	if (lockend <= lockstart)
 		lockend = lockstart + fs_info->sectorsize;
 	lockend--;
@@ -3381,7 +3380,7 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			 &cached_state);
 
-	while (start < inode->i_size) {
+	while (start < i_size) {
 		em = btrfs_get_extent_fiemap(BTRFS_I(inode), start, len);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR(em);
@@ -3404,46 +3403,39 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
 		cond_resched();
 	}
 	free_extent_map(em);
-	if (!ret) {
-		if (whence == SEEK_DATA && start >= inode->i_size)
-			ret = -ENXIO;
-		else
-			*offset = min_t(loff_t, start, inode->i_size);
-	}
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			     &cached_state);
-	return ret;
+	if (ret) {
+		offset = ret;
+	} else {
+		if (whence == SEEK_DATA && start >= i_size)
+			offset = -ENXIO;
+		else
+			offset = min_t(loff_t, start, i_size);
+	}
+
+	return offset;
 }
 
 static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
-	int ret;
 
-	inode_lock(inode);
 	switch (whence) {
-	case SEEK_END:
-	case SEEK_CUR:
-		offset = generic_file_llseek(file, offset, whence);
-		goto out;
+	default:
+		return generic_file_llseek(file, offset, whence);
 	case SEEK_DATA:
 	case SEEK_HOLE:
-		if (offset >= i_size_read(inode)) {
-			inode_unlock(inode);
-			return -ENXIO;
-		}
-
-		ret = find_desired_extent(inode, &offset, whence);
-		if (ret) {
-			inode_unlock(inode);
-			return ret;
-		}
+		inode_lock_shared(inode);
+		offset = find_desired_extent(inode, offset, whence);
+		inode_unlock_shared(inode);
+		break;
 	}
 
-	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
-out:
-	inode_unlock(inode);
-	return offset;
+	if (offset < 0)
+		return offset;
+
+	return vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 }
 
 static int btrfs_file_open(struct inode *inode, struct file *filp)
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index d54dcd0ab230..3283da419200 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -78,7 +78,7 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
 	 * sure NOFS is set to keep us from deadlocking.
 	 */
 	nofs_flag = memalloc_nofs_save();
-	inode = btrfs_iget_path(fs_info->sb, &location, root, NULL, path);
+	inode = btrfs_iget_path(fs_info->sb, &location, root, path);
 	btrfs_release_path(path);
 	memalloc_nofs_restore(nofs_flag);
 	if (IS_ERR(inode))
@@ -91,8 +91,7 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
 	return inode;
 }
 
-struct inode *lookup_free_space_inode(
-		struct btrfs_block_group_cache *block_group,
+struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group,
 		struct btrfs_path *path)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
@@ -107,7 +106,7 @@ struct inode *lookup_free_space_inode(
 		return inode;
 
 	inode = __lookup_free_space_inode(fs_info->tree_root, path,
-					  block_group->key.objectid);
+					  block_group->start);
 	if (IS_ERR(inode))
 		return inode;
 
@@ -190,7 +189,7 @@ static int __create_free_space_inode(struct btrfs_root *root,
 }
 
 int create_free_space_inode(struct btrfs_trans_handle *trans,
-			    struct btrfs_block_group_cache *block_group,
+			    struct btrfs_block_group *block_group,
 			    struct btrfs_path *path)
 {
 	int ret;
@@ -201,7 +200,7 @@ int create_free_space_inode(struct btrfs_trans_handle *trans,
 		return ret;
 
 	return __create_free_space_inode(trans->fs_info->tree_root, trans, path,
-					 ino, block_group->key.objectid);
+					 ino, block_group->start);
 }
 
 int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
@@ -224,7 +223,7 @@ int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
 }
 
 int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
-				    struct btrfs_block_group_cache *block_group,
+				    struct btrfs_block_group *block_group,
 				    struct inode *inode)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -385,6 +384,12 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, struct inode *inode
 		if (uptodate && !PageUptodate(page)) {
 			btrfs_readpage(NULL, page);
 			lock_page(page);
+			if (page->mapping != inode->i_mapping) {
+				btrfs_err(BTRFS_I(inode)->root->fs_info,
+					  "free space cache page truncated");
+				io_ctl_drop_pages(io_ctl);
+				return -EIO;
+			}
 			if (!PageUptodate(page)) {
 				btrfs_err(BTRFS_I(inode)->root->fs_info,
 					   "error reading free space cache");
@@ -814,7 +819,7 @@ free_cache:
 	goto out;
 }
 
-int load_free_space_cache(struct btrfs_block_group_cache *block_group)
+int load_free_space_cache(struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
@@ -822,7 +827,7 @@ int load_free_space_cache(struct btrfs_block_group_cache *block_group)
 	struct btrfs_path *path;
 	int ret = 0;
 	bool matched;
-	u64 used = btrfs_block_group_used(&block_group->item);
+	u64 used = block_group->used;
 
 	/*
 	 * If this block group has been marked to be cleared for one reason or
@@ -876,13 +881,13 @@ int load_free_space_cache(struct btrfs_block_group_cache *block_group)
 	spin_unlock(&block_group->lock);
 
 	ret = __load_free_space_cache(fs_info->tree_root, inode, ctl,
-				      path, block_group->key.objectid);
+				      path, block_group->start);
 	btrfs_free_path(path);
 	if (ret <= 0)
 		goto out;
 
 	spin_lock(&ctl->tree_lock);
-	matched = (ctl->free_space == (block_group->key.offset - used -
+	matched = (ctl->free_space == (block_group->length - used -
 				       block_group->bytes_super));
 	spin_unlock(&ctl->tree_lock);
 
@@ -890,7 +895,7 @@ int load_free_space_cache(struct btrfs_block_group_cache *block_group)
 		__btrfs_remove_free_space_cache(ctl);
 		btrfs_warn(fs_info,
 			   "block group %llu has wrong amount of free space",
-			   block_group->key.objectid);
+			   block_group->start);
 		ret = -1;
 	}
 out:
@@ -903,7 +908,7 @@ out:
 
 		btrfs_warn(fs_info,
 			   "failed to load free space cache for block group %llu, rebuilding it now",
-			   block_group->key.objectid);
+			   block_group->start);
 	}
 
 	iput(inode);
@@ -913,7 +918,7 @@ out:
 static noinline_for_stack
 int write_cache_extent_entries(struct btrfs_io_ctl *io_ctl,
 			      struct btrfs_free_space_ctl *ctl,
-			      struct btrfs_block_group_cache *block_group,
+			      struct btrfs_block_group *block_group,
 			      int *entries, int *bitmaps,
 			      struct list_head *bitmap_list)
 {
@@ -1041,7 +1046,7 @@ fail:
 }
 
 static noinline_for_stack int write_pinned_extent_entries(
-			    struct btrfs_block_group_cache *block_group,
+			    struct btrfs_block_group *block_group,
 			    struct btrfs_io_ctl *io_ctl,
 			    int *entries)
 {
@@ -1061,9 +1066,9 @@ static noinline_for_stack int write_pinned_extent_entries(
 	 */
 	unpin = block_group->fs_info->pinned_extents;
 
-	start = block_group->key.objectid;
+	start = block_group->start;
 
-	while (start < block_group->key.objectid + block_group->key.offset) {
+	while (start < block_group->start + block_group->length) {
 		ret = find_first_extent_bit(unpin, start,
 					    &extent_start, &extent_end,
 					    EXTENT_DIRTY, NULL);
@@ -1071,13 +1076,12 @@ static noinline_for_stack int write_pinned_extent_entries(
 			return 0;
 
 		/* This pinned extent is out of our range */
-		if (extent_start >= block_group->key.objectid +
-		    block_group->key.offset)
+		if (extent_start >= block_group->start + block_group->length)
 			return 0;
 
 		extent_start = max(extent_start, start);
-		extent_end = min(block_group->key.objectid +
-				 block_group->key.offset, extent_end + 1);
+		extent_end = min(block_group->start + block_group->length,
+				 extent_end + 1);
 		len = extent_end - extent_start;
 
 		*entries += 1;
@@ -1141,7 +1145,7 @@ cleanup_write_cache_enospc(struct inode *inode,
 
 static int __btrfs_wait_cache_io(struct btrfs_root *root,
 				 struct btrfs_trans_handle *trans,
-				 struct btrfs_block_group_cache *block_group,
+				 struct btrfs_block_group *block_group,
 				 struct btrfs_io_ctl *io_ctl,
 				 struct btrfs_path *path, u64 offset)
 {
@@ -1168,7 +1172,7 @@ out:
 #ifdef DEBUG
 			btrfs_err(root->fs_info,
 				  "failed to write free space cache for block group %llu",
-				  block_group->key.objectid);
+				  block_group->start);
 #endif
 		}
 	}
@@ -1210,12 +1214,12 @@ static int btrfs_wait_cache_io_root(struct btrfs_root *root,
 }
 
 int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
-			struct btrfs_block_group_cache *block_group,
+			struct btrfs_block_group *block_group,
 			struct btrfs_path *path)
 {
 	return __btrfs_wait_cache_io(block_group->fs_info->tree_root, trans,
 				     block_group, &block_group->io_ctl,
-				     path, block_group->key.objectid);
+				     path, block_group->start);
 }
 
 /**
@@ -1231,7 +1235,7 @@ int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
  */
 static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 				   struct btrfs_free_space_ctl *ctl,
-				   struct btrfs_block_group_cache *block_group,
+				   struct btrfs_block_group *block_group,
 				   struct btrfs_io_ctl *io_ctl,
 				   struct btrfs_trans_handle *trans)
 {
@@ -1369,7 +1373,7 @@ out_unlock:
 }
 
 int btrfs_write_out_cache(struct btrfs_trans_handle *trans,
-			  struct btrfs_block_group_cache *block_group,
+			  struct btrfs_block_group *block_group,
 			  struct btrfs_path *path)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
@@ -1394,7 +1398,7 @@ int btrfs_write_out_cache(struct btrfs_trans_handle *trans,
 #ifdef DEBUG
 		btrfs_err(fs_info,
 			  "failed to write free space cache for block group %llu",
-			  block_group->key.objectid);
+			  block_group->start);
 #endif
 		spin_lock(&block_group->lock);
 		block_group->disk_cache_state = BTRFS_DC_ERROR;
@@ -1647,11 +1651,11 @@ static int link_free_space(struct btrfs_free_space_ctl *ctl,
 
 static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
 {
-	struct btrfs_block_group_cache *block_group = ctl->private;
+	struct btrfs_block_group *block_group = ctl->private;
 	u64 max_bytes;
 	u64 bitmap_bytes;
 	u64 extent_bytes;
-	u64 size = block_group->key.offset;
+	u64 size = block_group->length;
 	u64 bytes_per_bg = BITS_PER_BITMAP * ctl->unit;
 	u64 max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg);
 
@@ -1991,7 +1995,7 @@ static u64 add_bytes_to_bitmap(struct btrfs_free_space_ctl *ctl,
 static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
 		      struct btrfs_free_space *info)
 {
-	struct btrfs_block_group_cache *block_group = ctl->private;
+	struct btrfs_block_group *block_group = ctl->private;
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	bool forced = false;
 
@@ -2028,7 +2032,7 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
 	 * so allow those block groups to still be allowed to have a bitmap
 	 * entry.
 	 */
-	if (((BITS_PER_BITMAP * ctl->unit) >> 1) > block_group->key.offset)
+	if (((BITS_PER_BITMAP * ctl->unit) >> 1) > block_group->length)
 		return false;
 
 	return true;
@@ -2043,7 +2047,7 @@ static int insert_into_bitmap(struct btrfs_free_space_ctl *ctl,
 			      struct btrfs_free_space *info)
 {
 	struct btrfs_free_space *bitmap_info;
-	struct btrfs_block_group_cache *block_group = NULL;
+	struct btrfs_block_group *block_group = NULL;
 	int added = 0;
 	u64 bytes, offset, bytes_added;
 	int ret;
@@ -2380,7 +2384,7 @@ out:
 	return ret;
 }
 
-int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
+int btrfs_add_free_space(struct btrfs_block_group *block_group,
 			 u64 bytenr, u64 size)
 {
 	return __btrfs_add_free_space(block_group->fs_info,
@@ -2388,7 +2392,7 @@ int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
 				      bytenr, size);
 }
 
-int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
+int btrfs_remove_free_space(struct btrfs_block_group *block_group,
 			    u64 offset, u64 bytes)
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
@@ -2478,7 +2482,7 @@ out:
 	return ret;
 }
 
-void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
+void btrfs_dump_free_space(struct btrfs_block_group *block_group,
 			   u64 bytes)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
@@ -2503,14 +2507,14 @@ void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
 		   "%d blocks of free space at or bigger than bytes is", count);
 }
 
-void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group)
+void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 
 	spin_lock_init(&ctl->tree_lock);
 	ctl->unit = fs_info->sectorsize;
-	ctl->start = block_group->key.objectid;
+	ctl->start = block_group->start;
 	ctl->private = block_group;
 	ctl->op = &free_space_op;
 	INIT_LIST_HEAD(&ctl->trimming_ranges);
@@ -2532,7 +2536,7 @@ void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group)
  */
 static int
 __btrfs_return_cluster_to_free_space(
-			     struct btrfs_block_group_cache *block_group,
+			     struct btrfs_block_group *block_group,
 			     struct btrfs_free_cluster *cluster)
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
@@ -2598,7 +2602,7 @@ void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl)
 	spin_unlock(&ctl->tree_lock);
 }
 
-void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group)
+void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group)
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_cluster *cluster;
@@ -2620,7 +2624,7 @@ void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group)
 
 }
 
-u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
+u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
 			       u64 offset, u64 bytes, u64 empty_size,
 			       u64 *max_extent_size)
 {
@@ -2674,7 +2678,7 @@ out:
  * cluster and remove the cluster from it.
  */
 int btrfs_return_cluster_to_free_space(
-			       struct btrfs_block_group_cache *block_group,
+			       struct btrfs_block_group *block_group,
 			       struct btrfs_free_cluster *cluster)
 {
 	struct btrfs_free_space_ctl *ctl;
@@ -2708,7 +2712,7 @@ int btrfs_return_cluster_to_free_space(
 	return ret;
 }
 
-static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
+static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group *block_group,
 				   struct btrfs_free_cluster *cluster,
 				   struct btrfs_free_space *entry,
 				   u64 bytes, u64 min_start,
@@ -2741,7 +2745,7 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
  * if it couldn't find anything suitably large, or a logical disk offset
  * if things worked out
  */
-u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
+u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group,
 			     struct btrfs_free_cluster *cluster, u64 bytes,
 			     u64 min_start, u64 *max_extent_size)
 {
@@ -2827,7 +2831,7 @@ out:
 	return ret;
 }
 
-static int btrfs_bitmap_cluster(struct btrfs_block_group_cache *block_group,
+static int btrfs_bitmap_cluster(struct btrfs_block_group *block_group,
 				struct btrfs_free_space *entry,
 				struct btrfs_free_cluster *cluster,
 				u64 offset, u64 bytes,
@@ -2909,7 +2913,7 @@ again:
  * extent of cont1_bytes, and other clusters of at least min_bytes.
  */
 static noinline int
-setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
+setup_cluster_no_bitmap(struct btrfs_block_group *block_group,
 			struct btrfs_free_cluster *cluster,
 			struct list_head *bitmaps, u64 offset, u64 bytes,
 			u64 cont1_bytes, u64 min_bytes)
@@ -3000,7 +3004,7 @@ setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
  * that we have already failed to find extents that will work.
  */
 static noinline int
-setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
+setup_cluster_bitmap(struct btrfs_block_group *block_group,
 		     struct btrfs_free_cluster *cluster,
 		     struct list_head *bitmaps, u64 offset, u64 bytes,
 		     u64 cont1_bytes, u64 min_bytes)
@@ -3050,7 +3054,7 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
  * returns zero and sets up cluster if things worked out, otherwise
  * it returns -enospc
  */
-int btrfs_find_space_cluster(struct btrfs_block_group_cache *block_group,
+int btrfs_find_space_cluster(struct btrfs_block_group *block_group,
 			     struct btrfs_free_cluster *cluster,
 			     u64 offset, u64 bytes, u64 empty_size)
 {
@@ -3141,7 +3145,7 @@ void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster)
 	cluster->block_group = NULL;
 }
 
-static int do_trimming(struct btrfs_block_group_cache *block_group,
+static int do_trimming(struct btrfs_block_group *block_group,
 		       u64 *total_trimmed, u64 start, u64 bytes,
 		       u64 reserved_start, u64 reserved_bytes,
 		       struct btrfs_trim_range *trim_entry)
@@ -3186,7 +3190,7 @@ static int do_trimming(struct btrfs_block_group_cache *block_group,
 	return ret;
 }
 
-static int trim_no_bitmap(struct btrfs_block_group_cache *block_group,
+static int trim_no_bitmap(struct btrfs_block_group *block_group,
 			  u64 *total_trimmed, u64 start, u64 end, u64 minlen)
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
@@ -3271,7 +3275,7 @@ out:
 	return ret;
 }
 
-static int trim_bitmaps(struct btrfs_block_group_cache *block_group,
+static int trim_bitmaps(struct btrfs_block_group *block_group,
 			u64 *total_trimmed, u64 start, u64 end, u64 minlen)
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
@@ -3352,12 +3356,12 @@ next:
 	return ret;
 }
 
-void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache)
+void btrfs_get_block_group_trimming(struct btrfs_block_group *cache)
 {
 	atomic_inc(&cache->trimming);
 }
 
-void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *block_group)
+void btrfs_put_block_group_trimming(struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	struct extent_map_tree *em_tree;
@@ -3373,7 +3377,7 @@ void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *block_group)
 		mutex_lock(&fs_info->chunk_mutex);
 		em_tree = &fs_info->mapping_tree;
 		write_lock(&em_tree->lock);
-		em = lookup_extent_mapping(em_tree, block_group->key.objectid,
+		em = lookup_extent_mapping(em_tree, block_group->start,
 					   1);
 		BUG_ON(!em); /* logic error, can't happen */
 		remove_extent_mapping(em_tree, em);
@@ -3392,7 +3396,7 @@ void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *block_group)
 	}
 }
 
-int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
+int btrfs_trim_block_group(struct btrfs_block_group *block_group,
 			   u64 *trimmed, u64 start, u64 end, u64 minlen)
 {
 	int ret;
@@ -3590,7 +3594,7 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root,
  * how the free space cache loading stuff works, so you can get really weird
  * configurations.
  */
-int test_add_free_space_entry(struct btrfs_block_group_cache *cache,
+int test_add_free_space_entry(struct btrfs_block_group *cache,
 			      u64 offset, u64 bytes, bool bitmap)
 {
 	struct btrfs_free_space_ctl *ctl = cache->free_space_ctl;
@@ -3658,7 +3662,7 @@ again:
  * just used to check the absence of space, so if there is free space in the
  * range at all we will return 1.
  */
-int test_check_exists(struct btrfs_block_group_cache *cache,
+int test_check_exists(struct btrfs_block_group *cache,
 		      u64 offset, u64 bytes)
 {
 	struct btrfs_free_space_ctl *ctl = cache->free_space_ctl;
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index 39c32c8fc24f..ba9a23241101 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -50,24 +50,23 @@ struct btrfs_io_ctl {
 	unsigned check_crcs:1;
 };
 
-struct inode *lookup_free_space_inode(
-		struct btrfs_block_group_cache *block_group,
+struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group,
 		struct btrfs_path *path);
 int create_free_space_inode(struct btrfs_trans_handle *trans,
-			    struct btrfs_block_group_cache *block_group,
+			    struct btrfs_block_group *block_group,
 			    struct btrfs_path *path);
 
 int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
 				       struct btrfs_block_rsv *rsv);
 int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
-				    struct btrfs_block_group_cache *block_group,
+				    struct btrfs_block_group *block_group,
 				    struct inode *inode);
-int load_free_space_cache(struct btrfs_block_group_cache *block_group);
+int load_free_space_cache(struct btrfs_block_group *block_group);
 int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
-			struct btrfs_block_group_cache *block_group,
+			struct btrfs_block_group *block_group,
 			struct btrfs_path *path);
 int btrfs_write_out_cache(struct btrfs_trans_handle *trans,
-			  struct btrfs_block_group_cache *block_group,
+			  struct btrfs_block_group *block_group,
 			  struct btrfs_path *path);
 struct inode *lookup_free_ino_inode(struct btrfs_root *root,
 				    struct btrfs_path *path);
@@ -81,42 +80,40 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root,
 			      struct btrfs_path *path,
 			      struct inode *inode);
 
-void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group);
+void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group);
 int __btrfs_add_free_space(struct btrfs_fs_info *fs_info,
 			   struct btrfs_free_space_ctl *ctl,
 			   u64 bytenr, u64 size);
-int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
+int btrfs_add_free_space(struct btrfs_block_group *block_group,
 			 u64 bytenr, u64 size);
-int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
+int btrfs_remove_free_space(struct btrfs_block_group *block_group,
 			    u64 bytenr, u64 size);
 void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl);
-void btrfs_remove_free_space_cache(struct btrfs_block_group_cache
-				     *block_group);
-u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
+void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group);
+u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
 			       u64 offset, u64 bytes, u64 empty_size,
 			       u64 *max_extent_size);
 u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root);
-void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
+void btrfs_dump_free_space(struct btrfs_block_group *block_group,
 			   u64 bytes);
-int btrfs_find_space_cluster(struct btrfs_block_group_cache *block_group,
+int btrfs_find_space_cluster(struct btrfs_block_group *block_group,
 			     struct btrfs_free_cluster *cluster,
 			     u64 offset, u64 bytes, u64 empty_size);
 void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster);
-u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
+u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group,
 			     struct btrfs_free_cluster *cluster, u64 bytes,
 			     u64 min_start, u64 *max_extent_size);
 int btrfs_return_cluster_to_free_space(
-			       struct btrfs_block_group_cache *block_group,
+			       struct btrfs_block_group *block_group,
 			       struct btrfs_free_cluster *cluster);
-int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
+int btrfs_trim_block_group(struct btrfs_block_group *block_group,
 			   u64 *trimmed, u64 start, u64 end, u64 minlen);
 
 /* Support functions for running our sanity tests */
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-int test_add_free_space_entry(struct btrfs_block_group_cache *cache,
+int test_add_free_space_entry(struct btrfs_block_group *cache,
 			      u64 offset, u64 bytes, bool bitmap);
-int test_check_exists(struct btrfs_block_group_cache *cache,
-		      u64 offset, u64 bytes);
+int test_check_exists(struct btrfs_block_group *cache, u64 offset, u64 bytes);
 #endif
 
 #endif
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 48a03f5240f5..258cb3fae17a 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -13,10 +13,10 @@
 #include "block-group.h"
 
 static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
-					struct btrfs_block_group_cache *block_group,
+					struct btrfs_block_group *block_group,
 					struct btrfs_path *path);
 
-void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache)
+void set_free_space_tree_thresholds(struct btrfs_block_group *cache)
 {
 	u32 bitmap_range;
 	size_t bitmap_size;
@@ -27,8 +27,7 @@ void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache)
 	 * exceeds that required for using bitmaps.
 	 */
 	bitmap_range = cache->fs_info->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS;
-	num_bitmaps = div_u64(cache->key.offset + bitmap_range - 1,
-			      bitmap_range);
+	num_bitmaps = div_u64(cache->length + bitmap_range - 1, bitmap_range);
 	bitmap_size = sizeof(struct btrfs_item) + BTRFS_FREE_SPACE_BITMAP_SIZE;
 	total_bitmap_size = num_bitmaps * bitmap_size;
 	cache->bitmap_high_thresh = div_u64(total_bitmap_size,
@@ -45,7 +44,7 @@ void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache)
 }
 
 static int add_new_free_space_info(struct btrfs_trans_handle *trans,
-				   struct btrfs_block_group_cache *block_group,
+				   struct btrfs_block_group *block_group,
 				   struct btrfs_path *path)
 {
 	struct btrfs_root *root = trans->fs_info->free_space_root;
@@ -54,9 +53,9 @@ static int add_new_free_space_info(struct btrfs_trans_handle *trans,
 	struct extent_buffer *leaf;
 	int ret;
 
-	key.objectid = block_group->key.objectid;
+	key.objectid = block_group->start;
 	key.type = BTRFS_FREE_SPACE_INFO_KEY;
-	key.offset = block_group->key.offset;
+	key.offset = block_group->length;
 
 	ret = btrfs_insert_empty_item(trans, root, path, &key, sizeof(*info));
 	if (ret)
@@ -78,7 +77,7 @@ out:
 EXPORT_FOR_TESTS
 struct btrfs_free_space_info *search_free_space_info(
 		struct btrfs_trans_handle *trans,
-		struct btrfs_block_group_cache *block_group,
+		struct btrfs_block_group *block_group,
 		struct btrfs_path *path, int cow)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
@@ -86,16 +85,16 @@ struct btrfs_free_space_info *search_free_space_info(
 	struct btrfs_key key;
 	int ret;
 
-	key.objectid = block_group->key.objectid;
+	key.objectid = block_group->start;
 	key.type = BTRFS_FREE_SPACE_INFO_KEY;
-	key.offset = block_group->key.offset;
+	key.offset = block_group->length;
 
 	ret = btrfs_search_slot(trans, root, &key, path, 0, cow);
 	if (ret < 0)
 		return ERR_PTR(ret);
 	if (ret != 0) {
 		btrfs_warn(fs_info, "missing free space info for %llu",
-			   block_group->key.objectid);
+			   block_group->start);
 		ASSERT(0);
 		return ERR_PTR(-ENOENT);
 	}
@@ -180,7 +179,7 @@ static void le_bitmap_set(unsigned long *map, unsigned int start, int len)
 
 EXPORT_FOR_TESTS
 int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_block_group *block_group,
 				  struct btrfs_path *path)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
@@ -197,7 +196,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
 	int done = 0, nr;
 	int ret;
 
-	bitmap_size = free_space_bitmap_size(block_group->key.offset,
+	bitmap_size = free_space_bitmap_size(block_group->length,
 					     fs_info->sectorsize);
 	bitmap = alloc_bitmap(bitmap_size);
 	if (!bitmap) {
@@ -205,8 +204,8 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	start = block_group->key.objectid;
-	end = block_group->key.objectid + block_group->key.offset;
+	start = block_group->start;
+	end = block_group->start + block_group->length;
 
 	key.objectid = end - 1;
 	key.type = (u8)-1;
@@ -224,8 +223,8 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
 			btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1);
 
 			if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) {
-				ASSERT(found_key.objectid == block_group->key.objectid);
-				ASSERT(found_key.offset == block_group->key.offset);
+				ASSERT(found_key.objectid == block_group->start);
+				ASSERT(found_key.offset == block_group->length);
 				done = 1;
 				break;
 			} else if (found_key.type == BTRFS_FREE_SPACE_EXTENT_KEY) {
@@ -271,7 +270,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
 	if (extent_count != expected_extent_count) {
 		btrfs_err(fs_info,
 			  "incorrect extent count for %llu; counted %u, expected %u",
-			  block_group->key.objectid, extent_count,
+			  block_group->start, extent_count,
 			  expected_extent_count);
 		ASSERT(0);
 		ret = -EIO;
@@ -320,7 +319,7 @@ out:
 
 EXPORT_FOR_TESTS
 int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_block_group *block_group,
 				  struct btrfs_path *path)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
@@ -336,7 +335,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 	int done = 0, nr;
 	int ret;
 
-	bitmap_size = free_space_bitmap_size(block_group->key.offset,
+	bitmap_size = free_space_bitmap_size(block_group->length,
 					     fs_info->sectorsize);
 	bitmap = alloc_bitmap(bitmap_size);
 	if (!bitmap) {
@@ -344,8 +343,8 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	start = block_group->key.objectid;
-	end = block_group->key.objectid + block_group->key.offset;
+	start = block_group->start;
+	end = block_group->start + block_group->length;
 
 	key.objectid = end - 1;
 	key.type = (u8)-1;
@@ -363,8 +362,8 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 			btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1);
 
 			if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) {
-				ASSERT(found_key.objectid == block_group->key.objectid);
-				ASSERT(found_key.offset == block_group->key.offset);
+				ASSERT(found_key.objectid == block_group->start);
+				ASSERT(found_key.offset == block_group->length);
 				done = 1;
 				break;
 			} else if (found_key.type == BTRFS_FREE_SPACE_BITMAP_KEY) {
@@ -413,7 +412,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_release_path(path);
 
-	nrbits = div_u64(block_group->key.offset, block_group->fs_info->sectorsize);
+	nrbits = div_u64(block_group->length, block_group->fs_info->sectorsize);
 	start_bit = find_next_bit_le(bitmap, nrbits, 0);
 
 	while (start_bit < nrbits) {
@@ -437,7 +436,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 	if (extent_count != expected_extent_count) {
 		btrfs_err(fs_info,
 			  "incorrect extent count for %llu; counted %u, expected %u",
-			  block_group->key.objectid, extent_count,
+			  block_group->start, extent_count,
 			  expected_extent_count);
 		ASSERT(0);
 		ret = -EIO;
@@ -453,7 +452,7 @@ out:
 }
 
 static int update_free_space_extent_count(struct btrfs_trans_handle *trans,
-					  struct btrfs_block_group_cache *block_group,
+					  struct btrfs_block_group *block_group,
 					  struct btrfs_path *path,
 					  int new_extents)
 {
@@ -491,7 +490,7 @@ out:
 }
 
 EXPORT_FOR_TESTS
-int free_space_test_bit(struct btrfs_block_group_cache *block_group,
+int free_space_test_bit(struct btrfs_block_group *block_group,
 			struct btrfs_path *path, u64 offset)
 {
 	struct extent_buffer *leaf;
@@ -513,7 +512,7 @@ int free_space_test_bit(struct btrfs_block_group_cache *block_group,
 	return !!extent_buffer_test_bit(leaf, ptr, i);
 }
 
-static void free_space_set_bits(struct btrfs_block_group_cache *block_group,
+static void free_space_set_bits(struct btrfs_block_group *block_group,
 				struct btrfs_path *path, u64 *start, u64 *size,
 				int bit)
 {
@@ -581,7 +580,7 @@ static int free_space_next_bitmap(struct btrfs_trans_handle *trans,
  * the bitmap.
  */
 static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
-				    struct btrfs_block_group_cache *block_group,
+				    struct btrfs_block_group *block_group,
 				    struct btrfs_path *path,
 				    u64 start, u64 size, int remove)
 {
@@ -597,7 +596,7 @@ static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
 	 * Read the bit for the block immediately before the extent of space if
 	 * that block is within the block group.
 	 */
-	if (start > block_group->key.objectid) {
+	if (start > block_group->start) {
 		u64 prev_block = start - block_group->fs_info->sectorsize;
 
 		key.objectid = prev_block;
@@ -649,7 +648,7 @@ static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
 	 * Read the bit for the block immediately after the extent of space if
 	 * that block is within the block group.
 	 */
-	if (end < block_group->key.objectid + block_group->key.offset) {
+	if (end < block_group->start + block_group->length) {
 		/* The next block may be in the next bitmap. */
 		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
 		if (end >= key.objectid + key.offset) {
@@ -694,7 +693,7 @@ out:
 }
 
 static int remove_free_space_extent(struct btrfs_trans_handle *trans,
-				    struct btrfs_block_group_cache *block_group,
+				    struct btrfs_block_group *block_group,
 				    struct btrfs_path *path,
 				    u64 start, u64 size)
 {
@@ -781,7 +780,7 @@ out:
 
 EXPORT_FOR_TESTS
 int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_block_group *block_group,
 				  struct btrfs_path *path, u64 start, u64 size)
 {
 	struct btrfs_free_space_info *info;
@@ -812,7 +811,7 @@ int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
 int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
 				u64 start, u64 size)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_path *path;
 	int ret;
 
@@ -846,7 +845,7 @@ out:
 }
 
 static int add_free_space_extent(struct btrfs_trans_handle *trans,
-				 struct btrfs_block_group_cache *block_group,
+				 struct btrfs_block_group *block_group,
 				 struct btrfs_path *path,
 				 u64 start, u64 size)
 {
@@ -880,7 +879,7 @@ static int add_free_space_extent(struct btrfs_trans_handle *trans,
 	new_key.offset = size;
 
 	/* Search for a neighbor on the left. */
-	if (start == block_group->key.objectid)
+	if (start == block_group->start)
 		goto right;
 	key.objectid = start - 1;
 	key.type = (u8)-1;
@@ -900,8 +899,8 @@ static int add_free_space_extent(struct btrfs_trans_handle *trans,
 
 	found_start = key.objectid;
 	found_end = key.objectid + key.offset;
-	ASSERT(found_start >= block_group->key.objectid &&
-	       found_end > block_group->key.objectid);
+	ASSERT(found_start >= block_group->start &&
+	       found_end > block_group->start);
 	ASSERT(found_start < start && found_end <= start);
 
 	/*
@@ -920,7 +919,7 @@ static int add_free_space_extent(struct btrfs_trans_handle *trans,
 
 right:
 	/* Search for a neighbor on the right. */
-	if (end == block_group->key.objectid + block_group->key.offset)
+	if (end == block_group->start + block_group->length)
 		goto insert;
 	key.objectid = end;
 	key.type = (u8)-1;
@@ -940,8 +939,8 @@ right:
 
 	found_start = key.objectid;
 	found_end = key.objectid + key.offset;
-	ASSERT(found_start >= block_group->key.objectid &&
-	       found_end > block_group->key.objectid);
+	ASSERT(found_start >= block_group->start &&
+	       found_end > block_group->start);
 	ASSERT((found_start < start && found_end <= start) ||
 	       (found_start >= end && found_end > end));
 
@@ -974,7 +973,7 @@ out:
 
 EXPORT_FOR_TESTS
 int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
-			     struct btrfs_block_group_cache *block_group,
+			     struct btrfs_block_group *block_group,
 			     struct btrfs_path *path, u64 start, u64 size)
 {
 	struct btrfs_free_space_info *info;
@@ -1005,7 +1004,7 @@ int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
 int add_to_free_space_tree(struct btrfs_trans_handle *trans,
 			   u64 start, u64 size)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_path *path;
 	int ret;
 
@@ -1043,7 +1042,7 @@ out:
  * through the normal add/remove hooks.
  */
 static int populate_free_space_tree(struct btrfs_trans_handle *trans,
-				    struct btrfs_block_group_cache *block_group)
+				    struct btrfs_block_group *block_group)
 {
 	struct btrfs_root *extent_root = trans->fs_info->extent_root;
 	struct btrfs_path *path, *path2;
@@ -1075,7 +1074,7 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
 	 * BLOCK_GROUP_ITEM, so an extent may precede the block group that it's
 	 * contained in.
 	 */
-	key.objectid = block_group->key.objectid;
+	key.objectid = block_group->start;
 	key.type = BTRFS_EXTENT_ITEM_KEY;
 	key.offset = 0;
 
@@ -1084,8 +1083,8 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
 		goto out_locked;
 	ASSERT(ret == 0);
 
-	start = block_group->key.objectid;
-	end = block_group->key.objectid + block_group->key.offset;
+	start = block_group->start;
+	end = block_group->start + block_group->length;
 	while (1) {
 		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
 
@@ -1109,7 +1108,7 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
 			else
 				start += key.offset;
 		} else if (key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) {
-			if (key.objectid != block_group->key.objectid)
+			if (key.objectid != block_group->start)
 				break;
 		}
 
@@ -1140,7 +1139,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *tree_root = fs_info->tree_root;
 	struct btrfs_root *free_space_root;
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct rb_node *node;
 	int ret;
 
@@ -1159,7 +1158,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
 
 	node = rb_first(&fs_info->block_group_cache_tree);
 	while (node) {
-		block_group = rb_entry(node, struct btrfs_block_group_cache,
+		block_group = rb_entry(node, struct btrfs_block_group,
 				       cache_node);
 		ret = populate_free_space_tree(trans, block_group);
 		if (ret)
@@ -1265,7 +1264,7 @@ abort:
 }
 
 static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
-					struct btrfs_block_group_cache *block_group,
+					struct btrfs_block_group *block_group,
 					struct btrfs_path *path)
 {
 	int ret;
@@ -1277,12 +1276,12 @@ static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
 		return ret;
 
 	return __add_to_free_space_tree(trans, block_group, path,
-					block_group->key.objectid,
-					block_group->key.offset);
+					block_group->start,
+					block_group->length);
 }
 
 int add_block_group_free_space(struct btrfs_trans_handle *trans,
-			       struct btrfs_block_group_cache *block_group)
+			       struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_path *path = NULL;
@@ -1312,7 +1311,7 @@ out:
 }
 
 int remove_block_group_free_space(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group)
+				  struct btrfs_block_group *block_group)
 {
 	struct btrfs_root *root = trans->fs_info->free_space_root;
 	struct btrfs_path *path;
@@ -1336,8 +1335,8 @@ int remove_block_group_free_space(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	start = block_group->key.objectid;
-	end = block_group->key.objectid + block_group->key.offset;
+	start = block_group->start;
+	end = block_group->start + block_group->length;
 
 	key.objectid = end - 1;
 	key.type = (u8)-1;
@@ -1355,8 +1354,8 @@ int remove_block_group_free_space(struct btrfs_trans_handle *trans,
 			btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1);
 
 			if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) {
-				ASSERT(found_key.objectid == block_group->key.objectid);
-				ASSERT(found_key.offset == block_group->key.offset);
+				ASSERT(found_key.objectid == block_group->start);
+				ASSERT(found_key.offset == block_group->length);
 				done = 1;
 				nr++;
 				path->slots[0]--;
@@ -1391,7 +1390,7 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
 				   struct btrfs_path *path,
 				   u32 expected_extent_count)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_fs_info *fs_info;
 	struct btrfs_root *root;
 	struct btrfs_key key;
@@ -1407,7 +1406,7 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
 	fs_info = block_group->fs_info;
 	root = fs_info->free_space_root;
 
-	end = block_group->key.objectid + block_group->key.offset;
+	end = block_group->start + block_group->length;
 
 	while (1) {
 		ret = btrfs_next_item(root, path);
@@ -1454,7 +1453,7 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
 	if (extent_count != expected_extent_count) {
 		btrfs_err(fs_info,
 			  "incorrect extent count for %llu; counted %u, expected %u",
-			  block_group->key.objectid, extent_count,
+			  block_group->start, extent_count,
 			  expected_extent_count);
 		ASSERT(0);
 		ret = -EIO;
@@ -1472,7 +1471,7 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
 				   struct btrfs_path *path,
 				   u32 expected_extent_count)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_fs_info *fs_info;
 	struct btrfs_root *root;
 	struct btrfs_key key;
@@ -1485,7 +1484,7 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
 	fs_info = block_group->fs_info;
 	root = fs_info->free_space_root;
 
-	end = block_group->key.objectid + block_group->key.offset;
+	end = block_group->start + block_group->length;
 
 	while (1) {
 		ret = btrfs_next_item(root, path);
@@ -1516,7 +1515,7 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
 	if (extent_count != expected_extent_count) {
 		btrfs_err(fs_info,
 			  "incorrect extent count for %llu; counted %u, expected %u",
-			  block_group->key.objectid, extent_count,
+			  block_group->start, extent_count,
 			  expected_extent_count);
 		ASSERT(0);
 		ret = -EIO;
@@ -1532,7 +1531,7 @@ out:
 
 int load_free_space_tree(struct btrfs_caching_control *caching_ctl)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_free_space_info *info;
 	struct btrfs_path *path;
 	u32 extent_count, flags;
diff --git a/fs/btrfs/free-space-tree.h b/fs/btrfs/free-space-tree.h
index 360d50e1cdea..dc2463e4cfe3 100644
--- a/fs/btrfs/free-space-tree.h
+++ b/fs/btrfs/free-space-tree.h
@@ -16,14 +16,14 @@ struct btrfs_caching_control;
 #define BTRFS_FREE_SPACE_BITMAP_SIZE 256
 #define BTRFS_FREE_SPACE_BITMAP_BITS (BTRFS_FREE_SPACE_BITMAP_SIZE * BITS_PER_BYTE)
 
-void set_free_space_tree_thresholds(struct btrfs_block_group_cache *block_group);
+void set_free_space_tree_thresholds(struct btrfs_block_group *block_group);
 int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info);
 int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info);
 int load_free_space_tree(struct btrfs_caching_control *caching_ctl);
 int add_block_group_free_space(struct btrfs_trans_handle *trans,
-			       struct btrfs_block_group_cache *block_group);
+			       struct btrfs_block_group *block_group);
 int remove_block_group_free_space(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group);
+				  struct btrfs_block_group *block_group);
 int add_to_free_space_tree(struct btrfs_trans_handle *trans,
 			   u64 start, u64 size);
 int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
@@ -32,21 +32,21 @@ int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 struct btrfs_free_space_info *
 search_free_space_info(struct btrfs_trans_handle *trans,
-		       struct btrfs_block_group_cache *block_group,
+		       struct btrfs_block_group *block_group,
 		       struct btrfs_path *path, int cow);
 int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
-			     struct btrfs_block_group_cache *block_group,
+			     struct btrfs_block_group *block_group,
 			     struct btrfs_path *path, u64 start, u64 size);
 int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_block_group *block_group,
 				  struct btrfs_path *path, u64 start, u64 size);
 int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_block_group *block_group,
 				  struct btrfs_path *path);
 int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_block_group *block_group,
 				  struct btrfs_path *path);
-int free_space_test_bit(struct btrfs_block_group_cache *block_group,
+int free_space_test_bit(struct btrfs_block_group *block_group,
 			struct btrfs_path *path, u64 offset);
 #endif
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 015910079e73..56032c518b26 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -368,6 +368,7 @@ struct async_chunk {
 	u64 end;
 	unsigned int write_flags;
 	struct list_head extents;
+	struct cgroup_subsys_state *blkcg_css;
 	struct btrfs_work work;
 	atomic_t *pending;
 };
@@ -712,10 +713,12 @@ cleanup_and_bail_uncompressed:
 	 * to our extent and set things up for the async work queue to run
 	 * cow_file_range to do the normal delalloc dance.
 	 */
-	if (page_offset(async_chunk->locked_page) >= start &&
-	    page_offset(async_chunk->locked_page) <= end)
+	if (async_chunk->locked_page &&
+	    (page_offset(async_chunk->locked_page) >= start &&
+	     page_offset(async_chunk->locked_page)) <= end) {
 		__set_page_dirty_nobuffers(async_chunk->locked_page);
 		/* unlocked later on in the async handlers */
+	}
 
 	if (redirty)
 		extent_range_redirty_for_io(inode, start, end);
@@ -795,7 +798,7 @@ retry:
 						  async_extent->start +
 						  async_extent->ram_size - 1,
 						  WB_SYNC_ALL);
-			else if (ret)
+			else if (ret && async_chunk->locked_page)
 				unlock_page(async_chunk->locked_page);
 			kfree(async_extent);
 			cond_resched();
@@ -878,7 +881,8 @@ retry:
 				    ins.objectid,
 				    ins.offset, async_extent->pages,
 				    async_extent->nr_pages,
-				    async_chunk->write_flags)) {
+				    async_chunk->write_flags,
+				    async_chunk->blkcg_css)) {
 			struct page *p = async_extent->pages[0];
 			const u64 start = async_extent->start;
 			const u64 end = start + async_extent->ram_size - 1;
@@ -1196,6 +1200,8 @@ static noinline void async_cow_free(struct btrfs_work *work)
 	async_chunk = container_of(work, struct async_chunk, work);
 	if (async_chunk->inode)
 		btrfs_add_delayed_iput(async_chunk->inode);
+	if (async_chunk->blkcg_css)
+		css_put(async_chunk->blkcg_css);
 	/*
 	 * Since the pointer to 'pending' is at the beginning of the array of
 	 * async_chunk's, freeing it ensures the whole array has been freed.
@@ -1204,12 +1210,14 @@ static noinline void async_cow_free(struct btrfs_work *work)
 		kvfree(async_chunk->pending);
 }
 
-static int cow_file_range_async(struct inode *inode, struct page *locked_page,
+static int cow_file_range_async(struct inode *inode,
+				struct writeback_control *wbc,
+				struct page *locked_page,
 				u64 start, u64 end, int *page_started,
-				unsigned long *nr_written,
-				unsigned int write_flags)
+				unsigned long *nr_written)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct cgroup_subsys_state *blkcg_css = wbc_blkcg_css(wbc);
 	struct async_cow *ctx;
 	struct async_chunk *async_chunk;
 	unsigned long nr_pages;
@@ -1218,6 +1226,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 	int i;
 	bool should_compress;
 	unsigned nofs_flag;
+	const unsigned int write_flags = wbc_to_write_flags(wbc);
 
 	unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
 
@@ -1264,14 +1273,45 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 		async_chunk[i].inode = inode;
 		async_chunk[i].start = start;
 		async_chunk[i].end = cur_end;
-		async_chunk[i].locked_page = locked_page;
 		async_chunk[i].write_flags = write_flags;
 		INIT_LIST_HEAD(&async_chunk[i].extents);
 
-		btrfs_init_work(&async_chunk[i].work,
-				btrfs_delalloc_helper,
-				async_cow_start, async_cow_submit,
-				async_cow_free);
+		/*
+		 * The locked_page comes all the way from writepage and its
+		 * the original page we were actually given.  As we spread
+		 * this large delalloc region across multiple async_chunk
+		 * structs, only the first struct needs a pointer to locked_page
+		 *
+		 * This way we don't need racey decisions about who is supposed
+		 * to unlock it.
+		 */
+		if (locked_page) {
+			/*
+			 * Depending on the compressibility, the pages might or
+			 * might not go through async.  We want all of them to
+			 * be accounted against wbc once.  Let's do it here
+			 * before the paths diverge.  wbc accounting is used
+			 * only for foreign writeback detection and doesn't
+			 * need full accuracy.  Just account the whole thing
+			 * against the first page.
+			 */
+			wbc_account_cgroup_owner(wbc, locked_page,
+						 cur_end - start);
+			async_chunk[i].locked_page = locked_page;
+			locked_page = NULL;
+		} else {
+			async_chunk[i].locked_page = NULL;
+		}
+
+		if (blkcg_css != blkcg_root_css) {
+			css_get(blkcg_css);
+			async_chunk[i].blkcg_css = blkcg_css;
+		} else {
+			async_chunk[i].blkcg_css = NULL;
+		}
+
+		btrfs_init_work(&async_chunk[i].work, async_cow_start,
+				async_cow_submit, async_cow_free);
 
 		nr_pages = DIV_ROUND_UP(cur_end - start, PAGE_SIZE);
 		atomic_add(nr_pages, &fs_info->async_delalloc_pages);
@@ -1697,7 +1737,6 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page,
 {
 	int ret;
 	int force_cow = need_force_cow(inode, start, end);
-	unsigned int write_flags = wbc_to_write_flags(wbc);
 
 	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW && !force_cow) {
 		ret = run_delalloc_nocow(inode, locked_page, start, end,
@@ -1712,9 +1751,8 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page,
 	} else {
 		set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
 			&BTRFS_I(inode)->runtime_flags);
-		ret = cow_file_range_async(inode, locked_page, start, end,
-					   page_started, nr_written,
-					   write_flags);
+		ret = cow_file_range_async(inode, wbc, locked_page, start, end,
+					   page_started, nr_written);
 	}
 	if (ret)
 		btrfs_cleanup_ordered_extents(inode, locked_page, start,
@@ -2110,7 +2148,7 @@ static blk_status_t btrfs_submit_bio_hook(struct inode *inode, struct bio *bio,
 	}
 
 mapit:
-	ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
+	ret = btrfs_map_bio(fs_info, bio, mirror_num);
 
 out:
 	if (ret) {
@@ -2214,12 +2252,16 @@ again:
 		mapping_set_error(page->mapping, ret);
 		end_extent_writepage(page, ret, page_start, page_end);
 		ClearPageChecked(page);
-		goto out;
+		goto out_reserved;
 	}
 
 	ClearPageChecked(page);
 	set_page_dirty(page);
+out_reserved:
 	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
+	if (ret)
+		btrfs_delalloc_release_space(inode, data_reserved, page_start,
+					     PAGE_SIZE, true);
 out:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end,
 			     &cached_state);
@@ -2260,8 +2302,7 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end)
 
 	SetPageChecked(page);
 	get_page(page);
-	btrfs_init_work(&fixup->work, btrfs_fixup_helper,
-			btrfs_writepage_fixup_worker, NULL, NULL);
+	btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL);
 	fixup->page = page;
 	btrfs_queue_work(fs_info->fixup_workers, &fixup->work);
 	return -EBUSY;
@@ -2675,7 +2716,7 @@ static noinline int relink_extent_backref(struct btrfs_path *path,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
-	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, root);
 	if (IS_ERR(inode)) {
 		srcu_read_unlock(&fs_info->subvol_srcu, index);
 		return 0;
@@ -2999,7 +3040,7 @@ out_kfree:
 static void btrfs_release_delalloc_bytes(struct btrfs_fs_info *fs_info,
 					 u64 start, u64 len)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 
 	cache = btrfs_lookup_block_group(fs_info, start);
 	ASSERT(cache);
@@ -3027,7 +3068,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 	int compress_type = 0;
 	int ret = 0;
 	u64 logical_len = ordered_extent->len;
-	bool nolock;
+	bool freespace_inode;
 	bool truncated = false;
 	bool range_locked = false;
 	bool clear_new_delalloc_bytes = false;
@@ -3038,7 +3079,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 	    !test_bit(BTRFS_ORDERED_DIRECT, &ordered_extent->flags))
 		clear_new_delalloc_bytes = true;
 
-	nolock = btrfs_is_free_space_inode(BTRFS_I(inode));
+	freespace_inode = btrfs_is_free_space_inode(BTRFS_I(inode));
 
 	if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) {
 		ret = -EIO;
@@ -3069,8 +3110,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset,
 				       ordered_extent->len);
 		btrfs_ordered_update_i_size(inode, 0, ordered_extent);
-		if (nolock)
-			trans = btrfs_join_transaction_nolock(root);
+		if (freespace_inode)
+			trans = btrfs_join_transaction_spacecache(root);
 		else
 			trans = btrfs_join_transaction(root);
 		if (IS_ERR(trans)) {
@@ -3104,8 +3145,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 			EXTENT_DEFRAG, 0, 0, &cached_state);
 	}
 
-	if (nolock)
-		trans = btrfs_join_transaction_nolock(root);
+	if (freespace_inode)
+		trans = btrfs_join_transaction_spacecache(root);
 	else
 		trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans)) {
@@ -3254,7 +3295,6 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ordered_extent *ordered_extent = NULL;
 	struct btrfs_workqueue *wq;
-	btrfs_work_func_t func;
 
 	trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
 
@@ -3263,16 +3303,12 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
 					    end - start + 1, uptodate))
 		return;
 
-	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode)))
 		wq = fs_info->endio_freespace_worker;
-		func = btrfs_freespace_write_helper;
-	} else {
+	else
 		wq = fs_info->endio_write_workers;
-		func = btrfs_endio_write_helper;
-	}
 
-	btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL,
-			NULL);
+	btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL);
 	btrfs_queue_work(wq, &ordered_extent->work);
 }
 
@@ -3531,7 +3567,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 		found_key.objectid = found_key.offset;
 		found_key.type = BTRFS_INODE_ITEM_KEY;
 		found_key.offset = 0;
-		inode = btrfs_iget(fs_info->sb, &found_key, root, NULL);
+		inode = btrfs_iget(fs_info->sb, &found_key, root);
 		ret = PTR_ERR_OR_ZERO(inode);
 		if (ret && ret != -ENOENT)
 			goto out;
@@ -5153,7 +5189,6 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 			hole_em->block_len = 0;
 			hole_em->orig_block_len = 0;
 			hole_em->ram_bytes = hole_size;
-			hole_em->bdev = fs_info->fs_devices->latest_bdev;
 			hole_em->compress_type = BTRFS_COMPRESS_NONE;
 			hole_em->generation = fs_info->generation;
 
@@ -5750,12 +5785,14 @@ static struct inode *btrfs_iget_locked(struct super_block *s,
 	return inode;
 }
 
-/* Get an inode object given its location and corresponding root.
- * Returns in *is_new if the inode was read from disk
+/*
+ * Get an inode object given its location and corresponding root.
+ * Path can be preallocated to prevent recursing back to iget through
+ * allocator. NULL is also valid but may require an additional allocation
+ * later.
  */
 struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
-			      struct btrfs_root *root, int *new,
-			      struct btrfs_path *path)
+			      struct btrfs_root *root, struct btrfs_path *path)
 {
 	struct inode *inode;
 
@@ -5770,8 +5807,6 @@ struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
 		if (!ret) {
 			inode_tree_add(inode);
 			unlock_new_inode(inode);
-			if (new)
-				*new = 1;
 		} else {
 			iget_failed(inode);
 			/*
@@ -5789,9 +5824,9 @@ struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
 }
 
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
-			 struct btrfs_root *root, int *new)
+			 struct btrfs_root *root)
 {
-	return btrfs_iget_path(s, location, root, new, NULL);
+	return btrfs_iget_path(s, location, root, NULL);
 }
 
 static struct inode *new_simple_dir(struct super_block *s,
@@ -5857,7 +5892,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 		return ERR_PTR(ret);
 
 	if (location.type == BTRFS_INODE_ITEM_KEY) {
-		inode = btrfs_iget(dir->i_sb, &location, root, NULL);
+		inode = btrfs_iget(dir->i_sb, &location, root);
 		if (IS_ERR(inode))
 			return inode;
 
@@ -5882,7 +5917,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 		else
 			inode = new_simple_dir(dir->i_sb, &location, sub_root);
 	} else {
-		inode = btrfs_iget(dir->i_sb, &location, sub_root, NULL);
+		inode = btrfs_iget(dir->i_sb, &location, sub_root);
 	}
 	srcu_read_unlock(&fs_info->subvol_srcu, index);
 
@@ -6931,8 +6966,6 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 
 	read_lock(&em_tree->lock);
 	em = lookup_extent_mapping(em_tree, start, len);
-	if (em)
-		em->bdev = fs_info->fs_devices->latest_bdev;
 	read_unlock(&em_tree->lock);
 
 	if (em) {
@@ -6948,7 +6981,6 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 		err = -ENOMEM;
 		goto out;
 	}
-	em->bdev = fs_info->fs_devices->latest_bdev;
 	em->start = EXTENT_MAP_HOLE;
 	em->orig_start = EXTENT_MAP_HOLE;
 	em->len = (u64)-1;
@@ -7207,7 +7239,6 @@ struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
 			err = -ENOMEM;
 			goto out;
 		}
-		em->bdev = NULL;
 
 		ASSERT(hole_em);
 		/*
@@ -7567,7 +7598,6 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
 {
 	struct extent_map_tree *em_tree;
 	struct extent_map *em;
-	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret;
 
 	ASSERT(type == BTRFS_ORDERED_PREALLOC ||
@@ -7585,7 +7615,6 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
 	em->len = len;
 	em->block_len = block_len;
 	em->block_start = block_start;
-	em->bdev = root->fs_info->fs_devices->latest_bdev;
 	em->orig_block_len = orig_block_len;
 	em->ram_bytes = ram_bytes;
 	em->generation = -1;
@@ -7624,6 +7653,8 @@ static int btrfs_get_blocks_direct_read(struct extent_map *em,
 					struct inode *inode,
 					u64 start, u64 len)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+
 	if (em->block_start == EXTENT_MAP_HOLE ||
 			test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 		return -ENOENT;
@@ -7633,7 +7664,7 @@ static int btrfs_get_blocks_direct_read(struct extent_map *em,
 	bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
 		inode->i_blkbits;
 	bh_result->b_size = len;
-	bh_result->b_bdev = em->bdev;
+	bh_result->b_bdev = fs_info->fs_devices->latest_bdev;
 	set_buffer_mapped(bh_result);
 
 	return 0;
@@ -7716,7 +7747,7 @@ skip_cow:
 	bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
 		inode->i_blkbits;
 	bh_result->b_size = len;
-	bh_result->b_bdev = em->bdev;
+	bh_result->b_bdev = fs_info->fs_devices->latest_bdev;
 	set_buffer_mapped(bh_result);
 
 	if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
@@ -7858,7 +7889,7 @@ static inline blk_status_t submit_dio_repair_bio(struct inode *inode,
 	if (ret)
 		return ret;
 
-	ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
+	ret = btrfs_map_bio(fs_info, bio, mirror_num);
 
 	return ret;
 }
@@ -8211,18 +8242,14 @@ static void __endio_write_update_ordered(struct inode *inode,
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ordered_extent *ordered = NULL;
 	struct btrfs_workqueue *wq;
-	btrfs_work_func_t func;
 	u64 ordered_offset = offset;
 	u64 ordered_bytes = bytes;
 	u64 last_offset;
 
-	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode)))
 		wq = fs_info->endio_freespace_worker;
-		func = btrfs_freespace_write_helper;
-	} else {
+	else
 		wq = fs_info->endio_write_workers;
-		func = btrfs_endio_write_helper;
-	}
 
 	while (ordered_offset < offset + bytes) {
 		last_offset = ordered_offset;
@@ -8230,9 +8257,8 @@ static void __endio_write_update_ordered(struct inode *inode,
 							   &ordered_offset,
 							   ordered_bytes,
 							   uptodate)) {
-			btrfs_init_work(&ordered->work, func,
-					finish_ordered_fn,
-					NULL, NULL);
+			btrfs_init_work(&ordered->work, finish_ordered_fn, NULL,
+					NULL);
 			btrfs_queue_work(wq, &ordered->work);
 		}
 		/*
@@ -8389,7 +8415,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio,
 			goto err;
 	}
 map:
-	ret = btrfs_map_bio(fs_info, bio, 0, 0);
+	ret = btrfs_map_bio(fs_info, bio, 0);
 err:
 	return ret;
 }
@@ -9321,7 +9347,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->io_failure_tree.track_uptodate = true;
 	atomic_set(&ei->sync_writers, 0);
 	mutex_init(&ei->log_mutex);
-	mutex_init(&ei->delalloc_mutex);
 	btrfs_ordered_inode_tree_init(&ei->ordered_tree);
 	INIT_LIST_HEAD(&ei->delalloc_inodes);
 	INIT_LIST_HEAD(&ei->delayed_iput);
@@ -9550,6 +9575,9 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 		goto out_notrans;
 	}
 
+	if (dest != root)
+		btrfs_record_root_in_trans(trans, dest);
+
 	/*
 	 * We need to find a free sequence number both in the source and
 	 * in the destination directory for the exchange.
@@ -10116,8 +10144,7 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode
 	init_completion(&work->completion);
 	INIT_LIST_HEAD(&work->list);
 	work->inode = inode;
-	btrfs_init_work(&work->work, btrfs_flush_delalloc_helper,
-			btrfs_run_delalloc_work, NULL, NULL);
+	btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL);
 
 	return work;
 }
@@ -10450,7 +10477,6 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 		em->block_len = ins.offset;
 		em->orig_block_len = ins.offset;
 		em->ram_bytes = ins.offset;
-		em->bdev = fs_info->fs_devices->latest_bdev;
 		set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
 		em->generation = trans->transid;
 
@@ -10806,7 +10832,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 	start = 0;
 	while (start < isize) {
 		u64 logical_block_start, physical_block_start;
-		struct btrfs_block_group_cache *bg;
+		struct btrfs_block_group *bg;
 		u64 len = isize - start;
 
 		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len, 0);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 23272d9154f3..a1ee0b775e65 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -479,10 +479,9 @@ static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
 	return put_user(inode->i_generation, arg);
 }
 
-static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
+static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info,
+					void __user *arg)
 {
-	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_device *device;
 	struct request_queue *q;
 	struct fstrim_range range;
@@ -541,7 +540,7 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
 	return 0;
 }
 
-int btrfs_is_empty_uuid(u8 *uuid)
+int __pure btrfs_is_empty_uuid(u8 *uuid)
 {
 	int i;
 
@@ -1409,7 +1408,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 		return -EINVAL;
 
 	if (do_compress) {
-		if (range->compress_type > BTRFS_COMPRESS_TYPES)
+		if (range->compress_type >= BTRFS_NR_COMPRESS_TYPES)
 			return -EINVAL;
 		if (range->compress_type)
 			compress_type = range->compress_type;
@@ -2462,7 +2461,7 @@ static int btrfs_search_path_in_tree_user(struct inode *inode,
 				goto out;
 			}
 
-			temp_inode = btrfs_iget(sb, &key2, root, NULL);
+			temp_inode = btrfs_iget(sb, &key2, root);
 			if (IS_ERR(temp_inode)) {
 				ret = PTR_ERR(temp_inode);
 				goto out;
@@ -4032,16 +4031,15 @@ out:
 static void get_block_group_info(struct list_head *groups_list,
 				 struct btrfs_ioctl_space_info *space)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 
 	space->total_bytes = 0;
 	space->used_bytes = 0;
 	space->flags = 0;
 	list_for_each_entry(block_group, groups_list, list) {
 		space->flags = block_group->flags;
-		space->total_bytes += block_group->key.offset;
-		space->used_bytes +=
-			btrfs_block_group_used(&block_group->item);
+		space->total_bytes += block_group->length;
+		space->used_bytes += block_group->used;
 	}
 }
 
@@ -4952,10 +4950,9 @@ drop_write:
 	return ret;
 }
 
-static long btrfs_ioctl_quota_rescan_status(struct file *file, void __user *arg)
+static long btrfs_ioctl_quota_rescan_status(struct btrfs_fs_info *fs_info,
+						void __user *arg)
 {
-	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ioctl_quota_rescan_args *qsa;
 	int ret = 0;
 
@@ -4978,11 +4975,9 @@ static long btrfs_ioctl_quota_rescan_status(struct file *file, void __user *arg)
 	return ret;
 }
 
-static long btrfs_ioctl_quota_rescan_wait(struct file *file, void __user *arg)
+static long btrfs_ioctl_quota_rescan_wait(struct btrfs_fs_info *fs_info,
+						void __user *arg)
 {
-	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
@@ -5154,10 +5149,9 @@ out:
 	return ret;
 }
 
-static int btrfs_ioctl_get_fslabel(struct file *file, void __user *arg)
+static int btrfs_ioctl_get_fslabel(struct btrfs_fs_info *fs_info,
+					void __user *arg)
 {
-	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	size_t len;
 	int ret;
 	char label[BTRFS_LABEL_SIZE];
@@ -5241,10 +5235,9 @@ int btrfs_ioctl_get_supported_features(void __user *arg)
 	return 0;
 }
 
-static int btrfs_ioctl_get_features(struct file *file, void __user *arg)
+static int btrfs_ioctl_get_features(struct btrfs_fs_info *fs_info,
+					void __user *arg)
 {
-	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_super_block *super_block = fs_info->super_copy;
 	struct btrfs_ioctl_feature_flags features;
 
@@ -5445,11 +5438,11 @@ long btrfs_ioctl(struct file *file, unsigned int
 	case FS_IOC_GETVERSION:
 		return btrfs_ioctl_getversion(file, argp);
 	case FS_IOC_GETFSLABEL:
-		return btrfs_ioctl_get_fslabel(file, argp);
+		return btrfs_ioctl_get_fslabel(fs_info, argp);
 	case FS_IOC_SETFSLABEL:
 		return btrfs_ioctl_set_fslabel(file, argp);
 	case FITRIM:
-		return btrfs_ioctl_fitrim(file, argp);
+		return btrfs_ioctl_fitrim(fs_info, argp);
 	case BTRFS_IOC_SNAP_CREATE:
 		return btrfs_ioctl_snap_create(file, argp, 0);
 	case BTRFS_IOC_SNAP_CREATE_V2:
@@ -5554,15 +5547,15 @@ long btrfs_ioctl(struct file *file, unsigned int
 	case BTRFS_IOC_QUOTA_RESCAN:
 		return btrfs_ioctl_quota_rescan(file, argp);
 	case BTRFS_IOC_QUOTA_RESCAN_STATUS:
-		return btrfs_ioctl_quota_rescan_status(file, argp);
+		return btrfs_ioctl_quota_rescan_status(fs_info, argp);
 	case BTRFS_IOC_QUOTA_RESCAN_WAIT:
-		return btrfs_ioctl_quota_rescan_wait(file, argp);
+		return btrfs_ioctl_quota_rescan_wait(fs_info, argp);
 	case BTRFS_IOC_DEV_REPLACE:
 		return btrfs_ioctl_dev_replace(fs_info, argp);
 	case BTRFS_IOC_GET_SUPPORTED_FEATURES:
 		return btrfs_ioctl_get_supported_features(argp);
 	case BTRFS_IOC_GET_FEATURES:
-		return btrfs_ioctl_get_features(file, argp);
+		return btrfs_ioctl_get_features(fs_info, argp);
 	case BTRFS_IOC_SET_FEATURES:
 		return btrfs_ioctl_set_features(file, argp);
 	case FS_IOC_FSGETXATTR:
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 7f9a578a1a20..571c4826c428 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -13,65 +13,164 @@
 #include "extent_io.h"
 #include "locking.h"
 
+/*
+ * Extent buffer locking
+ * =====================
+ *
+ * The locks use a custom scheme that allows to do more operations than are
+ * available fromt current locking primitives. The building blocks are still
+ * rwlock and wait queues.
+ *
+ * Required semantics:
+ *
+ * - reader/writer exclusion
+ * - writer/writer exclusion
+ * - reader/reader sharing
+ * - spinning lock semantics
+ * - blocking lock semantics
+ * - try-lock semantics for readers and writers
+ * - one level nesting, allowing read lock to be taken by the same thread that
+ *   already has write lock
+ *
+ * The extent buffer locks (also called tree locks) manage access to eb data
+ * related to the storage in the b-tree (keys, items, but not the individual
+ * members of eb).
+ * We want concurrency of many readers and safe updates. The underlying locking
+ * is done by read-write spinlock and the blocking part is implemented using
+ * counters and wait queues.
+ *
+ * spinning semantics - the low-level rwlock is held so all other threads that
+ *                      want to take it are spinning on it.
+ *
+ * blocking semantics - the low-level rwlock is not held but the counter
+ *                      denotes how many times the blocking lock was held;
+ *                      sleeping is possible
+ *
+ * Write lock always allows only one thread to access the data.
+ *
+ *
+ * Debugging
+ * ---------
+ *
+ * There are additional state counters that are asserted in various contexts,
+ * removed from non-debug build to reduce extent_buffer size and for
+ * performance reasons.
+ *
+ *
+ * Lock nesting
+ * ------------
+ *
+ * A write operation on a tree might indirectly start a look up on the same
+ * tree.  This can happen when btrfs_cow_block locks the tree and needs to
+ * lookup free extents.
+ *
+ * btrfs_cow_block
+ *   ..
+ *   alloc_tree_block_no_bg_flush
+ *     btrfs_alloc_tree_block
+ *       btrfs_reserve_extent
+ *         ..
+ *         load_free_space_cache
+ *           ..
+ *           btrfs_lookup_file_extent
+ *             btrfs_search_slot
+ *
+ *
+ * Locking pattern - spinning
+ * --------------------------
+ *
+ * The simple locking scenario, the +--+ denotes the spinning section.
+ *
+ * +- btrfs_tree_lock
+ * | - extent_buffer::rwlock is held
+ * | - no heavy operations should happen, eg. IO, memory allocations, large
+ * |   structure traversals
+ * +- btrfs_tree_unock
+*
+*
+ * Locking pattern - blocking
+ * --------------------------
+ *
+ * The blocking write uses the following scheme.  The +--+ denotes the spinning
+ * section.
+ *
+ * +- btrfs_tree_lock
+ * |
+ * +- btrfs_set_lock_blocking_write
+ *
+ *   - allowed: IO, memory allocations, etc.
+ *
+ * -- btrfs_tree_unlock - note, no explicit unblocking necessary
+ *
+ *
+ * Blocking read is similar.
+ *
+ * +- btrfs_tree_read_lock
+ * |
+ * +- btrfs_set_lock_blocking_read
+ *
+ *  - heavy operations allowed
+ *
+ * +- btrfs_tree_read_unlock_blocking
+ * |
+ * +- btrfs_tree_read_unlock
+ *
+ */
+
 #ifdef CONFIG_BTRFS_DEBUG
-static void btrfs_assert_spinning_writers_get(struct extent_buffer *eb)
+static inline void btrfs_assert_spinning_writers_get(struct extent_buffer *eb)
 {
 	WARN_ON(eb->spinning_writers);
 	eb->spinning_writers++;
 }
 
-static void btrfs_assert_spinning_writers_put(struct extent_buffer *eb)
+static inline void btrfs_assert_spinning_writers_put(struct extent_buffer *eb)
 {
 	WARN_ON(eb->spinning_writers != 1);
 	eb->spinning_writers--;
 }
 
-static void btrfs_assert_no_spinning_writers(struct extent_buffer *eb)
+static inline void btrfs_assert_no_spinning_writers(struct extent_buffer *eb)
 {
 	WARN_ON(eb->spinning_writers);
 }
 
-static void btrfs_assert_spinning_readers_get(struct extent_buffer *eb)
+static inline void btrfs_assert_spinning_readers_get(struct extent_buffer *eb)
 {
 	atomic_inc(&eb->spinning_readers);
 }
 
-static void btrfs_assert_spinning_readers_put(struct extent_buffer *eb)
+static inline void btrfs_assert_spinning_readers_put(struct extent_buffer *eb)
 {
 	WARN_ON(atomic_read(&eb->spinning_readers) == 0);
 	atomic_dec(&eb->spinning_readers);
 }
 
-static void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb)
+static inline void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb)
 {
 	atomic_inc(&eb->read_locks);
 }
 
-static void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb)
+static inline void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb)
 {
 	atomic_dec(&eb->read_locks);
 }
 
-static void btrfs_assert_tree_read_locked(struct extent_buffer *eb)
+static inline void btrfs_assert_tree_read_locked(struct extent_buffer *eb)
 {
 	BUG_ON(!atomic_read(&eb->read_locks));
 }
 
-static void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb)
+static inline void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb)
 {
 	eb->write_locks++;
 }
 
-static void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb)
+static inline void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb)
 {
 	eb->write_locks--;
 }
 
-void btrfs_assert_tree_locked(struct extent_buffer *eb)
-{
-	BUG_ON(!eb->write_locks);
-}
-
 #else
 static void btrfs_assert_spinning_writers_get(struct extent_buffer *eb) { }
 static void btrfs_assert_spinning_writers_put(struct extent_buffer *eb) { }
@@ -81,11 +180,19 @@ static void btrfs_assert_spinning_readers_get(struct extent_buffer *eb) { }
 static void btrfs_assert_tree_read_locked(struct extent_buffer *eb) { }
 static void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb) { }
 static void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb) { }
-void btrfs_assert_tree_locked(struct extent_buffer *eb) { }
 static void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb) { }
 static void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb) { }
 #endif
 
+/*
+ * Mark already held read lock as blocking. Can be nested in write lock by the
+ * same thread.
+ *
+ * Use when there are potentially long operations ahead so other thread waiting
+ * on the lock will not actively spin but sleep instead.
+ *
+ * The rwlock is released and blocking reader counter is increased.
+ */
 void btrfs_set_lock_blocking_read(struct extent_buffer *eb)
 {
 	trace_btrfs_set_lock_blocking_read(eb);
@@ -102,6 +209,14 @@ void btrfs_set_lock_blocking_read(struct extent_buffer *eb)
 	read_unlock(&eb->lock);
 }
 
+/*
+ * Mark already held write lock as blocking.
+ *
+ * Use when there are potentially long operations ahead so other threads
+ * waiting on the lock will not actively spin but sleep instead.
+ *
+ * The rwlock is released and blocking writers is set.
+ */
 void btrfs_set_lock_blocking_write(struct extent_buffer *eb)
 {
 	trace_btrfs_set_lock_blocking_write(eb);
@@ -115,14 +230,19 @@ void btrfs_set_lock_blocking_write(struct extent_buffer *eb)
 	if (eb->blocking_writers == 0) {
 		btrfs_assert_spinning_writers_put(eb);
 		btrfs_assert_tree_locked(eb);
-		eb->blocking_writers++;
+		WRITE_ONCE(eb->blocking_writers, 1);
 		write_unlock(&eb->lock);
 	}
 }
 
 /*
- * take a spinning read lock.  This will wait for any blocking
- * writers
+ * Lock the extent buffer for read. Wait for any writers (spinning or blocking).
+ * Can be nested in write lock by the same thread.
+ *
+ * Use when the locked section does only lightweight actions and busy waiting
+ * would be cheaper than making other threads do the wait/wake loop.
+ *
+ * The rwlock is held upon exit.
  */
 void btrfs_tree_read_lock(struct extent_buffer *eb)
 {
@@ -134,23 +254,24 @@ again:
 	read_lock(&eb->lock);
 	BUG_ON(eb->blocking_writers == 0 &&
 	       current->pid == eb->lock_owner);
-	if (eb->blocking_writers && current->pid == eb->lock_owner) {
-		/*
-		 * This extent is already write-locked by our thread. We allow
-		 * an additional read lock to be added because it's for the same
-		 * thread. btrfs_find_all_roots() depends on this as it may be
-		 * called on a partly (write-)locked tree.
-		 */
-		BUG_ON(eb->lock_nested);
-		eb->lock_nested = true;
-		read_unlock(&eb->lock);
-		trace_btrfs_tree_read_lock(eb, start_ns);
-		return;
-	}
 	if (eb->blocking_writers) {
+		if (current->pid == eb->lock_owner) {
+			/*
+			 * This extent is already write-locked by our thread.
+			 * We allow an additional read lock to be added because
+			 * it's for the same thread. btrfs_find_all_roots()
+			 * depends on this as it may be called on a partly
+			 * (write-)locked tree.
+			 */
+			BUG_ON(eb->lock_nested);
+			eb->lock_nested = true;
+			read_unlock(&eb->lock);
+			trace_btrfs_tree_read_lock(eb, start_ns);
+			return;
+		}
 		read_unlock(&eb->lock);
 		wait_event(eb->write_lock_wq,
-			   eb->blocking_writers == 0);
+			   READ_ONCE(eb->blocking_writers) == 0);
 		goto again;
 	}
 	btrfs_assert_tree_read_locks_get(eb);
@@ -159,17 +280,19 @@ again:
 }
 
 /*
- * take a spinning read lock.
- * returns 1 if we get the read lock and 0 if we don't
- * this won't wait for blocking writers
+ * Lock extent buffer for read, optimistically expecting that there are no
+ * contending blocking writers. If there are, don't wait.
+ *
+ * Return 1 if the rwlock has been taken, 0 otherwise
  */
 int btrfs_tree_read_lock_atomic(struct extent_buffer *eb)
 {
-	if (eb->blocking_writers)
+	if (READ_ONCE(eb->blocking_writers))
 		return 0;
 
 	read_lock(&eb->lock);
-	if (eb->blocking_writers) {
+	/* Refetch value after lock */
+	if (READ_ONCE(eb->blocking_writers)) {
 		read_unlock(&eb->lock);
 		return 0;
 	}
@@ -180,18 +303,20 @@ int btrfs_tree_read_lock_atomic(struct extent_buffer *eb)
 }
 
 /*
- * returns 1 if we get the read lock and 0 if we don't
- * this won't wait for blocking writers
+ * Try-lock for read. Don't block or wait for contending writers.
+ *
+ * Retrun 1 if the rwlock has been taken, 0 otherwise
  */
 int btrfs_try_tree_read_lock(struct extent_buffer *eb)
 {
-	if (eb->blocking_writers)
+	if (READ_ONCE(eb->blocking_writers))
 		return 0;
 
 	if (!read_trylock(&eb->lock))
 		return 0;
 
-	if (eb->blocking_writers) {
+	/* Refetch value after lock */
+	if (READ_ONCE(eb->blocking_writers)) {
 		read_unlock(&eb->lock);
 		return 0;
 	}
@@ -202,16 +327,19 @@ int btrfs_try_tree_read_lock(struct extent_buffer *eb)
 }
 
 /*
- * returns 1 if we get the read lock and 0 if we don't
- * this won't wait for blocking writers or readers
+ * Try-lock for write. May block until the lock is uncontended, but does not
+ * wait until it is free.
+ *
+ * Retrun 1 if the rwlock has been taken, 0 otherwise
  */
 int btrfs_try_tree_write_lock(struct extent_buffer *eb)
 {
-	if (eb->blocking_writers || atomic_read(&eb->blocking_readers))
+	if (READ_ONCE(eb->blocking_writers) || atomic_read(&eb->blocking_readers))
 		return 0;
 
 	write_lock(&eb->lock);
-	if (eb->blocking_writers || atomic_read(&eb->blocking_readers)) {
+	/* Refetch value after lock */
+	if (READ_ONCE(eb->blocking_writers) || atomic_read(&eb->blocking_readers)) {
 		write_unlock(&eb->lock);
 		return 0;
 	}
@@ -223,7 +351,10 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
 }
 
 /*
- * drop a spinning read lock
+ * Release read lock. Must be used only if the lock is in spinning mode.  If
+ * the read lock is nested, must pair with read lock before the write unlock.
+ *
+ * The rwlock is not held upon exit.
  */
 void btrfs_tree_read_unlock(struct extent_buffer *eb)
 {
@@ -245,7 +376,11 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb)
 }
 
 /*
- * drop a blocking read lock
+ * Release read lock, previously set to blocking by a pairing call to
+ * btrfs_set_lock_blocking_read(). Can be nested in write lock by the same
+ * thread.
+ *
+ * State of rwlock is unchanged, last reader wakes waiting threads.
  */
 void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
 {
@@ -269,8 +404,10 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
 }
 
 /*
- * take a spinning write lock.  This will wait for both
- * blocking readers or writers
+ * Lock for write. Wait for all blocking and spinning readers and writers. This
+ * starts context where reader lock could be nested by the same thread.
+ *
+ * The rwlock is held for write upon exit.
  */
 void btrfs_tree_lock(struct extent_buffer *eb)
 {
@@ -282,9 +419,11 @@ void btrfs_tree_lock(struct extent_buffer *eb)
 	WARN_ON(eb->lock_owner == current->pid);
 again:
 	wait_event(eb->read_lock_wq, atomic_read(&eb->blocking_readers) == 0);
-	wait_event(eb->write_lock_wq, eb->blocking_writers == 0);
+	wait_event(eb->write_lock_wq, READ_ONCE(eb->blocking_writers) == 0);
 	write_lock(&eb->lock);
-	if (atomic_read(&eb->blocking_readers) || eb->blocking_writers) {
+	/* Refetch value after lock */
+	if (atomic_read(&eb->blocking_readers) ||
+	    READ_ONCE(eb->blocking_writers)) {
 		write_unlock(&eb->lock);
 		goto again;
 	}
@@ -295,10 +434,19 @@ again:
 }
 
 /*
- * drop a spinning or a blocking write lock.
+ * Release the write lock, either blocking or spinning (ie. there's no need
+ * for an explicit blocking unlock, like btrfs_tree_read_unlock_blocking).
+ * This also ends the context for nesting, the read lock must have been
+ * released already.
+ *
+ * Tasks blocked and waiting are woken, rwlock is not held upon exit.
  */
 void btrfs_tree_unlock(struct extent_buffer *eb)
 {
+	/*
+	 * This is read both locked and unlocked but always by the same thread
+	 * that already owns the lock so we don't need to use READ_ONCE
+	 */
 	int blockers = eb->blocking_writers;
 
 	BUG_ON(blockers > 1);
@@ -310,7 +458,8 @@ void btrfs_tree_unlock(struct extent_buffer *eb)
 
 	if (blockers) {
 		btrfs_assert_no_spinning_writers(eb);
-		eb->blocking_writers--;
+		/* Unlocked write */
+		WRITE_ONCE(eb->blocking_writers, 0);
 		/*
 		 * We need to order modifying blocking_writers above with
 		 * actually waking up the sleepers to ensure they see the
@@ -322,3 +471,55 @@ void btrfs_tree_unlock(struct extent_buffer *eb)
 		write_unlock(&eb->lock);
 	}
 }
+
+/*
+ * Set all locked nodes in the path to blocking locks.  This should be done
+ * before scheduling
+ */
+void btrfs_set_path_blocking(struct btrfs_path *p)
+{
+	int i;
+
+	for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
+		if (!p->nodes[i] || !p->locks[i])
+			continue;
+		/*
+		 * If we currently have a spinning reader or writer lock this
+		 * will bump the count of blocking holders and drop the
+		 * spinlock.
+		 */
+		if (p->locks[i] == BTRFS_READ_LOCK) {
+			btrfs_set_lock_blocking_read(p->nodes[i]);
+			p->locks[i] = BTRFS_READ_LOCK_BLOCKING;
+		} else if (p->locks[i] == BTRFS_WRITE_LOCK) {
+			btrfs_set_lock_blocking_write(p->nodes[i]);
+			p->locks[i] = BTRFS_WRITE_LOCK_BLOCKING;
+		}
+	}
+}
+
+/*
+ * This releases any locks held in the path starting at level and going all the
+ * way up to the root.
+ *
+ * btrfs_search_slot will keep the lock held on higher nodes in a few corner
+ * cases, such as COW of the block at slot zero in the node.  This ignores
+ * those rules, and it should only be called when there are no more updates to
+ * be done higher up in the tree.
+ */
+void btrfs_unlock_up_safe(struct btrfs_path *path, int level)
+{
+	int i;
+
+	if (path->keep_locks)
+		return;
+
+	for (i = level; i < BTRFS_MAX_LEVEL; i++) {
+		if (!path->nodes[i])
+			continue;
+		if (!path->locks[i])
+			continue;
+		btrfs_tree_unlock_rw(path->nodes[i], path->locks[i]);
+		path->locks[i] = 0;
+	}
+}
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index b775a4207ed9..21a285883e89 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -6,6 +6,8 @@
 #ifndef BTRFS_LOCKING_H
 #define BTRFS_LOCKING_H
 
+#include "extent_io.h"
+
 #define BTRFS_WRITE_LOCK 1
 #define BTRFS_READ_LOCK 2
 #define BTRFS_WRITE_LOCK_BLOCKING 3
@@ -19,11 +21,20 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb);
 void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb);
 void btrfs_set_lock_blocking_read(struct extent_buffer *eb);
 void btrfs_set_lock_blocking_write(struct extent_buffer *eb);
-void btrfs_assert_tree_locked(struct extent_buffer *eb);
 int btrfs_try_tree_read_lock(struct extent_buffer *eb);
 int btrfs_try_tree_write_lock(struct extent_buffer *eb);
 int btrfs_tree_read_lock_atomic(struct extent_buffer *eb);
 
+#ifdef CONFIG_BTRFS_DEBUG
+static inline void btrfs_assert_tree_locked(struct extent_buffer *eb) {
+	BUG_ON(!eb->write_locks);
+}
+#else
+static inline void btrfs_assert_tree_locked(struct extent_buffer *eb) { }
+#endif
+
+void btrfs_set_path_blocking(struct btrfs_path *p);
+void btrfs_unlock_up_safe(struct btrfs_path *path, int level);
 
 static inline void btrfs_tree_unlock_rw(struct extent_buffer *eb, int rw)
 {
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index acad4174f68d..aa9cd11f4b78 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -63,27 +63,7 @@ struct workspace {
 
 static struct workspace_manager wsm;
 
-static void lzo_init_workspace_manager(void)
-{
-	btrfs_init_workspace_manager(&wsm, &btrfs_lzo_compress);
-}
-
-static void lzo_cleanup_workspace_manager(void)
-{
-	btrfs_cleanup_workspace_manager(&wsm);
-}
-
-static struct list_head *lzo_get_workspace(unsigned int level)
-{
-	return btrfs_get_workspace(&wsm, level);
-}
-
-static void lzo_put_workspace(struct list_head *ws)
-{
-	btrfs_put_workspace(&wsm, ws);
-}
-
-static void lzo_free_workspace(struct list_head *ws)
+void lzo_free_workspace(struct list_head *ws)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 
@@ -93,7 +73,7 @@ static void lzo_free_workspace(struct list_head *ws)
 	kfree(workspace);
 }
 
-static struct list_head *lzo_alloc_workspace(unsigned int level)
+struct list_head *lzo_alloc_workspace(unsigned int level)
 {
 	struct workspace *workspace;
 
@@ -131,13 +111,9 @@ static inline size_t read_compress_length(const char *buf)
 	return le32_to_cpu(dlen);
 }
 
-static int lzo_compress_pages(struct list_head *ws,
-			      struct address_space *mapping,
-			      u64 start,
-			      struct page **pages,
-			      unsigned long *out_pages,
-			      unsigned long *total_in,
-			      unsigned long *total_out)
+int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
+		u64 start, struct page **pages, unsigned long *out_pages,
+		unsigned long *total_in, unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0;
@@ -303,7 +279,7 @@ out:
 	return ret;
 }
 
-static int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
+int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0, ret2;
@@ -444,10 +420,9 @@ done:
 	return ret;
 }
 
-static int lzo_decompress(struct list_head *ws, unsigned char *data_in,
-			  struct page *dest_page,
-			  unsigned long start_byte,
-			  size_t srclen, size_t destlen)
+int lzo_decompress(struct list_head *ws, unsigned char *data_in,
+		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	size_t in_len;
@@ -508,15 +483,7 @@ out:
 }
 
 const struct btrfs_compress_op btrfs_lzo_compress = {
-	.init_workspace_manager	= lzo_init_workspace_manager,
-	.cleanup_workspace_manager = lzo_cleanup_workspace_manager,
-	.get_workspace		= lzo_get_workspace,
-	.put_workspace		= lzo_put_workspace,
-	.alloc_workspace	= lzo_alloc_workspace,
-	.free_workspace		= lzo_free_workspace,
-	.compress_pages		= lzo_compress_pages,
-	.decompress_bio		= lzo_decompress_bio,
-	.decompress		= lzo_decompress,
+	.workspace_manager	= &wsm,
 	.max_level		= 1,
 	.default_level		= 1,
 };
diff --git a/fs/btrfs/misc.h b/fs/btrfs/misc.h
index 7d564924dfeb..72bab64ecf60 100644
--- a/fs/btrfs/misc.h
+++ b/fs/btrfs/misc.h
@@ -47,4 +47,15 @@ static inline u64 div_factor_fine(u64 num, int factor)
 	return div_u64(num, 100);
 }
 
+/* Copy of is_power_of_two that is 64bit safe */
+static inline bool is_power_of_two_u64(u64 n)
+{
+	return n != 0 && (n & (n - 1)) == 0;
+}
+
+static inline bool has_single_bit_set(u64 n)
+{
+	return is_power_of_two_u64(n);
+}
+
 #endif
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 24b6c72b9a59..fb09bc2f8e4d 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -547,7 +547,6 @@ u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
 		spin_unlock(&root->ordered_extent_lock);
 
 		btrfs_init_work(&ordered->flush_work,
-				btrfs_flush_delalloc_helper,
 				btrfs_run_ordered_extent_work, NULL, NULL);
 		list_add_tail(&ordered->work_list, &works);
 		btrfs_queue_work(fs_info->flush_workers, &ordered->flush_work);
@@ -573,12 +572,11 @@ u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
 	return count;
 }
 
-u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
+void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
 			     const u64 range_start, const u64 range_len)
 {
 	struct btrfs_root *root;
 	struct list_head splice;
-	u64 total_done = 0;
 	u64 done;
 
 	INIT_LIST_HEAD(&splice);
@@ -598,7 +596,6 @@ u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
 		done = btrfs_wait_ordered_extents(root, nr,
 						  range_start, range_len);
 		btrfs_put_fs_root(root);
-		total_done += done;
 
 		spin_lock(&fs_info->ordered_root_lock);
 		if (nr != U64_MAX) {
@@ -608,8 +605,6 @@ u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
 	list_splice_tail(&splice, &fs_info->ordered_roots);
 	spin_unlock(&fs_info->ordered_root_lock);
 	mutex_unlock(&fs_info->ordered_operations_mutex);
-
-	return total_done;
 }
 
 /*
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 5204171ea962..4eb0319a86d7 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -186,7 +186,7 @@ int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
 			   u8 *sum, int len);
 u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
 			       const u64 range_start, const u64 range_len);
-u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
+void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
 			      const u64 range_start, const u64 range_len);
 void btrfs_lock_and_flush_ordered_range(struct extent_io_tree *tree,
 					struct btrfs_inode *inode, u64 start,
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 9cb50577d982..873b6b694107 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -266,9 +266,9 @@ void btrfs_print_leaf(struct extent_buffer *l)
 					    struct btrfs_block_group_item);
 			pr_info(
 		   "\t\tblock group used %llu chunk_objectid %llu flags %llu\n",
-				btrfs_disk_block_group_used(l, bi),
-				btrfs_disk_block_group_chunk_objectid(l, bi),
-				btrfs_disk_block_group_flags(l, bi));
+				btrfs_block_group_used(l, bi),
+				btrfs_block_group_chunk_objectid(l, bi),
+				btrfs_block_group_flags(l, bi));
 			break;
 		case BTRFS_CHUNK_ITEM_KEY:
 			print_chunk(l, btrfs_item_ptr(l, i,
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index 1e664e0b59b8..deb59e7cfcac 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -416,11 +416,11 @@ int btrfs_subvol_inherit_props(struct btrfs_trans_handle *trans,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
-	parent_inode = btrfs_iget(sb, &key, parent_root, NULL);
+	parent_inode = btrfs_iget(sb, &key, parent_root);
 	if (IS_ERR(parent_inode))
 		return PTR_ERR(parent_inode);
 
-	child_inode = btrfs_iget(sb, &key, root, NULL);
+	child_inode = btrfs_iget(sb, &key, root);
 	if (IS_ERR(child_inode)) {
 		iput(parent_inode);
 		return PTR_ERR(child_inode);
@@ -437,8 +437,6 @@ void __init btrfs_props_init(void)
 {
 	int i;
 
-	hash_init(prop_handlers_ht);
-
 	for (i = 0; i < ARRAY_SIZE(prop_handlers); i++) {
 		struct prop_handler *p = &prop_handlers[i];
 		u64 h = btrfs_name_hash(p->xattr_name, strlen(p->xattr_name));
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 3ad151655eb8..93aeb2e539a4 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1811,7 +1811,7 @@ static int qgroup_trace_extent_swap(struct btrfs_trans_handle* trans,
 		btrfs_item_key_to_cpu(dst_path->nodes[dst_level], &key, 0);
 
 	/* For src_path */
-	extent_buffer_get(src_eb);
+	atomic_inc(&src_eb->refs);
 	src_path->nodes[root_level] = src_eb;
 	src_path->slots[root_level] = dst_path->slots[root_level];
 	src_path->locks[root_level] = 0;
@@ -2067,7 +2067,7 @@ static int qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 	/* For dst_path */
-	extent_buffer_get(dst_eb);
+	atomic_inc(&dst_eb->refs);
 	dst_path->nodes[level] = dst_eb;
 	dst_path->slots[level] = 0;
 	dst_path->locks[level] = 0;
@@ -2126,7 +2126,7 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
 	 * walk back up the tree (adjusting slot pointers as we go)
 	 * and restart the search process.
 	 */
-	extent_buffer_get(root_eb); /* For path */
+	atomic_inc(&root_eb->refs);	/* For path */
 	path->nodes[root_level] = root_eb;
 	path->slots[root_level] = 0;
 	path->locks[root_level] = 0; /* so release_path doesn't try to unlock */
@@ -3277,10 +3277,7 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 	spin_unlock(&fs_info->qgroup_lock);
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
 
-	memset(&fs_info->qgroup_rescan_work, 0,
-	       sizeof(fs_info->qgroup_rescan_work));
 	btrfs_init_work(&fs_info->qgroup_rescan_work,
-			btrfs_qgroup_rescan_helper,
 			btrfs_qgroup_rescan_worker, NULL, NULL);
 	return 0;
 }
@@ -3826,7 +3823,7 @@ out:
  */
 int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans,
 		struct btrfs_root *subvol_root,
-		struct btrfs_block_group_cache *bg,
+		struct btrfs_block_group *bg,
 		struct extent_buffer *subvol_parent, int subvol_slot,
 		struct extent_buffer *reloc_parent, int reloc_slot,
 		u64 last_snapshot)
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 46ba7bd2961c..236f12224d52 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -408,7 +408,7 @@ void btrfs_qgroup_init_swapped_blocks(
 void btrfs_qgroup_clean_swapped_blocks(struct btrfs_root *root);
 int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans,
 		struct btrfs_root *subvol_root,
-		struct btrfs_block_group_cache *bg,
+		struct btrfs_block_group *bg,
 		struct extent_buffer *subvol_parent, int subvol_slot,
 		struct extent_buffer *reloc_parent, int reloc_slot,
 		u64 last_snapshot);
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 57a2ac721985..a8e53c8e7b01 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -190,7 +190,7 @@ static void scrub_parity_work(struct btrfs_work *work);
 
 static void start_async_work(struct btrfs_raid_bio *rbio, btrfs_func_t work_func)
 {
-	btrfs_init_work(&rbio->work, btrfs_rmw_helper, work_func, NULL, NULL);
+	btrfs_init_work(&rbio->work, work_func, NULL, NULL);
 	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
 }
 
@@ -671,8 +671,7 @@ static struct page *rbio_qstripe_page(struct btrfs_raid_bio *rbio, int index)
  */
 static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio)
 {
-	int bucket = rbio_bucket(rbio);
-	struct btrfs_stripe_hash *h = rbio->fs_info->stripe_hash_table->table + bucket;
+	struct btrfs_stripe_hash *h;
 	struct btrfs_raid_bio *cur;
 	struct btrfs_raid_bio *pending;
 	unsigned long flags;
@@ -680,64 +679,63 @@ static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio)
 	struct btrfs_raid_bio *cache_drop = NULL;
 	int ret = 0;
 
+	h = rbio->fs_info->stripe_hash_table->table + rbio_bucket(rbio);
+
 	spin_lock_irqsave(&h->lock, flags);
 	list_for_each_entry(cur, &h->hash_list, hash_list) {
-		if (cur->bbio->raid_map[0] == rbio->bbio->raid_map[0]) {
-			spin_lock(&cur->bio_list_lock);
-
-			/* can we steal this cached rbio's pages? */
-			if (bio_list_empty(&cur->bio_list) &&
-			    list_empty(&cur->plug_list) &&
-			    test_bit(RBIO_CACHE_BIT, &cur->flags) &&
-			    !test_bit(RBIO_RMW_LOCKED_BIT, &cur->flags)) {
-				list_del_init(&cur->hash_list);
-				refcount_dec(&cur->refs);
-
-				steal_rbio(cur, rbio);
-				cache_drop = cur;
-				spin_unlock(&cur->bio_list_lock);
+		if (cur->bbio->raid_map[0] != rbio->bbio->raid_map[0])
+			continue;
 
-				goto lockit;
-			}
+		spin_lock(&cur->bio_list_lock);
 
-			/* can we merge into the lock owner? */
-			if (rbio_can_merge(cur, rbio)) {
-				merge_rbio(cur, rbio);
-				spin_unlock(&cur->bio_list_lock);
-				freeit = rbio;
-				ret = 1;
-				goto out;
-			}
+		/* Can we steal this cached rbio's pages? */
+		if (bio_list_empty(&cur->bio_list) &&
+		    list_empty(&cur->plug_list) &&
+		    test_bit(RBIO_CACHE_BIT, &cur->flags) &&
+		    !test_bit(RBIO_RMW_LOCKED_BIT, &cur->flags)) {
+			list_del_init(&cur->hash_list);
+			refcount_dec(&cur->refs);
 
+			steal_rbio(cur, rbio);
+			cache_drop = cur;
+			spin_unlock(&cur->bio_list_lock);
 
-			/*
-			 * we couldn't merge with the running
-			 * rbio, see if we can merge with the
-			 * pending ones.  We don't have to
-			 * check for rmw_locked because there
-			 * is no way they are inside finish_rmw
-			 * right now
-			 */
-			list_for_each_entry(pending, &cur->plug_list,
-					    plug_list) {
-				if (rbio_can_merge(pending, rbio)) {
-					merge_rbio(pending, rbio);
-					spin_unlock(&cur->bio_list_lock);
-					freeit = rbio;
-					ret = 1;
-					goto out;
-				}
-			}
+			goto lockit;
+		}
 
-			/* no merging, put us on the tail of the plug list,
-			 * our rbio will be started with the currently
-			 * running rbio unlocks
-			 */
-			list_add_tail(&rbio->plug_list, &cur->plug_list);
+		/* Can we merge into the lock owner? */
+		if (rbio_can_merge(cur, rbio)) {
+			merge_rbio(cur, rbio);
 			spin_unlock(&cur->bio_list_lock);
+			freeit = rbio;
 			ret = 1;
 			goto out;
 		}
+
+
+		/*
+		 * We couldn't merge with the running rbio, see if we can merge
+		 * with the pending ones.  We don't have to check for rmw_locked
+		 * because there is no way they are inside finish_rmw right now
+		 */
+		list_for_each_entry(pending, &cur->plug_list, plug_list) {
+			if (rbio_can_merge(pending, rbio)) {
+				merge_rbio(pending, rbio);
+				spin_unlock(&cur->bio_list_lock);
+				freeit = rbio;
+				ret = 1;
+				goto out;
+			}
+		}
+
+		/*
+		 * No merging, put us on the tail of the plug list, our rbio
+		 * will be started with the currently running rbio unlocks
+		 */
+		list_add_tail(&rbio->plug_list, &cur->plug_list);
+		spin_unlock(&cur->bio_list_lock);
+		ret = 1;
+		goto out;
 	}
 lockit:
 	refcount_inc(&rbio->refs);
@@ -1743,8 +1741,7 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	plug = container_of(cb, struct btrfs_plug_cb, cb);
 
 	if (from_schedule) {
-		btrfs_init_work(&plug->work, btrfs_rmw_helper,
-				unplug_work, NULL, NULL);
+		btrfs_init_work(&plug->work, unplug_work, NULL, NULL);
 		btrfs_queue_work(plug->info->rmw_workers,
 				 &plug->work);
 		return;
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index ee6f60547a8d..243a2e44526e 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -227,7 +227,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
 	struct btrfs_fs_info *fs_info = dev->fs_info;
 	int ret;
 	struct reada_zone *zone;
-	struct btrfs_block_group_cache *cache = NULL;
+	struct btrfs_block_group *cache = NULL;
 	u64 start;
 	u64 end;
 	int i;
@@ -248,8 +248,8 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
 	if (!cache)
 		return NULL;
 
-	start = cache->key.objectid;
-	end = start + cache->key.offset - 1;
+	start = cache->start;
+	end = start + cache->length - 1;
 	btrfs_put_block_group(cache);
 
 	zone = kzalloc(sizeof(*zone), GFP_KERNEL);
@@ -752,21 +752,19 @@ static int reada_start_machine_dev(struct btrfs_device *dev)
 static void reada_start_machine_worker(struct btrfs_work *work)
 {
 	struct reada_machine_work *rmw;
-	struct btrfs_fs_info *fs_info;
 	int old_ioprio;
 
 	rmw = container_of(work, struct reada_machine_work, work);
-	fs_info = rmw->fs_info;
-
-	kfree(rmw);
 
 	old_ioprio = IOPRIO_PRIO_VALUE(task_nice_ioclass(current),
 				       task_nice_ioprio(current));
 	set_task_ioprio(current, BTRFS_IOPRIO_READA);
-	__reada_start_machine(fs_info);
+	__reada_start_machine(rmw->fs_info);
 	set_task_ioprio(current, old_ioprio);
 
-	atomic_dec(&fs_info->reada_works_cnt);
+	atomic_dec(&rmw->fs_info->reada_works_cnt);
+
+	kfree(rmw);
 }
 
 static void __reada_start_machine(struct btrfs_fs_info *fs_info)
@@ -821,8 +819,7 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info)
 		/* FIXME we cannot handle this properly right now */
 		BUG();
 	}
-	btrfs_init_work(&rmw->work, btrfs_readahead_helper,
-			reada_start_machine_worker, NULL, NULL);
+	btrfs_init_work(&rmw->work, reada_start_machine_worker, NULL, NULL);
 	rmw->fs_info = fs_info;
 
 	btrfs_queue_work(fs_info->readahead_workers, &rmw->work);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 5cd42b66818c..d897a8e5e430 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -147,7 +147,7 @@ struct file_extent_cluster {
 
 struct reloc_control {
 	/* block group to relocate */
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	/* extent tree */
 	struct btrfs_root *extent_root;
 	/* inode for moving data */
@@ -1560,11 +1560,10 @@ again:
 	return NULL;
 }
 
-static int in_block_group(u64 bytenr,
-			  struct btrfs_block_group_cache *block_group)
+static int in_block_group(u64 bytenr, struct btrfs_block_group *block_group)
 {
-	if (bytenr >= block_group->key.objectid &&
-	    bytenr < block_group->key.objectid + block_group->key.offset)
+	if (bytenr >= block_group->start &&
+	    bytenr < block_group->start + block_group->length)
 		return 1;
 	return 0;
 }
@@ -2246,7 +2245,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 
 	if (btrfs_disk_key_objectid(&root_item->drop_progress) == 0) {
 		level = btrfs_root_level(root_item);
-		extent_buffer_get(reloc_root->node);
+		atomic_inc(&reloc_root->node->refs);
 		path->nodes[level] = reloc_root->node;
 		path->slots[level] = 0;
 	} else {
@@ -3195,7 +3194,6 @@ static noinline_for_stack
 int setup_extent_mapping(struct inode *inode, u64 start, u64 end,
 			 u64 block_start)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
 	struct extent_map *em;
 	int ret = 0;
@@ -3208,7 +3206,6 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end,
 	em->len = end + 1 - start;
 	em->block_len = em->len;
 	em->block_start = block_start;
-	em->bdev = fs_info->fs_devices->latest_bdev;
 	set_bit(EXTENT_FLAG_PINNED, &em->flags);
 
 	lock_extent(&BTRFS_I(inode)->io_tree, start, end);
@@ -3544,7 +3541,7 @@ static int block_use_full_backref(struct reloc_control *rc,
 }
 
 static int delete_block_group_cache(struct btrfs_fs_info *fs_info,
-				    struct btrfs_block_group_cache *block_group,
+				    struct btrfs_block_group *block_group,
 				    struct inode *inode,
 				    u64 ino)
 {
@@ -3560,7 +3557,7 @@ static int delete_block_group_cache(struct btrfs_fs_info *fs_info,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
-	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, root);
 	if (IS_ERR(inode))
 		return -ENOENT;
 
@@ -3863,7 +3860,7 @@ int find_next_extent(struct reloc_control *rc, struct btrfs_path *path,
 	u64 start, end, last;
 	int ret;
 
-	last = rc->block_group->key.objectid + rc->block_group->key.offset;
+	last = rc->block_group->start + rc->block_group->length;
 	while (1) {
 		cond_resched();
 		if (rc->search_start >= last) {
@@ -3980,7 +3977,7 @@ int prepare_to_relocate(struct reloc_control *rc)
 		return -ENOMEM;
 
 	memset(&rc->cluster, 0, sizeof(rc->cluster));
-	rc->search_start = rc->block_group->key.objectid;
+	rc->search_start = rc->block_group->start;
 	rc->extents_found = 0;
 	rc->nodes_relocated = 0;
 	rc->merging_rsv_size = 0;
@@ -4219,7 +4216,7 @@ out:
  */
 static noinline_for_stack
 struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
-				 struct btrfs_block_group_cache *group)
+				 struct btrfs_block_group *group)
 {
 	struct inode *inode = NULL;
 	struct btrfs_trans_handle *trans;
@@ -4246,9 +4243,9 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
 	key.objectid = objectid;
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
-	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, root);
 	BUG_ON(IS_ERR(inode));
-	BTRFS_I(inode)->index_cnt = group->key.objectid;
+	BTRFS_I(inode)->index_cnt = group->start;
 
 	err = btrfs_orphan_add(trans, BTRFS_I(inode));
 out:
@@ -4283,7 +4280,7 @@ static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info)
  * Print the block group being relocated
  */
 static void describe_relocation(struct btrfs_fs_info *fs_info,
-				struct btrfs_block_group_cache *block_group)
+				struct btrfs_block_group *block_group)
 {
 	char buf[128] = {'\0'};
 
@@ -4291,7 +4288,7 @@ static void describe_relocation(struct btrfs_fs_info *fs_info,
 
 	btrfs_info(fs_info,
 		   "relocating block group %llu flags %s",
-		   block_group->key.objectid, buf);
+		   block_group->start, buf);
 }
 
 /*
@@ -4299,7 +4296,7 @@ static void describe_relocation(struct btrfs_fs_info *fs_info,
  */
 int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 {
-	struct btrfs_block_group_cache *bg;
+	struct btrfs_block_group *bg;
 	struct btrfs_root *extent_root = fs_info->extent_root;
 	struct reloc_control *rc;
 	struct inode *inode;
@@ -4326,7 +4323,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 	rc->extent_root = extent_root;
 	rc->block_group = bg;
 
-	ret = btrfs_inc_block_group_ro(rc->block_group);
+	ret = btrfs_inc_block_group_ro(rc->block_group, true);
 	if (ret) {
 		err = ret;
 		goto out;
@@ -4364,8 +4361,8 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 	btrfs_wait_block_group_reservations(rc->block_group);
 	btrfs_wait_nocow_writers(rc->block_group);
 	btrfs_wait_ordered_roots(fs_info, U64_MAX,
-				 rc->block_group->key.objectid,
-				 rc->block_group->key.offset);
+				 rc->block_group->start,
+				 rc->block_group->length);
 
 	while (1) {
 		mutex_lock(&fs_info->cleaner_mutex);
@@ -4405,7 +4402,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 
 	WARN_ON(rc->block_group->pinned > 0);
 	WARN_ON(rc->block_group->reserved > 0);
-	WARN_ON(btrfs_block_group_used(&rc->block_group->item) > 0);
+	WARN_ON(rc->block_group->used > 0);
 out:
 	if (err && rw)
 		btrfs_dec_block_group_ro(rc->block_group);
@@ -4688,7 +4685,7 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
 		       node->new_bytenr != buf->start);
 
 		drop_node_buffer(node);
-		extent_buffer_get(cow);
+		atomic_inc(&cow->refs);
 		node->eb = cow;
 		node->new_bytenr = cow->start;
 
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index f7d4e03f4c5d..21de630b0730 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -389,8 +389,7 @@ static struct full_stripe_lock *search_full_stripe_lock(
  *
  * Caller must ensure @cache is a RAID56 block group.
  */
-static u64 get_full_stripe_logical(struct btrfs_block_group_cache *cache,
-				   u64 bytenr)
+static u64 get_full_stripe_logical(struct btrfs_block_group *cache, u64 bytenr)
 {
 	u64 ret;
 
@@ -404,8 +403,8 @@ static u64 get_full_stripe_logical(struct btrfs_block_group_cache *cache,
 	 * round_down() can only handle power of 2, while RAID56 full
 	 * stripe length can be 64KiB * n, so we need to manually round down.
 	 */
-	ret = div64_u64(bytenr - cache->key.objectid, cache->full_stripe_len) *
-		cache->full_stripe_len + cache->key.objectid;
+	ret = div64_u64(bytenr - cache->start, cache->full_stripe_len) *
+			cache->full_stripe_len + cache->start;
 	return ret;
 }
 
@@ -423,7 +422,7 @@ static u64 get_full_stripe_logical(struct btrfs_block_group_cache *cache,
 static int lock_full_stripe(struct btrfs_fs_info *fs_info, u64 bytenr,
 			    bool *locked_ret)
 {
-	struct btrfs_block_group_cache *bg_cache;
+	struct btrfs_block_group *bg_cache;
 	struct btrfs_full_stripe_locks_tree *locks_root;
 	struct full_stripe_lock *existing;
 	u64 fstripe_start;
@@ -470,7 +469,7 @@ out:
 static int unlock_full_stripe(struct btrfs_fs_info *fs_info, u64 bytenr,
 			      bool locked)
 {
-	struct btrfs_block_group_cache *bg_cache;
+	struct btrfs_block_group *bg_cache;
 	struct btrfs_full_stripe_locks_tree *locks_root;
 	struct full_stripe_lock *fstripe_lock;
 	u64 fstripe_start;
@@ -598,8 +597,8 @@ static noinline_for_stack struct scrub_ctx *scrub_setup_ctx(
 		sbio->index = i;
 		sbio->sctx = sctx;
 		sbio->page_count = 0;
-		btrfs_init_work(&sbio->work, btrfs_scrub_helper,
-				scrub_bio_end_io_worker, NULL, NULL);
+		btrfs_init_work(&sbio->work, scrub_bio_end_io_worker, NULL,
+				NULL);
 
 		if (i != SCRUB_BIOS_PER_SCTX - 1)
 			sctx->bios[i]->next_free = i + 1;
@@ -1720,8 +1719,7 @@ static void scrub_wr_bio_end_io(struct bio *bio)
 	sbio->status = bio->bi_status;
 	sbio->bio = bio;
 
-	btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper,
-			 scrub_wr_bio_end_io_worker, NULL, NULL);
+	btrfs_init_work(&sbio->work, scrub_wr_bio_end_io_worker, NULL, NULL);
 	btrfs_queue_work(fs_info->scrub_wr_completion_workers, &sbio->work);
 }
 
@@ -2149,14 +2147,13 @@ static void scrub_missing_raid56_worker(struct btrfs_work *work)
 		scrub_write_block_to_dev_replace(sblock);
 	}
 
-	scrub_block_put(sblock);
-
 	if (sctx->is_dev_replace && sctx->flush_all_writes) {
 		mutex_lock(&sctx->wr_lock);
 		scrub_wr_submit(sctx);
 		mutex_unlock(&sctx->wr_lock);
 	}
 
+	scrub_block_put(sblock);
 	scrub_pending_bio_dec(sctx);
 }
 
@@ -2204,8 +2201,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
 		raid56_add_scrub_pages(rbio, spage->page, spage->logical);
 	}
 
-	btrfs_init_work(&sblock->work, btrfs_scrub_helper,
-			scrub_missing_raid56_worker, NULL, NULL);
+	btrfs_init_work(&sblock->work, scrub_missing_raid56_worker, NULL, NULL);
 	scrub_block_get(sblock);
 	scrub_pending_bio_inc(sctx);
 	raid56_submit_missing_rbio(rbio);
@@ -2743,8 +2739,8 @@ static void scrub_parity_bio_endio(struct bio *bio)
 
 	bio_put(bio);
 
-	btrfs_init_work(&sparity->work, btrfs_scrubparity_helper,
-			scrub_parity_bio_endio_worker, NULL, NULL);
+	btrfs_init_work(&sparity->work, scrub_parity_bio_endio_worker, NULL,
+			NULL);
 	btrfs_queue_work(fs_info->scrub_parity_workers, &sparity->work);
 }
 
@@ -3420,7 +3416,7 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
 					  struct btrfs_device *scrub_dev,
 					  u64 chunk_offset, u64 length,
 					  u64 dev_offset,
-					  struct btrfs_block_group_cache *cache)
+					  struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
 	struct extent_map_tree *map_tree = &fs_info->mapping_tree;
@@ -3484,7 +3480,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 	struct extent_buffer *l;
 	struct btrfs_key key;
 	struct btrfs_key found_key;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 
 	path = btrfs_alloc_path();
@@ -3563,46 +3559,26 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		 * -> btrfs_scrub_pause()
 		 */
 		scrub_pause_on(fs_info);
-		ret = btrfs_inc_block_group_ro(cache);
-		if (!ret && sctx->is_dev_replace) {
-			/*
-			 * If we are doing a device replace wait for any tasks
-			 * that started delalloc right before we set the block
-			 * group to RO mode, as they might have just allocated
-			 * an extent from it or decided they could do a nocow
-			 * write. And if any such tasks did that, wait for their
-			 * ordered extents to complete and then commit the
-			 * current transaction, so that we can later see the new
-			 * extent items in the extent tree - the ordered extents
-			 * create delayed data references (for cow writes) when
-			 * they complete, which will be run and insert the
-			 * corresponding extent items into the extent tree when
-			 * we commit the transaction they used when running
-			 * inode.c:btrfs_finish_ordered_io(). We later use
-			 * the commit root of the extent tree to find extents
-			 * to copy from the srcdev into the tgtdev, and we don't
-			 * want to miss any new extents.
-			 */
-			btrfs_wait_block_group_reservations(cache);
-			btrfs_wait_nocow_writers(cache);
-			ret = btrfs_wait_ordered_roots(fs_info, U64_MAX,
-						       cache->key.objectid,
-						       cache->key.offset);
-			if (ret > 0) {
-				struct btrfs_trans_handle *trans;
-
-				trans = btrfs_join_transaction(root);
-				if (IS_ERR(trans))
-					ret = PTR_ERR(trans);
-				else
-					ret = btrfs_commit_transaction(trans);
-				if (ret) {
-					scrub_pause_off(fs_info);
-					btrfs_put_block_group(cache);
-					break;
-				}
-			}
-		}
+
+		/*
+		 * Don't do chunk preallocation for scrub.
+		 *
+		 * This is especially important for SYSTEM bgs, or we can hit
+		 * -EFBIG from btrfs_finish_chunk_alloc() like:
+		 * 1. The only SYSTEM bg is marked RO.
+		 *    Since SYSTEM bg is small, that's pretty common.
+		 * 2. New SYSTEM bg will be allocated
+		 *    Due to regular version will allocate new chunk.
+		 * 3. New SYSTEM bg is empty and will get cleaned up
+		 *    Before cleanup really happens, it's marked RO again.
+		 * 4. Empty SYSTEM bg get scrubbed
+		 *    We go back to 2.
+		 *
+		 * This can easily boost the amount of SYSTEM chunks if cleaner
+		 * thread can't be triggered fast enough, and use up all space
+		 * of btrfs_super_block::sys_chunk_array
+		 */
+		ret = btrfs_inc_block_group_ro(cache, false);
 		scrub_pause_off(fs_info);
 
 		if (ret == 0) {
@@ -3623,7 +3599,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 			break;
 		}
 
-		down_write(&fs_info->dev_replace.rwsem);
+		down_write(&dev_replace->rwsem);
 		dev_replace->cursor_right = found_key.offset + length;
 		dev_replace->cursor_left = found_key.offset;
 		dev_replace->item_needs_writeback = 1;
@@ -3664,10 +3640,10 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 
 		scrub_pause_off(fs_info);
 
-		down_write(&fs_info->dev_replace.rwsem);
+		down_write(&dev_replace->rwsem);
 		dev_replace->cursor_left = dev_replace->cursor_right;
 		dev_replace->item_needs_writeback = 1;
-		up_write(&fs_info->dev_replace.rwsem);
+		up_write(&dev_replace->rwsem);
 
 		if (ro_set)
 			btrfs_dec_block_group_ro(cache);
@@ -3681,7 +3657,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		 */
 		spin_lock(&cache->lock);
 		if (!cache->removed && !cache->ro && cache->reserved == 0 &&
-		    btrfs_block_group_used(&cache->item) == 0) {
+		    cache->used == 0) {
 			spin_unlock(&cache->lock);
 			btrfs_mark_bg_unused(cache);
 		} else {
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 123ac54af071..ae2db5eb1549 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -25,6 +25,14 @@
 #include "compression.h"
 
 /*
+ * Maximum number of references an extent can have in order for us to attempt to
+ * issue clone operations instead of write operations. This currently exists to
+ * avoid hitting limitations of the backreference walking code (taking a lot of
+ * time and using too much memory for extents with large number of references).
+ */
+#define SEND_MAX_EXTENT_REFS	64
+
+/*
  * A fs_path is a helper to dynamically build path names with unknown size.
  * It reallocates the internal buffer on demand.
  * It allows fast adding of path elements on the right side (normal path) and
@@ -1248,12 +1256,20 @@ static int __iterate_backrefs(u64 ino, u64 offset, u64 root, void *ctx_)
 	 */
 	if (found->root == bctx->sctx->send_root) {
 		/*
-		 * TODO for the moment we don't accept clones from the inode
-		 * that is currently send. We may change this when
-		 * BTRFS_IOC_CLONE_RANGE supports cloning from and to the same
-		 * file.
+		 * If the source inode was not yet processed we can't issue a
+		 * clone operation, as the source extent does not exist yet at
+		 * the destination of the stream.
 		 */
-		if (ino >= bctx->cur_objectid)
+		if (ino > bctx->cur_objectid)
+			return 0;
+		/*
+		 * We clone from the inode currently being sent as long as the
+		 * source extent is already processed, otherwise we could try
+		 * to clone from an extent that does not exist yet at the
+		 * destination of the stream.
+		 */
+		if (ino == bctx->cur_objectid &&
+		    offset >= bctx->sctx->cur_inode_next_write_offset)
 			return 0;
 	}
 
@@ -1302,6 +1318,7 @@ static int find_extent_clone(struct send_ctx *sctx,
 	struct clone_root *cur_clone_root;
 	struct btrfs_key found_key;
 	struct btrfs_path *tmp_path;
+	struct btrfs_extent_item *ei;
 	int compressed;
 	u32 i;
 
@@ -1349,7 +1366,6 @@ static int find_extent_clone(struct send_ctx *sctx,
 	ret = extent_from_logical(fs_info, disk_byte, tmp_path,
 				  &found_key, &flags);
 	up_read(&fs_info->commit_root_sem);
-	btrfs_release_path(tmp_path);
 
 	if (ret < 0)
 		goto out;
@@ -1358,6 +1374,21 @@ static int find_extent_clone(struct send_ctx *sctx,
 		goto out;
 	}
 
+	ei = btrfs_item_ptr(tmp_path->nodes[0], tmp_path->slots[0],
+			    struct btrfs_extent_item);
+	/*
+	 * Backreference walking (iterate_extent_inodes() below) is currently
+	 * too expensive when an extent has a large number of references, both
+	 * in time spent and used memory. So for now just fallback to write
+	 * operations instead of clone operations when an extent has more than
+	 * a certain amount of references.
+	 */
+	if (btrfs_extent_refs(tmp_path->nodes[0], ei) > SEND_MAX_EXTENT_REFS) {
+		ret = -ENOENT;
+		goto out;
+	}
+	btrfs_release_path(tmp_path);
+
 	/*
 	 * Setup the clone roots.
 	 */
@@ -4779,7 +4810,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
-	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, root);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index e8a4b0ebe97f..f09aa6ee9113 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -10,7 +10,7 @@
 #include "transaction.h"
 #include "block-group.h"
 
-u64 btrfs_space_info_used(struct btrfs_space_info *s_info,
+u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info,
 			  bool may_use_included)
 {
 	ASSERT(s_info);
@@ -58,7 +58,6 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags)
 	spin_lock_init(&space_info->lock);
 	space_info->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
 	space_info->force_alloc = CHUNK_ALLOC_NO_FORCE;
-	init_waitqueue_head(&space_info->wait);
 	INIT_LIST_HEAD(&space_info->ro_bgs);
 	INIT_LIST_HEAD(&space_info->tickets);
 	INIT_LIST_HEAD(&space_info->priority_tickets);
@@ -285,7 +284,7 @@ void btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
 			   struct btrfs_space_info *info, u64 bytes,
 			   int dump_block_groups)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	int index = 0;
 
 	spin_lock(&info->lock);
@@ -301,8 +300,7 @@ again:
 		spin_lock(&cache->lock);
 		btrfs_info(fs_info,
 			"block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s",
-			cache->key.objectid, cache->key.offset,
-			btrfs_block_group_used(&cache->item), cache->pinned,
+			cache->start, cache->length, cache->used, cache->pinned,
 			cache->reserved, cache->ro ? "[readonly]" : "");
 		btrfs_dump_free_space(cache, bytes);
 		spin_unlock(&cache->lock);
diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h
index 8867e84aa33d..1a349e3f9cc1 100644
--- a/fs/btrfs/space-info.h
+++ b/fs/btrfs/space-info.h
@@ -63,7 +63,6 @@ struct btrfs_space_info {
 	struct rw_semaphore groups_sem;
 	/* for block groups in our same type */
 	struct list_head block_groups[BTRFS_NR_RAID_TYPES];
-	wait_queue_head_t wait;
 
 	struct kobject kobj;
 	struct kobject *block_group_kobjs[BTRFS_NR_RAID_TYPES];
@@ -116,7 +115,7 @@ void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags,
 			     struct btrfs_space_info **space_info);
 struct btrfs_space_info *btrfs_find_space_info(struct btrfs_fs_info *info,
 					       u64 flags);
-u64 btrfs_space_info_used(struct btrfs_space_info *s_info,
+u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info,
 			  bool may_use_included);
 void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
 void btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 1b151af25772..a98c3c71fc54 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -66,7 +66,7 @@ static struct file_system_type btrfs_root_fs_type;
 
 static int btrfs_remount(struct super_block *sb, int *flags, char *data);
 
-const char *btrfs_decode_error(int errno)
+const char * __attribute_const__ btrfs_decode_error(int errno)
 {
 	char *errstr = "unknown";
 
@@ -187,7 +187,7 @@ static struct ratelimit_state printk_limits[] = {
 	RATELIMIT_STATE_INIT(printk_limits[7], DEFAULT_RATELIMIT_INTERVAL, 100),
 };
 
-void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...)
+void __cold btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...)
 {
 	char lvl[PRINTK_MAX_SINGLE_HEADER_LEN + 1] = "\0";
 	struct va_format vaf;
@@ -1219,7 +1219,7 @@ static int btrfs_fill_super(struct super_block *sb,
 	key.objectid = BTRFS_FIRST_FREE_OBJECTID;
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
-	inode = btrfs_iget(sb, &key, fs_info->fs_root, NULL);
+	inode = btrfs_iget(sb, &key, fs_info->fs_root);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto fail_close;
@@ -1669,7 +1669,6 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info,
 
 	btrfs_workqueue_set_max(fs_info->workers, new_pool_size);
 	btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size);
-	btrfs_workqueue_set_max(fs_info->submit_workers, new_pool_size);
 	btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size);
 	btrfs_workqueue_set_max(fs_info->endio_workers, new_pool_size);
 	btrfs_workqueue_set_max(fs_info->endio_meta_workers, new_pool_size);
@@ -1936,6 +1935,10 @@ static inline int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
 		num_stripes = nr_devices;
 	else if (type & BTRFS_BLOCK_GROUP_RAID1)
 		num_stripes = 2;
+	else if (type & BTRFS_BLOCK_GROUP_RAID1C3)
+		num_stripes = 3;
+	else if (type & BTRFS_BLOCK_GROUP_RAID1C4)
+		num_stripes = 4;
 	else if (type & BTRFS_BLOCK_GROUP_RAID10)
 		num_stripes = 4;
 
@@ -2022,7 +2025,6 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb);
 	struct btrfs_super_block *disk_super = fs_info->super_copy;
-	struct list_head *head = &fs_info->space_info;
 	struct btrfs_space_info *found;
 	u64 total_used = 0;
 	u64 total_free_data = 0;
@@ -2036,7 +2038,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	int mixed = 0;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(found, head, list) {
+	list_for_each_entry_rcu(found, &fs_info->space_info, list) {
 		if (found->flags & BTRFS_BLOCK_GROUP_DATA) {
 			int i;
 
@@ -2360,10 +2362,14 @@ static int __init init_btrfs_fs(void)
 	if (err)
 		goto free_cachep;
 
-	err = extent_map_init();
+	err = extent_state_cache_init();
 	if (err)
 		goto free_extent_io;
 
+	err = extent_map_init();
+	if (err)
+		goto free_extent_state_cache;
+
 	err = ordered_data_init();
 	if (err)
 		goto free_extent_map;
@@ -2422,6 +2428,8 @@ free_ordered_data:
 	ordered_data_exit();
 free_extent_map:
 	extent_map_exit();
+free_extent_state_cache:
+	extent_state_cache_exit();
 free_extent_io:
 	extent_io_exit();
 free_cachep:
@@ -2442,6 +2450,7 @@ static void __exit exit_btrfs_fs(void)
 	btrfs_prelim_ref_exit();
 	ordered_data_exit();
 	extent_map_exit();
+	extent_state_cache_exit();
 	extent_io_exit();
 	btrfs_interface_exit();
 	btrfs_end_io_wq_exit();
@@ -2456,3 +2465,6 @@ module_exit(exit_btrfs_fs)
 
 MODULE_LICENSE("GPL");
 MODULE_SOFTDEP("pre: crc32c");
+MODULE_SOFTDEP("pre: xxhash64");
+MODULE_SOFTDEP("pre: sha256");
+MODULE_SOFTDEP("pre: blake2b-256");
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index f6d3c80f2e28..5ebbe8a5ee76 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -9,6 +9,7 @@
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/bug.h>
+#include <crypto/hash.h>
 
 #include "ctree.h"
 #include "disk-io.h"
@@ -258,6 +259,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA);
 BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES);
 BTRFS_FEAT_ATTR_INCOMPAT(metadata_uuid, METADATA_UUID);
 BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE);
+BTRFS_FEAT_ATTR_INCOMPAT(raid1c34, RAID1C34);
 
 static struct attribute *btrfs_supported_feature_attrs[] = {
 	BTRFS_FEAT_ATTR_PTR(mixed_backref),
@@ -272,6 +274,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = {
 	BTRFS_FEAT_ATTR_PTR(no_holes),
 	BTRFS_FEAT_ATTR_PTR(metadata_uuid),
 	BTRFS_FEAT_ATTR_PTR(free_space_tree),
+	BTRFS_FEAT_ATTR_PTR(raid1c34),
 	NULL
 };
 
@@ -295,8 +298,30 @@ static ssize_t rmdir_subvol_show(struct kobject *kobj,
 }
 BTRFS_ATTR(static_feature, rmdir_subvol, rmdir_subvol_show);
 
+static ssize_t supported_checksums_show(struct kobject *kobj,
+					struct kobj_attribute *a, char *buf)
+{
+	ssize_t ret = 0;
+	int i;
+
+	for (i = 0; i < btrfs_get_num_csums(); i++) {
+		/*
+		 * This "trick" only works as long as 'enum btrfs_csum_type' has
+		 * no holes in it
+		 */
+		ret += snprintf(buf + ret, PAGE_SIZE - ret, "%s%s",
+				(i == 0 ? "" : " "), btrfs_super_csum_name(i));
+
+	}
+
+	ret += snprintf(buf + ret, PAGE_SIZE - ret, "\n");
+	return ret;
+}
+BTRFS_ATTR(static_feature, supported_checksums, supported_checksums_show);
+
 static struct attribute *btrfs_supported_static_feature_attrs[] = {
 	BTRFS_ATTR_PTR(static_feature, rmdir_subvol),
+	BTRFS_ATTR_PTR(static_feature, supported_checksums),
 	NULL
 };
 
@@ -372,16 +397,16 @@ static ssize_t raid_bytes_show(struct kobject *kobj,
 
 {
 	struct btrfs_space_info *sinfo = to_space_info(kobj->parent);
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	int index = btrfs_bg_flags_to_raid_index(to_raid_kobj(kobj)->flags);
 	u64 val = 0;
 
 	down_read(&sinfo->groups_sem);
 	list_for_each_entry(block_group, &sinfo->block_groups[index], list) {
 		if (&attr->attr == BTRFS_ATTR_PTR(raid, total_bytes))
-			val += block_group->key.offset;
+			val += block_group->length;
 		else
-			val += btrfs_block_group_used(&block_group->item);
+			val += block_group->used;
 	}
 	up_read(&sinfo->groups_sem);
 	return snprintf(buf, PAGE_SIZE, "%llu\n", val);
@@ -604,6 +629,19 @@ static ssize_t btrfs_metadata_uuid_show(struct kobject *kobj,
 
 BTRFS_ATTR(, metadata_uuid, btrfs_metadata_uuid_show);
 
+static ssize_t btrfs_checksum_show(struct kobject *kobj,
+				   struct kobj_attribute *a, char *buf)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+	u16 csum_type = btrfs_super_csum_type(fs_info->super_copy);
+
+	return snprintf(buf, PAGE_SIZE, "%s (%s)\n",
+			btrfs_super_csum_name(csum_type),
+			crypto_shash_driver_name(fs_info->csum_shash));
+}
+
+BTRFS_ATTR(, checksum, btrfs_checksum_show);
+
 static const struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(, label),
 	BTRFS_ATTR_PTR(, nodesize),
@@ -611,6 +649,7 @@ static const struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(, clone_alignment),
 	BTRFS_ATTR_PTR(, quota_override),
 	BTRFS_ATTR_PTR(, metadata_uuid),
+	BTRFS_ATTR_PTR(, checksum),
 	NULL,
 };
 
@@ -822,7 +861,7 @@ static void init_feature_attrs(void)
  * Create a sysfs entry for a given block group type at path
  * /sys/fs/btrfs/UUID/allocation/data/TYPE
  */
-void btrfs_sysfs_add_block_group_type(struct btrfs_block_group_cache *cache)
+void btrfs_sysfs_add_block_group_type(struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_space_info *space_info = cache->space_info;
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index 610e9c36a94c..e10c3adfc30f 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -32,7 +32,7 @@ int __init btrfs_init_sysfs(void);
 void __cold btrfs_exit_sysfs(void);
 int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info);
 void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info);
-void btrfs_sysfs_add_block_group_type(struct btrfs_block_group_cache *cache);
+void btrfs_sysfs_add_block_group_type(struct btrfs_block_group *cache);
 int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info,
 				    struct btrfs_space_info *space_info);
 void btrfs_sysfs_remove_space_info(struct btrfs_space_info *space_info);
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 99fe9bf3fdac..a7aca4141788 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -202,11 +202,11 @@ void btrfs_free_dummy_root(struct btrfs_root *root)
 	kfree(root);
 }
 
-struct btrfs_block_group_cache *
+struct btrfs_block_group *
 btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info,
 			      unsigned long length)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 
 	cache = kzalloc(sizeof(*cache), GFP_KERNEL);
 	if (!cache)
@@ -218,9 +218,8 @@ btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info,
 		return NULL;
 	}
 
-	cache->key.objectid = 0;
-	cache->key.offset = length;
-	cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+	cache->start = 0;
+	cache->length = length;
 	cache->full_stripe_len = fs_info->sectorsize;
 	cache->fs_info = fs_info;
 
@@ -233,7 +232,7 @@ btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info,
 	return cache;
 }
 
-void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache)
+void btrfs_free_dummy_block_group(struct btrfs_block_group *cache)
 {
 	if (!cache)
 		return;
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
index ee277bbd939b..9e52527357d8 100644
--- a/fs/btrfs/tests/btrfs-tests.h
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -41,9 +41,9 @@ struct inode *btrfs_new_test_inode(void);
 struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize);
 void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info);
 void btrfs_free_dummy_root(struct btrfs_root *root);
-struct btrfs_block_group_cache *
+struct btrfs_block_group *
 btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info, unsigned long length);
-void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache);
+void btrfs_free_dummy_block_group(struct btrfs_block_group *cache);
 void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans,
 			    struct btrfs_fs_info *fs_info);
 #else
diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c
index 43ec7060fcd2..aebdf23f0cdd 100644
--- a/fs/btrfs/tests/free-space-tests.c
+++ b/fs/btrfs/tests/free-space-tests.c
@@ -17,7 +17,7 @@
  * entry and remove space from either end and the middle, and make sure we can
  * remove space that covers adjacent extent entries.
  */
-static int test_extents(struct btrfs_block_group_cache *cache)
+static int test_extents(struct btrfs_block_group *cache)
 {
 	int ret = 0;
 
@@ -87,8 +87,7 @@ static int test_extents(struct btrfs_block_group_cache *cache)
 	return 0;
 }
 
-static int test_bitmaps(struct btrfs_block_group_cache *cache,
-			u32 sectorsize)
+static int test_bitmaps(struct btrfs_block_group *cache, u32 sectorsize)
 {
 	u64 next_bitmap_offset;
 	int ret;
@@ -156,7 +155,7 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache,
 }
 
 /* This is the high grade jackassery */
-static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
+static int test_bitmaps_and_extents(struct btrfs_block_group *cache,
 				    u32 sectorsize)
 {
 	u64 bitmap_offset = (u64)(BITS_PER_BITMAP * sectorsize);
@@ -331,7 +330,7 @@ static bool test_use_bitmap(struct btrfs_free_space_ctl *ctl,
 
 /* Used by test_steal_space_from_bitmap_to_extent(). */
 static int
-check_num_extents_and_bitmaps(const struct btrfs_block_group_cache *cache,
+check_num_extents_and_bitmaps(const struct btrfs_block_group *cache,
 			      const int num_extents,
 			      const int num_bitmaps)
 {
@@ -351,7 +350,7 @@ check_num_extents_and_bitmaps(const struct btrfs_block_group_cache *cache,
 }
 
 /* Used by test_steal_space_from_bitmap_to_extent(). */
-static int check_cache_empty(struct btrfs_block_group_cache *cache)
+static int check_cache_empty(struct btrfs_block_group *cache)
 {
 	u64 offset;
 	u64 max_extent_size;
@@ -393,7 +392,7 @@ static int check_cache_empty(struct btrfs_block_group_cache *cache)
  * requests.
  */
 static int
-test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
+test_steal_space_from_bitmap_to_extent(struct btrfs_block_group *cache,
 				       u32 sectorsize)
 {
 	int ret;
@@ -829,7 +828,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_fs_info *fs_info;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	struct btrfs_root *root = NULL;
 	int ret = -ENOMEM;
 
diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c
index bc92df977630..1a846bf6e197 100644
--- a/fs/btrfs/tests/free-space-tree-tests.c
+++ b/fs/btrfs/tests/free-space-tree-tests.c
@@ -18,7 +18,7 @@ struct free_space_extent {
 
 static int __check_free_space_extents(struct btrfs_trans_handle *trans,
 				      struct btrfs_fs_info *fs_info,
-				      struct btrfs_block_group_cache *cache,
+				      struct btrfs_block_group *cache,
 				      struct btrfs_path *path,
 				      const struct free_space_extent * const extents,
 				      unsigned int num_extents)
@@ -48,7 +48,7 @@ static int __check_free_space_extents(struct btrfs_trans_handle *trans,
 	if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) {
 		if (path->slots[0] != 0)
 			goto invalid;
-		end = cache->key.objectid + cache->key.offset;
+		end = cache->start + cache->length;
 		i = 0;
 		while (++path->slots[0] < btrfs_header_nritems(path->nodes[0])) {
 			btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
@@ -107,7 +107,7 @@ invalid:
 
 static int check_free_space_extents(struct btrfs_trans_handle *trans,
 				    struct btrfs_fs_info *fs_info,
-				    struct btrfs_block_group_cache *cache,
+				    struct btrfs_block_group *cache,
 				    struct btrfs_path *path,
 				    const struct free_space_extent * const extents,
 				    unsigned int num_extents)
@@ -150,12 +150,12 @@ static int check_free_space_extents(struct btrfs_trans_handle *trans,
 
 static int test_empty_block_group(struct btrfs_trans_handle *trans,
 				  struct btrfs_fs_info *fs_info,
-				  struct btrfs_block_group_cache *cache,
+				  struct btrfs_block_group *cache,
 				  struct btrfs_path *path,
 				  u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid, cache->key.offset},
+		{cache->start, cache->length},
 	};
 
 	return check_free_space_extents(trans, fs_info, cache, path,
@@ -164,7 +164,7 @@ static int test_empty_block_group(struct btrfs_trans_handle *trans,
 
 static int test_remove_all(struct btrfs_trans_handle *trans,
 			   struct btrfs_fs_info *fs_info,
-			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_block_group *cache,
 			   struct btrfs_path *path,
 			   u32 alignment)
 {
@@ -172,8 +172,8 @@ static int test_remove_all(struct btrfs_trans_handle *trans,
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid,
-					    cache->key.offset);
+					    cache->start,
+					    cache->length);
 	if (ret) {
 		test_err("could not remove free space");
 		return ret;
@@ -185,18 +185,17 @@ static int test_remove_all(struct btrfs_trans_handle *trans,
 
 static int test_remove_beginning(struct btrfs_trans_handle *trans,
 				 struct btrfs_fs_info *fs_info,
-				 struct btrfs_block_group_cache *cache,
+				 struct btrfs_block_group *cache,
 				 struct btrfs_path *path,
 				 u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid + alignment,
-			cache->key.offset - alignment},
+		{cache->start + alignment, cache->length - alignment},
 	};
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid, alignment);
+					    cache->start, alignment);
 	if (ret) {
 		test_err("could not remove free space");
 		return ret;
@@ -209,19 +208,18 @@ static int test_remove_beginning(struct btrfs_trans_handle *trans,
 
 static int test_remove_end(struct btrfs_trans_handle *trans,
 			   struct btrfs_fs_info *fs_info,
-			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_block_group *cache,
 			   struct btrfs_path *path,
 			   u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid, cache->key.offset - alignment},
+		{cache->start, cache->length - alignment},
 	};
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid +
-					    cache->key.offset - alignment,
-					    alignment);
+				    cache->start + cache->length - alignment,
+				    alignment);
 	if (ret) {
 		test_err("could not remove free space");
 		return ret;
@@ -233,19 +231,18 @@ static int test_remove_end(struct btrfs_trans_handle *trans,
 
 static int test_remove_middle(struct btrfs_trans_handle *trans,
 			      struct btrfs_fs_info *fs_info,
-			      struct btrfs_block_group_cache *cache,
+			      struct btrfs_block_group *cache,
 			      struct btrfs_path *path,
 			      u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid, alignment},
-		{cache->key.objectid + 2 * alignment,
-			cache->key.offset - 2 * alignment},
+		{cache->start, alignment},
+		{cache->start + 2 * alignment, cache->length - 2 * alignment},
 	};
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid + alignment,
+					    cache->start + alignment,
 					    alignment);
 	if (ret) {
 		test_err("could not remove free space");
@@ -258,24 +255,23 @@ static int test_remove_middle(struct btrfs_trans_handle *trans,
 
 static int test_merge_left(struct btrfs_trans_handle *trans,
 			   struct btrfs_fs_info *fs_info,
-			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_block_group *cache,
 			   struct btrfs_path *path,
 			   u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid, 2 * alignment},
+		{cache->start, 2 * alignment},
 	};
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid,
-					    cache->key.offset);
+					    cache->start, cache->length);
 	if (ret) {
 		test_err("could not remove free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid,
+	ret = __add_to_free_space_tree(trans, cache, path, cache->start,
 				       alignment);
 	if (ret) {
 		test_err("could not add free space");
@@ -283,7 +279,7 @@ static int test_merge_left(struct btrfs_trans_handle *trans,
 	}
 
 	ret = __add_to_free_space_tree(trans, cache, path,
-				       cache->key.objectid + alignment,
+				       cache->start + alignment,
 				       alignment);
 	if (ret) {
 		test_err("could not add free space");
@@ -296,25 +292,24 @@ static int test_merge_left(struct btrfs_trans_handle *trans,
 
 static int test_merge_right(struct btrfs_trans_handle *trans,
 			   struct btrfs_fs_info *fs_info,
-			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_block_group *cache,
 			   struct btrfs_path *path,
 			   u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid + alignment, 2 * alignment},
+		{cache->start + alignment, 2 * alignment},
 	};
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid,
-					    cache->key.offset);
+					    cache->start, cache->length);
 	if (ret) {
 		test_err("could not remove free space");
 		return ret;
 	}
 
 	ret = __add_to_free_space_tree(trans, cache, path,
-				       cache->key.objectid + 2 * alignment,
+				       cache->start + 2 * alignment,
 				       alignment);
 	if (ret) {
 		test_err("could not add free space");
@@ -322,7 +317,7 @@ static int test_merge_right(struct btrfs_trans_handle *trans,
 	}
 
 	ret = __add_to_free_space_tree(trans, cache, path,
-				       cache->key.objectid + alignment,
+				       cache->start + alignment,
 				       alignment);
 	if (ret) {
 		test_err("could not add free space");
@@ -335,24 +330,23 @@ static int test_merge_right(struct btrfs_trans_handle *trans,
 
 static int test_merge_both(struct btrfs_trans_handle *trans,
 			   struct btrfs_fs_info *fs_info,
-			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_block_group *cache,
 			   struct btrfs_path *path,
 			   u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid, 3 * alignment},
+		{cache->start, 3 * alignment},
 	};
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid,
-					    cache->key.offset);
+					    cache->start, cache->length);
 	if (ret) {
 		test_err("could not remove free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid,
+	ret = __add_to_free_space_tree(trans, cache, path, cache->start,
 				       alignment);
 	if (ret) {
 		test_err("could not add free space");
@@ -360,16 +354,14 @@ static int test_merge_both(struct btrfs_trans_handle *trans,
 	}
 
 	ret = __add_to_free_space_tree(trans, cache, path,
-				       cache->key.objectid + 2 * alignment,
-				       alignment);
+				       cache->start + 2 * alignment, alignment);
 	if (ret) {
 		test_err("could not add free space");
 		return ret;
 	}
 
 	ret = __add_to_free_space_tree(trans, cache, path,
-				       cache->key.objectid + alignment,
-				       alignment);
+				       cache->start + alignment, alignment);
 	if (ret) {
 		test_err("could not add free space");
 		return ret;
@@ -381,26 +373,25 @@ static int test_merge_both(struct btrfs_trans_handle *trans,
 
 static int test_merge_none(struct btrfs_trans_handle *trans,
 			   struct btrfs_fs_info *fs_info,
-			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_block_group *cache,
 			   struct btrfs_path *path,
 			   u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid, alignment},
-		{cache->key.objectid + 2 * alignment, alignment},
-		{cache->key.objectid + 4 * alignment, alignment},
+		{cache->start, alignment},
+		{cache->start + 2 * alignment, alignment},
+		{cache->start + 4 * alignment, alignment},
 	};
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid,
-					    cache->key.offset);
+					    cache->start, cache->length);
 	if (ret) {
 		test_err("could not remove free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid,
+	ret = __add_to_free_space_tree(trans, cache, path, cache->start,
 				       alignment);
 	if (ret) {
 		test_err("could not add free space");
@@ -408,16 +399,14 @@ static int test_merge_none(struct btrfs_trans_handle *trans,
 	}
 
 	ret = __add_to_free_space_tree(trans, cache, path,
-				       cache->key.objectid + 4 * alignment,
-				       alignment);
+				       cache->start + 4 * alignment, alignment);
 	if (ret) {
 		test_err("could not add free space");
 		return ret;
 	}
 
 	ret = __add_to_free_space_tree(trans, cache, path,
-				       cache->key.objectid + 2 * alignment,
-				       alignment);
+				       cache->start + 2 * alignment, alignment);
 	if (ret) {
 		test_err("could not add free space");
 		return ret;
@@ -429,7 +418,7 @@ static int test_merge_none(struct btrfs_trans_handle *trans,
 
 typedef int (*test_func_t)(struct btrfs_trans_handle *,
 			   struct btrfs_fs_info *,
-			   struct btrfs_block_group_cache *,
+			   struct btrfs_block_group *,
 			   struct btrfs_path *,
 			   u32 alignment);
 
@@ -438,7 +427,7 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize,
 {
 	struct btrfs_fs_info *fs_info;
 	struct btrfs_root *root = NULL;
-	struct btrfs_block_group_cache *cache = NULL;
+	struct btrfs_block_group *cache = NULL;
 	struct btrfs_trans_handle trans;
 	struct btrfs_path *path = NULL;
 	int ret;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 8624bdee8c5b..cfc08ef9b876 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -24,9 +24,79 @@
 
 #define BTRFS_ROOT_TRANS_TAG 0
 
+/*
+ * Transaction states and transitions
+ *
+ * No running transaction (fs tree blocks are not modified)
+ * |
+ * | To next stage:
+ * |  Call start_transaction() variants. Except btrfs_join_transaction_nostart().
+ * V
+ * Transaction N [[TRANS_STATE_RUNNING]]
+ * |
+ * | New trans handles can be attached to transaction N by calling all
+ * | start_transaction() variants.
+ * |
+ * | To next stage:
+ * |  Call btrfs_commit_transaction() on any trans handle attached to
+ * |  transaction N
+ * V
+ * Transaction N [[TRANS_STATE_COMMIT_START]]
+ * |
+ * | Will wait for previous running transaction to completely finish if there
+ * | is one
+ * |
+ * | Then one of the following happes:
+ * | - Wait for all other trans handle holders to release.
+ * |   The btrfs_commit_transaction() caller will do the commit work.
+ * | - Wait for current transaction to be committed by others.
+ * |   Other btrfs_commit_transaction() caller will do the commit work.
+ * |
+ * | At this stage, only btrfs_join_transaction*() variants can attach
+ * | to this running transaction.
+ * | All other variants will wait for current one to finish and attach to
+ * | transaction N+1.
+ * |
+ * | To next stage:
+ * |  Caller is chosen to commit transaction N, and all other trans handle
+ * |  haven been released.
+ * V
+ * Transaction N [[TRANS_STATE_COMMIT_DOING]]
+ * |
+ * | The heavy lifting transaction work is started.
+ * | From running delayed refs (modifying extent tree) to creating pending
+ * | snapshots, running qgroups.
+ * | In short, modify supporting trees to reflect modifications of subvolume
+ * | trees.
+ * |
+ * | At this stage, all start_transaction() calls will wait for this
+ * | transaction to finish and attach to transaction N+1.
+ * |
+ * | To next stage:
+ * |  Until all supporting trees are updated.
+ * V
+ * Transaction N [[TRANS_STATE_UNBLOCKED]]
+ * |						    Transaction N+1
+ * | All needed trees are modified, thus we only    [[TRANS_STATE_RUNNING]]
+ * | need to write them back to disk and update	    |
+ * | super blocks.				    |
+ * |						    |
+ * | At this stage, new transaction is allowed to   |
+ * | start.					    |
+ * | All new start_transaction() calls will be	    |
+ * | attached to transid N+1.			    |
+ * |						    |
+ * | To next stage:				    |
+ * |  Until all tree blocks are super blocks are    |
+ * |  written to block devices			    |
+ * V						    |
+ * Transaction N [[TRANS_STATE_COMPLETED]]	    V
+ *   All tree blocks and super blocks are written.  Transaction N+1
+ *   This transaction is finished and all its	    [[TRANS_STATE_COMMIT_START]]
+ *   data structures will be cleaned up.	    | Life goes on
+ */
 static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = {
 	[TRANS_STATE_RUNNING]		= 0U,
-	[TRANS_STATE_BLOCKED]		=  __TRANS_START,
 	[TRANS_STATE_COMMIT_START]	= (__TRANS_START | __TRANS_ATTACH),
 	[TRANS_STATE_COMMIT_DOING]	= (__TRANS_START |
 					   __TRANS_ATTACH |
@@ -63,10 +133,10 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction)
 		 * discard the physical locations of the block groups.
 		 */
 		while (!list_empty(&transaction->deleted_bgs)) {
-			struct btrfs_block_group_cache *cache;
+			struct btrfs_block_group *cache;
 
 			cache = list_first_entry(&transaction->deleted_bgs,
-						 struct btrfs_block_group_cache,
+						 struct btrfs_block_group,
 						 bg_list);
 			list_del_init(&cache->bg_list);
 			btrfs_put_block_group_trimming(cache);
@@ -383,7 +453,7 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
 
 static inline int is_transaction_blocked(struct btrfs_transaction *trans)
 {
-	return (trans->state >= TRANS_STATE_BLOCKED &&
+	return (trans->state >= TRANS_STATE_COMMIT_START &&
 		trans->state < TRANS_STATE_UNBLOCKED &&
 		!trans->aborted);
 }
@@ -570,7 +640,7 @@ again:
 	INIT_LIST_HEAD(&h->new_bgs);
 
 	smp_mb();
-	if (cur_trans->state >= TRANS_STATE_BLOCKED &&
+	if (cur_trans->state >= TRANS_STATE_COMMIT_START &&
 	    may_wait_transaction(fs_info, type)) {
 		current->journal_info = h;
 		btrfs_commit_transaction(h);
@@ -659,7 +729,7 @@ struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root)
 				 true);
 }
 
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root)
+struct btrfs_trans_handle *btrfs_join_transaction_spacecache(struct btrfs_root *root)
 {
 	return start_transaction(root, 0, TRANS_JOIN_NOLOCK,
 				 BTRFS_RESERVE_NO_FLUSH, true);
@@ -798,7 +868,7 @@ int btrfs_should_end_transaction(struct btrfs_trans_handle *trans)
 	struct btrfs_transaction *cur_trans = trans->transaction;
 
 	smp_mb();
-	if (cur_trans->state >= TRANS_STATE_BLOCKED ||
+	if (cur_trans->state >= TRANS_STATE_COMMIT_START ||
 	    cur_trans->delayed_refs.flushing)
 		return 1;
 
@@ -831,7 +901,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_fs_info *info = trans->fs_info;
 	struct btrfs_transaction *cur_trans = trans->transaction;
-	int lock = (trans->type != TRANS_JOIN_NOLOCK);
 	int err = 0;
 
 	if (refcount_read(&trans->use_count) > 1) {
@@ -847,13 +916,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 
 	btrfs_trans_release_chunk_metadata(trans);
 
-	if (lock && READ_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) {
-		if (throttle)
-			return btrfs_commit_transaction(trans);
-		else
-			wake_up_process(info->transaction_kthread);
-	}
-
 	if (trans->type & __TRANS_FREEZABLE)
 		sb_end_intwrite(info->sb);
 
@@ -990,7 +1052,7 @@ static int __btrfs_wait_marked_extents(struct btrfs_fs_info *fs_info,
 	return werr;
 }
 
-int btrfs_wait_extents(struct btrfs_fs_info *fs_info,
+static int btrfs_wait_extents(struct btrfs_fs_info *fs_info,
 		       struct extent_io_tree *dirty_pages)
 {
 	bool errors = false;
@@ -1875,7 +1937,7 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err)
 static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans)
 {
        struct btrfs_fs_info *fs_info = trans->fs_info;
-       struct btrfs_block_group_cache *block_group, *tmp;
+       struct btrfs_block_group *block_group, *tmp;
 
        list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) {
                btrfs_delayed_refs_rsv_release(fs_info, 1);
@@ -1949,6 +2011,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	struct btrfs_transaction *prev_trans = NULL;
 	int ret;
 
+	ASSERT(refcount_read(&trans->use_count) == 1);
+
 	/* Stop the commit early if ->aborted is set */
 	if (unlikely(READ_ONCE(cur_trans->aborted))) {
 		ret = cur_trans->aborted;
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 2c5a6f6e5bb0..49f7196368f5 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -13,7 +13,6 @@
 
 enum btrfs_trans_state {
 	TRANS_STATE_RUNNING,
-	TRANS_STATE_BLOCKED,
 	TRANS_STATE_COMMIT_START,
 	TRANS_STATE_COMMIT_DOING,
 	TRANS_STATE_UNBLOCKED,
@@ -184,7 +183,7 @@ struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
 					unsigned int num_items,
 					int min_factor);
 struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root);
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root);
+struct btrfs_trans_handle *btrfs_join_transaction_spacecache(struct btrfs_root *root);
 struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root);
 struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root);
 struct btrfs_trans_handle *btrfs_attach_transaction_barrier(
@@ -218,8 +217,6 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root);
 int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
 				struct extent_io_tree *dirty_pages, int mark);
-int btrfs_wait_extents(struct btrfs_fs_info *fs_info,
-		       struct extent_io_tree *dirty_pages);
 int btrfs_wait_tree_log_extents(struct btrfs_root *root, int mark);
 int btrfs_transaction_blocked(struct btrfs_fs_info *info);
 int btrfs_transaction_in_commit(struct btrfs_fs_info *info);
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 076d5b8014fb..493d4d9e0f79 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -23,6 +23,7 @@
 #include "disk-io.h"
 #include "compression.h"
 #include "volumes.h"
+#include "misc.h"
 
 /*
  * Error message should follow the following format:
@@ -124,6 +125,74 @@ static u64 file_extent_end(struct extent_buffer *leaf,
 	return end;
 }
 
+/*
+ * Customized report for dir_item, the only new important information is
+ * key->objectid, which represents inode number
+ */
+__printf(3, 4)
+__cold
+static void dir_item_err(const struct extent_buffer *eb, int slot,
+			 const char *fmt, ...)
+{
+	const struct btrfs_fs_info *fs_info = eb->fs_info;
+	struct btrfs_key key;
+	struct va_format vaf;
+	va_list args;
+
+	btrfs_item_key_to_cpu(eb, &key, slot);
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	btrfs_crit(fs_info,
+		"corrupt %s: root=%llu block=%llu slot=%d ino=%llu, %pV",
+		btrfs_header_level(eb) == 0 ? "leaf" : "node",
+		btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
+		key.objectid, &vaf);
+	va_end(args);
+}
+
+/*
+ * This functions checks prev_key->objectid, to ensure current key and prev_key
+ * share the same objectid as inode number.
+ *
+ * This is to detect missing INODE_ITEM in subvolume trees.
+ *
+ * Return true if everything is OK or we don't need to check.
+ * Return false if anything is wrong.
+ */
+static bool check_prev_ino(struct extent_buffer *leaf,
+			   struct btrfs_key *key, int slot,
+			   struct btrfs_key *prev_key)
+{
+	/* No prev key, skip check */
+	if (slot == 0)
+		return true;
+
+	/* Only these key->types needs to be checked */
+	ASSERT(key->type == BTRFS_XATTR_ITEM_KEY ||
+	       key->type == BTRFS_INODE_REF_KEY ||
+	       key->type == BTRFS_DIR_INDEX_KEY ||
+	       key->type == BTRFS_DIR_ITEM_KEY ||
+	       key->type == BTRFS_EXTENT_DATA_KEY);
+
+	/*
+	 * Only subvolume trees along with their reloc trees need this check.
+	 * Things like log tree doesn't follow this ino requirement.
+	 */
+	if (!is_fstree(btrfs_header_owner(leaf)))
+		return true;
+
+	if (key->objectid == prev_key->objectid)
+		return true;
+
+	/* Error found */
+	dir_item_err(leaf, slot,
+		"invalid previous key objectid, have %llu expect %llu",
+		prev_key->objectid, key->objectid);
+	return false;
+}
 static int check_extent_data_item(struct extent_buffer *leaf,
 				  struct btrfs_key *key, int slot,
 				  struct btrfs_key *prev_key)
@@ -141,13 +210,33 @@ static int check_extent_data_item(struct extent_buffer *leaf,
 		return -EUCLEAN;
 	}
 
+	/*
+	 * Previous key must have the same key->objectid (ino).
+	 * It can be XATTR_ITEM, INODE_ITEM or just another EXTENT_DATA.
+	 * But if objectids mismatch, it means we have a missing
+	 * INODE_ITEM.
+	 */
+	if (!check_prev_ino(leaf, key, slot, prev_key))
+		return -EUCLEAN;
+
 	fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
 
-	if (btrfs_file_extent_type(leaf, fi) > BTRFS_FILE_EXTENT_TYPES) {
+	/*
+	 * Make sure the item contains at least inline header, so the file
+	 * extent type is not some garbage.
+	 */
+	if (item_size < BTRFS_FILE_EXTENT_INLINE_DATA_START) {
+		file_extent_err(leaf, slot,
+				"invalid item size, have %u expect [%lu, %u)",
+				item_size, BTRFS_FILE_EXTENT_INLINE_DATA_START,
+				SZ_4K);
+		return -EUCLEAN;
+	}
+	if (btrfs_file_extent_type(leaf, fi) >= BTRFS_NR_FILE_EXTENT_TYPES) {
 		file_extent_err(leaf, slot,
 		"invalid type for file extent, have %u expect range [0, %u]",
 			btrfs_file_extent_type(leaf, fi),
-			BTRFS_FILE_EXTENT_TYPES);
+			BTRFS_NR_FILE_EXTENT_TYPES - 1);
 		return -EUCLEAN;
 	}
 
@@ -155,11 +244,11 @@ static int check_extent_data_item(struct extent_buffer *leaf,
 	 * Support for new compression/encryption must introduce incompat flag,
 	 * and must be caught in open_ctree().
 	 */
-	if (btrfs_file_extent_compression(leaf, fi) > BTRFS_COMPRESS_TYPES) {
+	if (btrfs_file_extent_compression(leaf, fi) >= BTRFS_NR_COMPRESS_TYPES) {
 		file_extent_err(leaf, slot,
 	"invalid compression for file extent, have %u expect range [0, %u]",
 			btrfs_file_extent_compression(leaf, fi),
-			BTRFS_COMPRESS_TYPES);
+			BTRFS_NR_COMPRESS_TYPES - 1);
 		return -EUCLEAN;
 	}
 	if (btrfs_file_extent_encryption(leaf, fi)) {
@@ -270,42 +359,17 @@ static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key,
 	return 0;
 }
 
-/*
- * Customized reported for dir_item, only important new info is key->objectid,
- * which represents inode number
- */
-__printf(3, 4)
-__cold
-static void dir_item_err(const struct extent_buffer *eb, int slot,
-			 const char *fmt, ...)
-{
-	const struct btrfs_fs_info *fs_info = eb->fs_info;
-	struct btrfs_key key;
-	struct va_format vaf;
-	va_list args;
-
-	btrfs_item_key_to_cpu(eb, &key, slot);
-	va_start(args, fmt);
-
-	vaf.fmt = fmt;
-	vaf.va = &args;
-
-	btrfs_crit(fs_info,
-	"corrupt %s: root=%llu block=%llu slot=%d ino=%llu, %pV",
-		btrfs_header_level(eb) == 0 ? "leaf" : "node",
-		btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
-		key.objectid, &vaf);
-	va_end(args);
-}
-
 static int check_dir_item(struct extent_buffer *leaf,
-			  struct btrfs_key *key, int slot)
+			  struct btrfs_key *key, struct btrfs_key *prev_key,
+			  int slot)
 {
 	struct btrfs_fs_info *fs_info = leaf->fs_info;
 	struct btrfs_dir_item *di;
 	u32 item_size = btrfs_item_size_nr(leaf, slot);
 	u32 cur = 0;
 
+	if (!check_prev_ino(leaf, key, slot, prev_key))
+		return -EUCLEAN;
 	di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
 	while (cur < item_size) {
 		u32 name_len;
@@ -459,23 +523,23 @@ static int check_block_group_item(struct extent_buffer *leaf,
 
 	read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
 			   sizeof(bgi));
-	if (btrfs_block_group_chunk_objectid(&bgi) !=
+	if (btrfs_stack_block_group_chunk_objectid(&bgi) !=
 	    BTRFS_FIRST_CHUNK_TREE_OBJECTID) {
 		block_group_err(leaf, slot,
 		"invalid block group chunk objectid, have %llu expect %llu",
-				btrfs_block_group_chunk_objectid(&bgi),
+				btrfs_stack_block_group_chunk_objectid(&bgi),
 				BTRFS_FIRST_CHUNK_TREE_OBJECTID);
 		return -EUCLEAN;
 	}
 
-	if (btrfs_block_group_used(&bgi) > key->offset) {
+	if (btrfs_stack_block_group_used(&bgi) > key->offset) {
 		block_group_err(leaf, slot,
 			"invalid block group used, have %llu expect [0, %llu)",
-				btrfs_block_group_used(&bgi), key->offset);
+				btrfs_stack_block_group_used(&bgi), key->offset);
 		return -EUCLEAN;
 	}
 
-	flags = btrfs_block_group_flags(&bgi);
+	flags = btrfs_stack_block_group_flags(&bgi);
 	if (hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) > 1) {
 		block_group_err(leaf, slot,
 "invalid profile flags, have 0x%llx (%lu bits set) expect no more than 1 bit set",
@@ -609,7 +673,7 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf,
 		return -EUCLEAN;
 	}
 
-	if (!is_power_of_2(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) &&
+	if (!has_single_bit_set(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) &&
 	    (type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0) {
 		chunk_err(leaf, chunk, logical,
 		"invalid chunk profile flag: 0x%llx, expect 0 or 1 bit set",
@@ -785,11 +849,11 @@ static int check_inode_item(struct extent_buffer *leaf,
 	}
 
 	/*
-	 * S_IFMT is not bit mapped so we can't completely rely on is_power_of_2,
-	 * but is_power_of_2() can save us from checking FIFO/CHR/DIR/REG.
-	 * Only needs to check BLK, LNK and SOCKS
+	 * S_IFMT is not bit mapped so we can't completely rely on
+	 * is_power_of_2/has_single_bit_set, but it can save us from checking
+	 * FIFO/CHR/DIR/REG.  Only needs to check BLK, LNK and SOCKS
 	 */
-	if (!is_power_of_2(mode & S_IFMT)) {
+	if (!has_single_bit_set(mode & S_IFMT)) {
 		if (!S_ISLNK(mode) && !S_ISBLK(mode) && !S_ISSOCK(mode)) {
 			inode_item_err(fs_info, leaf, slot,
 			"invalid mode: has 0%o expect valid S_IF* bit(s)",
@@ -1010,8 +1074,8 @@ static int check_extent_item(struct extent_buffer *leaf,
 			   btrfs_super_generation(fs_info->super_copy) + 1);
 		return -EUCLEAN;
 	}
-	if (!is_power_of_2(flags & (BTRFS_EXTENT_FLAG_DATA |
-				    BTRFS_EXTENT_FLAG_TREE_BLOCK))) {
+	if (!has_single_bit_set(flags & (BTRFS_EXTENT_FLAG_DATA |
+					 BTRFS_EXTENT_FLAG_TREE_BLOCK))) {
 		extent_err(leaf, slot,
 		"invalid extent flag, have 0x%llx expect 1 bit set in 0x%llx",
 			flags, BTRFS_EXTENT_FLAG_DATA |
@@ -1224,6 +1288,58 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
 	return 0;
 }
 
+#define inode_ref_err(fs_info, eb, slot, fmt, args...)			\
+	inode_item_err(fs_info, eb, slot, fmt, ##args)
+static int check_inode_ref(struct extent_buffer *leaf,
+			   struct btrfs_key *key, struct btrfs_key *prev_key,
+			   int slot)
+{
+	struct btrfs_inode_ref *iref;
+	unsigned long ptr;
+	unsigned long end;
+
+	if (!check_prev_ino(leaf, key, slot, prev_key))
+		return -EUCLEAN;
+	/* namelen can't be 0, so item_size == sizeof() is also invalid */
+	if (btrfs_item_size_nr(leaf, slot) <= sizeof(*iref)) {
+		inode_ref_err(fs_info, leaf, slot,
+			"invalid item size, have %u expect (%zu, %u)",
+			btrfs_item_size_nr(leaf, slot),
+			sizeof(*iref), BTRFS_LEAF_DATA_SIZE(leaf->fs_info));
+		return -EUCLEAN;
+	}
+
+	ptr = btrfs_item_ptr_offset(leaf, slot);
+	end = ptr + btrfs_item_size_nr(leaf, slot);
+	while (ptr < end) {
+		u16 namelen;
+
+		if (ptr + sizeof(iref) > end) {
+			inode_ref_err(fs_info, leaf, slot,
+			"inode ref overflow, ptr %lu end %lu inode_ref_size %zu",
+				ptr, end, sizeof(iref));
+			return -EUCLEAN;
+		}
+
+		iref = (struct btrfs_inode_ref *)ptr;
+		namelen = btrfs_inode_ref_name_len(leaf, iref);
+		if (ptr + sizeof(*iref) + namelen > end) {
+			inode_ref_err(fs_info, leaf, slot,
+				"inode ref overflow, ptr %lu end %lu namelen %u",
+				ptr, end, namelen);
+			return -EUCLEAN;
+		}
+
+		/*
+		 * NOTE: In theory we should record all found index numbers
+		 * to find any duplicated indexes, but that will be too time
+		 * consuming for inodes with too many hard links.
+		 */
+		ptr += sizeof(*iref) + namelen;
+	}
+	return 0;
+}
+
 /*
  * Common point to switch the item-specific validation.
  */
@@ -1244,7 +1360,10 @@ static int check_leaf_item(struct extent_buffer *leaf,
 	case BTRFS_DIR_ITEM_KEY:
 	case BTRFS_DIR_INDEX_KEY:
 	case BTRFS_XATTR_ITEM_KEY:
-		ret = check_dir_item(leaf, key, slot);
+		ret = check_dir_item(leaf, key, prev_key, slot);
+		break;
+	case BTRFS_INODE_REF_KEY:
+		ret = check_inode_ref(leaf, key, prev_key, slot);
 		break;
 	case BTRFS_BLOCK_GROUP_ITEM_KEY:
 		ret = check_block_group_item(leaf, key, slot);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 8a6cc600bf18..6f757361db53 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -559,7 +559,7 @@ static noinline struct inode *read_one_inode(struct btrfs_root *root,
 	key.objectid = objectid;
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
-	inode = btrfs_iget(root->fs_info->sb, &key, root, NULL);
+	inode = btrfs_iget(root->fs_info->sb, &key, root);
 	if (IS_ERR(inode))
 		inode = NULL;
 	return inode;
@@ -945,54 +945,32 @@ static noinline int backref_in_log(struct btrfs_root *log,
 				   const char *name, int namelen)
 {
 	struct btrfs_path *path;
-	struct btrfs_inode_ref *ref;
-	unsigned long ptr;
-	unsigned long ptr_end;
-	unsigned long name_ptr;
-	int found_name_len;
-	int item_size;
 	int ret;
-	int match = 0;
 
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 
 	ret = btrfs_search_slot(NULL, log, key, path, 0, 0);
-	if (ret != 0)
+	if (ret < 0) {
 		goto out;
-
-	ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
-
-	if (key->type == BTRFS_INODE_EXTREF_KEY) {
-		if (btrfs_find_name_in_ext_backref(path->nodes[0],
-						   path->slots[0],
-						   ref_objectid,
-						   name, namelen))
-			match = 1;
-
+	} else if (ret == 1) {
+		ret = 0;
 		goto out;
 	}
 
-	item_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
-	ptr_end = ptr + item_size;
-	while (ptr < ptr_end) {
-		ref = (struct btrfs_inode_ref *)ptr;
-		found_name_len = btrfs_inode_ref_name_len(path->nodes[0], ref);
-		if (found_name_len == namelen) {
-			name_ptr = (unsigned long)(ref + 1);
-			ret = memcmp_extent_buffer(path->nodes[0], name,
-						   name_ptr, namelen);
-			if (ret == 0) {
-				match = 1;
-				goto out;
-			}
-		}
-		ptr = (unsigned long)(ref + 1) + found_name_len;
-	}
+	if (key->type == BTRFS_INODE_EXTREF_KEY)
+		ret = !!btrfs_find_name_in_ext_backref(path->nodes[0],
+						       path->slots[0],
+						       ref_objectid,
+						       name, namelen);
+	else
+		ret = !!btrfs_find_name_in_backref(path->nodes[0],
+						   path->slots[0],
+						   name, namelen);
 out:
 	btrfs_free_path(path);
-	return match;
+	return ret;
 }
 
 static inline int __add_inode_ref(struct btrfs_trans_handle *trans,
@@ -1050,10 +1028,13 @@ again:
 					   (unsigned long)(victim_ref + 1),
 					   victim_name_len);
 
-			if (!backref_in_log(log_root, &search_key,
-					    parent_objectid,
-					    victim_name,
-					    victim_name_len)) {
+			ret = backref_in_log(log_root, &search_key,
+					     parent_objectid, victim_name,
+					     victim_name_len);
+			if (ret < 0) {
+				kfree(victim_name);
+				return ret;
+			} else if (!ret) {
 				inc_nlink(&inode->vfs_inode);
 				btrfs_release_path(path);
 
@@ -1115,10 +1096,12 @@ again:
 			search_key.offset = btrfs_extref_hash(parent_objectid,
 							      victim_name,
 							      victim_name_len);
-			ret = 0;
-			if (!backref_in_log(log_root, &search_key,
-					    parent_objectid, victim_name,
-					    victim_name_len)) {
+			ret = backref_in_log(log_root, &search_key,
+					     parent_objectid, victim_name,
+					     victim_name_len);
+			if (ret < 0) {
+				return ret;
+			} else if (!ret) {
 				ret = -ENOENT;
 				victim_parent = read_one_inode(root,
 						parent_objectid);
@@ -1885,30 +1868,6 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans,
 }
 
 /*
- * Return true if an inode reference exists in the log for the given name,
- * inode and parent inode.
- */
-static bool name_in_log_ref(struct btrfs_root *log_root,
-			    const char *name, const int name_len,
-			    const u64 dirid, const u64 ino)
-{
-	struct btrfs_key search_key;
-
-	search_key.objectid = ino;
-	search_key.type = BTRFS_INODE_REF_KEY;
-	search_key.offset = dirid;
-	if (backref_in_log(log_root, &search_key, dirid, name, name_len))
-		return true;
-
-	search_key.type = BTRFS_INODE_EXTREF_KEY;
-	search_key.offset = btrfs_extref_hash(dirid, name, name_len);
-	if (backref_in_log(log_root, &search_key, dirid, name, name_len))
-		return true;
-
-	return false;
-}
-
-/*
  * take a single entry in a log directory item and replay it into
  * the subvolume.
  *
@@ -2024,8 +1983,31 @@ out:
 	return ret;
 
 insert:
-	if (name_in_log_ref(root->log_root, name, name_len,
-			    key->objectid, log_key.objectid)) {
+	/*
+	 * Check if the inode reference exists in the log for the given name,
+	 * inode and parent inode
+	 */
+	found_key.objectid = log_key.objectid;
+	found_key.type = BTRFS_INODE_REF_KEY;
+	found_key.offset = key->objectid;
+	ret = backref_in_log(root->log_root, &found_key, 0, name, name_len);
+	if (ret < 0) {
+	        goto out;
+	} else if (ret) {
+	        /* The dentry will be added later. */
+	        ret = 0;
+	        update_size = false;
+	        goto out;
+	}
+
+	found_key.objectid = log_key.objectid;
+	found_key.type = BTRFS_INODE_EXTREF_KEY;
+	found_key.offset = key->objectid;
+	ret = backref_in_log(root->log_root, &found_key, key->objectid, name,
+			     name_len);
+	if (ret < 0) {
+		goto out;
+	} else if (ret) {
 		/* The dentry will be added later. */
 		ret = 0;
 		update_size = false;
@@ -2869,7 +2851,7 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
 	level = btrfs_header_level(log->node);
 	orig_level = level;
 	path->nodes[level] = log->node;
-	extent_buffer_get(log->node);
+	atomic_inc(&log->node->refs);
 	path->slots[level] = 0;
 
 	while (1) {
@@ -4983,7 +4965,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
 		key.objectid = ino;
 		key.type = BTRFS_INODE_ITEM_KEY;
 		key.offset = 0;
-		inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+		inode = btrfs_iget(fs_info->sb, &key, root);
 		/*
 		 * If the other inode that had a conflicting dir entry was
 		 * deleted in the current transaction, we need to log its parent
@@ -4993,8 +4975,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
 			ret = PTR_ERR(inode);
 			if (ret == -ENOENT) {
 				key.objectid = parent;
-				inode = btrfs_iget(fs_info->sb, &key, root,
-						   NULL);
+				inode = btrfs_iget(fs_info->sb, &key, root);
 				if (IS_ERR(inode)) {
 					ret = PTR_ERR(inode);
 				} else {
@@ -5699,7 +5680,7 @@ process_leaf:
 				continue;
 
 			btrfs_release_path(path);
-			di_inode = btrfs_iget(fs_info->sb, &di_key, root, NULL);
+			di_inode = btrfs_iget(fs_info->sb, &di_key, root);
 			if (IS_ERR(di_inode)) {
 				ret = PTR_ERR(di_inode);
 				goto next_dir_inode;
@@ -5825,8 +5806,7 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
 				cur_offset = item_size;
 			}
 
-			dir_inode = btrfs_iget(fs_info->sb, &inode_key,
-					       root, NULL);
+			dir_inode = btrfs_iget(fs_info->sb, &inode_key, root);
 			/*
 			 * If the parent inode was deleted, return an error to
 			 * fallback to a transaction commit. This is to prevent
@@ -5900,7 +5880,7 @@ static int log_new_ancestors(struct btrfs_trans_handle *trans,
 		search_key.objectid = found_key.offset;
 		search_key.type = BTRFS_INODE_ITEM_KEY;
 		search_key.offset = 0;
-		inode = btrfs_iget(fs_info->sb, &search_key, root, NULL);
+		inode = btrfs_iget(fs_info->sb, &search_key, root);
 		if (IS_ERR(inode))
 			return PTR_ERR(inode);
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index e04409f85063..d8e5560db285 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -58,6 +58,30 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 		.bg_flag	= BTRFS_BLOCK_GROUP_RAID1,
 		.mindev_error	= BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET,
 	},
+	[BTRFS_RAID_RAID1C3] = {
+		.sub_stripes	= 1,
+		.dev_stripes	= 1,
+		.devs_max	= 0,
+		.devs_min	= 3,
+		.tolerated_failures = 2,
+		.devs_increment	= 3,
+		.ncopies	= 3,
+		.raid_name	= "raid1c3",
+		.bg_flag	= BTRFS_BLOCK_GROUP_RAID1C3,
+		.mindev_error	= BTRFS_ERROR_DEV_RAID1C3_MIN_NOT_MET,
+	},
+	[BTRFS_RAID_RAID1C4] = {
+		.sub_stripes	= 1,
+		.dev_stripes	= 1,
+		.devs_max	= 0,
+		.devs_min	= 4,
+		.tolerated_failures = 3,
+		.devs_increment	= 4,
+		.ncopies	= 4,
+		.raid_name	= "raid1c4",
+		.bg_flag	= BTRFS_BLOCK_GROUP_RAID1C4,
+		.mindev_error	= BTRFS_ERROR_DEV_RAID1C4_MIN_NOT_MET,
+	},
 	[BTRFS_RAID_DUP] = {
 		.sub_stripes	= 1,
 		.dev_stripes	= 2,
@@ -297,7 +321,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 
 DEFINE_MUTEX(uuid_mutex);
 static LIST_HEAD(fs_uuids);
-struct list_head *btrfs_get_fs_uuids(void)
+struct list_head * __attribute_const__ btrfs_get_fs_uuids(void)
 {
 	return &fs_uuids;
 }
@@ -397,8 +421,6 @@ static struct btrfs_device *__alloc_device(void)
 	INIT_LIST_HEAD(&dev->dev_alloc_list);
 	INIT_LIST_HEAD(&dev->post_commit_list);
 
-	spin_lock_init(&dev->io_lock);
-
 	atomic_set(&dev->reada_in_flight, 0);
 	atomic_set(&dev->dev_stats_ccnt, 0);
 	btrfs_device_data_ordered_init(dev);
@@ -501,212 +523,6 @@ error:
 	return ret;
 }
 
-static void requeue_list(struct btrfs_pending_bios *pending_bios,
-			struct bio *head, struct bio *tail)
-{
-
-	struct bio *old_head;
-
-	old_head = pending_bios->head;
-	pending_bios->head = head;
-	if (pending_bios->tail)
-		tail->bi_next = old_head;
-	else
-		pending_bios->tail = tail;
-}
-
-/*
- * we try to collect pending bios for a device so we don't get a large
- * number of procs sending bios down to the same device.  This greatly
- * improves the schedulers ability to collect and merge the bios.
- *
- * But, it also turns into a long list of bios to process and that is sure
- * to eventually make the worker thread block.  The solution here is to
- * make some progress and then put this work struct back at the end of
- * the list if the block device is congested.  This way, multiple devices
- * can make progress from a single worker thread.
- */
-static noinline void run_scheduled_bios(struct btrfs_device *device)
-{
-	struct btrfs_fs_info *fs_info = device->fs_info;
-	struct bio *pending;
-	struct backing_dev_info *bdi;
-	struct btrfs_pending_bios *pending_bios;
-	struct bio *tail;
-	struct bio *cur;
-	int again = 0;
-	unsigned long num_run;
-	unsigned long batch_run = 0;
-	unsigned long last_waited = 0;
-	int force_reg = 0;
-	int sync_pending = 0;
-	struct blk_plug plug;
-
-	/*
-	 * this function runs all the bios we've collected for
-	 * a particular device.  We don't want to wander off to
-	 * another device without first sending all of these down.
-	 * So, setup a plug here and finish it off before we return
-	 */
-	blk_start_plug(&plug);
-
-	bdi = device->bdev->bd_bdi;
-
-loop:
-	spin_lock(&device->io_lock);
-
-loop_lock:
-	num_run = 0;
-
-	/* take all the bios off the list at once and process them
-	 * later on (without the lock held).  But, remember the
-	 * tail and other pointers so the bios can be properly reinserted
-	 * into the list if we hit congestion
-	 */
-	if (!force_reg && device->pending_sync_bios.head) {
-		pending_bios = &device->pending_sync_bios;
-		force_reg = 1;
-	} else {
-		pending_bios = &device->pending_bios;
-		force_reg = 0;
-	}
-
-	pending = pending_bios->head;
-	tail = pending_bios->tail;
-	WARN_ON(pending && !tail);
-
-	/*
-	 * if pending was null this time around, no bios need processing
-	 * at all and we can stop.  Otherwise it'll loop back up again
-	 * and do an additional check so no bios are missed.
-	 *
-	 * device->running_pending is used to synchronize with the
-	 * schedule_bio code.
-	 */
-	if (device->pending_sync_bios.head == NULL &&
-	    device->pending_bios.head == NULL) {
-		again = 0;
-		device->running_pending = 0;
-	} else {
-		again = 1;
-		device->running_pending = 1;
-	}
-
-	pending_bios->head = NULL;
-	pending_bios->tail = NULL;
-
-	spin_unlock(&device->io_lock);
-
-	while (pending) {
-
-		rmb();
-		/* we want to work on both lists, but do more bios on the
-		 * sync list than the regular list
-		 */
-		if ((num_run > 32 &&
-		    pending_bios != &device->pending_sync_bios &&
-		    device->pending_sync_bios.head) ||
-		   (num_run > 64 && pending_bios == &device->pending_sync_bios &&
-		    device->pending_bios.head)) {
-			spin_lock(&device->io_lock);
-			requeue_list(pending_bios, pending, tail);
-			goto loop_lock;
-		}
-
-		cur = pending;
-		pending = pending->bi_next;
-		cur->bi_next = NULL;
-
-		BUG_ON(atomic_read(&cur->__bi_cnt) == 0);
-
-		/*
-		 * if we're doing the sync list, record that our
-		 * plug has some sync requests on it
-		 *
-		 * If we're doing the regular list and there are
-		 * sync requests sitting around, unplug before
-		 * we add more
-		 */
-		if (pending_bios == &device->pending_sync_bios) {
-			sync_pending = 1;
-		} else if (sync_pending) {
-			blk_finish_plug(&plug);
-			blk_start_plug(&plug);
-			sync_pending = 0;
-		}
-
-		btrfsic_submit_bio(cur);
-		num_run++;
-		batch_run++;
-
-		cond_resched();
-
-		/*
-		 * we made progress, there is more work to do and the bdi
-		 * is now congested.  Back off and let other work structs
-		 * run instead
-		 */
-		if (pending && bdi_write_congested(bdi) && batch_run > 8 &&
-		    fs_info->fs_devices->open_devices > 1) {
-			struct io_context *ioc;
-
-			ioc = current->io_context;
-
-			/*
-			 * the main goal here is that we don't want to
-			 * block if we're going to be able to submit
-			 * more requests without blocking.
-			 *
-			 * This code does two great things, it pokes into
-			 * the elevator code from a filesystem _and_
-			 * it makes assumptions about how batching works.
-			 */
-			if (ioc && ioc->nr_batch_requests > 0 &&
-			    time_before(jiffies, ioc->last_waited + HZ/50UL) &&
-			    (last_waited == 0 ||
-			     ioc->last_waited == last_waited)) {
-				/*
-				 * we want to go through our batch of
-				 * requests and stop.  So, we copy out
-				 * the ioc->last_waited time and test
-				 * against it before looping
-				 */
-				last_waited = ioc->last_waited;
-				cond_resched();
-				continue;
-			}
-			spin_lock(&device->io_lock);
-			requeue_list(pending_bios, pending, tail);
-			device->running_pending = 1;
-
-			spin_unlock(&device->io_lock);
-			btrfs_queue_work(fs_info->submit_workers,
-					 &device->work);
-			goto done;
-		}
-	}
-
-	cond_resched();
-	if (again)
-		goto loop;
-
-	spin_lock(&device->io_lock);
-	if (device->pending_bios.head || device->pending_sync_bios.head)
-		goto loop_lock;
-	spin_unlock(&device->io_lock);
-
-done:
-	blk_finish_plug(&plug);
-}
-
-static void pending_bios_fn(struct btrfs_work *work)
-{
-	struct btrfs_device *device;
-
-	device = container_of(work, struct btrfs_device, work);
-	run_scheduled_bios(device);
-}
-
 static bool device_path_matched(const char *path, struct btrfs_device *device)
 {
 	int found;
@@ -818,7 +634,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 		}
 
 		clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
-		fs_devices->seeding = 1;
+		fs_devices->seeding = true;
 	} else {
 		if (bdev_read_only(bdev))
 			clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
@@ -828,7 +644,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 
 	q = bdev_get_queue(bdev);
 	if (!blk_queue_nonrot(q))
-		fs_devices->rotating = 1;
+		fs_devices->rotating = true;
 
 	device->bdev = bdev;
 	clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
@@ -1005,11 +821,15 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		*new_device_added = true;
 
 		if (disk_super->label[0])
-			pr_info("BTRFS: device label %s devid %llu transid %llu %s\n",
-				disk_super->label, devid, found_transid, path);
+			pr_info(
+	"BTRFS: device label %s devid %llu transid %llu %s scanned by %s (%d)\n",
+				disk_super->label, devid, found_transid, path,
+				current->comm, task_pid_nr(current));
 		else
-			pr_info("BTRFS: device fsid %pU devid %llu transid %llu %s\n",
-				disk_super->fsid, devid, found_transid, path);
+			pr_info(
+	"BTRFS: device fsid %pU devid %llu transid %llu %s scanned by %s (%d)\n",
+				disk_super->fsid, devid, found_transid, path,
+				current->comm, task_pid_nr(current));
 
 	} else if (!device->name || strcmp(device->name->str, path)) {
 		/*
@@ -1295,7 +1115,7 @@ static int close_fs_devices(struct btrfs_fs_devices *fs_devices)
 	WARN_ON(fs_devices->open_devices);
 	WARN_ON(fs_devices->rw_devices);
 	fs_devices->opened = 0;
-	fs_devices->seeding = 0;
+	fs_devices->seeding = false;
 
 	return 0;
 }
@@ -2048,7 +1868,7 @@ static struct btrfs_device * btrfs_find_next_active_device(
  * where this function called, there should be always be another device (or
  * this_dev) which is active.
  */
-void btrfs_assign_next_active_device(struct btrfs_device *device,
+void __cold btrfs_assign_next_active_device(struct btrfs_device *device,
 				     struct btrfs_device *this_dev)
 {
 	struct btrfs_fs_info *fs_info = device->fs_info;
@@ -2450,11 +2270,11 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
 	list_splice_init(&fs_devices->alloc_list, &seed_devices->alloc_list);
 	mutex_unlock(&fs_info->chunk_mutex);
 
-	fs_devices->seeding = 0;
+	fs_devices->seeding = false;
 	fs_devices->num_devices = 0;
 	fs_devices->open_devices = 0;
 	fs_devices->missing_devices = 0;
-	fs_devices->rotating = 0;
+	fs_devices->rotating = false;
 	fs_devices->seed = seed_devices;
 
 	generate_random_uuid(fs_devices->fsid);
@@ -2649,7 +2469,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	atomic64_add(device->total_bytes, &fs_info->free_chunk_space);
 
 	if (!blk_queue_nonrot(q))
-		fs_devices->rotating = 1;
+		fs_devices->rotating = true;
 
 	orig_super_total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
 	btrfs_set_super_total_bytes(fs_info->super_copy,
@@ -3177,7 +2997,7 @@ error:
 static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info,
 				      u64 chunk_offset)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	u64 bytes_used;
 	u64 chunk_type;
 
@@ -3186,27 +3006,28 @@ static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info,
 	chunk_type = cache->flags;
 	btrfs_put_block_group(cache);
 
-	if (chunk_type & BTRFS_BLOCK_GROUP_DATA) {
-		spin_lock(&fs_info->data_sinfo->lock);
-		bytes_used = fs_info->data_sinfo->bytes_used;
-		spin_unlock(&fs_info->data_sinfo->lock);
+	if (!(chunk_type & BTRFS_BLOCK_GROUP_DATA))
+		return 0;
+
+	spin_lock(&fs_info->data_sinfo->lock);
+	bytes_used = fs_info->data_sinfo->bytes_used;
+	spin_unlock(&fs_info->data_sinfo->lock);
 
-		if (!bytes_used) {
-			struct btrfs_trans_handle *trans;
-			int ret;
+	if (!bytes_used) {
+		struct btrfs_trans_handle *trans;
+		int ret;
 
-			trans =	btrfs_join_transaction(fs_info->tree_root);
-			if (IS_ERR(trans))
-				return PTR_ERR(trans);
+		trans =	btrfs_join_transaction(fs_info->tree_root);
+		if (IS_ERR(trans))
+			return PTR_ERR(trans);
 
-			ret = btrfs_force_chunk_alloc(trans,
-						      BTRFS_BLOCK_GROUP_DATA);
-			btrfs_end_transaction(trans);
-			if (ret < 0)
-				return ret;
-			return 1;
-		}
+		ret = btrfs_force_chunk_alloc(trans, BTRFS_BLOCK_GROUP_DATA);
+		btrfs_end_transaction(trans);
+		if (ret < 0)
+			return ret;
+		return 1;
 	}
+
 	return 0;
 }
 
@@ -3385,28 +3206,28 @@ static int chunk_profiles_filter(u64 chunk_type,
 static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
 			      struct btrfs_balance_args *bargs)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	u64 chunk_used;
 	u64 user_thresh_min;
 	u64 user_thresh_max;
 	int ret = 1;
 
 	cache = btrfs_lookup_block_group(fs_info, chunk_offset);
-	chunk_used = btrfs_block_group_used(&cache->item);
+	chunk_used = cache->used;
 
 	if (bargs->usage_min == 0)
 		user_thresh_min = 0;
 	else
-		user_thresh_min = div_factor_fine(cache->key.offset,
-					bargs->usage_min);
+		user_thresh_min = div_factor_fine(cache->length,
+						  bargs->usage_min);
 
 	if (bargs->usage_max == 0)
 		user_thresh_max = 1;
 	else if (bargs->usage_max > 100)
-		user_thresh_max = cache->key.offset;
+		user_thresh_max = cache->length;
 	else
-		user_thresh_max = div_factor_fine(cache->key.offset,
-					bargs->usage_max);
+		user_thresh_max = div_factor_fine(cache->length,
+						  bargs->usage_max);
 
 	if (user_thresh_min <= chunk_used && chunk_used < user_thresh_max)
 		ret = 0;
@@ -3418,20 +3239,19 @@ static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, u64 chunk_off
 static int chunk_usage_filter(struct btrfs_fs_info *fs_info,
 		u64 chunk_offset, struct btrfs_balance_args *bargs)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	u64 chunk_used, user_thresh;
 	int ret = 1;
 
 	cache = btrfs_lookup_block_group(fs_info, chunk_offset);
-	chunk_used = btrfs_block_group_used(&cache->item);
+	chunk_used = cache->used;
 
 	if (bargs->usage_min == 0)
 		user_thresh = 1;
 	else if (bargs->usage > 100)
-		user_thresh = cache->key.offset;
+		user_thresh = cache->length;
 	else
-		user_thresh = div_factor_fine(cache->key.offset,
-					      bargs->usage);
+		user_thresh = div_factor_fine(cache->length, bargs->usage);
 
 	if (chunk_used < user_thresh)
 		ret = 0;
@@ -3844,12 +3664,7 @@ static int alloc_profile_is_valid(u64 flags, int extended)
 	if (flags == 0)
 		return !extended; /* "0" is valid for usual profiles */
 
-	/* true if exactly one bit set */
-	/*
-	 * Don't use is_power_of_2(unsigned long) because it won't work
-	 * for the single profile (1ULL << 48) on 32-bit CPUs.
-	 */
-	return flags != 0 && (flags & (flags - 1)) == 0;
+	return has_single_bit_set(flags);
 }
 
 static inline int balance_need_close(struct btrfs_fs_info *fs_info)
@@ -4036,7 +3851,7 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
 	int ret;
 	u64 num_devices;
 	unsigned seq;
-	bool reducing_integrity;
+	bool reducing_redundancy;
 	int i;
 
 	if (btrfs_fs_closing(fs_info) ||
@@ -4119,9 +3934,9 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
 		    ((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
 		     (fs_info->avail_metadata_alloc_bits & allowed) &&
 		     !(bctl->meta.target & allowed)))
-			reducing_integrity = true;
+			reducing_redundancy = true;
 		else
-			reducing_integrity = false;
+			reducing_redundancy = false;
 
 		/* if we're not converting, the target field is uninitialized */
 		meta_target = (bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) ?
@@ -4130,13 +3945,13 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
 			bctl->data.target : fs_info->avail_data_alloc_bits;
 	} while (read_seqretry(&fs_info->profiles_lock, seq));
 
-	if (reducing_integrity) {
+	if (reducing_redundancy) {
 		if (bctl->flags & BTRFS_BALANCE_FORCE) {
 			btrfs_info(fs_info,
-				   "balance: force reducing metadata integrity");
+			   "balance: force reducing metadata redundancy");
 		} else {
 			btrfs_err(fs_info,
-	  "balance: reduces metadata integrity, use --force if you want this");
+	"balance: reduces metadata redundancy, use --force if you want this");
 			ret = -EINVAL;
 			goto out;
 		}
@@ -4902,6 +4717,14 @@ static void check_raid56_incompat_flag(struct btrfs_fs_info *info, u64 type)
 	btrfs_set_fs_incompat(info, RAID56);
 }
 
+static void check_raid1c34_incompat_flag(struct btrfs_fs_info *info, u64 type)
+{
+	if (!(type & (BTRFS_BLOCK_GROUP_RAID1C3 | BTRFS_BLOCK_GROUP_RAID1C4)))
+		return;
+
+	btrfs_set_fs_incompat(info, RAID1C34);
+}
+
 static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 			       u64 start, u64 type)
 {
@@ -5048,8 +4871,11 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	sort(devices_info, ndevs, sizeof(struct btrfs_device_info),
 	     btrfs_cmp_device_info, NULL);
 
-	/* round down to number of usable stripes */
-	ndevs = round_down(ndevs, devs_increment);
+	/*
+	 * Round down to number of usable stripes, devs_increment can be any
+	 * number so we can't use round_down()
+	 */
+	ndevs -= ndevs % devs_increment;
 
 	if (ndevs < devs_min) {
 		ret = -ENOSPC;
@@ -5165,6 +4991,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 
 	free_extent_map(em);
 	check_raid56_incompat_flag(info, type);
+	check_raid1c34_incompat_flag(info, type);
 
 	kfree(devices_info);
 	return 0;
@@ -5583,12 +5410,13 @@ void btrfs_put_bbio(struct btrfs_bio *bbio)
  * replace.
  */
 static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
-					 u64 logical, u64 length,
+					 u64 logical, u64 *length_ret,
 					 struct btrfs_bio **bbio_ret)
 {
 	struct extent_map *em;
 	struct map_lookup *map;
 	struct btrfs_bio *bbio;
+	u64 length = *length_ret;
 	u64 offset;
 	u64 stripe_nr;
 	u64 stripe_nr_end;
@@ -5621,7 +5449,8 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
 	}
 
 	offset = logical - em->start;
-	length = min_t(u64, em->len - offset, length);
+	length = min_t(u64, em->start + em->len - logical, length);
+	*length_ret = length;
 
 	stripe_len = map->stripe_len;
 	/*
@@ -6036,7 +5865,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 
 	if (op == BTRFS_MAP_DISCARD)
 		return __btrfs_map_block_for_discard(fs_info, logical,
-						     *length, bbio_ret);
+						     length, bbio_ret);
 
 	ret = btrfs_get_io_geometry(fs_info, op, logical, *length, &geom);
 	if (ret < 0)
@@ -6416,52 +6245,8 @@ static void btrfs_end_bio(struct bio *bio)
 	}
 }
 
-/*
- * see run_scheduled_bios for a description of why bios are collected for
- * async submit.
- *
- * This will add one bio to the pending list for a device and make sure
- * the work struct is scheduled.
- */
-static noinline void btrfs_schedule_bio(struct btrfs_device *device,
-					struct bio *bio)
-{
-	struct btrfs_fs_info *fs_info = device->fs_info;
-	int should_queue = 1;
-	struct btrfs_pending_bios *pending_bios;
-
-	/* don't bother with additional async steps for reads, right now */
-	if (bio_op(bio) == REQ_OP_READ) {
-		btrfsic_submit_bio(bio);
-		return;
-	}
-
-	WARN_ON(bio->bi_next);
-	bio->bi_next = NULL;
-
-	spin_lock(&device->io_lock);
-	if (op_is_sync(bio->bi_opf))
-		pending_bios = &device->pending_sync_bios;
-	else
-		pending_bios = &device->pending_bios;
-
-	if (pending_bios->tail)
-		pending_bios->tail->bi_next = bio;
-
-	pending_bios->tail = bio;
-	if (!pending_bios->head)
-		pending_bios->head = bio;
-	if (device->running_pending)
-		should_queue = 0;
-
-	spin_unlock(&device->io_lock);
-
-	if (should_queue)
-		btrfs_queue_work(fs_info->submit_workers, &device->work);
-}
-
 static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio,
-			      u64 physical, int dev_nr, int async)
+			      u64 physical, int dev_nr)
 {
 	struct btrfs_device *dev = bbio->stripes[dev_nr].dev;
 	struct btrfs_fs_info *fs_info = bbio->fs_info;
@@ -6479,10 +6264,7 @@ static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio,
 
 	btrfs_bio_counter_inc_noblocked(fs_info);
 
-	if (async)
-		btrfs_schedule_bio(dev, bio);
-	else
-		btrfsic_submit_bio(bio);
+	btrfsic_submit_bio(bio);
 }
 
 static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
@@ -6503,7 +6285,7 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
 }
 
 blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
-			   int mirror_num, int async_submit)
+			   int mirror_num)
 {
 	struct btrfs_device *dev;
 	struct bio *first_bio = bio;
@@ -6572,7 +6354,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 			bio = first_bio;
 
 		submit_stripe_bio(bbio, bio, bbio->stripes[dev_nr].physical,
-				  dev_nr, async_submit);
+				  dev_nr);
 	}
 	btrfs_bio_counter_dec(fs_info);
 	return BLK_STS_OK;
@@ -6676,9 +6458,6 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 	else
 		generate_random_uuid(dev->uuid);
 
-	btrfs_init_work(&dev->work, btrfs_submit_helper,
-			pending_bios_fn, NULL, NULL);
-
 	return dev;
 }
 
@@ -6875,7 +6654,7 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info,
 		if (IS_ERR(fs_devices))
 			return fs_devices;
 
-		fs_devices->seeding = 1;
+		fs_devices->seeding = true;
 		fs_devices->opened = 1;
 		return fs_devices;
 	}
@@ -7064,48 +6843,49 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info)
 		sb_array_offset += len;
 		cur_offset += len;
 
-		if (key.type == BTRFS_CHUNK_ITEM_KEY) {
-			chunk = (struct btrfs_chunk *)sb_array_offset;
-			/*
-			 * At least one btrfs_chunk with one stripe must be
-			 * present, exact stripe count check comes afterwards
-			 */
-			len = btrfs_chunk_item_size(1);
-			if (cur_offset + len > array_size)
-				goto out_short_read;
-
-			num_stripes = btrfs_chunk_num_stripes(sb, chunk);
-			if (!num_stripes) {
-				btrfs_err(fs_info,
-					"invalid number of stripes %u in sys_array at offset %u",
-					num_stripes, cur_offset);
-				ret = -EIO;
-				break;
-			}
+		if (key.type != BTRFS_CHUNK_ITEM_KEY) {
+			btrfs_err(fs_info,
+			    "unexpected item type %u in sys_array at offset %u",
+				  (u32)key.type, cur_offset);
+			ret = -EIO;
+			break;
+		}
 
-			type = btrfs_chunk_type(sb, chunk);
-			if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) {
-				btrfs_err(fs_info,
-			    "invalid chunk type %llu in sys_array at offset %u",
-					type, cur_offset);
-				ret = -EIO;
-				break;
-			}
+		chunk = (struct btrfs_chunk *)sb_array_offset;
+		/*
+		 * At least one btrfs_chunk with one stripe must be present,
+		 * exact stripe count check comes afterwards
+		 */
+		len = btrfs_chunk_item_size(1);
+		if (cur_offset + len > array_size)
+			goto out_short_read;
 
-			len = btrfs_chunk_item_size(num_stripes);
-			if (cur_offset + len > array_size)
-				goto out_short_read;
+		num_stripes = btrfs_chunk_num_stripes(sb, chunk);
+		if (!num_stripes) {
+			btrfs_err(fs_info,
+			"invalid number of stripes %u in sys_array at offset %u",
+				  num_stripes, cur_offset);
+			ret = -EIO;
+			break;
+		}
 
-			ret = read_one_chunk(&key, sb, chunk);
-			if (ret)
-				break;
-		} else {
+		type = btrfs_chunk_type(sb, chunk);
+		if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) {
 			btrfs_err(fs_info,
-			    "unexpected item type %u in sys_array at offset %u",
-				  (u32)key.type, cur_offset);
+			"invalid chunk type %llu in sys_array at offset %u",
+				  type, cur_offset);
 			ret = -EIO;
 			break;
 		}
+
+		len = btrfs_chunk_item_size(num_stripes);
+		if (cur_offset + len > array_size)
+			goto out_short_read;
+
+		ret = read_one_chunk(&key, sb, chunk);
+		if (ret)
+			break;
+
 		array_ptr += len;
 		sb_array_offset += len;
 		cur_offset += len;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index a7da1f3e3627..fc1b564b9cfe 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -18,10 +18,6 @@ extern struct mutex uuid_mutex;
 #define BTRFS_STRIPE_LEN	SZ_64K
 
 struct buffer_head;
-struct btrfs_pending_bios {
-	struct bio *head;
-	struct bio *tail;
-};
 
 struct btrfs_io_geometry {
 	/* remaining bytes before crossing a stripe */
@@ -68,13 +64,6 @@ struct btrfs_device {
 
 	u64 generation;
 
-	spinlock_t io_lock ____cacheline_aligned;
-	int running_pending;
-	/* regular prio bios */
-	struct btrfs_pending_bios pending_bios;
-	/* sync bios */
-	struct btrfs_pending_bios pending_sync_bios;
-
 	struct block_device *bdev;
 
 	/* the mode sent to blkdev_get */
@@ -254,14 +243,14 @@ struct btrfs_fs_devices {
 	struct list_head alloc_list;
 
 	struct btrfs_fs_devices *seed;
-	int seeding;
+	bool seeding;
 
 	int opened;
 
 	/* set when we find or add a device that doesn't have the
 	 * nonrot flag set
 	 */
-	int rotating;
+	bool rotating;
 
 	struct btrfs_fs_info *fs_info;
 	/* sysfs kobjects */
@@ -330,7 +319,6 @@ struct btrfs_bio {
 	u64 map_type; /* get from map_lookup->type */
 	bio_end_io_t *end_io;
 	struct bio *orig_bio;
-	unsigned long flags;
 	void *private;
 	atomic_t error;
 	int max_errors;
@@ -436,7 +424,7 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
 int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type);
 void btrfs_mapping_tree_free(struct extent_map_tree *tree);
 blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
-			   int mirror_num, int async_submit);
+			   int mirror_num);
 int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		       fmode_t flags, void *holder);
 struct btrfs_device *btrfs_scan_one_device(const char *path,
@@ -557,6 +545,10 @@ static inline enum btrfs_raid_types btrfs_bg_flags_to_raid_index(u64 flags)
 		return BTRFS_RAID_RAID10;
 	else if (flags & BTRFS_BLOCK_GROUP_RAID1)
 		return BTRFS_RAID_RAID1;
+	else if (flags & BTRFS_BLOCK_GROUP_RAID1C3)
+		return BTRFS_RAID_RAID1C3;
+	else if (flags & BTRFS_BLOCK_GROUP_RAID1C4)
+		return BTRFS_RAID_RAID1C4;
 	else if (flags & BTRFS_BLOCK_GROUP_DUP)
 		return BTRFS_RAID_DUP;
 	else if (flags & BTRFS_BLOCK_GROUP_RAID0)
@@ -571,7 +563,7 @@ static inline enum btrfs_raid_types btrfs_bg_flags_to_raid_index(u64 flags)
 
 void btrfs_commit_device_sizes(struct btrfs_transaction *trans);
 
-struct list_head *btrfs_get_fs_uuids(void);
+struct list_head * __attribute_const__ btrfs_get_fs_uuids(void);
 void btrfs_set_fs_info_ptr(struct btrfs_fs_info *fs_info);
 void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info);
 bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index df1aace5df50..a6c90a003c12 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -29,19 +29,9 @@ struct workspace {
 
 static struct workspace_manager wsm;
 
-static void zlib_init_workspace_manager(void)
+struct list_head *zlib_get_workspace(unsigned int level)
 {
-	btrfs_init_workspace_manager(&wsm, &btrfs_zlib_compress);
-}
-
-static void zlib_cleanup_workspace_manager(void)
-{
-	btrfs_cleanup_workspace_manager(&wsm);
-}
-
-static struct list_head *zlib_get_workspace(unsigned int level)
-{
-	struct list_head *ws = btrfs_get_workspace(&wsm, level);
+	struct list_head *ws = btrfs_get_workspace(BTRFS_COMPRESS_ZLIB, level);
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 
 	workspace->level = level;
@@ -49,12 +39,7 @@ static struct list_head *zlib_get_workspace(unsigned int level)
 	return ws;
 }
 
-static void zlib_put_workspace(struct list_head *ws)
-{
-	btrfs_put_workspace(&wsm, ws);
-}
-
-static void zlib_free_workspace(struct list_head *ws)
+void zlib_free_workspace(struct list_head *ws)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 
@@ -63,7 +48,7 @@ static void zlib_free_workspace(struct list_head *ws)
 	kfree(workspace);
 }
 
-static struct list_head *zlib_alloc_workspace(unsigned int level)
+struct list_head *zlib_alloc_workspace(unsigned int level)
 {
 	struct workspace *workspace;
 	int workspacesize;
@@ -88,13 +73,9 @@ fail:
 	return ERR_PTR(-ENOMEM);
 }
 
-static int zlib_compress_pages(struct list_head *ws,
-			       struct address_space *mapping,
-			       u64 start,
-			       struct page **pages,
-			       unsigned long *out_pages,
-			       unsigned long *total_in,
-			       unsigned long *total_out)
+int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
+		u64 start, struct page **pages, unsigned long *out_pages,
+		unsigned long *total_in, unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret;
@@ -228,7 +209,7 @@ out:
 	return ret;
 }
 
-static int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
+int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0, ret2;
@@ -319,10 +300,9 @@ done:
 	return ret;
 }
 
-static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
-			   struct page *dest_page,
-			   unsigned long start_byte,
-			   size_t srclen, size_t destlen)
+int zlib_decompress(struct list_head *ws, unsigned char *data_in,
+		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0;
@@ -419,15 +399,7 @@ next:
 }
 
 const struct btrfs_compress_op btrfs_zlib_compress = {
-	.init_workspace_manager	= zlib_init_workspace_manager,
-	.cleanup_workspace_manager = zlib_cleanup_workspace_manager,
-	.get_workspace		= zlib_get_workspace,
-	.put_workspace		= zlib_put_workspace,
-	.alloc_workspace	= zlib_alloc_workspace,
-	.free_workspace		= zlib_free_workspace,
-	.compress_pages		= zlib_compress_pages,
-	.decompress_bio		= zlib_decompress_bio,
-	.decompress		= zlib_decompress,
+	.workspace_manager	= &wsm,
 	.max_level		= 9,
 	.default_level		= BTRFS_ZLIB_DEFAULT_LEVEL,
 };
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 764d47b107e5..9a4871636c6c 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -91,9 +91,8 @@ static inline struct workspace *list_to_workspace(struct list_head *list)
 	return container_of(list, struct workspace, list);
 }
 
-static void zstd_free_workspace(struct list_head *ws);
-static struct list_head *zstd_alloc_workspace(unsigned int level);
-
+void zstd_free_workspace(struct list_head *ws);
+struct list_head *zstd_alloc_workspace(unsigned int level);
 /*
  * zstd_reclaim_timer_fn - reclaim timer
  * @t: timer
@@ -168,7 +167,7 @@ static void zstd_calc_ws_mem_sizes(void)
 	}
 }
 
-static void zstd_init_workspace_manager(void)
+void zstd_init_workspace_manager(void)
 {
 	struct list_head *ws;
 	int i;
@@ -194,7 +193,7 @@ static void zstd_init_workspace_manager(void)
 	}
 }
 
-static void zstd_cleanup_workspace_manager(void)
+void zstd_cleanup_workspace_manager(void)
 {
 	struct workspace *workspace;
 	int i;
@@ -261,7 +260,7 @@ static struct list_head *zstd_find_workspace(unsigned int level)
  * attempt to allocate a new workspace.  If we fail to allocate one due to
  * memory pressure, go to sleep waiting for the max level workspace to free up.
  */
-static struct list_head *zstd_get_workspace(unsigned int level)
+struct list_head *zstd_get_workspace(unsigned int level)
 {
 	struct list_head *ws;
 	unsigned int nofs_flag;
@@ -302,7 +301,7 @@ again:
  * isn't set, it is also set here.  Only the max level workspace tries and wakes
  * up waiting workspaces.
  */
-static void zstd_put_workspace(struct list_head *ws)
+void zstd_put_workspace(struct list_head *ws)
 {
 	struct workspace *workspace = list_to_workspace(ws);
 
@@ -332,7 +331,7 @@ static void zstd_put_workspace(struct list_head *ws)
 		cond_wake_up(&wsm.wait);
 }
 
-static void zstd_free_workspace(struct list_head *ws)
+void zstd_free_workspace(struct list_head *ws)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 
@@ -341,7 +340,7 @@ static void zstd_free_workspace(struct list_head *ws)
 	kfree(workspace);
 }
 
-static struct list_head *zstd_alloc_workspace(unsigned int level)
+struct list_head *zstd_alloc_workspace(unsigned int level)
 {
 	struct workspace *workspace;
 
@@ -367,13 +366,9 @@ fail:
 	return ERR_PTR(-ENOMEM);
 }
 
-static int zstd_compress_pages(struct list_head *ws,
-		struct address_space *mapping,
-		u64 start,
-		struct page **pages,
-		unsigned long *out_pages,
-		unsigned long *total_in,
-		unsigned long *total_out)
+int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
+		u64 start, struct page **pages, unsigned long *out_pages,
+		unsigned long *total_in, unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	ZSTD_CStream *stream;
@@ -548,7 +543,7 @@ out:
 	return ret;
 }
 
-static int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
+int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	struct page **pages_in = cb->compressed_pages;
@@ -626,10 +621,9 @@ done:
 	return ret;
 }
 
-static int zstd_decompress(struct list_head *ws, unsigned char *data_in,
-		struct page *dest_page,
-		unsigned long start_byte,
-		size_t srclen, size_t destlen)
+int zstd_decompress(struct list_head *ws, unsigned char *data_in,
+		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	ZSTD_DStream *stream;
@@ -712,15 +706,8 @@ finish:
 }
 
 const struct btrfs_compress_op btrfs_zstd_compress = {
-	.init_workspace_manager = zstd_init_workspace_manager,
-	.cleanup_workspace_manager = zstd_cleanup_workspace_manager,
-	.get_workspace = zstd_get_workspace,
-	.put_workspace = zstd_put_workspace,
-	.alloc_workspace = zstd_alloc_workspace,
-	.free_workspace = zstd_free_workspace,
-	.compress_pages = zstd_compress_pages,
-	.decompress_bio = zstd_decompress_bio,
-	.decompress = zstd_decompress,
+	/* ZSTD uses own workspace manager */
+	.workspace_manager = NULL,
 	.max_level	= ZSTD_BTRFS_MAX_LEVEL,
 	.default_level	= ZSTD_BTRFS_DEFAULT_LEVEL,
 };
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index d12ea28836a5..2f04024c3588 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -958,8 +958,8 @@ static int cramfs_get_tree(struct fs_context *fc)
 
 	if (IS_ENABLED(CONFIG_CRAMFS_MTD)) {
 		ret = get_tree_mtd(fc, cramfs_mtd_fill_super);
-		if (ret < 0)
-			return ret;
+		if (!ret)
+			return 0;
 	}
 	if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV))
 		ret = get_tree_bdev(fc, cramfs_blkdev_fill_super);
diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c
index 82da2510721f..1f4b8a277060 100644
--- a/fs/crypto/bio.c
+++ b/fs/crypto/bio.c
@@ -26,7 +26,7 @@
 #include <linux/namei.h>
 #include "fscrypt_private.h"
 
-static void __fscrypt_decrypt_bio(struct bio *bio, bool done)
+void fscrypt_decrypt_bio(struct bio *bio)
 {
 	struct bio_vec *bv;
 	struct bvec_iter_all iter_all;
@@ -37,37 +37,10 @@ static void __fscrypt_decrypt_bio(struct bio *bio, bool done)
 							   bv->bv_offset);
 		if (ret)
 			SetPageError(page);
-		else if (done)
-			SetPageUptodate(page);
-		if (done)
-			unlock_page(page);
 	}
 }
-
-void fscrypt_decrypt_bio(struct bio *bio)
-{
-	__fscrypt_decrypt_bio(bio, false);
-}
 EXPORT_SYMBOL(fscrypt_decrypt_bio);
 
-static void completion_pages(struct work_struct *work)
-{
-	struct fscrypt_ctx *ctx = container_of(work, struct fscrypt_ctx, work);
-	struct bio *bio = ctx->bio;
-
-	__fscrypt_decrypt_bio(bio, true);
-	fscrypt_release_ctx(ctx);
-	bio_put(bio);
-}
-
-void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, struct bio *bio)
-{
-	INIT_WORK(&ctx->work, completion_pages);
-	ctx->bio = bio;
-	fscrypt_enqueue_decrypt_work(&ctx->work);
-}
-EXPORT_SYMBOL(fscrypt_enqueue_decrypt_bio);
-
 int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
 				sector_t pblk, unsigned int len)
 {
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index 32a7ad0098cc..3719efa546c6 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -27,29 +27,20 @@
 #include <linux/ratelimit.h>
 #include <linux/dcache.h>
 #include <linux/namei.h>
-#include <crypto/aes.h>
 #include <crypto/skcipher.h>
 #include "fscrypt_private.h"
 
 static unsigned int num_prealloc_crypto_pages = 32;
-static unsigned int num_prealloc_crypto_ctxs = 128;
 
 module_param(num_prealloc_crypto_pages, uint, 0444);
 MODULE_PARM_DESC(num_prealloc_crypto_pages,
 		"Number of crypto pages to preallocate");
-module_param(num_prealloc_crypto_ctxs, uint, 0444);
-MODULE_PARM_DESC(num_prealloc_crypto_ctxs,
-		"Number of crypto contexts to preallocate");
 
 static mempool_t *fscrypt_bounce_page_pool = NULL;
 
-static LIST_HEAD(fscrypt_free_ctxs);
-static DEFINE_SPINLOCK(fscrypt_ctx_lock);
-
 static struct workqueue_struct *fscrypt_read_workqueue;
 static DEFINE_MUTEX(fscrypt_init_mutex);
 
-static struct kmem_cache *fscrypt_ctx_cachep;
 struct kmem_cache *fscrypt_info_cachep;
 
 void fscrypt_enqueue_decrypt_work(struct work_struct *work)
@@ -58,62 +49,6 @@ void fscrypt_enqueue_decrypt_work(struct work_struct *work)
 }
 EXPORT_SYMBOL(fscrypt_enqueue_decrypt_work);
 
-/**
- * fscrypt_release_ctx() - Release a decryption context
- * @ctx: The decryption context to release.
- *
- * If the decryption context was allocated from the pre-allocated pool, return
- * it to that pool.  Else, free it.
- */
-void fscrypt_release_ctx(struct fscrypt_ctx *ctx)
-{
-	unsigned long flags;
-
-	if (ctx->flags & FS_CTX_REQUIRES_FREE_ENCRYPT_FL) {
-		kmem_cache_free(fscrypt_ctx_cachep, ctx);
-	} else {
-		spin_lock_irqsave(&fscrypt_ctx_lock, flags);
-		list_add(&ctx->free_list, &fscrypt_free_ctxs);
-		spin_unlock_irqrestore(&fscrypt_ctx_lock, flags);
-	}
-}
-EXPORT_SYMBOL(fscrypt_release_ctx);
-
-/**
- * fscrypt_get_ctx() - Get a decryption context
- * @gfp_flags:   The gfp flag for memory allocation
- *
- * Allocate and initialize a decryption context.
- *
- * Return: A new decryption context on success; an ERR_PTR() otherwise.
- */
-struct fscrypt_ctx *fscrypt_get_ctx(gfp_t gfp_flags)
-{
-	struct fscrypt_ctx *ctx;
-	unsigned long flags;
-
-	/*
-	 * First try getting a ctx from the free list so that we don't have to
-	 * call into the slab allocator.
-	 */
-	spin_lock_irqsave(&fscrypt_ctx_lock, flags);
-	ctx = list_first_entry_or_null(&fscrypt_free_ctxs,
-					struct fscrypt_ctx, free_list);
-	if (ctx)
-		list_del(&ctx->free_list);
-	spin_unlock_irqrestore(&fscrypt_ctx_lock, flags);
-	if (!ctx) {
-		ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, gfp_flags);
-		if (!ctx)
-			return ERR_PTR(-ENOMEM);
-		ctx->flags |= FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
-	} else {
-		ctx->flags &= ~FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
-	}
-	return ctx;
-}
-EXPORT_SYMBOL(fscrypt_get_ctx);
-
 struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags)
 {
 	return mempool_alloc(fscrypt_bounce_page_pool, gfp_flags);
@@ -138,14 +73,17 @@ EXPORT_SYMBOL(fscrypt_free_bounce_page);
 void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num,
 			 const struct fscrypt_info *ci)
 {
+	u8 flags = fscrypt_policy_flags(&ci->ci_policy);
+
 	memset(iv, 0, ci->ci_mode->ivsize);
-	iv->lblk_num = cpu_to_le64(lblk_num);
 
-	if (fscrypt_is_direct_key_policy(&ci->ci_policy))
+	if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) {
+		WARN_ON_ONCE((u32)lblk_num != lblk_num);
+		lblk_num |= (u64)ci->ci_inode->i_ino << 32;
+	} else if (flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) {
 		memcpy(iv->nonce, ci->ci_nonce, FS_KEY_DERIVATION_NONCE_SIZE);
-
-	if (ci->ci_essiv_tfm != NULL)
-		crypto_cipher_encrypt_one(ci->ci_essiv_tfm, iv->raw, iv->raw);
+	}
+	iv->lblk_num = cpu_to_le64(lblk_num);
 }
 
 /* Encrypt or decrypt a single filesystem block of file contents */
@@ -396,17 +334,6 @@ const struct dentry_operations fscrypt_d_ops = {
 	.d_revalidate = fscrypt_d_revalidate,
 };
 
-static void fscrypt_destroy(void)
-{
-	struct fscrypt_ctx *pos, *n;
-
-	list_for_each_entry_safe(pos, n, &fscrypt_free_ctxs, free_list)
-		kmem_cache_free(fscrypt_ctx_cachep, pos);
-	INIT_LIST_HEAD(&fscrypt_free_ctxs);
-	mempool_destroy(fscrypt_bounce_page_pool);
-	fscrypt_bounce_page_pool = NULL;
-}
-
 /**
  * fscrypt_initialize() - allocate major buffers for fs encryption.
  * @cop_flags:  fscrypt operations flags
@@ -414,11 +341,11 @@ static void fscrypt_destroy(void)
  * We only call this when we start accessing encrypted files, since it
  * results in memory getting allocated that wouldn't otherwise be used.
  *
- * Return: Zero on success, non-zero otherwise.
+ * Return: 0 on success; -errno on failure
  */
 int fscrypt_initialize(unsigned int cop_flags)
 {
-	int i, res = -ENOMEM;
+	int err = 0;
 
 	/* No need to allocate a bounce page pool if this FS won't use it. */
 	if (cop_flags & FS_CFLG_OWN_PAGES)
@@ -426,29 +353,18 @@ int fscrypt_initialize(unsigned int cop_flags)
 
 	mutex_lock(&fscrypt_init_mutex);
 	if (fscrypt_bounce_page_pool)
-		goto already_initialized;
-
-	for (i = 0; i < num_prealloc_crypto_ctxs; i++) {
-		struct fscrypt_ctx *ctx;
-
-		ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, GFP_NOFS);
-		if (!ctx)
-			goto fail;
-		list_add(&ctx->free_list, &fscrypt_free_ctxs);
-	}
+		goto out_unlock;
 
+	err = -ENOMEM;
 	fscrypt_bounce_page_pool =
 		mempool_create_page_pool(num_prealloc_crypto_pages, 0);
 	if (!fscrypt_bounce_page_pool)
-		goto fail;
+		goto out_unlock;
 
-already_initialized:
-	mutex_unlock(&fscrypt_init_mutex);
-	return 0;
-fail:
-	fscrypt_destroy();
+	err = 0;
+out_unlock:
 	mutex_unlock(&fscrypt_init_mutex);
-	return res;
+	return err;
 }
 
 void fscrypt_msg(const struct inode *inode, const char *level,
@@ -494,13 +410,9 @@ static int __init fscrypt_init(void)
 	if (!fscrypt_read_workqueue)
 		goto fail;
 
-	fscrypt_ctx_cachep = KMEM_CACHE(fscrypt_ctx, SLAB_RECLAIM_ACCOUNT);
-	if (!fscrypt_ctx_cachep)
-		goto fail_free_queue;
-
 	fscrypt_info_cachep = KMEM_CACHE(fscrypt_info, SLAB_RECLAIM_ACCOUNT);
 	if (!fscrypt_info_cachep)
-		goto fail_free_ctx;
+		goto fail_free_queue;
 
 	err = fscrypt_init_keyring();
 	if (err)
@@ -510,8 +422,6 @@ static int __init fscrypt_init(void)
 
 fail_free_info:
 	kmem_cache_destroy(fscrypt_info_cachep);
-fail_free_ctx:
-	kmem_cache_destroy(fscrypt_ctx_cachep);
 fail_free_queue:
 	destroy_workqueue(fscrypt_read_workqueue);
 fail:
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index e84efc01512e..130b50e5a011 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -163,11 +163,8 @@ struct fscrypt_info {
 	/* The actual crypto transform used for encryption and decryption */
 	struct crypto_skcipher *ci_ctfm;
 
-	/*
-	 * Cipher for ESSIV IV generation.  Only set for CBC contents
-	 * encryption, otherwise is NULL.
-	 */
-	struct crypto_cipher *ci_essiv_tfm;
+	/* True if the key should be freed when this fscrypt_info is freed */
+	bool ci_owns_key;
 
 	/*
 	 * Encryption mode used for this inode.  It corresponds to either the
@@ -209,8 +206,6 @@ typedef enum {
 	FS_ENCRYPT,
 } fscrypt_direction_t;
 
-#define FS_CTX_REQUIRES_FREE_ENCRYPT_FL		0x00000001
-
 static inline bool fscrypt_valid_enc_modes(u32 contents_mode,
 					   u32 filenames_mode)
 {
@@ -289,7 +284,8 @@ extern int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key,
  */
 #define HKDF_CONTEXT_KEY_IDENTIFIER	1
 #define HKDF_CONTEXT_PER_FILE_KEY	2
-#define HKDF_CONTEXT_PER_MODE_KEY	3
+#define HKDF_CONTEXT_DIRECT_KEY		3
+#define HKDF_CONTEXT_IV_INO_LBLK_64_KEY	4
 
 extern int fscrypt_hkdf_expand(struct fscrypt_hkdf *hkdf, u8 context,
 			       const u8 *info, unsigned int infolen,
@@ -386,8 +382,14 @@ struct fscrypt_master_key {
 	struct list_head	mk_decrypted_inodes;
 	spinlock_t		mk_decrypted_inodes_lock;
 
-	/* Per-mode tfms for DIRECT_KEY policies, allocated on-demand */
-	struct crypto_skcipher	*mk_mode_keys[__FSCRYPT_MODE_MAX + 1];
+	/* Crypto API transforms for DIRECT_KEY policies, allocated on-demand */
+	struct crypto_skcipher	*mk_direct_tfms[__FSCRYPT_MODE_MAX + 1];
+
+	/*
+	 * Crypto API transforms for filesystem-layer implementation of
+	 * IV_INO_LBLK_64 policies, allocated on-demand.
+	 */
+	struct crypto_skcipher	*mk_iv_ino_lblk_64_tfms[__FSCRYPT_MODE_MAX + 1];
 
 } __randomize_layout;
 
@@ -443,8 +445,7 @@ struct fscrypt_mode {
 	const char *cipher_str;
 	int keysize;
 	int ivsize;
-	bool logged_impl_name;
-	bool needs_essiv;
+	int logged_impl_name;
 };
 
 static inline bool
diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c
index c34fa7c61b43..040df1f5e1c8 100644
--- a/fs/crypto/keyring.c
+++ b/fs/crypto/keyring.c
@@ -43,8 +43,10 @@ static void free_master_key(struct fscrypt_master_key *mk)
 
 	wipe_master_key_secret(&mk->mk_secret);
 
-	for (i = 0; i < ARRAY_SIZE(mk->mk_mode_keys); i++)
-		crypto_free_skcipher(mk->mk_mode_keys[i]);
+	for (i = 0; i <= __FSCRYPT_MODE_MAX; i++) {
+		crypto_free_skcipher(mk->mk_direct_tfms[i]);
+		crypto_free_skcipher(mk->mk_iv_ino_lblk_64_tfms[i]);
+	}
 
 	key_put(mk->mk_users);
 	kzfree(mk);
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index d71c2d6dd162..f577bb6613f9 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -8,15 +8,11 @@
  * Heavily modified since then.
  */
 
-#include <crypto/aes.h>
-#include <crypto/sha.h>
 #include <crypto/skcipher.h>
 #include <linux/key.h>
 
 #include "fscrypt_private.h"
 
-static struct crypto_shash *essiv_hash_tfm;
-
 static struct fscrypt_mode available_modes[] = {
 	[FSCRYPT_MODE_AES_256_XTS] = {
 		.friendly_name = "AES-256-XTS",
@@ -31,11 +27,10 @@ static struct fscrypt_mode available_modes[] = {
 		.ivsize = 16,
 	},
 	[FSCRYPT_MODE_AES_128_CBC] = {
-		.friendly_name = "AES-128-CBC",
-		.cipher_str = "cbc(aes)",
+		.friendly_name = "AES-128-CBC-ESSIV",
+		.cipher_str = "essiv(cbc(aes),sha256)",
 		.keysize = 16,
 		.ivsize = 16,
-		.needs_essiv = true,
 	},
 	[FSCRYPT_MODE_AES_128_CTS] = {
 		.friendly_name = "AES-128-CTS-CBC",
@@ -86,15 +81,13 @@ struct crypto_skcipher *fscrypt_allocate_skcipher(struct fscrypt_mode *mode,
 			    mode->cipher_str, PTR_ERR(tfm));
 		return tfm;
 	}
-	if (unlikely(!mode->logged_impl_name)) {
+	if (!xchg(&mode->logged_impl_name, 1)) {
 		/*
 		 * fscrypt performance can vary greatly depending on which
 		 * crypto algorithm implementation is used.  Help people debug
 		 * performance problems by logging the ->cra_driver_name the
-		 * first time a mode is used.  Note that multiple threads can
-		 * race here, but it doesn't really matter.
+		 * first time a mode is used.
 		 */
-		mode->logged_impl_name = true;
 		pr_info("fscrypt: %s using implementation \"%s\"\n",
 			mode->friendly_name,
 			crypto_skcipher_alg(tfm)->base.cra_driver_name);
@@ -111,131 +104,64 @@ err_free_tfm:
 	return ERR_PTR(err);
 }
 
-static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt)
-{
-	struct crypto_shash *tfm = READ_ONCE(essiv_hash_tfm);
-
-	/* init hash transform on demand */
-	if (unlikely(!tfm)) {
-		struct crypto_shash *prev_tfm;
-
-		tfm = crypto_alloc_shash("sha256", 0, 0);
-		if (IS_ERR(tfm)) {
-			if (PTR_ERR(tfm) == -ENOENT) {
-				fscrypt_warn(NULL,
-					     "Missing crypto API support for SHA-256");
-				return -ENOPKG;
-			}
-			fscrypt_err(NULL,
-				    "Error allocating SHA-256 transform: %ld",
-				    PTR_ERR(tfm));
-			return PTR_ERR(tfm);
-		}
-		prev_tfm = cmpxchg(&essiv_hash_tfm, NULL, tfm);
-		if (prev_tfm) {
-			crypto_free_shash(tfm);
-			tfm = prev_tfm;
-		}
-	}
-
-	{
-		SHASH_DESC_ON_STACK(desc, tfm);
-		desc->tfm = tfm;
-
-		return crypto_shash_digest(desc, key, keysize, salt);
-	}
-}
-
-static int init_essiv_generator(struct fscrypt_info *ci, const u8 *raw_key,
-				int keysize)
-{
-	int err;
-	struct crypto_cipher *essiv_tfm;
-	u8 salt[SHA256_DIGEST_SIZE];
-
-	if (WARN_ON(ci->ci_mode->ivsize != AES_BLOCK_SIZE))
-		return -EINVAL;
-
-	essiv_tfm = crypto_alloc_cipher("aes", 0, 0);
-	if (IS_ERR(essiv_tfm))
-		return PTR_ERR(essiv_tfm);
-
-	ci->ci_essiv_tfm = essiv_tfm;
-
-	err = derive_essiv_salt(raw_key, keysize, salt);
-	if (err)
-		goto out;
-
-	/*
-	 * Using SHA256 to derive the salt/key will result in AES-256 being
-	 * used for IV generation. File contents encryption will still use the
-	 * configured keysize (AES-128) nevertheless.
-	 */
-	err = crypto_cipher_setkey(essiv_tfm, salt, sizeof(salt));
-	if (err)
-		goto out;
-
-out:
-	memzero_explicit(salt, sizeof(salt));
-	return err;
-}
-
-/* Given the per-file key, set up the file's crypto transform object(s) */
+/* Given the per-file key, set up the file's crypto transform object */
 int fscrypt_set_derived_key(struct fscrypt_info *ci, const u8 *derived_key)
 {
-	struct fscrypt_mode *mode = ci->ci_mode;
-	struct crypto_skcipher *ctfm;
-	int err;
-
-	ctfm = fscrypt_allocate_skcipher(mode, derived_key, ci->ci_inode);
-	if (IS_ERR(ctfm))
-		return PTR_ERR(ctfm);
+	struct crypto_skcipher *tfm;
 
-	ci->ci_ctfm = ctfm;
+	tfm = fscrypt_allocate_skcipher(ci->ci_mode, derived_key, ci->ci_inode);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
 
-	if (mode->needs_essiv) {
-		err = init_essiv_generator(ci, derived_key, mode->keysize);
-		if (err) {
-			fscrypt_warn(ci->ci_inode,
-				     "Error initializing ESSIV generator: %d",
-				     err);
-			return err;
-		}
-	}
+	ci->ci_ctfm = tfm;
+	ci->ci_owns_key = true;
 	return 0;
 }
 
 static int setup_per_mode_key(struct fscrypt_info *ci,
-			      struct fscrypt_master_key *mk)
+			      struct fscrypt_master_key *mk,
+			      struct crypto_skcipher **tfms,
+			      u8 hkdf_context, bool include_fs_uuid)
 {
+	const struct inode *inode = ci->ci_inode;
+	const struct super_block *sb = inode->i_sb;
 	struct fscrypt_mode *mode = ci->ci_mode;
 	u8 mode_num = mode - available_modes;
 	struct crypto_skcipher *tfm, *prev_tfm;
 	u8 mode_key[FSCRYPT_MAX_KEY_SIZE];
+	u8 hkdf_info[sizeof(mode_num) + sizeof(sb->s_uuid)];
+	unsigned int hkdf_infolen = 0;
 	int err;
 
-	if (WARN_ON(mode_num >= ARRAY_SIZE(mk->mk_mode_keys)))
+	if (WARN_ON(mode_num > __FSCRYPT_MODE_MAX))
 		return -EINVAL;
 
 	/* pairs with cmpxchg() below */
-	tfm = READ_ONCE(mk->mk_mode_keys[mode_num]);
+	tfm = READ_ONCE(tfms[mode_num]);
 	if (likely(tfm != NULL))
 		goto done;
 
 	BUILD_BUG_ON(sizeof(mode_num) != 1);
+	BUILD_BUG_ON(sizeof(sb->s_uuid) != 16);
+	BUILD_BUG_ON(sizeof(hkdf_info) != 17);
+	hkdf_info[hkdf_infolen++] = mode_num;
+	if (include_fs_uuid) {
+		memcpy(&hkdf_info[hkdf_infolen], &sb->s_uuid,
+		       sizeof(sb->s_uuid));
+		hkdf_infolen += sizeof(sb->s_uuid);
+	}
 	err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf,
-				  HKDF_CONTEXT_PER_MODE_KEY,
-				  &mode_num, sizeof(mode_num),
+				  hkdf_context, hkdf_info, hkdf_infolen,
 				  mode_key, mode->keysize);
 	if (err)
 		return err;
-	tfm = fscrypt_allocate_skcipher(mode, mode_key, ci->ci_inode);
+	tfm = fscrypt_allocate_skcipher(mode, mode_key, inode);
 	memzero_explicit(mode_key, mode->keysize);
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
 	/* pairs with READ_ONCE() above */
-	prev_tfm = cmpxchg(&mk->mk_mode_keys[mode_num], NULL, tfm);
+	prev_tfm = cmpxchg(&tfms[mode_num], NULL, tfm);
 	if (prev_tfm != NULL) {
 		crypto_free_skcipher(tfm);
 		tfm = prev_tfm;
@@ -266,7 +192,19 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci,
 				     ci->ci_mode->friendly_name);
 			return -EINVAL;
 		}
-		return setup_per_mode_key(ci, mk);
+		return setup_per_mode_key(ci, mk, mk->mk_direct_tfms,
+					  HKDF_CONTEXT_DIRECT_KEY, false);
+	} else if (ci->ci_policy.v2.flags &
+		   FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) {
+		/*
+		 * IV_INO_LBLK_64: encryption keys are derived from (master_key,
+		 * mode_num, filesystem_uuid), and inode number is included in
+		 * the IVs.  This format is optimized for use with inline
+		 * encryption hardware compliant with the UFS or eMMC standards.
+		 */
+		return setup_per_mode_key(ci, mk, mk->mk_iv_ino_lblk_64_tfms,
+					  HKDF_CONTEXT_IV_INO_LBLK_64_KEY,
+					  true);
 	}
 
 	err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf,
@@ -388,13 +326,10 @@ static void put_crypt_info(struct fscrypt_info *ci)
 	if (!ci)
 		return;
 
-	if (ci->ci_direct_key) {
+	if (ci->ci_direct_key)
 		fscrypt_put_direct_key(ci->ci_direct_key);
-	} else if ((ci->ci_ctfm != NULL || ci->ci_essiv_tfm != NULL) &&
-		   !fscrypt_is_direct_key_policy(&ci->ci_policy)) {
+	else if (ci->ci_owns_key)
 		crypto_free_skcipher(ci->ci_ctfm);
-		crypto_free_cipher(ci->ci_essiv_tfm);
-	}
 
 	key = ci->ci_master_key;
 	if (key) {
@@ -415,6 +350,7 @@ static void put_crypt_info(struct fscrypt_info *ci)
 			key_invalidate(key);
 		key_put(key);
 	}
+	memzero_explicit(ci, sizeof(*ci));
 	kmem_cache_free(fscrypt_info_cachep, ci);
 }
 
diff --git a/fs/crypto/keysetup_v1.c b/fs/crypto/keysetup_v1.c
index ad1a36c370c3..5298ef22aa85 100644
--- a/fs/crypto/keysetup_v1.c
+++ b/fs/crypto/keysetup_v1.c
@@ -270,10 +270,6 @@ static int setup_v1_file_key_direct(struct fscrypt_info *ci,
 		return -EINVAL;
 	}
 
-	/* ESSIV implies 16-byte IVs which implies !DIRECT_KEY */
-	if (WARN_ON(mode->needs_essiv))
-		return -EINVAL;
-
 	dk = fscrypt_get_direct_key(ci, raw_master_key);
 	if (IS_ERR(dk))
 		return PTR_ERR(dk);
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 4072ba644595..96f528071bed 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -29,6 +29,40 @@ bool fscrypt_policies_equal(const union fscrypt_policy *policy1,
 	return !memcmp(policy1, policy2, fscrypt_policy_size(policy1));
 }
 
+static bool supported_iv_ino_lblk_64_policy(
+					const struct fscrypt_policy_v2 *policy,
+					const struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+	int ino_bits = 64, lblk_bits = 64;
+
+	if (policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) {
+		fscrypt_warn(inode,
+			     "The DIRECT_KEY and IV_INO_LBLK_64 flags are mutually exclusive");
+		return false;
+	}
+	/*
+	 * It's unsafe to include inode numbers in the IVs if the filesystem can
+	 * potentially renumber inodes, e.g. via filesystem shrinking.
+	 */
+	if (!sb->s_cop->has_stable_inodes ||
+	    !sb->s_cop->has_stable_inodes(sb)) {
+		fscrypt_warn(inode,
+			     "Can't use IV_INO_LBLK_64 policy on filesystem '%s' because it doesn't have stable inode numbers",
+			     sb->s_id);
+		return false;
+	}
+	if (sb->s_cop->get_ino_and_lblk_bits)
+		sb->s_cop->get_ino_and_lblk_bits(sb, &ino_bits, &lblk_bits);
+	if (ino_bits > 32 || lblk_bits > 32) {
+		fscrypt_warn(inode,
+			     "Can't use IV_INO_LBLK_64 policy on filesystem '%s' because it doesn't use 32-bit inode and block numbers",
+			     sb->s_id);
+		return false;
+	}
+	return true;
+}
+
 /**
  * fscrypt_supported_policy - check whether an encryption policy is supported
  *
@@ -55,7 +89,8 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u,
 			return false;
 		}
 
-		if (policy->flags & ~FSCRYPT_POLICY_FLAGS_VALID) {
+		if (policy->flags & ~(FSCRYPT_POLICY_FLAGS_PAD_MASK |
+				      FSCRYPT_POLICY_FLAG_DIRECT_KEY)) {
 			fscrypt_warn(inode,
 				     "Unsupported encryption flags (0x%02x)",
 				     policy->flags);
@@ -83,6 +118,10 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u,
 			return false;
 		}
 
+		if ((policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) &&
+		    !supported_iv_ino_lblk_64_policy(policy, inode))
+			return false;
+
 		if (memchr_inv(policy->__reserved, 0,
 			       sizeof(policy->__reserved))) {
 			fscrypt_warn(inode,
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index cbb5ca830e57..ef42ab040905 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -106,3 +106,20 @@ config EXT4_DEBUG
 	  If you select Y here, then you will be able to turn on debugging
 	  with a command such as:
 		echo 1 > /sys/module/ext4/parameters/mballoc_debug
+
+config EXT4_KUNIT_TESTS
+	bool "KUnit tests for ext4"
+	select EXT4_FS
+	depends on KUNIT
+	help
+	  This builds the ext4 KUnit tests.
+
+	  KUnit tests run during boot and output the results to the debug log
+	  in TAP format (http://testanything.org/). Only useful for kernel devs
+	  running KUnit test harness and are not for inclusion into a production
+	  build.
+
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index b17ddc229ac5..840b91d040f1 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -13,4 +13,5 @@ ext4-y	:= balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \
 
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
 ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o
+ext4-$(CONFIG_EXT4_KUNIT_TESTS)		+= inode-test.o
 ext4-$(CONFIG_FS_VERITY)		+= verity.o
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 03db3e71676c..b3a2cc7c0252 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1678,6 +1678,7 @@ static inline bool ext4_verity_in_progress(struct inode *inode)
 #define EXT4_FEATURE_COMPAT_RESIZE_INODE	0x0010
 #define EXT4_FEATURE_COMPAT_DIR_INDEX		0x0020
 #define EXT4_FEATURE_COMPAT_SPARSE_SUPER2	0x0200
+#define EXT4_FEATURE_COMPAT_STABLE_INODES	0x0800
 
 #define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
 #define EXT4_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
@@ -1779,6 +1780,7 @@ EXT4_FEATURE_COMPAT_FUNCS(xattr,		EXT_ATTR)
 EXT4_FEATURE_COMPAT_FUNCS(resize_inode,		RESIZE_INODE)
 EXT4_FEATURE_COMPAT_FUNCS(dir_index,		DIR_INDEX)
 EXT4_FEATURE_COMPAT_FUNCS(sparse_super2,	SPARSE_SUPER2)
+EXT4_FEATURE_COMPAT_FUNCS(stable_inodes,	STABLE_INODES)
 
 EXT4_FEATURE_RO_COMPAT_FUNCS(sparse_super,	SPARSE_SUPER)
 EXT4_FEATURE_RO_COMPAT_FUNCS(large_file,	LARGE_FILE)
diff --git a/fs/ext4/inode-test.c b/fs/ext4/inode-test.c
new file mode 100644
index 000000000000..92a9da1774aa
--- /dev/null
+++ b/fs/ext4/inode-test.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnit test of ext4 inode that verify the seconds part of [a/c/m]
+ * timestamps in ext4 inode structs are decoded correctly.
+ */
+
+#include <kunit/test.h>
+#include <linux/kernel.h>
+#include <linux/time64.h>
+
+#include "ext4.h"
+
+/*
+ * For constructing the nonnegative timestamp lower bound value.
+ * binary: 00000000 00000000 00000000 00000000
+ */
+#define LOWER_MSB_0 0L
+/*
+ * For constructing the nonnegative timestamp upper bound value.
+ * binary: 01111111 11111111 11111111 11111111
+ *
+ */
+#define UPPER_MSB_0 0x7fffffffL
+/*
+ * For constructing the negative timestamp lower bound value.
+ * binary: 10000000 00000000 00000000 00000000
+ */
+#define LOWER_MSB_1 (-0x80000000L)
+/*
+ * For constructing the negative timestamp upper bound value.
+ * binary: 11111111 11111111 11111111 11111111
+ */
+#define UPPER_MSB_1 (-1L)
+/*
+ * Upper bound for nanoseconds value supported by the encoding.
+ * binary: 00111111 11111111 11111111 11111111
+ */
+#define MAX_NANOSECONDS ((1L << 30) - 1)
+
+#define CASE_NAME_FORMAT "%s: msb:%x lower_bound:%x extra_bits: %x"
+
+#define LOWER_BOUND_NEG_NO_EXTRA_BITS_CASE\
+	"1901-12-13 Lower bound of 32bit < 0 timestamp, no extra bits"
+#define UPPER_BOUND_NEG_NO_EXTRA_BITS_CASE\
+	"1969-12-31 Upper bound of 32bit < 0 timestamp, no extra bits"
+#define LOWER_BOUND_NONNEG_NO_EXTRA_BITS_CASE\
+	"1970-01-01 Lower bound of 32bit >=0 timestamp, no extra bits"
+#define UPPER_BOUND_NONNEG_NO_EXTRA_BITS_CASE\
+	"2038-01-19 Upper bound of 32bit >=0 timestamp, no extra bits"
+#define LOWER_BOUND_NEG_LO_1_CASE\
+	"2038-01-19 Lower bound of 32bit <0 timestamp, lo extra sec bit on"
+#define UPPER_BOUND_NEG_LO_1_CASE\
+	"2106-02-07 Upper bound of 32bit <0 timestamp, lo extra sec bit on"
+#define LOWER_BOUND_NONNEG_LO_1_CASE\
+	"2106-02-07 Lower bound of 32bit >=0 timestamp, lo extra sec bit on"
+#define UPPER_BOUND_NONNEG_LO_1_CASE\
+	"2174-02-25 Upper bound of 32bit >=0 timestamp, lo extra sec bit on"
+#define LOWER_BOUND_NEG_HI_1_CASE\
+	"2174-02-25 Lower bound of 32bit <0 timestamp, hi extra sec bit on"
+#define UPPER_BOUND_NEG_HI_1_CASE\
+	"2242-03-16 Upper bound of 32bit <0 timestamp, hi extra sec bit on"
+#define LOWER_BOUND_NONNEG_HI_1_CASE\
+	"2242-03-16 Lower bound of 32bit >=0 timestamp, hi extra sec bit on"
+#define UPPER_BOUND_NONNEG_HI_1_CASE\
+	"2310-04-04 Upper bound of 32bit >=0 timestamp, hi extra sec bit on"
+#define UPPER_BOUND_NONNEG_HI_1_NS_1_CASE\
+	"2310-04-04 Upper bound of 32bit>=0 timestamp, hi extra sec bit 1. 1 ns"
+#define LOWER_BOUND_NONNEG_HI_1_NS_MAX_CASE\
+	"2378-04-22 Lower bound of 32bit>= timestamp. Extra sec bits 1. Max ns"
+#define LOWER_BOUND_NONNEG_EXTRA_BITS_1_CASE\
+	"2378-04-22 Lower bound of 32bit >=0 timestamp. All extra sec bits on"
+#define UPPER_BOUND_NONNEG_EXTRA_BITS_1_CASE\
+	"2446-05-10 Upper bound of 32bit >=0 timestamp. All extra sec bits on"
+
+struct timestamp_expectation {
+	const char *test_case_name;
+	struct timespec64 expected;
+	u32 extra_bits;
+	bool msb_set;
+	bool lower_bound;
+};
+
+static time64_t get_32bit_time(const struct timestamp_expectation * const test)
+{
+	if (test->msb_set) {
+		if (test->lower_bound)
+			return LOWER_MSB_1;
+
+		return UPPER_MSB_1;
+	}
+
+	if (test->lower_bound)
+		return LOWER_MSB_0;
+	return UPPER_MSB_0;
+}
+
+
+/*
+ *  Test data is derived from the table in the Inode Timestamps section of
+ *  Documentation/filesystems/ext4/inodes.rst.
+ */
+static void inode_test_xtimestamp_decoding(struct kunit *test)
+{
+	const struct timestamp_expectation test_data[] = {
+		{
+			.test_case_name = LOWER_BOUND_NEG_NO_EXTRA_BITS_CASE,
+			.msb_set = true,
+			.lower_bound = true,
+			.extra_bits = 0,
+			.expected = {.tv_sec = -0x80000000LL, .tv_nsec = 0L},
+		},
+
+		{
+			.test_case_name = UPPER_BOUND_NEG_NO_EXTRA_BITS_CASE,
+			.msb_set = true,
+			.lower_bound = false,
+			.extra_bits = 0,
+			.expected = {.tv_sec = -1LL, .tv_nsec = 0L},
+		},
+
+		{
+			.test_case_name = LOWER_BOUND_NONNEG_NO_EXTRA_BITS_CASE,
+			.msb_set = false,
+			.lower_bound = true,
+			.extra_bits = 0,
+			.expected = {0LL, 0L},
+		},
+
+		{
+			.test_case_name = UPPER_BOUND_NONNEG_NO_EXTRA_BITS_CASE,
+			.msb_set = false,
+			.lower_bound = false,
+			.extra_bits = 0,
+			.expected = {.tv_sec = 0x7fffffffLL, .tv_nsec = 0L},
+		},
+
+		{
+			.test_case_name = LOWER_BOUND_NEG_LO_1_CASE,
+			.msb_set = true,
+			.lower_bound = true,
+			.extra_bits = 1,
+			.expected = {.tv_sec = 0x80000000LL, .tv_nsec = 0L},
+		},
+
+		{
+			.test_case_name = UPPER_BOUND_NEG_LO_1_CASE,
+			.msb_set = true,
+			.lower_bound = false,
+			.extra_bits = 1,
+			.expected = {.tv_sec = 0xffffffffLL, .tv_nsec = 0L},
+		},
+
+		{
+			.test_case_name = LOWER_BOUND_NONNEG_LO_1_CASE,
+			.msb_set = false,
+			.lower_bound = true,
+			.extra_bits = 1,
+			.expected = {.tv_sec = 0x100000000LL, .tv_nsec = 0L},
+		},
+
+		{
+			.test_case_name = UPPER_BOUND_NONNEG_LO_1_CASE,
+			.msb_set = false,
+			.lower_bound = false,
+			.extra_bits = 1,
+			.expected = {.tv_sec = 0x17fffffffLL, .tv_nsec = 0L},
+		},
+
+		{
+			.test_case_name = LOWER_BOUND_NEG_HI_1_CASE,
+			.msb_set = true,
+			.lower_bound = true,
+			.extra_bits =  2,
+			.expected = {.tv_sec = 0x180000000LL, .tv_nsec = 0L},
+		},
+
+		{
+			.test_case_name = UPPER_BOUND_NEG_HI_1_CASE,
+			.msb_set = true,
+			.lower_bound = false,
+			.extra_bits = 2,
+			.expected = {.tv_sec = 0x1ffffffffLL, .tv_nsec = 0L},
+		},
+
+		{
+			.test_case_name = LOWER_BOUND_NONNEG_HI_1_CASE,
+			.msb_set = false,
+			.lower_bound = true,
+			.extra_bits = 2,
+			.expected = {.tv_sec = 0x200000000LL, .tv_nsec = 0L},
+		},
+
+		{
+			.test_case_name = UPPER_BOUND_NONNEG_HI_1_CASE,
+			.msb_set = false,
+			.lower_bound = false,
+			.extra_bits = 2,
+			.expected = {.tv_sec = 0x27fffffffLL, .tv_nsec = 0L},
+		},
+
+		{
+			.test_case_name = UPPER_BOUND_NONNEG_HI_1_NS_1_CASE,
+			.msb_set = false,
+			.lower_bound = false,
+			.extra_bits = 6,
+			.expected = {.tv_sec = 0x27fffffffLL, .tv_nsec = 1L},
+		},
+
+		{
+			.test_case_name = LOWER_BOUND_NONNEG_HI_1_NS_MAX_CASE,
+			.msb_set = false,
+			.lower_bound = true,
+			.extra_bits = 0xFFFFFFFF,
+			.expected = {.tv_sec = 0x300000000LL,
+				     .tv_nsec = MAX_NANOSECONDS},
+		},
+
+		{
+			.test_case_name = LOWER_BOUND_NONNEG_EXTRA_BITS_1_CASE,
+			.msb_set = false,
+			.lower_bound = true,
+			.extra_bits = 3,
+			.expected = {.tv_sec = 0x300000000LL, .tv_nsec = 0L},
+		},
+
+		{
+			.test_case_name = UPPER_BOUND_NONNEG_EXTRA_BITS_1_CASE,
+			.msb_set = false,
+			.lower_bound = false,
+			.extra_bits = 3,
+			.expected = {.tv_sec = 0x37fffffffLL, .tv_nsec = 0L},
+		}
+	};
+
+	struct timespec64 timestamp;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data); ++i) {
+		timestamp.tv_sec = get_32bit_time(&test_data[i]);
+		ext4_decode_extra_time(&timestamp,
+				       cpu_to_le32(test_data[i].extra_bits));
+
+		KUNIT_EXPECT_EQ_MSG(test,
+				    test_data[i].expected.tv_sec,
+				    timestamp.tv_sec,
+				    CASE_NAME_FORMAT,
+				    test_data[i].test_case_name,
+				    test_data[i].msb_set,
+				    test_data[i].lower_bound,
+				    test_data[i].extra_bits);
+		KUNIT_EXPECT_EQ_MSG(test,
+				    test_data[i].expected.tv_nsec,
+				    timestamp.tv_nsec,
+				    CASE_NAME_FORMAT,
+				    test_data[i].test_case_name,
+				    test_data[i].msb_set,
+				    test_data[i].lower_bound,
+				    test_data[i].extra_bits);
+	}
+}
+
+static struct kunit_case ext4_inode_test_cases[] = {
+	KUNIT_CASE(inode_test_xtimestamp_decoding),
+	{}
+};
+
+static struct kunit_suite ext4_inode_test_suite = {
+	.name = "ext4_inode_test",
+	.test_cases = ext4_inode_test_cases,
+};
+
+kunit_test_suite(ext4_inode_test_suite);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 516faa280ced..a7ca65177980 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5717,12 +5717,15 @@ int ext4_getattr(const struct path *path, struct kstat *stat,
 		stat->attributes |= STATX_ATTR_IMMUTABLE;
 	if (flags & EXT4_NODUMP_FL)
 		stat->attributes |= STATX_ATTR_NODUMP;
+	if (flags & EXT4_VERITY_FL)
+		stat->attributes |= STATX_ATTR_VERITY;
 
 	stat->attributes_mask |= (STATX_ATTR_APPEND |
 				  STATX_ATTR_COMPRESSED |
 				  STATX_ATTR_ENCRYPTED |
 				  STATX_ATTR_IMMUTABLE |
-				  STATX_ATTR_NODUMP);
+				  STATX_ATTR_NODUMP |
+				  STATX_ATTR_VERITY);
 
 	generic_fillattr(inode, stat);
 	return 0;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index dd654e53ba3d..b3cbf8622eab 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1345,6 +1345,18 @@ static bool ext4_dummy_context(struct inode *inode)
 	return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb));
 }
 
+static bool ext4_has_stable_inodes(struct super_block *sb)
+{
+	return ext4_has_feature_stable_inodes(sb);
+}
+
+static void ext4_get_ino_and_lblk_bits(struct super_block *sb,
+				       int *ino_bits_ret, int *lblk_bits_ret)
+{
+	*ino_bits_ret = 8 * sizeof(EXT4_SB(sb)->s_es->s_inodes_count);
+	*lblk_bits_ret = 8 * sizeof(ext4_lblk_t);
+}
+
 static const struct fscrypt_operations ext4_cryptops = {
 	.key_prefix		= "ext4:",
 	.get_context		= ext4_get_context,
@@ -1352,6 +1364,8 @@ static const struct fscrypt_operations ext4_cryptops = {
 	.dummy_context		= ext4_dummy_context,
 	.empty_dir		= ext4_empty_dir,
 	.max_namelen		= EXT4_NAME_LEN,
+	.has_stable_inodes	= ext4_has_stable_inodes,
+	.get_ino_and_lblk_bits	= ext4_get_ino_and_lblk_bits,
 };
 #endif
 
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 29bc0a542759..6a2e5b7d8fc7 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -726,11 +726,14 @@ int f2fs_getattr(const struct path *path, struct kstat *stat,
 		stat->attributes |= STATX_ATTR_IMMUTABLE;
 	if (flags & F2FS_NODUMP_FL)
 		stat->attributes |= STATX_ATTR_NODUMP;
+	if (IS_VERITY(inode))
+		stat->attributes |= STATX_ATTR_VERITY;
 
 	stat->attributes_mask |= (STATX_ATTR_APPEND |
 				  STATX_ATTR_ENCRYPTED |
 				  STATX_ATTR_IMMUTABLE |
-				  STATX_ATTR_NODUMP);
+				  STATX_ATTR_NODUMP |
+				  STATX_ATTR_VERITY);
 
 	generic_fillattr(inode, stat);
 
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 808709581481..2c997f94a3b2 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1771,7 +1771,8 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
 			return -EIO;
 		}
 		trace_f2fs_issue_reset_zone(bdev, blkstart);
-		return blkdev_reset_zones(bdev, sector, nr_sects, GFP_NOFS);
+		return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
+					sector, nr_sects, GFP_NOFS);
 	}
 
 	/* For conventional zones, use regular discard if supported */
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 1443cee15863..197ad6b314de 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -2308,13 +2308,27 @@ static bool f2fs_dummy_context(struct inode *inode)
 	return DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(inode));
 }
 
+static bool f2fs_has_stable_inodes(struct super_block *sb)
+{
+	return true;
+}
+
+static void f2fs_get_ino_and_lblk_bits(struct super_block *sb,
+				       int *ino_bits_ret, int *lblk_bits_ret)
+{
+	*ino_bits_ret = 8 * sizeof(nid_t);
+	*lblk_bits_ret = 8 * sizeof(block_t);
+}
+
 static const struct fscrypt_operations f2fs_cryptops = {
-	.key_prefix	= "f2fs:",
-	.get_context	= f2fs_get_context,
-	.set_context	= f2fs_set_context,
-	.dummy_context	= f2fs_dummy_context,
-	.empty_dir	= f2fs_empty_dir,
-	.max_namelen	= F2FS_NAME_LEN,
+	.key_prefix		= "f2fs:",
+	.get_context		= f2fs_get_context,
+	.set_context		= f2fs_set_context,
+	.dummy_context		= f2fs_dummy_context,
+	.empty_dir		= f2fs_empty_dir,
+	.max_namelen		= F2FS_NAME_LEN,
+	.has_stable_inodes	= f2fs_has_stable_inodes,
+	.get_ino_and_lblk_bits	= f2fs_get_ino_and_lblk_bits,
 };
 #endif
 
@@ -2857,15 +2871,21 @@ static int init_percpu_info(struct f2fs_sb_info *sbi)
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
+static int f2fs_report_zone_cb(struct blk_zone *zone, unsigned int idx,
+			       void *data)
+{
+	struct f2fs_dev_info *dev = data;
+
+	if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL)
+		set_bit(idx, dev->blkz_seq);
+	return 0;
+}
+
 static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
 {
 	struct block_device *bdev = FDEV(devi).bdev;
 	sector_t nr_sectors = bdev->bd_part->nr_sects;
-	sector_t sector = 0;
-	struct blk_zone *zones;
-	unsigned int i, nr_zones;
-	unsigned int n = 0;
-	int err = -EIO;
+	int ret;
 
 	if (!f2fs_sb_has_blkzoned(sbi))
 		return 0;
@@ -2890,38 +2910,13 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
 	if (!FDEV(devi).blkz_seq)
 		return -ENOMEM;
 
-#define F2FS_REPORT_NR_ZONES   4096
-
-	zones = f2fs_kzalloc(sbi,
-			     array_size(F2FS_REPORT_NR_ZONES,
-					sizeof(struct blk_zone)),
-			     GFP_KERNEL);
-	if (!zones)
-		return -ENOMEM;
-
 	/* Get block zones type */
-	while (zones && sector < nr_sectors) {
-
-		nr_zones = F2FS_REPORT_NR_ZONES;
-		err = blkdev_report_zones(bdev, sector, zones, &nr_zones);
-		if (err)
-			break;
-		if (!nr_zones) {
-			err = -EIO;
-			break;
-		}
-
-		for (i = 0; i < nr_zones; i++) {
-			if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL)
-				set_bit(n, FDEV(devi).blkz_seq);
-			sector += zones[i].len;
-			n++;
-		}
-	}
-
-	kvfree(zones);
+	ret = blkdev_report_zones(bdev, 0, BLK_ALL_ZONES, f2fs_report_zone_cb,
+				  &FDEV(devi));
+	if (ret < 0)
+		return ret;
 
-	return err;
+	return 0;
 }
 #endif
 
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 3d40771e8e7c..41b6438bd2d9 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -261,7 +261,7 @@ static int f_getowner_uids(struct file *filp, unsigned long arg)
 static bool rw_hint_valid(enum rw_hint hint)
 {
 	switch (hint) {
-	case RWF_WRITE_LIFE_NOT_SET:
+	case RWH_WRITE_LIFE_NOT_SET:
 	case RWH_WRITE_LIFE_NONE:
 	case RWH_WRITE_LIFE_SHORT:
 	case RWH_WRITE_LIFE_MEDIUM:
diff --git a/fs/file.c b/fs/file.c
index 3da91a112bab..b241ea7f1aa4 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -795,7 +795,7 @@ unsigned long __fdget_pos(unsigned int fd)
 	unsigned long v = __fdget(fd);
 	struct file *file = (struct file *)(v & ~3);
 
-	if (file && (file->f_mode & FMODE_ATOMIC_POS)) {
+	if (file && !(file->f_mode & FMODE_STREAM)) {
 		if (file_count(file) > 1) {
 			v |= FDPUT_POS_UNLOCK;
 			mutex_lock(&file->f_pos_lock);
diff --git a/fs/io-wq.c b/fs/io-wq.c
new file mode 100644
index 000000000000..9174007ce107
--- /dev/null
+++ b/fs/io-wq.c
@@ -0,0 +1,1065 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Basic worker thread pool for io_uring
+ *
+ * Copyright (C) 2019 Jens Axboe
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/sched/signal.h>
+#include <linux/mm.h>
+#include <linux/mmu_context.h>
+#include <linux/sched/mm.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+#include <linux/kthread.h>
+#include <linux/rculist_nulls.h>
+
+#include "io-wq.h"
+
+#define WORKER_IDLE_TIMEOUT	(5 * HZ)
+
+enum {
+	IO_WORKER_F_UP		= 1,	/* up and active */
+	IO_WORKER_F_RUNNING	= 2,	/* account as running */
+	IO_WORKER_F_FREE	= 4,	/* worker on free list */
+	IO_WORKER_F_EXITING	= 8,	/* worker exiting */
+	IO_WORKER_F_FIXED	= 16,	/* static idle worker */
+	IO_WORKER_F_BOUND	= 32,	/* is doing bounded work */
+};
+
+enum {
+	IO_WQ_BIT_EXIT		= 0,	/* wq exiting */
+	IO_WQ_BIT_CANCEL	= 1,	/* cancel work on list */
+};
+
+enum {
+	IO_WQE_FLAG_STALLED	= 1,	/* stalled on hash */
+};
+
+/*
+ * One for each thread in a wqe pool
+ */
+struct io_worker {
+	refcount_t ref;
+	unsigned flags;
+	struct hlist_nulls_node nulls_node;
+	struct list_head all_list;
+	struct task_struct *task;
+	wait_queue_head_t wait;
+	struct io_wqe *wqe;
+
+	struct io_wq_work *cur_work;
+	spinlock_t lock;
+
+	struct rcu_head rcu;
+	struct mm_struct *mm;
+	struct files_struct *restore_files;
+};
+
+#if BITS_PER_LONG == 64
+#define IO_WQ_HASH_ORDER	6
+#else
+#define IO_WQ_HASH_ORDER	5
+#endif
+
+struct io_wqe_acct {
+	unsigned nr_workers;
+	unsigned max_workers;
+	atomic_t nr_running;
+};
+
+enum {
+	IO_WQ_ACCT_BOUND,
+	IO_WQ_ACCT_UNBOUND,
+};
+
+/*
+ * Per-node worker thread pool
+ */
+struct io_wqe {
+	struct {
+		spinlock_t lock;
+		struct list_head work_list;
+		unsigned long hash_map;
+		unsigned flags;
+	} ____cacheline_aligned_in_smp;
+
+	int node;
+	struct io_wqe_acct acct[2];
+
+	struct hlist_nulls_head free_list;
+	struct hlist_nulls_head busy_list;
+	struct list_head all_list;
+
+	struct io_wq *wq;
+};
+
+/*
+ * Per io_wq state
+  */
+struct io_wq {
+	struct io_wqe **wqes;
+	unsigned long state;
+	unsigned nr_wqes;
+
+	get_work_fn *get_work;
+	put_work_fn *put_work;
+
+	struct task_struct *manager;
+	struct user_struct *user;
+	struct mm_struct *mm;
+	refcount_t refs;
+	struct completion done;
+};
+
+static bool io_worker_get(struct io_worker *worker)
+{
+	return refcount_inc_not_zero(&worker->ref);
+}
+
+static void io_worker_release(struct io_worker *worker)
+{
+	if (refcount_dec_and_test(&worker->ref))
+		wake_up_process(worker->task);
+}
+
+/*
+ * Note: drops the wqe->lock if returning true! The caller must re-acquire
+ * the lock in that case. Some callers need to restart handling if this
+ * happens, so we can't just re-acquire the lock on behalf of the caller.
+ */
+static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker)
+{
+	bool dropped_lock = false;
+
+	if (current->files != worker->restore_files) {
+		__acquire(&wqe->lock);
+		spin_unlock_irq(&wqe->lock);
+		dropped_lock = true;
+
+		task_lock(current);
+		current->files = worker->restore_files;
+		task_unlock(current);
+	}
+
+	/*
+	 * If we have an active mm, we need to drop the wq lock before unusing
+	 * it. If we do, return true and let the caller retry the idle loop.
+	 */
+	if (worker->mm) {
+		if (!dropped_lock) {
+			__acquire(&wqe->lock);
+			spin_unlock_irq(&wqe->lock);
+			dropped_lock = true;
+		}
+		__set_current_state(TASK_RUNNING);
+		set_fs(KERNEL_DS);
+		unuse_mm(worker->mm);
+		mmput(worker->mm);
+		worker->mm = NULL;
+	}
+
+	return dropped_lock;
+}
+
+static inline struct io_wqe_acct *io_work_get_acct(struct io_wqe *wqe,
+						   struct io_wq_work *work)
+{
+	if (work->flags & IO_WQ_WORK_UNBOUND)
+		return &wqe->acct[IO_WQ_ACCT_UNBOUND];
+
+	return &wqe->acct[IO_WQ_ACCT_BOUND];
+}
+
+static inline struct io_wqe_acct *io_wqe_get_acct(struct io_wqe *wqe,
+						  struct io_worker *worker)
+{
+	if (worker->flags & IO_WORKER_F_BOUND)
+		return &wqe->acct[IO_WQ_ACCT_BOUND];
+
+	return &wqe->acct[IO_WQ_ACCT_UNBOUND];
+}
+
+static void io_worker_exit(struct io_worker *worker)
+{
+	struct io_wqe *wqe = worker->wqe;
+	struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker);
+	unsigned nr_workers;
+
+	/*
+	 * If we're not at zero, someone else is holding a brief reference
+	 * to the worker. Wait for that to go away.
+	 */
+	set_current_state(TASK_INTERRUPTIBLE);
+	if (!refcount_dec_and_test(&worker->ref))
+		schedule();
+	__set_current_state(TASK_RUNNING);
+
+	preempt_disable();
+	current->flags &= ~PF_IO_WORKER;
+	if (worker->flags & IO_WORKER_F_RUNNING)
+		atomic_dec(&acct->nr_running);
+	if (!(worker->flags & IO_WORKER_F_BOUND))
+		atomic_dec(&wqe->wq->user->processes);
+	worker->flags = 0;
+	preempt_enable();
+
+	spin_lock_irq(&wqe->lock);
+	hlist_nulls_del_rcu(&worker->nulls_node);
+	list_del_rcu(&worker->all_list);
+	if (__io_worker_unuse(wqe, worker)) {
+		__release(&wqe->lock);
+		spin_lock_irq(&wqe->lock);
+	}
+	acct->nr_workers--;
+	nr_workers = wqe->acct[IO_WQ_ACCT_BOUND].nr_workers +
+			wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers;
+	spin_unlock_irq(&wqe->lock);
+
+	/* all workers gone, wq exit can proceed */
+	if (!nr_workers && refcount_dec_and_test(&wqe->wq->refs))
+		complete(&wqe->wq->done);
+
+	kfree_rcu(worker, rcu);
+}
+
+static inline bool io_wqe_run_queue(struct io_wqe *wqe)
+	__must_hold(wqe->lock)
+{
+	if (!list_empty(&wqe->work_list) && !(wqe->flags & IO_WQE_FLAG_STALLED))
+		return true;
+	return false;
+}
+
+/*
+ * Check head of free list for an available worker. If one isn't available,
+ * caller must wake up the wq manager to create one.
+ */
+static bool io_wqe_activate_free_worker(struct io_wqe *wqe)
+	__must_hold(RCU)
+{
+	struct hlist_nulls_node *n;
+	struct io_worker *worker;
+
+	n = rcu_dereference(hlist_nulls_first_rcu(&wqe->free_list));
+	if (is_a_nulls(n))
+		return false;
+
+	worker = hlist_nulls_entry(n, struct io_worker, nulls_node);
+	if (io_worker_get(worker)) {
+		wake_up(&worker->wait);
+		io_worker_release(worker);
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * We need a worker. If we find a free one, we're good. If not, and we're
+ * below the max number of workers, wake up the manager to create one.
+ */
+static void io_wqe_wake_worker(struct io_wqe *wqe, struct io_wqe_acct *acct)
+{
+	bool ret;
+
+	/*
+	 * Most likely an attempt to queue unbounded work on an io_wq that
+	 * wasn't setup with any unbounded workers.
+	 */
+	WARN_ON_ONCE(!acct->max_workers);
+
+	rcu_read_lock();
+	ret = io_wqe_activate_free_worker(wqe);
+	rcu_read_unlock();
+
+	if (!ret && acct->nr_workers < acct->max_workers)
+		wake_up_process(wqe->wq->manager);
+}
+
+static void io_wqe_inc_running(struct io_wqe *wqe, struct io_worker *worker)
+{
+	struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker);
+
+	atomic_inc(&acct->nr_running);
+}
+
+static void io_wqe_dec_running(struct io_wqe *wqe, struct io_worker *worker)
+	__must_hold(wqe->lock)
+{
+	struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker);
+
+	if (atomic_dec_and_test(&acct->nr_running) && io_wqe_run_queue(wqe))
+		io_wqe_wake_worker(wqe, acct);
+}
+
+static void io_worker_start(struct io_wqe *wqe, struct io_worker *worker)
+{
+	allow_kernel_signal(SIGINT);
+
+	current->flags |= PF_IO_WORKER;
+
+	worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);
+	worker->restore_files = current->files;
+	io_wqe_inc_running(wqe, worker);
+}
+
+/*
+ * Worker will start processing some work. Move it to the busy list, if
+ * it's currently on the freelist
+ */
+static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker,
+			     struct io_wq_work *work)
+	__must_hold(wqe->lock)
+{
+	bool worker_bound, work_bound;
+
+	if (worker->flags & IO_WORKER_F_FREE) {
+		worker->flags &= ~IO_WORKER_F_FREE;
+		hlist_nulls_del_init_rcu(&worker->nulls_node);
+		hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->busy_list);
+	}
+
+	/*
+	 * If worker is moving from bound to unbound (or vice versa), then
+	 * ensure we update the running accounting.
+	 */
+	 worker_bound = (worker->flags & IO_WORKER_F_BOUND) != 0;
+	 work_bound = (work->flags & IO_WQ_WORK_UNBOUND) == 0;
+	 if (worker_bound != work_bound) {
+		io_wqe_dec_running(wqe, worker);
+		if (work_bound) {
+			worker->flags |= IO_WORKER_F_BOUND;
+			wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers--;
+			wqe->acct[IO_WQ_ACCT_BOUND].nr_workers++;
+			atomic_dec(&wqe->wq->user->processes);
+		} else {
+			worker->flags &= ~IO_WORKER_F_BOUND;
+			wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers++;
+			wqe->acct[IO_WQ_ACCT_BOUND].nr_workers--;
+			atomic_inc(&wqe->wq->user->processes);
+		}
+		io_wqe_inc_running(wqe, worker);
+	 }
+}
+
+/*
+ * No work, worker going to sleep. Move to freelist, and unuse mm if we
+ * have one attached. Dropping the mm may potentially sleep, so we drop
+ * the lock in that case and return success. Since the caller has to
+ * retry the loop in that case (we changed task state), we don't regrab
+ * the lock if we return success.
+ */
+static bool __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker)
+	__must_hold(wqe->lock)
+{
+	if (!(worker->flags & IO_WORKER_F_FREE)) {
+		worker->flags |= IO_WORKER_F_FREE;
+		hlist_nulls_del_init_rcu(&worker->nulls_node);
+		hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list);
+	}
+
+	return __io_worker_unuse(wqe, worker);
+}
+
+static struct io_wq_work *io_get_next_work(struct io_wqe *wqe, unsigned *hash)
+	__must_hold(wqe->lock)
+{
+	struct io_wq_work *work;
+
+	list_for_each_entry(work, &wqe->work_list, list) {
+		/* not hashed, can run anytime */
+		if (!(work->flags & IO_WQ_WORK_HASHED)) {
+			list_del(&work->list);
+			return work;
+		}
+
+		/* hashed, can run if not already running */
+		*hash = work->flags >> IO_WQ_HASH_SHIFT;
+		if (!(wqe->hash_map & BIT_ULL(*hash))) {
+			wqe->hash_map |= BIT_ULL(*hash);
+			list_del(&work->list);
+			return work;
+		}
+	}
+
+	return NULL;
+}
+
+static void io_worker_handle_work(struct io_worker *worker)
+	__releases(wqe->lock)
+{
+	struct io_wq_work *work, *old_work = NULL, *put_work = NULL;
+	struct io_wqe *wqe = worker->wqe;
+	struct io_wq *wq = wqe->wq;
+
+	do {
+		unsigned hash = -1U;
+
+		/*
+		 * If we got some work, mark us as busy. If we didn't, but
+		 * the list isn't empty, it means we stalled on hashed work.
+		 * Mark us stalled so we don't keep looking for work when we
+		 * can't make progress, any work completion or insertion will
+		 * clear the stalled flag.
+		 */
+		work = io_get_next_work(wqe, &hash);
+		if (work)
+			__io_worker_busy(wqe, worker, work);
+		else if (!list_empty(&wqe->work_list))
+			wqe->flags |= IO_WQE_FLAG_STALLED;
+
+		spin_unlock_irq(&wqe->lock);
+		if (put_work && wq->put_work)
+			wq->put_work(old_work);
+		if (!work)
+			break;
+next:
+		/* flush any pending signals before assigning new work */
+		if (signal_pending(current))
+			flush_signals(current);
+
+		spin_lock_irq(&worker->lock);
+		worker->cur_work = work;
+		spin_unlock_irq(&worker->lock);
+
+		if ((work->flags & IO_WQ_WORK_NEEDS_FILES) &&
+		    current->files != work->files) {
+			task_lock(current);
+			current->files = work->files;
+			task_unlock(current);
+		}
+		if ((work->flags & IO_WQ_WORK_NEEDS_USER) && !worker->mm &&
+		    wq->mm && mmget_not_zero(wq->mm)) {
+			use_mm(wq->mm);
+			set_fs(USER_DS);
+			worker->mm = wq->mm;
+		}
+		if (test_bit(IO_WQ_BIT_CANCEL, &wq->state))
+			work->flags |= IO_WQ_WORK_CANCEL;
+		if (worker->mm)
+			work->flags |= IO_WQ_WORK_HAS_MM;
+
+		if (wq->get_work && !(work->flags & IO_WQ_WORK_INTERNAL)) {
+			put_work = work;
+			wq->get_work(work);
+		}
+
+		old_work = work;
+		work->func(&work);
+
+		spin_lock_irq(&worker->lock);
+		worker->cur_work = NULL;
+		spin_unlock_irq(&worker->lock);
+
+		spin_lock_irq(&wqe->lock);
+
+		if (hash != -1U) {
+			wqe->hash_map &= ~BIT_ULL(hash);
+			wqe->flags &= ~IO_WQE_FLAG_STALLED;
+		}
+		if (work && work != old_work) {
+			spin_unlock_irq(&wqe->lock);
+
+			if (put_work && wq->put_work) {
+				wq->put_work(put_work);
+				put_work = NULL;
+			}
+
+			/* dependent work not hashed */
+			hash = -1U;
+			goto next;
+		}
+	} while (1);
+}
+
+static int io_wqe_worker(void *data)
+{
+	struct io_worker *worker = data;
+	struct io_wqe *wqe = worker->wqe;
+	struct io_wq *wq = wqe->wq;
+	DEFINE_WAIT(wait);
+
+	io_worker_start(wqe, worker);
+
+	while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
+		prepare_to_wait(&worker->wait, &wait, TASK_INTERRUPTIBLE);
+
+		spin_lock_irq(&wqe->lock);
+		if (io_wqe_run_queue(wqe)) {
+			__set_current_state(TASK_RUNNING);
+			io_worker_handle_work(worker);
+			continue;
+		}
+		/* drops the lock on success, retry */
+		if (__io_worker_idle(wqe, worker)) {
+			__release(&wqe->lock);
+			continue;
+		}
+		spin_unlock_irq(&wqe->lock);
+		if (signal_pending(current))
+			flush_signals(current);
+		if (schedule_timeout(WORKER_IDLE_TIMEOUT))
+			continue;
+		/* timed out, exit unless we're the fixed worker */
+		if (test_bit(IO_WQ_BIT_EXIT, &wq->state) ||
+		    !(worker->flags & IO_WORKER_F_FIXED))
+			break;
+	}
+
+	finish_wait(&worker->wait, &wait);
+
+	if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
+		spin_lock_irq(&wqe->lock);
+		if (!list_empty(&wqe->work_list))
+			io_worker_handle_work(worker);
+		else
+			spin_unlock_irq(&wqe->lock);
+	}
+
+	io_worker_exit(worker);
+	return 0;
+}
+
+/*
+ * Called when a worker is scheduled in. Mark us as currently running.
+ */
+void io_wq_worker_running(struct task_struct *tsk)
+{
+	struct io_worker *worker = kthread_data(tsk);
+	struct io_wqe *wqe = worker->wqe;
+
+	if (!(worker->flags & IO_WORKER_F_UP))
+		return;
+	if (worker->flags & IO_WORKER_F_RUNNING)
+		return;
+	worker->flags |= IO_WORKER_F_RUNNING;
+	io_wqe_inc_running(wqe, worker);
+}
+
+/*
+ * Called when worker is going to sleep. If there are no workers currently
+ * running and we have work pending, wake up a free one or have the manager
+ * set one up.
+ */
+void io_wq_worker_sleeping(struct task_struct *tsk)
+{
+	struct io_worker *worker = kthread_data(tsk);
+	struct io_wqe *wqe = worker->wqe;
+
+	if (!(worker->flags & IO_WORKER_F_UP))
+		return;
+	if (!(worker->flags & IO_WORKER_F_RUNNING))
+		return;
+
+	worker->flags &= ~IO_WORKER_F_RUNNING;
+
+	spin_lock_irq(&wqe->lock);
+	io_wqe_dec_running(wqe, worker);
+	spin_unlock_irq(&wqe->lock);
+}
+
+static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
+{
+	struct io_wqe_acct *acct =&wqe->acct[index];
+	struct io_worker *worker;
+
+	worker = kcalloc_node(1, sizeof(*worker), GFP_KERNEL, wqe->node);
+	if (!worker)
+		return;
+
+	refcount_set(&worker->ref, 1);
+	worker->nulls_node.pprev = NULL;
+	init_waitqueue_head(&worker->wait);
+	worker->wqe = wqe;
+	spin_lock_init(&worker->lock);
+
+	worker->task = kthread_create_on_node(io_wqe_worker, worker, wqe->node,
+				"io_wqe_worker-%d/%d", index, wqe->node);
+	if (IS_ERR(worker->task)) {
+		kfree(worker);
+		return;
+	}
+
+	spin_lock_irq(&wqe->lock);
+	hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list);
+	list_add_tail_rcu(&worker->all_list, &wqe->all_list);
+	worker->flags |= IO_WORKER_F_FREE;
+	if (index == IO_WQ_ACCT_BOUND)
+		worker->flags |= IO_WORKER_F_BOUND;
+	if (!acct->nr_workers && (worker->flags & IO_WORKER_F_BOUND))
+		worker->flags |= IO_WORKER_F_FIXED;
+	acct->nr_workers++;
+	spin_unlock_irq(&wqe->lock);
+
+	if (index == IO_WQ_ACCT_UNBOUND)
+		atomic_inc(&wq->user->processes);
+
+	wake_up_process(worker->task);
+}
+
+static inline bool io_wqe_need_worker(struct io_wqe *wqe, int index)
+	__must_hold(wqe->lock)
+{
+	struct io_wqe_acct *acct = &wqe->acct[index];
+
+	/* always ensure we have one bounded worker */
+	if (index == IO_WQ_ACCT_BOUND && !acct->nr_workers)
+		return true;
+	/* if we have available workers or no work, no need */
+	if (!hlist_nulls_empty(&wqe->free_list) || !io_wqe_run_queue(wqe))
+		return false;
+	return acct->nr_workers < acct->max_workers;
+}
+
+/*
+ * Manager thread. Tasked with creating new workers, if we need them.
+ */
+static int io_wq_manager(void *data)
+{
+	struct io_wq *wq = data;
+
+	while (!kthread_should_stop()) {
+		int i;
+
+		for (i = 0; i < wq->nr_wqes; i++) {
+			struct io_wqe *wqe = wq->wqes[i];
+			bool fork_worker[2] = { false, false };
+
+			spin_lock_irq(&wqe->lock);
+			if (io_wqe_need_worker(wqe, IO_WQ_ACCT_BOUND))
+				fork_worker[IO_WQ_ACCT_BOUND] = true;
+			if (io_wqe_need_worker(wqe, IO_WQ_ACCT_UNBOUND))
+				fork_worker[IO_WQ_ACCT_UNBOUND] = true;
+			spin_unlock_irq(&wqe->lock);
+			if (fork_worker[IO_WQ_ACCT_BOUND])
+				create_io_worker(wq, wqe, IO_WQ_ACCT_BOUND);
+			if (fork_worker[IO_WQ_ACCT_UNBOUND])
+				create_io_worker(wq, wqe, IO_WQ_ACCT_UNBOUND);
+		}
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule_timeout(HZ);
+	}
+
+	return 0;
+}
+
+static bool io_wq_can_queue(struct io_wqe *wqe, struct io_wqe_acct *acct,
+			    struct io_wq_work *work)
+{
+	bool free_worker;
+
+	if (!(work->flags & IO_WQ_WORK_UNBOUND))
+		return true;
+	if (atomic_read(&acct->nr_running))
+		return true;
+
+	rcu_read_lock();
+	free_worker = !hlist_nulls_empty(&wqe->free_list);
+	rcu_read_unlock();
+	if (free_worker)
+		return true;
+
+	if (atomic_read(&wqe->wq->user->processes) >= acct->max_workers &&
+	    !(capable(CAP_SYS_RESOURCE) || capable(CAP_SYS_ADMIN)))
+		return false;
+
+	return true;
+}
+
+static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
+{
+	struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
+	unsigned long flags;
+
+	/*
+	 * Do early check to see if we need a new unbound worker, and if we do,
+	 * if we're allowed to do so. This isn't 100% accurate as there's a
+	 * gap between this check and incrementing the value, but that's OK.
+	 * It's close enough to not be an issue, fork() has the same delay.
+	 */
+	if (unlikely(!io_wq_can_queue(wqe, acct, work))) {
+		work->flags |= IO_WQ_WORK_CANCEL;
+		work->func(&work);
+		return;
+	}
+
+	spin_lock_irqsave(&wqe->lock, flags);
+	list_add_tail(&work->list, &wqe->work_list);
+	wqe->flags &= ~IO_WQE_FLAG_STALLED;
+	spin_unlock_irqrestore(&wqe->lock, flags);
+
+	if (!atomic_read(&acct->nr_running))
+		io_wqe_wake_worker(wqe, acct);
+}
+
+void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work)
+{
+	struct io_wqe *wqe = wq->wqes[numa_node_id()];
+
+	io_wqe_enqueue(wqe, work);
+}
+
+/*
+ * Enqueue work, hashed by some key. Work items that hash to the same value
+ * will not be done in parallel. Used to limit concurrent writes, generally
+ * hashed by inode.
+ */
+void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val)
+{
+	struct io_wqe *wqe = wq->wqes[numa_node_id()];
+	unsigned bit;
+
+
+	bit = hash_ptr(val, IO_WQ_HASH_ORDER);
+	work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT));
+	io_wqe_enqueue(wqe, work);
+}
+
+static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data)
+{
+	send_sig(SIGINT, worker->task, 1);
+	return false;
+}
+
+/*
+ * Iterate the passed in list and call the specific function for each
+ * worker that isn't exiting
+ */
+static bool io_wq_for_each_worker(struct io_wqe *wqe,
+				  bool (*func)(struct io_worker *, void *),
+				  void *data)
+{
+	struct io_worker *worker;
+	bool ret = false;
+
+	list_for_each_entry_rcu(worker, &wqe->all_list, all_list) {
+		if (io_worker_get(worker)) {
+			ret = func(worker, data);
+			io_worker_release(worker);
+			if (ret)
+				break;
+		}
+	}
+
+	return ret;
+}
+
+void io_wq_cancel_all(struct io_wq *wq)
+{
+	int i;
+
+	set_bit(IO_WQ_BIT_CANCEL, &wq->state);
+
+	/*
+	 * Browse both lists, as there's a gap between handing work off
+	 * to a worker and the worker putting itself on the busy_list
+	 */
+	rcu_read_lock();
+	for (i = 0; i < wq->nr_wqes; i++) {
+		struct io_wqe *wqe = wq->wqes[i];
+
+		io_wq_for_each_worker(wqe, io_wqe_worker_send_sig, NULL);
+	}
+	rcu_read_unlock();
+}
+
+struct io_cb_cancel_data {
+	struct io_wqe *wqe;
+	work_cancel_fn *cancel;
+	void *caller_data;
+};
+
+static bool io_work_cancel(struct io_worker *worker, void *cancel_data)
+{
+	struct io_cb_cancel_data *data = cancel_data;
+	unsigned long flags;
+	bool ret = false;
+
+	/*
+	 * Hold the lock to avoid ->cur_work going out of scope, caller
+	 * may dereference the passed in work.
+	 */
+	spin_lock_irqsave(&worker->lock, flags);
+	if (worker->cur_work &&
+	    data->cancel(worker->cur_work, data->caller_data)) {
+		send_sig(SIGINT, worker->task, 1);
+		ret = true;
+	}
+	spin_unlock_irqrestore(&worker->lock, flags);
+
+	return ret;
+}
+
+static enum io_wq_cancel io_wqe_cancel_cb_work(struct io_wqe *wqe,
+					       work_cancel_fn *cancel,
+					       void *cancel_data)
+{
+	struct io_cb_cancel_data data = {
+		.wqe = wqe,
+		.cancel = cancel,
+		.caller_data = cancel_data,
+	};
+	struct io_wq_work *work;
+	unsigned long flags;
+	bool found = false;
+
+	spin_lock_irqsave(&wqe->lock, flags);
+	list_for_each_entry(work, &wqe->work_list, list) {
+		if (cancel(work, cancel_data)) {
+			list_del(&work->list);
+			found = true;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&wqe->lock, flags);
+
+	if (found) {
+		work->flags |= IO_WQ_WORK_CANCEL;
+		work->func(&work);
+		return IO_WQ_CANCEL_OK;
+	}
+
+	rcu_read_lock();
+	found = io_wq_for_each_worker(wqe, io_work_cancel, &data);
+	rcu_read_unlock();
+	return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND;
+}
+
+enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
+				  void *data)
+{
+	enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
+	int i;
+
+	for (i = 0; i < wq->nr_wqes; i++) {
+		struct io_wqe *wqe = wq->wqes[i];
+
+		ret = io_wqe_cancel_cb_work(wqe, cancel, data);
+		if (ret != IO_WQ_CANCEL_NOTFOUND)
+			break;
+	}
+
+	return ret;
+}
+
+static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
+{
+	struct io_wq_work *work = data;
+	unsigned long flags;
+	bool ret = false;
+
+	if (worker->cur_work != work)
+		return false;
+
+	spin_lock_irqsave(&worker->lock, flags);
+	if (worker->cur_work == work) {
+		send_sig(SIGINT, worker->task, 1);
+		ret = true;
+	}
+	spin_unlock_irqrestore(&worker->lock, flags);
+
+	return ret;
+}
+
+static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe,
+					    struct io_wq_work *cwork)
+{
+	struct io_wq_work *work;
+	unsigned long flags;
+	bool found = false;
+
+	cwork->flags |= IO_WQ_WORK_CANCEL;
+
+	/*
+	 * First check pending list, if we're lucky we can just remove it
+	 * from there. CANCEL_OK means that the work is returned as-new,
+	 * no completion will be posted for it.
+	 */
+	spin_lock_irqsave(&wqe->lock, flags);
+	list_for_each_entry(work, &wqe->work_list, list) {
+		if (work == cwork) {
+			list_del(&work->list);
+			found = true;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&wqe->lock, flags);
+
+	if (found) {
+		work->flags |= IO_WQ_WORK_CANCEL;
+		work->func(&work);
+		return IO_WQ_CANCEL_OK;
+	}
+
+	/*
+	 * Now check if a free (going busy) or busy worker has the work
+	 * currently running. If we find it there, we'll return CANCEL_RUNNING
+	 * as an indication that we attempte to signal cancellation. The
+	 * completion will run normally in this case.
+	 */
+	rcu_read_lock();
+	found = io_wq_for_each_worker(wqe, io_wq_worker_cancel, cwork);
+	rcu_read_unlock();
+	return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND;
+}
+
+enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork)
+{
+	enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
+	int i;
+
+	for (i = 0; i < wq->nr_wqes; i++) {
+		struct io_wqe *wqe = wq->wqes[i];
+
+		ret = io_wqe_cancel_work(wqe, cwork);
+		if (ret != IO_WQ_CANCEL_NOTFOUND)
+			break;
+	}
+
+	return ret;
+}
+
+struct io_wq_flush_data {
+	struct io_wq_work work;
+	struct completion done;
+};
+
+static void io_wq_flush_func(struct io_wq_work **workptr)
+{
+	struct io_wq_work *work = *workptr;
+	struct io_wq_flush_data *data;
+
+	data = container_of(work, struct io_wq_flush_data, work);
+	complete(&data->done);
+}
+
+/*
+ * Doesn't wait for previously queued work to finish. When this completes,
+ * it just means that previously queued work was started.
+ */
+void io_wq_flush(struct io_wq *wq)
+{
+	struct io_wq_flush_data data;
+	int i;
+
+	for (i = 0; i < wq->nr_wqes; i++) {
+		struct io_wqe *wqe = wq->wqes[i];
+
+		init_completion(&data.done);
+		INIT_IO_WORK(&data.work, io_wq_flush_func);
+		data.work.flags |= IO_WQ_WORK_INTERNAL;
+		io_wqe_enqueue(wqe, &data.work);
+		wait_for_completion(&data.done);
+	}
+}
+
+struct io_wq *io_wq_create(unsigned bounded, struct mm_struct *mm,
+			   struct user_struct *user, get_work_fn *get_work,
+			   put_work_fn *put_work)
+{
+	int ret = -ENOMEM, i, node;
+	struct io_wq *wq;
+
+	wq = kcalloc(1, sizeof(*wq), GFP_KERNEL);
+	if (!wq)
+		return ERR_PTR(-ENOMEM);
+
+	wq->nr_wqes = num_online_nodes();
+	wq->wqes = kcalloc(wq->nr_wqes, sizeof(struct io_wqe *), GFP_KERNEL);
+	if (!wq->wqes) {
+		kfree(wq);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	wq->get_work = get_work;
+	wq->put_work = put_work;
+
+	/* caller must already hold a reference to this */
+	wq->user = user;
+
+	i = 0;
+	refcount_set(&wq->refs, wq->nr_wqes);
+	for_each_online_node(node) {
+		struct io_wqe *wqe;
+
+		wqe = kcalloc_node(1, sizeof(struct io_wqe), GFP_KERNEL, node);
+		if (!wqe)
+			break;
+		wq->wqes[i] = wqe;
+		wqe->node = node;
+		wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded;
+		atomic_set(&wqe->acct[IO_WQ_ACCT_BOUND].nr_running, 0);
+		if (user) {
+			wqe->acct[IO_WQ_ACCT_UNBOUND].max_workers =
+					task_rlimit(current, RLIMIT_NPROC);
+		}
+		atomic_set(&wqe->acct[IO_WQ_ACCT_UNBOUND].nr_running, 0);
+		wqe->node = node;
+		wqe->wq = wq;
+		spin_lock_init(&wqe->lock);
+		INIT_LIST_HEAD(&wqe->work_list);
+		INIT_HLIST_NULLS_HEAD(&wqe->free_list, 0);
+		INIT_HLIST_NULLS_HEAD(&wqe->busy_list, 1);
+		INIT_LIST_HEAD(&wqe->all_list);
+
+		i++;
+	}
+
+	init_completion(&wq->done);
+
+	if (i != wq->nr_wqes)
+		goto err;
+
+	/* caller must have already done mmgrab() on this mm */
+	wq->mm = mm;
+
+	wq->manager = kthread_create(io_wq_manager, wq, "io_wq_manager");
+	if (!IS_ERR(wq->manager)) {
+		wake_up_process(wq->manager);
+		return wq;
+	}
+
+	ret = PTR_ERR(wq->manager);
+	wq->manager = NULL;
+err:
+	complete(&wq->done);
+	io_wq_destroy(wq);
+	return ERR_PTR(ret);
+}
+
+static bool io_wq_worker_wake(struct io_worker *worker, void *data)
+{
+	wake_up_process(worker->task);
+	return false;
+}
+
+void io_wq_destroy(struct io_wq *wq)
+{
+	int i;
+
+	if (wq->manager) {
+		set_bit(IO_WQ_BIT_EXIT, &wq->state);
+		kthread_stop(wq->manager);
+	}
+
+	rcu_read_lock();
+	for (i = 0; i < wq->nr_wqes; i++) {
+		struct io_wqe *wqe = wq->wqes[i];
+
+		if (!wqe)
+			continue;
+		io_wq_for_each_worker(wqe, io_wq_worker_wake, NULL);
+	}
+	rcu_read_unlock();
+
+	wait_for_completion(&wq->done);
+
+	for (i = 0; i < wq->nr_wqes; i++)
+		kfree(wq->wqes[i]);
+	kfree(wq->wqes);
+	kfree(wq);
+}
diff --git a/fs/io-wq.h b/fs/io-wq.h
new file mode 100644
index 000000000000..4b29f922f80c
--- /dev/null
+++ b/fs/io-wq.h
@@ -0,0 +1,74 @@
+#ifndef INTERNAL_IO_WQ_H
+#define INTERNAL_IO_WQ_H
+
+struct io_wq;
+
+enum {
+	IO_WQ_WORK_CANCEL	= 1,
+	IO_WQ_WORK_HAS_MM	= 2,
+	IO_WQ_WORK_HASHED	= 4,
+	IO_WQ_WORK_NEEDS_USER	= 8,
+	IO_WQ_WORK_NEEDS_FILES	= 16,
+	IO_WQ_WORK_UNBOUND	= 32,
+	IO_WQ_WORK_INTERNAL	= 64,
+
+	IO_WQ_HASH_SHIFT	= 24,	/* upper 8 bits are used for hash key */
+};
+
+enum io_wq_cancel {
+	IO_WQ_CANCEL_OK,	/* cancelled before started */
+	IO_WQ_CANCEL_RUNNING,	/* found, running, and attempted cancelled */
+	IO_WQ_CANCEL_NOTFOUND,	/* work not found */
+};
+
+struct io_wq_work {
+	struct list_head list;
+	void (*func)(struct io_wq_work **);
+	unsigned flags;
+	struct files_struct *files;
+};
+
+#define INIT_IO_WORK(work, _func)			\
+	do {						\
+		(work)->func = _func;			\
+		(work)->flags = 0;			\
+		(work)->files = NULL;			\
+	} while (0)					\
+
+typedef void (get_work_fn)(struct io_wq_work *);
+typedef void (put_work_fn)(struct io_wq_work *);
+
+struct io_wq *io_wq_create(unsigned bounded, struct mm_struct *mm,
+				struct user_struct *user,
+				get_work_fn *get_work, put_work_fn *put_work);
+void io_wq_destroy(struct io_wq *wq);
+
+void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);
+void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val);
+void io_wq_flush(struct io_wq *wq);
+
+void io_wq_cancel_all(struct io_wq *wq);
+enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork);
+
+typedef bool (work_cancel_fn)(struct io_wq_work *, void *);
+
+enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
+					void *data);
+
+#if defined(CONFIG_IO_WQ)
+extern void io_wq_worker_sleeping(struct task_struct *);
+extern void io_wq_worker_running(struct task_struct *);
+#else
+static inline void io_wq_worker_sleeping(struct task_struct *tsk)
+{
+}
+static inline void io_wq_worker_running(struct task_struct *tsk)
+{
+}
+#endif
+
+static inline bool io_wq_current_is_worker(void)
+{
+	return in_task() && (current->flags & PF_IO_WORKER);
+}
+#endif
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 2c819c3c855d..4c030a92de79 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -56,7 +56,6 @@
 #include <linux/mmu_context.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
-#include <linux/workqueue.h>
 #include <linux/kthread.h>
 #include <linux/blkdev.h>
 #include <linux/bvec.h>
@@ -71,12 +70,24 @@
 #include <linux/sizes.h>
 #include <linux/hugetlb.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/io_uring.h>
+
 #include <uapi/linux/io_uring.h>
 
 #include "internal.h"
+#include "io-wq.h"
 
 #define IORING_MAX_ENTRIES	32768
-#define IORING_MAX_FIXED_FILES	1024
+#define IORING_MAX_CQ_ENTRIES	(2 * IORING_MAX_ENTRIES)
+
+/*
+ * Shift of 9 is 512 entries, or exactly one page on 64-bit archs
+ */
+#define IORING_FILE_TABLE_SHIFT	9
+#define IORING_MAX_FILES_TABLE	(1U << IORING_FILE_TABLE_SHIFT)
+#define IORING_FILE_TABLE_MASK	(IORING_MAX_FILES_TABLE - 1)
+#define IORING_MAX_FIXED_FILES	(64 * IORING_MAX_FILES_TABLE)
 
 struct io_uring {
 	u32 head ____cacheline_aligned_in_smp;
@@ -161,14 +172,8 @@ struct io_mapped_ubuf {
 	unsigned int	nr_bvecs;
 };
 
-struct async_list {
-	spinlock_t		lock;
-	atomic_t		cnt;
-	struct list_head	list;
-
-	struct file		*file;
-	off_t			io_start;
-	size_t			io_len;
+struct fixed_file_table {
+	struct file		**files;
 };
 
 struct io_ring_ctx {
@@ -180,6 +185,7 @@ struct io_ring_ctx {
 		unsigned int		flags;
 		bool			compat;
 		bool			account_mem;
+		bool			cq_overflow_flushed;
 
 		/*
 		 * Ring buffer of indices into array of io_uring_sqe, which is
@@ -198,38 +204,30 @@ struct io_ring_ctx {
 		unsigned		sq_mask;
 		unsigned		sq_thread_idle;
 		unsigned		cached_sq_dropped;
+		atomic_t		cached_cq_overflow;
 		struct io_uring_sqe	*sq_sqes;
 
 		struct list_head	defer_list;
 		struct list_head	timeout_list;
+		struct list_head	cq_overflow_list;
+
+		wait_queue_head_t	inflight_wait;
 	} ____cacheline_aligned_in_smp;
 
+	struct io_rings	*rings;
+
 	/* IO offload */
-	struct workqueue_struct	*sqo_wq[2];
+	struct io_wq		*io_wq;
 	struct task_struct	*sqo_thread;	/* if using sq thread polling */
 	struct mm_struct	*sqo_mm;
 	wait_queue_head_t	sqo_wait;
-	struct completion	sqo_thread_started;
-
-	struct {
-		unsigned		cached_cq_tail;
-		atomic_t		cached_cq_overflow;
-		unsigned		cq_entries;
-		unsigned		cq_mask;
-		struct wait_queue_head	cq_wait;
-		struct fasync_struct	*cq_fasync;
-		struct eventfd_ctx	*cq_ev_fd;
-		atomic_t		cq_timeouts;
-	} ____cacheline_aligned_in_smp;
-
-	struct io_rings	*rings;
 
 	/*
 	 * If used, fixed file set. Writers must ensure that ->refs is dead,
 	 * readers must ensure that ->refs is alive as long as the file* is
 	 * used. Only updated through io_uring_register(2).
 	 */
-	struct file		**user_files;
+	struct fixed_file_table	*file_table;
 	unsigned		nr_user_files;
 
 	/* if used, fixed mapped user buffers */
@@ -238,7 +236,25 @@ struct io_ring_ctx {
 
 	struct user_struct	*user;
 
-	struct completion	ctx_done;
+	/* 0 is for ctx quiesce/reinit/free, 1 is for sqo_thread started */
+	struct completion	*completions;
+
+	/* if all else fails... */
+	struct io_kiocb		*fallback_req;
+
+#if defined(CONFIG_UNIX)
+	struct socket		*ring_sock;
+#endif
+
+	struct {
+		unsigned		cached_cq_tail;
+		unsigned		cq_entries;
+		unsigned		cq_mask;
+		atomic_t		cq_timeouts;
+		struct wait_queue_head	cq_wait;
+		struct fasync_struct	*cq_fasync;
+		struct eventfd_ctx	*cq_ev_fd;
+	} ____cacheline_aligned_in_smp;
 
 	struct {
 		struct mutex		uring_lock;
@@ -255,22 +271,20 @@ struct io_ring_ctx {
 		 * manipulate the list, hence no extra locking is needed there.
 		 */
 		struct list_head	poll_list;
-		struct list_head	cancel_list;
-	} ____cacheline_aligned_in_smp;
+		struct rb_root		cancel_tree;
 
-	struct async_list	pending_async[2];
-
-#if defined(CONFIG_UNIX)
-	struct socket		*ring_sock;
-#endif
+		spinlock_t		inflight_lock;
+		struct list_head	inflight_list;
+	} ____cacheline_aligned_in_smp;
 };
 
 struct sqe_submit {
 	const struct io_uring_sqe	*sqe;
-	unsigned short			index;
+	struct file			*ring_file;
+	int				ring_fd;
 	u32				sequence;
 	bool				has_user;
-	bool				needs_lock;
+	bool				in_async;
 	bool				needs_fixed_file;
 };
 
@@ -309,7 +323,10 @@ struct io_kiocb {
 	struct sqe_submit	submit;
 
 	struct io_ring_ctx	*ctx;
-	struct list_head	list;
+	union {
+		struct list_head	list;
+		struct rb_node		rb_node;
+	};
 	struct list_head	link_list;
 	unsigned int		flags;
 	refcount_t		refs;
@@ -320,18 +337,22 @@ struct io_kiocb {
 #define REQ_F_IO_DRAIN		16	/* drain existing IO first */
 #define REQ_F_IO_DRAINED	32	/* drain done */
 #define REQ_F_LINK		64	/* linked sqes */
-#define REQ_F_LINK_DONE		128	/* linked sqes done */
+#define REQ_F_LINK_TIMEOUT	128	/* has linked timeout */
 #define REQ_F_FAIL_LINK		256	/* fail rest of links */
 #define REQ_F_SHADOW_DRAIN	512	/* link-drain shadow req */
 #define REQ_F_TIMEOUT		1024	/* timeout request */
 #define REQ_F_ISREG		2048	/* regular file */
 #define REQ_F_MUST_PUNT		4096	/* must be punted even for NONBLOCK */
 #define REQ_F_TIMEOUT_NOSEQ	8192	/* no timeout sequence */
+#define REQ_F_INFLIGHT		16384	/* on inflight list */
+#define REQ_F_COMP_LOCKED	32768	/* completion under lock */
 	u64			user_data;
 	u32			result;
 	u32			sequence;
 
-	struct work_struct	work;
+	struct list_head	inflight_entry;
+
+	struct io_wq_work	work;
 };
 
 #define IO_PLUG_THRESHOLD		2
@@ -357,10 +378,11 @@ struct io_submit_state {
 	unsigned int		ios_left;
 };
 
-static void io_sq_wq_submit_work(struct work_struct *work);
-static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data,
-				 long res);
+static void io_wq_submit_work(struct io_wq_work **workptr);
+static void io_cqring_fill_event(struct io_kiocb *req, long res);
 static void __io_free_req(struct io_kiocb *req);
+static void io_put_req(struct io_kiocb *req);
+static void io_double_put_req(struct io_kiocb *req);
 
 static struct kmem_cache *req_cachep;
 
@@ -383,57 +405,67 @@ static void io_ring_ctx_ref_free(struct percpu_ref *ref)
 {
 	struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs);
 
-	complete(&ctx->ctx_done);
+	complete(&ctx->completions[0]);
 }
 
 static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 {
 	struct io_ring_ctx *ctx;
-	int i;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return NULL;
 
+	ctx->fallback_req = kmem_cache_alloc(req_cachep, GFP_KERNEL);
+	if (!ctx->fallback_req)
+		goto err;
+
+	ctx->completions = kmalloc(2 * sizeof(struct completion), GFP_KERNEL);
+	if (!ctx->completions)
+		goto err;
+
 	if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free,
-			    PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) {
-		kfree(ctx);
-		return NULL;
-	}
+			    PERCPU_REF_ALLOW_REINIT, GFP_KERNEL))
+		goto err;
 
 	ctx->flags = p->flags;
 	init_waitqueue_head(&ctx->cq_wait);
-	init_completion(&ctx->ctx_done);
-	init_completion(&ctx->sqo_thread_started);
+	INIT_LIST_HEAD(&ctx->cq_overflow_list);
+	init_completion(&ctx->completions[0]);
+	init_completion(&ctx->completions[1]);
 	mutex_init(&ctx->uring_lock);
 	init_waitqueue_head(&ctx->wait);
-	for (i = 0; i < ARRAY_SIZE(ctx->pending_async); i++) {
-		spin_lock_init(&ctx->pending_async[i].lock);
-		INIT_LIST_HEAD(&ctx->pending_async[i].list);
-		atomic_set(&ctx->pending_async[i].cnt, 0);
-	}
 	spin_lock_init(&ctx->completion_lock);
 	INIT_LIST_HEAD(&ctx->poll_list);
-	INIT_LIST_HEAD(&ctx->cancel_list);
+	ctx->cancel_tree = RB_ROOT;
 	INIT_LIST_HEAD(&ctx->defer_list);
 	INIT_LIST_HEAD(&ctx->timeout_list);
+	init_waitqueue_head(&ctx->inflight_wait);
+	spin_lock_init(&ctx->inflight_lock);
+	INIT_LIST_HEAD(&ctx->inflight_list);
 	return ctx;
+err:
+	if (ctx->fallback_req)
+		kmem_cache_free(req_cachep, ctx->fallback_req);
+	kfree(ctx->completions);
+	kfree(ctx);
+	return NULL;
 }
 
-static inline bool __io_sequence_defer(struct io_ring_ctx *ctx,
-				       struct io_kiocb *req)
+static inline bool __req_need_defer(struct io_kiocb *req)
 {
+	struct io_ring_ctx *ctx = req->ctx;
+
 	return req->sequence != ctx->cached_cq_tail + ctx->cached_sq_dropped
 					+ atomic_read(&ctx->cached_cq_overflow);
 }
 
-static inline bool io_sequence_defer(struct io_ring_ctx *ctx,
-				     struct io_kiocb *req)
+static inline bool req_need_defer(struct io_kiocb *req)
 {
-	if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN)
-		return false;
+	if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) == REQ_F_IO_DRAIN)
+		return __req_need_defer(req);
 
-	return __io_sequence_defer(ctx, req);
+	return false;
 }
 
 static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx)
@@ -441,7 +473,7 @@ static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx)
 	struct io_kiocb *req;
 
 	req = list_first_entry_or_null(&ctx->defer_list, struct io_kiocb, list);
-	if (req && !io_sequence_defer(ctx, req)) {
+	if (req && !req_need_defer(req)) {
 		list_del_init(&req->list);
 		return req;
 	}
@@ -457,7 +489,7 @@ static struct io_kiocb *io_get_timeout_req(struct io_ring_ctx *ctx)
 	if (req) {
 		if (req->flags & REQ_F_TIMEOUT_NOSEQ)
 			return NULL;
-		if (!__io_sequence_defer(ctx, req)) {
+		if (!__req_need_defer(req)) {
 			list_del_init(&req->list);
 			return req;
 		}
@@ -481,21 +513,59 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx)
 	}
 }
 
-static inline void io_queue_async_work(struct io_ring_ctx *ctx,
-				       struct io_kiocb *req)
+static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe)
 {
-	int rw = 0;
+	u8 opcode = READ_ONCE(sqe->opcode);
+
+	return !(opcode == IORING_OP_READ_FIXED ||
+		 opcode == IORING_OP_WRITE_FIXED);
+}
+
+static inline bool io_prep_async_work(struct io_kiocb *req)
+{
+	bool do_hashed = false;
 
 	if (req->submit.sqe) {
 		switch (req->submit.sqe->opcode) {
 		case IORING_OP_WRITEV:
 		case IORING_OP_WRITE_FIXED:
-			rw = !(req->rw.ki_flags & IOCB_DIRECT);
+			do_hashed = true;
+			/* fall-through */
+		case IORING_OP_READV:
+		case IORING_OP_READ_FIXED:
+		case IORING_OP_SENDMSG:
+		case IORING_OP_RECVMSG:
+		case IORING_OP_ACCEPT:
+		case IORING_OP_POLL_ADD:
+			/*
+			 * We know REQ_F_ISREG is not set on some of these
+			 * opcodes, but this enables us to keep the check in
+			 * just one place.
+			 */
+			if (!(req->flags & REQ_F_ISREG))
+				req->work.flags |= IO_WQ_WORK_UNBOUND;
 			break;
 		}
+		if (io_sqe_needs_user(req->submit.sqe))
+			req->work.flags |= IO_WQ_WORK_NEEDS_USER;
 	}
 
-	queue_work(ctx->sqo_wq[rw], &req->work);
+	return do_hashed;
+}
+
+static inline void io_queue_async_work(struct io_kiocb *req)
+{
+	bool do_hashed = io_prep_async_work(req);
+	struct io_ring_ctx *ctx = req->ctx;
+
+	trace_io_uring_queue_async_work(ctx, do_hashed, req, &req->work,
+					req->flags);
+	if (!do_hashed) {
+		io_wq_enqueue(ctx->io_wq, &req->work);
+	} else {
+		io_wq_enqueue_hashed(ctx->io_wq, &req->work,
+					file_inode(req->file));
+	}
 }
 
 static void io_kill_timeout(struct io_kiocb *req)
@@ -505,9 +575,9 @@ static void io_kill_timeout(struct io_kiocb *req)
 	ret = hrtimer_try_to_cancel(&req->timeout.timer);
 	if (ret != -1) {
 		atomic_inc(&req->ctx->cq_timeouts);
-		list_del(&req->list);
-		io_cqring_fill_event(req->ctx, req->user_data, 0);
-		__io_free_req(req);
+		list_del_init(&req->list);
+		io_cqring_fill_event(req, 0);
+		io_put_req(req);
 	}
 }
 
@@ -537,7 +607,7 @@ static void io_commit_cqring(struct io_ring_ctx *ctx)
 			continue;
 		}
 		req->flags |= REQ_F_IO_DRAINED;
-		io_queue_async_work(ctx, req);
+		io_queue_async_work(req);
 	}
 }
 
@@ -559,50 +629,124 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
 	return &rings->cqes[tail & ctx->cq_mask];
 }
 
-static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data,
-				 long res)
+static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
+{
+	if (waitqueue_active(&ctx->wait))
+		wake_up(&ctx->wait);
+	if (waitqueue_active(&ctx->sqo_wait))
+		wake_up(&ctx->sqo_wait);
+	if (ctx->cq_ev_fd)
+		eventfd_signal(ctx->cq_ev_fd, 1);
+}
+
+static void io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
+{
+	struct io_rings *rings = ctx->rings;
+	struct io_uring_cqe *cqe;
+	struct io_kiocb *req;
+	unsigned long flags;
+	LIST_HEAD(list);
+
+	if (!force) {
+		if (list_empty_careful(&ctx->cq_overflow_list))
+			return;
+		if ((ctx->cached_cq_tail - READ_ONCE(rings->cq.head) ==
+		    rings->cq_ring_entries))
+			return;
+	}
+
+	spin_lock_irqsave(&ctx->completion_lock, flags);
+
+	/* if force is set, the ring is going away. always drop after that */
+	if (force)
+		ctx->cq_overflow_flushed = true;
+
+	while (!list_empty(&ctx->cq_overflow_list)) {
+		cqe = io_get_cqring(ctx);
+		if (!cqe && !force)
+			break;
+
+		req = list_first_entry(&ctx->cq_overflow_list, struct io_kiocb,
+						list);
+		list_move(&req->list, &list);
+		if (cqe) {
+			WRITE_ONCE(cqe->user_data, req->user_data);
+			WRITE_ONCE(cqe->res, req->result);
+			WRITE_ONCE(cqe->flags, 0);
+		} else {
+			WRITE_ONCE(ctx->rings->cq_overflow,
+				atomic_inc_return(&ctx->cached_cq_overflow));
+		}
+	}
+
+	io_commit_cqring(ctx);
+	spin_unlock_irqrestore(&ctx->completion_lock, flags);
+	io_cqring_ev_posted(ctx);
+
+	while (!list_empty(&list)) {
+		req = list_first_entry(&list, struct io_kiocb, list);
+		list_del(&req->list);
+		io_put_req(req);
+	}
+}
+
+static void io_cqring_fill_event(struct io_kiocb *req, long res)
 {
+	struct io_ring_ctx *ctx = req->ctx;
 	struct io_uring_cqe *cqe;
 
+	trace_io_uring_complete(ctx, req->user_data, res);
+
 	/*
 	 * If we can't get a cq entry, userspace overflowed the
 	 * submission (by quite a lot). Increment the overflow count in
 	 * the ring.
 	 */
 	cqe = io_get_cqring(ctx);
-	if (cqe) {
-		WRITE_ONCE(cqe->user_data, ki_user_data);
+	if (likely(cqe)) {
+		WRITE_ONCE(cqe->user_data, req->user_data);
 		WRITE_ONCE(cqe->res, res);
 		WRITE_ONCE(cqe->flags, 0);
-	} else {
+	} else if (ctx->cq_overflow_flushed) {
 		WRITE_ONCE(ctx->rings->cq_overflow,
 				atomic_inc_return(&ctx->cached_cq_overflow));
+	} else {
+		refcount_inc(&req->refs);
+		req->result = res;
+		list_add_tail(&req->list, &ctx->cq_overflow_list);
 	}
 }
 
-static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
-{
-	if (waitqueue_active(&ctx->wait))
-		wake_up(&ctx->wait);
-	if (waitqueue_active(&ctx->sqo_wait))
-		wake_up(&ctx->sqo_wait);
-	if (ctx->cq_ev_fd)
-		eventfd_signal(ctx->cq_ev_fd, 1);
-}
-
-static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 user_data,
-				long res)
+static void io_cqring_add_event(struct io_kiocb *req, long res)
 {
+	struct io_ring_ctx *ctx = req->ctx;
 	unsigned long flags;
 
 	spin_lock_irqsave(&ctx->completion_lock, flags);
-	io_cqring_fill_event(ctx, user_data, res);
+	io_cqring_fill_event(req, res);
 	io_commit_cqring(ctx);
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 
 	io_cqring_ev_posted(ctx);
 }
 
+static inline bool io_is_fallback_req(struct io_kiocb *req)
+{
+	return req == (struct io_kiocb *)
+			((unsigned long) req->ctx->fallback_req & ~1UL);
+}
+
+static struct io_kiocb *io_get_fallback_req(struct io_ring_ctx *ctx)
+{
+	struct io_kiocb *req;
+
+	req = ctx->fallback_req;
+	if (!test_and_set_bit_lock(0, (unsigned long *) ctx->fallback_req))
+		return req;
+
+	return NULL;
+}
+
 static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
 				   struct io_submit_state *state)
 {
@@ -615,7 +759,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
 	if (!state) {
 		req = kmem_cache_alloc(req_cachep, gfp);
 		if (unlikely(!req))
-			goto out;
+			goto fallback;
 	} else if (!state->free_reqs) {
 		size_t sz;
 		int ret;
@@ -630,7 +774,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
 		if (unlikely(ret <= 0)) {
 			state->reqs[0] = kmem_cache_alloc(req_cachep, gfp);
 			if (!state->reqs[0])
-				goto out;
+				goto fallback;
 			ret = 1;
 		}
 		state->free_reqs = ret - 1;
@@ -642,14 +786,19 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
 		state->cur_req++;
 	}
 
+got_it:
 	req->file = NULL;
 	req->ctx = ctx;
 	req->flags = 0;
 	/* one is dropped after submission, the other at completion */
 	refcount_set(&req->refs, 2);
 	req->result = 0;
+	INIT_IO_WORK(&req->work, io_wq_submit_work);
 	return req;
-out:
+fallback:
+	req = io_get_fallback_req(ctx);
+	if (req)
+		goto got_it;
 	percpu_ref_put(&ctx->refs);
 	return NULL;
 }
@@ -665,15 +814,48 @@ static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr)
 
 static void __io_free_req(struct io_kiocb *req)
 {
+	struct io_ring_ctx *ctx = req->ctx;
+
 	if (req->file && !(req->flags & REQ_F_FIXED_FILE))
 		fput(req->file);
-	percpu_ref_put(&req->ctx->refs);
-	kmem_cache_free(req_cachep, req);
+	if (req->flags & REQ_F_INFLIGHT) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&ctx->inflight_lock, flags);
+		list_del(&req->inflight_entry);
+		if (waitqueue_active(&ctx->inflight_wait))
+			wake_up(&ctx->inflight_wait);
+		spin_unlock_irqrestore(&ctx->inflight_lock, flags);
+	}
+	percpu_ref_put(&ctx->refs);
+	if (likely(!io_is_fallback_req(req)))
+		kmem_cache_free(req_cachep, req);
+	else
+		clear_bit_unlock(0, (unsigned long *) ctx->fallback_req);
 }
 
-static void io_req_link_next(struct io_kiocb *req)
+static bool io_link_cancel_timeout(struct io_kiocb *req)
 {
+	struct io_ring_ctx *ctx = req->ctx;
+	int ret;
+
+	ret = hrtimer_try_to_cancel(&req->timeout.timer);
+	if (ret != -1) {
+		io_cqring_fill_event(req, -ECANCELED);
+		io_commit_cqring(ctx);
+		req->flags &= ~REQ_F_LINK;
+		io_put_req(req);
+		return true;
+	}
+
+	return false;
+}
+
+static void io_req_link_next(struct io_kiocb *req, struct io_kiocb **nxtptr)
+{
+	struct io_ring_ctx *ctx = req->ctx;
 	struct io_kiocb *nxt;
+	bool wake_ev = false;
 
 	/*
 	 * The list should never be empty when we are called here. But could
@@ -681,18 +863,35 @@ static void io_req_link_next(struct io_kiocb *req)
 	 * safe side.
 	 */
 	nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb, list);
-	if (nxt) {
-		list_del(&nxt->list);
+	while (nxt) {
+		list_del_init(&nxt->list);
 		if (!list_empty(&req->link_list)) {
 			INIT_LIST_HEAD(&nxt->link_list);
 			list_splice(&req->link_list, &nxt->link_list);
 			nxt->flags |= REQ_F_LINK;
 		}
 
-		nxt->flags |= REQ_F_LINK_DONE;
-		INIT_WORK(&nxt->work, io_sq_wq_submit_work);
-		io_queue_async_work(req->ctx, nxt);
+		/*
+		 * If we're in async work, we can continue processing the chain
+		 * in this context instead of having to queue up new async work.
+		 */
+		if (req->flags & REQ_F_LINK_TIMEOUT) {
+			wake_ev = io_link_cancel_timeout(nxt);
+
+			/* we dropped this link, get next */
+			nxt = list_first_entry_or_null(&req->link_list,
+							struct io_kiocb, list);
+		} else if (nxtptr && io_wq_current_is_worker()) {
+			*nxtptr = nxt;
+			break;
+		} else {
+			io_queue_async_work(nxt);
+			break;
+		}
 	}
+
+	if (wake_ev)
+		io_cqring_ev_posted(ctx);
 }
 
 /*
@@ -700,43 +899,118 @@ static void io_req_link_next(struct io_kiocb *req)
  */
 static void io_fail_links(struct io_kiocb *req)
 {
+	struct io_ring_ctx *ctx = req->ctx;
 	struct io_kiocb *link;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctx->completion_lock, flags);
 
 	while (!list_empty(&req->link_list)) {
 		link = list_first_entry(&req->link_list, struct io_kiocb, list);
-		list_del(&link->list);
+		list_del_init(&link->list);
 
-		io_cqring_add_event(req->ctx, link->user_data, -ECANCELED);
-		__io_free_req(link);
+		trace_io_uring_fail_link(req, link);
+
+		if ((req->flags & REQ_F_LINK_TIMEOUT) &&
+		    link->submit.sqe->opcode == IORING_OP_LINK_TIMEOUT) {
+			io_link_cancel_timeout(link);
+		} else {
+			io_cqring_fill_event(link, -ECANCELED);
+			io_double_put_req(link);
+		}
 	}
+
+	io_commit_cqring(ctx);
+	spin_unlock_irqrestore(&ctx->completion_lock, flags);
+	io_cqring_ev_posted(ctx);
 }
 
-static void io_free_req(struct io_kiocb *req)
+static void io_free_req_find_next(struct io_kiocb *req, struct io_kiocb **nxt)
 {
+	if (likely(!(req->flags & REQ_F_LINK))) {
+		__io_free_req(req);
+		return;
+	}
+
 	/*
 	 * If LINK is set, we have dependent requests in this chain. If we
 	 * didn't fail this request, queue the first one up, moving any other
 	 * dependencies to the next request. In case of failure, fail the rest
 	 * of the chain.
 	 */
-	if (req->flags & REQ_F_LINK) {
-		if (req->flags & REQ_F_FAIL_LINK)
-			io_fail_links(req);
-		else
-			io_req_link_next(req);
+	if (req->flags & REQ_F_FAIL_LINK) {
+		io_fail_links(req);
+	} else if ((req->flags & (REQ_F_LINK_TIMEOUT | REQ_F_COMP_LOCKED)) ==
+			REQ_F_LINK_TIMEOUT) {
+		struct io_ring_ctx *ctx = req->ctx;
+		unsigned long flags;
+
+		/*
+		 * If this is a timeout link, we could be racing with the
+		 * timeout timer. Grab the completion lock for this case to
+		 * protect against that.
+		 */
+		spin_lock_irqsave(&ctx->completion_lock, flags);
+		io_req_link_next(req, nxt);
+		spin_unlock_irqrestore(&ctx->completion_lock, flags);
+	} else {
+		io_req_link_next(req, nxt);
 	}
 
 	__io_free_req(req);
 }
 
+static void io_free_req(struct io_kiocb *req)
+{
+	io_free_req_find_next(req, NULL);
+}
+
+/*
+ * Drop reference to request, return next in chain (if there is one) if this
+ * was the last reference to this request.
+ */
+static void io_put_req_find_next(struct io_kiocb *req, struct io_kiocb **nxtptr)
+{
+	struct io_kiocb *nxt = NULL;
+
+	if (refcount_dec_and_test(&req->refs))
+		io_free_req_find_next(req, &nxt);
+
+	if (nxt) {
+		if (nxtptr)
+			*nxtptr = nxt;
+		else
+			io_queue_async_work(nxt);
+	}
+}
+
 static void io_put_req(struct io_kiocb *req)
 {
 	if (refcount_dec_and_test(&req->refs))
 		io_free_req(req);
 }
 
-static unsigned io_cqring_events(struct io_rings *rings)
+static void io_double_put_req(struct io_kiocb *req)
+{
+	/* drop both submit and complete references */
+	if (refcount_sub_and_test(2, &req->refs))
+		__io_free_req(req);
+}
+
+static unsigned io_cqring_events(struct io_ring_ctx *ctx, bool noflush)
 {
+	struct io_rings *rings = ctx->rings;
+
+	/*
+	 * noflush == true is from the waitqueue handler, just ensure we wake
+	 * up the task, and the next invocation will flush the entries. We
+	 * cannot safely to it from here.
+	 */
+	if (noflush && !list_empty(&ctx->cq_overflow_list))
+		return -1U;
+
+	io_cqring_overflow_flush(ctx, false);
+
 	/* See comment at the top of this file */
 	smp_rmb();
 	return READ_ONCE(rings->cq.tail) - READ_ONCE(rings->cq.head);
@@ -765,7 +1039,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 		req = list_first_entry(done, struct io_kiocb, list);
 		list_del(&req->list);
 
-		io_cqring_fill_event(ctx, req->user_data, req->result);
+		io_cqring_fill_event(req, req->result);
 		(*nr_events)++;
 
 		if (refcount_dec_and_test(&req->refs)) {
@@ -774,8 +1048,8 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 			 * completions for those, only batch free for fixed
 			 * file and non-linked commands.
 			 */
-			if ((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) ==
-			    REQ_F_FIXED_FILE) {
+			if (((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) ==
+			    REQ_F_FIXED_FILE) && !io_is_fallback_req(req)) {
 				reqs[to_free++] = req;
 				if (to_free == ARRAY_SIZE(reqs))
 					io_free_req_many(ctx, reqs, &to_free);
@@ -892,7 +1166,7 @@ static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
 		 * If we do, we can potentially be spinning for commands that
 		 * already triggered a CQE (eg in error).
 		 */
-		if (io_cqring_events(ctx->rings))
+		if (io_cqring_events(ctx, false))
 			break;
 
 		/*
@@ -952,7 +1226,7 @@ static void kiocb_end_write(struct io_kiocb *req)
 	file_end_write(req->file);
 }
 
-static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
+static void io_complete_rw_common(struct kiocb *kiocb, long res)
 {
 	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
 
@@ -961,10 +1235,28 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
 
 	if ((req->flags & REQ_F_LINK) && res != req->result)
 		req->flags |= REQ_F_FAIL_LINK;
-	io_cqring_add_event(req->ctx, req->user_data, res);
+	io_cqring_add_event(req, res);
+}
+
+static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
+{
+	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
+
+	io_complete_rw_common(kiocb, res);
 	io_put_req(req);
 }
 
+static struct io_kiocb *__io_complete_rw(struct kiocb *kiocb, long res)
+{
+	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
+	struct io_kiocb *nxt = NULL;
+
+	io_complete_rw_common(kiocb, res);
+	io_put_req_find_next(req, &nxt);
+
+	return nxt;
+}
+
 static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
 {
 	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
@@ -1072,10 +1364,9 @@ static bool io_file_supports_async(struct file *file)
 	return false;
 }
 
-static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
-		      bool force_nonblock)
+static int io_prep_rw(struct io_kiocb *req, bool force_nonblock)
 {
-	const struct io_uring_sqe *sqe = s->sqe;
+	const struct io_uring_sqe *sqe = req->submit.sqe;
 	struct io_ring_ctx *ctx = req->ctx;
 	struct kiocb *kiocb = &req->rw;
 	unsigned ioprio;
@@ -1159,6 +1450,15 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
 	}
 }
 
+static void kiocb_done(struct kiocb *kiocb, ssize_t ret, struct io_kiocb **nxt,
+		       bool in_async)
+{
+	if (in_async && ret >= 0 && nxt && kiocb->ki_complete == io_complete_rw)
+		*nxt = __io_complete_rw(kiocb, ret);
+	else
+		io_rw_done(kiocb, ret);
+}
+
 static int io_import_fixed(struct io_ring_ctx *ctx, int rw,
 			   const struct io_uring_sqe *sqe,
 			   struct iov_iter *iter)
@@ -1270,65 +1570,6 @@ static ssize_t io_import_iovec(struct io_ring_ctx *ctx, int rw,
 	return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter);
 }
 
-static inline bool io_should_merge(struct async_list *al, struct kiocb *kiocb)
-{
-	if (al->file == kiocb->ki_filp) {
-		off_t start, end;
-
-		/*
-		 * Allow merging if we're anywhere in the range of the same
-		 * page. Generally this happens for sub-page reads or writes,
-		 * and it's beneficial to allow the first worker to bring the
-		 * page in and the piggy backed work can then work on the
-		 * cached page.
-		 */
-		start = al->io_start & PAGE_MASK;
-		end = (al->io_start + al->io_len + PAGE_SIZE - 1) & PAGE_MASK;
-		if (kiocb->ki_pos >= start && kiocb->ki_pos <= end)
-			return true;
-	}
-
-	al->file = NULL;
-	return false;
-}
-
-/*
- * Make a note of the last file/offset/direction we punted to async
- * context. We'll use this information to see if we can piggy back a
- * sequential request onto the previous one, if it's still hasn't been
- * completed by the async worker.
- */
-static void io_async_list_note(int rw, struct io_kiocb *req, size_t len)
-{
-	struct async_list *async_list = &req->ctx->pending_async[rw];
-	struct kiocb *kiocb = &req->rw;
-	struct file *filp = kiocb->ki_filp;
-
-	if (io_should_merge(async_list, kiocb)) {
-		unsigned long max_bytes;
-
-		/* Use 8x RA size as a decent limiter for both reads/writes */
-		max_bytes = filp->f_ra.ra_pages << (PAGE_SHIFT + 3);
-		if (!max_bytes)
-			max_bytes = VM_READAHEAD_PAGES << (PAGE_SHIFT + 3);
-
-		/* If max len are exceeded, reset the state */
-		if (async_list->io_len + len <= max_bytes) {
-			req->flags |= REQ_F_SEQ_PREV;
-			async_list->io_len += len;
-		} else {
-			async_list->file = NULL;
-		}
-	}
-
-	/* New file? Reset state. */
-	if (async_list->file != filp) {
-		async_list->io_start = kiocb->ki_pos;
-		async_list->io_len = len;
-		async_list->file = filp;
-	}
-}
-
 /*
  * For files that don't have ->read_iter() and ->write_iter(), handle them
  * by looping over ->read() or ->write() manually.
@@ -1374,7 +1615,7 @@ static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb,
 	return ret;
 }
 
-static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
+static int io_read(struct io_kiocb *req, struct io_kiocb **nxt,
 		   bool force_nonblock)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
@@ -1384,7 +1625,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 	size_t iov_count;
 	ssize_t read_size, ret;
 
-	ret = io_prep_rw(req, s, force_nonblock);
+	ret = io_prep_rw(req, force_nonblock);
 	if (ret)
 		return ret;
 	file = kiocb->ki_filp;
@@ -1392,7 +1633,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 	if (unlikely(!(file->f_mode & FMODE_READ)))
 		return -EBADF;
 
-	ret = io_import_iovec(req->ctx, READ, s, &iovec, &iter);
+	ret = io_import_iovec(req->ctx, READ, &req->submit, &iovec, &iter);
 	if (ret < 0)
 		return ret;
 
@@ -1423,23 +1664,16 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 		    ret2 > 0 && ret2 < read_size)
 			ret2 = -EAGAIN;
 		/* Catch -EAGAIN return for forced non-blocking submission */
-		if (!force_nonblock || ret2 != -EAGAIN) {
-			io_rw_done(kiocb, ret2);
-		} else {
-			/*
-			 * If ->needs_lock is true, we're already in async
-			 * context.
-			 */
-			if (!s->needs_lock)
-				io_async_list_note(READ, req, iov_count);
+		if (!force_nonblock || ret2 != -EAGAIN)
+			kiocb_done(kiocb, ret2, nxt, req->submit.in_async);
+		else
 			ret = -EAGAIN;
-		}
 	}
 	kfree(iovec);
 	return ret;
 }
 
-static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
+static int io_write(struct io_kiocb *req, struct io_kiocb **nxt,
 		    bool force_nonblock)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
@@ -1449,7 +1683,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
 	size_t iov_count;
 	ssize_t ret;
 
-	ret = io_prep_rw(req, s, force_nonblock);
+	ret = io_prep_rw(req, force_nonblock);
 	if (ret)
 		return ret;
 
@@ -1457,7 +1691,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
 	if (unlikely(!(file->f_mode & FMODE_WRITE)))
 		return -EBADF;
 
-	ret = io_import_iovec(req->ctx, WRITE, s, &iovec, &iter);
+	ret = io_import_iovec(req->ctx, WRITE, &req->submit, &iovec, &iter);
 	if (ret < 0)
 		return ret;
 
@@ -1467,12 +1701,8 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
 	iov_count = iov_iter_count(&iter);
 
 	ret = -EAGAIN;
-	if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT)) {
-		/* If ->needs_lock is true, we're already in async context. */
-		if (!s->needs_lock)
-			io_async_list_note(WRITE, req, iov_count);
+	if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT))
 		goto out_free;
-	}
 
 	ret = rw_verify_area(WRITE, file, &kiocb->ki_pos, iov_count);
 	if (!ret) {
@@ -1497,17 +1727,10 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
 			ret2 = call_write_iter(file, kiocb, &iter);
 		else
 			ret2 = loop_rw_iter(WRITE, file, kiocb, &iter);
-		if (!force_nonblock || ret2 != -EAGAIN) {
-			io_rw_done(kiocb, ret2);
-		} else {
-			/*
-			 * If ->needs_lock is true, we're already in async
-			 * context.
-			 */
-			if (!s->needs_lock)
-				io_async_list_note(WRITE, req, iov_count);
+		if (!force_nonblock || ret2 != -EAGAIN)
+			kiocb_done(kiocb, ret2, nxt, req->submit.in_async);
+		else
 			ret = -EAGAIN;
-		}
 	}
 out_free:
 	kfree(iovec);
@@ -1517,15 +1740,14 @@ out_free:
 /*
  * IORING_OP_NOP just posts a completion event, nothing else.
  */
-static int io_nop(struct io_kiocb *req, u64 user_data)
+static int io_nop(struct io_kiocb *req)
 {
 	struct io_ring_ctx *ctx = req->ctx;
-	long err = 0;
 
 	if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
 		return -EINVAL;
 
-	io_cqring_add_event(ctx, user_data, err);
+	io_cqring_add_event(req, 0);
 	io_put_req(req);
 	return 0;
 }
@@ -1546,7 +1768,7 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 }
 
 static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
-		    bool force_nonblock)
+		    struct io_kiocb **nxt, bool force_nonblock)
 {
 	loff_t sqe_off = READ_ONCE(sqe->off);
 	loff_t sqe_len = READ_ONCE(sqe->len);
@@ -1572,8 +1794,8 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 
 	if (ret < 0 && (req->flags & REQ_F_LINK))
 		req->flags |= REQ_F_FAIL_LINK;
-	io_cqring_add_event(req->ctx, sqe->user_data, ret);
-	io_put_req(req);
+	io_cqring_add_event(req, ret);
+	io_put_req_find_next(req, nxt);
 	return 0;
 }
 
@@ -1595,6 +1817,7 @@ static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 
 static int io_sync_file_range(struct io_kiocb *req,
 			      const struct io_uring_sqe *sqe,
+			      struct io_kiocb **nxt,
 			      bool force_nonblock)
 {
 	loff_t sqe_off;
@@ -1618,14 +1841,14 @@ static int io_sync_file_range(struct io_kiocb *req,
 
 	if (ret < 0 && (req->flags & REQ_F_LINK))
 		req->flags |= REQ_F_FAIL_LINK;
-	io_cqring_add_event(req->ctx, sqe->user_data, ret);
-	io_put_req(req);
+	io_cqring_add_event(req, ret);
+	io_put_req_find_next(req, nxt);
 	return 0;
 }
 
 #if defined(CONFIG_NET)
 static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
-			   bool force_nonblock,
+			   struct io_kiocb **nxt, bool force_nonblock,
 		   long (*fn)(struct socket *, struct user_msghdr __user *,
 				unsigned int))
 {
@@ -1654,32 +1877,80 @@ static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			return ret;
 	}
 
-	io_cqring_add_event(req->ctx, sqe->user_data, ret);
-	io_put_req(req);
+	io_cqring_add_event(req, ret);
+	if (ret < 0 && (req->flags & REQ_F_LINK))
+		req->flags |= REQ_F_FAIL_LINK;
+	io_put_req_find_next(req, nxt);
 	return 0;
 }
 #endif
 
 static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
-		      bool force_nonblock)
+		      struct io_kiocb **nxt, bool force_nonblock)
 {
 #if defined(CONFIG_NET)
-	return io_send_recvmsg(req, sqe, force_nonblock, __sys_sendmsg_sock);
+	return io_send_recvmsg(req, sqe, nxt, force_nonblock,
+				__sys_sendmsg_sock);
 #else
 	return -EOPNOTSUPP;
 #endif
 }
 
 static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
-		      bool force_nonblock)
+		      struct io_kiocb **nxt, bool force_nonblock)
 {
 #if defined(CONFIG_NET)
-	return io_send_recvmsg(req, sqe, force_nonblock, __sys_recvmsg_sock);
+	return io_send_recvmsg(req, sqe, nxt, force_nonblock,
+				__sys_recvmsg_sock);
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int io_accept(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+		     struct io_kiocb **nxt, bool force_nonblock)
+{
+#if defined(CONFIG_NET)
+	struct sockaddr __user *addr;
+	int __user *addr_len;
+	unsigned file_flags;
+	int flags, ret;
+
+	if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL)))
+		return -EINVAL;
+	if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index)
+		return -EINVAL;
+
+	addr = (struct sockaddr __user *) (unsigned long) READ_ONCE(sqe->addr);
+	addr_len = (int __user *) (unsigned long) READ_ONCE(sqe->addr2);
+	flags = READ_ONCE(sqe->accept_flags);
+	file_flags = force_nonblock ? O_NONBLOCK : 0;
+
+	ret = __sys_accept4_file(req->file, file_flags, addr, addr_len, flags);
+	if (ret == -EAGAIN && force_nonblock) {
+		req->work.flags |= IO_WQ_WORK_NEEDS_FILES;
+		return -EAGAIN;
+	}
+	if (ret == -ERESTARTSYS)
+		ret = -EINTR;
+	if (ret < 0 && (req->flags & REQ_F_LINK))
+		req->flags |= REQ_F_FAIL_LINK;
+	io_cqring_add_event(req, ret);
+	io_put_req_find_next(req, nxt);
+	return 0;
 #else
 	return -EOPNOTSUPP;
 #endif
 }
 
+static inline void io_poll_remove_req(struct io_kiocb *req)
+{
+	if (!RB_EMPTY_NODE(&req->rb_node)) {
+		rb_erase(&req->rb_node, &req->ctx->cancel_tree);
+		RB_CLEAR_NODE(&req->rb_node);
+	}
+}
+
 static void io_poll_remove_one(struct io_kiocb *req)
 {
 	struct io_poll_iocb *poll = &req->poll;
@@ -1688,25 +1959,47 @@ static void io_poll_remove_one(struct io_kiocb *req)
 	WRITE_ONCE(poll->canceled, true);
 	if (!list_empty(&poll->wait.entry)) {
 		list_del_init(&poll->wait.entry);
-		io_queue_async_work(req->ctx, req);
+		io_queue_async_work(req);
 	}
 	spin_unlock(&poll->head->lock);
-
-	list_del_init(&req->list);
+	io_poll_remove_req(req);
 }
 
 static void io_poll_remove_all(struct io_ring_ctx *ctx)
 {
+	struct rb_node *node;
 	struct io_kiocb *req;
 
 	spin_lock_irq(&ctx->completion_lock);
-	while (!list_empty(&ctx->cancel_list)) {
-		req = list_first_entry(&ctx->cancel_list, struct io_kiocb,list);
+	while ((node = rb_first(&ctx->cancel_tree)) != NULL) {
+		req = rb_entry(node, struct io_kiocb, rb_node);
 		io_poll_remove_one(req);
 	}
 	spin_unlock_irq(&ctx->completion_lock);
 }
 
+static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr)
+{
+	struct rb_node *p, *parent = NULL;
+	struct io_kiocb *req;
+
+	p = ctx->cancel_tree.rb_node;
+	while (p) {
+		parent = p;
+		req = rb_entry(parent, struct io_kiocb, rb_node);
+		if (sqe_addr < req->user_data) {
+			p = p->rb_left;
+		} else if (sqe_addr > req->user_data) {
+			p = p->rb_right;
+		} else {
+			io_poll_remove_one(req);
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
 /*
  * Find a running poll command that matches one specified in sqe->addr,
  * and remove it if found.
@@ -1714,8 +2007,7 @@ static void io_poll_remove_all(struct io_ring_ctx *ctx)
 static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_ring_ctx *ctx = req->ctx;
-	struct io_kiocb *poll_req, *next;
-	int ret = -ENOENT;
+	int ret;
 
 	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
 		return -EINVAL;
@@ -1724,36 +2016,38 @@ static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return -EINVAL;
 
 	spin_lock_irq(&ctx->completion_lock);
-	list_for_each_entry_safe(poll_req, next, &ctx->cancel_list, list) {
-		if (READ_ONCE(sqe->addr) == poll_req->user_data) {
-			io_poll_remove_one(poll_req);
-			ret = 0;
-			break;
-		}
-	}
+	ret = io_poll_cancel(ctx, READ_ONCE(sqe->addr));
 	spin_unlock_irq(&ctx->completion_lock);
 
-	io_cqring_add_event(req->ctx, sqe->user_data, ret);
+	io_cqring_add_event(req, ret);
+	if (ret < 0 && (req->flags & REQ_F_LINK))
+		req->flags |= REQ_F_FAIL_LINK;
 	io_put_req(req);
 	return 0;
 }
 
-static void io_poll_complete(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			     __poll_t mask)
+static void io_poll_complete(struct io_kiocb *req, __poll_t mask)
 {
+	struct io_ring_ctx *ctx = req->ctx;
+
 	req->poll.done = true;
-	io_cqring_fill_event(ctx, req->user_data, mangle_poll(mask));
+	io_cqring_fill_event(req, mangle_poll(mask));
 	io_commit_cqring(ctx);
 }
 
-static void io_poll_complete_work(struct work_struct *work)
+static void io_poll_complete_work(struct io_wq_work **workptr)
 {
+	struct io_wq_work *work = *workptr;
 	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
 	struct io_poll_iocb *poll = &req->poll;
 	struct poll_table_struct pt = { ._key = poll->events };
 	struct io_ring_ctx *ctx = req->ctx;
+	struct io_kiocb *nxt = NULL;
 	__poll_t mask = 0;
 
+	if (work->flags & IO_WQ_WORK_CANCEL)
+		WRITE_ONCE(poll->canceled, true);
+
 	if (!READ_ONCE(poll->canceled))
 		mask = vfs_poll(poll->file, &pt) & poll->events;
 
@@ -1770,12 +2064,15 @@ static void io_poll_complete_work(struct work_struct *work)
 		spin_unlock_irq(&ctx->completion_lock);
 		return;
 	}
-	list_del_init(&req->list);
-	io_poll_complete(ctx, req, mask);
+	io_poll_remove_req(req);
+	io_poll_complete(req, mask);
 	spin_unlock_irq(&ctx->completion_lock);
 
 	io_cqring_ev_posted(ctx);
-	io_put_req(req);
+
+	io_put_req_find_next(req, &nxt);
+	if (nxt)
+		*workptr = &nxt->work;
 }
 
 static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
@@ -1794,15 +2091,22 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 
 	list_del_init(&poll->wait.entry);
 
+	/*
+	 * Run completion inline if we can. We're using trylock here because
+	 * we are violating the completion_lock -> poll wq lock ordering.
+	 * If we have a link timeout we're going to need the completion_lock
+	 * for finalizing the request, mark us as having grabbed that already.
+	 */
 	if (mask && spin_trylock_irqsave(&ctx->completion_lock, flags)) {
-		list_del(&req->list);
-		io_poll_complete(ctx, req, mask);
+		io_poll_remove_req(req);
+		io_poll_complete(req, mask);
+		req->flags |= REQ_F_COMP_LOCKED;
+		io_put_req(req);
 		spin_unlock_irqrestore(&ctx->completion_lock, flags);
 
 		io_cqring_ev_posted(ctx);
-		io_put_req(req);
 	} else {
-		io_queue_async_work(ctx, req);
+		io_queue_async_work(req);
 	}
 
 	return 1;
@@ -1829,7 +2133,27 @@ static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
 	add_wait_queue(head, &pt->req->poll.wait);
 }
 
-static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+static void io_poll_req_insert(struct io_kiocb *req)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	struct rb_node **p = &ctx->cancel_tree.rb_node;
+	struct rb_node *parent = NULL;
+	struct io_kiocb *tmp;
+
+	while (*p) {
+		parent = *p;
+		tmp = rb_entry(parent, struct io_kiocb, rb_node);
+		if (req->user_data < tmp->user_data)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+	rb_link_node(&req->rb_node, parent, p);
+	rb_insert_color(&req->rb_node, &ctx->cancel_tree);
+}
+
+static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+		       struct io_kiocb **nxt)
 {
 	struct io_poll_iocb *poll = &req->poll;
 	struct io_ring_ctx *ctx = req->ctx;
@@ -1846,9 +2170,10 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return -EBADF;
 
 	req->submit.sqe = NULL;
-	INIT_WORK(&req->work, io_poll_complete_work);
+	INIT_IO_WORK(&req->work, io_poll_complete_work);
 	events = READ_ONCE(sqe->poll_events);
 	poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP;
+	RB_CLEAR_NODE(&req->rb_node);
 
 	poll->head = NULL;
 	poll->done = false;
@@ -1881,18 +2206,18 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		else if (cancel)
 			WRITE_ONCE(poll->canceled, true);
 		else if (!poll->done) /* actually waiting for an event */
-			list_add_tail(&req->list, &ctx->cancel_list);
+			io_poll_req_insert(req);
 		spin_unlock(&poll->head->lock);
 	}
 	if (mask) { /* no async, we'd stolen it */
 		ipt.error = 0;
-		io_poll_complete(ctx, req, mask);
+		io_poll_complete(req, mask);
 	}
 	spin_unlock_irq(&ctx->completion_lock);
 
 	if (mask) {
 		io_cqring_ev_posted(ctx);
-		io_put_req(req);
+		io_put_req_find_next(req, nxt);
 	}
 	return ipt.error;
 }
@@ -1900,7 +2225,7 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
 {
 	struct io_ring_ctx *ctx;
-	struct io_kiocb *req, *prev;
+	struct io_kiocb *req;
 	unsigned long flags;
 
 	req = container_of(timer, struct io_kiocb, timeout.timer);
@@ -1909,43 +2234,118 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
 
 	spin_lock_irqsave(&ctx->completion_lock, flags);
 	/*
-	 * Adjust the reqs sequence before the current one because it
-	 * will consume a slot in the cq_ring and the the cq_tail pointer
-	 * will be increased, otherwise other timeout reqs may return in
-	 * advance without waiting for enough wait_nr.
+	 * We could be racing with timeout deletion. If the list is empty,
+	 * then timeout lookup already found it and will be handling it.
 	 */
-	prev = req;
-	list_for_each_entry_continue_reverse(prev, &ctx->timeout_list, list)
-		prev->sequence++;
-	list_del(&req->list);
+	if (!list_empty(&req->list)) {
+		struct io_kiocb *prev;
+
+		/*
+		 * Adjust the reqs sequence before the current one because it
+		 * will consume a slot in the cq_ring and the the cq_tail
+		 * pointer will be increased, otherwise other timeout reqs may
+		 * return in advance without waiting for enough wait_nr.
+		 */
+		prev = req;
+		list_for_each_entry_continue_reverse(prev, &ctx->timeout_list, list)
+			prev->sequence++;
+		list_del_init(&req->list);
+	}
 
-	io_cqring_fill_event(ctx, req->user_data, -ETIME);
+	io_cqring_fill_event(req, -ETIME);
 	io_commit_cqring(ctx);
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 
 	io_cqring_ev_posted(ctx);
-
+	if (req->flags & REQ_F_LINK)
+		req->flags |= REQ_F_FAIL_LINK;
 	io_put_req(req);
 	return HRTIMER_NORESTART;
 }
 
+static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data)
+{
+	struct io_kiocb *req;
+	int ret = -ENOENT;
+
+	list_for_each_entry(req, &ctx->timeout_list, list) {
+		if (user_data == req->user_data) {
+			list_del_init(&req->list);
+			ret = 0;
+			break;
+		}
+	}
+
+	if (ret == -ENOENT)
+		return ret;
+
+	ret = hrtimer_try_to_cancel(&req->timeout.timer);
+	if (ret == -1)
+		return -EALREADY;
+
+	io_cqring_fill_event(req, -ECANCELED);
+	io_put_req(req);
+	return 0;
+}
+
+/*
+ * Remove or update an existing timeout command
+ */
+static int io_timeout_remove(struct io_kiocb *req,
+			     const struct io_uring_sqe *sqe)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	unsigned flags;
+	int ret;
+
+	if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+	if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->len)
+		return -EINVAL;
+	flags = READ_ONCE(sqe->timeout_flags);
+	if (flags)
+		return -EINVAL;
+
+	spin_lock_irq(&ctx->completion_lock);
+	ret = io_timeout_cancel(ctx, READ_ONCE(sqe->addr));
+
+	io_cqring_fill_event(req, ret);
+	io_commit_cqring(ctx);
+	spin_unlock_irq(&ctx->completion_lock);
+	io_cqring_ev_posted(ctx);
+	if (ret < 0 && req->flags & REQ_F_LINK)
+		req->flags |= REQ_F_FAIL_LINK;
+	io_put_req(req);
+	return 0;
+}
+
 static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	unsigned count;
 	struct io_ring_ctx *ctx = req->ctx;
 	struct list_head *entry;
+	enum hrtimer_mode mode;
 	struct timespec64 ts;
 	unsigned span = 0;
+	unsigned flags;
 
 	if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
 		return -EINVAL;
-	if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->timeout_flags ||
-	    sqe->len != 1)
+	if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->len != 1)
+		return -EINVAL;
+	flags = READ_ONCE(sqe->timeout_flags);
+	if (flags & ~IORING_TIMEOUT_ABS)
 		return -EINVAL;
 
 	if (get_timespec64(&ts, u64_to_user_ptr(sqe->addr)))
 		return -EFAULT;
 
+	if (flags & IORING_TIMEOUT_ABS)
+		mode = HRTIMER_MODE_ABS;
+	else
+		mode = HRTIMER_MODE_REL;
+
+	hrtimer_init(&req->timeout.timer, CLOCK_MONOTONIC, mode);
 	req->flags |= REQ_F_TIMEOUT;
 
 	/*
@@ -2006,21 +2406,92 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	req->sequence -= span;
 add:
 	list_add(&req->list, entry);
+	req->timeout.timer.function = io_timeout_fn;
+	hrtimer_start(&req->timeout.timer, timespec64_to_ktime(ts), mode);
 	spin_unlock_irq(&ctx->completion_lock);
+	return 0;
+}
 
-	hrtimer_init(&req->timeout.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	req->timeout.timer.function = io_timeout_fn;
-	hrtimer_start(&req->timeout.timer, timespec64_to_ktime(ts),
-			HRTIMER_MODE_REL);
+static bool io_cancel_cb(struct io_wq_work *work, void *data)
+{
+	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+
+	return req->user_data == (unsigned long) data;
+}
+
+static int io_async_cancel_one(struct io_ring_ctx *ctx, void *sqe_addr)
+{
+	enum io_wq_cancel cancel_ret;
+	int ret = 0;
+
+	cancel_ret = io_wq_cancel_cb(ctx->io_wq, io_cancel_cb, sqe_addr);
+	switch (cancel_ret) {
+	case IO_WQ_CANCEL_OK:
+		ret = 0;
+		break;
+	case IO_WQ_CANCEL_RUNNING:
+		ret = -EALREADY;
+		break;
+	case IO_WQ_CANCEL_NOTFOUND:
+		ret = -ENOENT;
+		break;
+	}
+
+	return ret;
+}
+
+static void io_async_find_and_cancel(struct io_ring_ctx *ctx,
+				     struct io_kiocb *req, __u64 sqe_addr,
+				     struct io_kiocb **nxt)
+{
+	unsigned long flags;
+	int ret;
+
+	ret = io_async_cancel_one(ctx, (void *) (unsigned long) sqe_addr);
+	if (ret != -ENOENT) {
+		spin_lock_irqsave(&ctx->completion_lock, flags);
+		goto done;
+	}
+
+	spin_lock_irqsave(&ctx->completion_lock, flags);
+	ret = io_timeout_cancel(ctx, sqe_addr);
+	if (ret != -ENOENT)
+		goto done;
+	ret = io_poll_cancel(ctx, sqe_addr);
+done:
+	io_cqring_fill_event(req, ret);
+	io_commit_cqring(ctx);
+	spin_unlock_irqrestore(&ctx->completion_lock, flags);
+	io_cqring_ev_posted(ctx);
+
+	if (ret < 0 && (req->flags & REQ_F_LINK))
+		req->flags |= REQ_F_FAIL_LINK;
+	io_put_req_find_next(req, nxt);
+}
+
+static int io_async_cancel(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+			   struct io_kiocb **nxt)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+
+	if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+	if (sqe->flags || sqe->ioprio || sqe->off || sqe->len ||
+	    sqe->cancel_flags)
+		return -EINVAL;
+
+	io_async_find_and_cancel(ctx, req, READ_ONCE(sqe->addr), NULL);
 	return 0;
 }
 
-static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			const struct io_uring_sqe *sqe)
+static int io_req_defer(struct io_kiocb *req)
 {
+	const struct io_uring_sqe *sqe = req->submit.sqe;
 	struct io_uring_sqe *sqe_copy;
+	struct io_ring_ctx *ctx = req->ctx;
 
-	if (!io_sequence_defer(ctx, req) && list_empty(&ctx->defer_list))
+	/* Still need defer if there is pending req in defer list. */
+	if (!req_need_defer(req) && list_empty(&ctx->defer_list))
 		return 0;
 
 	sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL);
@@ -2028,7 +2499,7 @@ static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		return -EAGAIN;
 
 	spin_lock_irq(&ctx->completion_lock);
-	if (!io_sequence_defer(ctx, req) && list_empty(&ctx->defer_list)) {
+	if (!req_need_defer(req) && list_empty(&ctx->defer_list)) {
 		spin_unlock_irq(&ctx->completion_lock);
 		kfree(sqe_copy);
 		return 0;
@@ -2037,64 +2508,70 @@ static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	memcpy(sqe_copy, sqe, sizeof(*sqe_copy));
 	req->submit.sqe = sqe_copy;
 
-	INIT_WORK(&req->work, io_sq_wq_submit_work);
+	trace_io_uring_defer(ctx, req, false);
 	list_add_tail(&req->list, &ctx->defer_list);
 	spin_unlock_irq(&ctx->completion_lock);
 	return -EIOCBQUEUED;
 }
 
-static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			   const struct sqe_submit *s, bool force_nonblock)
+static int __io_submit_sqe(struct io_kiocb *req, struct io_kiocb **nxt,
+			   bool force_nonblock)
 {
 	int ret, opcode;
-
-	req->user_data = READ_ONCE(s->sqe->user_data);
-
-	if (unlikely(s->index >= ctx->sq_entries))
-		return -EINVAL;
+	struct sqe_submit *s = &req->submit;
+	struct io_ring_ctx *ctx = req->ctx;
 
 	opcode = READ_ONCE(s->sqe->opcode);
 	switch (opcode) {
 	case IORING_OP_NOP:
-		ret = io_nop(req, req->user_data);
+		ret = io_nop(req);
 		break;
 	case IORING_OP_READV:
 		if (unlikely(s->sqe->buf_index))
 			return -EINVAL;
-		ret = io_read(req, s, force_nonblock);
+		ret = io_read(req, nxt, force_nonblock);
 		break;
 	case IORING_OP_WRITEV:
 		if (unlikely(s->sqe->buf_index))
 			return -EINVAL;
-		ret = io_write(req, s, force_nonblock);
+		ret = io_write(req, nxt, force_nonblock);
 		break;
 	case IORING_OP_READ_FIXED:
-		ret = io_read(req, s, force_nonblock);
+		ret = io_read(req, nxt, force_nonblock);
 		break;
 	case IORING_OP_WRITE_FIXED:
-		ret = io_write(req, s, force_nonblock);
+		ret = io_write(req, nxt, force_nonblock);
 		break;
 	case IORING_OP_FSYNC:
-		ret = io_fsync(req, s->sqe, force_nonblock);
+		ret = io_fsync(req, s->sqe, nxt, force_nonblock);
 		break;
 	case IORING_OP_POLL_ADD:
-		ret = io_poll_add(req, s->sqe);
+		ret = io_poll_add(req, s->sqe, nxt);
 		break;
 	case IORING_OP_POLL_REMOVE:
 		ret = io_poll_remove(req, s->sqe);
 		break;
 	case IORING_OP_SYNC_FILE_RANGE:
-		ret = io_sync_file_range(req, s->sqe, force_nonblock);
+		ret = io_sync_file_range(req, s->sqe, nxt, force_nonblock);
 		break;
 	case IORING_OP_SENDMSG:
-		ret = io_sendmsg(req, s->sqe, force_nonblock);
+		ret = io_sendmsg(req, s->sqe, nxt, force_nonblock);
 		break;
 	case IORING_OP_RECVMSG:
-		ret = io_recvmsg(req, s->sqe, force_nonblock);
+		ret = io_recvmsg(req, s->sqe, nxt, force_nonblock);
 		break;
 	case IORING_OP_TIMEOUT:
 		ret = io_timeout(req, s->sqe);
 		break;
+	case IORING_OP_TIMEOUT_REMOVE:
+		ret = io_timeout_remove(req, s->sqe);
+		break;
+	case IORING_OP_ACCEPT:
+		ret = io_accept(req, s->sqe, nxt, force_nonblock);
+		break;
+	case IORING_OP_ASYNC_CANCEL:
+		ret = io_async_cancel(req, s->sqe, nxt);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -2108,187 +2585,65 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 			return -EAGAIN;
 
 		/* workqueue context doesn't hold uring_lock, grab it now */
-		if (s->needs_lock)
+		if (s->in_async)
 			mutex_lock(&ctx->uring_lock);
 		io_iopoll_req_issued(req);
-		if (s->needs_lock)
+		if (s->in_async)
 			mutex_unlock(&ctx->uring_lock);
 	}
 
 	return 0;
 }
 
-static struct async_list *io_async_list_from_sqe(struct io_ring_ctx *ctx,
-						 const struct io_uring_sqe *sqe)
-{
-	switch (sqe->opcode) {
-	case IORING_OP_READV:
-	case IORING_OP_READ_FIXED:
-		return &ctx->pending_async[READ];
-	case IORING_OP_WRITEV:
-	case IORING_OP_WRITE_FIXED:
-		return &ctx->pending_async[WRITE];
-	default:
-		return NULL;
-	}
-}
-
-static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe)
-{
-	u8 opcode = READ_ONCE(sqe->opcode);
-
-	return !(opcode == IORING_OP_READ_FIXED ||
-		 opcode == IORING_OP_WRITE_FIXED);
-}
-
-static void io_sq_wq_submit_work(struct work_struct *work)
+static void io_wq_submit_work(struct io_wq_work **workptr)
 {
+	struct io_wq_work *work = *workptr;
 	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
-	struct io_ring_ctx *ctx = req->ctx;
-	struct mm_struct *cur_mm = NULL;
-	struct async_list *async_list;
-	LIST_HEAD(req_list);
-	mm_segment_t old_fs;
-	int ret;
+	struct sqe_submit *s = &req->submit;
+	const struct io_uring_sqe *sqe = s->sqe;
+	struct io_kiocb *nxt = NULL;
+	int ret = 0;
 
-	async_list = io_async_list_from_sqe(ctx, req->submit.sqe);
-restart:
-	do {
-		struct sqe_submit *s = &req->submit;
-		const struct io_uring_sqe *sqe = s->sqe;
-		unsigned int flags = req->flags;
+	/* Ensure we clear previously set non-block flag */
+	req->rw.ki_flags &= ~IOCB_NOWAIT;
 
-		/* Ensure we clear previously set non-block flag */
-		req->rw.ki_flags &= ~IOCB_NOWAIT;
+	if (work->flags & IO_WQ_WORK_CANCEL)
+		ret = -ECANCELED;
 
-		ret = 0;
-		if (io_sqe_needs_user(sqe) && !cur_mm) {
-			if (!mmget_not_zero(ctx->sqo_mm)) {
-				ret = -EFAULT;
-			} else {
-				cur_mm = ctx->sqo_mm;
-				use_mm(cur_mm);
-				old_fs = get_fs();
-				set_fs(USER_DS);
-			}
-		}
+	if (!ret) {
+		s->has_user = (work->flags & IO_WQ_WORK_HAS_MM) != 0;
+		s->in_async = true;
+		do {
+			ret = __io_submit_sqe(req, &nxt, false);
+			/*
+			 * We can get EAGAIN for polled IO even though we're
+			 * forcing a sync submission from here, since we can't
+			 * wait for request slots on the block side.
+			 */
+			if (ret != -EAGAIN)
+				break;
+			cond_resched();
+		} while (1);
+	}
 
-		if (!ret) {
-			s->has_user = cur_mm != NULL;
-			s->needs_lock = true;
-			do {
-				ret = __io_submit_sqe(ctx, req, s, false);
-				/*
-				 * We can get EAGAIN for polled IO even though
-				 * we're forcing a sync submission from here,
-				 * since we can't wait for request slots on the
-				 * block side.
-				 */
-				if (ret != -EAGAIN)
-					break;
-				cond_resched();
-			} while (1);
-		}
+	/* drop submission reference */
+	io_put_req(req);
 
-		/* drop submission reference */
+	if (ret) {
+		if (req->flags & REQ_F_LINK)
+			req->flags |= REQ_F_FAIL_LINK;
+		io_cqring_add_event(req, ret);
 		io_put_req(req);
-
-		if (ret) {
-			io_cqring_add_event(ctx, sqe->user_data, ret);
-			io_put_req(req);
-		}
-
-		/* async context always use a copy of the sqe */
-		kfree(sqe);
-
-		/* req from defer and link list needn't decrease async cnt */
-		if (flags & (REQ_F_IO_DRAINED | REQ_F_LINK_DONE))
-			goto out;
-
-		if (!async_list)
-			break;
-		if (!list_empty(&req_list)) {
-			req = list_first_entry(&req_list, struct io_kiocb,
-						list);
-			list_del(&req->list);
-			continue;
-		}
-		if (list_empty(&async_list->list))
-			break;
-
-		req = NULL;
-		spin_lock(&async_list->lock);
-		if (list_empty(&async_list->list)) {
-			spin_unlock(&async_list->lock);
-			break;
-		}
-		list_splice_init(&async_list->list, &req_list);
-		spin_unlock(&async_list->lock);
-
-		req = list_first_entry(&req_list, struct io_kiocb, list);
-		list_del(&req->list);
-	} while (req);
-
-	/*
-	 * Rare case of racing with a submitter. If we find the count has
-	 * dropped to zero AND we have pending work items, then restart
-	 * the processing. This is a tiny race window.
-	 */
-	if (async_list) {
-		ret = atomic_dec_return(&async_list->cnt);
-		while (!ret && !list_empty(&async_list->list)) {
-			spin_lock(&async_list->lock);
-			atomic_inc(&async_list->cnt);
-			list_splice_init(&async_list->list, &req_list);
-			spin_unlock(&async_list->lock);
-
-			if (!list_empty(&req_list)) {
-				req = list_first_entry(&req_list,
-							struct io_kiocb, list);
-				list_del(&req->list);
-				goto restart;
-			}
-			ret = atomic_dec_return(&async_list->cnt);
-		}
-	}
-
-out:
-	if (cur_mm) {
-		set_fs(old_fs);
-		unuse_mm(cur_mm);
-		mmput(cur_mm);
 	}
-}
 
-/*
- * See if we can piggy back onto previously submitted work, that is still
- * running. We currently only allow this if the new request is sequential
- * to the previous one we punted.
- */
-static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req)
-{
-	bool ret;
-
-	if (!list)
-		return false;
-	if (!(req->flags & REQ_F_SEQ_PREV))
-		return false;
-	if (!atomic_read(&list->cnt))
-		return false;
+	/* async context always use a copy of the sqe */
+	kfree(sqe);
 
-	ret = true;
-	spin_lock(&list->lock);
-	list_add_tail(&req->list, &list->list);
-	/*
-	 * Ensure we see a simultaneous modification from io_sq_wq_submit_work()
-	 */
-	smp_mb();
-	if (!atomic_read(&list->cnt)) {
-		list_del_init(&req->list);
-		ret = false;
+	/* if a dependent link is ready, pass it back */
+	if (!ret && nxt) {
+		io_prep_async_work(nxt);
+		*workptr = &nxt->work;
 	}
-	spin_unlock(&list->lock);
-	return ret;
 }
 
 static bool io_op_needs_file(const struct io_uring_sqe *sqe)
@@ -2299,15 +2654,28 @@ static bool io_op_needs_file(const struct io_uring_sqe *sqe)
 	case IORING_OP_NOP:
 	case IORING_OP_POLL_REMOVE:
 	case IORING_OP_TIMEOUT:
+	case IORING_OP_TIMEOUT_REMOVE:
+	case IORING_OP_ASYNC_CANCEL:
+	case IORING_OP_LINK_TIMEOUT:
 		return false;
 	default:
 		return true;
 	}
 }
 
-static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s,
-			   struct io_submit_state *state, struct io_kiocb *req)
+static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
+					      int index)
 {
+	struct fixed_file_table *table;
+
+	table = &ctx->file_table[index >> IORING_FILE_TABLE_SHIFT];
+	return table->files[index & IORING_FILE_TABLE_MASK];
+}
+
+static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req)
+{
+	struct sqe_submit *s = &req->submit;
+	struct io_ring_ctx *ctx = req->ctx;
 	unsigned flags;
 	int fd;
 
@@ -2327,14 +2695,18 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s,
 		return 0;
 
 	if (flags & IOSQE_FIXED_FILE) {
-		if (unlikely(!ctx->user_files ||
+		if (unlikely(!ctx->file_table ||
 		    (unsigned) fd >= ctx->nr_user_files))
 			return -EBADF;
-		req->file = ctx->user_files[fd];
+		fd = array_index_nospec(fd, ctx->nr_user_files);
+		req->file = io_file_from_index(ctx, fd);
+		if (!req->file)
+			return -EBADF;
 		req->flags |= REQ_F_FIXED_FILE;
 	} else {
 		if (s->needs_fixed_file)
 			return -EBADF;
+		trace_io_uring_file_get(ctx, fd);
 		req->file = io_file_get(state, fd);
 		if (unlikely(!req->file))
 			return -EBADF;
@@ -2343,12 +2715,146 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s,
 	return 0;
 }
 
-static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			struct sqe_submit *s)
+static int io_grab_files(struct io_kiocb *req)
+{
+	int ret = -EBADF;
+	struct io_ring_ctx *ctx = req->ctx;
+
+	rcu_read_lock();
+	spin_lock_irq(&ctx->inflight_lock);
+	/*
+	 * We use the f_ops->flush() handler to ensure that we can flush
+	 * out work accessing these files if the fd is closed. Check if
+	 * the fd has changed since we started down this path, and disallow
+	 * this operation if it has.
+	 */
+	if (fcheck(req->submit.ring_fd) == req->submit.ring_file) {
+		list_add(&req->inflight_entry, &ctx->inflight_list);
+		req->flags |= REQ_F_INFLIGHT;
+		req->work.files = current->files;
+		ret = 0;
+	}
+	spin_unlock_irq(&ctx->inflight_lock);
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer)
+{
+	struct io_kiocb *req = container_of(timer, struct io_kiocb,
+						timeout.timer);
+	struct io_ring_ctx *ctx = req->ctx;
+	struct io_kiocb *prev = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctx->completion_lock, flags);
+
+	/*
+	 * We don't expect the list to be empty, that will only happen if we
+	 * race with the completion of the linked work.
+	 */
+	if (!list_empty(&req->list)) {
+		prev = list_entry(req->list.prev, struct io_kiocb, link_list);
+		if (refcount_inc_not_zero(&prev->refs))
+			list_del_init(&req->list);
+		else
+			prev = NULL;
+	}
+
+	spin_unlock_irqrestore(&ctx->completion_lock, flags);
+
+	if (prev) {
+		io_async_find_and_cancel(ctx, req, prev->user_data, NULL);
+		io_put_req(prev);
+	} else {
+		io_cqring_add_event(req, -ETIME);
+		io_put_req(req);
+	}
+	return HRTIMER_NORESTART;
+}
+
+static void io_queue_linked_timeout(struct io_kiocb *req, struct timespec64 *ts,
+				    enum hrtimer_mode *mode)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+
+	/*
+	 * If the list is now empty, then our linked request finished before
+	 * we got a chance to setup the timer
+	 */
+	spin_lock_irq(&ctx->completion_lock);
+	if (!list_empty(&req->list)) {
+		req->timeout.timer.function = io_link_timeout_fn;
+		hrtimer_start(&req->timeout.timer, timespec64_to_ktime(*ts),
+				*mode);
+	}
+	spin_unlock_irq(&ctx->completion_lock);
+
+	/* drop submission reference */
+	io_put_req(req);
+}
+
+static int io_validate_link_timeout(const struct io_uring_sqe *sqe,
+				    struct timespec64 *ts)
+{
+	if (sqe->ioprio || sqe->buf_index || sqe->len != 1 || sqe->off)
+		return -EINVAL;
+	if (sqe->timeout_flags & ~IORING_TIMEOUT_ABS)
+		return -EINVAL;
+	if (get_timespec64(ts, u64_to_user_ptr(sqe->addr)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req,
+					       struct timespec64 *ts,
+					       enum hrtimer_mode *mode)
 {
+	struct io_kiocb *nxt;
 	int ret;
 
-	ret = __io_submit_sqe(ctx, req, s, true);
+	if (!(req->flags & REQ_F_LINK))
+		return NULL;
+
+	nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb, list);
+	if (!nxt || nxt->submit.sqe->opcode != IORING_OP_LINK_TIMEOUT)
+		return NULL;
+
+	ret = io_validate_link_timeout(nxt->submit.sqe, ts);
+	if (ret) {
+		list_del_init(&nxt->list);
+		io_cqring_add_event(nxt, ret);
+		io_double_put_req(nxt);
+		return ERR_PTR(-ECANCELED);
+	}
+
+	if (nxt->submit.sqe->timeout_flags & IORING_TIMEOUT_ABS)
+		*mode = HRTIMER_MODE_ABS;
+	else
+		*mode = HRTIMER_MODE_REL;
+
+	req->flags |= REQ_F_LINK_TIMEOUT;
+	hrtimer_init(&nxt->timeout.timer, CLOCK_MONOTONIC, *mode);
+	return nxt;
+}
+
+static int __io_queue_sqe(struct io_kiocb *req)
+{
+	enum hrtimer_mode mode;
+	struct io_kiocb *nxt;
+	struct timespec64 ts;
+	int ret;
+
+	nxt = io_prep_linked_timeout(req, &ts, &mode);
+	if (IS_ERR(nxt)) {
+		ret = PTR_ERR(nxt);
+		nxt = NULL;
+		goto err;
+	}
+
+	ret = __io_submit_sqe(req, NULL, true);
 
 	/*
 	 * We async punt it if the file wasn't marked NOWAIT, or if the file
@@ -2356,36 +2862,47 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	 */
 	if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) ||
 	    (req->flags & REQ_F_MUST_PUNT))) {
+		struct sqe_submit *s = &req->submit;
 		struct io_uring_sqe *sqe_copy;
 
 		sqe_copy = kmemdup(s->sqe, sizeof(*sqe_copy), GFP_KERNEL);
 		if (sqe_copy) {
-			struct async_list *list;
-
 			s->sqe = sqe_copy;
-			memcpy(&req->submit, s, sizeof(*s));
-			list = io_async_list_from_sqe(ctx, s->sqe);
-			if (!io_add_to_prev_work(list, req)) {
-				if (list)
-					atomic_inc(&list->cnt);
-				INIT_WORK(&req->work, io_sq_wq_submit_work);
-				io_queue_async_work(ctx, req);
+			if (req->work.flags & IO_WQ_WORK_NEEDS_FILES) {
+				ret = io_grab_files(req);
+				if (ret) {
+					kfree(sqe_copy);
+					goto err;
+				}
 			}
 
 			/*
 			 * Queued up for async execution, worker will release
 			 * submit reference when the iocb is actually submitted.
 			 */
+			io_queue_async_work(req);
+
+			if (nxt)
+				io_queue_linked_timeout(nxt, &ts, &mode);
+
 			return 0;
 		}
 	}
 
+err:
 	/* drop submission reference */
 	io_put_req(req);
 
+	if (nxt) {
+		if (!ret)
+			io_queue_linked_timeout(nxt, &ts, &mode);
+		else
+			io_put_req(nxt);
+	}
+
 	/* and drop final reference, if we failed */
 	if (ret) {
-		io_cqring_add_event(ctx, req->user_data, ret);
+		io_cqring_add_event(req, ret);
 		if (req->flags & REQ_F_LINK)
 			req->flags |= REQ_F_FAIL_LINK;
 		io_put_req(req);
@@ -2394,31 +2911,30 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	return ret;
 }
 
-static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			struct sqe_submit *s)
+static int io_queue_sqe(struct io_kiocb *req)
 {
 	int ret;
 
-	ret = io_req_defer(ctx, req, s->sqe);
+	ret = io_req_defer(req);
 	if (ret) {
 		if (ret != -EIOCBQUEUED) {
-			io_free_req(req);
-			io_cqring_add_event(ctx, s->sqe->user_data, ret);
+			io_cqring_add_event(req, ret);
+			io_double_put_req(req);
 		}
 		return 0;
 	}
 
-	return __io_queue_sqe(ctx, req, s);
+	return __io_queue_sqe(req);
 }
 
-static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			      struct sqe_submit *s, struct io_kiocb *shadow)
+static int io_queue_link_head(struct io_kiocb *req, struct io_kiocb *shadow)
 {
 	int ret;
 	int need_submit = false;
+	struct io_ring_ctx *ctx = req->ctx;
 
 	if (!shadow)
-		return io_queue_sqe(ctx, req, s);
+		return io_queue_sqe(req);
 
 	/*
 	 * Mark the first IO in link list as DRAIN, let all the following
@@ -2426,12 +2942,12 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	 * list.
 	 */
 	req->flags |= REQ_F_IO_DRAIN;
-	ret = io_req_defer(ctx, req, s->sqe);
+	ret = io_req_defer(req);
 	if (ret) {
 		if (ret != -EIOCBQUEUED) {
-			io_free_req(req);
+			io_cqring_add_event(req, ret);
+			io_double_put_req(req);
 			__io_free_req(shadow);
-			io_cqring_add_event(ctx, s->sqe->user_data, ret);
 			return 0;
 		}
 	} else {
@@ -2444,47 +2960,42 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
 
 	/* Insert shadow req to defer_list, blocking next IOs */
 	spin_lock_irq(&ctx->completion_lock);
+	trace_io_uring_defer(ctx, shadow, true);
 	list_add_tail(&shadow->list, &ctx->defer_list);
 	spin_unlock_irq(&ctx->completion_lock);
 
 	if (need_submit)
-		return __io_queue_sqe(ctx, req, s);
+		return __io_queue_sqe(req);
 
 	return 0;
 }
 
 #define SQE_VALID_FLAGS	(IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK)
 
-static void io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
-			  struct io_submit_state *state, struct io_kiocb **link)
+static void io_submit_sqe(struct io_kiocb *req, struct io_submit_state *state,
+			  struct io_kiocb **link)
 {
 	struct io_uring_sqe *sqe_copy;
-	struct io_kiocb *req;
+	struct sqe_submit *s = &req->submit;
+	struct io_ring_ctx *ctx = req->ctx;
 	int ret;
 
+	req->user_data = s->sqe->user_data;
+
 	/* enforce forwards compatibility on users */
 	if (unlikely(s->sqe->flags & ~SQE_VALID_FLAGS)) {
 		ret = -EINVAL;
-		goto err;
-	}
-
-	req = io_get_req(ctx, state);
-	if (unlikely(!req)) {
-		ret = -EAGAIN;
-		goto err;
+		goto err_req;
 	}
 
-	ret = io_req_set_file(ctx, s, state, req);
+	ret = io_req_set_file(state, req);
 	if (unlikely(ret)) {
 err_req:
-		io_free_req(req);
-err:
-		io_cqring_add_event(ctx, s->sqe->user_data, ret);
+		io_cqring_add_event(req, ret);
+		io_double_put_req(req);
 		return;
 	}
 
-	req->user_data = s->sqe->user_data;
-
 	/*
 	 * If we already have a head request, queue this one for async
 	 * submittal once the head completes. If we don't have a head but
@@ -2502,16 +3013,19 @@ err:
 		}
 
 		s->sqe = sqe_copy;
-		memcpy(&req->submit, s, sizeof(*s));
+		trace_io_uring_link(ctx, req, prev);
 		list_add_tail(&req->list, &prev->link_list);
 	} else if (s->sqe->flags & IOSQE_IO_LINK) {
 		req->flags |= REQ_F_LINK;
 
-		memcpy(&req->submit, s, sizeof(*s));
 		INIT_LIST_HEAD(&req->link_list);
 		*link = req;
+	} else if (READ_ONCE(s->sqe->opcode) == IORING_OP_LINK_TIMEOUT) {
+		/* Only valid as a linked SQE */
+		ret = -EINVAL;
+		goto err_req;
 	} else {
-		io_queue_sqe(ctx, req, s);
+		io_queue_sqe(req);
 	}
 }
 
@@ -2582,7 +3096,7 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
 
 	head = READ_ONCE(sq_array[head & ctx->sq_mask]);
 	if (head < ctx->sq_entries) {
-		s->index = head;
+		s->ring_file = NULL;
 		s->sqe = &ctx->sq_sqes[head];
 		s->sequence = ctx->cached_sq_head;
 		ctx->cached_sq_head++;
@@ -2597,13 +3111,19 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
 }
 
 static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
-			  bool has_user, bool mm_fault)
+			  struct file *ring_file, int ring_fd,
+			  struct mm_struct **mm, bool async)
 {
 	struct io_submit_state state, *statep = NULL;
 	struct io_kiocb *link = NULL;
 	struct io_kiocb *shadow_req = NULL;
-	bool prev_was_link = false;
 	int i, submitted = 0;
+	bool mm_fault = false;
+
+	if (!list_empty(&ctx->cq_overflow_list)) {
+		io_cqring_overflow_flush(ctx, false);
+		return -EBUSY;
+	}
 
 	if (nr > IO_PLUG_THRESHOLD) {
 		io_submit_state_start(&state, ctx, nr);
@@ -2611,23 +3131,31 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
 	}
 
 	for (i = 0; i < nr; i++) {
-		struct sqe_submit s;
+		struct io_kiocb *req;
+		unsigned int sqe_flags;
 
-		if (!io_get_sqring(ctx, &s))
+		req = io_get_req(ctx, statep);
+		if (unlikely(!req)) {
+			if (!submitted)
+				submitted = -EAGAIN;
 			break;
+		}
+		if (!io_get_sqring(ctx, &req->submit)) {
+			__io_free_req(req);
+			break;
+		}
 
-		/*
-		 * If previous wasn't linked and we have a linked command,
-		 * that's the end of the chain. Submit the previous link.
-		 */
-		if (!prev_was_link && link) {
-			io_queue_link_head(ctx, link, &link->submit, shadow_req);
-			link = NULL;
-			shadow_req = NULL;
+		if (io_sqe_needs_user(req->submit.sqe) && !*mm) {
+			mm_fault = mm_fault || !mmget_not_zero(ctx->sqo_mm);
+			if (!mm_fault) {
+				use_mm(ctx->sqo_mm);
+				*mm = ctx->sqo_mm;
+			}
 		}
-		prev_was_link = (s.sqe->flags & IOSQE_IO_LINK) != 0;
 
-		if (link && (s.sqe->flags & IOSQE_IO_DRAIN)) {
+		sqe_flags = req->submit.sqe->flags;
+
+		if (link && (sqe_flags & IOSQE_IO_DRAIN)) {
 			if (!shadow_req) {
 				shadow_req = io_get_req(ctx, NULL);
 				if (unlikely(!shadow_req))
@@ -2635,27 +3163,39 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
 				shadow_req->flags |= (REQ_F_IO_DRAIN | REQ_F_SHADOW_DRAIN);
 				refcount_dec(&shadow_req->refs);
 			}
-			shadow_req->sequence = s.sequence;
+			shadow_req->sequence = req->submit.sequence;
 		}
 
 out:
-		if (unlikely(mm_fault)) {
-			io_cqring_add_event(ctx, s.sqe->user_data,
-						-EFAULT);
-		} else {
-			s.has_user = has_user;
-			s.needs_lock = true;
-			s.needs_fixed_file = true;
-			io_submit_sqe(ctx, &s, statep, &link);
-			submitted++;
+		req->submit.ring_file = ring_file;
+		req->submit.ring_fd = ring_fd;
+		req->submit.has_user = *mm != NULL;
+		req->submit.in_async = async;
+		req->submit.needs_fixed_file = async;
+		trace_io_uring_submit_sqe(ctx, req->submit.sqe->user_data,
+					  true, async);
+		io_submit_sqe(req, statep, &link);
+		submitted++;
+
+		/*
+		 * If previous wasn't linked and we have a linked command,
+		 * that's the end of the chain. Submit the previous link.
+		 */
+		if (!(sqe_flags & IOSQE_IO_LINK) && link) {
+			io_queue_link_head(link, shadow_req);
+			link = NULL;
+			shadow_req = NULL;
 		}
 	}
 
 	if (link)
-		io_queue_link_head(ctx, link, &link->submit, shadow_req);
+		io_queue_link_head(link, shadow_req);
 	if (statep)
 		io_submit_state_end(&state);
 
+	 /* Commit SQ ring head once we've consumed and submitted all SQEs */
+	io_commit_sqring(ctx);
+
 	return submitted;
 }
 
@@ -2667,15 +3207,15 @@ static int io_sq_thread(void *data)
 	DEFINE_WAIT(wait);
 	unsigned inflight;
 	unsigned long timeout;
+	int ret;
 
-	complete(&ctx->sqo_thread_started);
+	complete(&ctx->completions[1]);
 
 	old_fs = get_fs();
 	set_fs(USER_DS);
 
-	timeout = inflight = 0;
+	ret = timeout = inflight = 0;
 	while (!kthread_should_park()) {
-		bool mm_fault = false;
 		unsigned int to_submit;
 
 		if (inflight) {
@@ -2710,13 +3250,21 @@ static int io_sq_thread(void *data)
 		}
 
 		to_submit = io_sqring_entries(ctx);
-		if (!to_submit) {
+
+		/*
+		 * If submit got -EBUSY, flag us as needing the application
+		 * to enter the kernel to reap and flush events.
+		 */
+		if (!to_submit || ret == -EBUSY) {
 			/*
 			 * We're polling. If we're within the defined idle
 			 * period, then let us spin without work before going
-			 * to sleep.
+			 * to sleep. The exception is if we got EBUSY doing
+			 * more IO, we should wait for the application to
+			 * reap events and wake us up.
 			 */
-			if (inflight || !time_after(jiffies, timeout)) {
+			if (inflight ||
+			    (!time_after(jiffies, timeout) && ret != -EBUSY)) {
 				cond_resched();
 				continue;
 			}
@@ -2742,7 +3290,7 @@ static int io_sq_thread(void *data)
 			smp_mb();
 
 			to_submit = io_sqring_entries(ctx);
-			if (!to_submit) {
+			if (!to_submit || ret == -EBUSY) {
 				if (kthread_should_park()) {
 					finish_wait(&ctx->sqo_wait, &wait);
 					break;
@@ -2760,21 +3308,10 @@ static int io_sq_thread(void *data)
 			ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
 		}
 
-		/* Unless all new commands are FIXED regions, grab mm */
-		if (!cur_mm) {
-			mm_fault = !mmget_not_zero(ctx->sqo_mm);
-			if (!mm_fault) {
-				use_mm(ctx->sqo_mm);
-				cur_mm = ctx->sqo_mm;
-			}
-		}
-
 		to_submit = min(to_submit, ctx->sq_entries);
-		inflight += io_submit_sqes(ctx, to_submit, cur_mm != NULL,
-					   mm_fault);
-
-		/* Commit SQ ring head once we've consumed all SQEs */
-		io_commit_sqring(ctx);
+		ret = io_submit_sqes(ctx, to_submit, NULL, -1, &cur_mm, true);
+		if (ret > 0)
+			inflight += ret;
 	}
 
 	set_fs(old_fs);
@@ -2788,65 +3325,6 @@ static int io_sq_thread(void *data)
 	return 0;
 }
 
-static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
-{
-	struct io_submit_state state, *statep = NULL;
-	struct io_kiocb *link = NULL;
-	struct io_kiocb *shadow_req = NULL;
-	bool prev_was_link = false;
-	int i, submit = 0;
-
-	if (to_submit > IO_PLUG_THRESHOLD) {
-		io_submit_state_start(&state, ctx, to_submit);
-		statep = &state;
-	}
-
-	for (i = 0; i < to_submit; i++) {
-		struct sqe_submit s;
-
-		if (!io_get_sqring(ctx, &s))
-			break;
-
-		/*
-		 * If previous wasn't linked and we have a linked command,
-		 * that's the end of the chain. Submit the previous link.
-		 */
-		if (!prev_was_link && link) {
-			io_queue_link_head(ctx, link, &link->submit, shadow_req);
-			link = NULL;
-			shadow_req = NULL;
-		}
-		prev_was_link = (s.sqe->flags & IOSQE_IO_LINK) != 0;
-
-		if (link && (s.sqe->flags & IOSQE_IO_DRAIN)) {
-			if (!shadow_req) {
-				shadow_req = io_get_req(ctx, NULL);
-				if (unlikely(!shadow_req))
-					goto out;
-				shadow_req->flags |= (REQ_F_IO_DRAIN | REQ_F_SHADOW_DRAIN);
-				refcount_dec(&shadow_req->refs);
-			}
-			shadow_req->sequence = s.sequence;
-		}
-
-out:
-		s.has_user = true;
-		s.needs_lock = false;
-		s.needs_fixed_file = false;
-		submit++;
-		io_submit_sqe(ctx, &s, statep, &link);
-	}
-
-	if (link)
-		io_queue_link_head(ctx, link, &link->submit, shadow_req);
-	if (statep)
-		io_submit_state_end(statep);
-
-	io_commit_sqring(ctx);
-
-	return submit;
-}
-
 struct io_wait_queue {
 	struct wait_queue_entry wq;
 	struct io_ring_ctx *ctx;
@@ -2854,7 +3332,7 @@ struct io_wait_queue {
 	unsigned nr_timeouts;
 };
 
-static inline bool io_should_wake(struct io_wait_queue *iowq)
+static inline bool io_should_wake(struct io_wait_queue *iowq, bool noflush)
 {
 	struct io_ring_ctx *ctx = iowq->ctx;
 
@@ -2863,7 +3341,7 @@ static inline bool io_should_wake(struct io_wait_queue *iowq)
 	 * started waiting. For timeouts, we always want to return to userspace,
 	 * regardless of event count.
 	 */
-	return io_cqring_events(ctx->rings) >= iowq->to_wait ||
+	return io_cqring_events(ctx, noflush) >= iowq->to_wait ||
 			atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
 }
 
@@ -2873,7 +3351,8 @@ static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode,
 	struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue,
 							wq);
 
-	if (!io_should_wake(iowq))
+	/* use noflush == true, as we can't safely rely on locking context */
+	if (!io_should_wake(iowq, true))
 		return -1;
 
 	return autoremove_wake_function(curr, mode, wake_flags, key);
@@ -2896,9 +3375,9 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 		.to_wait	= min_events,
 	};
 	struct io_rings *rings = ctx->rings;
-	int ret;
+	int ret = 0;
 
-	if (io_cqring_events(rings) >= min_events)
+	if (io_cqring_events(ctx, false) >= min_events)
 		return 0;
 
 	if (sig) {
@@ -2914,24 +3393,22 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 			return ret;
 	}
 
-	ret = 0;
 	iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts);
+	trace_io_uring_cqring_wait(ctx, min_events);
 	do {
 		prepare_to_wait_exclusive(&ctx->wait, &iowq.wq,
 						TASK_INTERRUPTIBLE);
-		if (io_should_wake(&iowq))
+		if (io_should_wake(&iowq, false))
 			break;
 		schedule();
 		if (signal_pending(current)) {
-			ret = -ERESTARTSYS;
+			ret = -EINTR;
 			break;
 		}
 	} while (1);
 	finish_wait(&ctx->wait, &iowq.wq);
 
-	restore_saved_sigmask_unless(ret == -ERESTARTSYS);
-	if (ret == -ERESTARTSYS)
-		ret = -EINTR;
+	restore_saved_sigmask_unless(ret == -EINTR);
 
 	return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0;
 }
@@ -2949,19 +3426,29 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
 #else
 	int i;
 
-	for (i = 0; i < ctx->nr_user_files; i++)
-		fput(ctx->user_files[i]);
+	for (i = 0; i < ctx->nr_user_files; i++) {
+		struct file *file;
+
+		file = io_file_from_index(ctx, i);
+		if (file)
+			fput(file);
+	}
 #endif
 }
 
 static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 {
-	if (!ctx->user_files)
+	unsigned nr_tables, i;
+
+	if (!ctx->file_table)
 		return -ENXIO;
 
 	__io_sqe_files_unregister(ctx);
-	kfree(ctx->user_files);
-	ctx->user_files = NULL;
+	nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE);
+	for (i = 0; i < nr_tables; i++)
+		kfree(ctx->file_table[i].files);
+	kfree(ctx->file_table);
+	ctx->file_table = NULL;
 	ctx->nr_user_files = 0;
 	return 0;
 }
@@ -2969,7 +3456,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 static void io_sq_thread_stop(struct io_ring_ctx *ctx)
 {
 	if (ctx->sqo_thread) {
-		wait_for_completion(&ctx->sqo_thread_started);
+		wait_for_completion(&ctx->completions[1]);
 		/*
 		 * The park is a bit of a work-around, without it we get
 		 * warning spews on shutdown with SQPOLL set and affinity
@@ -2983,15 +3470,11 @@ static void io_sq_thread_stop(struct io_ring_ctx *ctx)
 
 static void io_finish_async(struct io_ring_ctx *ctx)
 {
-	int i;
-
 	io_sq_thread_stop(ctx);
 
-	for (i = 0; i < ARRAY_SIZE(ctx->sqo_wq); i++) {
-		if (ctx->sqo_wq[i]) {
-			destroy_workqueue(ctx->sqo_wq[i]);
-			ctx->sqo_wq[i] = NULL;
-		}
+	if (ctx->io_wq) {
+		io_wq_destroy(ctx->io_wq);
+		ctx->io_wq = NULL;
 	}
 }
 
@@ -2999,11 +3482,9 @@ static void io_finish_async(struct io_ring_ctx *ctx)
 static void io_destruct_skb(struct sk_buff *skb)
 {
 	struct io_ring_ctx *ctx = skb->sk->sk_user_data;
-	int i;
 
-	for (i = 0; i < ARRAY_SIZE(ctx->sqo_wq); i++)
-		if (ctx->sqo_wq[i])
-			flush_workqueue(ctx->sqo_wq[i]);
+	if (ctx->io_wq)
+		io_wq_flush(ctx->io_wq);
 
 	unix_destruct_scm(skb);
 }
@@ -3018,7 +3499,7 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset)
 	struct sock *sk = ctx->ring_sock->sk;
 	struct scm_fp_list *fpl;
 	struct sk_buff *skb;
-	int i;
+	int i, nr_files;
 
 	if (!capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) {
 		unsigned long inflight = ctx->user->unix_inflight + nr;
@@ -3038,21 +3519,33 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset)
 	}
 
 	skb->sk = sk;
-	skb->destructor = io_destruct_skb;
 
+	nr_files = 0;
 	fpl->user = get_uid(ctx->user);
 	for (i = 0; i < nr; i++) {
-		fpl->fp[i] = get_file(ctx->user_files[i + offset]);
-		unix_inflight(fpl->user, fpl->fp[i]);
+		struct file *file = io_file_from_index(ctx, i + offset);
+
+		if (!file)
+			continue;
+		fpl->fp[nr_files] = get_file(file);
+		unix_inflight(fpl->user, fpl->fp[nr_files]);
+		nr_files++;
 	}
 
-	fpl->max = fpl->count = nr;
-	UNIXCB(skb).fp = fpl;
-	refcount_add(skb->truesize, &sk->sk_wmem_alloc);
-	skb_queue_head(&sk->sk_receive_queue, skb);
+	if (nr_files) {
+		fpl->max = SCM_MAX_FD;
+		fpl->count = nr_files;
+		UNIXCB(skb).fp = fpl;
+		skb->destructor = io_destruct_skb;
+		refcount_add(skb->truesize, &sk->sk_wmem_alloc);
+		skb_queue_head(&sk->sk_receive_queue, skb);
 
-	for (i = 0; i < nr; i++)
-		fput(fpl->fp[i]);
+		for (i = 0; i < nr_files; i++)
+			fput(fpl->fp[i]);
+	} else {
+		kfree_skb(skb);
+		kfree(fpl);
+	}
 
 	return 0;
 }
@@ -3083,7 +3576,10 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx)
 		return 0;
 
 	while (total < ctx->nr_user_files) {
-		fput(ctx->user_files[total]);
+		struct file *file = io_file_from_index(ctx, total);
+
+		if (file)
+			fput(file);
 		total++;
 	}
 
@@ -3096,33 +3592,79 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx)
 }
 #endif
 
+static int io_sqe_alloc_file_tables(struct io_ring_ctx *ctx, unsigned nr_tables,
+				    unsigned nr_files)
+{
+	int i;
+
+	for (i = 0; i < nr_tables; i++) {
+		struct fixed_file_table *table = &ctx->file_table[i];
+		unsigned this_files;
+
+		this_files = min(nr_files, IORING_MAX_FILES_TABLE);
+		table->files = kcalloc(this_files, sizeof(struct file *),
+					GFP_KERNEL);
+		if (!table->files)
+			break;
+		nr_files -= this_files;
+	}
+
+	if (i == nr_tables)
+		return 0;
+
+	for (i = 0; i < nr_tables; i++) {
+		struct fixed_file_table *table = &ctx->file_table[i];
+		kfree(table->files);
+	}
+	return 1;
+}
+
 static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 				 unsigned nr_args)
 {
 	__s32 __user *fds = (__s32 __user *) arg;
+	unsigned nr_tables;
 	int fd, ret = 0;
 	unsigned i;
 
-	if (ctx->user_files)
+	if (ctx->file_table)
 		return -EBUSY;
 	if (!nr_args)
 		return -EINVAL;
 	if (nr_args > IORING_MAX_FIXED_FILES)
 		return -EMFILE;
 
-	ctx->user_files = kcalloc(nr_args, sizeof(struct file *), GFP_KERNEL);
-	if (!ctx->user_files)
+	nr_tables = DIV_ROUND_UP(nr_args, IORING_MAX_FILES_TABLE);
+	ctx->file_table = kcalloc(nr_tables, sizeof(struct fixed_file_table),
+					GFP_KERNEL);
+	if (!ctx->file_table)
 		return -ENOMEM;
 
-	for (i = 0; i < nr_args; i++) {
+	if (io_sqe_alloc_file_tables(ctx, nr_tables, nr_args)) {
+		kfree(ctx->file_table);
+		ctx->file_table = NULL;
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < nr_args; i++, ctx->nr_user_files++) {
+		struct fixed_file_table *table;
+		unsigned index;
+
 		ret = -EFAULT;
 		if (copy_from_user(&fd, &fds[i], sizeof(fd)))
 			break;
+		/* allow sparse sets */
+		if (fd == -1) {
+			ret = 0;
+			continue;
+		}
 
-		ctx->user_files[i] = fget(fd);
+		table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT];
+		index = i & IORING_FILE_TABLE_MASK;
+		table->files[index] = fget(fd);
 
 		ret = -EBADF;
-		if (!ctx->user_files[i])
+		if (!table->files[index])
 			break;
 		/*
 		 * Don't allow io_uring instances to be registered. If UNIX
@@ -3131,20 +3673,26 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 		 * handle it just fine, but there's still no point in allowing
 		 * a ring fd as it doesn't support regular read/write anyway.
 		 */
-		if (ctx->user_files[i]->f_op == &io_uring_fops) {
-			fput(ctx->user_files[i]);
+		if (table->files[index]->f_op == &io_uring_fops) {
+			fput(table->files[index]);
 			break;
 		}
-		ctx->nr_user_files++;
 		ret = 0;
 	}
 
 	if (ret) {
-		for (i = 0; i < ctx->nr_user_files; i++)
-			fput(ctx->user_files[i]);
+		for (i = 0; i < ctx->nr_user_files; i++) {
+			struct file *file;
 
-		kfree(ctx->user_files);
-		ctx->user_files = NULL;
+			file = io_file_from_index(ctx, i);
+			if (file)
+				fput(file);
+		}
+		for (i = 0; i < nr_tables; i++)
+			kfree(ctx->file_table[i].files);
+
+		kfree(ctx->file_table);
+		ctx->file_table = NULL;
 		ctx->nr_user_files = 0;
 		return ret;
 	}
@@ -3156,9 +3704,201 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 	return ret;
 }
 
+static void io_sqe_file_unregister(struct io_ring_ctx *ctx, int index)
+{
+#if defined(CONFIG_UNIX)
+	struct file *file = io_file_from_index(ctx, index);
+	struct sock *sock = ctx->ring_sock->sk;
+	struct sk_buff_head list, *head = &sock->sk_receive_queue;
+	struct sk_buff *skb;
+	int i;
+
+	__skb_queue_head_init(&list);
+
+	/*
+	 * Find the skb that holds this file in its SCM_RIGHTS. When found,
+	 * remove this entry and rearrange the file array.
+	 */
+	skb = skb_dequeue(head);
+	while (skb) {
+		struct scm_fp_list *fp;
+
+		fp = UNIXCB(skb).fp;
+		for (i = 0; i < fp->count; i++) {
+			int left;
+
+			if (fp->fp[i] != file)
+				continue;
+
+			unix_notinflight(fp->user, fp->fp[i]);
+			left = fp->count - 1 - i;
+			if (left) {
+				memmove(&fp->fp[i], &fp->fp[i + 1],
+						left * sizeof(struct file *));
+			}
+			fp->count--;
+			if (!fp->count) {
+				kfree_skb(skb);
+				skb = NULL;
+			} else {
+				__skb_queue_tail(&list, skb);
+			}
+			fput(file);
+			file = NULL;
+			break;
+		}
+
+		if (!file)
+			break;
+
+		__skb_queue_tail(&list, skb);
+
+		skb = skb_dequeue(head);
+	}
+
+	if (skb_peek(&list)) {
+		spin_lock_irq(&head->lock);
+		while ((skb = __skb_dequeue(&list)) != NULL)
+			__skb_queue_tail(head, skb);
+		spin_unlock_irq(&head->lock);
+	}
+#else
+	fput(io_file_from_index(ctx, index));
+#endif
+}
+
+static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file,
+				int index)
+{
+#if defined(CONFIG_UNIX)
+	struct sock *sock = ctx->ring_sock->sk;
+	struct sk_buff_head *head = &sock->sk_receive_queue;
+	struct sk_buff *skb;
+
+	/*
+	 * See if we can merge this file into an existing skb SCM_RIGHTS
+	 * file set. If there's no room, fall back to allocating a new skb
+	 * and filling it in.
+	 */
+	spin_lock_irq(&head->lock);
+	skb = skb_peek(head);
+	if (skb) {
+		struct scm_fp_list *fpl = UNIXCB(skb).fp;
+
+		if (fpl->count < SCM_MAX_FD) {
+			__skb_unlink(skb, head);
+			spin_unlock_irq(&head->lock);
+			fpl->fp[fpl->count] = get_file(file);
+			unix_inflight(fpl->user, fpl->fp[fpl->count]);
+			fpl->count++;
+			spin_lock_irq(&head->lock);
+			__skb_queue_head(head, skb);
+		} else {
+			skb = NULL;
+		}
+	}
+	spin_unlock_irq(&head->lock);
+
+	if (skb) {
+		fput(file);
+		return 0;
+	}
+
+	return __io_sqe_files_scm(ctx, 1, index);
+#else
+	return 0;
+#endif
+}
+
+static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
+			       unsigned nr_args)
+{
+	struct io_uring_files_update up;
+	__s32 __user *fds;
+	int fd, i, err;
+	__u32 done;
+
+	if (!ctx->file_table)
+		return -ENXIO;
+	if (!nr_args)
+		return -EINVAL;
+	if (copy_from_user(&up, arg, sizeof(up)))
+		return -EFAULT;
+	if (check_add_overflow(up.offset, nr_args, &done))
+		return -EOVERFLOW;
+	if (done > ctx->nr_user_files)
+		return -EINVAL;
+
+	done = 0;
+	fds = (__s32 __user *) up.fds;
+	while (nr_args) {
+		struct fixed_file_table *table;
+		unsigned index;
+
+		err = 0;
+		if (copy_from_user(&fd, &fds[done], sizeof(fd))) {
+			err = -EFAULT;
+			break;
+		}
+		i = array_index_nospec(up.offset, ctx->nr_user_files);
+		table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT];
+		index = i & IORING_FILE_TABLE_MASK;
+		if (table->files[index]) {
+			io_sqe_file_unregister(ctx, i);
+			table->files[index] = NULL;
+		}
+		if (fd != -1) {
+			struct file *file;
+
+			file = fget(fd);
+			if (!file) {
+				err = -EBADF;
+				break;
+			}
+			/*
+			 * Don't allow io_uring instances to be registered. If
+			 * UNIX isn't enabled, then this causes a reference
+			 * cycle and this instance can never get freed. If UNIX
+			 * is enabled we'll handle it just fine, but there's
+			 * still no point in allowing a ring fd as it doesn't
+			 * support regular read/write anyway.
+			 */
+			if (file->f_op == &io_uring_fops) {
+				fput(file);
+				err = -EBADF;
+				break;
+			}
+			table->files[index] = file;
+			err = io_sqe_file_register(ctx, file, i);
+			if (err)
+				break;
+		}
+		nr_args--;
+		done++;
+		up.offset++;
+	}
+
+	return done ? done : err;
+}
+
+static void io_put_work(struct io_wq_work *work)
+{
+	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+
+	io_put_req(req);
+}
+
+static void io_get_work(struct io_wq_work *work)
+{
+	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+
+	refcount_inc(&req->refs);
+}
+
 static int io_sq_offload_start(struct io_ring_ctx *ctx,
 			       struct io_uring_params *p)
 {
+	unsigned concurrency;
 	int ret;
 
 	init_waitqueue_head(&ctx->sqo_wait);
@@ -3202,26 +3942,13 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 		goto err;
 	}
 
-	/* Do QD, or 2 * CPUS, whatever is smallest */
-	ctx->sqo_wq[0] = alloc_workqueue("io_ring-wq",
-			WQ_UNBOUND | WQ_FREEZABLE,
-			min(ctx->sq_entries - 1, 2 * num_online_cpus()));
-	if (!ctx->sqo_wq[0]) {
-		ret = -ENOMEM;
-		goto err;
-	}
-
-	/*
-	 * This is for buffered writes, where we want to limit the parallelism
-	 * due to file locking in file systems. As "normal" buffered writes
-	 * should parellelize on writeout quite nicely, limit us to having 2
-	 * pending. This avoids massive contention on the inode when doing
-	 * buffered async writes.
-	 */
-	ctx->sqo_wq[1] = alloc_workqueue("io_ring-write-wq",
-						WQ_UNBOUND | WQ_FREEZABLE, 2);
-	if (!ctx->sqo_wq[1]) {
-		ret = -ENOMEM;
+	/* Do QD, or 4 * CPUS, whatever is smallest */
+	concurrency = min(ctx->sq_entries, 4 * num_online_cpus());
+	ctx->io_wq = io_wq_create(concurrency, ctx->sqo_mm, ctx->user,
+					io_get_work, io_put_work);
+	if (IS_ERR(ctx->io_wq)) {
+		ret = PTR_ERR(ctx->io_wq);
+		ctx->io_wq = NULL;
 		goto err;
 	}
 
@@ -3567,6 +4294,8 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
 		io_unaccount_mem(ctx->user,
 				ring_pages(ctx->sq_entries, ctx->cq_entries));
 	free_uid(ctx->user);
+	kfree(ctx->completions);
+	kmem_cache_free(req_cachep, ctx->fallback_req);
 	kfree(ctx);
 }
 
@@ -3605,8 +4334,15 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 
 	io_kill_timeouts(ctx);
 	io_poll_remove_all(ctx);
+
+	if (ctx->io_wq)
+		io_wq_cancel_all(ctx->io_wq);
+
 	io_iopoll_reap_events(ctx);
-	wait_for_completion(&ctx->ctx_done);
+	/* if we failed setting up the ctx, we might not have any rings */
+	if (ctx->rings)
+		io_cqring_overflow_flush(ctx, true);
+	wait_for_completion(&ctx->completions[0]);
 	io_ring_ctx_free(ctx);
 }
 
@@ -3619,6 +4355,53 @@ static int io_uring_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
+static void io_uring_cancel_files(struct io_ring_ctx *ctx,
+				  struct files_struct *files)
+{
+	struct io_kiocb *req;
+	DEFINE_WAIT(wait);
+
+	while (!list_empty_careful(&ctx->inflight_list)) {
+		struct io_kiocb *cancel_req = NULL;
+
+		spin_lock_irq(&ctx->inflight_lock);
+		list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
+			if (req->work.files != files)
+				continue;
+			/* req is being completed, ignore */
+			if (!refcount_inc_not_zero(&req->refs))
+				continue;
+			cancel_req = req;
+			break;
+		}
+		if (cancel_req)
+			prepare_to_wait(&ctx->inflight_wait, &wait,
+						TASK_UNINTERRUPTIBLE);
+		spin_unlock_irq(&ctx->inflight_lock);
+
+		/* We need to keep going until we don't find a matching req */
+		if (!cancel_req)
+			break;
+
+		io_wq_cancel_work(ctx->io_wq, &cancel_req->work);
+		io_put_req(cancel_req);
+		schedule();
+	}
+	finish_wait(&ctx->inflight_wait, &wait);
+}
+
+static int io_uring_flush(struct file *file, void *data)
+{
+	struct io_ring_ctx *ctx = file->private_data;
+
+	io_uring_cancel_files(ctx, data);
+	if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) {
+		io_cqring_overflow_flush(ctx, true);
+		io_wq_cancel_all(ctx->io_wq);
+	}
+	return 0;
+}
+
 static int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	loff_t offset = (loff_t) vma->vm_pgoff << PAGE_SHIFT;
@@ -3680,14 +4463,20 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 	 */
 	ret = 0;
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
+		if (!list_empty_careful(&ctx->cq_overflow_list))
+			io_cqring_overflow_flush(ctx, false);
 		if (flags & IORING_ENTER_SQ_WAKEUP)
 			wake_up(&ctx->sqo_wait);
 		submitted = to_submit;
 	} else if (to_submit) {
-		to_submit = min(to_submit, ctx->sq_entries);
+		struct mm_struct *cur_mm;
 
+		to_submit = min(to_submit, ctx->sq_entries);
 		mutex_lock(&ctx->uring_lock);
-		submitted = io_ring_submit(ctx, to_submit);
+		/* already have mm, so io_submit_sqes() won't try to grab it */
+		cur_mm = ctx->sqo_mm;
+		submitted = io_submit_sqes(ctx, to_submit, f.file, fd,
+					   &cur_mm, false);
 		mutex_unlock(&ctx->uring_lock);
 	}
 	if (flags & IORING_ENTER_GETEVENTS) {
@@ -3710,6 +4499,7 @@ out_fput:
 
 static const struct file_operations io_uring_fops = {
 	.release	= io_uring_release,
+	.flush		= io_uring_flush,
 	.mmap		= io_uring_mmap,
 	.poll		= io_uring_poll,
 	.fasync		= io_uring_fasync,
@@ -3809,10 +4599,23 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 	 * Use twice as many entries for the CQ ring. It's possible for the
 	 * application to drive a higher depth than the size of the SQ ring,
 	 * since the sqes are only used at submission time. This allows for
-	 * some flexibility in overcommitting a bit.
+	 * some flexibility in overcommitting a bit. If the application has
+	 * set IORING_SETUP_CQSIZE, it will have passed in the desired number
+	 * of CQ ring entries manually.
 	 */
 	p->sq_entries = roundup_pow_of_two(entries);
-	p->cq_entries = 2 * p->sq_entries;
+	if (p->flags & IORING_SETUP_CQSIZE) {
+		/*
+		 * If IORING_SETUP_CQSIZE is set, we do the same roundup
+		 * to a power-of-two, if it isn't already. We do NOT impose
+		 * any cq vs sq ring sizing.
+		 */
+		if (p->cq_entries < p->sq_entries || p->cq_entries > IORING_MAX_CQ_ENTRIES)
+			return -EINVAL;
+		p->cq_entries = roundup_pow_of_two(p->cq_entries);
+	} else {
+		p->cq_entries = 2 * p->sq_entries;
+	}
 
 	user = get_uid(current_user());
 	account_mem = !capable(CAP_IPC_LOCK);
@@ -3871,7 +4674,8 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 	if (ret < 0)
 		goto err;
 
-	p->features = IORING_FEAT_SINGLE_MMAP;
+	p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP;
+	trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
 	return ret;
 err:
 	io_ring_ctx_wait_and_kill(ctx);
@@ -3897,7 +4701,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 	}
 
 	if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL |
-			IORING_SETUP_SQ_AFF))
+			IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE))
 		return -EINVAL;
 
 	ret = io_uring_create(entries, &p);
@@ -3941,7 +4745,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 	 * no new references will come in after we've killed the percpu ref.
 	 */
 	mutex_unlock(&ctx->uring_lock);
-	wait_for_completion(&ctx->ctx_done);
+	wait_for_completion(&ctx->completions[0]);
 	mutex_lock(&ctx->uring_lock);
 
 	switch (opcode) {
@@ -3963,6 +4767,9 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_sqe_files_unregister(ctx);
 		break;
+	case IORING_REGISTER_FILES_UPDATE:
+		ret = io_sqe_files_update(ctx, arg, nr_args);
+		break;
 	case IORING_REGISTER_EVENTFD:
 		ret = -EINVAL;
 		if (nr_args != 1)
@@ -3981,7 +4788,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 	}
 
 	/* bring the ctx back to life */
-	reinit_completion(&ctx->ctx_done);
+	reinit_completion(&ctx->completions[0]);
 	percpu_ref_reinit(&ctx->refs);
 	return ret;
 }
@@ -4006,6 +4813,8 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
 	mutex_lock(&ctx->uring_lock);
 	ret = __io_uring_register(ctx, opcode, arg, nr_args);
 	mutex_unlock(&ctx->uring_lock);
+	trace_io_uring_register(ctx, opcode, ctx->nr_user_files, ctx->nr_user_bufs,
+							ctx->cq_ev_fd != NULL, ret);
 out_fput:
 	fdput(f);
 	return ret;
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 6ebae6bbe6a5..b2d9f79c4a7c 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -508,10 +508,6 @@ void kernfs_put(struct kernfs_node *kn)
 	struct kernfs_node *parent;
 	struct kernfs_root *root;
 
-	/*
-	 * kernfs_node is freed with ->count 0, kernfs_find_and_get_node_by_ino
-	 * depends on this to filter reused stale node
-	 */
 	if (!kn || !atomic_dec_and_test(&kn->count))
 		return;
 	root = kernfs_root(kn);
@@ -536,7 +532,7 @@ void kernfs_put(struct kernfs_node *kn)
 		kmem_cache_free(kernfs_iattrs_cache, kn->iattr);
 	}
 	spin_lock(&kernfs_idr_lock);
-	idr_remove(&root->ino_idr, kn->id.ino);
+	idr_remove(&root->ino_idr, (u32)kernfs_ino(kn));
 	spin_unlock(&kernfs_idr_lock);
 	kmem_cache_free(kernfs_node_cache, kn);
 
@@ -621,8 +617,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 					     unsigned flags)
 {
 	struct kernfs_node *kn;
-	u32 gen;
-	int cursor;
+	u32 id_highbits;
 	int ret;
 
 	name = kstrdup_const(name, GFP_KERNEL);
@@ -635,23 +630,19 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 
 	idr_preload(GFP_KERNEL);
 	spin_lock(&kernfs_idr_lock);
-	cursor = idr_get_cursor(&root->ino_idr);
 	ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC);
-	if (ret >= 0 && ret < cursor)
-		root->next_generation++;
-	gen = root->next_generation;
+	if (ret >= 0 && ret < root->last_id_lowbits)
+		root->id_highbits++;
+	id_highbits = root->id_highbits;
+	root->last_id_lowbits = ret;
 	spin_unlock(&kernfs_idr_lock);
 	idr_preload_end();
 	if (ret < 0)
 		goto err_out2;
-	kn->id.ino = ret;
-	kn->id.generation = gen;
 
-	/*
-	 * set ino first. This RELEASE is paired with atomic_inc_not_zero in
-	 * kernfs_find_and_get_node_by_ino
-	 */
-	atomic_set_release(&kn->count, 1);
+	kn->id = (u64)id_highbits << 32 | ret;
+
+	atomic_set(&kn->count, 1);
 	atomic_set(&kn->active, KN_DEACTIVATED_BIAS);
 	RB_CLEAR_NODE(&kn->rb);
 
@@ -680,7 +671,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 	return kn;
 
  err_out3:
-	idr_remove(&root->ino_idr, kn->id.ino);
+	idr_remove(&root->ino_idr, (u32)kernfs_ino(kn));
  err_out2:
 	kmem_cache_free(kernfs_node_cache, kn);
  err_out1:
@@ -705,50 +696,52 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 }
 
 /*
- * kernfs_find_and_get_node_by_ino - get kernfs_node from inode number
+ * kernfs_find_and_get_node_by_id - get kernfs_node from node id
  * @root: the kernfs root
- * @ino: inode number
+ * @id: the target node id
+ *
+ * @id's lower 32bits encode ino and upper gen.  If the gen portion is
+ * zero, all generations are matched.
  *
  * RETURNS:
  * NULL on failure. Return a kernfs node with reference counter incremented
  */
-struct kernfs_node *kernfs_find_and_get_node_by_ino(struct kernfs_root *root,
-						    unsigned int ino)
+struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root,
+						   u64 id)
 {
 	struct kernfs_node *kn;
+	ino_t ino = kernfs_id_ino(id);
+	u32 gen = kernfs_id_gen(id);
 
-	rcu_read_lock();
-	kn = idr_find(&root->ino_idr, ino);
+	spin_lock(&kernfs_idr_lock);
+
+	kn = idr_find(&root->ino_idr, (u32)ino);
 	if (!kn)
-		goto out;
+		goto err_unlock;
 
-	/*
-	 * Since kernfs_node is freed in RCU, it's possible an old node for ino
-	 * is freed, but reused before RCU grace period. But a freed node (see
-	 * kernfs_put) or an incompletedly initialized node (see
-	 * __kernfs_new_node) should have 'count' 0. We can use this fact to
-	 * filter out such node.
-	 */
-	if (!atomic_inc_not_zero(&kn->count)) {
-		kn = NULL;
-		goto out;
+	if (sizeof(ino_t) >= sizeof(u64)) {
+		/* we looked up with the low 32bits, compare the whole */
+		if (kernfs_ino(kn) != ino)
+			goto err_unlock;
+	} else {
+		/* 0 matches all generations */
+		if (unlikely(gen && kernfs_gen(kn) != gen))
+			goto err_unlock;
 	}
 
 	/*
-	 * The node could be a new node or a reused node. If it's a new node,
-	 * we are ok. If it's reused because of RCU (because of
-	 * SLAB_TYPESAFE_BY_RCU), the __kernfs_new_node always sets its 'ino'
-	 * before 'count'. So if 'count' is uptodate, 'ino' should be uptodate,
-	 * hence we can use 'ino' to filter stale node.
+	 * ACTIVATED is protected with kernfs_mutex but it was clear when
+	 * @kn was added to idr and we just wanna see it set.  No need to
+	 * grab kernfs_mutex.
 	 */
-	if (kn->id.ino != ino)
-		goto out;
-	rcu_read_unlock();
+	if (unlikely(!(kn->flags & KERNFS_ACTIVATED) ||
+		     !atomic_inc_not_zero(&kn->count)))
+		goto err_unlock;
 
+	spin_unlock(&kernfs_idr_lock);
 	return kn;
-out:
-	rcu_read_unlock();
-	kernfs_put(kn);
+err_unlock:
+	spin_unlock(&kernfs_idr_lock);
 	return NULL;
 }
 
@@ -962,7 +955,17 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
 
 	idr_init(&root->ino_idr);
 	INIT_LIST_HEAD(&root->supers);
-	root->next_generation = 1;
+
+	/*
+	 * On 64bit ino setups, id is ino.  On 32bit, low 32bits are ino.
+	 * High bits generation.  The starting value for both ino and
+	 * genenration is 1.  Initialize upper 32bit allocation
+	 * accordingly.
+	 */
+	if (sizeof(ino_t) >= sizeof(u64))
+		root->id_highbits = 0;
+	else
+		root->id_highbits = 1;
 
 	kn = __kernfs_new_node(root, NULL, "", S_IFDIR | S_IRUGO | S_IXUGO,
 			       GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
@@ -1678,7 +1681,7 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx)
 		const char *name = pos->name;
 		unsigned int type = dt_type(pos);
 		int len = strlen(name);
-		ino_t ino = pos->id.ino;
+		ino_t ino = kernfs_ino(pos);
 
 		ctx->pos = pos->hash;
 		file->private_data = pos;
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index e8c792b49616..34366db3620d 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -892,7 +892,7 @@ repeat:
 		 * have the matching @file available.  Look up the inodes
 		 * and generate the events manually.
 		 */
-		inode = ilookup(info->sb, kn->id.ino);
+		inode = ilookup(info->sb, kernfs_ino(kn));
 		if (!inode)
 			continue;
 
@@ -901,7 +901,7 @@ repeat:
 		if (parent) {
 			struct inode *p_inode;
 
-			p_inode = ilookup(info->sb, parent->id.ino);
+			p_inode = ilookup(info->sb, kernfs_ino(parent));
 			if (p_inode) {
 				fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD,
 					 inode, FSNOTIFY_EVENT_INODE, &name, 0);
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index f3eaa8869f42..eac277c63d42 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -201,7 +201,7 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
 	inode->i_private = kn;
 	inode->i_mapping->a_ops = &kernfs_aops;
 	inode->i_op = &kernfs_iops;
-	inode->i_generation = kn->id.generation;
+	inode->i_generation = kernfs_gen(kn);
 
 	set_default_inode_attr(inode, kn->mode);
 	kernfs_refresh_inode(kn, inode);
@@ -247,7 +247,7 @@ struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn)
 {
 	struct inode *inode;
 
-	inode = iget_locked(sb, kn->id.ino);
+	inode = iget_locked(sb, kernfs_ino(kn));
 	if (inode && (inode->i_state & I_NEW))
 		kernfs_init_inode(kn, inode);
 
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 02ce570a9a3c..2f3c51d55261 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -109,8 +109,6 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 				    const char *name, umode_t mode,
 				    kuid_t uid, kgid_t gid,
 				    unsigned flags);
-struct kernfs_node *kernfs_find_and_get_node_by_ino(struct kernfs_root *root,
-						    unsigned int ino);
 
 /*
  * file.c
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 6c12fac2c287..4d31503abaee 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -53,63 +53,85 @@ const struct super_operations kernfs_sops = {
 	.show_path	= kernfs_sop_show_path,
 };
 
-/*
- * Similar to kernfs_fh_get_inode, this one gets kernfs node from inode
- * number and generation
- */
-struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root,
-	const union kernfs_node_id *id)
+static int kernfs_encode_fh(struct inode *inode, __u32 *fh, int *max_len,
+			    struct inode *parent)
 {
-	struct kernfs_node *kn;
+	struct kernfs_node *kn = inode->i_private;
 
-	kn = kernfs_find_and_get_node_by_ino(root, id->ino);
-	if (!kn)
-		return NULL;
-	if (kn->id.generation != id->generation) {
-		kernfs_put(kn);
-		return NULL;
+	if (*max_len < 2) {
+		*max_len = 2;
+		return FILEID_INVALID;
 	}
-	return kn;
+
+	*max_len = 2;
+	*(u64 *)fh = kn->id;
+	return FILEID_KERNFS;
 }
 
-static struct inode *kernfs_fh_get_inode(struct super_block *sb,
-		u64 ino, u32 generation)
+static struct dentry *__kernfs_fh_to_dentry(struct super_block *sb,
+					    struct fid *fid, int fh_len,
+					    int fh_type, bool get_parent)
 {
 	struct kernfs_super_info *info = kernfs_info(sb);
-	struct inode *inode;
 	struct kernfs_node *kn;
+	struct inode *inode;
+	u64 id;
 
-	if (ino == 0)
-		return ERR_PTR(-ESTALE);
+	if (fh_len < 2)
+		return NULL;
+
+	switch (fh_type) {
+	case FILEID_KERNFS:
+		id = *(u64 *)fid;
+		break;
+	case FILEID_INO32_GEN:
+	case FILEID_INO32_GEN_PARENT:
+		/*
+		 * blk_log_action() exposes "LOW32,HIGH32" pair without
+		 * type and userland can call us with generic fid
+		 * constructed from them.  Combine it back to ID.  See
+		 * blk_log_action().
+		 */
+		id = ((u64)fid->i32.gen << 32) | fid->i32.ino;
+		break;
+	default:
+		return NULL;
+	}
 
-	kn = kernfs_find_and_get_node_by_ino(info->root, ino);
+	kn = kernfs_find_and_get_node_by_id(info->root, id);
 	if (!kn)
 		return ERR_PTR(-ESTALE);
+
+	if (get_parent) {
+		struct kernfs_node *parent;
+
+		parent = kernfs_get_parent(kn);
+		kernfs_put(kn);
+		kn = parent;
+		if (!kn)
+			return ERR_PTR(-ESTALE);
+	}
+
 	inode = kernfs_get_inode(sb, kn);
 	kernfs_put(kn);
 	if (!inode)
 		return ERR_PTR(-ESTALE);
 
-	if (generation && inode->i_generation != generation) {
-		/* we didn't find the right inode.. */
-		iput(inode);
-		return ERR_PTR(-ESTALE);
-	}
-	return inode;
+	return d_obtain_alias(inode);
 }
 
-static struct dentry *kernfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type)
+static struct dentry *kernfs_fh_to_dentry(struct super_block *sb,
+					  struct fid *fid, int fh_len,
+					  int fh_type)
 {
-	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
-				    kernfs_fh_get_inode);
+	return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, false);
 }
 
-static struct dentry *kernfs_fh_to_parent(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type)
+static struct dentry *kernfs_fh_to_parent(struct super_block *sb,
+					  struct fid *fid, int fh_len,
+					  int fh_type)
 {
-	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
-				    kernfs_fh_get_inode);
+	return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, true);
 }
 
 static struct dentry *kernfs_get_parent_dentry(struct dentry *child)
@@ -120,6 +142,7 @@ static struct dentry *kernfs_get_parent_dentry(struct dentry *child)
 }
 
 static const struct export_operations kernfs_export_ops = {
+	.encode_fh	= kernfs_encode_fh,
 	.fh_to_dentry	= kernfs_fh_to_dentry,
 	.fh_to_parent	= kernfs_fh_to_parent,
 	.get_parent	= kernfs_get_parent_dentry,
@@ -363,18 +386,9 @@ void kernfs_kill_sb(struct super_block *sb)
 
 void __init kernfs_init(void)
 {
-
-	/*
-	 * the slab is freed in RCU context, so kernfs_find_and_get_node_by_ino
-	 * can access the slab lock free. This could introduce stale nodes,
-	 * please see how kernfs_find_and_get_node_by_ino filters out stale
-	 * nodes.
-	 */
 	kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
 					      sizeof(struct kernfs_node),
-					      0,
-					      SLAB_PANIC | SLAB_TYPESAFE_BY_RCU,
-					      NULL);
+					      0, SLAB_PANIC, NULL);
 
 	/* Creates slab cache for kernfs inode attributes */
 	kernfs_iattrs_cache  = kmem_cache_create("kernfs_iattrs_cache",
diff --git a/fs/open.c b/fs/open.c
index b62f5c0923a8..5c68282ea79e 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -771,10 +771,6 @@ static int do_dentry_open(struct file *f,
 		f->f_mode |= FMODE_WRITER;
 	}
 
-	/* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
-	if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))
-		f->f_mode |= FMODE_ATOMIC_POS;
-
 	f->f_op = fops_get(inode->i_fop);
 	if (WARN_ON(!f->f_op)) {
 		error = -ENODEV;
@@ -1256,7 +1252,7 @@ EXPORT_SYMBOL(nonseekable_open);
  */
 int stream_open(struct inode *inode, struct file *filp)
 {
-	filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS);
+	filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
 	filp->f_mode |= FMODE_STREAM;
 	return 0;
 }
diff --git a/fs/pipe.c b/fs/pipe.c
index 8a2ab2f974bd..a9149199e0e7 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -793,6 +793,8 @@ int create_pipe_files(struct file **res, int flags)
 	}
 	res[0]->private_data = inode->i_pipe;
 	res[1] = f;
+	stream_open(inode, res[0]);
+	stream_open(inode, res[1]);
 	return 0;
 }
 
@@ -931,9 +933,9 @@ static int fifo_open(struct inode *inode, struct file *filp)
 	__pipe_lock(pipe);
 
 	/* We can only do regular read/write on fifos */
-	filp->f_mode &= (FMODE_READ | FMODE_WRITE);
+	stream_open(inode, filp);
 
-	switch (filp->f_mode) {
+	switch (filp->f_mode & (FMODE_READ | FMODE_WRITE)) {
 	case FMODE_READ:
 	/*
 	 *  O_RDONLY
diff --git a/include/Kbuild b/include/Kbuild
index ffba79483cc5..25edc43483e0 100644
--- a/include/Kbuild
+++ b/include/Kbuild
@@ -65,8 +65,9 @@ header-test-			+= keys/asymmetric-subtype.h
 header-test-			+= keys/asymmetric-type.h
 header-test-			+= keys/big_key-type.h
 header-test-			+= keys/request_key_auth-type.h
-header-test-			+= keys/trusted.h
 header-test-			+= kvm/arm_arch_timer.h
+header-test-$(CONFIG_ARM)	+= kvm/arm_hypercalls.h
+header-test-$(CONFIG_ARM64)	+= kvm/arm_hypercalls.h
 header-test-			+= kvm/arm_pmu.h
 header-test-$(CONFIG_ARM)	+= kvm/arm_psci.h
 header-test-$(CONFIG_ARM64)	+= kvm/arm_psci.h
@@ -1028,6 +1029,7 @@ header-test-			+= trace/events/fsi_master_gpio.h
 header-test-			+= trace/events/huge_memory.h
 header-test-			+= trace/events/ib_mad.h
 header-test-			+= trace/events/ib_umad.h
+header-test-			+= trace/events/io_uring.h
 header-test-			+= trace/events/iscsi.h
 header-test-			+= trace/events/jbd2.h
 header-test-			+= trace/events/kvm.h
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index dae64600ccbf..a9c4e4721434 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -110,17 +110,17 @@
 #endif
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
-#ifdef CC_USING_PATCHABLE_FUNCTION_ENTRY
-#define MCOUNT_REC()	. = ALIGN(8);				\
-			__start_mcount_loc = .;			\
-			KEEP(*(__patchable_function_entries))	\
-			__stop_mcount_loc = .;
-#else
+/*
+ * The ftrace call sites are logged to a section whose name depends on the
+ * compiler option used. A given kernel image will only use one, AKA
+ * FTRACE_CALLSITE_SECTION. We capture all of them here to avoid header
+ * dependencies for FTRACE_CALLSITE_SECTION's definition.
+ */
 #define MCOUNT_REC()	. = ALIGN(8);				\
 			__start_mcount_loc = .;			\
 			KEEP(*(__mcount_loc))			\
+			KEEP(*(__patchable_function_entries))	\
 			__stop_mcount_loc = .;
-#endif
 #else
 #define MCOUNT_REC()
 #endif
diff --git a/include/crypto/aead.h b/include/crypto/aead.h
index 3c245b1859e7..a3bdadf6221e 100644
--- a/include/crypto/aead.h
+++ b/include/crypto/aead.h
@@ -321,7 +321,7 @@ int crypto_aead_encrypt(struct aead_request *req);
 
 /**
  * crypto_aead_decrypt() - decrypt ciphertext
- * @req: reference to the ablkcipher_request handle that holds all information
+ * @req: reference to the aead_request handle that holds all information
  *	 needed to perform the cipher operation
  *
  * Decrypt ciphertext data using the aead_request handle. That data structure
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index e5bd302f2c49..5cd846defdd6 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -85,56 +85,6 @@ struct scatter_walk {
 	unsigned int offset;
 };
 
-struct blkcipher_walk {
-	union {
-		struct {
-			struct page *page;
-			unsigned long offset;
-		} phys;
-
-		struct {
-			u8 *page;
-			u8 *addr;
-		} virt;
-	} src, dst;
-
-	struct scatter_walk in;
-	unsigned int nbytes;
-
-	struct scatter_walk out;
-	unsigned int total;
-
-	void *page;
-	u8 *buffer;
-	u8 *iv;
-	unsigned int ivsize;
-
-	int flags;
-	unsigned int walk_blocksize;
-	unsigned int cipher_blocksize;
-	unsigned int alignmask;
-};
-
-struct ablkcipher_walk {
-	struct {
-		struct page *page;
-		unsigned int offset;
-	} src, dst;
-
-	struct scatter_walk	in;
-	unsigned int		nbytes;
-	struct scatter_walk	out;
-	unsigned int		total;
-	struct list_head	buffers;
-	u8			*iv_buffer;
-	u8			*iv;
-	int			flags;
-	unsigned int		blocksize;
-};
-
-extern const struct crypto_type crypto_ablkcipher_type;
-extern const struct crypto_type crypto_blkcipher_type;
-
 void crypto_mod_put(struct crypto_alg *alg);
 
 int crypto_register_template(struct crypto_template *tmpl);
@@ -233,26 +183,6 @@ static inline void crypto_xor_cpy(u8 *dst, const u8 *src1, const u8 *src2,
 	}
 }
 
-int blkcipher_walk_done(struct blkcipher_desc *desc,
-			struct blkcipher_walk *walk, int err);
-int blkcipher_walk_virt(struct blkcipher_desc *desc,
-			struct blkcipher_walk *walk);
-int blkcipher_walk_phys(struct blkcipher_desc *desc,
-			struct blkcipher_walk *walk);
-int blkcipher_walk_virt_block(struct blkcipher_desc *desc,
-			      struct blkcipher_walk *walk,
-			      unsigned int blocksize);
-int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc,
-				   struct blkcipher_walk *walk,
-				   struct crypto_aead *tfm,
-				   unsigned int blocksize);
-
-int ablkcipher_walk_done(struct ablkcipher_request *req,
-			 struct ablkcipher_walk *walk, int err);
-int ablkcipher_walk_phys(struct ablkcipher_request *req,
-			 struct ablkcipher_walk *walk);
-void __ablkcipher_walk_complete(struct ablkcipher_walk *walk);
-
 static inline void *crypto_tfm_ctx_aligned(struct crypto_tfm *tfm)
 {
 	return PTR_ALIGN(crypto_tfm_ctx(tfm),
@@ -270,41 +200,6 @@ static inline void *crypto_instance_ctx(struct crypto_instance *inst)
 	return inst->__ctx;
 }
 
-static inline struct ablkcipher_alg *crypto_ablkcipher_alg(
-	struct crypto_ablkcipher *tfm)
-{
-	return &crypto_ablkcipher_tfm(tfm)->__crt_alg->cra_ablkcipher;
-}
-
-static inline void *crypto_ablkcipher_ctx(struct crypto_ablkcipher *tfm)
-{
-	return crypto_tfm_ctx(&tfm->base);
-}
-
-static inline void *crypto_ablkcipher_ctx_aligned(struct crypto_ablkcipher *tfm)
-{
-	return crypto_tfm_ctx_aligned(&tfm->base);
-}
-
-static inline struct crypto_blkcipher *crypto_spawn_blkcipher(
-	struct crypto_spawn *spawn)
-{
-	u32 type = CRYPTO_ALG_TYPE_BLKCIPHER;
-	u32 mask = CRYPTO_ALG_TYPE_MASK;
-
-	return __crypto_blkcipher_cast(crypto_spawn_tfm(spawn, type, mask));
-}
-
-static inline void *crypto_blkcipher_ctx(struct crypto_blkcipher *tfm)
-{
-	return crypto_tfm_ctx(&tfm->base);
-}
-
-static inline void *crypto_blkcipher_ctx_aligned(struct crypto_blkcipher *tfm)
-{
-	return crypto_tfm_ctx_aligned(&tfm->base);
-}
-
 static inline struct crypto_cipher *crypto_spawn_cipher(
 	struct crypto_spawn *spawn)
 {
@@ -319,33 +214,6 @@ static inline struct cipher_alg *crypto_cipher_alg(struct crypto_cipher *tfm)
 	return &crypto_cipher_tfm(tfm)->__crt_alg->cra_cipher;
 }
 
-static inline void blkcipher_walk_init(struct blkcipher_walk *walk,
-				       struct scatterlist *dst,
-				       struct scatterlist *src,
-				       unsigned int nbytes)
-{
-	walk->in.sg = src;
-	walk->out.sg = dst;
-	walk->total = nbytes;
-}
-
-static inline void ablkcipher_walk_init(struct ablkcipher_walk *walk,
-					struct scatterlist *dst,
-					struct scatterlist *src,
-					unsigned int nbytes)
-{
-	walk->in.sg = src;
-	walk->out.sg = dst;
-	walk->total = nbytes;
-	INIT_LIST_HEAD(&walk->buffers);
-}
-
-static inline void ablkcipher_walk_complete(struct ablkcipher_walk *walk)
-{
-	if (unlikely(!list_empty(&walk->buffers)))
-		__ablkcipher_walk_complete(walk);
-}
-
 static inline struct crypto_async_request *crypto_get_backlog(
 	struct crypto_queue *queue)
 {
@@ -353,23 +221,6 @@ static inline struct crypto_async_request *crypto_get_backlog(
 	       container_of(queue->backlog, struct crypto_async_request, list);
 }
 
-static inline int ablkcipher_enqueue_request(struct crypto_queue *queue,
-					     struct ablkcipher_request *request)
-{
-	return crypto_enqueue_request(queue, &request->base);
-}
-
-static inline struct ablkcipher_request *ablkcipher_dequeue_request(
-	struct crypto_queue *queue)
-{
-	return ablkcipher_request_cast(crypto_dequeue_request(queue));
-}
-
-static inline void *ablkcipher_request_ctx(struct ablkcipher_request *req)
-{
-	return req->__ctx;
-}
-
 static inline struct crypto_alg *crypto_get_attr_alg(struct rtattr **tb,
 						     u32 type, u32 mask)
 {
diff --git a/include/crypto/blake2s.h b/include/crypto/blake2s.h
new file mode 100644
index 000000000000..b471deac28ff
--- /dev/null
+++ b/include/crypto/blake2s.h
@@ -0,0 +1,106 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#ifndef BLAKE2S_H
+#define BLAKE2S_H
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+
+#include <asm/bug.h>
+
+enum blake2s_lengths {
+	BLAKE2S_BLOCK_SIZE = 64,
+	BLAKE2S_HASH_SIZE = 32,
+	BLAKE2S_KEY_SIZE = 32,
+
+	BLAKE2S_128_HASH_SIZE = 16,
+	BLAKE2S_160_HASH_SIZE = 20,
+	BLAKE2S_224_HASH_SIZE = 28,
+	BLAKE2S_256_HASH_SIZE = 32,
+};
+
+struct blake2s_state {
+	u32 h[8];
+	u32 t[2];
+	u32 f[2];
+	u8 buf[BLAKE2S_BLOCK_SIZE];
+	unsigned int buflen;
+	unsigned int outlen;
+};
+
+enum blake2s_iv {
+	BLAKE2S_IV0 = 0x6A09E667UL,
+	BLAKE2S_IV1 = 0xBB67AE85UL,
+	BLAKE2S_IV2 = 0x3C6EF372UL,
+	BLAKE2S_IV3 = 0xA54FF53AUL,
+	BLAKE2S_IV4 = 0x510E527FUL,
+	BLAKE2S_IV5 = 0x9B05688CUL,
+	BLAKE2S_IV6 = 0x1F83D9ABUL,
+	BLAKE2S_IV7 = 0x5BE0CD19UL,
+};
+
+void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen);
+void blake2s_final(struct blake2s_state *state, u8 *out);
+
+static inline void blake2s_init_param(struct blake2s_state *state,
+				      const u32 param)
+{
+	*state = (struct blake2s_state){{
+		BLAKE2S_IV0 ^ param,
+		BLAKE2S_IV1,
+		BLAKE2S_IV2,
+		BLAKE2S_IV3,
+		BLAKE2S_IV4,
+		BLAKE2S_IV5,
+		BLAKE2S_IV6,
+		BLAKE2S_IV7,
+	}};
+}
+
+static inline void blake2s_init(struct blake2s_state *state,
+				const size_t outlen)
+{
+	blake2s_init_param(state, 0x01010000 | outlen);
+	state->outlen = outlen;
+}
+
+static inline void blake2s_init_key(struct blake2s_state *state,
+				    const size_t outlen, const void *key,
+				    const size_t keylen)
+{
+	WARN_ON(IS_ENABLED(DEBUG) && (!outlen || outlen > BLAKE2S_HASH_SIZE ||
+		!key || !keylen || keylen > BLAKE2S_KEY_SIZE));
+
+	blake2s_init_param(state, 0x01010000 | keylen << 8 | outlen);
+	memcpy(state->buf, key, keylen);
+	state->buflen = BLAKE2S_BLOCK_SIZE;
+	state->outlen = outlen;
+}
+
+static inline void blake2s(u8 *out, const u8 *in, const u8 *key,
+			   const size_t outlen, const size_t inlen,
+			   const size_t keylen)
+{
+	struct blake2s_state state;
+
+	WARN_ON(IS_ENABLED(DEBUG) && ((!in && inlen > 0) || !out || !outlen ||
+		outlen > BLAKE2S_HASH_SIZE || keylen > BLAKE2S_KEY_SIZE ||
+		(!key && keylen)));
+
+	if (keylen)
+		blake2s_init_key(&state, outlen, key, keylen);
+	else
+		blake2s_init(&state, outlen);
+
+	blake2s_update(&state, in, inlen);
+	blake2s_final(&state, out);
+}
+
+void blake2s256_hmac(u8 *out, const u8 *in, const u8 *key, const size_t inlen,
+		     const size_t keylen);
+
+#endif /* BLAKE2S_H */
diff --git a/include/crypto/chacha.h b/include/crypto/chacha.h
index d1e723c6a37d..2676f4fbd4c1 100644
--- a/include/crypto/chacha.h
+++ b/include/crypto/chacha.h
@@ -15,9 +15,8 @@
 #ifndef _CRYPTO_CHACHA_H
 #define _CRYPTO_CHACHA_H
 
-#include <crypto/skcipher.h>
+#include <asm/unaligned.h>
 #include <linux/types.h>
-#include <linux/crypto.h>
 
 /* 32-bit stream position, then 96-bit nonce (RFC7539 convention) */
 #define CHACHA_IV_SIZE		16
@@ -26,29 +25,79 @@
 #define CHACHA_BLOCK_SIZE	64
 #define CHACHAPOLY_IV_SIZE	12
 
+#ifdef CONFIG_X86_64
+#define CHACHA_STATE_WORDS	((CHACHA_BLOCK_SIZE + 12) / sizeof(u32))
+#else
+#define CHACHA_STATE_WORDS	(CHACHA_BLOCK_SIZE / sizeof(u32))
+#endif
+
 /* 192-bit nonce, then 64-bit stream position */
 #define XCHACHA_IV_SIZE		32
 
-struct chacha_ctx {
-	u32 key[8];
-	int nrounds;
-};
-
-void chacha_block(u32 *state, u8 *stream, int nrounds);
+void chacha_block_generic(u32 *state, u8 *stream, int nrounds);
 static inline void chacha20_block(u32 *state, u8 *stream)
 {
-	chacha_block(state, stream, 20);
+	chacha_block_generic(state, stream, 20);
+}
+
+void hchacha_block_arch(const u32 *state, u32 *out, int nrounds);
+void hchacha_block_generic(const u32 *state, u32 *out, int nrounds);
+
+static inline void hchacha_block(const u32 *state, u32 *out, int nrounds)
+{
+	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA))
+		hchacha_block_arch(state, out, nrounds);
+	else
+		hchacha_block_generic(state, out, nrounds);
+}
+
+void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv);
+static inline void chacha_init_generic(u32 *state, const u32 *key, const u8 *iv)
+{
+	state[0]  = 0x61707865; /* "expa" */
+	state[1]  = 0x3320646e; /* "nd 3" */
+	state[2]  = 0x79622d32; /* "2-by" */
+	state[3]  = 0x6b206574; /* "te k" */
+	state[4]  = key[0];
+	state[5]  = key[1];
+	state[6]  = key[2];
+	state[7]  = key[3];
+	state[8]  = key[4];
+	state[9]  = key[5];
+	state[10] = key[6];
+	state[11] = key[7];
+	state[12] = get_unaligned_le32(iv +  0);
+	state[13] = get_unaligned_le32(iv +  4);
+	state[14] = get_unaligned_le32(iv +  8);
+	state[15] = get_unaligned_le32(iv + 12);
+}
+
+static inline void chacha_init(u32 *state, const u32 *key, const u8 *iv)
+{
+	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA))
+		chacha_init_arch(state, key, iv);
+	else
+		chacha_init_generic(state, key, iv);
 }
-void hchacha_block(const u32 *in, u32 *out, int nrounds);
 
-void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv);
+void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src,
+		       unsigned int bytes, int nrounds);
+void chacha_crypt_generic(u32 *state, u8 *dst, const u8 *src,
+			  unsigned int bytes, int nrounds);
 
-int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			   unsigned int keysize);
-int crypto_chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			   unsigned int keysize);
+static inline void chacha_crypt(u32 *state, u8 *dst, const u8 *src,
+				unsigned int bytes, int nrounds)
+{
+	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA))
+		chacha_crypt_arch(state, dst, src, bytes, nrounds);
+	else
+		chacha_crypt_generic(state, dst, src, bytes, nrounds);
+}
 
-int crypto_chacha_crypt(struct skcipher_request *req);
-int crypto_xchacha_crypt(struct skcipher_request *req);
+static inline void chacha20_crypt(u32 *state, u8 *dst, const u8 *src,
+				  unsigned int bytes)
+{
+	chacha_crypt(state, dst, src, bytes, 20);
+}
 
 #endif /* _CRYPTO_CHACHA_H */
diff --git a/include/crypto/chacha20poly1305.h b/include/crypto/chacha20poly1305.h
new file mode 100644
index 000000000000..234ee28078ef
--- /dev/null
+++ b/include/crypto/chacha20poly1305.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#ifndef __CHACHA20POLY1305_H
+#define __CHACHA20POLY1305_H
+
+#include <linux/types.h>
+#include <linux/scatterlist.h>
+
+enum chacha20poly1305_lengths {
+	XCHACHA20POLY1305_NONCE_SIZE = 24,
+	CHACHA20POLY1305_KEY_SIZE = 32,
+	CHACHA20POLY1305_AUTHTAG_SIZE = 16
+};
+
+void chacha20poly1305_encrypt(u8 *dst, const u8 *src, const size_t src_len,
+			      const u8 *ad, const size_t ad_len,
+			      const u64 nonce,
+			      const u8 key[CHACHA20POLY1305_KEY_SIZE]);
+
+bool __must_check
+chacha20poly1305_decrypt(u8 *dst, const u8 *src, const size_t src_len,
+			 const u8 *ad, const size_t ad_len, const u64 nonce,
+			 const u8 key[CHACHA20POLY1305_KEY_SIZE]);
+
+void xchacha20poly1305_encrypt(u8 *dst, const u8 *src, const size_t src_len,
+			       const u8 *ad, const size_t ad_len,
+			       const u8 nonce[XCHACHA20POLY1305_NONCE_SIZE],
+			       const u8 key[CHACHA20POLY1305_KEY_SIZE]);
+
+bool __must_check xchacha20poly1305_decrypt(
+	u8 *dst, const u8 *src, const size_t src_len, const u8 *ad,
+	const size_t ad_len, const u8 nonce[XCHACHA20POLY1305_NONCE_SIZE],
+	const u8 key[CHACHA20POLY1305_KEY_SIZE]);
+
+bool chacha20poly1305_encrypt_sg_inplace(struct scatterlist *src, size_t src_len,
+					 const u8 *ad, const size_t ad_len,
+					 const u64 nonce,
+					 const u8 key[CHACHA20POLY1305_KEY_SIZE]);
+
+bool chacha20poly1305_decrypt_sg_inplace(struct scatterlist *src, size_t src_len,
+					 const u8 *ad, const size_t ad_len,
+					 const u64 nonce,
+					 const u8 key[CHACHA20POLY1305_KEY_SIZE]);
+
+#endif /* __CHACHA20POLY1305_H */
diff --git a/include/crypto/curve25519.h b/include/crypto/curve25519.h
new file mode 100644
index 000000000000..4e6dc840b159
--- /dev/null
+++ b/include/crypto/curve25519.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#ifndef CURVE25519_H
+#define CURVE25519_H
+
+#include <crypto/algapi.h> // For crypto_memneq.
+#include <linux/types.h>
+#include <linux/random.h>
+
+enum curve25519_lengths {
+	CURVE25519_KEY_SIZE = 32
+};
+
+extern const u8 curve25519_null_point[];
+extern const u8 curve25519_base_point[];
+
+void curve25519_generic(u8 out[CURVE25519_KEY_SIZE],
+			const u8 scalar[CURVE25519_KEY_SIZE],
+			const u8 point[CURVE25519_KEY_SIZE]);
+
+void curve25519_arch(u8 out[CURVE25519_KEY_SIZE],
+		     const u8 scalar[CURVE25519_KEY_SIZE],
+		     const u8 point[CURVE25519_KEY_SIZE]);
+
+void curve25519_base_arch(u8 pub[CURVE25519_KEY_SIZE],
+			  const u8 secret[CURVE25519_KEY_SIZE]);
+
+static inline
+bool __must_check curve25519(u8 mypublic[CURVE25519_KEY_SIZE],
+			     const u8 secret[CURVE25519_KEY_SIZE],
+			     const u8 basepoint[CURVE25519_KEY_SIZE])
+{
+	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519))
+		curve25519_arch(mypublic, secret, basepoint);
+	else
+		curve25519_generic(mypublic, secret, basepoint);
+	return crypto_memneq(mypublic, curve25519_null_point,
+			     CURVE25519_KEY_SIZE);
+}
+
+static inline bool
+__must_check curve25519_generate_public(u8 pub[CURVE25519_KEY_SIZE],
+					const u8 secret[CURVE25519_KEY_SIZE])
+{
+	if (unlikely(!crypto_memneq(secret, curve25519_null_point,
+				    CURVE25519_KEY_SIZE)))
+		return false;
+
+	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519))
+		curve25519_base_arch(pub, secret);
+	else
+		curve25519_generic(pub, secret, curve25519_base_point);
+	return crypto_memneq(pub, curve25519_null_point, CURVE25519_KEY_SIZE);
+}
+
+static inline void curve25519_clamp_secret(u8 secret[CURVE25519_KEY_SIZE])
+{
+	secret[0] &= 248;
+	secret[31] = (secret[31] & 127) | 64;
+}
+
+static inline void curve25519_generate_secret(u8 secret[CURVE25519_KEY_SIZE])
+{
+	get_random_bytes_wait(secret, CURVE25519_KEY_SIZE);
+	curve25519_clamp_secret(secret);
+}
+
+#endif /* CURVE25519_H */
diff --git a/include/crypto/engine.h b/include/crypto/engine.h
index 84c708bba00b..e29cd67f93c7 100644
--- a/include/crypto/engine.h
+++ b/include/crypto/engine.h
@@ -83,8 +83,6 @@ struct crypto_engine_ctx {
 	struct crypto_engine_op op;
 };
 
-int crypto_transfer_ablkcipher_request_to_engine(struct crypto_engine *engine,
-						 struct ablkcipher_request *req);
 int crypto_transfer_aead_request_to_engine(struct crypto_engine *engine,
 					   struct aead_request *req);
 int crypto_transfer_akcipher_request_to_engine(struct crypto_engine *engine,
@@ -93,8 +91,6 @@ int crypto_transfer_hash_request_to_engine(struct crypto_engine *engine,
 					       struct ahash_request *req);
 int crypto_transfer_skcipher_request_to_engine(struct crypto_engine *engine,
 					       struct skcipher_request *req);
-void crypto_finalize_ablkcipher_request(struct crypto_engine *engine,
-					struct ablkcipher_request *req, int err);
 void crypto_finalize_aead_request(struct crypto_engine *engine,
 				  struct aead_request *req, int err);
 void crypto_finalize_akcipher_request(struct crypto_engine *engine,
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index d52b95b75ae4..fe7f73bad1e2 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -227,7 +227,7 @@ struct crypto_shash {
  * CRYPTO_ALG_TYPE_AHASH (listed as type "ahash" in /proc/crypto)
  *
  * The asynchronous cipher operation discussion provided for the
- * CRYPTO_ALG_TYPE_ABLKCIPHER API applies here as well.
+ * CRYPTO_ALG_TYPE_SKCIPHER API applies here as well.
  */
 
 static inline struct crypto_ahash *__crypto_ahash_cast(struct crypto_tfm *tfm)
diff --git a/include/crypto/internal/blake2s.h b/include/crypto/internal/blake2s.h
new file mode 100644
index 000000000000..74ff77032e52
--- /dev/null
+++ b/include/crypto/internal/blake2s.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+
+#ifndef BLAKE2S_INTERNAL_H
+#define BLAKE2S_INTERNAL_H
+
+#include <crypto/blake2s.h>
+
+struct blake2s_tfm_ctx {
+	u8 key[BLAKE2S_KEY_SIZE];
+	unsigned int keylen;
+};
+
+void blake2s_compress_generic(struct blake2s_state *state,const u8 *block,
+			      size_t nblocks, const u32 inc);
+
+void blake2s_compress_arch(struct blake2s_state *state,const u8 *block,
+			   size_t nblocks, const u32 inc);
+
+static inline void blake2s_set_lastblock(struct blake2s_state *state)
+{
+	state->f[0] = -1;
+}
+
+#endif /* BLAKE2S_INTERNAL_H */
diff --git a/include/crypto/internal/chacha.h b/include/crypto/internal/chacha.h
new file mode 100644
index 000000000000..aa5d4a16aac5
--- /dev/null
+++ b/include/crypto/internal/chacha.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _CRYPTO_INTERNAL_CHACHA_H
+#define _CRYPTO_INTERNAL_CHACHA_H
+
+#include <crypto/chacha.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/crypto.h>
+
+struct chacha_ctx {
+	u32 key[8];
+	int nrounds;
+};
+
+static inline int chacha_setkey(struct crypto_skcipher *tfm, const u8 *key,
+				unsigned int keysize, int nrounds)
+{
+	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int i;
+
+	if (keysize != CHACHA_KEY_SIZE)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(ctx->key); i++)
+		ctx->key[i] = get_unaligned_le32(key + i * sizeof(u32));
+
+	ctx->nrounds = nrounds;
+	return 0;
+}
+
+static inline int chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key,
+				  unsigned int keysize)
+{
+	return chacha_setkey(tfm, key, keysize, 20);
+}
+
+static int inline chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key,
+				  unsigned int keysize)
+{
+	return chacha_setkey(tfm, key, keysize, 12);
+}
+
+#endif /* _CRYPTO_CHACHA_H */
diff --git a/include/crypto/internal/des.h b/include/crypto/internal/des.h
index 81ea1a425e9c..f62a2bb1866b 100644
--- a/include/crypto/internal/des.h
+++ b/include/crypto/internal/des.h
@@ -117,18 +117,6 @@ static inline int verify_skcipher_des3_key(struct crypto_skcipher *tfm,
 	return crypto_des3_ede_verify_key(crypto_skcipher_tfm(tfm), key);
 }
 
-static inline int verify_ablkcipher_des_key(struct crypto_ablkcipher *tfm,
-					    const u8 *key)
-{
-	return crypto_des_verify_key(crypto_ablkcipher_tfm(tfm), key);
-}
-
-static inline int verify_ablkcipher_des3_key(struct crypto_ablkcipher *tfm,
-					     const u8 *key)
-{
-	return crypto_des3_ede_verify_key(crypto_ablkcipher_tfm(tfm), key);
-}
-
 static inline int verify_aead_des_key(struct crypto_aead *tfm, const u8 *key,
 				      int keylen)
 {
diff --git a/include/crypto/internal/poly1305.h b/include/crypto/internal/poly1305.h
new file mode 100644
index 000000000000..479b0cab2a1a
--- /dev/null
+++ b/include/crypto/internal/poly1305.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common values for the Poly1305 algorithm
+ */
+
+#ifndef _CRYPTO_INTERNAL_POLY1305_H
+#define _CRYPTO_INTERNAL_POLY1305_H
+
+#include <asm/unaligned.h>
+#include <linux/types.h>
+#include <crypto/poly1305.h>
+
+/*
+ * Poly1305 core functions.  These implement the ε-almost-∆-universal hash
+ * function underlying the Poly1305 MAC, i.e. they don't add an encrypted nonce
+ * ("s key") at the end.  They also only support block-aligned inputs.
+ */
+void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key);
+static inline void poly1305_core_init(struct poly1305_state *state)
+{
+	*state = (struct poly1305_state){};
+}
+
+void poly1305_core_blocks(struct poly1305_state *state,
+			  const struct poly1305_key *key, const void *src,
+			  unsigned int nblocks, u32 hibit);
+void poly1305_core_emit(const struct poly1305_state *state, void *dst);
+
+/*
+ * Poly1305 requires a unique key for each tag, which implies that we can't set
+ * it on the tfm that gets accessed by multiple users simultaneously. Instead we
+ * expect the key as the first 32 bytes in the update() call.
+ */
+static inline
+unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
+					const u8 *src, unsigned int srclen)
+{
+	if (!dctx->sset) {
+		if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) {
+			poly1305_core_setkey(dctx->r, src);
+			src += POLY1305_BLOCK_SIZE;
+			srclen -= POLY1305_BLOCK_SIZE;
+			dctx->rset = 1;
+		}
+		if (srclen >= POLY1305_BLOCK_SIZE) {
+			dctx->s[0] = get_unaligned_le32(src +  0);
+			dctx->s[1] = get_unaligned_le32(src +  4);
+			dctx->s[2] = get_unaligned_le32(src +  8);
+			dctx->s[3] = get_unaligned_le32(src + 12);
+			src += POLY1305_BLOCK_SIZE;
+			srclen -= POLY1305_BLOCK_SIZE;
+			dctx->sset = true;
+		}
+	}
+	return srclen;
+}
+
+#endif
diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h
index 734b6f7081b8..921c409fe1b1 100644
--- a/include/crypto/internal/skcipher.h
+++ b/include/crypto/internal/skcipher.h
@@ -153,17 +153,6 @@ static inline void skcipher_walk_abort(struct skcipher_walk *walk)
 	skcipher_walk_done(walk, -ECANCELED);
 }
 
-static inline void ablkcipher_request_complete(struct ablkcipher_request *req,
-					       int err)
-{
-	req->base.complete(&req->base, err);
-}
-
-static inline u32 ablkcipher_request_flags(struct ablkcipher_request *req)
-{
-	return req->base.flags;
-}
-
 static inline void *crypto_skcipher_ctx(struct crypto_skcipher *tfm)
 {
 	return crypto_tfm_ctx(&tfm->base);
@@ -182,73 +171,22 @@ static inline u32 skcipher_request_flags(struct skcipher_request *req)
 static inline unsigned int crypto_skcipher_alg_min_keysize(
 	struct skcipher_alg *alg)
 {
-	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	    CRYPTO_ALG_TYPE_BLKCIPHER)
-		return alg->base.cra_blkcipher.min_keysize;
-
-	if (alg->base.cra_ablkcipher.encrypt)
-		return alg->base.cra_ablkcipher.min_keysize;
-
 	return alg->min_keysize;
 }
 
 static inline unsigned int crypto_skcipher_alg_max_keysize(
 	struct skcipher_alg *alg)
 {
-	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	    CRYPTO_ALG_TYPE_BLKCIPHER)
-		return alg->base.cra_blkcipher.max_keysize;
-
-	if (alg->base.cra_ablkcipher.encrypt)
-		return alg->base.cra_ablkcipher.max_keysize;
-
 	return alg->max_keysize;
 }
 
-static inline unsigned int crypto_skcipher_alg_chunksize(
-	struct skcipher_alg *alg)
-{
-	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	    CRYPTO_ALG_TYPE_BLKCIPHER)
-		return alg->base.cra_blocksize;
-
-	if (alg->base.cra_ablkcipher.encrypt)
-		return alg->base.cra_blocksize;
-
-	return alg->chunksize;
-}
-
 static inline unsigned int crypto_skcipher_alg_walksize(
 	struct skcipher_alg *alg)
 {
-	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	    CRYPTO_ALG_TYPE_BLKCIPHER)
-		return alg->base.cra_blocksize;
-
-	if (alg->base.cra_ablkcipher.encrypt)
-		return alg->base.cra_blocksize;
-
 	return alg->walksize;
 }
 
 /**
- * crypto_skcipher_chunksize() - obtain chunk size
- * @tfm: cipher handle
- *
- * The block size is set to one for ciphers such as CTR.  However,
- * you still need to provide incremental updates in multiples of
- * the underlying block size as the IV does not have sub-block
- * granularity.  This is known in this API as the chunk size.
- *
- * Return: chunk size in bytes
- */
-static inline unsigned int crypto_skcipher_chunksize(
-	struct crypto_skcipher *tfm)
-{
-	return crypto_skcipher_alg_chunksize(crypto_skcipher_alg(tfm));
-}
-
-/**
  * crypto_skcipher_walksize() - obtain walk size
  * @tfm: cipher handle
  *
diff --git a/include/crypto/poly1305.h b/include/crypto/poly1305.h
index 34317ed2071e..74c6e1cd73ee 100644
--- a/include/crypto/poly1305.h
+++ b/include/crypto/poly1305.h
@@ -22,43 +22,56 @@ struct poly1305_state {
 };
 
 struct poly1305_desc_ctx {
-	/* key */
-	struct poly1305_key r;
-	/* finalize key */
-	u32 s[4];
-	/* accumulator */
-	struct poly1305_state h;
 	/* partial buffer */
 	u8 buf[POLY1305_BLOCK_SIZE];
 	/* bytes used in partial buffer */
 	unsigned int buflen;
-	/* r key has been set */
-	bool rset;
-	/* s key has been set */
+	/* how many keys have been set in r[] */
+	unsigned short rset;
+	/* whether s[] has been set */
 	bool sset;
+	/* finalize key */
+	u32 s[4];
+	/* accumulator */
+	struct poly1305_state h;
+	/* key */
+	struct poly1305_key r[CONFIG_CRYPTO_LIB_POLY1305_RSIZE];
 };
 
-/*
- * Poly1305 core functions.  These implement the ε-almost-∆-universal hash
- * function underlying the Poly1305 MAC, i.e. they don't add an encrypted nonce
- * ("s key") at the end.  They also only support block-aligned inputs.
- */
-void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key);
-static inline void poly1305_core_init(struct poly1305_state *state)
+void poly1305_init_arch(struct poly1305_desc_ctx *desc, const u8 *key);
+void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 *key);
+
+static inline void poly1305_init(struct poly1305_desc_ctx *desc, const u8 *key)
+{
+	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305))
+		poly1305_init_arch(desc, key);
+	else
+		poly1305_init_generic(desc, key);
+}
+
+void poly1305_update_arch(struct poly1305_desc_ctx *desc, const u8 *src,
+			  unsigned int nbytes);
+void poly1305_update_generic(struct poly1305_desc_ctx *desc, const u8 *src,
+			     unsigned int nbytes);
+
+static inline void poly1305_update(struct poly1305_desc_ctx *desc,
+				   const u8 *src, unsigned int nbytes)
 {
-	memset(state->h, 0, sizeof(state->h));
+	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305))
+		poly1305_update_arch(desc, src, nbytes);
+	else
+		poly1305_update_generic(desc, src, nbytes);
 }
-void poly1305_core_blocks(struct poly1305_state *state,
-			  const struct poly1305_key *key,
-			  const void *src, unsigned int nblocks);
-void poly1305_core_emit(const struct poly1305_state *state, void *dst);
 
-/* Crypto API helper functions for the Poly1305 MAC */
-int crypto_poly1305_init(struct shash_desc *desc);
-unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
-					const u8 *src, unsigned int srclen);
-int crypto_poly1305_update(struct shash_desc *desc,
-			   const u8 *src, unsigned int srclen);
-int crypto_poly1305_final(struct shash_desc *desc, u8 *dst);
+void poly1305_final_arch(struct poly1305_desc_ctx *desc, u8 *digest);
+void poly1305_final_generic(struct poly1305_desc_ctx *desc, u8 *digest);
+
+static inline void poly1305_final(struct poly1305_desc_ctx *desc, u8 *digest)
+{
+	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305))
+		poly1305_final_arch(desc, digest);
+	else
+		poly1305_final_generic(desc, digest);
+}
 
 #endif
diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h
index 37c164234d97..b4655d91661f 100644
--- a/include/crypto/skcipher.h
+++ b/include/crypto/skcipher.h
@@ -218,30 +218,13 @@ static inline void crypto_free_sync_skcipher(struct crypto_sync_skcipher *tfm)
  * crypto_has_skcipher() - Search for the availability of an skcipher.
  * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
  *	      skcipher
- * @type: specifies the type of the cipher
- * @mask: specifies the mask for the cipher
- *
- * Return: true when the skcipher is known to the kernel crypto API; false
- *	   otherwise
- */
-static inline int crypto_has_skcipher(const char *alg_name, u32 type,
-					u32 mask)
-{
-	return crypto_has_alg(alg_name, crypto_skcipher_type(type),
-			      crypto_skcipher_mask(mask));
-}
-
-/**
- * crypto_has_skcipher2() - Search for the availability of an skcipher.
- * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
- *	      skcipher
  * @type: specifies the type of the skcipher
  * @mask: specifies the mask for the skcipher
  *
  * Return: true when the skcipher is known to the kernel crypto API; false
  *	   otherwise
  */
-int crypto_has_skcipher2(const char *alg_name, u32 type, u32 mask);
+int crypto_has_skcipher(const char *alg_name, u32 type, u32 mask);
 
 static inline const char *crypto_skcipher_driver_name(
 	struct crypto_skcipher *tfm)
@@ -258,13 +241,6 @@ static inline struct skcipher_alg *crypto_skcipher_alg(
 
 static inline unsigned int crypto_skcipher_alg_ivsize(struct skcipher_alg *alg)
 {
-	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	    CRYPTO_ALG_TYPE_BLKCIPHER)
-		return alg->base.cra_blkcipher.ivsize;
-
-	if (alg->base.cra_ablkcipher.encrypt)
-		return alg->base.cra_ablkcipher.ivsize;
-
 	return alg->ivsize;
 }
 
@@ -304,6 +280,29 @@ static inline unsigned int crypto_skcipher_blocksize(
 	return crypto_tfm_alg_blocksize(crypto_skcipher_tfm(tfm));
 }
 
+static inline unsigned int crypto_skcipher_alg_chunksize(
+	struct skcipher_alg *alg)
+{
+	return alg->chunksize;
+}
+
+/**
+ * crypto_skcipher_chunksize() - obtain chunk size
+ * @tfm: cipher handle
+ *
+ * The block size is set to one for ciphers such as CTR.  However,
+ * you still need to provide incremental updates in multiples of
+ * the underlying block size as the IV does not have sub-block
+ * granularity.  This is known in this API as the chunk size.
+ *
+ * Return: chunk size in bytes
+ */
+static inline unsigned int crypto_skcipher_chunksize(
+	struct crypto_skcipher *tfm)
+{
+	return crypto_skcipher_alg_chunksize(crypto_skcipher_alg(tfm));
+}
+
 static inline unsigned int crypto_sync_skcipher_blocksize(
 	struct crypto_sync_skcipher *tfm)
 {
diff --git a/include/drm/drm_cache.h b/include/drm/drm_cache.h
index 987ff16b9420..e9ad4863d915 100644
--- a/include/drm/drm_cache.h
+++ b/include/drm/drm_cache.h
@@ -45,7 +45,7 @@ static inline bool drm_arch_can_wc_memory(void)
 {
 #if defined(CONFIG_PPC) && !defined(CONFIG_NOT_COHERENT_CACHE)
 	return false;
-#elif defined(CONFIG_MIPS) && defined(CONFIG_CPU_LOONGSON3)
+#elif defined(CONFIG_MIPS) && defined(CONFIG_CPU_LOONGSON64)
 	return false;
 #elif defined(CONFIG_ARM) || defined(CONFIG_ARM64)
 	/*
diff --git a/include/keys/trusted.h b/include/keys/trusted_tpm.h
index 0071298b9b28..a56d8e1298f2 100644
--- a/include/keys/trusted.h
+++ b/include/keys/trusted_tpm.h
@@ -1,14 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __TRUSTED_KEY_H
-#define __TRUSTED_KEY_H
+#ifndef __TRUSTED_TPM_H
+#define __TRUSTED_TPM_H
+
+#include <keys/trusted-type.h>
+#include <linux/tpm_command.h>
 
 /* implementation specific TPM constants */
 #define MAX_BUF_SIZE			1024
 #define TPM_GETRANDOM_SIZE		14
-#define TPM_OSAP_SIZE			36
-#define TPM_OIAP_SIZE			10
-#define TPM_SEAL_SIZE			87
-#define TPM_UNSEAL_SIZE			104
 #define TPM_SIZE_OFFSET			2
 #define TPM_RETURN_OFFSET		6
 #define TPM_DATA_OFFSET			10
@@ -17,13 +16,6 @@
 #define LOAD32N(buffer, offset)	(*(uint32_t *)&buffer[offset])
 #define LOAD16(buffer, offset)	(ntohs(*(uint16_t *)&buffer[offset]))
 
-struct tpm_buf {
-	int len;
-	unsigned char data[MAX_BUF_SIZE];
-};
-
-#define INIT_BUF(tb) (tb->len = 0)
-
 struct osapsess {
 	uint32_t handle;
 	unsigned char secret[SHA1_DIGEST_SIZE];
@@ -48,6 +40,13 @@ int TSS_checkhmac1(unsigned char *buffer,
 int trusted_tpm_send(unsigned char *cmd, size_t buflen);
 int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce);
 
+int tpm2_seal_trusted(struct tpm_chip *chip,
+		      struct trusted_key_payload *payload,
+		      struct trusted_key_options *options);
+int tpm2_unseal_trusted(struct tpm_chip *chip,
+			struct trusted_key_payload *payload,
+			struct trusted_key_options *options);
+
 #define TPM_DEBUG 0
 
 #if TPM_DEBUG
@@ -109,28 +108,4 @@ static inline void dump_tpm_buf(unsigned char *buf)
 {
 }
 #endif
-
-static inline void store8(struct tpm_buf *buf, const unsigned char value)
-{
-	buf->data[buf->len++] = value;
-}
-
-static inline void store16(struct tpm_buf *buf, const uint16_t value)
-{
-	*(uint16_t *) & buf->data[buf->len] = htons(value);
-	buf->len += sizeof value;
-}
-
-static inline void store32(struct tpm_buf *buf, const uint32_t value)
-{
-	*(uint32_t *) & buf->data[buf->len] = htonl(value);
-	buf->len += sizeof value;
-}
-
-static inline void storebytes(struct tpm_buf *buf, const unsigned char *in,
-			      const int len)
-{
-	memcpy(buf->data + buf->len, in, len);
-	buf->len += len;
-}
 #endif
diff --git a/include/kunit/assert.h b/include/kunit/assert.h
new file mode 100644
index 000000000000..db6a0fca09b4
--- /dev/null
+++ b/include/kunit/assert.h
@@ -0,0 +1,356 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Assertion and expectation serialization API.
+ *
+ * Copyright (C) 2019, Google LLC.
+ * Author: Brendan Higgins <brendanhiggins@google.com>
+ */
+
+#ifndef _KUNIT_ASSERT_H
+#define _KUNIT_ASSERT_H
+
+#include <kunit/string-stream.h>
+#include <linux/err.h>
+
+struct kunit;
+
+/**
+ * enum kunit_assert_type - Type of expectation/assertion.
+ * @KUNIT_ASSERTION: Used to denote that a kunit_assert represents an assertion.
+ * @KUNIT_EXPECTATION: Denotes that a kunit_assert represents an expectation.
+ *
+ * Used in conjunction with a &struct kunit_assert to denote whether it
+ * represents an expectation or an assertion.
+ */
+enum kunit_assert_type {
+	KUNIT_ASSERTION,
+	KUNIT_EXPECTATION,
+};
+
+/**
+ * struct kunit_assert - Data for printing a failed assertion or expectation.
+ * @test: the test case this expectation/assertion is associated with.
+ * @type: the type (either an expectation or an assertion) of this kunit_assert.
+ * @line: the source code line number that the expectation/assertion is at.
+ * @file: the file path of the source file that the expectation/assertion is in.
+ * @message: an optional message to provide additional context.
+ * @format: a function which formats the data in this kunit_assert to a string.
+ *
+ * Represents a failed expectation/assertion. Contains all the data necessary to
+ * format a string to a user reporting the failure.
+ */
+struct kunit_assert {
+	struct kunit *test;
+	enum kunit_assert_type type;
+	int line;
+	const char *file;
+	struct va_format message;
+	void (*format)(const struct kunit_assert *assert,
+		       struct string_stream *stream);
+};
+
+/**
+ * KUNIT_INIT_VA_FMT_NULL - Default initializer for struct va_format.
+ *
+ * Used inside a struct initialization block to initialize struct va_format to
+ * default values where fmt and va are null.
+ */
+#define KUNIT_INIT_VA_FMT_NULL { .fmt = NULL, .va = NULL }
+
+/**
+ * KUNIT_INIT_ASSERT_STRUCT() - Initializer for a &struct kunit_assert.
+ * @kunit: The test case that this expectation/assertion is associated with.
+ * @assert_type: The type (assertion or expectation) of this kunit_assert.
+ * @fmt: The formatting function which builds a string out of this kunit_assert.
+ *
+ * The base initializer for a &struct kunit_assert.
+ */
+#define KUNIT_INIT_ASSERT_STRUCT(kunit, assert_type, fmt) {		       \
+	.test = kunit,							       \
+	.type = assert_type,						       \
+	.file = __FILE__,						       \
+	.line = __LINE__,						       \
+	.message = KUNIT_INIT_VA_FMT_NULL,				       \
+	.format = fmt							       \
+}
+
+void kunit_base_assert_format(const struct kunit_assert *assert,
+			      struct string_stream *stream);
+
+void kunit_assert_print_msg(const struct kunit_assert *assert,
+			    struct string_stream *stream);
+
+/**
+ * struct kunit_fail_assert - Represents a plain fail expectation/assertion.
+ * @assert: The parent of this type.
+ *
+ * Represents a simple KUNIT_FAIL/KUNIT_ASSERT_FAILURE that always fails.
+ */
+struct kunit_fail_assert {
+	struct kunit_assert assert;
+};
+
+void kunit_fail_assert_format(const struct kunit_assert *assert,
+			      struct string_stream *stream);
+
+/**
+ * KUNIT_INIT_FAIL_ASSERT_STRUCT() - Initializer for &struct kunit_fail_assert.
+ * @test: The test case that this expectation/assertion is associated with.
+ * @type: The type (assertion or expectation) of this kunit_assert.
+ *
+ * Initializes a &struct kunit_fail_assert. Intended to be used in
+ * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros.
+ */
+#define KUNIT_INIT_FAIL_ASSERT_STRUCT(test, type) {			       \
+	.assert = KUNIT_INIT_ASSERT_STRUCT(test,			       \
+					   type,			       \
+					   kunit_fail_assert_format)	       \
+}
+
+/**
+ * struct kunit_unary_assert - Represents a KUNIT_{EXPECT|ASSERT}_{TRUE|FALSE}
+ * @assert: The parent of this type.
+ * @condition: A string representation of a conditional expression.
+ * @expected_true: True if of type KUNIT_{EXPECT|ASSERT}_TRUE, false otherwise.
+ *
+ * Represents a simple expectation or assertion that simply asserts something is
+ * true or false. In other words, represents the expectations:
+ * KUNIT_{EXPECT|ASSERT}_{TRUE|FALSE}
+ */
+struct kunit_unary_assert {
+	struct kunit_assert assert;
+	const char *condition;
+	bool expected_true;
+};
+
+void kunit_unary_assert_format(const struct kunit_assert *assert,
+			       struct string_stream *stream);
+
+/**
+ * KUNIT_INIT_UNARY_ASSERT_STRUCT() - Initializes &struct kunit_unary_assert.
+ * @test: The test case that this expectation/assertion is associated with.
+ * @type: The type (assertion or expectation) of this kunit_assert.
+ * @cond: A string representation of the expression asserted true or false.
+ * @expect_true: True if of type KUNIT_{EXPECT|ASSERT}_TRUE, false otherwise.
+ *
+ * Initializes a &struct kunit_unary_assert. Intended to be used in
+ * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros.
+ */
+#define KUNIT_INIT_UNARY_ASSERT_STRUCT(test, type, cond, expect_true) {	       \
+	.assert = KUNIT_INIT_ASSERT_STRUCT(test,			       \
+					   type,			       \
+					   kunit_unary_assert_format),	       \
+	.condition = cond,						       \
+	.expected_true = expect_true					       \
+}
+
+/**
+ * struct kunit_ptr_not_err_assert - An expectation/assertion that a pointer is
+ *	not NULL and not a -errno.
+ * @assert: The parent of this type.
+ * @text: A string representation of the expression passed to the expectation.
+ * @value: The actual evaluated pointer value of the expression.
+ *
+ * Represents an expectation/assertion that a pointer is not null and is does
+ * not contain a -errno. (See IS_ERR_OR_NULL().)
+ */
+struct kunit_ptr_not_err_assert {
+	struct kunit_assert assert;
+	const char *text;
+	const void *value;
+};
+
+void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert,
+				     struct string_stream *stream);
+
+/**
+ * KUNIT_INIT_PTR_NOT_ERR_ASSERT_STRUCT() - Initializes a
+ *	&struct kunit_ptr_not_err_assert.
+ * @test: The test case that this expectation/assertion is associated with.
+ * @type: The type (assertion or expectation) of this kunit_assert.
+ * @txt: A string representation of the expression passed to the expectation.
+ * @val: The actual evaluated pointer value of the expression.
+ *
+ * Initializes a &struct kunit_ptr_not_err_assert. Intended to be used in
+ * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros.
+ */
+#define KUNIT_INIT_PTR_NOT_ERR_STRUCT(test, type, txt, val) {		       \
+	.assert = KUNIT_INIT_ASSERT_STRUCT(test,			       \
+					   type,			       \
+					   kunit_ptr_not_err_assert_format),   \
+	.text = txt,							       \
+	.value = val							       \
+}
+
+/**
+ * struct kunit_binary_assert - An expectation/assertion that compares two
+ *	non-pointer values (for example, KUNIT_EXPECT_EQ(test, 1 + 1, 2)).
+ * @assert: The parent of this type.
+ * @operation: A string representation of the comparison operator (e.g. "==").
+ * @left_text: A string representation of the expression in the left slot.
+ * @left_value: The actual evaluated value of the expression in the left slot.
+ * @right_text: A string representation of the expression in the right slot.
+ * @right_value: The actual evaluated value of the expression in the right slot.
+ *
+ * Represents an expectation/assertion that compares two non-pointer values. For
+ * example, to expect that 1 + 1 == 2, you can use the expectation
+ * KUNIT_EXPECT_EQ(test, 1 + 1, 2);
+ */
+struct kunit_binary_assert {
+	struct kunit_assert assert;
+	const char *operation;
+	const char *left_text;
+	long long left_value;
+	const char *right_text;
+	long long right_value;
+};
+
+void kunit_binary_assert_format(const struct kunit_assert *assert,
+				struct string_stream *stream);
+
+/**
+ * KUNIT_INIT_BINARY_ASSERT_STRUCT() - Initializes a
+ *	&struct kunit_binary_assert.
+ * @test: The test case that this expectation/assertion is associated with.
+ * @type: The type (assertion or expectation) of this kunit_assert.
+ * @op_str: A string representation of the comparison operator (e.g. "==").
+ * @left_str: A string representation of the expression in the left slot.
+ * @left_val: The actual evaluated value of the expression in the left slot.
+ * @right_str: A string representation of the expression in the right slot.
+ * @right_val: The actual evaluated value of the expression in the right slot.
+ *
+ * Initializes a &struct kunit_binary_assert. Intended to be used in
+ * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros.
+ */
+#define KUNIT_INIT_BINARY_ASSERT_STRUCT(test,				       \
+					type,				       \
+					op_str,				       \
+					left_str,			       \
+					left_val,			       \
+					right_str,			       \
+					right_val) {			       \
+	.assert = KUNIT_INIT_ASSERT_STRUCT(test,			       \
+					   type,			       \
+					   kunit_binary_assert_format),	       \
+	.operation = op_str,						       \
+	.left_text = left_str,						       \
+	.left_value = left_val,						       \
+	.right_text = right_str,					       \
+	.right_value = right_val					       \
+}
+
+/**
+ * struct kunit_binary_ptr_assert - An expectation/assertion that compares two
+ *	pointer values (for example, KUNIT_EXPECT_PTR_EQ(test, foo, bar)).
+ * @assert: The parent of this type.
+ * @operation: A string representation of the comparison operator (e.g. "==").
+ * @left_text: A string representation of the expression in the left slot.
+ * @left_value: The actual evaluated value of the expression in the left slot.
+ * @right_text: A string representation of the expression in the right slot.
+ * @right_value: The actual evaluated value of the expression in the right slot.
+ *
+ * Represents an expectation/assertion that compares two pointer values. For
+ * example, to expect that foo and bar point to the same thing, you can use the
+ * expectation KUNIT_EXPECT_PTR_EQ(test, foo, bar);
+ */
+struct kunit_binary_ptr_assert {
+	struct kunit_assert assert;
+	const char *operation;
+	const char *left_text;
+	const void *left_value;
+	const char *right_text;
+	const void *right_value;
+};
+
+void kunit_binary_ptr_assert_format(const struct kunit_assert *assert,
+				    struct string_stream *stream);
+
+/**
+ * KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT() - Initializes a
+ *	&struct kunit_binary_ptr_assert.
+ * @test: The test case that this expectation/assertion is associated with.
+ * @type: The type (assertion or expectation) of this kunit_assert.
+ * @op_str: A string representation of the comparison operator (e.g. "==").
+ * @left_str: A string representation of the expression in the left slot.
+ * @left_val: The actual evaluated value of the expression in the left slot.
+ * @right_str: A string representation of the expression in the right slot.
+ * @right_val: The actual evaluated value of the expression in the right slot.
+ *
+ * Initializes a &struct kunit_binary_ptr_assert. Intended to be used in
+ * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros.
+ */
+#define KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT(test,			       \
+					    type,			       \
+					    op_str,			       \
+					    left_str,			       \
+					    left_val,			       \
+					    right_str,			       \
+					    right_val) {		       \
+	.assert = KUNIT_INIT_ASSERT_STRUCT(test,			       \
+					   type,			       \
+					   kunit_binary_ptr_assert_format),    \
+	.operation = op_str,						       \
+	.left_text = left_str,						       \
+	.left_value = left_val,						       \
+	.right_text = right_str,					       \
+	.right_value = right_val					       \
+}
+
+/**
+ * struct kunit_binary_str_assert - An expectation/assertion that compares two
+ *	string values (for example, KUNIT_EXPECT_STREQ(test, foo, "bar")).
+ * @assert: The parent of this type.
+ * @operation: A string representation of the comparison operator (e.g. "==").
+ * @left_text: A string representation of the expression in the left slot.
+ * @left_value: The actual evaluated value of the expression in the left slot.
+ * @right_text: A string representation of the expression in the right slot.
+ * @right_value: The actual evaluated value of the expression in the right slot.
+ *
+ * Represents an expectation/assertion that compares two string values. For
+ * example, to expect that the string in foo is equal to "bar", you can use the
+ * expectation KUNIT_EXPECT_STREQ(test, foo, "bar");
+ */
+struct kunit_binary_str_assert {
+	struct kunit_assert assert;
+	const char *operation;
+	const char *left_text;
+	const char *left_value;
+	const char *right_text;
+	const char *right_value;
+};
+
+void kunit_binary_str_assert_format(const struct kunit_assert *assert,
+				    struct string_stream *stream);
+
+/**
+ * KUNIT_INIT_BINARY_STR_ASSERT_STRUCT() - Initializes a
+ *	&struct kunit_binary_str_assert.
+ * @test: The test case that this expectation/assertion is associated with.
+ * @type: The type (assertion or expectation) of this kunit_assert.
+ * @op_str: A string representation of the comparison operator (e.g. "==").
+ * @left_str: A string representation of the expression in the left slot.
+ * @left_val: The actual evaluated value of the expression in the left slot.
+ * @right_str: A string representation of the expression in the right slot.
+ * @right_val: The actual evaluated value of the expression in the right slot.
+ *
+ * Initializes a &struct kunit_binary_str_assert. Intended to be used in
+ * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros.
+ */
+#define KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(test,			       \
+					    type,			       \
+					    op_str,			       \
+					    left_str,			       \
+					    left_val,			       \
+					    right_str,			       \
+					    right_val) {		       \
+	.assert = KUNIT_INIT_ASSERT_STRUCT(test,			       \
+					   type,			       \
+					   kunit_binary_str_assert_format),    \
+	.operation = op_str,						       \
+	.left_text = left_str,						       \
+	.left_value = left_val,						       \
+	.right_text = right_str,					       \
+	.right_value = right_val					       \
+}
+
+#endif /*  _KUNIT_ASSERT_H */
diff --git a/include/kunit/string-stream.h b/include/kunit/string-stream.h
new file mode 100644
index 000000000000..fe98a00b75a9
--- /dev/null
+++ b/include/kunit/string-stream.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * C++ stream style string builder used in KUnit for building messages.
+ *
+ * Copyright (C) 2019, Google LLC.
+ * Author: Brendan Higgins <brendanhiggins@google.com>
+ */
+
+#ifndef _KUNIT_STRING_STREAM_H
+#define _KUNIT_STRING_STREAM_H
+
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <stdarg.h>
+
+struct string_stream_fragment {
+	struct kunit *test;
+	struct list_head node;
+	char *fragment;
+};
+
+struct string_stream {
+	size_t length;
+	struct list_head fragments;
+	/* length and fragments are protected by this lock */
+	spinlock_t lock;
+	struct kunit *test;
+	gfp_t gfp;
+};
+
+struct kunit;
+
+struct string_stream *alloc_string_stream(struct kunit *test, gfp_t gfp);
+
+int __printf(2, 3) string_stream_add(struct string_stream *stream,
+				     const char *fmt, ...);
+
+int string_stream_vadd(struct string_stream *stream,
+		       const char *fmt,
+		       va_list args);
+
+char *string_stream_get_string(struct string_stream *stream);
+
+int string_stream_append(struct string_stream *stream,
+			 struct string_stream *other);
+
+bool string_stream_is_empty(struct string_stream *stream);
+
+int string_stream_destroy(struct string_stream *stream);
+
+#endif /* _KUNIT_STRING_STREAM_H */
diff --git a/include/kunit/test.h b/include/kunit/test.h
new file mode 100644
index 000000000000..dba48304b3bd
--- /dev/null
+++ b/include/kunit/test.h
@@ -0,0 +1,1490 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Base unit test (KUnit) API.
+ *
+ * Copyright (C) 2019, Google LLC.
+ * Author: Brendan Higgins <brendanhiggins@google.com>
+ */
+
+#ifndef _KUNIT_TEST_H
+#define _KUNIT_TEST_H
+
+#include <kunit/assert.h>
+#include <kunit/try-catch.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+struct kunit_resource;
+
+typedef int (*kunit_resource_init_t)(struct kunit_resource *, void *);
+typedef void (*kunit_resource_free_t)(struct kunit_resource *);
+
+/**
+ * struct kunit_resource - represents a *test managed resource*
+ * @allocation: for the user to store arbitrary data.
+ * @free: a user supplied function to free the resource. Populated by
+ * kunit_alloc_resource().
+ *
+ * Represents a *test managed resource*, a resource which will automatically be
+ * cleaned up at the end of a test case.
+ *
+ * Example:
+ *
+ * .. code-block:: c
+ *
+ *	struct kunit_kmalloc_params {
+ *		size_t size;
+ *		gfp_t gfp;
+ *	};
+ *
+ *	static int kunit_kmalloc_init(struct kunit_resource *res, void *context)
+ *	{
+ *		struct kunit_kmalloc_params *params = context;
+ *		res->allocation = kmalloc(params->size, params->gfp);
+ *
+ *		if (!res->allocation)
+ *			return -ENOMEM;
+ *
+ *		return 0;
+ *	}
+ *
+ *	static void kunit_kmalloc_free(struct kunit_resource *res)
+ *	{
+ *		kfree(res->allocation);
+ *	}
+ *
+ *	void *kunit_kmalloc(struct kunit *test, size_t size, gfp_t gfp)
+ *	{
+ *		struct kunit_kmalloc_params params;
+ *		struct kunit_resource *res;
+ *
+ *		params.size = size;
+ *		params.gfp = gfp;
+ *
+ *		res = kunit_alloc_resource(test, kunit_kmalloc_init,
+ *			kunit_kmalloc_free, &params);
+ *		if (res)
+ *			return res->allocation;
+ *
+ *		return NULL;
+ *	}
+ */
+struct kunit_resource {
+	void *allocation;
+	kunit_resource_free_t free;
+
+	/* private: internal use only. */
+	struct list_head node;
+};
+
+struct kunit;
+
+/**
+ * struct kunit_case - represents an individual test case.
+ *
+ * @run_case: the function representing the actual test case.
+ * @name:     the name of the test case.
+ *
+ * A test case is a function with the signature,
+ * ``void (*)(struct kunit *)``
+ * that makes expectations and assertions (see KUNIT_EXPECT_TRUE() and
+ * KUNIT_ASSERT_TRUE()) about code under test. Each test case is associated
+ * with a &struct kunit_suite and will be run after the suite's init
+ * function and followed by the suite's exit function.
+ *
+ * A test case should be static and should only be created with the
+ * KUNIT_CASE() macro; additionally, every array of test cases should be
+ * terminated with an empty test case.
+ *
+ * Example:
+ *
+ * .. code-block:: c
+ *
+ *	void add_test_basic(struct kunit *test)
+ *	{
+ *		KUNIT_EXPECT_EQ(test, 1, add(1, 0));
+ *		KUNIT_EXPECT_EQ(test, 2, add(1, 1));
+ *		KUNIT_EXPECT_EQ(test, 0, add(-1, 1));
+ *		KUNIT_EXPECT_EQ(test, INT_MAX, add(0, INT_MAX));
+ *		KUNIT_EXPECT_EQ(test, -1, add(INT_MAX, INT_MIN));
+ *	}
+ *
+ *	static struct kunit_case example_test_cases[] = {
+ *		KUNIT_CASE(add_test_basic),
+ *		{}
+ *	};
+ *
+ */
+struct kunit_case {
+	void (*run_case)(struct kunit *test);
+	const char *name;
+
+	/* private: internal use only. */
+	bool success;
+};
+
+/**
+ * KUNIT_CASE - A helper for creating a &struct kunit_case
+ *
+ * @test_name: a reference to a test case function.
+ *
+ * Takes a symbol for a function representing a test case and creates a
+ * &struct kunit_case object from it. See the documentation for
+ * &struct kunit_case for an example on how to use it.
+ */
+#define KUNIT_CASE(test_name) { .run_case = test_name, .name = #test_name }
+
+/**
+ * struct kunit_suite - describes a related collection of &struct kunit_case
+ *
+ * @name:	the name of the test. Purely informational.
+ * @init:	called before every test case.
+ * @exit:	called after every test case.
+ * @test_cases:	a null terminated array of test cases.
+ *
+ * A kunit_suite is a collection of related &struct kunit_case s, such that
+ * @init is called before every test case and @exit is called after every
+ * test case, similar to the notion of a *test fixture* or a *test class*
+ * in other unit testing frameworks like JUnit or Googletest.
+ *
+ * Every &struct kunit_case must be associated with a kunit_suite for KUnit
+ * to run it.
+ */
+struct kunit_suite {
+	const char name[256];
+	int (*init)(struct kunit *test);
+	void (*exit)(struct kunit *test);
+	struct kunit_case *test_cases;
+};
+
+/**
+ * struct kunit - represents a running instance of a test.
+ *
+ * @priv: for user to store arbitrary data. Commonly used to pass data
+ *	  created in the init function (see &struct kunit_suite).
+ *
+ * Used to store information about the current context under which the test
+ * is running. Most of this data is private and should only be accessed
+ * indirectly via public functions; the one exception is @priv which can be
+ * used by the test writer to store arbitrary data.
+ */
+struct kunit {
+	void *priv;
+
+	/* private: internal use only. */
+	const char *name; /* Read only after initialization! */
+	struct kunit_try_catch try_catch;
+	/*
+	 * success starts as true, and may only be set to false during a
+	 * test case; thus, it is safe to update this across multiple
+	 * threads using WRITE_ONCE; however, as a consequence, it may only
+	 * be read after the test case finishes once all threads associated
+	 * with the test case have terminated.
+	 */
+	bool success; /* Read only after test_case finishes! */
+	spinlock_t lock; /* Guards all mutable test state. */
+	/*
+	 * Because resources is a list that may be updated multiple times (with
+	 * new resources) from any thread associated with a test case, we must
+	 * protect it with some type of lock.
+	 */
+	struct list_head resources; /* Protected by lock. */
+};
+
+void kunit_init_test(struct kunit *test, const char *name);
+
+int kunit_run_tests(struct kunit_suite *suite);
+
+/**
+ * kunit_test_suite() - used to register a &struct kunit_suite with KUnit.
+ *
+ * @suite: a statically allocated &struct kunit_suite.
+ *
+ * Registers @suite with the test framework. See &struct kunit_suite for
+ * more information.
+ *
+ * NOTE: Currently KUnit tests are all run as late_initcalls; this means
+ * that they cannot test anything where tests must run at a different init
+ * phase. One significant restriction resulting from this is that KUnit
+ * cannot reliably test anything that is initialize in the late_init phase;
+ * another is that KUnit is useless to test things that need to be run in
+ * an earlier init phase.
+ *
+ * TODO(brendanhiggins@google.com): Don't run all KUnit tests as
+ * late_initcalls.  I have some future work planned to dispatch all KUnit
+ * tests from the same place, and at the very least to do so after
+ * everything else is definitely initialized.
+ */
+#define kunit_test_suite(suite)						       \
+	static int kunit_suite_init##suite(void)			       \
+	{								       \
+		return kunit_run_tests(&suite);				       \
+	}								       \
+	late_initcall(kunit_suite_init##suite)
+
+/*
+ * Like kunit_alloc_resource() below, but returns the struct kunit_resource
+ * object that contains the allocation. This is mostly for testing purposes.
+ */
+struct kunit_resource *kunit_alloc_and_get_resource(struct kunit *test,
+						    kunit_resource_init_t init,
+						    kunit_resource_free_t free,
+						    gfp_t internal_gfp,
+						    void *context);
+
+/**
+ * kunit_alloc_resource() - Allocates a *test managed resource*.
+ * @test: The test context object.
+ * @init: a user supplied function to initialize the resource.
+ * @free: a user supplied function to free the resource.
+ * @internal_gfp: gfp to use for internal allocations, if unsure, use GFP_KERNEL
+ * @context: for the user to pass in arbitrary data to the init function.
+ *
+ * Allocates a *test managed resource*, a resource which will automatically be
+ * cleaned up at the end of a test case. See &struct kunit_resource for an
+ * example.
+ *
+ * NOTE: KUnit needs to allocate memory for each kunit_resource object. You must
+ * specify an @internal_gfp that is compatible with the use context of your
+ * resource.
+ */
+static inline void *kunit_alloc_resource(struct kunit *test,
+					 kunit_resource_init_t init,
+					 kunit_resource_free_t free,
+					 gfp_t internal_gfp,
+					 void *context)
+{
+	struct kunit_resource *res;
+
+	res = kunit_alloc_and_get_resource(test, init, free, internal_gfp,
+					   context);
+
+	if (res)
+		return res->allocation;
+
+	return NULL;
+}
+
+typedef bool (*kunit_resource_match_t)(struct kunit *test,
+				       const void *res,
+				       void *match_data);
+
+/**
+ * kunit_resource_instance_match() - Match a resource with the same instance.
+ * @test: Test case to which the resource belongs.
+ * @res: The data stored in kunit_resource->allocation.
+ * @match_data: The resource pointer to match against.
+ *
+ * An instance of kunit_resource_match_t that matches a resource whose
+ * allocation matches @match_data.
+ */
+static inline bool kunit_resource_instance_match(struct kunit *test,
+						 const void *res,
+						 void *match_data)
+{
+	return res == match_data;
+}
+
+/**
+ * kunit_resource_destroy() - Find a kunit_resource and destroy it.
+ * @test: Test case to which the resource belongs.
+ * @match: Match function. Returns whether a given resource matches @match_data.
+ * @free: Must match free on the kunit_resource to free.
+ * @match_data: Data passed into @match.
+ *
+ * Free the latest kunit_resource of @test for which @free matches the
+ * kunit_resource_free_t associated with the resource and for which @match
+ * returns true.
+ *
+ * RETURNS:
+ * 0 if kunit_resource is found and freed, -ENOENT if not found.
+ */
+int kunit_resource_destroy(struct kunit *test,
+			   kunit_resource_match_t match,
+			   kunit_resource_free_t free,
+			   void *match_data);
+
+/**
+ * kunit_kmalloc() - Like kmalloc() except the allocation is *test managed*.
+ * @test: The test context object.
+ * @size: The size in bytes of the desired memory.
+ * @gfp: flags passed to underlying kmalloc().
+ *
+ * Just like `kmalloc(...)`, except the allocation is managed by the test case
+ * and is automatically cleaned up after the test case concludes. See &struct
+ * kunit_resource for more information.
+ */
+void *kunit_kmalloc(struct kunit *test, size_t size, gfp_t gfp);
+
+/**
+ * kunit_kfree() - Like kfree except for allocations managed by KUnit.
+ * @test: The test case to which the resource belongs.
+ * @ptr: The memory allocation to free.
+ */
+void kunit_kfree(struct kunit *test, const void *ptr);
+
+/**
+ * kunit_kzalloc() - Just like kunit_kmalloc(), but zeroes the allocation.
+ * @test: The test context object.
+ * @size: The size in bytes of the desired memory.
+ * @gfp: flags passed to underlying kmalloc().
+ *
+ * See kzalloc() and kunit_kmalloc() for more information.
+ */
+static inline void *kunit_kzalloc(struct kunit *test, size_t size, gfp_t gfp)
+{
+	return kunit_kmalloc(test, size, gfp | __GFP_ZERO);
+}
+
+void kunit_cleanup(struct kunit *test);
+
+#define kunit_printk(lvl, test, fmt, ...) \
+	printk(lvl "\t# %s: " fmt, (test)->name, ##__VA_ARGS__)
+
+/**
+ * kunit_info() - Prints an INFO level message associated with @test.
+ *
+ * @test: The test context object.
+ * @fmt:  A printk() style format string.
+ *
+ * Prints an info level message associated with the test suite being run.
+ * Takes a variable number of format parameters just like printk().
+ */
+#define kunit_info(test, fmt, ...) \
+	kunit_printk(KERN_INFO, test, fmt, ##__VA_ARGS__)
+
+/**
+ * kunit_warn() - Prints a WARN level message associated with @test.
+ *
+ * @test: The test context object.
+ * @fmt:  A printk() style format string.
+ *
+ * Prints a warning level message.
+ */
+#define kunit_warn(test, fmt, ...) \
+	kunit_printk(KERN_WARNING, test, fmt, ##__VA_ARGS__)
+
+/**
+ * kunit_err() - Prints an ERROR level message associated with @test.
+ *
+ * @test: The test context object.
+ * @fmt:  A printk() style format string.
+ *
+ * Prints an error level message.
+ */
+#define kunit_err(test, fmt, ...) \
+	kunit_printk(KERN_ERR, test, fmt, ##__VA_ARGS__)
+
+/**
+ * KUNIT_SUCCEED() - A no-op expectation. Only exists for code clarity.
+ * @test: The test context object.
+ *
+ * The opposite of KUNIT_FAIL(), it is an expectation that cannot fail. In other
+ * words, it does nothing and only exists for code clarity. See
+ * KUNIT_EXPECT_TRUE() for more information.
+ */
+#define KUNIT_SUCCEED(test) do {} while (0)
+
+void kunit_do_assertion(struct kunit *test,
+			struct kunit_assert *assert,
+			bool pass,
+			const char *fmt, ...);
+
+#define KUNIT_ASSERTION(test, pass, assert_class, INITIALIZER, fmt, ...) do {  \
+	struct assert_class __assertion = INITIALIZER;			       \
+	kunit_do_assertion(test,					       \
+			   &__assertion.assert,				       \
+			   pass,					       \
+			   fmt,						       \
+			   ##__VA_ARGS__);				       \
+} while (0)
+
+
+#define KUNIT_FAIL_ASSERTION(test, assert_type, fmt, ...)		       \
+	KUNIT_ASSERTION(test,						       \
+			false,						       \
+			kunit_fail_assert,				       \
+			KUNIT_INIT_FAIL_ASSERT_STRUCT(test, assert_type),      \
+			fmt,						       \
+			##__VA_ARGS__)
+
+/**
+ * KUNIT_FAIL() - Always causes a test to fail when evaluated.
+ * @test: The test context object.
+ * @fmt: an informational message to be printed when the assertion is made.
+ * @...: string format arguments.
+ *
+ * The opposite of KUNIT_SUCCEED(), it is an expectation that always fails. In
+ * other words, it always results in a failed expectation, and consequently
+ * always causes the test case to fail when evaluated. See KUNIT_EXPECT_TRUE()
+ * for more information.
+ */
+#define KUNIT_FAIL(test, fmt, ...)					       \
+	KUNIT_FAIL_ASSERTION(test,					       \
+			     KUNIT_EXPECTATION,				       \
+			     fmt,					       \
+			     ##__VA_ARGS__)
+
+#define KUNIT_UNARY_ASSERTION(test,					       \
+			      assert_type,				       \
+			      condition,				       \
+			      expected_true,				       \
+			      fmt,					       \
+			      ...)					       \
+	KUNIT_ASSERTION(test,						       \
+			!!(condition) == !!expected_true,		       \
+			kunit_unary_assert,				       \
+			KUNIT_INIT_UNARY_ASSERT_STRUCT(test,		       \
+						       assert_type,	       \
+						       #condition,	       \
+						       expected_true),	       \
+			fmt,						       \
+			##__VA_ARGS__)
+
+#define KUNIT_TRUE_MSG_ASSERTION(test, assert_type, condition, fmt, ...)       \
+	KUNIT_UNARY_ASSERTION(test,					       \
+			      assert_type,				       \
+			      condition,				       \
+			      true,					       \
+			      fmt,					       \
+			      ##__VA_ARGS__)
+
+#define KUNIT_TRUE_ASSERTION(test, assert_type, condition) \
+	KUNIT_TRUE_MSG_ASSERTION(test, assert_type, condition, NULL)
+
+#define KUNIT_FALSE_MSG_ASSERTION(test, assert_type, condition, fmt, ...)      \
+	KUNIT_UNARY_ASSERTION(test,					       \
+			      assert_type,				       \
+			      condition,				       \
+			      false,					       \
+			      fmt,					       \
+			      ##__VA_ARGS__)
+
+#define KUNIT_FALSE_ASSERTION(test, assert_type, condition) \
+	KUNIT_FALSE_MSG_ASSERTION(test, assert_type, condition, NULL)
+
+/*
+ * A factory macro for defining the assertions and expectations for the basic
+ * comparisons defined for the built in types.
+ *
+ * Unfortunately, there is no common type that all types can be promoted to for
+ * which all the binary operators behave the same way as for the actual types
+ * (for example, there is no type that long long and unsigned long long can
+ * both be cast to where the comparison result is preserved for all values). So
+ * the best we can do is do the comparison in the original types and then coerce
+ * everything to long long for printing; this way, the comparison behaves
+ * correctly and the printed out value usually makes sense without
+ * interpretation, but can always be interpreted to figure out the actual
+ * value.
+ */
+#define KUNIT_BASE_BINARY_ASSERTION(test,				       \
+				    assert_class,			       \
+				    ASSERT_CLASS_INIT,			       \
+				    assert_type,			       \
+				    left,				       \
+				    op,					       \
+				    right,				       \
+				    fmt,				       \
+				    ...)				       \
+do {									       \
+	typeof(left) __left = (left);					       \
+	typeof(right) __right = (right);				       \
+	((void)__typecheck(__left, __right));				       \
+									       \
+	KUNIT_ASSERTION(test,						       \
+			__left op __right,				       \
+			assert_class,					       \
+			ASSERT_CLASS_INIT(test,				       \
+					  assert_type,			       \
+					  #op,				       \
+					  #left,			       \
+					  __left,			       \
+					  #right,			       \
+					  __right),			       \
+			fmt,						       \
+			##__VA_ARGS__);					       \
+} while (0)
+
+#define KUNIT_BASE_EQ_MSG_ASSERTION(test,				       \
+				    assert_class,			       \
+				    ASSERT_CLASS_INIT,			       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ...)				       \
+	KUNIT_BASE_BINARY_ASSERTION(test,				       \
+				    assert_class,			       \
+				    ASSERT_CLASS_INIT,			       \
+				    assert_type,			       \
+				    left, ==, right,			       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BASE_NE_MSG_ASSERTION(test,				       \
+				    assert_class,			       \
+				    ASSERT_CLASS_INIT,			       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ...)				       \
+	KUNIT_BASE_BINARY_ASSERTION(test,				       \
+				    assert_class,			       \
+				    ASSERT_CLASS_INIT,			       \
+				    assert_type,			       \
+				    left, !=, right,			       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BASE_LT_MSG_ASSERTION(test,				       \
+				    assert_class,			       \
+				    ASSERT_CLASS_INIT,			       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ...)				       \
+	KUNIT_BASE_BINARY_ASSERTION(test,				       \
+				    assert_class,			       \
+				    ASSERT_CLASS_INIT,			       \
+				    assert_type,			       \
+				    left, <, right,			       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BASE_LE_MSG_ASSERTION(test,				       \
+				    assert_class,			       \
+				    ASSERT_CLASS_INIT,			       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ...)				       \
+	KUNIT_BASE_BINARY_ASSERTION(test,				       \
+				    assert_class,			       \
+				    ASSERT_CLASS_INIT,			       \
+				    assert_type,			       \
+				    left, <=, right,			       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BASE_GT_MSG_ASSERTION(test,				       \
+				    assert_class,			       \
+				    ASSERT_CLASS_INIT,			       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ...)				       \
+	KUNIT_BASE_BINARY_ASSERTION(test,				       \
+				    assert_class,			       \
+				    ASSERT_CLASS_INIT,			       \
+				    assert_type,			       \
+				    left, >, right,			       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BASE_GE_MSG_ASSERTION(test,				       \
+				    assert_class,			       \
+				    ASSERT_CLASS_INIT,			       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ...)				       \
+	KUNIT_BASE_BINARY_ASSERTION(test,				       \
+				    assert_class,			       \
+				    ASSERT_CLASS_INIT,			       \
+				    assert_type,			       \
+				    left, >=, right,			       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BINARY_EQ_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\
+	KUNIT_BASE_EQ_MSG_ASSERTION(test,				       \
+				    kunit_binary_assert,		       \
+				    KUNIT_INIT_BINARY_ASSERT_STRUCT,	       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BINARY_EQ_ASSERTION(test, assert_type, left, right)	       \
+	KUNIT_BINARY_EQ_MSG_ASSERTION(test,				       \
+				      assert_type,			       \
+				      left,				       \
+				      right,				       \
+				      NULL)
+
+#define KUNIT_BINARY_PTR_EQ_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ...)				       \
+	KUNIT_BASE_EQ_MSG_ASSERTION(test,				       \
+				    kunit_binary_ptr_assert,		       \
+				    KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT,       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BINARY_PTR_EQ_ASSERTION(test, assert_type, left, right)	       \
+	KUNIT_BINARY_PTR_EQ_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  NULL)
+
+#define KUNIT_BINARY_NE_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\
+	KUNIT_BASE_NE_MSG_ASSERTION(test,				       \
+				    kunit_binary_assert,		       \
+				    KUNIT_INIT_BINARY_ASSERT_STRUCT,	       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BINARY_NE_ASSERTION(test, assert_type, left, right)	       \
+	KUNIT_BINARY_NE_MSG_ASSERTION(test,				       \
+				      assert_type,			       \
+				      left,				       \
+				      right,				       \
+				      NULL)
+
+#define KUNIT_BINARY_PTR_NE_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ...)				       \
+	KUNIT_BASE_NE_MSG_ASSERTION(test,				       \
+				    kunit_binary_ptr_assert,		       \
+				    KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT,       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BINARY_PTR_NE_ASSERTION(test, assert_type, left, right)	       \
+	KUNIT_BINARY_PTR_NE_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  NULL)
+
+#define KUNIT_BINARY_LT_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\
+	KUNIT_BASE_LT_MSG_ASSERTION(test,				       \
+				    kunit_binary_assert,		       \
+				    KUNIT_INIT_BINARY_ASSERT_STRUCT,	       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BINARY_LT_ASSERTION(test, assert_type, left, right)	       \
+	KUNIT_BINARY_LT_MSG_ASSERTION(test,				       \
+				      assert_type,			       \
+				      left,				       \
+				      right,				       \
+				      NULL)
+
+#define KUNIT_BINARY_PTR_LT_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ...)				       \
+	KUNIT_BASE_LT_MSG_ASSERTION(test,				       \
+				    kunit_binary_ptr_assert,		       \
+				    KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT,       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BINARY_PTR_LT_ASSERTION(test, assert_type, left, right)	       \
+	KUNIT_BINARY_PTR_LT_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  NULL)
+
+#define KUNIT_BINARY_LE_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\
+	KUNIT_BASE_LE_MSG_ASSERTION(test,				       \
+				    kunit_binary_assert,		       \
+				    KUNIT_INIT_BINARY_ASSERT_STRUCT,	       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BINARY_LE_ASSERTION(test, assert_type, left, right)	       \
+	KUNIT_BINARY_LE_MSG_ASSERTION(test,				       \
+				      assert_type,			       \
+				      left,				       \
+				      right,				       \
+				      NULL)
+
+#define KUNIT_BINARY_PTR_LE_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ...)				       \
+	KUNIT_BASE_LE_MSG_ASSERTION(test,				       \
+				    kunit_binary_ptr_assert,		       \
+				    KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT,       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BINARY_PTR_LE_ASSERTION(test, assert_type, left, right)	       \
+	KUNIT_BINARY_PTR_LE_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  NULL)
+
+#define KUNIT_BINARY_GT_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\
+	KUNIT_BASE_GT_MSG_ASSERTION(test,				       \
+				    kunit_binary_assert,		       \
+				    KUNIT_INIT_BINARY_ASSERT_STRUCT,	       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BINARY_GT_ASSERTION(test, assert_type, left, right)	       \
+	KUNIT_BINARY_GT_MSG_ASSERTION(test,				       \
+				      assert_type,			       \
+				      left,				       \
+				      right,				       \
+				      NULL)
+
+#define KUNIT_BINARY_PTR_GT_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ...)				       \
+	KUNIT_BASE_GT_MSG_ASSERTION(test,				       \
+				    kunit_binary_ptr_assert,		       \
+				    KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT,       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BINARY_PTR_GT_ASSERTION(test, assert_type, left, right)	       \
+	KUNIT_BINARY_PTR_GT_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  NULL)
+
+#define KUNIT_BINARY_GE_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\
+	KUNIT_BASE_GE_MSG_ASSERTION(test,				       \
+				    kunit_binary_assert,		       \
+				    KUNIT_INIT_BINARY_ASSERT_STRUCT,	       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BINARY_GE_ASSERTION(test, assert_type, left, right)	       \
+	KUNIT_BINARY_GE_MSG_ASSERTION(test,				       \
+				      assert_type,			       \
+				      left,				       \
+				      right,				       \
+				      NULL)
+
+#define KUNIT_BINARY_PTR_GE_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ...)				       \
+	KUNIT_BASE_GE_MSG_ASSERTION(test,				       \
+				    kunit_binary_ptr_assert,		       \
+				    KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT,       \
+				    assert_type,			       \
+				    left,				       \
+				    right,				       \
+				    fmt,				       \
+				    ##__VA_ARGS__)
+
+#define KUNIT_BINARY_PTR_GE_ASSERTION(test, assert_type, left, right)	       \
+	KUNIT_BINARY_PTR_GE_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  NULL)
+
+#define KUNIT_BINARY_STR_ASSERTION(test,				       \
+				   assert_type,				       \
+				   left,				       \
+				   op,					       \
+				   right,				       \
+				   fmt,					       \
+				   ...)					       \
+do {									       \
+	typeof(left) __left = (left);					       \
+	typeof(right) __right = (right);				       \
+									       \
+	KUNIT_ASSERTION(test,						       \
+			strcmp(__left, __right) op 0,			       \
+			kunit_binary_str_assert,			       \
+			KUNIT_INIT_BINARY_ASSERT_STRUCT(test,		       \
+							assert_type,	       \
+							#op,		       \
+							#left,		       \
+							__left,		       \
+							#right,		       \
+							__right),	       \
+			fmt,						       \
+			##__VA_ARGS__);					       \
+} while (0)
+
+#define KUNIT_BINARY_STR_EQ_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ...)				       \
+	KUNIT_BINARY_STR_ASSERTION(test,				       \
+				   assert_type,				       \
+				   left, ==, right,			       \
+				   fmt,					       \
+				   ##__VA_ARGS__)
+
+#define KUNIT_BINARY_STR_EQ_ASSERTION(test, assert_type, left, right)	       \
+	KUNIT_BINARY_STR_EQ_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  NULL)
+
+#define KUNIT_BINARY_STR_NE_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ...)				       \
+	KUNIT_BINARY_STR_ASSERTION(test,				       \
+				   assert_type,				       \
+				   left, !=, right,			       \
+				   fmt,					       \
+				   ##__VA_ARGS__)
+
+#define KUNIT_BINARY_STR_NE_ASSERTION(test, assert_type, left, right)	       \
+	KUNIT_BINARY_STR_NE_MSG_ASSERTION(test,				       \
+					  assert_type,			       \
+					  left,				       \
+					  right,			       \
+					  NULL)
+
+#define KUNIT_PTR_NOT_ERR_OR_NULL_MSG_ASSERTION(test,			       \
+						assert_type,		       \
+						ptr,			       \
+						fmt,			       \
+						...)			       \
+do {									       \
+	typeof(ptr) __ptr = (ptr);					       \
+									       \
+	KUNIT_ASSERTION(test,						       \
+			!IS_ERR_OR_NULL(__ptr),				       \
+			kunit_ptr_not_err_assert,			       \
+			KUNIT_INIT_PTR_NOT_ERR_STRUCT(test,		       \
+						      assert_type,	       \
+						      #ptr,		       \
+						      __ptr),		       \
+			fmt,						       \
+			##__VA_ARGS__);					       \
+} while (0)
+
+#define KUNIT_PTR_NOT_ERR_OR_NULL_ASSERTION(test, assert_type, ptr)	       \
+	KUNIT_PTR_NOT_ERR_OR_NULL_MSG_ASSERTION(test,			       \
+						assert_type,		       \
+						ptr,			       \
+						NULL)
+
+/**
+ * KUNIT_EXPECT_TRUE() - Causes a test failure when the expression is not true.
+ * @test: The test context object.
+ * @condition: an arbitrary boolean expression. The test fails when this does
+ * not evaluate to true.
+ *
+ * This and expectations of the form `KUNIT_EXPECT_*` will cause the test case
+ * to fail when the specified condition is not met; however, it will not prevent
+ * the test case from continuing to run; this is otherwise known as an
+ * *expectation failure*.
+ */
+#define KUNIT_EXPECT_TRUE(test, condition) \
+	KUNIT_TRUE_ASSERTION(test, KUNIT_EXPECTATION, condition)
+
+#define KUNIT_EXPECT_TRUE_MSG(test, condition, fmt, ...)		       \
+	KUNIT_TRUE_MSG_ASSERTION(test,					       \
+				 KUNIT_EXPECTATION,			       \
+				 condition,				       \
+				 fmt,					       \
+				 ##__VA_ARGS__)
+
+/**
+ * KUNIT_EXPECT_FALSE() - Makes a test failure when the expression is not false.
+ * @test: The test context object.
+ * @condition: an arbitrary boolean expression. The test fails when this does
+ * not evaluate to false.
+ *
+ * Sets an expectation that @condition evaluates to false. See
+ * KUNIT_EXPECT_TRUE() for more information.
+ */
+#define KUNIT_EXPECT_FALSE(test, condition) \
+	KUNIT_FALSE_ASSERTION(test, KUNIT_EXPECTATION, condition)
+
+#define KUNIT_EXPECT_FALSE_MSG(test, condition, fmt, ...)		       \
+	KUNIT_FALSE_MSG_ASSERTION(test,					       \
+				  KUNIT_EXPECTATION,			       \
+				  condition,				       \
+				  fmt,					       \
+				  ##__VA_ARGS__)
+
+/**
+ * KUNIT_EXPECT_EQ() - Sets an expectation that @left and @right are equal.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a primitive C type.
+ * @right: an arbitrary expression that evaluates to a primitive C type.
+ *
+ * Sets an expectation that the values that @left and @right evaluate to are
+ * equal. This is semantically equivalent to
+ * KUNIT_EXPECT_TRUE(@test, (@left) == (@right)). See KUNIT_EXPECT_TRUE() for
+ * more information.
+ */
+#define KUNIT_EXPECT_EQ(test, left, right) \
+	KUNIT_BINARY_EQ_ASSERTION(test, KUNIT_EXPECTATION, left, right)
+
+#define KUNIT_EXPECT_EQ_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_EQ_MSG_ASSERTION(test,				       \
+				      KUNIT_EXPECTATION,		       \
+				      left,				       \
+				      right,				       \
+				      fmt,				       \
+				      ##__VA_ARGS__)
+
+/**
+ * KUNIT_EXPECT_PTR_EQ() - Expects that pointers @left and @right are equal.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a pointer.
+ * @right: an arbitrary expression that evaluates to a pointer.
+ *
+ * Sets an expectation that the values that @left and @right evaluate to are
+ * equal. This is semantically equivalent to
+ * KUNIT_EXPECT_TRUE(@test, (@left) == (@right)). See KUNIT_EXPECT_TRUE() for
+ * more information.
+ */
+#define KUNIT_EXPECT_PTR_EQ(test, left, right)				       \
+	KUNIT_BINARY_PTR_EQ_ASSERTION(test,				       \
+				      KUNIT_EXPECTATION,		       \
+				      left,				       \
+				      right)
+
+#define KUNIT_EXPECT_PTR_EQ_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_PTR_EQ_MSG_ASSERTION(test,				       \
+					  KUNIT_EXPECTATION,		       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ##__VA_ARGS__)
+
+/**
+ * KUNIT_EXPECT_NE() - An expectation that @left and @right are not equal.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a primitive C type.
+ * @right: an arbitrary expression that evaluates to a primitive C type.
+ *
+ * Sets an expectation that the values that @left and @right evaluate to are not
+ * equal. This is semantically equivalent to
+ * KUNIT_EXPECT_TRUE(@test, (@left) != (@right)). See KUNIT_EXPECT_TRUE() for
+ * more information.
+ */
+#define KUNIT_EXPECT_NE(test, left, right) \
+	KUNIT_BINARY_NE_ASSERTION(test, KUNIT_EXPECTATION, left, right)
+
+#define KUNIT_EXPECT_NE_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_NE_MSG_ASSERTION(test,				       \
+				      KUNIT_EXPECTATION,		       \
+				      left,				       \
+				      right,				       \
+				      fmt,				       \
+				      ##__VA_ARGS__)
+
+/**
+ * KUNIT_EXPECT_PTR_NE() - Expects that pointers @left and @right are not equal.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a pointer.
+ * @right: an arbitrary expression that evaluates to a pointer.
+ *
+ * Sets an expectation that the values that @left and @right evaluate to are not
+ * equal. This is semantically equivalent to
+ * KUNIT_EXPECT_TRUE(@test, (@left) != (@right)). See KUNIT_EXPECT_TRUE() for
+ * more information.
+ */
+#define KUNIT_EXPECT_PTR_NE(test, left, right)				       \
+	KUNIT_BINARY_PTR_NE_ASSERTION(test,				       \
+				      KUNIT_EXPECTATION,		       \
+				      left,				       \
+				      right)
+
+#define KUNIT_EXPECT_PTR_NE_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_PTR_NE_MSG_ASSERTION(test,				       \
+					  KUNIT_EXPECTATION,		       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ##__VA_ARGS__)
+
+/**
+ * KUNIT_EXPECT_LT() - An expectation that @left is less than @right.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a primitive C type.
+ * @right: an arbitrary expression that evaluates to a primitive C type.
+ *
+ * Sets an expectation that the value that @left evaluates to is less than the
+ * value that @right evaluates to. This is semantically equivalent to
+ * KUNIT_EXPECT_TRUE(@test, (@left) < (@right)). See KUNIT_EXPECT_TRUE() for
+ * more information.
+ */
+#define KUNIT_EXPECT_LT(test, left, right) \
+	KUNIT_BINARY_LT_ASSERTION(test, KUNIT_EXPECTATION, left, right)
+
+#define KUNIT_EXPECT_LT_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_LT_MSG_ASSERTION(test,				       \
+				      KUNIT_EXPECTATION,		       \
+				      left,				       \
+				      right,				       \
+				      fmt,				       \
+				      ##__VA_ARGS__)
+
+/**
+ * KUNIT_EXPECT_LE() - Expects that @left is less than or equal to @right.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a primitive C type.
+ * @right: an arbitrary expression that evaluates to a primitive C type.
+ *
+ * Sets an expectation that the value that @left evaluates to is less than or
+ * equal to the value that @right evaluates to. Semantically this is equivalent
+ * to KUNIT_EXPECT_TRUE(@test, (@left) <= (@right)). See KUNIT_EXPECT_TRUE() for
+ * more information.
+ */
+#define KUNIT_EXPECT_LE(test, left, right) \
+	KUNIT_BINARY_LE_ASSERTION(test, KUNIT_EXPECTATION, left, right)
+
+#define KUNIT_EXPECT_LE_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_LE_MSG_ASSERTION(test,				       \
+				      KUNIT_EXPECTATION,		       \
+				      left,				       \
+				      right,				       \
+				      fmt,				       \
+				      ##__VA_ARGS__)
+
+/**
+ * KUNIT_EXPECT_GT() - An expectation that @left is greater than @right.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a primitive C type.
+ * @right: an arbitrary expression that evaluates to a primitive C type.
+ *
+ * Sets an expectation that the value that @left evaluates to is greater than
+ * the value that @right evaluates to. This is semantically equivalent to
+ * KUNIT_EXPECT_TRUE(@test, (@left) > (@right)). See KUNIT_EXPECT_TRUE() for
+ * more information.
+ */
+#define KUNIT_EXPECT_GT(test, left, right) \
+	KUNIT_BINARY_GT_ASSERTION(test, KUNIT_EXPECTATION, left, right)
+
+#define KUNIT_EXPECT_GT_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_GT_MSG_ASSERTION(test,				       \
+				      KUNIT_EXPECTATION,		       \
+				      left,				       \
+				      right,				       \
+				      fmt,				       \
+				      ##__VA_ARGS__)
+
+/**
+ * KUNIT_EXPECT_GE() - Expects that @left is greater than or equal to @right.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a primitive C type.
+ * @right: an arbitrary expression that evaluates to a primitive C type.
+ *
+ * Sets an expectation that the value that @left evaluates to is greater than
+ * the value that @right evaluates to. This is semantically equivalent to
+ * KUNIT_EXPECT_TRUE(@test, (@left) >= (@right)). See KUNIT_EXPECT_TRUE() for
+ * more information.
+ */
+#define KUNIT_EXPECT_GE(test, left, right) \
+	KUNIT_BINARY_GE_ASSERTION(test, KUNIT_EXPECTATION, left, right)
+
+#define KUNIT_EXPECT_GE_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_GE_MSG_ASSERTION(test,				       \
+				      KUNIT_EXPECTATION,		       \
+				      left,				       \
+				      right,				       \
+				      fmt,				       \
+				      ##__VA_ARGS__)
+
+/**
+ * KUNIT_EXPECT_STREQ() - Expects that strings @left and @right are equal.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a null terminated string.
+ * @right: an arbitrary expression that evaluates to a null terminated string.
+ *
+ * Sets an expectation that the values that @left and @right evaluate to are
+ * equal. This is semantically equivalent to
+ * KUNIT_EXPECT_TRUE(@test, !strcmp((@left), (@right))). See KUNIT_EXPECT_TRUE()
+ * for more information.
+ */
+#define KUNIT_EXPECT_STREQ(test, left, right) \
+	KUNIT_BINARY_STR_EQ_ASSERTION(test, KUNIT_EXPECTATION, left, right)
+
+#define KUNIT_EXPECT_STREQ_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_STR_EQ_MSG_ASSERTION(test,				       \
+					  KUNIT_EXPECTATION,		       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ##__VA_ARGS__)
+
+/**
+ * KUNIT_EXPECT_STRNEQ() - Expects that strings @left and @right are not equal.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a null terminated string.
+ * @right: an arbitrary expression that evaluates to a null terminated string.
+ *
+ * Sets an expectation that the values that @left and @right evaluate to are
+ * not equal. This is semantically equivalent to
+ * KUNIT_EXPECT_TRUE(@test, strcmp((@left), (@right))). See KUNIT_EXPECT_TRUE()
+ * for more information.
+ */
+#define KUNIT_EXPECT_STRNEQ(test, left, right) \
+	KUNIT_BINARY_STR_NE_ASSERTION(test, KUNIT_EXPECTATION, left, right)
+
+#define KUNIT_EXPECT_STRNEQ_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_STR_NE_MSG_ASSERTION(test,				       \
+					  KUNIT_EXPECTATION,		       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ##__VA_ARGS__)
+
+/**
+ * KUNIT_EXPECT_NOT_ERR_OR_NULL() - Expects that @ptr is not null and not err.
+ * @test: The test context object.
+ * @ptr: an arbitrary pointer.
+ *
+ * Sets an expectation that the value that @ptr evaluates to is not null and not
+ * an errno stored in a pointer. This is semantically equivalent to
+ * KUNIT_EXPECT_TRUE(@test, !IS_ERR_OR_NULL(@ptr)). See KUNIT_EXPECT_TRUE() for
+ * more information.
+ */
+#define KUNIT_EXPECT_NOT_ERR_OR_NULL(test, ptr) \
+	KUNIT_PTR_NOT_ERR_OR_NULL_ASSERTION(test, KUNIT_EXPECTATION, ptr)
+
+#define KUNIT_EXPECT_NOT_ERR_OR_NULL_MSG(test, ptr, fmt, ...)		       \
+	KUNIT_PTR_NOT_ERR_OR_NULL_MSG_ASSERTION(test,			       \
+						KUNIT_EXPECTATION,	       \
+						ptr,			       \
+						fmt,			       \
+						##__VA_ARGS__)
+
+#define KUNIT_ASSERT_FAILURE(test, fmt, ...) \
+	KUNIT_FAIL_ASSERTION(test, KUNIT_ASSERTION, fmt, ##__VA_ARGS__)
+
+/**
+ * KUNIT_ASSERT_TRUE() - Sets an assertion that @condition is true.
+ * @test: The test context object.
+ * @condition: an arbitrary boolean expression. The test fails and aborts when
+ * this does not evaluate to true.
+ *
+ * This and assertions of the form `KUNIT_ASSERT_*` will cause the test case to
+ * fail *and immediately abort* when the specified condition is not met. Unlike
+ * an expectation failure, it will prevent the test case from continuing to run;
+ * this is otherwise known as an *assertion failure*.
+ */
+#define KUNIT_ASSERT_TRUE(test, condition) \
+	KUNIT_TRUE_ASSERTION(test, KUNIT_ASSERTION, condition)
+
+#define KUNIT_ASSERT_TRUE_MSG(test, condition, fmt, ...)		       \
+	KUNIT_TRUE_MSG_ASSERTION(test,					       \
+				 KUNIT_ASSERTION,			       \
+				 condition,				       \
+				 fmt,					       \
+				 ##__VA_ARGS__)
+
+/**
+ * KUNIT_ASSERT_FALSE() - Sets an assertion that @condition is false.
+ * @test: The test context object.
+ * @condition: an arbitrary boolean expression.
+ *
+ * Sets an assertion that the value that @condition evaluates to is false. This
+ * is the same as KUNIT_EXPECT_FALSE(), except it causes an assertion failure
+ * (see KUNIT_ASSERT_TRUE()) when the assertion is not met.
+ */
+#define KUNIT_ASSERT_FALSE(test, condition) \
+	KUNIT_FALSE_ASSERTION(test, KUNIT_ASSERTION, condition)
+
+#define KUNIT_ASSERT_FALSE_MSG(test, condition, fmt, ...)		       \
+	KUNIT_FALSE_MSG_ASSERTION(test,					       \
+				  KUNIT_ASSERTION,			       \
+				  condition,				       \
+				  fmt,					       \
+				  ##__VA_ARGS__)
+
+/**
+ * KUNIT_ASSERT_EQ() - Sets an assertion that @left and @right are equal.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a primitive C type.
+ * @right: an arbitrary expression that evaluates to a primitive C type.
+ *
+ * Sets an assertion that the values that @left and @right evaluate to are
+ * equal. This is the same as KUNIT_EXPECT_EQ(), except it causes an assertion
+ * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met.
+ */
+#define KUNIT_ASSERT_EQ(test, left, right) \
+	KUNIT_BINARY_EQ_ASSERTION(test, KUNIT_ASSERTION, left, right)
+
+#define KUNIT_ASSERT_EQ_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_EQ_MSG_ASSERTION(test,				       \
+				      KUNIT_ASSERTION,			       \
+				      left,				       \
+				      right,				       \
+				      fmt,				       \
+				      ##__VA_ARGS__)
+
+/**
+ * KUNIT_ASSERT_PTR_EQ() - Asserts that pointers @left and @right are equal.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a pointer.
+ * @right: an arbitrary expression that evaluates to a pointer.
+ *
+ * Sets an assertion that the values that @left and @right evaluate to are
+ * equal. This is the same as KUNIT_EXPECT_EQ(), except it causes an assertion
+ * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met.
+ */
+#define KUNIT_ASSERT_PTR_EQ(test, left, right) \
+	KUNIT_BINARY_PTR_EQ_ASSERTION(test, KUNIT_ASSERTION, left, right)
+
+#define KUNIT_ASSERT_PTR_EQ_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_PTR_EQ_MSG_ASSERTION(test,				       \
+					  KUNIT_ASSERTION,		       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ##__VA_ARGS__)
+
+/**
+ * KUNIT_ASSERT_NE() - An assertion that @left and @right are not equal.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a primitive C type.
+ * @right: an arbitrary expression that evaluates to a primitive C type.
+ *
+ * Sets an assertion that the values that @left and @right evaluate to are not
+ * equal. This is the same as KUNIT_EXPECT_NE(), except it causes an assertion
+ * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met.
+ */
+#define KUNIT_ASSERT_NE(test, left, right) \
+	KUNIT_BINARY_NE_ASSERTION(test, KUNIT_ASSERTION, left, right)
+
+#define KUNIT_ASSERT_NE_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_NE_MSG_ASSERTION(test,				       \
+				      KUNIT_ASSERTION,			       \
+				      left,				       \
+				      right,				       \
+				      fmt,				       \
+				      ##__VA_ARGS__)
+
+/**
+ * KUNIT_ASSERT_PTR_NE() - Asserts that pointers @left and @right are not equal.
+ * KUNIT_ASSERT_PTR_EQ() - Asserts that pointers @left and @right are equal.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a pointer.
+ * @right: an arbitrary expression that evaluates to a pointer.
+ *
+ * Sets an assertion that the values that @left and @right evaluate to are not
+ * equal. This is the same as KUNIT_EXPECT_NE(), except it causes an assertion
+ * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met.
+ */
+#define KUNIT_ASSERT_PTR_NE(test, left, right) \
+	KUNIT_BINARY_PTR_NE_ASSERTION(test, KUNIT_ASSERTION, left, right)
+
+#define KUNIT_ASSERT_PTR_NE_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_PTR_NE_MSG_ASSERTION(test,				       \
+					  KUNIT_ASSERTION,		       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ##__VA_ARGS__)
+/**
+ * KUNIT_ASSERT_LT() - An assertion that @left is less than @right.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a primitive C type.
+ * @right: an arbitrary expression that evaluates to a primitive C type.
+ *
+ * Sets an assertion that the value that @left evaluates to is less than the
+ * value that @right evaluates to. This is the same as KUNIT_EXPECT_LT(), except
+ * it causes an assertion failure (see KUNIT_ASSERT_TRUE()) when the assertion
+ * is not met.
+ */
+#define KUNIT_ASSERT_LT(test, left, right) \
+	KUNIT_BINARY_LT_ASSERTION(test, KUNIT_ASSERTION, left, right)
+
+#define KUNIT_ASSERT_LT_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_LT_MSG_ASSERTION(test,				       \
+				      KUNIT_ASSERTION,			       \
+				      left,				       \
+				      right,				       \
+				      fmt,				       \
+				      ##__VA_ARGS__)
+/**
+ * KUNIT_ASSERT_LE() - An assertion that @left is less than or equal to @right.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a primitive C type.
+ * @right: an arbitrary expression that evaluates to a primitive C type.
+ *
+ * Sets an assertion that the value that @left evaluates to is less than or
+ * equal to the value that @right evaluates to. This is the same as
+ * KUNIT_EXPECT_LE(), except it causes an assertion failure (see
+ * KUNIT_ASSERT_TRUE()) when the assertion is not met.
+ */
+#define KUNIT_ASSERT_LE(test, left, right) \
+	KUNIT_BINARY_LE_ASSERTION(test, KUNIT_ASSERTION, left, right)
+
+#define KUNIT_ASSERT_LE_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_LE_MSG_ASSERTION(test,				       \
+				      KUNIT_ASSERTION,			       \
+				      left,				       \
+				      right,				       \
+				      fmt,				       \
+				      ##__VA_ARGS__)
+
+/**
+ * KUNIT_ASSERT_GT() - An assertion that @left is greater than @right.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a primitive C type.
+ * @right: an arbitrary expression that evaluates to a primitive C type.
+ *
+ * Sets an assertion that the value that @left evaluates to is greater than the
+ * value that @right evaluates to. This is the same as KUNIT_EXPECT_GT(), except
+ * it causes an assertion failure (see KUNIT_ASSERT_TRUE()) when the assertion
+ * is not met.
+ */
+#define KUNIT_ASSERT_GT(test, left, right) \
+	KUNIT_BINARY_GT_ASSERTION(test, KUNIT_ASSERTION, left, right)
+
+#define KUNIT_ASSERT_GT_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_GT_MSG_ASSERTION(test,				       \
+				      KUNIT_ASSERTION,			       \
+				      left,				       \
+				      right,				       \
+				      fmt,				       \
+				      ##__VA_ARGS__)
+
+/**
+ * KUNIT_ASSERT_GE() - Assertion that @left is greater than or equal to @right.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a primitive C type.
+ * @right: an arbitrary expression that evaluates to a primitive C type.
+ *
+ * Sets an assertion that the value that @left evaluates to is greater than the
+ * value that @right evaluates to. This is the same as KUNIT_EXPECT_GE(), except
+ * it causes an assertion failure (see KUNIT_ASSERT_TRUE()) when the assertion
+ * is not met.
+ */
+#define KUNIT_ASSERT_GE(test, left, right) \
+	KUNIT_BINARY_GE_ASSERTION(test, KUNIT_ASSERTION, left, right)
+
+#define KUNIT_ASSERT_GE_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_GE_MSG_ASSERTION(test,				       \
+				      KUNIT_ASSERTION,			       \
+				      left,				       \
+				      right,				       \
+				      fmt,				       \
+				      ##__VA_ARGS__)
+
+/**
+ * KUNIT_ASSERT_STREQ() - An assertion that strings @left and @right are equal.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a null terminated string.
+ * @right: an arbitrary expression that evaluates to a null terminated string.
+ *
+ * Sets an assertion that the values that @left and @right evaluate to are
+ * equal. This is the same as KUNIT_EXPECT_STREQ(), except it causes an
+ * assertion failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met.
+ */
+#define KUNIT_ASSERT_STREQ(test, left, right) \
+	KUNIT_BINARY_STR_EQ_ASSERTION(test, KUNIT_ASSERTION, left, right)
+
+#define KUNIT_ASSERT_STREQ_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_STR_EQ_MSG_ASSERTION(test,				       \
+					  KUNIT_ASSERTION,		       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ##__VA_ARGS__)
+
+/**
+ * KUNIT_ASSERT_STRNEQ() - Expects that strings @left and @right are not equal.
+ * @test: The test context object.
+ * @left: an arbitrary expression that evaluates to a null terminated string.
+ * @right: an arbitrary expression that evaluates to a null terminated string.
+ *
+ * Sets an expectation that the values that @left and @right evaluate to are
+ * not equal. This is semantically equivalent to
+ * KUNIT_ASSERT_TRUE(@test, strcmp((@left), (@right))). See KUNIT_ASSERT_TRUE()
+ * for more information.
+ */
+#define KUNIT_ASSERT_STRNEQ(test, left, right) \
+	KUNIT_BINARY_STR_NE_ASSERTION(test, KUNIT_ASSERTION, left, right)
+
+#define KUNIT_ASSERT_STRNEQ_MSG(test, left, right, fmt, ...)		       \
+	KUNIT_BINARY_STR_NE_MSG_ASSERTION(test,				       \
+					  KUNIT_ASSERTION,		       \
+					  left,				       \
+					  right,			       \
+					  fmt,				       \
+					  ##__VA_ARGS__)
+
+/**
+ * KUNIT_ASSERT_NOT_ERR_OR_NULL() - Assertion that @ptr is not null and not err.
+ * @test: The test context object.
+ * @ptr: an arbitrary pointer.
+ *
+ * Sets an assertion that the value that @ptr evaluates to is not null and not
+ * an errno stored in a pointer. This is the same as
+ * KUNIT_EXPECT_NOT_ERR_OR_NULL(), except it causes an assertion failure (see
+ * KUNIT_ASSERT_TRUE()) when the assertion is not met.
+ */
+#define KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr) \
+	KUNIT_PTR_NOT_ERR_OR_NULL_ASSERTION(test, KUNIT_ASSERTION, ptr)
+
+#define KUNIT_ASSERT_NOT_ERR_OR_NULL_MSG(test, ptr, fmt, ...)		       \
+	KUNIT_PTR_NOT_ERR_OR_NULL_MSG_ASSERTION(test,			       \
+						KUNIT_ASSERTION,	       \
+						ptr,			       \
+						fmt,			       \
+						##__VA_ARGS__)
+
+#endif /* _KUNIT_TEST_H */
diff --git a/include/kunit/try-catch.h b/include/kunit/try-catch.h
new file mode 100644
index 000000000000..404f336cbdc8
--- /dev/null
+++ b/include/kunit/try-catch.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * An API to allow a function, that may fail, to be executed, and recover in a
+ * controlled manner.
+ *
+ * Copyright (C) 2019, Google LLC.
+ * Author: Brendan Higgins <brendanhiggins@google.com>
+ */
+
+#ifndef _KUNIT_TRY_CATCH_H
+#define _KUNIT_TRY_CATCH_H
+
+#include <linux/types.h>
+
+typedef void (*kunit_try_catch_func_t)(void *);
+
+struct completion;
+struct kunit;
+
+/**
+ * struct kunit_try_catch - provides a generic way to run code which might fail.
+ * @test: The test case that is currently being executed.
+ * @try_completion: Completion that the control thread waits on while test runs.
+ * @try_result: Contains any errno obtained while running test case.
+ * @try: The function, the test case, to attempt to run.
+ * @catch: The function called if @try bails out.
+ * @context: used to pass user data to the try and catch functions.
+ *
+ * kunit_try_catch provides a generic, architecture independent way to execute
+ * an arbitrary function of type kunit_try_catch_func_t which may bail out by
+ * calling kunit_try_catch_throw(). If kunit_try_catch_throw() is called, @try
+ * is stopped at the site of invocation and @catch is called.
+ *
+ * struct kunit_try_catch provides a generic interface for the functionality
+ * needed to implement kunit->abort() which in turn is needed for implementing
+ * assertions. Assertions allow stating a precondition for a test simplifying
+ * how test cases are written and presented.
+ *
+ * Assertions are like expectations, except they abort (call
+ * kunit_try_catch_throw()) when the specified condition is not met. This is
+ * useful when you look at a test case as a logical statement about some piece
+ * of code, where assertions are the premises for the test case, and the
+ * conclusion is a set of predicates, rather expectations, that must all be
+ * true. If your premises are violated, it does not makes sense to continue.
+ */
+struct kunit_try_catch {
+	/* private: internal use only. */
+	struct kunit *test;
+	struct completion *try_completion;
+	int try_result;
+	kunit_try_catch_func_t try;
+	kunit_try_catch_func_t catch;
+	void *context;
+};
+
+void kunit_try_catch_init(struct kunit_try_catch *try_catch,
+			  struct kunit *test,
+			  kunit_try_catch_func_t try,
+			  kunit_try_catch_func_t catch);
+
+void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context);
+
+void __noreturn kunit_try_catch_throw(struct kunit_try_catch *try_catch);
+
+static inline int kunit_try_catch_get_result(struct kunit_try_catch *try_catch)
+{
+	return try_catch->try_result;
+}
+
+/*
+ * Exposed for testing only.
+ */
+void kunit_generic_try_catch_init(struct kunit_try_catch *try_catch);
+
+#endif /* _KUNIT_TRY_CATCH_H */
diff --git a/include/kvm/arm_hypercalls.h b/include/kvm/arm_hypercalls.h
new file mode 100644
index 000000000000..0e2509d27910
--- /dev/null
+++ b/include/kvm/arm_hypercalls.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 Arm Ltd. */
+
+#ifndef __KVM_ARM_HYPERCALLS_H
+#define __KVM_ARM_HYPERCALLS_H
+
+#include <asm/kvm_emulate.h>
+
+int kvm_hvc_call_handler(struct kvm_vcpu *vcpu);
+
+static inline u32 smccc_get_function(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 0);
+}
+
+static inline unsigned long smccc_get_arg1(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 1);
+}
+
+static inline unsigned long smccc_get_arg2(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 2);
+}
+
+static inline unsigned long smccc_get_arg3(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 3);
+}
+
+static inline void smccc_set_retval(struct kvm_vcpu *vcpu,
+				    unsigned long a0,
+				    unsigned long a1,
+				    unsigned long a2,
+				    unsigned long a3)
+{
+	vcpu_set_reg(vcpu, 0, a0);
+	vcpu_set_reg(vcpu, 1, a1);
+	vcpu_set_reg(vcpu, 2, a2);
+	vcpu_set_reg(vcpu, 3, a3);
+}
+
+#endif
diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h
index 632e78bdef4d..5b58bd2fe088 100644
--- a/include/kvm/arm_psci.h
+++ b/include/kvm/arm_psci.h
@@ -40,7 +40,7 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm)
 }
 
 
-int kvm_hvc_call_handler(struct kvm_vcpu *vcpu);
+int kvm_psci_call(struct kvm_vcpu *vcpu);
 
 struct kvm_one_reg;
 
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index af4f09c02bf1..9d53f545a3d5 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -240,7 +240,7 @@ struct vgic_dist {
 	 * Contains the attributes and gpa of the LPI configuration table.
 	 * Since we report GICR_TYPER.CommonLPIAff as 0b00, we can share
 	 * one address across all redistributors.
-	 * GICv3 spec: 6.1.2 "LPI Configuration tables"
+	 * GICv3 spec: IHI 0069E 6.1.1 "LPI Configuration tables"
 	 */
 	u64			propbaser;
 
@@ -378,8 +378,6 @@ static inline int kvm_vgic_get_max_vcpus(void)
 	return kvm_vgic_global_state.max_gic_vcpus;
 }
 
-int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
-
 /**
  * kvm_vgic_setup_default_irq_routing:
  * Setup a default flat gsi routing table mapping all SPIs
@@ -396,7 +394,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int irq,
 int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq,
 				 struct kvm_kernel_irq_routing_entry *irq_entry);
 
-void kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu);
-void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu);
+int vgic_v4_load(struct kvm_vcpu *vcpu);
+int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db);
 
 #endif /* __KVM_ARM_VGIC_H */
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 080012a6f025..59494df0f55b 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -45,6 +45,7 @@
 #define ARM_SMCCC_OWNER_SIP		2
 #define ARM_SMCCC_OWNER_OEM		3
 #define ARM_SMCCC_OWNER_STANDARD	4
+#define ARM_SMCCC_OWNER_STANDARD_HYP	5
 #define ARM_SMCCC_OWNER_TRUSTED_APP	48
 #define ARM_SMCCC_OWNER_TRUSTED_APP_END	49
 #define ARM_SMCCC_OWNER_TRUSTED_OS	50
@@ -80,6 +81,22 @@
 
 #include <linux/linkage.h>
 #include <linux/types.h>
+
+enum arm_smccc_conduit {
+	SMCCC_CONDUIT_NONE,
+	SMCCC_CONDUIT_SMC,
+	SMCCC_CONDUIT_HVC,
+};
+
+/**
+ * arm_smccc_1_1_get_conduit()
+ *
+ * Returns the conduit to be used for SMCCCv1.1 or later.
+ *
+ * When SMCCCv1.1 is not present, returns SMCCC_CONDUIT_NONE.
+ */
+enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void);
+
 /**
  * struct arm_smccc_res - Result from SMC/HVC call
  * @a0-a3 result values from registers 0 to 3
@@ -302,5 +319,63 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 #define SMCCC_RET_NOT_SUPPORTED			-1
 #define SMCCC_RET_NOT_REQUIRED			-2
 
+/*
+ * Like arm_smccc_1_1* but always returns SMCCC_RET_NOT_SUPPORTED.
+ * Used when the SMCCC conduit is not defined. The empty asm statement
+ * avoids compiler warnings about unused variables.
+ */
+#define __fail_smccc_1_1(...)						\
+	do {								\
+		__declare_args(__count_args(__VA_ARGS__), __VA_ARGS__);	\
+		asm ("" __constraints(__count_args(__VA_ARGS__)));	\
+		if (___res)						\
+			___res->a0 = SMCCC_RET_NOT_SUPPORTED;		\
+	} while (0)
+
+/*
+ * arm_smccc_1_1_invoke() - make an SMCCC v1.1 compliant call
+ *
+ * This is a variadic macro taking one to eight source arguments, and
+ * an optional return structure.
+ *
+ * @a0-a7: arguments passed in registers 0 to 7
+ * @res: result values from registers 0 to 3
+ *
+ * This macro will make either an HVC call or an SMC call depending on the
+ * current SMCCC conduit. If no valid conduit is available then -1
+ * (SMCCC_RET_NOT_SUPPORTED) is returned in @res.a0 (if supplied).
+ *
+ * The return value also provides the conduit that was used.
+ */
+#define arm_smccc_1_1_invoke(...) ({					\
+		int method = arm_smccc_1_1_get_conduit();		\
+		switch (method) {					\
+		case SMCCC_CONDUIT_HVC:					\
+			arm_smccc_1_1_hvc(__VA_ARGS__);			\
+			break;						\
+		case SMCCC_CONDUIT_SMC:					\
+			arm_smccc_1_1_smc(__VA_ARGS__);			\
+			break;						\
+		default:						\
+			__fail_smccc_1_1(__VA_ARGS__);			\
+			method = SMCCC_CONDUIT_NONE;			\
+			break;						\
+		}							\
+		method;							\
+	})
+
+/* Paravirtualised time calls (defined by ARM DEN0057A) */
+#define ARM_SMCCC_HV_PV_TIME_FEATURES				\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
+			   ARM_SMCCC_SMC_64,			\
+			   ARM_SMCCC_OWNER_STANDARD_HYP,	\
+			   0x20)
+
+#define ARM_SMCCC_HV_PV_TIME_ST					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
+			   ARM_SMCCC_SMC_64,			\
+			   ARM_SMCCC_OWNER_STANDARD_HYP,	\
+			   0x21)
+
 #endif /*__ASSEMBLY__*/
 #endif /*__LINUX_ARM_SMCCC_H*/
diff --git a/include/linux/arm_sdei.h b/include/linux/arm_sdei.h
index 3305ea7f9dc7..0a241c5c911d 100644
--- a/include/linux/arm_sdei.h
+++ b/include/linux/arm_sdei.h
@@ -5,12 +5,6 @@
 
 #include <uapi/linux/arm_sdei.h>
 
-enum sdei_conduit_types {
-	CONDUIT_INVALID = 0,
-	CONDUIT_SMC,
-	CONDUIT_HVC,
-};
-
 #include <acpi/ghes.h>
 
 #ifdef CONFIG_ARM_SDE_INTERFACE
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index bed9e43f9426..19394c77ed99 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -15,7 +15,9 @@
  */
 
 #include <linux/cgroup.h>
+#include <linux/percpu.h>
 #include <linux/percpu_counter.h>
+#include <linux/u64_stats_sync.h>
 #include <linux/seq_file.h>
 #include <linux/radix-tree.h>
 #include <linux/blkdev.h>
@@ -31,15 +33,12 @@
 
 #ifdef CONFIG_BLK_CGROUP
 
-enum blkg_rwstat_type {
-	BLKG_RWSTAT_READ,
-	BLKG_RWSTAT_WRITE,
-	BLKG_RWSTAT_SYNC,
-	BLKG_RWSTAT_ASYNC,
-	BLKG_RWSTAT_DISCARD,
+enum blkg_iostat_type {
+	BLKG_IOSTAT_READ,
+	BLKG_IOSTAT_WRITE,
+	BLKG_IOSTAT_DISCARD,
 
-	BLKG_RWSTAT_NR,
-	BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
+	BLKG_IOSTAT_NR,
 };
 
 struct blkcg_gq;
@@ -61,17 +60,15 @@ struct blkcg {
 #endif
 };
 
-/*
- * blkg_[rw]stat->aux_cnt is excluded for local stats but included for
- * recursive.  Used to carry stats of dead children.
- */
-struct blkg_rwstat {
-	struct percpu_counter		cpu_cnt[BLKG_RWSTAT_NR];
-	atomic64_t			aux_cnt[BLKG_RWSTAT_NR];
+struct blkg_iostat {
+	u64				bytes[BLKG_IOSTAT_NR];
+	u64				ios[BLKG_IOSTAT_NR];
 };
 
-struct blkg_rwstat_sample {
-	u64				cnt[BLKG_RWSTAT_NR];
+struct blkg_iostat_set {
+	struct u64_stats_sync		sync;
+	struct blkg_iostat		cur;
+	struct blkg_iostat		last;
 };
 
 /*
@@ -127,8 +124,8 @@ struct blkcg_gq {
 	/* is this blkg online? protected by both blkcg and q locks */
 	bool				online;
 
-	struct blkg_rwstat		stat_bytes;
-	struct blkg_rwstat		stat_ios;
+	struct blkg_iostat_set __percpu	*iostat_cpu;
+	struct blkg_iostat_set		iostat;
 
 	struct blkg_policy_data		*pd[BLKCG_MAX_POLS];
 
@@ -202,13 +199,6 @@ int blkcg_activate_policy(struct request_queue *q,
 void blkcg_deactivate_policy(struct request_queue *q,
 			     const struct blkcg_policy *pol);
 
-static inline u64 blkg_rwstat_read_counter(struct blkg_rwstat *rwstat,
-		unsigned int idx)
-{
-	return atomic64_read(&rwstat->aux_cnt[idx]) +
-		percpu_counter_sum_positive(&rwstat->cpu_cnt[idx]);
-}
-
 const char *blkg_dev_name(struct blkcg_gq *blkg);
 void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
 		       u64 (*prfill)(struct seq_file *,
@@ -216,17 +206,6 @@ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
 		       const struct blkcg_policy *pol, int data,
 		       bool show_total);
 u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v);
-u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
-			 const struct blkg_rwstat_sample *rwstat);
-u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
-		       int off);
-int blkg_print_stat_bytes(struct seq_file *sf, void *v);
-int blkg_print_stat_ios(struct seq_file *sf, void *v);
-int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v);
-int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v);
-
-void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
-		int off, struct blkg_rwstat_sample *sum);
 
 struct blkg_conf_ctx {
 	struct gendisk			*disk;
@@ -578,128 +557,6 @@ static inline void blkg_put(struct blkcg_gq *blkg)
 		if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css),	\
 					      (p_blkg)->q, false)))
 
-static inline int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp)
-{
-	int i, ret;
-
-	for (i = 0; i < BLKG_RWSTAT_NR; i++) {
-		ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp);
-		if (ret) {
-			while (--i >= 0)
-				percpu_counter_destroy(&rwstat->cpu_cnt[i]);
-			return ret;
-		}
-		atomic64_set(&rwstat->aux_cnt[i], 0);
-	}
-	return 0;
-}
-
-static inline void blkg_rwstat_exit(struct blkg_rwstat *rwstat)
-{
-	int i;
-
-	for (i = 0; i < BLKG_RWSTAT_NR; i++)
-		percpu_counter_destroy(&rwstat->cpu_cnt[i]);
-}
-
-/**
- * blkg_rwstat_add - add a value to a blkg_rwstat
- * @rwstat: target blkg_rwstat
- * @op: REQ_OP and flags
- * @val: value to add
- *
- * Add @val to @rwstat.  The counters are chosen according to @rw.  The
- * caller is responsible for synchronizing calls to this function.
- */
-static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
-				   unsigned int op, uint64_t val)
-{
-	struct percpu_counter *cnt;
-
-	if (op_is_discard(op))
-		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD];
-	else if (op_is_write(op))
-		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE];
-	else
-		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ];
-
-	percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
-
-	if (op_is_sync(op))
-		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC];
-	else
-		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC];
-
-	percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
-}
-
-/**
- * blkg_rwstat_read - read the current values of a blkg_rwstat
- * @rwstat: blkg_rwstat to read
- *
- * Read the current snapshot of @rwstat and return it in the aux counts.
- */
-static inline void blkg_rwstat_read(struct blkg_rwstat *rwstat,
-		struct blkg_rwstat_sample *result)
-{
-	int i;
-
-	for (i = 0; i < BLKG_RWSTAT_NR; i++)
-		result->cnt[i] =
-			percpu_counter_sum_positive(&rwstat->cpu_cnt[i]);
-}
-
-/**
- * blkg_rwstat_total - read the total count of a blkg_rwstat
- * @rwstat: blkg_rwstat to read
- *
- * Return the total count of @rwstat regardless of the IO direction.  This
- * function can be called without synchronization and takes care of u64
- * atomicity.
- */
-static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat)
-{
-	struct blkg_rwstat_sample tmp = { };
-
-	blkg_rwstat_read(rwstat, &tmp);
-	return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE];
-}
-
-/**
- * blkg_rwstat_reset - reset a blkg_rwstat
- * @rwstat: blkg_rwstat to reset
- */
-static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat)
-{
-	int i;
-
-	for (i = 0; i < BLKG_RWSTAT_NR; i++) {
-		percpu_counter_set(&rwstat->cpu_cnt[i], 0);
-		atomic64_set(&rwstat->aux_cnt[i], 0);
-	}
-}
-
-/**
- * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count
- * @to: the destination blkg_rwstat
- * @from: the source
- *
- * Add @from's count including the aux one to @to's aux count.
- */
-static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to,
-				       struct blkg_rwstat *from)
-{
-	u64 sum[BLKG_RWSTAT_NR];
-	int i;
-
-	for (i = 0; i < BLKG_RWSTAT_NR; i++)
-		sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]);
-
-	for (i = 0; i < BLKG_RWSTAT_NR; i++)
-		atomic64_add(sum[i] + atomic64_read(&from->aux_cnt[i]),
-			     &to->aux_cnt[i]);
-}
-
 #ifdef CONFIG_BLK_DEV_THROTTLING
 extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 			   struct bio *bio);
@@ -745,15 +602,33 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 	throtl = blk_throtl_bio(q, blkg, bio);
 
 	if (!throtl) {
+		struct blkg_iostat_set *bis;
+		int rwd, cpu;
+
+		if (op_is_discard(bio->bi_opf))
+			rwd = BLKG_IOSTAT_DISCARD;
+		else if (op_is_write(bio->bi_opf))
+			rwd = BLKG_IOSTAT_WRITE;
+		else
+			rwd = BLKG_IOSTAT_READ;
+
+		cpu = get_cpu();
+		bis = per_cpu_ptr(blkg->iostat_cpu, cpu);
+		u64_stats_update_begin(&bis->sync);
+
 		/*
 		 * If the bio is flagged with BIO_QUEUE_ENTERED it means this
 		 * is a split bio and we would have already accounted for the
 		 * size of the bio.
 		 */
 		if (!bio_flagged(bio, BIO_QUEUE_ENTERED))
-			blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf,
-					bio->bi_iter.bi_size);
-		blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1);
+			bis->cur.bytes[rwd] += bio->bi_iter.bi_size;
+		bis->cur.ios[rwd]++;
+
+		u64_stats_update_end(&bis->sync);
+		if (cgroup_subsys_on_dfl(io_cgrp_subsys))
+			cgroup_rstat_updated(blkg->blkcg->css.cgroup, cpu);
+		put_cpu();
 	}
 
 	blkcg_bio_issue_init(bio);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 0bf056de5cc3..11cfd6470b1a 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -10,103 +10,239 @@ struct blk_mq_tags;
 struct blk_flush_queue;
 
 /**
- * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware block device
+ * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware
+ * block device
  */
 struct blk_mq_hw_ctx {
 	struct {
+		/** @lock: Protects the dispatch list. */
 		spinlock_t		lock;
+		/**
+		 * @dispatch: Used for requests that are ready to be
+		 * dispatched to the hardware but for some reason (e.g. lack of
+		 * resources) could not be sent to the hardware. As soon as the
+		 * driver can send new requests, requests at this list will
+		 * be sent first for a fairer dispatch.
+		 */
 		struct list_head	dispatch;
-		unsigned long		state;		/* BLK_MQ_S_* flags */
+		 /**
+		  * @state: BLK_MQ_S_* flags. Defines the state of the hw
+		  * queue (active, scheduled to restart, stopped).
+		  */
+		unsigned long		state;
 	} ____cacheline_aligned_in_smp;
 
+	/**
+	 * @run_work: Used for scheduling a hardware queue run at a later time.
+	 */
 	struct delayed_work	run_work;
+	/** @cpumask: Map of available CPUs where this hctx can run. */
 	cpumask_var_t		cpumask;
+	/**
+	 * @next_cpu: Used by blk_mq_hctx_next_cpu() for round-robin CPU
+	 * selection from @cpumask.
+	 */
 	int			next_cpu;
+	/**
+	 * @next_cpu_batch: Counter of how many works left in the batch before
+	 * changing to the next CPU.
+	 */
 	int			next_cpu_batch;
 
-	unsigned long		flags;		/* BLK_MQ_F_* flags */
+	/** @flags: BLK_MQ_F_* flags. Defines the behaviour of the queue. */
+	unsigned long		flags;
 
+	/**
+	 * @sched_data: Pointer owned by the IO scheduler attached to a request
+	 * queue. It's up to the IO scheduler how to use this pointer.
+	 */
 	void			*sched_data;
+	/**
+	 * @queue: Pointer to the request queue that owns this hardware context.
+	 */
 	struct request_queue	*queue;
+	/** @fq: Queue of requests that need to perform a flush operation. */
 	struct blk_flush_queue	*fq;
 
+	/**
+	 * @driver_data: Pointer to data owned by the block driver that created
+	 * this hctx
+	 */
 	void			*driver_data;
 
+	/**
+	 * @ctx_map: Bitmap for each software queue. If bit is on, there is a
+	 * pending request in that software queue.
+	 */
 	struct sbitmap		ctx_map;
 
+	/**
+	 * @dispatch_from: Software queue to be used when no scheduler was
+	 * selected.
+	 */
 	struct blk_mq_ctx	*dispatch_from;
+	/**
+	 * @dispatch_busy: Number used by blk_mq_update_dispatch_busy() to
+	 * decide if the hw_queue is busy using Exponential Weighted Moving
+	 * Average algorithm.
+	 */
 	unsigned int		dispatch_busy;
 
+	/** @type: HCTX_TYPE_* flags. Type of hardware queue. */
 	unsigned short		type;
+	/** @nr_ctx: Number of software queues. */
 	unsigned short		nr_ctx;
+	/** @ctxs: Array of software queues. */
 	struct blk_mq_ctx	**ctxs;
 
+	/** @dispatch_wait_lock: Lock for dispatch_wait queue. */
 	spinlock_t		dispatch_wait_lock;
+	/**
+	 * @dispatch_wait: Waitqueue to put requests when there is no tag
+	 * available at the moment, to wait for another try in the future.
+	 */
 	wait_queue_entry_t	dispatch_wait;
+
+	/**
+	 * @wait_index: Index of next available dispatch_wait queue to insert
+	 * requests.
+	 */
 	atomic_t		wait_index;
 
+	/**
+	 * @tags: Tags owned by the block driver. A tag at this set is only
+	 * assigned when a request is dispatched from a hardware queue.
+	 */
 	struct blk_mq_tags	*tags;
+	/**
+	 * @sched_tags: Tags owned by I/O scheduler. If there is an I/O
+	 * scheduler associated with a request queue, a tag is assigned when
+	 * that request is allocated. Else, this member is not used.
+	 */
 	struct blk_mq_tags	*sched_tags;
 
+	/** @queued: Number of queued requests. */
 	unsigned long		queued;
+	/** @run: Number of dispatched requests. */
 	unsigned long		run;
 #define BLK_MQ_MAX_DISPATCH_ORDER	7
+	/** @dispatched: Number of dispatch requests by queue. */
 	unsigned long		dispatched[BLK_MQ_MAX_DISPATCH_ORDER];
 
+	/** @numa_node: NUMA node the storage adapter has been connected to. */
 	unsigned int		numa_node;
+	/** @queue_num: Index of this hardware queue. */
 	unsigned int		queue_num;
 
+	/**
+	 * @nr_active: Number of active requests. Only used when a tag set is
+	 * shared across request queues.
+	 */
 	atomic_t		nr_active;
 
+	/** @cpuhp_dead: List to store request if some CPU die. */
 	struct hlist_node	cpuhp_dead;
+	/** @kobj: Kernel object for sysfs. */
 	struct kobject		kobj;
 
+	/** @poll_considered: Count times blk_poll() was called. */
 	unsigned long		poll_considered;
+	/** @poll_invoked: Count how many requests blk_poll() polled. */
 	unsigned long		poll_invoked;
+	/** @poll_success: Count how many polled requests were completed. */
 	unsigned long		poll_success;
 
 #ifdef CONFIG_BLK_DEBUG_FS
+	/**
+	 * @debugfs_dir: debugfs directory for this hardware queue. Named
+	 * as cpu<cpu_number>.
+	 */
 	struct dentry		*debugfs_dir;
+	/** @sched_debugfs_dir:	debugfs directory for the scheduler. */
 	struct dentry		*sched_debugfs_dir;
 #endif
 
+	/** @hctx_list:	List of all hardware queues. */
 	struct list_head	hctx_list;
 
-	/* Must be the last member - see also blk_mq_hw_ctx_size(). */
+	/**
+	 * @srcu: Sleepable RCU. Use as lock when type of the hardware queue is
+	 * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also
+	 * blk_mq_hw_ctx_size().
+	 */
 	struct srcu_struct	srcu[0];
 };
 
+/**
+ * struct blk_mq_queue_map - Map software queues to hardware queues
+ * @mq_map:       CPU ID to hardware queue index map. This is an array
+ *	with nr_cpu_ids elements. Each element has a value in the range
+ *	[@queue_offset, @queue_offset + @nr_queues).
+ * @nr_queues:    Number of hardware queues to map CPU IDs onto.
+ * @queue_offset: First hardware queue to map onto. Used by the PCIe NVMe
+ *	driver to map each hardware queue type (enum hctx_type) onto a distinct
+ *	set of hardware queues.
+ */
 struct blk_mq_queue_map {
 	unsigned int *mq_map;
 	unsigned int nr_queues;
 	unsigned int queue_offset;
 };
 
+/**
+ * enum hctx_type - Type of hardware queue
+ * @HCTX_TYPE_DEFAULT:	All I/O not otherwise accounted for.
+ * @HCTX_TYPE_READ:	Just for READ I/O.
+ * @HCTX_TYPE_POLL:	Polled I/O of any kind.
+ * @HCTX_MAX_TYPES:	Number of types of hctx.
+ */
 enum hctx_type {
-	HCTX_TYPE_DEFAULT,	/* all I/O not otherwise accounted for */
-	HCTX_TYPE_READ,		/* just for READ I/O */
-	HCTX_TYPE_POLL,		/* polled I/O of any kind */
+	HCTX_TYPE_DEFAULT,
+	HCTX_TYPE_READ,
+	HCTX_TYPE_POLL,
 
 	HCTX_MAX_TYPES,
 };
 
+/**
+ * struct blk_mq_tag_set - tag set that can be shared between request queues
+ * @map:	   One or more ctx -> hctx mappings. One map exists for each
+ *		   hardware queue type (enum hctx_type) that the driver wishes
+ *		   to support. There are no restrictions on maps being of the
+ *		   same size, and it's perfectly legal to share maps between
+ *		   types.
+ * @nr_maps:	   Number of elements in the @map array. A number in the range
+ *		   [1, HCTX_MAX_TYPES].
+ * @ops:	   Pointers to functions that implement block driver behavior.
+ * @nr_hw_queues:  Number of hardware queues supported by the block driver that
+ *		   owns this data structure.
+ * @queue_depth:   Number of tags per hardware queue, reserved tags included.
+ * @reserved_tags: Number of tags to set aside for BLK_MQ_REQ_RESERVED tag
+ *		   allocations.
+ * @cmd_size:	   Number of additional bytes to allocate per request. The block
+ *		   driver owns these additional bytes.
+ * @numa_node:	   NUMA node the storage adapter has been connected to.
+ * @timeout:	   Request processing timeout in jiffies.
+ * @flags:	   Zero or more BLK_MQ_F_* flags.
+ * @driver_data:   Pointer to data owned by the block driver that created this
+ *		   tag set.
+ * @tags:	   Tag sets. One tag set per hardware queue. Has @nr_hw_queues
+ *		   elements.
+ * @tag_list_lock: Serializes tag_list accesses.
+ * @tag_list:	   List of the request queues that use this tag set. See also
+ *		   request_queue.tag_set_list.
+ */
 struct blk_mq_tag_set {
-	/*
-	 * map[] holds ctx -> hctx mappings, one map exists for each type
-	 * that the driver wishes to support. There are no restrictions
-	 * on maps being of the same size, and it's perfectly legal to
-	 * share maps between types.
-	 */
 	struct blk_mq_queue_map	map[HCTX_MAX_TYPES];
-	unsigned int		nr_maps;	/* nr entries in map[] */
+	unsigned int		nr_maps;
 	const struct blk_mq_ops	*ops;
-	unsigned int		nr_hw_queues;	/* nr hw queues across maps */
-	unsigned int		queue_depth;	/* max hw supported */
+	unsigned int		nr_hw_queues;
+	unsigned int		queue_depth;
 	unsigned int		reserved_tags;
-	unsigned int		cmd_size;	/* per-request extra data */
+	unsigned int		cmd_size;
 	int			numa_node;
 	unsigned int		timeout;
-	unsigned int		flags;		/* BLK_MQ_F_* */
+	unsigned int		flags;
 	void			*driver_data;
 
 	struct blk_mq_tags	**tags;
@@ -115,6 +251,12 @@ struct blk_mq_tag_set {
 	struct list_head	tag_list;
 };
 
+/**
+ * struct blk_mq_queue_data - Data about a request inserted in a queue
+ *
+ * @rq:   Request pointer.
+ * @last: If it is the last request in the queue.
+ */
 struct blk_mq_queue_data {
 	struct request *rq;
 	bool last;
@@ -142,81 +284,101 @@ typedef bool (busy_fn)(struct request_queue *);
 typedef void (complete_fn)(struct request *);
 typedef void (cleanup_rq_fn)(struct request *);
 
-
+/**
+ * struct blk_mq_ops - Callback functions that implements block driver
+ * behaviour.
+ */
 struct blk_mq_ops {
-	/*
-	 * Queue request
+	/**
+	 * @queue_rq: Queue a new request from block IO.
 	 */
 	queue_rq_fn		*queue_rq;
 
-	/*
-	 * If a driver uses bd->last to judge when to submit requests to
-	 * hardware, it must define this function. In case of errors that
-	 * make us stop issuing further requests, this hook serves the
+	/**
+	 * @commit_rqs: If a driver uses bd->last to judge when to submit
+	 * requests to hardware, it must define this function. In case of errors
+	 * that make us stop issuing further requests, this hook serves the
 	 * purpose of kicking the hardware (which the last request otherwise
 	 * would have done).
 	 */
 	commit_rqs_fn		*commit_rqs;
 
-	/*
-	 * Reserve budget before queue request, once .queue_rq is
+	/**
+	 * @get_budget: Reserve budget before queue request, once .queue_rq is
 	 * run, it is driver's responsibility to release the
 	 * reserved budget. Also we have to handle failure case
 	 * of .get_budget for avoiding I/O deadlock.
 	 */
 	get_budget_fn		*get_budget;
+	/**
+	 * @put_budget: Release the reserved budget.
+	 */
 	put_budget_fn		*put_budget;
 
-	/*
-	 * Called on request timeout
+	/**
+	 * @timeout: Called on request timeout.
 	 */
 	timeout_fn		*timeout;
 
-	/*
-	 * Called to poll for completion of a specific tag.
+	/**
+	 * @poll: Called to poll for completion of a specific tag.
 	 */
 	poll_fn			*poll;
 
+	/**
+	 * @complete: Mark the request as complete.
+	 */
 	complete_fn		*complete;
 
-	/*
-	 * Called when the block layer side of a hardware queue has been
-	 * set up, allowing the driver to allocate/init matching structures.
-	 * Ditto for exit/teardown.
+	/**
+	 * @init_hctx: Called when the block layer side of a hardware queue has
+	 * been set up, allowing the driver to allocate/init matching
+	 * structures.
 	 */
 	init_hctx_fn		*init_hctx;
+	/**
+	 * @exit_hctx: Ditto for exit/teardown.
+	 */
 	exit_hctx_fn		*exit_hctx;
 
-	/*
-	 * Called for every command allocated by the block layer to allow
-	 * the driver to set up driver specific data.
+	/**
+	 * @init_request: Called for every command allocated by the block layer
+	 * to allow the driver to set up driver specific data.
 	 *
 	 * Tag greater than or equal to queue_depth is for setting up
 	 * flush request.
-	 *
-	 * Ditto for exit/teardown.
 	 */
 	init_request_fn		*init_request;
+	/**
+	 * @exit_request: Ditto for exit/teardown.
+	 */
 	exit_request_fn		*exit_request;
-	/* Called from inside blk_get_request() */
+
+	/**
+	 * @initialize_rq_fn: Called from inside blk_get_request().
+	 */
 	void (*initialize_rq_fn)(struct request *rq);
 
-	/*
-	 * Called before freeing one request which isn't completed yet,
-	 * and usually for freeing the driver private data
+	/**
+	 * @cleanup_rq: Called before freeing one request which isn't completed
+	 * yet, and usually for freeing the driver private data.
 	 */
 	cleanup_rq_fn		*cleanup_rq;
 
-	/*
-	 * If set, returns whether or not this queue currently is busy
+	/**
+	 * @busy: If set, returns whether or not this queue currently is busy.
 	 */
 	busy_fn			*busy;
 
+	/**
+	 * @map_queues: This allows drivers specify their own queue mapping by
+	 * overriding the setup-time function that builds the mq_map.
+	 */
 	map_queues_fn		*map_queues;
 
 #ifdef CONFIG_BLK_DEBUG_FS
-	/*
-	 * Used by the debugfs implementation to show driver-specific
+	/**
+	 * @show_rq: Used by the debugfs implementation to show driver-specific
 	 * information about a request.
 	 */
 	void (*show_rq)(struct seq_file *m, struct request *rq);
@@ -262,7 +424,6 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
 void blk_mq_free_request(struct request *rq);
-bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
 
 bool blk_mq_queue_inflight(struct request_queue *q);
 
@@ -301,9 +462,25 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
 	return unique_tag & BLK_MQ_UNIQUE_TAG_MASK;
 }
 
+/**
+ * blk_mq_rq_state() - read the current MQ_RQ_* state of a request
+ * @rq: target request.
+ */
+static inline enum mq_rq_state blk_mq_rq_state(struct request *rq)
+{
+	return READ_ONCE(rq->state);
+}
+
+static inline int blk_mq_request_started(struct request *rq)
+{
+	return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
+}
+
+static inline int blk_mq_request_completed(struct request *rq)
+{
+	return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE;
+}
 
-int blk_mq_request_started(struct request *rq);
-int blk_mq_request_completed(struct request *rq);
 void blk_mq_start_request(struct request *rq);
 void blk_mq_end_request(struct request *rq, blk_status_t error);
 void __blk_mq_end_request(struct request *rq, blk_status_t error);
@@ -324,7 +501,7 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
 void blk_mq_quiesce_queue(struct request_queue *q);
 void blk_mq_unquiesce_queue(struct request_queue *q);
 void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
-bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
+void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_run_hw_queues(struct request_queue *q, bool async);
 void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 		busy_tag_iter_fn *fn, void *priv);
@@ -343,14 +520,29 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q);
 
 unsigned int blk_mq_rq_cpu(struct request *rq);
 
-/*
+/**
+ * blk_mq_rq_from_pdu - cast a PDU to a request
+ * @pdu: the PDU (Protocol Data Unit) to be casted
+ *
+ * Return: request
+ *
  * Driver command data is immediately after the request. So subtract request
- * size to get back to the original request, add request size to get the PDU.
+ * size to get back to the original request.
  */
 static inline struct request *blk_mq_rq_from_pdu(void *pdu)
 {
 	return pdu - sizeof(struct request);
 }
+
+/**
+ * blk_mq_rq_to_pdu - cast a request to a PDU
+ * @rq: the request to be casted
+ *
+ * Return: pointer to the PDU
+ *
+ * Driver command data is immediately after the request. So add request to get
+ * the PDU.
+ */
 static inline void *blk_mq_rq_to_pdu(struct request *rq)
 {
 	return rq + 1;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d688b96d1d63..70254ae11769 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -153,10 +153,10 @@ struct bio {
 	unsigned short		bi_write_hint;
 	blk_status_t		bi_status;
 	u8			bi_partno;
+	atomic_t		__bi_remaining;
 
 	struct bvec_iter	bi_iter;
 
-	atomic_t		__bi_remaining;
 	bio_end_io_t		*bi_end_io;
 
 	void			*bi_private;
@@ -290,6 +290,12 @@ enum req_opf {
 	REQ_OP_ZONE_RESET_ALL	= 8,
 	/* write the zero filled sector many times */
 	REQ_OP_WRITE_ZEROES	= 9,
+	/* Open a zone */
+	REQ_OP_ZONE_OPEN	= 10,
+	/* Close a zone */
+	REQ_OP_ZONE_CLOSE	= 11,
+	/* Transition a zone to full */
+	REQ_OP_ZONE_FINISH	= 12,
 
 	/* SCSI passthrough using struct scsi_request */
 	REQ_OP_SCSI_IN		= 32,
@@ -371,6 +377,7 @@ enum stat_group {
 	STAT_READ,
 	STAT_WRITE,
 	STAT_DISCARD,
+	STAT_FLUSH,
 
 	NR_STAT_GROUPS
 };
@@ -417,6 +424,25 @@ static inline bool op_is_discard(unsigned int op)
 	return (op & REQ_OP_MASK) == REQ_OP_DISCARD;
 }
 
+/*
+ * Check if a bio or request operation is a zone management operation, with
+ * the exception of REQ_OP_ZONE_RESET_ALL which is treated as a special case
+ * due to its different handling in the block layer and device response in
+ * case of command failure.
+ */
+static inline bool op_is_zone_mgmt(enum req_opf op)
+{
+	switch (op & REQ_OP_MASK) {
+	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_OPEN:
+	case REQ_OP_ZONE_CLOSE:
+	case REQ_OP_ZONE_FINISH:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static inline int op_stat_group(unsigned int op)
 {
 	if (op_is_discard(op))
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index f3ea78b0c91c..397bb9bc230b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -349,25 +349,25 @@ struct queue_limits {
 	enum blk_zoned_model	zoned;
 };
 
+typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
+			       void *data);
+
 #ifdef CONFIG_BLK_DEV_ZONED
 
-/*
- * Maximum number of zones to report with a single report zones command.
- */
-#define BLK_ZONED_REPORT_MAX_ZONES	8192U
+#define BLK_ALL_ZONES  ((unsigned int)-1)
+int blkdev_report_zones(struct block_device *bdev, sector_t sector,
+			unsigned int nr_zones, report_zones_cb cb, void *data);
 
 extern unsigned int blkdev_nr_zones(struct block_device *bdev);
-extern int blkdev_report_zones(struct block_device *bdev,
-			       sector_t sector, struct blk_zone *zones,
-			       unsigned int *nr_zones);
-extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors,
-			      sector_t nr_sectors, gfp_t gfp_mask);
+extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
+			    sector_t sectors, sector_t nr_sectors,
+			    gfp_t gfp_mask);
 extern int blk_revalidate_disk_zones(struct gendisk *disk);
 
 extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 				     unsigned int cmd, unsigned long arg);
-extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
-				    unsigned int cmd, unsigned long arg);
+extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
+				  unsigned int cmd, unsigned long arg);
 
 #else /* CONFIG_BLK_DEV_ZONED */
 
@@ -388,9 +388,9 @@ static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
 	return -ENOTTY;
 }
 
-static inline int blkdev_reset_zones_ioctl(struct block_device *bdev,
-					   fmode_t mode, unsigned int cmd,
-					   unsigned long arg)
+static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev,
+					 fmode_t mode, unsigned int cmd,
+					 unsigned long arg)
 {
 	return -ENOTTY;
 }
@@ -411,7 +411,6 @@ struct request_queue {
 
 	/* sw queues */
 	struct blk_mq_ctx __percpu	*queue_ctx;
-	unsigned int		nr_queues;
 
 	unsigned int		queue_depth;
 
@@ -1709,7 +1708,7 @@ struct block_device_operations {
 	/* this callback is with swap_lock and sometimes page table lock held */
 	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
 	int (*report_zones)(struct gendisk *, sector_t sector,
-			    struct blk_zone *zones, unsigned int *nr_zones);
+			unsigned int nr_zones, report_zones_cb cb, void *data);
 	struct module *owner;
 	const struct pr_ops *pr_ops;
 };
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 430e219e3aba..63097cb243cb 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -355,16 +355,6 @@ struct cgroup {
 	unsigned long flags;		/* "unsigned long" so bitops work */
 
 	/*
-	 * idr allocated in-hierarchy ID.
-	 *
-	 * ID 0 is not used, the ID of the root cgroup is always 1, and a
-	 * new cgroup will be assigned with a smallest available ID.
-	 *
-	 * Allocating/Removing ID must be protected by cgroup_mutex.
-	 */
-	int id;
-
-	/*
 	 * The depth this cgroup is at.  The root is at depth zero and each
 	 * step down the hierarchy increments the level.  This along with
 	 * ancestor_ids[] can determine whether a given cgroup is a
@@ -458,7 +448,7 @@ struct cgroup {
 	struct list_head rstat_css_list;
 
 	/* cgroup basic resource statistics */
-	struct cgroup_base_stat pending_bstat;	/* pending from children */
+	struct cgroup_base_stat last_bstat;
 	struct cgroup_base_stat bstat;
 	struct prev_cputime prev_cputime;	/* for printing out cputime */
 
@@ -488,7 +478,7 @@ struct cgroup {
 	struct cgroup_freezer_state freezer;
 
 	/* ids of the ancestors at each level including self */
-	int ancestor_ids[];
+	u64 ancestor_ids[];
 };
 
 /*
@@ -509,7 +499,7 @@ struct cgroup_root {
 	struct cgroup cgrp;
 
 	/* for cgrp->ancestor_ids[0] */
-	int cgrp_ancestor_id_storage;
+	u64 cgrp_ancestor_id_storage;
 
 	/* Number of cgroups in the hierarchy, used only for /proc/cgroups */
 	atomic_t nr_cgrps;
@@ -520,9 +510,6 @@ struct cgroup_root {
 	/* Hierarchy-specific flags */
 	unsigned int flags;
 
-	/* IDs for cgroups in this hierarchy */
-	struct idr cgroup_idr;
-
 	/* The path to use for release notifications. */
 	char release_agent_path[PATH_MAX];
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 3ba3e6da13a6..d7ddebd0cdec 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -150,7 +150,6 @@ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
 struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
 					struct cgroup_subsys_state **dst_cssp);
 
-void cgroup_enable_task_cg_lists(void);
 void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
 			 struct css_task_iter *it);
 struct task_struct *css_task_iter_next(struct css_task_iter *it);
@@ -305,6 +304,11 @@ void css_task_iter_end(struct css_task_iter *it);
  * Inline functions.
  */
 
+static inline u64 cgroup_id(struct cgroup *cgrp)
+{
+	return cgrp->kn->id;
+}
+
 /**
  * css_get - obtain a reference on the specified css
  * @css: target css
@@ -566,7 +570,7 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp,
 {
 	if (cgrp->root != ancestor->root || cgrp->level < ancestor->level)
 		return false;
-	return cgrp->ancestor_ids[ancestor->level] == ancestor->id;
+	return cgrp->ancestor_ids[ancestor->level] == cgroup_id(ancestor);
 }
 
 /**
@@ -617,7 +621,7 @@ static inline bool cgroup_is_populated(struct cgroup *cgrp)
 /* returns ino associated with a cgroup */
 static inline ino_t cgroup_ino(struct cgroup *cgrp)
 {
-	return cgrp->kn->id.ino;
+	return kernfs_ino(cgrp->kn);
 }
 
 /* cft/css accessors for cftype->write() operation */
@@ -688,18 +692,13 @@ static inline void cgroup_kthread_ready(void)
 	current->no_cgroup_migration = 0;
 }
 
-static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp)
-{
-	return &cgrp->kn->id;
-}
-
-void cgroup_path_from_kernfs_id(const union kernfs_node_id *id,
-					char *buf, size_t buflen);
+void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen);
 #else /* !CONFIG_CGROUPS */
 
 struct cgroup_subsys_state;
 struct cgroup;
 
+static inline u64 cgroup_id(struct cgroup *cgrp) { return 1; }
 static inline void css_get(struct cgroup_subsys_state *css) {}
 static inline void css_put(struct cgroup_subsys_state *css) {}
 static inline int cgroup_attach_task_all(struct task_struct *from,
@@ -719,10 +718,6 @@ static inline int cgroup_init_early(void) { return 0; }
 static inline int cgroup_init(void) { return 0; }
 static inline void cgroup_init_kthreadd(void) {}
 static inline void cgroup_kthread_ready(void) {}
-static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp)
-{
-	return NULL;
-}
 
 static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
 {
@@ -740,8 +735,8 @@ static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
 	return true;
 }
 
-static inline void cgroup_path_from_kernfs_id(const union kernfs_node_id *id,
-	char *buf, size_t buflen) {}
+static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen)
+{}
 #endif /* !CONFIG_CGROUPS */
 
 #ifdef CONFIG_CGROUPS
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 068793a619ca..89d75edb5750 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -136,6 +136,7 @@ enum cpuhp_state {
 	/* Must be the last timer callback */
 	CPUHP_AP_DUMMY_TIMER_STARTING,
 	CPUHP_AP_ARM_XEN_STARTING,
+	CPUHP_AP_ARM_KVMPV_STARTING,
 	CPUHP_AP_ARM_CORESIGHT_STARTING,
 	CPUHP_AP_ARM64_ISNDEP_STARTING,
 	CPUHP_AP_SMPCFD_DYING,
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 19ea3a371d7b..23365a9d062e 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -41,8 +41,6 @@
 #define CRYPTO_ALG_TYPE_CIPHER		0x00000001
 #define CRYPTO_ALG_TYPE_COMPRESS	0x00000002
 #define CRYPTO_ALG_TYPE_AEAD		0x00000003
-#define CRYPTO_ALG_TYPE_BLKCIPHER	0x00000004
-#define CRYPTO_ALG_TYPE_ABLKCIPHER	0x00000005
 #define CRYPTO_ALG_TYPE_SKCIPHER	0x00000005
 #define CRYPTO_ALG_TYPE_KPP		0x00000008
 #define CRYPTO_ALG_TYPE_ACOMPRESS	0x0000000a
@@ -55,7 +53,6 @@
 
 #define CRYPTO_ALG_TYPE_HASH_MASK	0x0000000e
 #define CRYPTO_ALG_TYPE_AHASH_MASK	0x0000000e
-#define CRYPTO_ALG_TYPE_BLKCIPHER_MASK	0x0000000c
 #define CRYPTO_ALG_TYPE_ACOMPRESS_MASK	0x0000000e
 
 #define CRYPTO_ALG_LARVAL		0x00000010
@@ -139,9 +136,7 @@
 #define CRYPTO_MINALIGN_ATTR __attribute__ ((__aligned__(CRYPTO_MINALIGN)))
 
 struct scatterlist;
-struct crypto_ablkcipher;
 struct crypto_async_request;
-struct crypto_blkcipher;
 struct crypto_tfm;
 struct crypto_type;
 
@@ -163,25 +158,6 @@ struct crypto_async_request {
 	u32 flags;
 };
 
-struct ablkcipher_request {
-	struct crypto_async_request base;
-
-	unsigned int nbytes;
-
-	void *info;
-
-	struct scatterlist *src;
-	struct scatterlist *dst;
-
-	void *__ctx[] CRYPTO_MINALIGN_ATTR;
-};
-
-struct blkcipher_desc {
-	struct crypto_blkcipher *tfm;
-	void *info;
-	u32 flags;
-};
-
 /**
  * DOC: Block Cipher Algorithm Definitions
  *
@@ -190,83 +166,6 @@ struct blkcipher_desc {
  */
 
 /**
- * struct ablkcipher_alg - asynchronous block cipher definition
- * @min_keysize: Minimum key size supported by the transformation. This is the
- *		 smallest key length supported by this transformation algorithm.
- *		 This must be set to one of the pre-defined values as this is
- *		 not hardware specific. Possible values for this field can be
- *		 found via git grep "_MIN_KEY_SIZE" include/crypto/
- * @max_keysize: Maximum key size supported by the transformation. This is the
- *		 largest key length supported by this transformation algorithm.
- *		 This must be set to one of the pre-defined values as this is
- *		 not hardware specific. Possible values for this field can be
- *		 found via git grep "_MAX_KEY_SIZE" include/crypto/
- * @setkey: Set key for the transformation. This function is used to either
- *	    program a supplied key into the hardware or store the key in the
- *	    transformation context for programming it later. Note that this
- *	    function does modify the transformation context. This function can
- *	    be called multiple times during the existence of the transformation
- *	    object, so one must make sure the key is properly reprogrammed into
- *	    the hardware. This function is also responsible for checking the key
- *	    length for validity. In case a software fallback was put in place in
- *	    the @cra_init call, this function might need to use the fallback if
- *	    the algorithm doesn't support all of the key sizes.
- * @encrypt: Encrypt a scatterlist of blocks. This function is used to encrypt
- *	     the supplied scatterlist containing the blocks of data. The crypto
- *	     API consumer is responsible for aligning the entries of the
- *	     scatterlist properly and making sure the chunks are correctly
- *	     sized. In case a software fallback was put in place in the
- *	     @cra_init call, this function might need to use the fallback if
- *	     the algorithm doesn't support all of the key sizes. In case the
- *	     key was stored in transformation context, the key might need to be
- *	     re-programmed into the hardware in this function. This function
- *	     shall not modify the transformation context, as this function may
- *	     be called in parallel with the same transformation object.
- * @decrypt: Decrypt a single block. This is a reverse counterpart to @encrypt
- *	     and the conditions are exactly the same.
- * @ivsize: IV size applicable for transformation. The consumer must provide an
- *	    IV of exactly that size to perform the encrypt or decrypt operation.
- *
- * All fields except @ivsize are mandatory and must be filled.
- */
-struct ablkcipher_alg {
-	int (*setkey)(struct crypto_ablkcipher *tfm, const u8 *key,
-	              unsigned int keylen);
-	int (*encrypt)(struct ablkcipher_request *req);
-	int (*decrypt)(struct ablkcipher_request *req);
-
-	unsigned int min_keysize;
-	unsigned int max_keysize;
-	unsigned int ivsize;
-};
-
-/**
- * struct blkcipher_alg - synchronous block cipher definition
- * @min_keysize: see struct ablkcipher_alg
- * @max_keysize: see struct ablkcipher_alg
- * @setkey: see struct ablkcipher_alg
- * @encrypt: see struct ablkcipher_alg
- * @decrypt: see struct ablkcipher_alg
- * @ivsize: see struct ablkcipher_alg
- *
- * All fields except @ivsize are mandatory and must be filled.
- */
-struct blkcipher_alg {
-	int (*setkey)(struct crypto_tfm *tfm, const u8 *key,
-	              unsigned int keylen);
-	int (*encrypt)(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes);
-	int (*decrypt)(struct blkcipher_desc *desc,
-		       struct scatterlist *dst, struct scatterlist *src,
-		       unsigned int nbytes);
-
-	unsigned int min_keysize;
-	unsigned int max_keysize;
-	unsigned int ivsize;
-};
-
-/**
  * struct cipher_alg - single-block symmetric ciphers definition
  * @cia_min_keysize: Minimum key size supported by the transformation. This is
  *		     the smallest key length supported by this transformation
@@ -450,8 +349,6 @@ struct crypto_istat_rng {
 };
 #endif /* CONFIG_CRYPTO_STATS */
 
-#define cra_ablkcipher	cra_u.ablkcipher
-#define cra_blkcipher	cra_u.blkcipher
 #define cra_cipher	cra_u.cipher
 #define cra_compress	cra_u.compress
 
@@ -499,9 +396,8 @@ struct crypto_istat_rng {
  *		     transformation algorithm.
  * @cra_type: Type of the cryptographic transformation. This is a pointer to
  *	      struct crypto_type, which implements callbacks common for all
- *	      transformation types. There are multiple options:
- *	      &crypto_blkcipher_type, &crypto_ablkcipher_type,
- *	      &crypto_ahash_type, &crypto_rng_type.
+ *	      transformation types. There are multiple options, such as
+ *	      &crypto_skcipher_type, &crypto_ahash_type, &crypto_rng_type.
  *	      This field might be empty. In that case, there are no common
  *	      callbacks. This is the case for: cipher, compress, shash.
  * @cra_u: Callbacks implementing the transformation. This is a union of
@@ -520,10 +416,6 @@ struct crypto_istat_rng {
  * @cra_exit: Deinitialize the cryptographic transformation object. This is a
  *	      counterpart to @cra_init, used to remove various changes set in
  *	      @cra_init.
- * @cra_u.ablkcipher: Union member which contains an asynchronous block cipher
- *		      definition. See @struct @ablkcipher_alg.
- * @cra_u.blkcipher: Union member which contains a synchronous block cipher
- * 		     definition See @struct @blkcipher_alg.
  * @cra_u.cipher: Union member which contains a single-block symmetric cipher
  *		  definition. See @struct @cipher_alg.
  * @cra_u.compress: Union member which contains a (de)compression algorithm.
@@ -565,8 +457,6 @@ struct crypto_alg {
 	const struct crypto_type *cra_type;
 
 	union {
-		struct ablkcipher_alg ablkcipher;
-		struct blkcipher_alg blkcipher;
 		struct cipher_alg cipher;
 		struct compress_alg compress;
 	} cra_u;
@@ -594,8 +484,6 @@ struct crypto_alg {
 #ifdef CONFIG_CRYPTO_STATS
 void crypto_stats_init(struct crypto_alg *alg);
 void crypto_stats_get(struct crypto_alg *alg);
-void crypto_stats_ablkcipher_encrypt(unsigned int nbytes, int ret, struct crypto_alg *alg);
-void crypto_stats_ablkcipher_decrypt(unsigned int nbytes, int ret, struct crypto_alg *alg);
 void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret);
 void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret);
 void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg);
@@ -618,10 +506,6 @@ static inline void crypto_stats_init(struct crypto_alg *alg)
 {}
 static inline void crypto_stats_get(struct crypto_alg *alg)
 {}
-static inline void crypto_stats_ablkcipher_encrypt(unsigned int nbytes, int ret, struct crypto_alg *alg)
-{}
-static inline void crypto_stats_ablkcipher_decrypt(unsigned int nbytes, int ret, struct crypto_alg *alg)
-{}
 static inline void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret)
 {}
 static inline void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret)
@@ -715,28 +599,6 @@ int crypto_has_alg(const char *name, u32 type, u32 mask);
  * crypto_free_*(), as well as the various helpers below.
  */
 
-struct ablkcipher_tfm {
-	int (*setkey)(struct crypto_ablkcipher *tfm, const u8 *key,
-	              unsigned int keylen);
-	int (*encrypt)(struct ablkcipher_request *req);
-	int (*decrypt)(struct ablkcipher_request *req);
-
-	struct crypto_ablkcipher *base;
-
-	unsigned int ivsize;
-	unsigned int reqsize;
-};
-
-struct blkcipher_tfm {
-	void *iv;
-	int (*setkey)(struct crypto_tfm *tfm, const u8 *key,
-		      unsigned int keylen);
-	int (*encrypt)(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes);
-	int (*decrypt)(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes);
-};
-
 struct cipher_tfm {
 	int (*cit_setkey)(struct crypto_tfm *tfm,
 	                  const u8 *key, unsigned int keylen);
@@ -753,8 +615,6 @@ struct compress_tfm {
 	                      u8 *dst, unsigned int *dlen);
 };
 
-#define crt_ablkcipher	crt_u.ablkcipher
-#define crt_blkcipher	crt_u.blkcipher
 #define crt_cipher	crt_u.cipher
 #define crt_compress	crt_u.compress
 
@@ -763,8 +623,6 @@ struct crypto_tfm {
 	u32 crt_flags;
 	
 	union {
-		struct ablkcipher_tfm ablkcipher;
-		struct blkcipher_tfm blkcipher;
 		struct cipher_tfm cipher;
 		struct compress_tfm compress;
 	} crt_u;
@@ -776,14 +634,6 @@ struct crypto_tfm {
 	void *__crt_ctx[] CRYPTO_MINALIGN_ATTR;
 };
 
-struct crypto_ablkcipher {
-	struct crypto_tfm base;
-};
-
-struct crypto_blkcipher {
-	struct crypto_tfm base;
-};
-
 struct crypto_cipher {
 	struct crypto_tfm base;
 };
@@ -891,713 +741,6 @@ static inline unsigned int crypto_tfm_ctx_alignment(void)
 	return __alignof__(tfm->__crt_ctx);
 }
 
-/*
- * API wrappers.
- */
-static inline struct crypto_ablkcipher *__crypto_ablkcipher_cast(
-	struct crypto_tfm *tfm)
-{
-	return (struct crypto_ablkcipher *)tfm;
-}
-
-static inline u32 crypto_skcipher_type(u32 type)
-{
-	type &= ~CRYPTO_ALG_TYPE_MASK;
-	type |= CRYPTO_ALG_TYPE_BLKCIPHER;
-	return type;
-}
-
-static inline u32 crypto_skcipher_mask(u32 mask)
-{
-	mask &= ~CRYPTO_ALG_TYPE_MASK;
-	mask |= CRYPTO_ALG_TYPE_BLKCIPHER_MASK;
-	return mask;
-}
-
-/**
- * DOC: Asynchronous Block Cipher API
- *
- * Asynchronous block cipher API is used with the ciphers of type
- * CRYPTO_ALG_TYPE_ABLKCIPHER (listed as type "ablkcipher" in /proc/crypto).
- *
- * Asynchronous cipher operations imply that the function invocation for a
- * cipher request returns immediately before the completion of the operation.
- * The cipher request is scheduled as a separate kernel thread and therefore
- * load-balanced on the different CPUs via the process scheduler. To allow
- * the kernel crypto API to inform the caller about the completion of a cipher
- * request, the caller must provide a callback function. That function is
- * invoked with the cipher handle when the request completes.
- *
- * To support the asynchronous operation, additional information than just the
- * cipher handle must be supplied to the kernel crypto API. That additional
- * information is given by filling in the ablkcipher_request data structure.
- *
- * For the asynchronous block cipher API, the state is maintained with the tfm
- * cipher handle. A single tfm can be used across multiple calls and in
- * parallel. For asynchronous block cipher calls, context data supplied and
- * only used by the caller can be referenced the request data structure in
- * addition to the IV used for the cipher request. The maintenance of such
- * state information would be important for a crypto driver implementer to
- * have, because when calling the callback function upon completion of the
- * cipher operation, that callback function may need some information about
- * which operation just finished if it invoked multiple in parallel. This
- * state information is unused by the kernel crypto API.
- */
-
-static inline struct crypto_tfm *crypto_ablkcipher_tfm(
-	struct crypto_ablkcipher *tfm)
-{
-	return &tfm->base;
-}
-
-/**
- * crypto_free_ablkcipher() - zeroize and free cipher handle
- * @tfm: cipher handle to be freed
- */
-static inline void crypto_free_ablkcipher(struct crypto_ablkcipher *tfm)
-{
-	crypto_free_tfm(crypto_ablkcipher_tfm(tfm));
-}
-
-/**
- * crypto_has_ablkcipher() - Search for the availability of an ablkcipher.
- * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
- *	      ablkcipher
- * @type: specifies the type of the cipher
- * @mask: specifies the mask for the cipher
- *
- * Return: true when the ablkcipher is known to the kernel crypto API; false
- *	   otherwise
- */
-static inline int crypto_has_ablkcipher(const char *alg_name, u32 type,
-					u32 mask)
-{
-	return crypto_has_alg(alg_name, crypto_skcipher_type(type),
-			      crypto_skcipher_mask(mask));
-}
-
-static inline struct ablkcipher_tfm *crypto_ablkcipher_crt(
-	struct crypto_ablkcipher *tfm)
-{
-	return &crypto_ablkcipher_tfm(tfm)->crt_ablkcipher;
-}
-
-/**
- * crypto_ablkcipher_ivsize() - obtain IV size
- * @tfm: cipher handle
- *
- * The size of the IV for the ablkcipher referenced by the cipher handle is
- * returned. This IV size may be zero if the cipher does not need an IV.
- *
- * Return: IV size in bytes
- */
-static inline unsigned int crypto_ablkcipher_ivsize(
-	struct crypto_ablkcipher *tfm)
-{
-	return crypto_ablkcipher_crt(tfm)->ivsize;
-}
-
-/**
- * crypto_ablkcipher_blocksize() - obtain block size of cipher
- * @tfm: cipher handle
- *
- * The block size for the ablkcipher referenced with the cipher handle is
- * returned. The caller may use that information to allocate appropriate
- * memory for the data returned by the encryption or decryption operation
- *
- * Return: block size of cipher
- */
-static inline unsigned int crypto_ablkcipher_blocksize(
-	struct crypto_ablkcipher *tfm)
-{
-	return crypto_tfm_alg_blocksize(crypto_ablkcipher_tfm(tfm));
-}
-
-static inline unsigned int crypto_ablkcipher_alignmask(
-	struct crypto_ablkcipher *tfm)
-{
-	return crypto_tfm_alg_alignmask(crypto_ablkcipher_tfm(tfm));
-}
-
-static inline u32 crypto_ablkcipher_get_flags(struct crypto_ablkcipher *tfm)
-{
-	return crypto_tfm_get_flags(crypto_ablkcipher_tfm(tfm));
-}
-
-static inline void crypto_ablkcipher_set_flags(struct crypto_ablkcipher *tfm,
-					       u32 flags)
-{
-	crypto_tfm_set_flags(crypto_ablkcipher_tfm(tfm), flags);
-}
-
-static inline void crypto_ablkcipher_clear_flags(struct crypto_ablkcipher *tfm,
-						 u32 flags)
-{
-	crypto_tfm_clear_flags(crypto_ablkcipher_tfm(tfm), flags);
-}
-
-/**
- * crypto_ablkcipher_setkey() - set key for cipher
- * @tfm: cipher handle
- * @key: buffer holding the key
- * @keylen: length of the key in bytes
- *
- * The caller provided key is set for the ablkcipher referenced by the cipher
- * handle.
- *
- * Note, the key length determines the cipher type. Many block ciphers implement
- * different cipher modes depending on the key size, such as AES-128 vs AES-192
- * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128
- * is performed.
- *
- * Return: 0 if the setting of the key was successful; < 0 if an error occurred
- */
-static inline int crypto_ablkcipher_setkey(struct crypto_ablkcipher *tfm,
-					   const u8 *key, unsigned int keylen)
-{
-	struct ablkcipher_tfm *crt = crypto_ablkcipher_crt(tfm);
-
-	return crt->setkey(crt->base, key, keylen);
-}
-
-/**
- * crypto_ablkcipher_reqtfm() - obtain cipher handle from request
- * @req: ablkcipher_request out of which the cipher handle is to be obtained
- *
- * Return the crypto_ablkcipher handle when furnishing an ablkcipher_request
- * data structure.
- *
- * Return: crypto_ablkcipher handle
- */
-static inline struct crypto_ablkcipher *crypto_ablkcipher_reqtfm(
-	struct ablkcipher_request *req)
-{
-	return __crypto_ablkcipher_cast(req->base.tfm);
-}
-
-/**
- * crypto_ablkcipher_encrypt() - encrypt plaintext
- * @req: reference to the ablkcipher_request handle that holds all information
- *	 needed to perform the cipher operation
- *
- * Encrypt plaintext data using the ablkcipher_request handle. That data
- * structure and how it is filled with data is discussed with the
- * ablkcipher_request_* functions.
- *
- * Return: 0 if the cipher operation was successful; < 0 if an error occurred
- */
-static inline int crypto_ablkcipher_encrypt(struct ablkcipher_request *req)
-{
-	struct ablkcipher_tfm *crt =
-		crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req));
-	struct crypto_alg *alg = crt->base->base.__crt_alg;
-	unsigned int nbytes = req->nbytes;
-	int ret;
-
-	crypto_stats_get(alg);
-	ret = crt->encrypt(req);
-	crypto_stats_ablkcipher_encrypt(nbytes, ret, alg);
-	return ret;
-}
-
-/**
- * crypto_ablkcipher_decrypt() - decrypt ciphertext
- * @req: reference to the ablkcipher_request handle that holds all information
- *	 needed to perform the cipher operation
- *
- * Decrypt ciphertext data using the ablkcipher_request handle. That data
- * structure and how it is filled with data is discussed with the
- * ablkcipher_request_* functions.
- *
- * Return: 0 if the cipher operation was successful; < 0 if an error occurred
- */
-static inline int crypto_ablkcipher_decrypt(struct ablkcipher_request *req)
-{
-	struct ablkcipher_tfm *crt =
-		crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req));
-	struct crypto_alg *alg = crt->base->base.__crt_alg;
-	unsigned int nbytes = req->nbytes;
-	int ret;
-
-	crypto_stats_get(alg);
-	ret = crt->decrypt(req);
-	crypto_stats_ablkcipher_decrypt(nbytes, ret, alg);
-	return ret;
-}
-
-/**
- * DOC: Asynchronous Cipher Request Handle
- *
- * The ablkcipher_request data structure contains all pointers to data
- * required for the asynchronous cipher operation. This includes the cipher
- * handle (which can be used by multiple ablkcipher_request instances), pointer
- * to plaintext and ciphertext, asynchronous callback function, etc. It acts
- * as a handle to the ablkcipher_request_* API calls in a similar way as
- * ablkcipher handle to the crypto_ablkcipher_* API calls.
- */
-
-/**
- * crypto_ablkcipher_reqsize() - obtain size of the request data structure
- * @tfm: cipher handle
- *
- * Return: number of bytes
- */
-static inline unsigned int crypto_ablkcipher_reqsize(
-	struct crypto_ablkcipher *tfm)
-{
-	return crypto_ablkcipher_crt(tfm)->reqsize;
-}
-
-/**
- * ablkcipher_request_set_tfm() - update cipher handle reference in request
- * @req: request handle to be modified
- * @tfm: cipher handle that shall be added to the request handle
- *
- * Allow the caller to replace the existing ablkcipher handle in the request
- * data structure with a different one.
- */
-static inline void ablkcipher_request_set_tfm(
-	struct ablkcipher_request *req, struct crypto_ablkcipher *tfm)
-{
-	req->base.tfm = crypto_ablkcipher_tfm(crypto_ablkcipher_crt(tfm)->base);
-}
-
-static inline struct ablkcipher_request *ablkcipher_request_cast(
-	struct crypto_async_request *req)
-{
-	return container_of(req, struct ablkcipher_request, base);
-}
-
-/**
- * ablkcipher_request_alloc() - allocate request data structure
- * @tfm: cipher handle to be registered with the request
- * @gfp: memory allocation flag that is handed to kmalloc by the API call.
- *
- * Allocate the request data structure that must be used with the ablkcipher
- * encrypt and decrypt API calls. During the allocation, the provided ablkcipher
- * handle is registered in the request data structure.
- *
- * Return: allocated request handle in case of success, or NULL if out of memory
- */
-static inline struct ablkcipher_request *ablkcipher_request_alloc(
-	struct crypto_ablkcipher *tfm, gfp_t gfp)
-{
-	struct ablkcipher_request *req;
-
-	req = kmalloc(sizeof(struct ablkcipher_request) +
-		      crypto_ablkcipher_reqsize(tfm), gfp);
-
-	if (likely(req))
-		ablkcipher_request_set_tfm(req, tfm);
-
-	return req;
-}
-
-/**
- * ablkcipher_request_free() - zeroize and free request data structure
- * @req: request data structure cipher handle to be freed
- */
-static inline void ablkcipher_request_free(struct ablkcipher_request *req)
-{
-	kzfree(req);
-}
-
-/**
- * ablkcipher_request_set_callback() - set asynchronous callback function
- * @req: request handle
- * @flags: specify zero or an ORing of the flags
- *	   CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and
- *	   increase the wait queue beyond the initial maximum size;
- *	   CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep
- * @compl: callback function pointer to be registered with the request handle
- * @data: The data pointer refers to memory that is not used by the kernel
- *	  crypto API, but provided to the callback function for it to use. Here,
- *	  the caller can provide a reference to memory the callback function can
- *	  operate on. As the callback function is invoked asynchronously to the
- *	  related functionality, it may need to access data structures of the
- *	  related functionality which can be referenced using this pointer. The
- *	  callback function can access the memory via the "data" field in the
- *	  crypto_async_request data structure provided to the callback function.
- *
- * This function allows setting the callback function that is triggered once the
- * cipher operation completes.
- *
- * The callback function is registered with the ablkcipher_request handle and
- * must comply with the following template::
- *
- *	void callback_function(struct crypto_async_request *req, int error)
- */
-static inline void ablkcipher_request_set_callback(
-	struct ablkcipher_request *req,
-	u32 flags, crypto_completion_t compl, void *data)
-{
-	req->base.complete = compl;
-	req->base.data = data;
-	req->base.flags = flags;
-}
-
-/**
- * ablkcipher_request_set_crypt() - set data buffers
- * @req: request handle
- * @src: source scatter / gather list
- * @dst: destination scatter / gather list
- * @nbytes: number of bytes to process from @src
- * @iv: IV for the cipher operation which must comply with the IV size defined
- *      by crypto_ablkcipher_ivsize
- *
- * This function allows setting of the source data and destination data
- * scatter / gather lists.
- *
- * For encryption, the source is treated as the plaintext and the
- * destination is the ciphertext. For a decryption operation, the use is
- * reversed - the source is the ciphertext and the destination is the plaintext.
- */
-static inline void ablkcipher_request_set_crypt(
-	struct ablkcipher_request *req,
-	struct scatterlist *src, struct scatterlist *dst,
-	unsigned int nbytes, void *iv)
-{
-	req->src = src;
-	req->dst = dst;
-	req->nbytes = nbytes;
-	req->info = iv;
-}
-
-/**
- * DOC: Synchronous Block Cipher API
- *
- * The synchronous block cipher API is used with the ciphers of type
- * CRYPTO_ALG_TYPE_BLKCIPHER (listed as type "blkcipher" in /proc/crypto)
- *
- * Synchronous calls, have a context in the tfm. But since a single tfm can be
- * used in multiple calls and in parallel, this info should not be changeable
- * (unless a lock is used). This applies, for example, to the symmetric key.
- * However, the IV is changeable, so there is an iv field in blkcipher_tfm
- * structure for synchronous blkcipher api. So, its the only state info that can
- * be kept for synchronous calls without using a big lock across a tfm.
- *
- * The block cipher API allows the use of a complete cipher, i.e. a cipher
- * consisting of a template (a block chaining mode) and a single block cipher
- * primitive (e.g. AES).
- *
- * The plaintext data buffer and the ciphertext data buffer are pointed to
- * by using scatter/gather lists. The cipher operation is performed
- * on all segments of the provided scatter/gather lists.
- *
- * The kernel crypto API supports a cipher operation "in-place" which means that
- * the caller may provide the same scatter/gather list for the plaintext and
- * cipher text. After the completion of the cipher operation, the plaintext
- * data is replaced with the ciphertext data in case of an encryption and vice
- * versa for a decryption. The caller must ensure that the scatter/gather lists
- * for the output data point to sufficiently large buffers, i.e. multiples of
- * the block size of the cipher.
- */
-
-static inline struct crypto_blkcipher *__crypto_blkcipher_cast(
-	struct crypto_tfm *tfm)
-{
-	return (struct crypto_blkcipher *)tfm;
-}
-
-static inline struct crypto_blkcipher *crypto_blkcipher_cast(
-	struct crypto_tfm *tfm)
-{
-	BUG_ON(crypto_tfm_alg_type(tfm) != CRYPTO_ALG_TYPE_BLKCIPHER);
-	return __crypto_blkcipher_cast(tfm);
-}
-
-/**
- * crypto_alloc_blkcipher() - allocate synchronous block cipher handle
- * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
- *	      blkcipher cipher
- * @type: specifies the type of the cipher
- * @mask: specifies the mask for the cipher
- *
- * Allocate a cipher handle for a block cipher. The returned struct
- * crypto_blkcipher is the cipher handle that is required for any subsequent
- * API invocation for that block cipher.
- *
- * Return: allocated cipher handle in case of success; IS_ERR() is true in case
- *	   of an error, PTR_ERR() returns the error code.
- */
-static inline struct crypto_blkcipher *crypto_alloc_blkcipher(
-	const char *alg_name, u32 type, u32 mask)
-{
-	type &= ~CRYPTO_ALG_TYPE_MASK;
-	type |= CRYPTO_ALG_TYPE_BLKCIPHER;
-	mask |= CRYPTO_ALG_TYPE_MASK;
-
-	return __crypto_blkcipher_cast(crypto_alloc_base(alg_name, type, mask));
-}
-
-static inline struct crypto_tfm *crypto_blkcipher_tfm(
-	struct crypto_blkcipher *tfm)
-{
-	return &tfm->base;
-}
-
-/**
- * crypto_free_blkcipher() - zeroize and free the block cipher handle
- * @tfm: cipher handle to be freed
- */
-static inline void crypto_free_blkcipher(struct crypto_blkcipher *tfm)
-{
-	crypto_free_tfm(crypto_blkcipher_tfm(tfm));
-}
-
-/**
- * crypto_has_blkcipher() - Search for the availability of a block cipher
- * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
- *	      block cipher
- * @type: specifies the type of the cipher
- * @mask: specifies the mask for the cipher
- *
- * Return: true when the block cipher is known to the kernel crypto API; false
- *	   otherwise
- */
-static inline int crypto_has_blkcipher(const char *alg_name, u32 type, u32 mask)
-{
-	type &= ~CRYPTO_ALG_TYPE_MASK;
-	type |= CRYPTO_ALG_TYPE_BLKCIPHER;
-	mask |= CRYPTO_ALG_TYPE_MASK;
-
-	return crypto_has_alg(alg_name, type, mask);
-}
-
-/**
- * crypto_blkcipher_name() - return the name / cra_name from the cipher handle
- * @tfm: cipher handle
- *
- * Return: The character string holding the name of the cipher
- */
-static inline const char *crypto_blkcipher_name(struct crypto_blkcipher *tfm)
-{
-	return crypto_tfm_alg_name(crypto_blkcipher_tfm(tfm));
-}
-
-static inline struct blkcipher_tfm *crypto_blkcipher_crt(
-	struct crypto_blkcipher *tfm)
-{
-	return &crypto_blkcipher_tfm(tfm)->crt_blkcipher;
-}
-
-static inline struct blkcipher_alg *crypto_blkcipher_alg(
-	struct crypto_blkcipher *tfm)
-{
-	return &crypto_blkcipher_tfm(tfm)->__crt_alg->cra_blkcipher;
-}
-
-/**
- * crypto_blkcipher_ivsize() - obtain IV size
- * @tfm: cipher handle
- *
- * The size of the IV for the block cipher referenced by the cipher handle is
- * returned. This IV size may be zero if the cipher does not need an IV.
- *
- * Return: IV size in bytes
- */
-static inline unsigned int crypto_blkcipher_ivsize(struct crypto_blkcipher *tfm)
-{
-	return crypto_blkcipher_alg(tfm)->ivsize;
-}
-
-/**
- * crypto_blkcipher_blocksize() - obtain block size of cipher
- * @tfm: cipher handle
- *
- * The block size for the block cipher referenced with the cipher handle is
- * returned. The caller may use that information to allocate appropriate
- * memory for the data returned by the encryption or decryption operation.
- *
- * Return: block size of cipher
- */
-static inline unsigned int crypto_blkcipher_blocksize(
-	struct crypto_blkcipher *tfm)
-{
-	return crypto_tfm_alg_blocksize(crypto_blkcipher_tfm(tfm));
-}
-
-static inline unsigned int crypto_blkcipher_alignmask(
-	struct crypto_blkcipher *tfm)
-{
-	return crypto_tfm_alg_alignmask(crypto_blkcipher_tfm(tfm));
-}
-
-static inline u32 crypto_blkcipher_get_flags(struct crypto_blkcipher *tfm)
-{
-	return crypto_tfm_get_flags(crypto_blkcipher_tfm(tfm));
-}
-
-static inline void crypto_blkcipher_set_flags(struct crypto_blkcipher *tfm,
-					      u32 flags)
-{
-	crypto_tfm_set_flags(crypto_blkcipher_tfm(tfm), flags);
-}
-
-static inline void crypto_blkcipher_clear_flags(struct crypto_blkcipher *tfm,
-						u32 flags)
-{
-	crypto_tfm_clear_flags(crypto_blkcipher_tfm(tfm), flags);
-}
-
-/**
- * crypto_blkcipher_setkey() - set key for cipher
- * @tfm: cipher handle
- * @key: buffer holding the key
- * @keylen: length of the key in bytes
- *
- * The caller provided key is set for the block cipher referenced by the cipher
- * handle.
- *
- * Note, the key length determines the cipher type. Many block ciphers implement
- * different cipher modes depending on the key size, such as AES-128 vs AES-192
- * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128
- * is performed.
- *
- * Return: 0 if the setting of the key was successful; < 0 if an error occurred
- */
-static inline int crypto_blkcipher_setkey(struct crypto_blkcipher *tfm,
-					  const u8 *key, unsigned int keylen)
-{
-	return crypto_blkcipher_crt(tfm)->setkey(crypto_blkcipher_tfm(tfm),
-						 key, keylen);
-}
-
-/**
- * crypto_blkcipher_encrypt() - encrypt plaintext
- * @desc: reference to the block cipher handle with meta data
- * @dst: scatter/gather list that is filled by the cipher operation with the
- *	ciphertext
- * @src: scatter/gather list that holds the plaintext
- * @nbytes: number of bytes of the plaintext to encrypt.
- *
- * Encrypt plaintext data using the IV set by the caller with a preceding
- * call of crypto_blkcipher_set_iv.
- *
- * The blkcipher_desc data structure must be filled by the caller and can
- * reside on the stack. The caller must fill desc as follows: desc.tfm is filled
- * with the block cipher handle; desc.flags is filled with either
- * CRYPTO_TFM_REQ_MAY_SLEEP or 0.
- *
- * Return: 0 if the cipher operation was successful; < 0 if an error occurred
- */
-static inline int crypto_blkcipher_encrypt(struct blkcipher_desc *desc,
-					   struct scatterlist *dst,
-					   struct scatterlist *src,
-					   unsigned int nbytes)
-{
-	desc->info = crypto_blkcipher_crt(desc->tfm)->iv;
-	return crypto_blkcipher_crt(desc->tfm)->encrypt(desc, dst, src, nbytes);
-}
-
-/**
- * crypto_blkcipher_encrypt_iv() - encrypt plaintext with dedicated IV
- * @desc: reference to the block cipher handle with meta data
- * @dst: scatter/gather list that is filled by the cipher operation with the
- *	ciphertext
- * @src: scatter/gather list that holds the plaintext
- * @nbytes: number of bytes of the plaintext to encrypt.
- *
- * Encrypt plaintext data with the use of an IV that is solely used for this
- * cipher operation. Any previously set IV is not used.
- *
- * The blkcipher_desc data structure must be filled by the caller and can
- * reside on the stack. The caller must fill desc as follows: desc.tfm is filled
- * with the block cipher handle; desc.info is filled with the IV to be used for
- * the current operation; desc.flags is filled with either
- * CRYPTO_TFM_REQ_MAY_SLEEP or 0.
- *
- * Return: 0 if the cipher operation was successful; < 0 if an error occurred
- */
-static inline int crypto_blkcipher_encrypt_iv(struct blkcipher_desc *desc,
-					      struct scatterlist *dst,
-					      struct scatterlist *src,
-					      unsigned int nbytes)
-{
-	return crypto_blkcipher_crt(desc->tfm)->encrypt(desc, dst, src, nbytes);
-}
-
-/**
- * crypto_blkcipher_decrypt() - decrypt ciphertext
- * @desc: reference to the block cipher handle with meta data
- * @dst: scatter/gather list that is filled by the cipher operation with the
- *	plaintext
- * @src: scatter/gather list that holds the ciphertext
- * @nbytes: number of bytes of the ciphertext to decrypt.
- *
- * Decrypt ciphertext data using the IV set by the caller with a preceding
- * call of crypto_blkcipher_set_iv.
- *
- * The blkcipher_desc data structure must be filled by the caller as documented
- * for the crypto_blkcipher_encrypt call above.
- *
- * Return: 0 if the cipher operation was successful; < 0 if an error occurred
- *
- */
-static inline int crypto_blkcipher_decrypt(struct blkcipher_desc *desc,
-					   struct scatterlist *dst,
-					   struct scatterlist *src,
-					   unsigned int nbytes)
-{
-	desc->info = crypto_blkcipher_crt(desc->tfm)->iv;
-	return crypto_blkcipher_crt(desc->tfm)->decrypt(desc, dst, src, nbytes);
-}
-
-/**
- * crypto_blkcipher_decrypt_iv() - decrypt ciphertext with dedicated IV
- * @desc: reference to the block cipher handle with meta data
- * @dst: scatter/gather list that is filled by the cipher operation with the
- *	plaintext
- * @src: scatter/gather list that holds the ciphertext
- * @nbytes: number of bytes of the ciphertext to decrypt.
- *
- * Decrypt ciphertext data with the use of an IV that is solely used for this
- * cipher operation. Any previously set IV is not used.
- *
- * The blkcipher_desc data structure must be filled by the caller as documented
- * for the crypto_blkcipher_encrypt_iv call above.
- *
- * Return: 0 if the cipher operation was successful; < 0 if an error occurred
- */
-static inline int crypto_blkcipher_decrypt_iv(struct blkcipher_desc *desc,
-					      struct scatterlist *dst,
-					      struct scatterlist *src,
-					      unsigned int nbytes)
-{
-	return crypto_blkcipher_crt(desc->tfm)->decrypt(desc, dst, src, nbytes);
-}
-
-/**
- * crypto_blkcipher_set_iv() - set IV for cipher
- * @tfm: cipher handle
- * @src: buffer holding the IV
- * @len: length of the IV in bytes
- *
- * The caller provided IV is set for the block cipher referenced by the cipher
- * handle.
- */
-static inline void crypto_blkcipher_set_iv(struct crypto_blkcipher *tfm,
-					   const u8 *src, unsigned int len)
-{
-	memcpy(crypto_blkcipher_crt(tfm)->iv, src, len);
-}
-
-/**
- * crypto_blkcipher_get_iv() - obtain IV from cipher
- * @tfm: cipher handle
- * @dst: buffer filled with the IV
- * @len: length of the buffer dst
- *
- * The caller can obtain the IV set for the block cipher referenced by the
- * cipher handle and store it into the user-provided buffer. If the buffer
- * has an insufficient space, the IV is truncated to fit the buffer.
- */
-static inline void crypto_blkcipher_get_iv(struct crypto_blkcipher *tfm,
-					   u8 *dst, unsigned int len)
-{
-	memcpy(dst, crypto_blkcipher_crt(tfm)->iv, len);
-}
-
 /**
  * DOC: Single Block Cipher API
  *
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 399ad8632356..475668c69dbc 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -17,6 +17,7 @@
 struct dm_dev;
 struct dm_target;
 struct dm_table;
+struct dm_report_zones_args;
 struct mapped_device;
 struct bio_vec;
 
@@ -93,9 +94,9 @@ typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv,
 
 typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev);
 
-typedef int (*dm_report_zones_fn) (struct dm_target *ti, sector_t sector,
-				   struct blk_zone *zones,
-				   unsigned int *nr_zones);
+typedef int (*dm_report_zones_fn) (struct dm_target *ti,
+				   struct dm_report_zones_args *args,
+				   unsigned int nr_zones);
 
 /*
  * These iteration functions are typically used to check (and combine)
@@ -422,10 +423,23 @@ struct gendisk *dm_disk(struct mapped_device *md);
 int dm_suspended(struct dm_target *ti);
 int dm_noflush_suspending(struct dm_target *ti);
 void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors);
-void dm_remap_zone_report(struct dm_target *ti, sector_t start,
-			  struct blk_zone *zones, unsigned int *nr_zones);
 union map_info *dm_get_rq_mapinfo(struct request *rq);
 
+#ifdef CONFIG_BLK_DEV_ZONED
+struct dm_report_zones_args {
+	struct dm_target *tgt;
+	sector_t next_sector;
+
+	void *orig_data;
+	report_zones_cb orig_cb;
+	unsigned int zone_idx;
+
+	/* must be filled by ->report_zones before calling dm_report_zones_cb */
+	sector_t start;
+};
+int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data);
+#endif /* CONFIG_BLK_DEV_ZONED */
+
 /*
  * Device mapper functions to parse and create devices specified by the
  * parameter "dm-mod.create="
@@ -594,9 +608,6 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size);
  */
 #define dm_round_up(n, sz) (dm_div_up((n), (sz)) * (sz))
 
-#define dm_array_too_big(fixed, obj, num) \
-	((num) > (UINT_MAX - (fixed)) / (obj))
-
 /*
  * Sector offset taken relative to the start of the target instead of
  * relative to the start of the device.
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index adf993a3bd58..d03af3605460 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -5,6 +5,8 @@
 #include <linux/dma-mapping.h>
 #include <linux/mem_encrypt.h>
 
+extern unsigned int zone_dma_bits;
+
 #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
 #include <asm/dma-direct.h>
 #else
diff --git a/include/linux/edac.h b/include/linux/edac.h
index c19483b90079..cc31b9742684 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -362,78 +362,6 @@ struct edac_mc_layer {
  */
 #define EDAC_MAX_LAYERS		3
 
-/**
- * EDAC_DIMM_OFF - Macro responsible to get a pointer offset inside a pointer
- *		   array for the element given by [layer0,layer1,layer2]
- *		   position
- *
- * @layers:	a struct edac_mc_layer array, describing how many elements
- *		were allocated for each layer
- * @nlayers:	Number of layers at the @layers array
- * @layer0:	layer0 position
- * @layer1:	layer1 position. Unused if n_layers < 2
- * @layer2:	layer2 position. Unused if n_layers < 3
- *
- * For 1 layer, this macro returns "var[layer0] - var";
- *
- * For 2 layers, this macro is similar to allocate a bi-dimensional array
- * and to return "var[layer0][layer1] - var";
- *
- * For 3 layers, this macro is similar to allocate a tri-dimensional array
- * and to return "var[layer0][layer1][layer2] - var".
- *
- * A loop could be used here to make it more generic, but, as we only have
- * 3 layers, this is a little faster.
- *
- * By design, layers can never be 0 or more than 3. If that ever happens,
- * a NULL is returned, causing an OOPS during the memory allocation routine,
- * with would point to the developer that he's doing something wrong.
- */
-#define EDAC_DIMM_OFF(layers, nlayers, layer0, layer1, layer2) ({		\
-	int __i;							\
-	if ((nlayers) == 1)						\
-		__i = layer0;						\
-	else if ((nlayers) == 2)					\
-		__i = (layer1) + ((layers[1]).size * (layer0));		\
-	else if ((nlayers) == 3)					\
-		__i = (layer2) + ((layers[2]).size * ((layer1) +	\
-			    ((layers[1]).size * (layer0))));		\
-	else								\
-		__i = -EINVAL;						\
-	__i;								\
-})
-
-/**
- * EDAC_DIMM_PTR - Macro responsible to get a pointer inside a pointer array
- *		   for the element given by [layer0,layer1,layer2] position
- *
- * @layers:	a struct edac_mc_layer array, describing how many elements
- *		were allocated for each layer
- * @var:	name of the var where we want to get the pointer
- *		(like mci->dimms)
- * @nlayers:	Number of layers at the @layers array
- * @layer0:	layer0 position
- * @layer1:	layer1 position. Unused if n_layers < 2
- * @layer2:	layer2 position. Unused if n_layers < 3
- *
- * For 1 layer, this macro returns "var[layer0]";
- *
- * For 2 layers, this macro is similar to allocate a bi-dimensional array
- * and to return "var[layer0][layer1]";
- *
- * For 3 layers, this macro is similar to allocate a tri-dimensional array
- * and to return "var[layer0][layer1][layer2]";
- */
-#define EDAC_DIMM_PTR(layers, var, nlayers, layer0, layer1, layer2) ({	\
-	typeof(*var) __p;						\
-	int ___i = EDAC_DIMM_OFF(layers, nlayers, layer0, layer1, layer2);	\
-	if (___i < 0)							\
-		__p = NULL;						\
-	else								\
-		__p = (var)[___i];					\
-	__p;								\
-})
-
 struct dimm_info {
 	struct device dev;
 
@@ -443,6 +371,7 @@ struct dimm_info {
 	unsigned int location[EDAC_MAX_LAYERS];
 
 	struct mem_ctl_info *mci;	/* the parent */
+	unsigned int idx;		/* index within the parent dimm array */
 
 	u32 grain;		/* granularity of reported error in bytes */
 	enum dev_type dtype;	/* memory device type */
@@ -528,15 +457,10 @@ struct errcount_attribute_data {
  *				(typically, a memory controller error)
  */
 struct edac_raw_error_desc {
-	/*
-	 * NOTE: everything before grain won't be cleaned by
-	 * edac_raw_error_desc_clean()
-	 */
 	char location[LOCATION_SIZE];
 	char label[(EDAC_MC_LABEL_LEN + 1 + sizeof(OTHER_LABEL)) * EDAC_MAX_LABELS];
 	long grain;
 
-	/* the vars below and grain will be cleaned on every new error report */
 	u16 error_count;
 	int top_layer;
 	int mid_layer;
@@ -669,4 +593,70 @@ struct mem_ctl_info {
 	bool fake_inject_ue;
 	u16 fake_inject_count;
 };
-#endif
+
+#define mci_for_each_dimm(mci, dimm)				\
+	for ((dimm) = (mci)->dimms[0];				\
+	     (dimm);						\
+	     (dimm) = (dimm)->idx + 1 < (mci)->tot_dimms	\
+		     ? (mci)->dimms[(dimm)->idx + 1]		\
+		     : NULL)
+
+/**
+ * edac_get_dimm_by_index - Get DIMM info at @index from a memory
+ * 			    controller
+ *
+ * @mci:	MC descriptor struct mem_ctl_info
+ * @index:	index in the memory controller's DIMM array
+ *
+ * Returns a struct dimm_info * or NULL on failure.
+ */
+static inline struct dimm_info *
+edac_get_dimm_by_index(struct mem_ctl_info *mci, int index)
+{
+	if (index < 0 || index >= mci->tot_dimms)
+		return NULL;
+
+	if (WARN_ON_ONCE(mci->dimms[index]->idx != index))
+		return NULL;
+
+	return mci->dimms[index];
+}
+
+/**
+ * edac_get_dimm - Get DIMM info from a memory controller given by
+ *                 [layer0,layer1,layer2] position
+ *
+ * @mci:	MC descriptor struct mem_ctl_info
+ * @layer0:	layer0 position
+ * @layer1:	layer1 position. Unused if n_layers < 2
+ * @layer2:	layer2 position. Unused if n_layers < 3
+ *
+ * For 1 layer, this function returns "dimms[layer0]";
+ *
+ * For 2 layers, this function is similar to allocating a two-dimensional
+ * array and returning "dimms[layer0][layer1]";
+ *
+ * For 3 layers, this function is similar to allocating a tri-dimensional
+ * array and returning "dimms[layer0][layer1][layer2]";
+ */
+static inline struct dimm_info *edac_get_dimm(struct mem_ctl_info *mci,
+	int layer0, int layer1, int layer2)
+{
+	int index;
+
+	if (layer0 < 0
+	    || (mci->n_layers > 1 && layer1 < 0)
+	    || (mci->n_layers > 2 && layer2 < 0))
+		return NULL;
+
+	index = layer0;
+
+	if (mci->n_layers > 1)
+		index = index * mci->layers[1].size + layer1;
+
+	if (mci->n_layers > 2)
+		index = index * mci->layers[2].size + layer2;
+
+	return edac_get_dimm_by_index(mci, index);
+}
+#endif /* _LINUX_EDAC_H_ */
diff --git a/include/linux/errname.h b/include/linux/errname.h
new file mode 100644
index 000000000000..e8576ad90cb7
--- /dev/null
+++ b/include/linux/errname.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_ERRNAME_H
+#define _LINUX_ERRNAME_H
+
+#include <linux/stddef.h>
+
+#ifdef CONFIG_SYMBOLIC_ERRNAME
+const char *errname(int err);
+#else
+static inline const char *errname(int err)
+{
+	return NULL;
+}
+#endif
+
+#endif /* _LINUX_ERRNAME_H */
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index cf6571fc9c01..d896b8657085 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -105,6 +105,11 @@ enum fid_type {
 	FILEID_LUSTRE = 0x97,
 
 	/*
+	 * 64 bit unique kernfs id
+	 */
+	FILEID_KERNFS = 0xfe,
+
+	/*
 	 * Filesystems must not use 0xff file ID.
 	 */
 	FILEID_INVALID = 0xff,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e0d909d35763..dde6dc4492a0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -148,8 +148,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File is opened with O_PATH; almost nothing can be done with it */
 #define FMODE_PATH		((__force fmode_t)0x4000)
 
-/* File needs atomic accesses to f_pos */
-#define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
 /* Write access to underlying fs */
 #define FMODE_WRITER		((__force fmode_t)0x10000)
 /* Has read method(s) */
@@ -2632,8 +2630,6 @@ extern void bd_finish_claiming(struct block_device *bdev,
 extern void bd_abort_claiming(struct block_device *bdev,
 			      struct block_device *whole, void *holder);
 extern void blkdev_put(struct block_device *bdev, fmode_t mode);
-extern int __blkdev_reread_part(struct block_device *bdev);
-extern int blkdev_reread_part(struct block_device *bdev);
 
 #ifdef CONFIG_SYSFS
 extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
@@ -2703,8 +2699,6 @@ extern void make_bad_inode(struct inode *);
 extern bool is_bad_inode(struct inode *);
 
 #ifdef CONFIG_BLOCK
-extern void check_disk_size_change(struct gendisk *disk,
-		struct block_device *bdev, bool verbose);
 extern int revalidate_disk(struct gendisk *);
 extern int check_disk_change(struct block_device *);
 extern int __invalidate_device(struct block_device *, bool);
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index f622f7460ed8..1a7bffe78ed5 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -20,7 +20,6 @@
 
 #define FS_CRYPTO_BLOCK_SIZE		16
 
-struct fscrypt_ctx;
 struct fscrypt_info;
 
 struct fscrypt_str {
@@ -62,18 +61,9 @@ struct fscrypt_operations {
 	bool (*dummy_context)(struct inode *);
 	bool (*empty_dir)(struct inode *);
 	unsigned int max_namelen;
-};
-
-/* Decryption work */
-struct fscrypt_ctx {
-	union {
-		struct {
-			struct bio *bio;
-			struct work_struct work;
-		};
-		struct list_head free_list;	/* Free list */
-	};
-	u8 flags;				/* Flags */
+	bool (*has_stable_inodes)(struct super_block *sb);
+	void (*get_ino_and_lblk_bits)(struct super_block *sb,
+				      int *ino_bits_ret, int *lblk_bits_ret);
 };
 
 static inline bool fscrypt_has_encryption_key(const struct inode *inode)
@@ -102,8 +92,6 @@ static inline void fscrypt_handle_d_move(struct dentry *dentry)
 
 /* crypto.c */
 extern void fscrypt_enqueue_decrypt_work(struct work_struct *);
-extern struct fscrypt_ctx *fscrypt_get_ctx(gfp_t);
-extern void fscrypt_release_ctx(struct fscrypt_ctx *);
 
 extern struct page *fscrypt_encrypt_pagecache_blocks(struct page *page,
 						     unsigned int len,
@@ -244,8 +232,6 @@ static inline bool fscrypt_match_name(const struct fscrypt_name *fname,
 
 /* bio.c */
 extern void fscrypt_decrypt_bio(struct bio *);
-extern void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx,
-					struct bio *bio);
 extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t,
 				 unsigned int);
 
@@ -295,16 +281,6 @@ static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work)
 {
 }
 
-static inline struct fscrypt_ctx *fscrypt_get_ctx(gfp_t gfp_flags)
-{
-	return ERR_PTR(-EOPNOTSUPP);
-}
-
-static inline void fscrypt_release_ctx(struct fscrypt_ctx *ctx)
-{
-	return;
-}
-
 static inline struct page *fscrypt_encrypt_pagecache_blocks(struct page *page,
 							    unsigned int len,
 							    unsigned int offs,
@@ -484,11 +460,6 @@ static inline void fscrypt_decrypt_bio(struct bio *bio)
 {
 }
 
-static inline void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx,
-					       struct bio *bio)
-{
-}
-
 static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
 					sector_t pblk, unsigned int len)
 {
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 8a8cb3c401b2..9141f2263286 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -499,7 +499,7 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; }
 /**
  * ftrace_make_nop - convert code into nop
  * @mod: module structure if called by module load initialization
- * @rec: the mcount call site record
+ * @rec: the call site record (e.g. mcount/fentry)
  * @addr: the address that the call site should be calling
  *
  * This is a very sensitive operation and great care needs
@@ -520,9 +520,38 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; }
 extern int ftrace_make_nop(struct module *mod,
 			   struct dyn_ftrace *rec, unsigned long addr);
 
+
+/**
+ * ftrace_init_nop - initialize a nop call site
+ * @mod: module structure if called by module load initialization
+ * @rec: the call site record (e.g. mcount/fentry)
+ *
+ * This is a very sensitive operation and great care needs
+ * to be taken by the arch.  The operation should carefully
+ * read the location, check to see if what is read is indeed
+ * what we expect it to be, and then on success of the compare,
+ * it should write to the location.
+ *
+ * The code segment at @rec->ip should contain the contents created by
+ * the compiler
+ *
+ * Return must be:
+ *  0 on success
+ *  -EFAULT on error reading the location
+ *  -EINVAL on a failed compare of the contents
+ *  -EPERM  on error writing to the location
+ * Any other value will be considered a failure.
+ */
+#ifndef ftrace_init_nop
+static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
+{
+	return ftrace_make_nop(mod, rec, MCOUNT_ADDR);
+}
+#endif
+
 /**
  * ftrace_make_call - convert a nop call site into a call to addr
- * @rec: the mcount call site record
+ * @rec: the call site record (e.g. mcount/fentry)
  * @addr: the address that the call site should call
  *
  * This is a very sensitive operation and great care needs
@@ -545,7 +574,7 @@ extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 /**
  * ftrace_modify_call - convert from one addr to another (no nop)
- * @rec: the mcount call site record
+ * @rec: the call site record (e.g. mcount/fentry)
  * @old_addr: the address expected to be currently called to
  * @addr: the address to change to
  *
@@ -709,6 +738,11 @@ static inline unsigned long get_lock_parent_ip(void)
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 extern void ftrace_init(void);
+#ifdef CC_USING_PATCHABLE_FUNCTION_ENTRY
+#define FTRACE_CALLSITE_SECTION	"__patchable_function_entries"
+#else
+#define FTRACE_CALLSITE_SECTION	"__mcount_loc"
+#endif
 #else
 static inline void ftrace_init(void) { }
 #endif
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 8b5330dd5ac0..8bb63027e4d6 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -621,9 +621,10 @@ extern void blk_invalidate_devt(dev_t devt);
 extern dev_t blk_lookup_devt(const char *name, int partno);
 extern char *disk_name (struct gendisk *hd, int partno, char *buf);
 
+int bdev_disk_changed(struct block_device *bdev, bool invalidate);
+int blk_add_partitions(struct gendisk *disk, struct block_device *bdev);
+int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev);
 extern int disk_expand_part_tbl(struct gendisk *disk, int target);
-extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev);
-extern int invalidate_partitions(struct gendisk *disk, struct block_device *bdev);
 extern struct hd_struct * __must_check add_partition(struct gendisk *disk,
 						     int partno, sector_t start,
 						     sector_t len, int flags,
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 5cc10cf7cb3e..a0bde9e12efa 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -487,6 +487,8 @@
 #define ICC_CTLR_EL1_EOImode_MASK	(1 << ICC_CTLR_EL1_EOImode_SHIFT)
 #define ICC_CTLR_EL1_CBPR_SHIFT		0
 #define ICC_CTLR_EL1_CBPR_MASK		(1 << ICC_CTLR_EL1_CBPR_SHIFT)
+#define ICC_CTLR_EL1_PMHE_SHIFT		6
+#define ICC_CTLR_EL1_PMHE_MASK		(1 << ICC_CTLR_EL1_PMHE_SHIFT)
 #define ICC_CTLR_EL1_PRI_BITS_SHIFT	8
 #define ICC_CTLR_EL1_PRI_BITS_MASK	(0x7 << ICC_CTLR_EL1_PRI_BITS_SHIFT)
 #define ICC_CTLR_EL1_ID_BITS_SHIFT	11
diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h
index e6b155713b47..5dbcfc65f21e 100644
--- a/include/linux/irqchip/arm-gic-v4.h
+++ b/include/linux/irqchip/arm-gic-v4.h
@@ -32,9 +32,13 @@ struct its_vm {
 struct its_vpe {
 	struct page 		*vpt_page;
 	struct its_vm		*its_vm;
+	/* per-vPE VLPI tracking */
+	atomic_t		vlpi_count;
 	/* Doorbell interrupt */
 	int			irq;
 	irq_hw_number_t		vpe_db_lpi;
+	/* VPE resident */
+	bool			resident;
 	/* VPE proxy mapping */
 	int			vpe_proxy_event;
 	/*
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 936b61bd504e..dded2e5a9f42 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -104,21 +104,6 @@ struct kernfs_elem_attr {
 	struct kernfs_node	*notify_next;	/* for kernfs_notify() */
 };
 
-/* represent a kernfs node */
-union kernfs_node_id {
-	struct {
-		/*
-		 * blktrace will export this struct as a simplified 'struct
-		 * fid' (which is a big data struction), so userspace can use
-		 * it to find kernfs node. The layout must match the first two
-		 * fields of 'struct fid' exactly.
-		 */
-		u32		ino;
-		u32		generation;
-	};
-	u64			id;
-};
-
 /*
  * kernfs_node - the building block of kernfs hierarchy.  Each and every
  * kernfs node is represented by single kernfs_node.  Most fields are
@@ -155,7 +140,12 @@ struct kernfs_node {
 
 	void			*priv;
 
-	union kernfs_node_id	id;
+	/*
+	 * 64bit unique ID.  On 64bit ino setups, id is the ino.  On 32bit,
+	 * the low 32bits are ino and upper generation.
+	 */
+	u64			id;
+
 	unsigned short		flags;
 	umode_t			mode;
 	struct kernfs_iattrs	*iattr;
@@ -187,7 +177,8 @@ struct kernfs_root {
 
 	/* private fields, do not use outside kernfs proper */
 	struct idr		ino_idr;
-	u32			next_generation;
+	u32			last_id_lowbits;
+	u32			id_highbits;
 	struct kernfs_syscall_ops *syscall_ops;
 
 	/* list of kernfs_super_info of this root, protected by kernfs_mutex */
@@ -291,6 +282,34 @@ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn)
 	return kn->flags & KERNFS_TYPE_MASK;
 }
 
+static inline ino_t kernfs_id_ino(u64 id)
+{
+	/* id is ino if ino_t is 64bit; otherwise, low 32bits */
+	if (sizeof(ino_t) >= sizeof(u64))
+		return id;
+	else
+		return (u32)id;
+}
+
+static inline u32 kernfs_id_gen(u64 id)
+{
+	/* gen is fixed at 1 if ino_t is 64bit; otherwise, high 32bits */
+	if (sizeof(ino_t) >= sizeof(u64))
+		return 1;
+	else
+		return id >> 32;
+}
+
+static inline ino_t kernfs_ino(struct kernfs_node *kn)
+{
+	return kernfs_id_ino(kn->id);
+}
+
+static inline ino_t kernfs_gen(struct kernfs_node *kn)
+{
+	return kernfs_id_gen(kn->id);
+}
+
 /**
  * kernfs_enable_ns - enable namespace under a directory
  * @kn: directory of interest, should be empty
@@ -382,8 +401,8 @@ void kernfs_kill_sb(struct super_block *sb);
 
 void kernfs_init(void);
 
-struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root,
-	const union kernfs_node_id *id);
+struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root,
+						   u64 id);
 #else	/* CONFIG_KERNFS */
 
 static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index d41c521a39da..7ed1e2f8641e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -266,7 +266,8 @@ struct kvm_vcpu {
 	struct preempt_notifier preempt_notifier;
 #endif
 	int cpu;
-	int vcpu_id;
+	int vcpu_id; /* id given by userspace at creation */
+	int vcpu_idx; /* index in kvm->vcpus array */
 	int srcu_idx;
 	int mode;
 	u64 requests;
@@ -278,7 +279,6 @@ struct kvm_vcpu {
 	struct mutex mutex;
 	struct kvm_run *run;
 
-	int guest_xcr0_loaded;
 	struct swait_queue_head wq;
 	struct pid __rcu *pid;
 	int sigset_active;
@@ -571,13 +571,7 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id)
 
 static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu *tmp;
-	int idx;
-
-	kvm_for_each_vcpu(idx, tmp, vcpu->kvm)
-		if (tmp == vcpu)
-			return idx;
-	BUG();
+	return vcpu->vcpu_idx;
 }
 
 #define kvm_for_each_memslot(memslot, slots)	\
@@ -622,6 +616,7 @@ void kvm_exit(void);
 
 void kvm_get_kvm(struct kvm *kvm);
 void kvm_put_kvm(struct kvm *kvm);
+void kvm_put_kvm_no_destroy(struct kvm *kvm);
 
 static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
 {
@@ -746,6 +741,28 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 				  unsigned long len);
 int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			      gpa_t gpa, unsigned long len);
+
+#define __kvm_put_guest(kvm, gfn, offset, value, type)			\
+({									\
+	unsigned long __addr = gfn_to_hva(kvm, gfn);			\
+	type __user *__uaddr = (type __user *)(__addr + offset);	\
+	int __ret = -EFAULT;						\
+									\
+	if (!kvm_is_error_hva(__addr))					\
+		__ret = put_user(value, __uaddr);			\
+	if (!__ret)							\
+		mark_page_dirty(kvm, gfn);				\
+	__ret;								\
+})
+
+#define kvm_put_guest(kvm, gpa, value, type)				\
+({									\
+	gpa_t __gpa = gpa;						\
+	struct kvm *__kvm = kvm;					\
+	__kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT,			\
+			offset_in_page(__gpa), (value), type);		\
+})
+
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
@@ -791,6 +808,8 @@ void kvm_reload_remote_mmus(struct kvm *kvm);
 bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
 				 unsigned long *vcpu_bitmap, cpumask_var_t tmp);
 bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);
+bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req,
+				unsigned long *vcpu_bitmap);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -1241,7 +1260,7 @@ extern unsigned int halt_poll_ns_grow_start;
 extern unsigned int halt_poll_ns_shrink;
 
 struct kvm_device {
-	struct kvm_device_ops *ops;
+	const struct kvm_device_ops *ops;
 	struct kvm *kvm;
 	void *private;
 	struct list_head vm_node;
@@ -1294,7 +1313,7 @@ struct kvm_device_ops {
 void kvm_device_get(struct kvm_device *dev);
 void kvm_device_put(struct kvm_device *dev);
 struct kvm_device *kvm_device_from_filp(struct file *filp);
-int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
+int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type);
 void kvm_unregister_device_ops(u32 type);
 
 extern struct kvm_device_ops kvm_mpic_ops;
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index bde5374ae021..1c88e69db3d9 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -35,6 +35,8 @@ typedef unsigned long  gva_t;
 typedef u64            gpa_t;
 typedef u64            gfn_t;
 
+#define GPA_INVALID	(~(gpa_t)0)
+
 typedef unsigned long  hva_t;
 typedef u64            hpa_t;
 typedef u64            hfn_t;
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 207e7ee764ce..d3bbfddf616a 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -484,6 +484,7 @@ enum hsm_task_states {
 };
 
 enum ata_completion_errors {
+	AC_ERR_OK		= 0,	    /* no error */
 	AC_ERR_DEV		= (1 << 0), /* device reported error */
 	AC_ERR_HSM		= (1 << 1), /* host state machine violation */
 	AC_ERR_TIMEOUT		= (1 << 2), /* timeout */
@@ -891,9 +892,9 @@ struct ata_port_operations {
 	/*
 	 * Command execution
 	 */
-	int  (*qc_defer)(struct ata_queued_cmd *qc);
-	int  (*check_atapi_dma)(struct ata_queued_cmd *qc);
-	void (*qc_prep)(struct ata_queued_cmd *qc);
+	int (*qc_defer)(struct ata_queued_cmd *qc);
+	int (*check_atapi_dma)(struct ata_queued_cmd *qc);
+	enum ata_completion_errors (*qc_prep)(struct ata_queued_cmd *qc);
 	unsigned int (*qc_issue)(struct ata_queued_cmd *qc);
 	bool (*qc_fill_rtf)(struct ata_queued_cmd *qc);
 
@@ -1161,7 +1162,7 @@ extern int ata_xfer_mode2shift(unsigned long xfer_mode);
 extern const char *ata_mode_string(unsigned long xfer_mask);
 extern unsigned long ata_id_xfermask(const u16 *id);
 extern int ata_std_qc_defer(struct ata_queued_cmd *qc);
-extern void ata_noop_qc_prep(struct ata_queued_cmd *qc);
+extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc);
 extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg,
 		 unsigned int n_elem);
 extern unsigned int ata_dev_classify(const struct ata_taskfile *tf);
@@ -1893,9 +1894,9 @@ extern const struct ata_port_operations ata_bmdma_port_ops;
 	.sg_tablesize		= LIBATA_MAX_PRD,		\
 	.dma_boundary		= ATA_DMA_BOUNDARY
 
-extern void ata_bmdma_qc_prep(struct ata_queued_cmd *qc);
+extern enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc);
 extern unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc);
-extern void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc);
+extern enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc);
 extern unsigned int ata_bmdma_port_intr(struct ata_port *ap,
 				      struct ata_queued_cmd *qc);
 extern irqreturn_t ata_bmdma_interrupt(int irq, void *dev_instance);
diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h
index 273400814020..e894e74905f3 100644
--- a/include/linux/livepatch.h
+++ b/include/linux/livepatch.h
@@ -131,9 +131,22 @@ struct klp_object {
 };
 
 /**
+ * struct klp_state - state of the system modified by the livepatch
+ * @id:		system state identifier (non-zero)
+ * @version:	version of the change
+ * @data:	custom data
+ */
+struct klp_state {
+	unsigned long id;
+	unsigned int version;
+	void *data;
+};
+
+/**
  * struct klp_patch - patch structure for live patching
  * @mod:	reference to the live patch module
  * @objs:	object entries for kernel objects to be patched
+ * @states:	system states that can get modified
  * @replace:	replace all actively used patches
  * @list:	list node for global list of actively used patches
  * @kobj:	kobject for sysfs resources
@@ -147,6 +160,7 @@ struct klp_patch {
 	/* external */
 	struct module *mod;
 	struct klp_object *objs;
+	struct klp_state *states;
 	bool replace;
 
 	/* internal */
@@ -217,6 +231,9 @@ void *klp_shadow_get_or_alloc(void *obj, unsigned long id,
 void klp_shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor);
 void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor);
 
+struct klp_state *klp_get_state(struct klp_patch *patch, unsigned long id);
+struct klp_state *klp_get_prev_state(unsigned long id);
+
 #else /* !CONFIG_LIVEPATCH */
 
 static inline int klp_module_coming(struct module *mod) { return 0; }
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index bda20282746b..b0a36d1580b6 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -359,33 +359,40 @@ struct per_cpu_nodestat {
 #endif /* !__GENERATING_BOUNDS.H */
 
 enum zone_type {
-#ifdef CONFIG_ZONE_DMA
 	/*
-	 * ZONE_DMA is used when there are devices that are not able
-	 * to do DMA to all of addressable memory (ZONE_NORMAL). Then we
-	 * carve out the portion of memory that is needed for these devices.
-	 * The range is arch specific.
+	 * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able
+	 * to DMA to all of the addressable memory (ZONE_NORMAL).
+	 * On architectures where this area covers the whole 32 bit address
+	 * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller
+	 * DMA addressing constraints. This distinction is important as a 32bit
+	 * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit
+	 * platforms may need both zones as they support peripherals with
+	 * different DMA addressing limitations.
+	 *
+	 * Some examples:
+	 *
+	 *  - i386 and x86_64 have a fixed 16M ZONE_DMA and ZONE_DMA32 for the
+	 *    rest of the lower 4G.
+	 *
+	 *  - arm only uses ZONE_DMA, the size, up to 4G, may vary depending on
+	 *    the specific device.
+	 *
+	 *  - arm64 has a fixed 1G ZONE_DMA and ZONE_DMA32 for the rest of the
+	 *    lower 4G.
 	 *
-	 * Some examples
+	 *  - powerpc only uses ZONE_DMA, the size, up to 2G, may vary
+	 *    depending on the specific device.
 	 *
-	 * Architecture		Limit
-	 * ---------------------------
-	 * parisc, ia64, sparc	<4G
-	 * s390, powerpc	<2G
-	 * arm			Various
-	 * alpha		Unlimited or 0-16MB.
+	 *  - s390 uses ZONE_DMA fixed to the lower 2G.
 	 *
-	 * i386, x86_64 and multiple other arches
-	 * 			<16M.
+	 *  - ia64 and riscv only use ZONE_DMA32.
+	 *
+	 *  - parisc uses neither.
 	 */
+#ifdef CONFIG_ZONE_DMA
 	ZONE_DMA,
 #endif
 #ifdef CONFIG_ZONE_DMA32
-	/*
-	 * x86_64 needs two ZONE_DMAs because it supports devices that are
-	 * only able to do DMA to the lower 16M but also 32 bit devices that
-	 * can only do DMA areas below 4G.
-	 */
 	ZONE_DMA32,
 #endif
 	/*
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index fc0b4b19c900..5a4623fc586b 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -22,6 +22,7 @@
 #define SNOR_MFR_INTEL		CFI_MFR_INTEL
 #define SNOR_MFR_ST		CFI_MFR_ST	/* ST Micro */
 #define SNOR_MFR_MICRON		CFI_MFR_MICRON	/* Micron */
+#define SNOR_MFR_ISSI		CFI_MFR_PMC
 #define SNOR_MFR_MACRONIX	CFI_MFR_MACRONIX
 #define SNOR_MFR_SPANSION	CFI_MFR_AMD
 #define SNOR_MFR_SST		CFI_MFR_SST
@@ -133,7 +134,7 @@
 #define SR_E_ERR		BIT(5)
 #define SR_P_ERR		BIT(6)
 
-#define SR_QUAD_EN_MX		BIT(6)	/* Macronix Quad I/O */
+#define SR1_QUAD_EN_BIT6	BIT(6)
 
 /* Enhanced Volatile Configuration Register bits */
 #define EVCR_QUAD_EN_MICRON	BIT(7)	/* Micron Quad I/O */
@@ -144,10 +145,8 @@
 #define FSR_P_ERR		BIT(4)	/* Program operation status */
 #define FSR_PT_ERR		BIT(1)	/* Protection error bit */
 
-/* Configuration Register bits. */
-#define CR_QUAD_EN_SPAN		BIT(1)	/* Spansion Quad I/O */
-
 /* Status Register 2 bits. */
+#define SR2_QUAD_EN_BIT1	BIT(1)
 #define SR2_QUAD_EN_BIT7	BIT(7)
 
 /* Supported SPI protocols */
@@ -243,6 +242,9 @@ enum spi_nor_option_flags {
 	SNOR_F_4B_OPCODES	= BIT(6),
 	SNOR_F_HAS_4BAIT	= BIT(7),
 	SNOR_F_HAS_LOCK		= BIT(8),
+	SNOR_F_HAS_16BIT_SR	= BIT(9),
+	SNOR_F_NO_READ_CR	= BIT(10),
+
 };
 
 /**
@@ -466,6 +468,34 @@ enum spi_nor_pp_command_index {
 struct spi_nor;
 
 /**
+ * struct spi_nor_controller_ops - SPI NOR controller driver specific
+ *                                 operations.
+ * @prepare:		[OPTIONAL] do some preparations for the
+ *			read/write/erase/lock/unlock operations.
+ * @unprepare:		[OPTIONAL] do some post work after the
+ *			read/write/erase/lock/unlock operations.
+ * @read_reg:		read out the register.
+ * @write_reg:		write data to the register.
+ * @read:		read data from the SPI NOR.
+ * @write:		write data to the SPI NOR.
+ * @erase:		erase a sector of the SPI NOR at the offset @offs; if
+ *			not provided by the driver, spi-nor will send the erase
+ *			opcode via write_reg().
+ */
+struct spi_nor_controller_ops {
+	int (*prepare)(struct spi_nor *nor, enum spi_nor_ops ops);
+	void (*unprepare)(struct spi_nor *nor, enum spi_nor_ops ops);
+	int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, size_t len);
+	int (*write_reg)(struct spi_nor *nor, u8 opcode, const u8 *buf,
+			 size_t len);
+
+	ssize_t (*read)(struct spi_nor *nor, loff_t from, size_t len, u8 *buf);
+	ssize_t (*write)(struct spi_nor *nor, loff_t to, size_t len,
+			 const u8 *buf);
+	int (*erase)(struct spi_nor *nor, loff_t offs);
+};
+
+/**
  * struct spi_nor_locking_ops - SPI NOR locking methods
  * @lock:	lock a region of the SPI NOR.
  * @unlock:	unlock a region of the SPI NOR.
@@ -549,19 +579,7 @@ struct flash_info;
  * @read_proto:		the SPI protocol for read operations
  * @write_proto:	the SPI protocol for write operations
  * @reg_proto		the SPI protocol for read_reg/write_reg/erase operations
- * @prepare:		[OPTIONAL] do some preparations for the
- *			read/write/erase/lock/unlock operations
- * @unprepare:		[OPTIONAL] do some post work after the
- *			read/write/erase/lock/unlock operations
- * @read_reg:		[DRIVER-SPECIFIC] read out the register
- * @write_reg:		[DRIVER-SPECIFIC] write data to the register
- * @read:		[DRIVER-SPECIFIC] read data from the SPI NOR
- * @write:		[DRIVER-SPECIFIC] write data to the SPI NOR
- * @erase:		[DRIVER-SPECIFIC] erase a sector of the SPI NOR
- *			at the offset @offs; if not provided by the driver,
- *			spi-nor will send the erase opcode via write_reg()
- * @clear_sr_bp:	[FLASH-SPECIFIC] clears the Block Protection Bits from
- *			the SPI NOR Status Register.
+ * @controller_ops:	SPI NOR controller driver specific operations.
  * @params:		[FLASH-SPECIFIC] SPI-NOR flash parameters and settings.
  *                      The structure includes legacy flash parameters and
  *                      settings that can be overwritten by the spi_nor_fixups
@@ -588,18 +606,8 @@ struct spi_nor {
 	bool			sst_write_second;
 	u32			flags;
 
-	int (*prepare)(struct spi_nor *nor, enum spi_nor_ops ops);
-	void (*unprepare)(struct spi_nor *nor, enum spi_nor_ops ops);
-	int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len);
-	int (*write_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len);
-
-	ssize_t (*read)(struct spi_nor *nor, loff_t from,
-			size_t len, u_char *read_buf);
-	ssize_t (*write)(struct spi_nor *nor, loff_t to,
-			size_t len, const u_char *write_buf);
-	int (*erase)(struct spi_nor *nor, loff_t offs);
+	const struct spi_nor_controller_ops *controller_ops;
 
-	int (*clear_sr_bp)(struct spi_nor *nor);
 	struct spi_nor_flash_parameter params;
 
 	void *priv;
diff --git a/include/linux/nvme-fc.h b/include/linux/nvme-fc.h
index 067c9fea64fe..e8c30b39bb27 100644
--- a/include/linux/nvme-fc.h
+++ b/include/linux/nvme-fc.h
@@ -4,33 +4,60 @@
  */
 
 /*
- * This file contains definitions relative to FC-NVME r1.14 (16-020vB).
- * The fcnvme_lsdesc_cr_assoc_cmd struct reflects expected r1.16 content.
+ * This file contains definitions relative to FC-NVME-2 r1.06
+ * (T11-2019-00210-v001).
  */
 
 #ifndef _NVME_FC_H
 #define _NVME_FC_H 1
 
+#include <uapi/scsi/fc/fc_fs.h>
 
-#define NVME_CMD_SCSI_ID		0xFD
+#define NVME_CMD_FORMAT_ID		0xFD
 #define NVME_CMD_FC_ID			FC_TYPE_NVME
 
 /* FC-NVME Cmd IU Flags */
-#define FCNVME_CMD_FLAGS_DIRMASK	0x03
-#define FCNVME_CMD_FLAGS_WRITE		0x01
-#define FCNVME_CMD_FLAGS_READ		0x02
+enum {
+	FCNVME_CMD_FLAGS_DIRMASK	= 0x03,
+	FCNVME_CMD_FLAGS_WRITE		= (1 << 0),
+	FCNVME_CMD_FLAGS_READ		= (1 << 1),
+
+	FCNVME_CMD_FLAGS_PICWP		= (1 << 2),
+};
+
+enum {
+	FCNVME_CMD_CAT_MASK		= 0x0F,
+	FCNVME_CMD_CAT_ADMINQ		= 0x01,
+	FCNVME_CMD_CAT_CSSMASK		= 0x07,
+	FCNVME_CMD_CAT_CSSFLAG		= 0x08,
+};
+
+static inline __u8 fccmnd_set_cat_admin(__u8 rsv_cat)
+{
+	return (rsv_cat & ~FCNVME_CMD_CAT_MASK) | FCNVME_CMD_CAT_ADMINQ;
+}
+
+static inline __u8 fccmnd_set_cat_css(__u8 rsv_cat, __u8 css)
+{
+	return (rsv_cat & ~FCNVME_CMD_CAT_MASK) | FCNVME_CMD_CAT_CSSFLAG |
+		(css & FCNVME_CMD_CAT_CSSMASK);
+}
 
 struct nvme_fc_cmd_iu {
-	__u8			scsi_id;
+	__u8			format_id;
 	__u8			fc_id;
 	__be16			iu_len;
-	__u8			rsvd4[3];
+	__u8			rsvd4[2];
+	__u8			rsv_cat;
 	__u8			flags;
 	__be64			connection_id;
 	__be32			csn;
 	__be32			data_len;
 	struct nvme_command	sqe;
-	__be32			rsvd88[2];
+	__u8			dps;
+	__u8			lbads;
+	__be16			ms;
+	__be32			rsvd92;
 };
 
 #define NVME_FC_SIZEOF_ZEROS_RSP	12
@@ -38,11 +65,12 @@ struct nvme_fc_cmd_iu {
 enum {
 	FCNVME_SC_SUCCESS		= 0,
 	FCNVME_SC_INVALID_FIELD		= 1,
-	FCNVME_SC_INVALID_CONNID	= 2,
+	/* reserved			  2 */
+	FCNVME_SC_ILL_CONN_PARAMS	= 3,
 };
 
 struct nvme_fc_ersp_iu {
-	__u8			status_code;
+	__u8			ersp_result;
 	__u8			rsvd1;
 	__be16			iu_len;
 	__be32			rsn;
@@ -53,14 +81,44 @@ struct nvme_fc_ersp_iu {
 };
 
 
-/* FC-NVME Link Services */
+#define FCNVME_NVME_SR_OPCODE	0x01
+
+struct nvme_fc_nvme_sr_iu {
+	__u8			fc_id;
+	__u8			opcode;
+	__u8			rsvd2;
+	__u8			retry_rctl;
+	__be32			rsvd4;
+};
+
+
+enum {
+	FCNVME_SRSTAT_ACC		= 0x0,
+	FCNVME_SRSTAT_INV_FCID		= 0x1,
+	/* reserved			  0x2 */
+	FCNVME_SRSTAT_LOGICAL_ERR	= 0x3,
+	FCNVME_SRSTAT_INV_QUALIF	= 0x4,
+	FCNVME_SRSTAT_UNABL2PERFORM	= 0x9,
+};
+
+struct nvme_fc_nvme_sr_rsp_iu {
+	__u8			fc_id;
+	__u8			opcode;
+	__u8			rsvd2;
+	__u8			status;
+	__be32			rsvd4;
+};
+
+
+/* FC-NVME Link Services - LS cmd values (w0 bits 31:24) */
 enum {
 	FCNVME_LS_RSVD			= 0,
 	FCNVME_LS_RJT			= 1,
 	FCNVME_LS_ACC			= 2,
-	FCNVME_LS_CREATE_ASSOCIATION	= 3,
-	FCNVME_LS_CREATE_CONNECTION	= 4,
-	FCNVME_LS_DISCONNECT		= 5,
+	FCNVME_LS_CREATE_ASSOCIATION	= 3,	/* Create Association */
+	FCNVME_LS_CREATE_CONNECTION	= 4,	/* Create I/O Connection */
+	FCNVME_LS_DISCONNECT_ASSOC	= 5,	/* Disconnect Association */
+	FCNVME_LS_DISCONNECT_CONN	= 6,	/* Disconnect Connection */
 };
 
 /* FC-NVME Link Service Descriptors */
@@ -117,14 +175,17 @@ enum fcnvme_ls_rjt_reason {
 	FCNVME_RJT_RC_UNSUP		= 0x0b,
 	/* command not supported */
 
-	FCNVME_RJT_RC_INPROG		= 0x0e,
-	/* command already in progress */
-
 	FCNVME_RJT_RC_INV_ASSOC		= 0x40,
-	/* Invalid Association ID*/
+	/* Invalid Association ID */
 
 	FCNVME_RJT_RC_INV_CONN		= 0x41,
-	/* Invalid Connection ID*/
+	/* Invalid Connection ID */
+
+	FCNVME_RJT_RC_INV_PARAM		= 0x42,
+	/* Invalid Parameters */
+
+	FCNVME_RJT_RC_INSUF_RES		= 0x43,
+	/* Insufficient Resources */
 
 	FCNVME_RJT_RC_VENDOR		= 0xff,
 	/* vendor specific error */
@@ -138,14 +199,32 @@ enum fcnvme_ls_rjt_explan {
 	FCNVME_RJT_EXP_OXID_RXID	= 0x17,
 	/* invalid OX_ID-RX_ID combination */
 
-	FCNVME_RJT_EXP_INSUF_RES	= 0x29,
-	/* insufficient resources */
-
 	FCNVME_RJT_EXP_UNAB_DATA	= 0x2a,
 	/* unable to supply requested data */
 
 	FCNVME_RJT_EXP_INV_LEN		= 0x2d,
 	/* Invalid payload length */
+
+	FCNVME_RJT_EXP_INV_ERSP_RAT	= 0x40,
+	/* Invalid NVMe_ERSP Ratio */
+
+	FCNVME_RJT_EXP_INV_CTLR_ID	= 0x41,
+	/* Invalid Controller ID */
+
+	FCNVME_RJT_EXP_INV_QUEUE_ID	= 0x42,
+	/* Invalid Queue ID */
+
+	FCNVME_RJT_EXP_INV_SQSIZE	= 0x43,
+	/* Invalid Submission Queue Size */
+
+	FCNVME_RJT_EXP_INV_HOSTID	= 0x44,
+	/* Invalid HOST ID */
+
+	FCNVME_RJT_EXP_INV_HOSTNQN	= 0x45,
+	/* Invalid HOSTNQN */
+
+	FCNVME_RJT_EXP_INV_SUBNQN	= 0x46,
+	/* Invalid SUBNQN */
 };
 
 /* FCNVME_LSDESC_RJT */
@@ -209,21 +288,11 @@ struct fcnvme_lsdesc_cr_conn_cmd {
 	__be32  rsvd52;
 };
 
-/* Disconnect Scope Values */
-enum {
-	FCNVME_DISCONN_ASSOCIATION	= 0,
-	FCNVME_DISCONN_CONNECTION	= 1,
-};
-
 /* FCNVME_LSDESC_DISCONN_CMD */
 struct fcnvme_lsdesc_disconn_cmd {
 	__be32	desc_tag;		/* FCNVME_LSDESC_xxx */
 	__be32	desc_len;
-	u8	rsvd8[3];
-	/* note: scope is really a 1 bit field */
-	u8	scope;			/* FCNVME_DISCONN_xxx */
-	__be32	rsvd12;
-	__be64	id;
+	__be32	rsvd8[4];
 };
 
 /* FCNVME_LSDESC_CONN_ID */
@@ -242,9 +311,14 @@ struct fcnvme_lsdesc_assoc_id {
 
 /* r_ctl values */
 enum {
-	FCNVME_RS_RCTL_DATA		= 1,
-	FCNVME_RS_RCTL_XFER_RDY		= 5,
-	FCNVME_RS_RCTL_RSP		= 8,
+	FCNVME_RS_RCTL_CMND		= 0x6,
+	FCNVME_RS_RCTL_DATA		= 0x1,
+	FCNVME_RS_RCTL_CONF		= 0x3,
+	FCNVME_RS_RCTL_SR		= 0x9,
+	FCNVME_RS_RCTL_XFER_RDY		= 0x5,
+	FCNVME_RS_RCTL_RSP		= 0x7,
+	FCNVME_RS_RCTL_ERSP		= 0x8,
+	FCNVME_RS_RCTL_SR_RSP		= 0xA,
 };
 
 
@@ -264,7 +338,10 @@ struct fcnvme_ls_acc_hdr {
 	struct fcnvme_ls_rqst_w0		w0;
 	__be32					desc_list_len;
 	struct fcnvme_lsdesc_rqst		rqst;
-	/* Followed by cmd-specific ACC descriptors, see next definitions */
+	/*
+	 * Followed by cmd-specific ACCEPT descriptors, see xxx_acc
+	 * definitions below
+	 */
 };
 
 /* FCNVME_LS_CREATE_ASSOCIATION */
@@ -302,25 +379,39 @@ struct fcnvme_ls_cr_conn_acc {
 	struct fcnvme_lsdesc_conn_id		connectid;
 };
 
-/* FCNVME_LS_DISCONNECT */
-struct fcnvme_ls_disconnect_rqst {
+/* FCNVME_LS_DISCONNECT_ASSOC */
+struct fcnvme_ls_disconnect_assoc_rqst {
 	struct fcnvme_ls_rqst_w0		w0;
 	__be32					desc_list_len;
 	struct fcnvme_lsdesc_assoc_id		associd;
 	struct fcnvme_lsdesc_disconn_cmd	discon_cmd;
 };
 
-struct fcnvme_ls_disconnect_acc {
+struct fcnvme_ls_disconnect_assoc_acc {
+	struct fcnvme_ls_acc_hdr		hdr;
+};
+
+
+/* FCNVME_LS_DISCONNECT_CONN */
+struct fcnvme_ls_disconnect_conn_rqst {
+	struct fcnvme_ls_rqst_w0		w0;
+	__be32					desc_list_len;
+	struct fcnvme_lsdesc_assoc_id		associd;
+	struct fcnvme_lsdesc_disconn_cmd	connectid;
+};
+
+struct fcnvme_ls_disconnect_conn_acc {
 	struct fcnvme_ls_acc_hdr		hdr;
 };
 
 
 /*
- * Yet to be defined in FC-NVME:
+ * Default R_A_TOV is pulled in from fc_fs.h but needs conversion
+ * from ms to seconds for our use.
  */
-#define NVME_FC_CONNECT_TIMEOUT_SEC	2		/* 2 seconds */
-#define NVME_FC_LS_TIMEOUT_SEC		2		/* 2 seconds */
-#define NVME_FC_TGTOP_TIMEOUT_SEC	2		/* 2 seconds */
+#define FC_TWO_TIMES_R_A_TOV		(2 * (FC_DEF_R_A_TOV / 1000))
+#define NVME_FC_LS_TIMEOUT_SEC		FC_TWO_TIMES_R_A_TOV
+#define NVME_FC_TGTOP_TIMEOUT_SEC	FC_TWO_TIMES_R_A_TOV
 
 /*
  * TRADDR string must be of form "nn-<16hexdigits>:pn-<16hexdigits>"
@@ -328,6 +419,7 @@ struct fcnvme_ls_disconnect_acc {
  * infront of the <16hexdigits>.  Without is considered the "min" string
  * and with is considered the "max" string. The hexdigits may be upper
  * or lower case.
+ * Note: FC-NVME-2 standard requires a "0x" prefix.
  */
 #define NVME_FC_TRADDR_NNLEN		3	/* "?n-" */
 #define NVME_FC_TRADDR_OXNNLEN		5	/* "?n-0x" */
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index f61d6906e59d..3d5189f46cb1 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -107,8 +107,22 @@ enum {
 	NVME_REG_AQA	= 0x0024,	/* Admin Queue Attributes */
 	NVME_REG_ASQ	= 0x0028,	/* Admin SQ Base Address */
 	NVME_REG_ACQ	= 0x0030,	/* Admin CQ Base Address */
-	NVME_REG_CMBLOC = 0x0038,	/* Controller Memory Buffer Location */
+	NVME_REG_CMBLOC	= 0x0038,	/* Controller Memory Buffer Location */
 	NVME_REG_CMBSZ	= 0x003c,	/* Controller Memory Buffer Size */
+	NVME_REG_BPINFO	= 0x0040,	/* Boot Partition Information */
+	NVME_REG_BPRSEL	= 0x0044,	/* Boot Partition Read Select */
+	NVME_REG_BPMBL	= 0x0048,	/* Boot Partition Memory Buffer
+					 * Location
+					 */
+	NVME_REG_PMRCAP	= 0x0e00,	/* Persistent Memory Capabilities */
+	NVME_REG_PMRCTL	= 0x0e04,	/* Persistent Memory Region Control */
+	NVME_REG_PMRSTS	= 0x0e08,	/* Persistent Memory Region Status */
+	NVME_REG_PMREBS	= 0x0e0c,	/* Persistent Memory Region Elasticity
+					 * Buffer Size
+					 */
+	NVME_REG_PMRSWTP = 0x0e10,	/* Persistent Memory Region Sustained
+					 * Write Throughput
+					 */
 	NVME_REG_DBS	= 0x1000,	/* SQ 0 Tail Doorbell */
 };
 
@@ -295,6 +309,14 @@ enum {
 	NVME_CTRL_OACS_DIRECTIVES		= 1 << 5,
 	NVME_CTRL_OACS_DBBUF_SUPP		= 1 << 8,
 	NVME_CTRL_LPA_CMD_EFFECTS_LOG		= 1 << 1,
+	NVME_CTRL_CTRATT_128_ID			= 1 << 0,
+	NVME_CTRL_CTRATT_NON_OP_PSP		= 1 << 1,
+	NVME_CTRL_CTRATT_NVM_SETS		= 1 << 2,
+	NVME_CTRL_CTRATT_READ_RECV_LVLS		= 1 << 3,
+	NVME_CTRL_CTRATT_ENDURANCE_GROUPS	= 1 << 4,
+	NVME_CTRL_CTRATT_PREDICTABLE_LAT	= 1 << 5,
+	NVME_CTRL_CTRATT_NAMESPACE_GRANULARITY	= 1 << 7,
+	NVME_CTRL_CTRATT_UUID_LIST		= 1 << 9,
 };
 
 struct nvme_lbaf {
@@ -352,6 +374,9 @@ enum {
 	NVME_ID_CNS_NS_PRESENT		= 0x11,
 	NVME_ID_CNS_CTRL_NS_LIST	= 0x12,
 	NVME_ID_CNS_CTRL_LIST		= 0x13,
+	NVME_ID_CNS_SCNDRY_CTRL_LIST	= 0x15,
+	NVME_ID_CNS_NS_GRANULARITY	= 0x16,
+	NVME_ID_CNS_UUID_LIST		= 0x17,
 };
 
 enum {
@@ -409,7 +434,8 @@ struct nvme_smart_log {
 	__u8			avail_spare;
 	__u8			spare_thresh;
 	__u8			percent_used;
-	__u8			rsvd6[26];
+	__u8			endu_grp_crit_warn_sumry;
+	__u8			rsvd7[25];
 	__u8			data_units_read[16];
 	__u8			data_units_written[16];
 	__u8			host_reads[16];
@@ -423,7 +449,11 @@ struct nvme_smart_log {
 	__le32			warning_temp_time;
 	__le32			critical_comp_time;
 	__le16			temp_sensor[8];
-	__u8			rsvd216[296];
+	__le32			thm_temp1_trans_count;
+	__le32			thm_temp2_trans_count;
+	__le32			thm_temp1_total_time;
+	__le32			thm_temp2_total_time;
+	__u8			rsvd232[280];
 };
 
 struct nvme_fw_slot_info_log {
@@ -440,6 +470,7 @@ enum {
 	NVME_CMD_EFFECTS_NIC		= 1 << 3,
 	NVME_CMD_EFFECTS_CCC		= 1 << 4,
 	NVME_CMD_EFFECTS_CSE_MASK	= 3 << 16,
+	NVME_CMD_EFFECTS_UUID_SEL	= 1 << 19,
 };
 
 struct nvme_effects_log {
@@ -563,6 +594,7 @@ enum nvme_opcode {
 	nvme_cmd_compare	= 0x05,
 	nvme_cmd_write_zeroes	= 0x08,
 	nvme_cmd_dsm		= 0x09,
+	nvme_cmd_verify		= 0x0c,
 	nvme_cmd_resv_register	= 0x0d,
 	nvme_cmd_resv_report	= 0x0e,
 	nvme_cmd_resv_acquire	= 0x11,
@@ -772,6 +804,12 @@ struct nvme_write_zeroes_cmd {
 
 /* Features */
 
+enum {
+	NVME_TEMP_THRESH_MASK		= 0xffff,
+	NVME_TEMP_THRESH_SELECT_SHIFT	= 16,
+	NVME_TEMP_THRESH_TYPE_UNDER	= 0x100000,
+};
+
 struct nvme_feat_auto_pst {
 	__le64 entries[32];
 };
@@ -806,10 +844,14 @@ enum nvme_admin_opcode {
 	nvme_admin_ns_mgmt		= 0x0d,
 	nvme_admin_activate_fw		= 0x10,
 	nvme_admin_download_fw		= 0x11,
+	nvme_admin_dev_self_test	= 0x14,
 	nvme_admin_ns_attach		= 0x15,
 	nvme_admin_keep_alive		= 0x18,
 	nvme_admin_directive_send	= 0x19,
 	nvme_admin_directive_recv	= 0x1a,
+	nvme_admin_virtual_mgmt		= 0x1c,
+	nvme_admin_nvme_mi_send		= 0x1d,
+	nvme_admin_nvme_mi_recv		= 0x1e,
 	nvme_admin_dbbuf		= 0x7C,
 	nvme_admin_format_nvm		= 0x80,
 	nvme_admin_security_send	= 0x81,
@@ -873,6 +915,7 @@ enum {
 	NVME_FEAT_PLM_CONFIG	= 0x13,
 	NVME_FEAT_PLM_WINDOW	= 0x14,
 	NVME_FEAT_HOST_BEHAVIOR	= 0x16,
+	NVME_FEAT_SANITIZE	= 0x17,
 	NVME_FEAT_SW_PROGRESS	= 0x80,
 	NVME_FEAT_HOST_ID	= 0x81,
 	NVME_FEAT_RESV_MASK	= 0x82,
@@ -883,6 +926,10 @@ enum {
 	NVME_LOG_FW_SLOT	= 0x03,
 	NVME_LOG_CHANGED_NS	= 0x04,
 	NVME_LOG_CMD_EFFECTS	= 0x05,
+	NVME_LOG_DEVICE_SELF_TEST = 0x06,
+	NVME_LOG_TELEMETRY_HOST = 0x07,
+	NVME_LOG_TELEMETRY_CTRL = 0x08,
+	NVME_LOG_ENDURANCE_GROUP = 0x09,
 	NVME_LOG_ANA		= 0x0c,
 	NVME_LOG_DISC		= 0x70,
 	NVME_LOG_RESERVATION	= 0x80,
@@ -1290,7 +1337,11 @@ enum {
 	NVME_SC_SGL_INVALID_OFFSET	= 0x16,
 	NVME_SC_SGL_INVALID_SUBTYPE	= 0x17,
 
+	NVME_SC_SANITIZE_FAILED		= 0x1C,
+	NVME_SC_SANITIZE_IN_PROGRESS	= 0x1D,
+
 	NVME_SC_NS_WRITE_PROTECTED	= 0x20,
+	NVME_SC_CMD_INTERRUPTED		= 0x21,
 
 	NVME_SC_LBA_RANGE		= 0x80,
 	NVME_SC_CAP_EXCEEDED		= 0x81,
@@ -1328,6 +1379,8 @@ enum {
 	NVME_SC_NS_NOT_ATTACHED		= 0x11a,
 	NVME_SC_THIN_PROV_NOT_SUPP	= 0x11b,
 	NVME_SC_CTRL_LIST_INVALID	= 0x11c,
+	NVME_SC_BP_WRITE_PROHIBITED	= 0x11e,
+	NVME_SC_PMR_SAN_PROHIBITED	= 0x123,
 
 	/*
 	 * I/O Command Set Specific - NVM commands:
@@ -1368,6 +1421,7 @@ enum {
 	NVME_SC_ANA_INACCESSIBLE	= 0x302,
 	NVME_SC_ANA_TRANSITION		= 0x303,
 	NVME_SC_HOST_PATH_ERROR		= 0x370,
+	NVME_SC_HOST_ABORTED_CMD	= 0x371,
 
 	NVME_SC_CRD			= 0x1800,
 	NVME_SC_DNR			= 0x4000,
diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h
index 8f8be5b00060..02dc4aa992b2 100644
--- a/include/linux/nvmem-consumer.h
+++ b/include/linux/nvmem-consumer.h
@@ -89,6 +89,9 @@ void nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries,
 int nvmem_register_notifier(struct notifier_block *nb);
 int nvmem_unregister_notifier(struct notifier_block *nb);
 
+struct nvmem_device *nvmem_device_find(void *data,
+			int (*match)(struct device *dev, const void *data));
+
 #else
 
 static inline struct nvmem_cell *nvmem_cell_get(struct device *dev,
@@ -204,6 +207,12 @@ static inline int nvmem_unregister_notifier(struct notifier_block *nb)
 	return -EOPNOTSUPP;
 }
 
+static inline struct nvmem_device *nvmem_device_find(void *data,
+			int (*match)(struct device *dev, const void *data))
+{
+	return NULL;
+}
+
 #endif /* CONFIG_NVMEM */
 
 #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index f9088c89a534..1a6cf19eac2d 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1686,6 +1686,7 @@ static inline struct pci_dev *pci_get_class(unsigned int class,
 static inline void pci_set_master(struct pci_dev *dev) { }
 static inline int pci_enable_device(struct pci_dev *dev) { return -EIO; }
 static inline void pci_disable_device(struct pci_dev *dev) { }
+static inline int pcim_enable_device(struct pci_dev *pdev) { return -EIO; }
 static inline int pci_assign_resource(struct pci_dev *dev, int i)
 { return -EBUSY; }
 static inline int __pci_register_driver(struct pci_driver *drv,
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 68ccc5b1913b..a07bfdb7d8ea 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1336,6 +1336,8 @@ extern void perf_event_disable_local(struct perf_event *event);
 extern void perf_event_disable_inatomic(struct perf_event *event);
 extern void perf_event_task_tick(void);
 extern int perf_event_account_interrupt(struct perf_event *event);
+extern int perf_event_period(struct perf_event *event, u64 value);
+extern u64 perf_event_pause(struct perf_event *event, bool reset);
 #else /* !CONFIG_PERF_EVENTS: */
 static inline void *
 perf_aux_output_begin(struct perf_output_handle *handle,
@@ -1415,6 +1417,14 @@ static inline void perf_event_disable(struct perf_event *event)		{ }
 static inline int __perf_event_disable(void *info)			{ return -1; }
 static inline void perf_event_task_tick(void)				{ }
 static inline int perf_event_release_kernel(struct perf_event *event)	{ return 0; }
+static inline int perf_event_period(struct perf_event *event, u64 value)
+{
+	return -EINVAL;
+}
+static inline u64 perf_event_pause(struct perf_event *event, bool reset)
+{
+	return 0;
+}
 #endif
 
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 9645b1194c98..998ae7d24450 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -85,6 +85,10 @@ static inline struct pid *get_pid(struct pid *pid)
 
 extern void put_pid(struct pid *pid);
 extern struct task_struct *pid_task(struct pid *pid, enum pid_type);
+static inline bool pid_has_task(struct pid *pid, enum pid_type type)
+{
+	return !hlist_empty(&pid->tasks[type]);
+}
 extern struct task_struct *get_pid_task(struct pid *pid, enum pid_type);
 
 extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type);
@@ -120,7 +124,8 @@ extern struct pid *find_vpid(int nr);
 extern struct pid *find_get_pid(int nr);
 extern struct pid *find_ge_pid(int nr, struct pid_namespace *);
 
-extern struct pid *alloc_pid(struct pid_namespace *ns);
+extern struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
+			     size_t set_tid_size);
 extern void free_pid(struct pid *pid);
 extern void disable_pid_allocation(struct pid_namespace *ns);
 
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index 49538b172483..2ed6af88794b 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -12,6 +12,8 @@
 #include <linux/ns_common.h>
 #include <linux/idr.h>
 
+/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */
+#define MAX_PID_NS_LEVEL 32
 
 struct fs_pin;
 
diff --git a/include/linux/platform_data/intel-spi.h b/include/linux/platform_data/intel-spi.h
index ebb4f332588b..7f53a5c6f35e 100644
--- a/include/linux/platform_data/intel-spi.h
+++ b/include/linux/platform_data/intel-spi.h
@@ -13,6 +13,7 @@ enum intel_spi_type {
 	INTEL_SPI_BYT = 1,
 	INTEL_SPI_LPT,
 	INTEL_SPI_BXT,
+	INTEL_SPI_CNL,
 };
 
 /**
diff --git a/include/linux/psci.h b/include/linux/psci.h
index e2bacc6fd2f2..ebe0a881d13d 100644
--- a/include/linux/psci.h
+++ b/include/linux/psci.h
@@ -7,6 +7,7 @@
 #ifndef __LINUX_PSCI_H
 #define __LINUX_PSCI_H
 
+#include <linux/arm-smccc.h>
 #include <linux/init.h>
 #include <linux/types.h>
 
@@ -18,12 +19,6 @@ bool psci_tos_resident_on(int cpu);
 int psci_cpu_suspend_enter(u32 state);
 bool psci_power_state_is_valid(u32 state);
 
-enum psci_conduit {
-	PSCI_CONDUIT_NONE,
-	PSCI_CONDUIT_SMC,
-	PSCI_CONDUIT_HVC,
-};
-
 enum smccc_version {
 	SMCCC_VERSION_1_0,
 	SMCCC_VERSION_1_1,
@@ -38,7 +33,7 @@ struct psci_operations {
 	int (*affinity_info)(unsigned long target_affinity,
 			unsigned long lowest_affinity_level);
 	int (*migrate_info_type)(void);
-	enum psci_conduit conduit;
+	enum arm_smccc_conduit conduit;
 	enum smccc_version smccc_version;
 };
 
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index a986ac12a848..e40d019c3d9d 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -216,15 +216,6 @@ int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint,
  */
 bool sbitmap_any_bit_set(const struct sbitmap *sb);
 
-/**
- * sbitmap_any_bit_clear() - Check for an unset bit in a &struct
- * sbitmap.
- * @sb: Bitmap to check.
- *
- * Return: true if any bit in the bitmap is clear, false otherwise.
- */
-bool sbitmap_any_bit_clear(const struct sbitmap *sb);
-
 #define SB_NR_TO_INDEX(sb, bitnr) ((bitnr) >> (sb)->shift)
 #define SB_NR_TO_BIT(sb, bitnr) ((bitnr) & ((1U << (sb)->shift) - 1U))
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 67a1d86981a9..6666e25606b7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1468,6 +1468,7 @@ extern struct pid *cad_pid;
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
 #define PF_MEMALLOC_NOCMA	0x10000000	/* All allocation request will have _GFP_MOVABLE cleared */
+#define PF_IO_WORKER		0x20000000	/* Task is an IO worker */
 #define PF_FREEZER_SKIP		0x40000000	/* Freezer should not count it as freezable */
 #define PF_SUSPEND_TASK		0x80000000      /* This thread called freeze_processes() and should not be frozen */
 
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 4b1c3b664f51..f1879884238e 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -26,6 +26,9 @@ struct kernel_clone_args {
 	unsigned long stack;
 	unsigned long stack_size;
 	unsigned long tls;
+	pid_t *set_tid;
+	/* Number of elements in *set_tid */
+	size_t set_tid_size;
 };
 
 /*
diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h
index 53c28d750a45..1ac0d712a9c3 100644
--- a/include/linux/sed-opal.h
+++ b/include/linux/sed-opal.h
@@ -42,6 +42,7 @@ static inline bool is_sed_ioctl(unsigned int cmd)
 	case IOC_OPAL_PSID_REVERT_TPR:
 	case IOC_OPAL_MBR_DONE:
 	case IOC_OPAL_WRITE_SHADOW_MBR:
+	case IOC_OPAL_GENERIC_TABLE_RW:
 		return true;
 	}
 	return false;
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 4049d9755cf1..09c32a21555b 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -392,6 +392,9 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
 extern int __sys_sendto(int fd, void __user *buff, size_t len,
 			unsigned int flags, struct sockaddr __user *addr,
 			int addr_len);
+extern int __sys_accept4_file(struct file *file, unsigned file_flags,
+			struct sockaddr __user *upeer_sockaddr,
+			 int __user *upeer_addrlen, int flags);
 extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 			 int __user *upeer_addrlen, int flags);
 extern int __sys_socket(int family, int type, int protocol);
diff --git a/include/linux/stat.h b/include/linux/stat.h
index 765573dc17d6..528c4baad091 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -33,7 +33,8 @@ struct kstat {
 	 STATX_ATTR_IMMUTABLE |				\
 	 STATX_ATTR_APPEND |				\
 	 STATX_ATTR_NODUMP |				\
-	 STATX_ATTR_ENCRYPTED				\
+	 STATX_ATTR_ENCRYPTED |				\
+	 STATX_ATTR_VERITY				\
 	 )/* Attrs corresponding to FS_*_FL flags */
 	u64		ino;
 	dev_t		dev;
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index 53c0ea9ec9df..0d6e949ba315 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -21,6 +21,7 @@
 #include <linux/acpi.h>
 #include <linux/cdev.h>
 #include <linux/fs.h>
+#include <linux/highmem.h>
 #include <crypto/hash_info.h>
 
 #define TPM_DIGEST_SIZE 20	/* Max TPM v1.2 PCR size */
@@ -67,6 +68,8 @@ struct tpm_class_ops {
 	u8 (*status) (struct tpm_chip *chip);
 	void (*update_timeouts)(struct tpm_chip *chip,
 				unsigned long *timeout_cap);
+	void (*update_durations)(struct tpm_chip *chip,
+				 unsigned long *duration_cap);
 	int (*go_idle)(struct tpm_chip *chip);
 	int (*cmd_ready)(struct tpm_chip *chip);
 	int (*request_locality)(struct tpm_chip *chip, int loc);
@@ -161,6 +164,235 @@ struct tpm_chip {
 	int locality;
 };
 
+#define TPM_HEADER_SIZE		10
+
+enum tpm2_const {
+	TPM2_PLATFORM_PCR       =     24,
+	TPM2_PCR_SELECT_MIN     = ((TPM2_PLATFORM_PCR + 7) / 8),
+};
+
+enum tpm2_timeouts {
+	TPM2_TIMEOUT_A          =    750,
+	TPM2_TIMEOUT_B          =   2000,
+	TPM2_TIMEOUT_C          =    200,
+	TPM2_TIMEOUT_D          =     30,
+	TPM2_DURATION_SHORT     =     20,
+	TPM2_DURATION_MEDIUM    =    750,
+	TPM2_DURATION_LONG      =   2000,
+	TPM2_DURATION_LONG_LONG = 300000,
+	TPM2_DURATION_DEFAULT   = 120000,
+};
+
+enum tpm2_structures {
+	TPM2_ST_NO_SESSIONS	= 0x8001,
+	TPM2_ST_SESSIONS	= 0x8002,
+};
+
+/* Indicates from what layer of the software stack the error comes from */
+#define TSS2_RC_LAYER_SHIFT	 16
+#define TSS2_RESMGR_TPM_RC_LAYER (11 << TSS2_RC_LAYER_SHIFT)
+
+enum tpm2_return_codes {
+	TPM2_RC_SUCCESS		= 0x0000,
+	TPM2_RC_HASH		= 0x0083, /* RC_FMT1 */
+	TPM2_RC_HANDLE		= 0x008B,
+	TPM2_RC_INITIALIZE	= 0x0100, /* RC_VER1 */
+	TPM2_RC_FAILURE		= 0x0101,
+	TPM2_RC_DISABLED	= 0x0120,
+	TPM2_RC_COMMAND_CODE    = 0x0143,
+	TPM2_RC_TESTING		= 0x090A, /* RC_WARN */
+	TPM2_RC_REFERENCE_H0	= 0x0910,
+	TPM2_RC_RETRY		= 0x0922,
+};
+
+enum tpm2_command_codes {
+	TPM2_CC_FIRST		        = 0x011F,
+	TPM2_CC_HIERARCHY_CONTROL       = 0x0121,
+	TPM2_CC_HIERARCHY_CHANGE_AUTH   = 0x0129,
+	TPM2_CC_CREATE_PRIMARY          = 0x0131,
+	TPM2_CC_SEQUENCE_COMPLETE       = 0x013E,
+	TPM2_CC_SELF_TEST	        = 0x0143,
+	TPM2_CC_STARTUP		        = 0x0144,
+	TPM2_CC_SHUTDOWN	        = 0x0145,
+	TPM2_CC_NV_READ                 = 0x014E,
+	TPM2_CC_CREATE		        = 0x0153,
+	TPM2_CC_LOAD		        = 0x0157,
+	TPM2_CC_SEQUENCE_UPDATE         = 0x015C,
+	TPM2_CC_UNSEAL		        = 0x015E,
+	TPM2_CC_CONTEXT_LOAD	        = 0x0161,
+	TPM2_CC_CONTEXT_SAVE	        = 0x0162,
+	TPM2_CC_FLUSH_CONTEXT	        = 0x0165,
+	TPM2_CC_VERIFY_SIGNATURE        = 0x0177,
+	TPM2_CC_GET_CAPABILITY	        = 0x017A,
+	TPM2_CC_GET_RANDOM	        = 0x017B,
+	TPM2_CC_PCR_READ	        = 0x017E,
+	TPM2_CC_PCR_EXTEND	        = 0x0182,
+	TPM2_CC_EVENT_SEQUENCE_COMPLETE = 0x0185,
+	TPM2_CC_HASH_SEQUENCE_START     = 0x0186,
+	TPM2_CC_CREATE_LOADED           = 0x0191,
+	TPM2_CC_LAST		        = 0x0193, /* Spec 1.36 */
+};
+
+enum tpm2_permanent_handles {
+	TPM2_RS_PW		= 0x40000009,
+};
+
+enum tpm2_capabilities {
+	TPM2_CAP_HANDLES	= 1,
+	TPM2_CAP_COMMANDS	= 2,
+	TPM2_CAP_PCRS		= 5,
+	TPM2_CAP_TPM_PROPERTIES = 6,
+};
+
+enum tpm2_properties {
+	TPM_PT_TOTAL_COMMANDS	= 0x0129,
+};
+
+enum tpm2_startup_types {
+	TPM2_SU_CLEAR	= 0x0000,
+	TPM2_SU_STATE	= 0x0001,
+};
+
+enum tpm2_cc_attrs {
+	TPM2_CC_ATTR_CHANDLES	= 25,
+	TPM2_CC_ATTR_RHANDLE	= 28,
+};
+
+#define TPM_VID_INTEL    0x8086
+#define TPM_VID_WINBOND  0x1050
+#define TPM_VID_STM      0x104A
+
+enum tpm_chip_flags {
+	TPM_CHIP_FLAG_TPM2		= BIT(1),
+	TPM_CHIP_FLAG_IRQ		= BIT(2),
+	TPM_CHIP_FLAG_VIRTUAL		= BIT(3),
+	TPM_CHIP_FLAG_HAVE_TIMEOUTS	= BIT(4),
+	TPM_CHIP_FLAG_ALWAYS_POWERED	= BIT(5),
+	TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED	= BIT(6),
+};
+
+#define to_tpm_chip(d) container_of(d, struct tpm_chip, dev)
+
+struct tpm_header {
+	__be16 tag;
+	__be32 length;
+	union {
+		__be32 ordinal;
+		__be32 return_code;
+	};
+} __packed;
+
+/* A string buffer type for constructing TPM commands. This is based on the
+ * ideas of string buffer code in security/keys/trusted.h but is heap based
+ * in order to keep the stack usage minimal.
+ */
+
+enum tpm_buf_flags {
+	TPM_BUF_OVERFLOW	= BIT(0),
+};
+
+struct tpm_buf {
+	unsigned int flags;
+	u8 *data;
+};
+
+enum tpm2_object_attributes {
+	TPM2_OA_USER_WITH_AUTH		= BIT(6),
+};
+
+enum tpm2_session_attributes {
+	TPM2_SA_CONTINUE_SESSION	= BIT(0),
+};
+
+struct tpm2_hash {
+	unsigned int crypto_id;
+	unsigned int tpm_id;
+};
+
+static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal)
+{
+	struct tpm_header *head = (struct tpm_header *)buf->data;
+
+	head->tag = cpu_to_be16(tag);
+	head->length = cpu_to_be32(sizeof(*head));
+	head->ordinal = cpu_to_be32(ordinal);
+}
+
+static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal)
+{
+	buf->data = (u8 *)__get_free_page(GFP_KERNEL);
+	if (!buf->data)
+		return -ENOMEM;
+
+	buf->flags = 0;
+	tpm_buf_reset(buf, tag, ordinal);
+	return 0;
+}
+
+static inline void tpm_buf_destroy(struct tpm_buf *buf)
+{
+	free_page((unsigned long)buf->data);
+}
+
+static inline u32 tpm_buf_length(struct tpm_buf *buf)
+{
+	struct tpm_header *head = (struct tpm_header *)buf->data;
+
+	return be32_to_cpu(head->length);
+}
+
+static inline u16 tpm_buf_tag(struct tpm_buf *buf)
+{
+	struct tpm_header *head = (struct tpm_header *)buf->data;
+
+	return be16_to_cpu(head->tag);
+}
+
+static inline void tpm_buf_append(struct tpm_buf *buf,
+				  const unsigned char *new_data,
+				  unsigned int new_len)
+{
+	struct tpm_header *head = (struct tpm_header *)buf->data;
+	u32 len = tpm_buf_length(buf);
+
+	/* Return silently if overflow has already happened. */
+	if (buf->flags & TPM_BUF_OVERFLOW)
+		return;
+
+	if ((len + new_len) > PAGE_SIZE) {
+		WARN(1, "tpm_buf: overflow\n");
+		buf->flags |= TPM_BUF_OVERFLOW;
+		return;
+	}
+
+	memcpy(&buf->data[len], new_data, new_len);
+	head->length = cpu_to_be32(len + new_len);
+}
+
+static inline void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value)
+{
+	tpm_buf_append(buf, &value, 1);
+}
+
+static inline void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value)
+{
+	__be16 value2 = cpu_to_be16(value);
+
+	tpm_buf_append(buf, (u8 *) &value2, 2);
+}
+
+static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value)
+{
+	__be32 value2 = cpu_to_be32(value);
+
+	tpm_buf_append(buf, (u8 *) &value2, 4);
+}
+
+static inline u32 tpm2_rc_value(u32 rc)
+{
+	return (rc & BIT(7)) ? rc & 0xff : rc;
+}
+
 #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE)
 
 extern int tpm_is_tpm2(struct tpm_chip *chip);
@@ -170,12 +402,6 @@ extern int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx,
 			  struct tpm_digest *digests);
 extern int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen);
 extern int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max);
-extern int tpm_seal_trusted(struct tpm_chip *chip,
-			    struct trusted_key_payload *payload,
-			    struct trusted_key_options *options);
-extern int tpm_unseal_trusted(struct tpm_chip *chip,
-			      struct trusted_key_payload *payload,
-			      struct trusted_key_options *options);
 extern struct tpm_chip *tpm_default_chip(void);
 #else
 static inline int tpm_is_tpm2(struct tpm_chip *chip)
@@ -204,18 +430,6 @@ static inline int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max)
 	return -ENODEV;
 }
 
-static inline int tpm_seal_trusted(struct tpm_chip *chip,
-				   struct trusted_key_payload *payload,
-				   struct trusted_key_options *options)
-{
-	return -ENODEV;
-}
-static inline int tpm_unseal_trusted(struct tpm_chip *chip,
-				     struct trusted_key_payload *payload,
-				     struct trusted_key_options *options)
-{
-	return -ENODEV;
-}
 static inline struct tpm_chip *tpm_default_chip(void)
 {
 	return NULL;
diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h
index cfc9441ef074..dec7522b6ce1 100644
--- a/include/net/netprio_cgroup.h
+++ b/include/net/netprio_cgroup.h
@@ -26,7 +26,7 @@ static inline u32 task_netprioidx(struct task_struct *p)
 
 	rcu_read_lock();
 	css = task_css(p, net_prio_cgrp_id);
-	idx = css->cgroup->id;
+	idx = css->id;
 	rcu_read_unlock();
 	return idx;
 }
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 75ae1899452b..620bf1b38fba 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -19,7 +19,7 @@ struct btrfs_delayed_ref_node;
 struct btrfs_delayed_tree_ref;
 struct btrfs_delayed_data_ref;
 struct btrfs_delayed_ref_head;
-struct btrfs_block_group_cache;
+struct btrfs_block_group;
 struct btrfs_free_cluster;
 struct map_lookup;
 struct extent_buffer;
@@ -170,7 +170,7 @@ DECLARE_EVENT_CLASS(btrfs__inode,
 
 	TP_STRUCT__entry_btrfs(
 		__field(	u64,  ino			)
-		__field(	blkcnt_t,  blocks		)
+		__field(	u64,  blocks			)
 		__field(	u64,  disk_i_size		)
 		__field(	u64,  generation		)
 		__field(	u64,  last_trans		)
@@ -194,7 +194,7 @@ DECLARE_EVENT_CLASS(btrfs__inode,
 		  show_root_type(__entry->root_objectid),
 		  __entry->generation,
 		  __entry->ino,
-		  (unsigned long long)__entry->blocks,
+		  __entry->blocks,
 		  __entry->disk_i_size,
 		  __entry->last_trans,
 		  __entry->logged_trans)
@@ -292,7 +292,7 @@ TRACE_EVENT_CONDITION(btrfs_get_extent,
 
 TRACE_EVENT(btrfs_handle_em_exist,
 
-	TP_PROTO(struct btrfs_fs_info *fs_info,
+	TP_PROTO(const struct btrfs_fs_info *fs_info,
 		const struct extent_map *existing, const struct extent_map *map,
 		u64 start, u64 len),
 
@@ -330,8 +330,8 @@ TRACE_EVENT(btrfs_handle_em_exist,
 /* file extent item */
 DECLARE_EVENT_CLASS(btrfs__file_extent_item_regular,
 
-	TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l,
-		 struct btrfs_file_extent_item *fi, u64 start),
+	TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l,
+		 const struct btrfs_file_extent_item *fi, u64 start),
 
 	TP_ARGS(bi, l, fi, start),
 
@@ -385,8 +385,8 @@ DECLARE_EVENT_CLASS(btrfs__file_extent_item_regular,
 DECLARE_EVENT_CLASS(
 	btrfs__file_extent_item_inline,
 
-	TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l,
-		 struct btrfs_file_extent_item *fi, int slot, u64 start),
+	TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l,
+		 const struct btrfs_file_extent_item *fi, int slot, u64 start),
 
 	TP_ARGS(bi, l, fi, slot,  start),
 
@@ -426,8 +426,8 @@ DECLARE_EVENT_CLASS(
 DEFINE_EVENT(
 	btrfs__file_extent_item_regular, btrfs_get_extent_show_fi_regular,
 
-	TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l,
-		 struct btrfs_file_extent_item *fi, u64 start),
+	TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l,
+		 const struct btrfs_file_extent_item *fi, u64 start),
 
 	TP_ARGS(bi, l, fi, start)
 );
@@ -435,8 +435,8 @@ DEFINE_EVENT(
 DEFINE_EVENT(
 	btrfs__file_extent_item_regular, btrfs_truncate_show_fi_regular,
 
-	TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l,
-		 struct btrfs_file_extent_item *fi, u64 start),
+	TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l,
+		 const struct btrfs_file_extent_item *fi, u64 start),
 
 	TP_ARGS(bi, l, fi, start)
 );
@@ -444,8 +444,8 @@ DEFINE_EVENT(
 DEFINE_EVENT(
 	btrfs__file_extent_item_inline, btrfs_get_extent_show_fi_inline,
 
-	TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l,
-		 struct btrfs_file_extent_item *fi, int slot, u64 start),
+	TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l,
+		 const struct btrfs_file_extent_item *fi, int slot, u64 start),
 
 	TP_ARGS(bi, l, fi, slot, start)
 );
@@ -453,8 +453,8 @@ DEFINE_EVENT(
 DEFINE_EVENT(
 	btrfs__file_extent_item_inline, btrfs_truncate_show_fi_inline,
 
-	TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l,
-		 struct btrfs_file_extent_item *fi, int slot, u64 start),
+	TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l,
+		 const struct btrfs_file_extent_item *fi, int slot, u64 start),
 
 	TP_ARGS(bi, l, fi, slot, start)
 );
@@ -574,7 +574,7 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
 		__field(	char,   for_kupdate		)
 		__field(	char,   for_reclaim		)
 		__field(	char,   range_cyclic		)
-		__field(	pgoff_t,  writeback_index	)
+		__field(	unsigned long,  writeback_index	)
 		__field(	u64,    root_objectid		)
 	),
 
@@ -603,7 +603,7 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
 		  __entry->range_start, __entry->range_end,
 		  __entry->for_kupdate,
 		  __entry->for_reclaim, __entry->range_cyclic,
-		  (unsigned long)__entry->writeback_index)
+		  __entry->writeback_index)
 );
 
 DEFINE_EVENT(btrfs__writepage, __extent_writepage,
@@ -622,7 +622,7 @@ TRACE_EVENT(btrfs_writepage_end_io_hook,
 
 	TP_STRUCT__entry_btrfs(
 		__field(	u64,	 ino		)
-		__field(	pgoff_t, index		)
+		__field(	unsigned long, index	)
 		__field(	u64,	 start		)
 		__field(	u64,	 end		)
 		__field(	int,	 uptodate	)
@@ -642,7 +642,7 @@ TRACE_EVENT(btrfs_writepage_end_io_hook,
 	TP_printk_btrfs("root=%llu(%s) ino=%llu page_index=%lu start=%llu "
 		  "end=%llu uptodate=%d",
 		  show_root_type(__entry->root_objectid),
-		  __entry->ino, (unsigned long)__entry->index,
+		  __entry->ino, __entry->index,
 		  __entry->start,
 		  __entry->end, __entry->uptodate)
 );
@@ -699,7 +699,7 @@ TRACE_EVENT(btrfs_sync_fs,
 TRACE_EVENT(btrfs_add_block_group,
 
 	TP_PROTO(const struct btrfs_fs_info *fs_info,
-		 const struct btrfs_block_group_cache *block_group, int create),
+		 const struct btrfs_block_group *block_group, int create),
 
 	TP_ARGS(fs_info, block_group, create),
 
@@ -713,11 +713,10 @@ TRACE_EVENT(btrfs_add_block_group,
 	),
 
 	TP_fast_assign_btrfs(fs_info,
-		__entry->offset		= block_group->key.objectid;
-		__entry->size		= block_group->key.offset;
+		__entry->offset		= block_group->start;
+		__entry->size		= block_group->length;
 		__entry->flags		= block_group->flags;
-		__entry->bytes_used	=
-			btrfs_block_group_used(&block_group->item);
+		__entry->bytes_used	= block_group->used;
 		__entry->bytes_super	= block_group->bytes_super;
 		__entry->create		= create;
 	),
@@ -1018,7 +1017,7 @@ TRACE_EVENT(btrfs_cow_block,
 
 TRACE_EVENT(btrfs_space_reservation,
 
-	TP_PROTO(const struct btrfs_fs_info *fs_info, char *type, u64 val,
+	TP_PROTO(const struct btrfs_fs_info *fs_info, const char *type, u64 val,
 		 u64 bytes, int reserve),
 
 	TP_ARGS(fs_info, type, val, bytes, reserve),
@@ -1051,7 +1050,7 @@ TRACE_EVENT(btrfs_space_reservation,
 TRACE_EVENT(btrfs_trigger_flush,
 
 	TP_PROTO(const struct btrfs_fs_info *fs_info, u64 flags, u64 bytes,
-		 int flush, char *reason),
+		 int flush, const char *reason),
 
 	TP_ARGS(fs_info, flags, bytes, flush, reason),
 
@@ -1185,7 +1184,7 @@ TRACE_EVENT(find_free_extent,
 
 DECLARE_EVENT_CLASS(btrfs__reserve_extent,
 
-	TP_PROTO(const struct btrfs_block_group_cache *block_group, u64 start,
+	TP_PROTO(const struct btrfs_block_group *block_group, u64 start,
 		 u64 len),
 
 	TP_ARGS(block_group, start, len),
@@ -1198,7 +1197,7 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent,
 	),
 
 	TP_fast_assign_btrfs(block_group->fs_info,
-		__entry->bg_objectid	= block_group->key.objectid;
+		__entry->bg_objectid	= block_group->start;
 		__entry->flags		= block_group->flags;
 		__entry->start		= start;
 		__entry->len		= len;
@@ -1215,7 +1214,7 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent,
 
 DEFINE_EVENT(btrfs__reserve_extent, btrfs_reserve_extent,
 
-	TP_PROTO(const struct btrfs_block_group_cache *block_group, u64 start,
+	TP_PROTO(const struct btrfs_block_group *block_group, u64 start,
 		 u64 len),
 
 	TP_ARGS(block_group, start, len)
@@ -1223,7 +1222,7 @@ DEFINE_EVENT(btrfs__reserve_extent, btrfs_reserve_extent,
 
 DEFINE_EVENT(btrfs__reserve_extent, btrfs_reserve_extent_cluster,
 
-	TP_PROTO(const struct btrfs_block_group_cache *block_group, u64 start,
+	TP_PROTO(const struct btrfs_block_group *block_group, u64 start,
 		 u64 len),
 
 	TP_ARGS(block_group, start, len)
@@ -1231,7 +1230,7 @@ DEFINE_EVENT(btrfs__reserve_extent, btrfs_reserve_extent_cluster,
 
 TRACE_EVENT(btrfs_find_cluster,
 
-	TP_PROTO(const struct btrfs_block_group_cache *block_group, u64 start,
+	TP_PROTO(const struct btrfs_block_group *block_group, u64 start,
 		 u64 bytes, u64 empty_size, u64 min_bytes),
 
 	TP_ARGS(block_group, start, bytes, empty_size, min_bytes),
@@ -1246,7 +1245,7 @@ TRACE_EVENT(btrfs_find_cluster,
 	),
 
 	TP_fast_assign_btrfs(block_group->fs_info,
-		__entry->bg_objectid	= block_group->key.objectid;
+		__entry->bg_objectid	= block_group->start;
 		__entry->flags		= block_group->flags;
 		__entry->start		= start;
 		__entry->bytes		= bytes;
@@ -1264,7 +1263,7 @@ TRACE_EVENT(btrfs_find_cluster,
 
 TRACE_EVENT(btrfs_failed_cluster_setup,
 
-	TP_PROTO(const struct btrfs_block_group_cache *block_group),
+	TP_PROTO(const struct btrfs_block_group *block_group),
 
 	TP_ARGS(block_group),
 
@@ -1273,7 +1272,7 @@ TRACE_EVENT(btrfs_failed_cluster_setup,
 	),
 
 	TP_fast_assign_btrfs(block_group->fs_info,
-		__entry->bg_objectid	= block_group->key.objectid;
+		__entry->bg_objectid	= block_group->start;
 	),
 
 	TP_printk_btrfs("block_group=%llu", __entry->bg_objectid)
@@ -1281,7 +1280,7 @@ TRACE_EVENT(btrfs_failed_cluster_setup,
 
 TRACE_EVENT(btrfs_setup_cluster,
 
-	TP_PROTO(const struct btrfs_block_group_cache *block_group,
+	TP_PROTO(const struct btrfs_block_group *block_group,
 		 const struct btrfs_free_cluster *cluster,
 		 u64 size, int bitmap),
 
@@ -1297,7 +1296,7 @@ TRACE_EVENT(btrfs_setup_cluster,
 	),
 
 	TP_fast_assign_btrfs(block_group->fs_info,
-		__entry->bg_objectid	= block_group->key.objectid;
+		__entry->bg_objectid	= block_group->start;
 		__entry->flags		= block_group->flags;
 		__entry->start		= cluster->window_start;
 		__entry->max_size	= cluster->max_size;
@@ -1325,17 +1324,17 @@ TRACE_EVENT(alloc_extent_state,
 	TP_STRUCT__entry(
 		__field(const struct extent_state *, state)
 		__field(gfp_t, mask)
-		__field(unsigned long, ip)
+		__field(const void*, ip)
 	),
 
 	TP_fast_assign(
 		__entry->state	= state,
 		__entry->mask	= mask,
-		__entry->ip	= IP
+		__entry->ip	= (const void *)IP
 	),
 
 	TP_printk("state=%p mask=%s caller=%pS", __entry->state,
-		  show_gfp_flags(__entry->mask), (const void *)__entry->ip)
+		  show_gfp_flags(__entry->mask), __entry->ip)
 );
 
 TRACE_EVENT(free_extent_state,
@@ -1346,16 +1345,15 @@ TRACE_EVENT(free_extent_state,
 
 	TP_STRUCT__entry(
 		__field(const struct extent_state *, state)
-		__field(unsigned long, ip)
+		__field(const void*, ip)
 	),
 
 	TP_fast_assign(
 		__entry->state	= state,
-		__entry->ip = IP
+		__entry->ip = (const void *)IP
 	),
 
-	TP_printk("state=%p caller=%pS", __entry->state,
-		  (const void *)__entry->ip)
+	TP_printk("state=%p caller=%pS", __entry->state, __entry->ip)
 );
 
 DECLARE_EVENT_CLASS(btrfs__work,
@@ -1389,9 +1387,9 @@ DECLARE_EVENT_CLASS(btrfs__work,
 );
 
 /*
- * For situiations when the work is freed, we pass fs_info and a tag that that
- * matches address of the work structure so it can be paired with the
- * scheduling event.
+ * For situations when the work is freed, we pass fs_info and a tag that matches
+ * the address of the work structure so it can be paired with the scheduling
+ * event. DO NOT add anything here that dereferences wtag.
  */
 DECLARE_EVENT_CLASS(btrfs__work__done,
 
@@ -1567,8 +1565,7 @@ DECLARE_EVENT_CLASS(btrfs_qgroup_extent,
 	),
 
 	TP_printk_btrfs("bytenr=%llu num_bytes=%llu",
-		  (unsigned long long)__entry->bytenr,
-		  (unsigned long long)__entry->num_bytes)
+		  __entry->bytenr, __entry->num_bytes)
 );
 
 DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_account_extents,
@@ -1644,7 +1641,7 @@ TRACE_EVENT(btrfs_qgroup_account_extent,
 TRACE_EVENT(qgroup_update_counters,
 
 	TP_PROTO(const struct btrfs_fs_info *fs_info,
-		 struct btrfs_qgroup *qgroup,
+		 const struct btrfs_qgroup *qgroup,
 		 u64 cur_old_count, u64 cur_new_count),
 
 	TP_ARGS(fs_info, qgroup, cur_old_count, cur_new_count),
@@ -1825,7 +1822,7 @@ DEFINE_EVENT(btrfs__prelim_ref, btrfs_prelim_ref_insert,
 );
 
 TRACE_EVENT(btrfs_inode_mod_outstanding_extents,
-	TP_PROTO(struct btrfs_root *root, u64 ino, int mod),
+	TP_PROTO(const struct btrfs_root *root, u64 ino, int mod),
 
 	TP_ARGS(root, ino, mod),
 
@@ -1847,7 +1844,7 @@ TRACE_EVENT(btrfs_inode_mod_outstanding_extents,
 );
 
 DECLARE_EVENT_CLASS(btrfs__block_group,
-	TP_PROTO(const struct btrfs_block_group_cache *bg_cache),
+	TP_PROTO(const struct btrfs_block_group *bg_cache),
 
 	TP_ARGS(bg_cache),
 
@@ -1859,9 +1856,9 @@ DECLARE_EVENT_CLASS(btrfs__block_group,
 	),
 
 	TP_fast_assign_btrfs(bg_cache->fs_info,
-		__entry->bytenr = bg_cache->key.objectid,
-		__entry->len	= bg_cache->key.offset,
-		__entry->used	= btrfs_block_group_used(&bg_cache->item);
+		__entry->bytenr = bg_cache->start,
+		__entry->len	= bg_cache->length,
+		__entry->used	= bg_cache->used;
 		__entry->flags	= bg_cache->flags;
 	),
 
@@ -1871,19 +1868,19 @@ DECLARE_EVENT_CLASS(btrfs__block_group,
 );
 
 DEFINE_EVENT(btrfs__block_group, btrfs_remove_block_group,
-	TP_PROTO(const struct btrfs_block_group_cache *bg_cache),
+	TP_PROTO(const struct btrfs_block_group *bg_cache),
 
 	TP_ARGS(bg_cache)
 );
 
 DEFINE_EVENT(btrfs__block_group, btrfs_add_unused_block_group,
-	TP_PROTO(const struct btrfs_block_group_cache *bg_cache),
+	TP_PROTO(const struct btrfs_block_group *bg_cache),
 
 	TP_ARGS(bg_cache)
 );
 
 DEFINE_EVENT(btrfs__block_group, btrfs_skip_unused_block_group,
-	TP_PROTO(const struct btrfs_block_group_cache *bg_cache),
+	TP_PROTO(const struct btrfs_block_group *bg_cache),
 
 	TP_ARGS(bg_cache)
 );
@@ -1906,7 +1903,7 @@ TRACE_EVENT(btrfs_set_extent_bit,
 	TP_fast_assign_btrfs(tree->fs_info,
 		__entry->owner = tree->owner;
 		if (tree->private_data) {
-			struct inode *inode = tree->private_data;
+			const struct inode *inode = tree->private_data;
 
 			__entry->ino	= btrfs_ino(BTRFS_I(inode));
 			__entry->rootid	=
@@ -1945,7 +1942,7 @@ TRACE_EVENT(btrfs_clear_extent_bit,
 	TP_fast_assign_btrfs(tree->fs_info,
 		__entry->owner = tree->owner;
 		if (tree->private_data) {
-			struct inode *inode = tree->private_data;
+			const struct inode *inode = tree->private_data;
 
 			__entry->ino	= btrfs_ino(BTRFS_I(inode));
 			__entry->rootid	=
@@ -1985,7 +1982,7 @@ TRACE_EVENT(btrfs_convert_extent_bit,
 	TP_fast_assign_btrfs(tree->fs_info,
 		__entry->owner = tree->owner;
 		if (tree->private_data) {
-			struct inode *inode = tree->private_data;
+			const struct inode *inode = tree->private_data;
 
 			__entry->ino	= btrfs_ino(BTRFS_I(inode));
 			__entry->rootid	=
@@ -2094,8 +2091,8 @@ DEFINE_BTRFS_LOCK_EVENT(btrfs_tree_read_lock_atomic);
 
 DECLARE_EVENT_CLASS(btrfs__space_info_update,
 
-	TP_PROTO(struct btrfs_fs_info *fs_info,
-		 struct btrfs_space_info *sinfo, u64 old, s64 diff),
+	TP_PROTO(const struct btrfs_fs_info *fs_info,
+		 const struct btrfs_space_info *sinfo, u64 old, s64 diff),
 
 	TP_ARGS(fs_info, sinfo, old, diff),
 
@@ -2117,16 +2114,16 @@ DECLARE_EVENT_CLASS(btrfs__space_info_update,
 
 DEFINE_EVENT(btrfs__space_info_update, update_bytes_may_use,
 
-	TP_PROTO(struct btrfs_fs_info *fs_info,
-		 struct btrfs_space_info *sinfo, u64 old, s64 diff),
+	TP_PROTO(const struct btrfs_fs_info *fs_info,
+		 const struct btrfs_space_info *sinfo, u64 old, s64 diff),
 
 	TP_ARGS(fs_info, sinfo, old, diff)
 );
 
 DEFINE_EVENT(btrfs__space_info_update, update_bytes_pinned,
 
-	TP_PROTO(struct btrfs_fs_info *fs_info,
-		 struct btrfs_space_info *sinfo, u64 old, s64 diff),
+	TP_PROTO(const struct btrfs_fs_info *fs_info,
+		 const struct btrfs_space_info *sinfo, u64 old, s64 diff),
 
 	TP_ARGS(fs_info, sinfo, old, diff)
 );
diff --git a/include/trace/events/cgroup.h b/include/trace/events/cgroup.h
index a566cc521476..7f42a3de59e6 100644
--- a/include/trace/events/cgroup.h
+++ b/include/trace/events/cgroup.h
@@ -66,7 +66,7 @@ DECLARE_EVENT_CLASS(cgroup,
 
 	TP_fast_assign(
 		__entry->root = cgrp->root->hierarchy_id;
-		__entry->id = cgrp->id;
+		__entry->id = cgroup_id(cgrp);
 		__entry->level = cgrp->level;
 		__assign_str(path, path);
 	),
@@ -135,7 +135,7 @@ DECLARE_EVENT_CLASS(cgroup_migrate,
 
 	TP_fast_assign(
 		__entry->dst_root = dst_cgrp->root->hierarchy_id;
-		__entry->dst_id = dst_cgrp->id;
+		__entry->dst_id = cgroup_id(dst_cgrp);
 		__entry->dst_level = dst_cgrp->level;
 		__assign_str(dst_path, path);
 		__entry->pid = task->pid;
@@ -179,7 +179,7 @@ DECLARE_EVENT_CLASS(cgroup_event,
 
 	TP_fast_assign(
 		__entry->root = cgrp->root->hierarchy_id;
-		__entry->id = cgrp->id;
+		__entry->id = cgroup_id(cgrp);
 		__entry->level = cgrp->level;
 		__assign_str(path, path);
 		__entry->val = val;
diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h
new file mode 100644
index 000000000000..72a4d0174b02
--- /dev/null
+++ b/include/trace/events/io_uring.h
@@ -0,0 +1,358 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM io_uring
+
+#if !defined(_TRACE_IO_URING_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_IO_URING_H
+
+#include <linux/tracepoint.h>
+
+struct io_wq_work;
+
+/**
+ * io_uring_create - called after a new io_uring context was prepared
+ *
+ * @fd:			corresponding file descriptor
+ * @ctx:		pointer to a ring context structure
+ * @sq_entries:	actual SQ size
+ * @cq_entries:	actual CQ size
+ * @flags:		SQ ring flags, provided to io_uring_setup(2)
+ *
+ * Allows to trace io_uring creation and provide pointer to a context, that can
+ * be used later to find correlated events.
+ */
+TRACE_EVENT(io_uring_create,
+
+	TP_PROTO(int fd, void *ctx, u32 sq_entries, u32 cq_entries, u32 flags),
+
+	TP_ARGS(fd, ctx, sq_entries, cq_entries, flags),
+
+	TP_STRUCT__entry (
+		__field(  int,		fd			)
+		__field(  void *,	ctx			)
+		__field(  u32,		sq_entries	)
+		__field(  u32,		cq_entries	)
+		__field(  u32,		flags		)
+	),
+
+	TP_fast_assign(
+		__entry->fd			= fd;
+		__entry->ctx		= ctx;
+		__entry->sq_entries	= sq_entries;
+		__entry->cq_entries	= cq_entries;
+		__entry->flags		= flags;
+	),
+
+	TP_printk("ring %p, fd %d sq size %d, cq size %d, flags %d",
+			  __entry->ctx, __entry->fd, __entry->sq_entries,
+			  __entry->cq_entries, __entry->flags)
+);
+
+/**
+ * io_uring_register - called after a buffer/file/eventfd was succesfully
+ * 					   registered for a ring
+ *
+ * @ctx:			pointer to a ring context structure
+ * @opcode:			describes which operation to perform
+ * @nr_user_files:	number of registered files
+ * @nr_user_bufs:	number of registered buffers
+ * @cq_ev_fd:		whether eventfs registered or not
+ * @ret:			return code
+ *
+ * Allows to trace fixed files/buffers/eventfds, that could be registered to
+ * avoid an overhead of getting references to them for every operation. This
+ * event, together with io_uring_file_get, can provide a full picture of how
+ * much overhead one can reduce via fixing.
+ */
+TRACE_EVENT(io_uring_register,
+
+	TP_PROTO(void *ctx, unsigned opcode, unsigned nr_files,
+			 unsigned nr_bufs, bool eventfd, long ret),
+
+	TP_ARGS(ctx, opcode, nr_files, nr_bufs, eventfd, ret),
+
+	TP_STRUCT__entry (
+		__field(  void *,	ctx			)
+		__field(  unsigned,	opcode		)
+		__field(  unsigned,	nr_files	)
+		__field(  unsigned,	nr_bufs		)
+		__field(  bool,		eventfd		)
+		__field(  long,		ret			)
+	),
+
+	TP_fast_assign(
+		__entry->ctx		= ctx;
+		__entry->opcode		= opcode;
+		__entry->nr_files	= nr_files;
+		__entry->nr_bufs	= nr_bufs;
+		__entry->eventfd	= eventfd;
+		__entry->ret		= ret;
+	),
+
+	TP_printk("ring %p, opcode %d, nr_user_files %d, nr_user_bufs %d, "
+			  "eventfd %d, ret %ld",
+			  __entry->ctx, __entry->opcode, __entry->nr_files,
+			  __entry->nr_bufs, __entry->eventfd, __entry->ret)
+);
+
+/**
+ * io_uring_file_get - called before getting references to an SQE file
+ *
+ * @ctx:	pointer to a ring context structure
+ * @fd:		SQE file descriptor
+ *
+ * Allows to trace out how often an SQE file reference is obtained, which can
+ * help figuring out if it makes sense to use fixed files, or check that fixed
+ * files are used correctly.
+ */
+TRACE_EVENT(io_uring_file_get,
+
+	TP_PROTO(void *ctx, int fd),
+
+	TP_ARGS(ctx, fd),
+
+	TP_STRUCT__entry (
+		__field(  void *,	ctx	)
+		__field(  int,		fd	)
+	),
+
+	TP_fast_assign(
+		__entry->ctx	= ctx;
+		__entry->fd		= fd;
+	),
+
+	TP_printk("ring %p, fd %d", __entry->ctx, __entry->fd)
+);
+
+/**
+ * io_uring_queue_async_work - called before submitting a new async work
+ *
+ * @ctx:	pointer to a ring context structure
+ * @hashed:	type of workqueue, hashed or normal
+ * @req:	pointer to a submitted request
+ * @work:	pointer to a submitted io_wq_work
+ *
+ * Allows to trace asynchronous work submission.
+ */
+TRACE_EVENT(io_uring_queue_async_work,
+
+	TP_PROTO(void *ctx, int rw, void * req, struct io_wq_work *work,
+			 unsigned int flags),
+
+	TP_ARGS(ctx, rw, req, work, flags),
+
+	TP_STRUCT__entry (
+		__field(  void *,				ctx		)
+		__field(  int,					rw		)
+		__field(  void *,				req		)
+		__field(  struct io_wq_work *,		work	)
+		__field(  unsigned int,			flags	)
+	),
+
+	TP_fast_assign(
+		__entry->ctx	= ctx;
+		__entry->rw		= rw;
+		__entry->req	= req;
+		__entry->work	= work;
+		__entry->flags	= flags;
+	),
+
+	TP_printk("ring %p, request %p, flags %d, %s queue, work %p",
+			  __entry->ctx, __entry->req, __entry->flags,
+			  __entry->rw ? "hashed" : "normal", __entry->work)
+);
+
+/**
+ * io_uring_defer_list - called before the io_uring work added into defer_list
+ *
+ * @ctx:	pointer to a ring context structure
+ * @req:	pointer to a deferred request
+ * @shadow: whether request is shadow or not
+ *
+ * Allows to track deferred requests, to get an insight about what requests are
+ * not started immediately.
+ */
+TRACE_EVENT(io_uring_defer,
+
+	TP_PROTO(void *ctx, void *req, bool shadow),
+
+	TP_ARGS(ctx, req, shadow),
+
+	TP_STRUCT__entry (
+		__field(  void *,	ctx		)
+		__field(  void *,	req		)
+		__field(  bool,		shadow	)
+	),
+
+	TP_fast_assign(
+		__entry->ctx	= ctx;
+		__entry->req	= req;
+		__entry->shadow	= shadow;
+	),
+
+	TP_printk("ring %p, request %p%s", __entry->ctx, __entry->req,
+			  __entry->shadow ? ", shadow": "")
+);
+
+/**
+ * io_uring_link - called before the io_uring request added into link_list of
+ * 				   another request
+ *
+ * @ctx:			pointer to a ring context structure
+ * @req:			pointer to a linked request
+ * @target_req:		pointer to a previous request, that would contain @req
+ *
+ * Allows to track linked requests, to understand dependencies between requests
+ * and how does it influence their execution flow.
+ */
+TRACE_EVENT(io_uring_link,
+
+	TP_PROTO(void *ctx, void *req, void *target_req),
+
+	TP_ARGS(ctx, req, target_req),
+
+	TP_STRUCT__entry (
+		__field(  void *,	ctx			)
+		__field(  void *,	req			)
+		__field(  void *,	target_req	)
+	),
+
+	TP_fast_assign(
+		__entry->ctx		= ctx;
+		__entry->req		= req;
+		__entry->target_req	= target_req;
+	),
+
+	TP_printk("ring %p, request %p linked after %p",
+			  __entry->ctx, __entry->req, __entry->target_req)
+);
+
+/**
+ * io_uring_cqring_wait - called before start waiting for an available CQE
+ *
+ * @ctx:		pointer to a ring context structure
+ * @min_events:	minimal number of events to wait for
+ *
+ * Allows to track waiting for CQE, so that we can e.g. troubleshoot
+ * situations, when an application wants to wait for an event, that never
+ * comes.
+ */
+TRACE_EVENT(io_uring_cqring_wait,
+
+	TP_PROTO(void *ctx, int min_events),
+
+	TP_ARGS(ctx, min_events),
+
+	TP_STRUCT__entry (
+		__field(  void *,	ctx			)
+		__field(  int,		min_events	)
+	),
+
+	TP_fast_assign(
+		__entry->ctx	= ctx;
+		__entry->min_events	= min_events;
+	),
+
+	TP_printk("ring %p, min_events %d", __entry->ctx, __entry->min_events)
+);
+
+/**
+ * io_uring_fail_link - called before failing a linked request
+ *
+ * @req:	request, which links were cancelled
+ * @link:	cancelled link
+ *
+ * Allows to track linked requests cancellation, to see not only that some work
+ * was cancelled, but also which request was the reason.
+ */
+TRACE_EVENT(io_uring_fail_link,
+
+	TP_PROTO(void *req, void *link),
+
+	TP_ARGS(req, link),
+
+	TP_STRUCT__entry (
+		__field(  void *,	req		)
+		__field(  void *,	link	)
+	),
+
+	TP_fast_assign(
+		__entry->req	= req;
+		__entry->link	= link;
+	),
+
+	TP_printk("request %p, link %p", __entry->req, __entry->link)
+);
+
+/**
+ * io_uring_complete - called when completing an SQE
+ *
+ * @ctx:		pointer to a ring context structure
+ * @user_data:		user data associated with the request
+ * @res:		result of the request
+ *
+ */
+TRACE_EVENT(io_uring_complete,
+
+	TP_PROTO(void *ctx, u64 user_data, long res),
+
+	TP_ARGS(ctx, user_data, res),
+
+	TP_STRUCT__entry (
+		__field(  void *,	ctx		)
+		__field(  u64,		user_data	)
+		__field(  long,		res		)
+	),
+
+	TP_fast_assign(
+		__entry->ctx		= ctx;
+		__entry->user_data	= user_data;
+		__entry->res		= res;
+	),
+
+	TP_printk("ring %p, user_data 0x%llx, result %ld",
+			  __entry->ctx, (unsigned long long)__entry->user_data,
+			  __entry->res)
+);
+
+
+/**
+ * io_uring_submit_sqe - called before submitting one SQE
+ *
+ * @ctx:		pointer to a ring context structure
+ * @user_data:		user data associated with the request
+ * @force_nonblock:	whether a context blocking or not
+ * @sq_thread:		true if sq_thread has submitted this SQE
+ *
+ * Allows to track SQE submitting, to understand what was the source of it, SQ
+ * thread or io_uring_enter call.
+ */
+TRACE_EVENT(io_uring_submit_sqe,
+
+	TP_PROTO(void *ctx, u64 user_data, bool force_nonblock, bool sq_thread),
+
+	TP_ARGS(ctx, user_data, force_nonblock, sq_thread),
+
+	TP_STRUCT__entry (
+		__field(  void *,	ctx		)
+		__field(  u64,		user_data	)
+		__field(  bool,		force_nonblock	)
+		__field(  bool,		sq_thread	)
+	),
+
+	TP_fast_assign(
+		__entry->ctx		= ctx;
+		__entry->user_data	= user_data;
+		__entry->force_nonblock	= force_nonblock;
+		__entry->sq_thread	= sq_thread;
+	),
+
+	TP_printk("ring %p, user data 0x%llx, non block %d, sq_thread %d",
+			  __entry->ctx, (unsigned long long) __entry->user_data,
+			  __entry->force_nonblock, __entry->sq_thread)
+);
+
+#endif /* _TRACE_IO_URING_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/wbt.h b/include/trace/events/wbt.h
index b048694070e2..37342a13c9cb 100644
--- a/include/trace/events/wbt.h
+++ b/include/trace/events/wbt.h
@@ -33,7 +33,8 @@ TRACE_EVENT(wbt_stat,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		strlcpy(__entry->name, dev_name(bdi->dev),
+			ARRAY_SIZE(__entry->name));
 		__entry->rmean		= stat[0].mean;
 		__entry->rmin		= stat[0].min;
 		__entry->rmax		= stat[0].max;
@@ -67,7 +68,8 @@ TRACE_EVENT(wbt_lat,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		strlcpy(__entry->name, dev_name(bdi->dev),
+			ARRAY_SIZE(__entry->name));
 		__entry->lat = div_u64(lat, 1000);
 	),
 
@@ -103,7 +105,8 @@ TRACE_EVENT(wbt_step,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		strlcpy(__entry->name, dev_name(bdi->dev),
+			ARRAY_SIZE(__entry->name));
 		__entry->msg	= msg;
 		__entry->step	= step;
 		__entry->window	= div_u64(window, 1000);
@@ -138,7 +141,8 @@ TRACE_EVENT(wbt_timer,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		strlcpy(__entry->name, dev_name(bdi->dev),
+			ARRAY_SIZE(__entry->name));
 		__entry->status		= status;
 		__entry->step		= step;
 		__entry->inflight	= inflight;
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index c2ce6480b4b1..ef50be4e5e6c 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -61,7 +61,7 @@ DECLARE_EVENT_CLASS(writeback_page_template,
 
 	TP_STRUCT__entry (
 		__array(char, name, 32)
-		__field(unsigned long, ino)
+		__field(ino_t, ino)
 		__field(pgoff_t, index)
 	),
 
@@ -75,7 +75,7 @@ DECLARE_EVENT_CLASS(writeback_page_template,
 
 	TP_printk("bdi %s: ino=%lu index=%lu",
 		__entry->name,
-		__entry->ino,
+		(unsigned long)__entry->ino,
 		__entry->index
 	)
 );
@@ -102,7 +102,7 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template,
 
 	TP_STRUCT__entry (
 		__array(char, name, 32)
-		__field(unsigned long, ino)
+		__field(ino_t, ino)
 		__field(unsigned long, state)
 		__field(unsigned long, flags)
 	),
@@ -120,7 +120,7 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template,
 
 	TP_printk("bdi %s: ino=%lu state=%s flags=%s",
 		__entry->name,
-		__entry->ino,
+		(unsigned long)__entry->ino,
 		show_inode_state(__entry->state),
 		show_inode_state(__entry->flags)
 	)
@@ -150,28 +150,28 @@ DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode,
 #ifdef CREATE_TRACE_POINTS
 #ifdef CONFIG_CGROUP_WRITEBACK
 
-static inline unsigned int __trace_wb_assign_cgroup(struct bdi_writeback *wb)
+static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb)
 {
-	return wb->memcg_css->cgroup->kn->id.ino;
+	return cgroup_ino(wb->memcg_css->cgroup);
 }
 
-static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *wbc)
+static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc)
 {
 	if (wbc->wb)
 		return __trace_wb_assign_cgroup(wbc->wb);
 	else
-		return -1U;
+		return 1;
 }
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
-static inline unsigned int __trace_wb_assign_cgroup(struct bdi_writeback *wb)
+static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb)
 {
-	return -1U;
+	return 1;
 }
 
-static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *wbc)
+static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc)
 {
-	return -1U;
+	return 1;
 }
 
 #endif	/* CONFIG_CGROUP_WRITEBACK */
@@ -187,8 +187,8 @@ TRACE_EVENT(inode_foreign_history,
 
 	TP_STRUCT__entry(
 		__array(char,		name, 32)
-		__field(unsigned long,	ino)
-		__field(unsigned int,	cgroup_ino)
+		__field(ino_t,		ino)
+		__field(ino_t,		cgroup_ino)
 		__field(unsigned int,	history)
 	),
 
@@ -199,10 +199,10 @@ TRACE_EVENT(inode_foreign_history,
 		__entry->history	= history;
 	),
 
-	TP_printk("bdi %s: ino=%lu cgroup_ino=%u history=0x%x",
+	TP_printk("bdi %s: ino=%lu cgroup_ino=%lu history=0x%x",
 		__entry->name,
-		__entry->ino,
-		__entry->cgroup_ino,
+		(unsigned long)__entry->ino,
+		(unsigned long)__entry->cgroup_ino,
 		__entry->history
 	)
 );
@@ -216,9 +216,9 @@ TRACE_EVENT(inode_switch_wbs,
 
 	TP_STRUCT__entry(
 		__array(char,		name, 32)
-		__field(unsigned long,	ino)
-		__field(unsigned int,	old_cgroup_ino)
-		__field(unsigned int,	new_cgroup_ino)
+		__field(ino_t,		ino)
+		__field(ino_t,		old_cgroup_ino)
+		__field(ino_t,		new_cgroup_ino)
 	),
 
 	TP_fast_assign(
@@ -228,11 +228,11 @@ TRACE_EVENT(inode_switch_wbs,
 		__entry->new_cgroup_ino	= __trace_wb_assign_cgroup(new_wb);
 	),
 
-	TP_printk("bdi %s: ino=%lu old_cgroup_ino=%u new_cgroup_ino=%u",
+	TP_printk("bdi %s: ino=%lu old_cgroup_ino=%lu new_cgroup_ino=%lu",
 		__entry->name,
-		__entry->ino,
-		__entry->old_cgroup_ino,
-		__entry->new_cgroup_ino
+		(unsigned long)__entry->ino,
+		(unsigned long)__entry->old_cgroup_ino,
+		(unsigned long)__entry->new_cgroup_ino
 	)
 );
 
@@ -245,10 +245,10 @@ TRACE_EVENT(track_foreign_dirty,
 	TP_STRUCT__entry(
 		__array(char,		name, 32)
 		__field(u64,		bdi_id)
-		__field(unsigned long,	ino)
+		__field(ino_t,		ino)
 		__field(unsigned int,	memcg_id)
-		__field(unsigned int,	cgroup_ino)
-		__field(unsigned int,	page_cgroup_ino)
+		__field(ino_t,		cgroup_ino)
+		__field(ino_t,		page_cgroup_ino)
 	),
 
 	TP_fast_assign(
@@ -260,16 +260,16 @@ TRACE_EVENT(track_foreign_dirty,
 		__entry->ino		= inode ? inode->i_ino : 0;
 		__entry->memcg_id	= wb->memcg_css->id;
 		__entry->cgroup_ino	= __trace_wb_assign_cgroup(wb);
-		__entry->page_cgroup_ino = page->mem_cgroup->css.cgroup->kn->id.ino;
+		__entry->page_cgroup_ino = cgroup_ino(page->mem_cgroup->css.cgroup);
 	),
 
-	TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%u page_cgroup_ino=%u",
+	TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu",
 		__entry->name,
 		__entry->bdi_id,
-		__entry->ino,
+		(unsigned long)__entry->ino,
 		__entry->memcg_id,
-		__entry->cgroup_ino,
-		__entry->page_cgroup_ino
+		(unsigned long)__entry->cgroup_ino,
+		(unsigned long)__entry->page_cgroup_ino
 	)
 );
 
@@ -282,7 +282,7 @@ TRACE_EVENT(flush_foreign,
 
 	TP_STRUCT__entry(
 		__array(char,		name, 32)
-		__field(unsigned int,	cgroup_ino)
+		__field(ino_t,		cgroup_ino)
 		__field(unsigned int,	frn_bdi_id)
 		__field(unsigned int,	frn_memcg_id)
 	),
@@ -294,9 +294,9 @@ TRACE_EVENT(flush_foreign,
 		__entry->frn_memcg_id	= frn_memcg_id;
 	),
 
-	TP_printk("bdi %s: cgroup_ino=%u frn_bdi_id=%u frn_memcg_id=%u",
+	TP_printk("bdi %s: cgroup_ino=%lu frn_bdi_id=%u frn_memcg_id=%u",
 		__entry->name,
-		__entry->cgroup_ino,
+		(unsigned long)__entry->cgroup_ino,
 		__entry->frn_bdi_id,
 		__entry->frn_memcg_id
 	)
@@ -311,9 +311,9 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template,
 
 	TP_STRUCT__entry (
 		__array(char, name, 32)
-		__field(unsigned long, ino)
+		__field(ino_t, ino)
 		__field(int, sync_mode)
-		__field(unsigned int, cgroup_ino)
+		__field(ino_t, cgroup_ino)
 	),
 
 	TP_fast_assign(
@@ -324,11 +324,11 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template,
 		__entry->cgroup_ino	= __trace_wbc_assign_cgroup(wbc);
 	),
 
-	TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup_ino=%u",
+	TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup_ino=%lu",
 		__entry->name,
-		__entry->ino,
+		(unsigned long)__entry->ino,
 		__entry->sync_mode,
-		__entry->cgroup_ino
+		(unsigned long)__entry->cgroup_ino
 	)
 );
 
@@ -358,7 +358,7 @@ DECLARE_EVENT_CLASS(writeback_work_class,
 		__field(int, range_cyclic)
 		__field(int, for_background)
 		__field(int, reason)
-		__field(unsigned int, cgroup_ino)
+		__field(ino_t, cgroup_ino)
 	),
 	TP_fast_assign(
 		strscpy_pad(__entry->name,
@@ -374,7 +374,7 @@ DECLARE_EVENT_CLASS(writeback_work_class,
 		__entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
 	),
 	TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d "
-		  "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup_ino=%u",
+		  "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup_ino=%lu",
 		  __entry->name,
 		  MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev),
 		  __entry->nr_pages,
@@ -383,7 +383,7 @@ DECLARE_EVENT_CLASS(writeback_work_class,
 		  __entry->range_cyclic,
 		  __entry->for_background,
 		  __print_symbolic(__entry->reason, WB_WORK_REASON),
-		  __entry->cgroup_ino
+		  (unsigned long)__entry->cgroup_ino
 	)
 );
 #define DEFINE_WRITEBACK_WORK_EVENT(name) \
@@ -413,15 +413,15 @@ DECLARE_EVENT_CLASS(writeback_class,
 	TP_ARGS(wb),
 	TP_STRUCT__entry(
 		__array(char, name, 32)
-		__field(unsigned int, cgroup_ino)
+		__field(ino_t, cgroup_ino)
 	),
 	TP_fast_assign(
 		strscpy_pad(__entry->name, dev_name(wb->bdi->dev), 32);
 		__entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
 	),
-	TP_printk("bdi %s: cgroup_ino=%u",
+	TP_printk("bdi %s: cgroup_ino=%lu",
 		  __entry->name,
-		  __entry->cgroup_ino
+		  (unsigned long)__entry->cgroup_ino
 	)
 );
 #define DEFINE_WRITEBACK_EVENT(name) \
@@ -459,7 +459,7 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__field(int, range_cyclic)
 		__field(long, range_start)
 		__field(long, range_end)
-		__field(unsigned int, cgroup_ino)
+		__field(ino_t, cgroup_ino)
 	),
 
 	TP_fast_assign(
@@ -478,7 +478,7 @@ DECLARE_EVENT_CLASS(wbc_class,
 
 	TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d "
 		"bgrd=%d reclm=%d cyclic=%d "
-		"start=0x%lx end=0x%lx cgroup_ino=%u",
+		"start=0x%lx end=0x%lx cgroup_ino=%lu",
 		__entry->name,
 		__entry->nr_to_write,
 		__entry->pages_skipped,
@@ -489,7 +489,7 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__entry->range_cyclic,
 		__entry->range_start,
 		__entry->range_end,
-		__entry->cgroup_ino
+		(unsigned long)__entry->cgroup_ino
 	)
 )
 
@@ -510,7 +510,7 @@ TRACE_EVENT(writeback_queue_io,
 		__field(long,		age)
 		__field(int,		moved)
 		__field(int,		reason)
-		__field(unsigned int,	cgroup_ino)
+		__field(ino_t,		cgroup_ino)
 	),
 	TP_fast_assign(
 		unsigned long *older_than_this = work->older_than_this;
@@ -522,13 +522,13 @@ TRACE_EVENT(writeback_queue_io,
 		__entry->reason	= work->reason;
 		__entry->cgroup_ino	= __trace_wb_assign_cgroup(wb);
 	),
-	TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%u",
+	TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%lu",
 		__entry->name,
 		__entry->older,	/* older_than_this in jiffies */
 		__entry->age,	/* older_than_this in relative milliseconds */
 		__entry->moved,
 		__print_symbolic(__entry->reason, WB_WORK_REASON),
-		__entry->cgroup_ino
+		(unsigned long)__entry->cgroup_ino
 	)
 );
 
@@ -596,7 +596,7 @@ TRACE_EVENT(bdi_dirty_ratelimit,
 		__field(unsigned long,	dirty_ratelimit)
 		__field(unsigned long,	task_ratelimit)
 		__field(unsigned long,	balanced_dirty_ratelimit)
-		__field(unsigned int,	cgroup_ino)
+		__field(ino_t,		cgroup_ino)
 	),
 
 	TP_fast_assign(
@@ -614,7 +614,7 @@ TRACE_EVENT(bdi_dirty_ratelimit,
 	TP_printk("bdi %s: "
 		  "write_bw=%lu awrite_bw=%lu dirty_rate=%lu "
 		  "dirty_ratelimit=%lu task_ratelimit=%lu "
-		  "balanced_dirty_ratelimit=%lu cgroup_ino=%u",
+		  "balanced_dirty_ratelimit=%lu cgroup_ino=%lu",
 		  __entry->bdi,
 		  __entry->write_bw,		/* write bandwidth */
 		  __entry->avg_write_bw,	/* avg write bandwidth */
@@ -622,7 +622,7 @@ TRACE_EVENT(bdi_dirty_ratelimit,
 		  __entry->dirty_ratelimit,	/* base ratelimit */
 		  __entry->task_ratelimit, /* ratelimit with position control */
 		  __entry->balanced_dirty_ratelimit, /* the balanced ratelimit */
-		  __entry->cgroup_ino
+		  (unsigned long)__entry->cgroup_ino
 	)
 );
 
@@ -660,7 +660,7 @@ TRACE_EVENT(balance_dirty_pages,
 		__field(	 long,	pause)
 		__field(unsigned long,	period)
 		__field(	 long,	think)
-		__field(unsigned int,	cgroup_ino)
+		__field(ino_t,		cgroup_ino)
 	),
 
 	TP_fast_assign(
@@ -692,7 +692,7 @@ TRACE_EVENT(balance_dirty_pages,
 		  "bdi_setpoint=%lu bdi_dirty=%lu "
 		  "dirty_ratelimit=%lu task_ratelimit=%lu "
 		  "dirtied=%u dirtied_pause=%u "
-		  "paused=%lu pause=%ld period=%lu think=%ld cgroup_ino=%u",
+		  "paused=%lu pause=%ld period=%lu think=%ld cgroup_ino=%lu",
 		  __entry->bdi,
 		  __entry->limit,
 		  __entry->setpoint,
@@ -707,7 +707,7 @@ TRACE_EVENT(balance_dirty_pages,
 		  __entry->pause,	/* ms */
 		  __entry->period,	/* ms */
 		  __entry->think,	/* ms */
-		  __entry->cgroup_ino
+		  (unsigned long)__entry->cgroup_ino
 	  )
 );
 
@@ -718,10 +718,10 @@ TRACE_EVENT(writeback_sb_inodes_requeue,
 
 	TP_STRUCT__entry(
 		__array(char, name, 32)
-		__field(unsigned long, ino)
+		__field(ino_t, ino)
 		__field(unsigned long, state)
 		__field(unsigned long, dirtied_when)
-		__field(unsigned int, cgroup_ino)
+		__field(ino_t, cgroup_ino)
 	),
 
 	TP_fast_assign(
@@ -733,13 +733,13 @@ TRACE_EVENT(writeback_sb_inodes_requeue,
 		__entry->cgroup_ino	= __trace_wb_assign_cgroup(inode_to_wb(inode));
 	),
 
-	TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup_ino=%u",
+	TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup_ino=%lu",
 		  __entry->name,
-		  __entry->ino,
+		  (unsigned long)__entry->ino,
 		  show_inode_state(__entry->state),
 		  __entry->dirtied_when,
 		  (jiffies - __entry->dirtied_when) / HZ,
-		  __entry->cgroup_ino
+		  (unsigned long)__entry->cgroup_ino
 	)
 );
 
@@ -789,13 +789,13 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template,
 
 	TP_STRUCT__entry(
 		__array(char, name, 32)
-		__field(unsigned long, ino)
+		__field(ino_t, ino)
 		__field(unsigned long, state)
 		__field(unsigned long, dirtied_when)
 		__field(unsigned long, writeback_index)
 		__field(long, nr_to_write)
 		__field(unsigned long, wrote)
-		__field(unsigned int, cgroup_ino)
+		__field(ino_t, cgroup_ino)
 	),
 
 	TP_fast_assign(
@@ -811,16 +811,16 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template,
 	),
 
 	TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu "
-		  "index=%lu to_write=%ld wrote=%lu cgroup_ino=%u",
+		  "index=%lu to_write=%ld wrote=%lu cgroup_ino=%lu",
 		  __entry->name,
-		  __entry->ino,
+		  (unsigned long)__entry->ino,
 		  show_inode_state(__entry->state),
 		  __entry->dirtied_when,
 		  (jiffies - __entry->dirtied_when) / HZ,
 		  __entry->writeback_index,
 		  __entry->nr_to_write,
 		  __entry->wrote,
-		  __entry->cgroup_ino
+		  (unsigned long)__entry->cgroup_ino
 	)
 );
 
@@ -845,7 +845,7 @@ DECLARE_EVENT_CLASS(writeback_inode_template,
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
-		__field(unsigned long,	ino			)
+		__field(	ino_t,	ino			)
 		__field(unsigned long,	state			)
 		__field(	__u16, mode			)
 		__field(unsigned long, dirtied_when		)
@@ -861,7 +861,7 @@ DECLARE_EVENT_CLASS(writeback_inode_template,
 
 	TP_printk("dev %d,%d ino %lu dirtied %lu state %s mode 0%o",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->ino, __entry->dirtied_when,
+		  (unsigned long)__entry->ino, __entry->dirtied_when,
 		  show_inode_state(__entry->state), __entry->mode)
 );
 
diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h
index 498eec813494..0cdef67135f0 100644
--- a/include/uapi/linux/blkzoned.h
+++ b/include/uapi/linux/blkzoned.h
@@ -120,9 +120,11 @@ struct blk_zone_report {
 };
 
 /**
- * struct blk_zone_range - BLKRESETZONE ioctl request
- * @sector: starting sector of the first zone to issue reset write pointer
- * @nr_sectors: Total number of sectors of 1 or more zones to reset
+ * struct blk_zone_range - BLKRESETZONE/BLKOPENZONE/
+ *                         BLKCLOSEZONE/BLKFINISHZONE ioctl
+ *                         requests
+ * @sector: Starting sector of the first zone to operate on.
+ * @nr_sectors: Total number of sectors of all zones to operate on.
  */
 struct blk_zone_range {
 	__u64		sector;
@@ -139,10 +141,19 @@ struct blk_zone_range {
  *                sector range. The sector range must be zone aligned.
  * @BLKGETZONESZ: Get the device zone size in number of 512 B sectors.
  * @BLKGETNRZONES: Get the total number of zones of the device.
+ * @BLKOPENZONE: Open the zones in the specified sector range.
+ *               The 512 B sector range must be zone aligned.
+ * @BLKCLOSEZONE: Close the zones in the specified sector range.
+ *                The 512 B sector range must be zone aligned.
+ * @BLKFINISHZONE: Mark the zones as full in the specified sector range.
+ *                 The 512 B sector range must be zone aligned.
  */
 #define BLKREPORTZONE	_IOWR(0x12, 130, struct blk_zone_report)
 #define BLKRESETZONE	_IOW(0x12, 131, struct blk_zone_range)
 #define BLKGETZONESZ	_IOR(0x12, 132, __u32)
 #define BLKGETNRZONES	_IOR(0x12, 133, __u32)
+#define BLKOPENZONE	_IOW(0x12, 134, struct blk_zone_range)
+#define BLKCLOSEZONE	_IOW(0x12, 135, struct blk_zone_range)
+#define BLKFINISHZONE	_IOW(0x12, 136, struct blk_zone_range)
 
 #endif /* _UAPI_BLKZONED_H */
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 3ee0678c0a83..7a8bc8b920f5 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -270,6 +270,7 @@ struct btrfs_ioctl_fs_info_args {
 #define BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA	(1ULL << 8)
 #define BTRFS_FEATURE_INCOMPAT_NO_HOLES		(1ULL << 9)
 #define BTRFS_FEATURE_INCOMPAT_METADATA_UUID	(1ULL << 10)
+#define BTRFS_FEATURE_INCOMPAT_RAID1C34		(1ULL << 11)
 
 struct btrfs_ioctl_feature_flags {
 	__u64 compat_flags;
@@ -831,7 +832,9 @@ enum btrfs_err_code {
 	BTRFS_ERROR_DEV_TGT_REPLACE,
 	BTRFS_ERROR_DEV_MISSING_NOT_FOUND,
 	BTRFS_ERROR_DEV_ONLY_WRITABLE,
-	BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS
+	BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS,
+	BTRFS_ERROR_DEV_RAID1C3_MIN_NOT_MET,
+	BTRFS_ERROR_DEV_RAID1C4_MIN_NOT_MET,
 };
 
 #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \
diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
index b65c7ee75bc7..8e322e2c7e78 100644
--- a/include/uapi/linux/btrfs_tree.h
+++ b/include/uapi/linux/btrfs_tree.h
@@ -302,6 +302,9 @@
 /* csum types */
 enum btrfs_csum_type {
 	BTRFS_CSUM_TYPE_CRC32	= 0,
+	BTRFS_CSUM_TYPE_XXHASH	= 1,
+	BTRFS_CSUM_TYPE_SHA256	= 2,
+	BTRFS_CSUM_TYPE_BLAKE2	= 3,
 };
 
 /*
@@ -737,10 +740,12 @@ struct btrfs_balance_item {
 	__le64 unused[4];
 } __attribute__ ((__packed__));
 
-#define BTRFS_FILE_EXTENT_INLINE 0
-#define BTRFS_FILE_EXTENT_REG 1
-#define BTRFS_FILE_EXTENT_PREALLOC 2
-#define BTRFS_FILE_EXTENT_TYPES	2
+enum {
+	BTRFS_FILE_EXTENT_INLINE   = 0,
+	BTRFS_FILE_EXTENT_REG      = 1,
+	BTRFS_FILE_EXTENT_PREALLOC = 2,
+	BTRFS_NR_FILE_EXTENT_TYPES = 3,
+};
 
 struct btrfs_file_extent_item {
 	/*
@@ -836,6 +841,8 @@ struct btrfs_dev_replace_item {
 #define BTRFS_BLOCK_GROUP_RAID10	(1ULL << 6)
 #define BTRFS_BLOCK_GROUP_RAID5         (1ULL << 7)
 #define BTRFS_BLOCK_GROUP_RAID6         (1ULL << 8)
+#define BTRFS_BLOCK_GROUP_RAID1C3       (1ULL << 9)
+#define BTRFS_BLOCK_GROUP_RAID1C4       (1ULL << 10)
 #define BTRFS_BLOCK_GROUP_RESERVED	(BTRFS_AVAIL_ALLOC_BIT_SINGLE | \
 					 BTRFS_SPACE_INFO_GLOBAL_RSV)
 
@@ -847,6 +854,8 @@ enum btrfs_raid_types {
 	BTRFS_RAID_SINGLE,
 	BTRFS_RAID_RAID5,
 	BTRFS_RAID_RAID6,
+	BTRFS_RAID_RAID1C3,
+	BTRFS_RAID_RAID1C4,
 	BTRFS_NR_RAID_TYPES
 };
 
@@ -856,6 +865,8 @@ enum btrfs_raid_types {
 
 #define BTRFS_BLOCK_GROUP_PROFILE_MASK	(BTRFS_BLOCK_GROUP_RAID0 |   \
 					 BTRFS_BLOCK_GROUP_RAID1 |   \
+					 BTRFS_BLOCK_GROUP_RAID1C3 | \
+					 BTRFS_BLOCK_GROUP_RAID1C4 | \
 					 BTRFS_BLOCK_GROUP_RAID5 |   \
 					 BTRFS_BLOCK_GROUP_RAID6 |   \
 					 BTRFS_BLOCK_GROUP_DUP |     \
@@ -863,7 +874,9 @@ enum btrfs_raid_types {
 #define BTRFS_BLOCK_GROUP_RAID56_MASK	(BTRFS_BLOCK_GROUP_RAID5 |   \
 					 BTRFS_BLOCK_GROUP_RAID6)
 
-#define BTRFS_BLOCK_GROUP_RAID1_MASK	(BTRFS_BLOCK_GROUP_RAID1)
+#define BTRFS_BLOCK_GROUP_RAID1_MASK	(BTRFS_BLOCK_GROUP_RAID1 |   \
+					 BTRFS_BLOCK_GROUP_RAID1C3 | \
+					 BTRFS_BLOCK_GROUP_RAID1C4)
 
 /*
  * We need a bit for restriper to be able to tell when chunks of type
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index 1d338357df8a..1f97b33c840e 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -58,7 +58,7 @@
  * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
  * used to clear any hints previously set.
  */
-#define RWF_WRITE_LIFE_NOT_SET	0
+#define RWH_WRITE_LIFE_NOT_SET	0
 #define RWH_WRITE_LIFE_NONE	1
 #define RWH_WRITE_LIFE_SHORT	2
 #define RWH_WRITE_LIFE_MEDIUM	3
@@ -66,6 +66,13 @@
 #define RWH_WRITE_LIFE_EXTREME	5
 
 /*
+ * The originally introduced spelling is remained from the first
+ * versions of the patch set that introduced the feature, see commit
+ * v4.13-rc1~212^2~51.
+ */
+#define RWF_WRITE_LIFE_NOT_SET	RWH_WRITE_LIFE_NOT_SET
+
+/*
  * Types of directory notifications that may be requested.
  */
 #define DN_ACCESS	0x00000001	/* File accessed */
diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h
index 39ccfe9311c3..1beb174ad950 100644
--- a/include/uapi/linux/fscrypt.h
+++ b/include/uapi/linux/fscrypt.h
@@ -17,7 +17,8 @@
 #define FSCRYPT_POLICY_FLAGS_PAD_32		0x03
 #define FSCRYPT_POLICY_FLAGS_PAD_MASK		0x03
 #define FSCRYPT_POLICY_FLAG_DIRECT_KEY		0x04
-#define FSCRYPT_POLICY_FLAGS_VALID		0x07
+#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64	0x08
+#define FSCRYPT_POLICY_FLAGS_VALID		0x0F
 
 /* Encryption algorithms */
 #define FSCRYPT_MODE_AES_256_XTS		1
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index ea57526a5b89..2a1569211d87 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -19,7 +19,10 @@ struct io_uring_sqe {
 	__u8	flags;		/* IOSQE_ flags */
 	__u16	ioprio;		/* ioprio for the request */
 	__s32	fd;		/* file descriptor to do IO on */
-	__u64	off;		/* offset into file */
+	union {
+		__u64	off;	/* offset into file */
+		__u64	addr2;
+	};
 	__u64	addr;		/* pointer to buffer or iovecs */
 	__u32	len;		/* buffer size or number of iovecs */
 	union {
@@ -29,6 +32,8 @@ struct io_uring_sqe {
 		__u32		sync_range_flags;
 		__u32		msg_flags;
 		__u32		timeout_flags;
+		__u32		accept_flags;
+		__u32		cancel_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	union {
@@ -50,6 +55,7 @@ struct io_uring_sqe {
 #define IORING_SETUP_IOPOLL	(1U << 0)	/* io_context is polled */
 #define IORING_SETUP_SQPOLL	(1U << 1)	/* SQ poll thread */
 #define IORING_SETUP_SQ_AFF	(1U << 2)	/* sq_thread_cpu is valid */
+#define IORING_SETUP_CQSIZE	(1U << 3)	/* app defines CQ size */
 
 #define IORING_OP_NOP		0
 #define IORING_OP_READV		1
@@ -63,6 +69,10 @@ struct io_uring_sqe {
 #define IORING_OP_SENDMSG	9
 #define IORING_OP_RECVMSG	10
 #define IORING_OP_TIMEOUT	11
+#define IORING_OP_TIMEOUT_REMOVE	12
+#define IORING_OP_ACCEPT	13
+#define IORING_OP_ASYNC_CANCEL	14
+#define IORING_OP_LINK_TIMEOUT	15
 
 /*
  * sqe->fsync_flags
@@ -70,6 +80,11 @@ struct io_uring_sqe {
 #define IORING_FSYNC_DATASYNC	(1U << 0)
 
 /*
+ * sqe->timeout_flags
+ */
+#define IORING_TIMEOUT_ABS	(1U << 0)
+
+/*
  * IO completion data structure (Completion Queue Entry)
  */
 struct io_uring_cqe {
@@ -140,6 +155,7 @@ struct io_uring_params {
  * io_uring_params->features flags
  */
 #define IORING_FEAT_SINGLE_MMAP		(1U << 0)
+#define IORING_FEAT_NODROP		(1U << 1)
 
 /*
  * io_uring_register(2) opcodes and arguments
@@ -150,5 +166,11 @@ struct io_uring_params {
 #define IORING_UNREGISTER_FILES		3
 #define IORING_REGISTER_EVENTFD		4
 #define IORING_UNREGISTER_EVENTFD	5
+#define IORING_REGISTER_FILES_UPDATE	6
+
+struct io_uring_files_update {
+	__u32 offset;
+	__s32 *fds;
+};
 
 #endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 52641d8ca9e8..e6f17c8e2dba 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -235,6 +235,7 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_S390_STSI        25
 #define KVM_EXIT_IOAPIC_EOI       26
 #define KVM_EXIT_HYPERV           27
+#define KVM_EXIT_ARM_NISV         28
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -394,6 +395,11 @@ struct kvm_run {
 		} eoi;
 		/* KVM_EXIT_HYPERV */
 		struct kvm_hyperv_exit hyperv;
+		/* KVM_EXIT_ARM_NISV */
+		struct {
+			__u64 esr_iss;
+			__u64 fault_ipa;
+		} arm_nisv;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1000,6 +1006,9 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PMU_EVENT_FILTER 173
 #define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174
 #define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175
+#define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176
+#define KVM_CAP_ARM_NISV_TO_USER 177
+#define KVM_CAP_ARM_INJECT_EXT_DABT 178
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1227,6 +1236,8 @@ enum kvm_device_type {
 #define KVM_DEV_TYPE_ARM_VGIC_ITS	KVM_DEV_TYPE_ARM_VGIC_ITS
 	KVM_DEV_TYPE_XIVE,
 #define KVM_DEV_TYPE_XIVE		KVM_DEV_TYPE_XIVE
+	KVM_DEV_TYPE_ARM_PV_TIME,
+#define KVM_DEV_TYPE_ARM_PV_TIME	KVM_DEV_TYPE_ARM_PV_TIME
 	KVM_DEV_TYPE_MAX,
 };
 
diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h
index 592a0c1b77c9..0549a5c622bf 100644
--- a/include/uapi/linux/psp-sev.h
+++ b/include/uapi/linux/psp-sev.h
@@ -58,6 +58,9 @@ typedef enum {
 	SEV_RET_HWSEV_RET_PLATFORM,
 	SEV_RET_HWSEV_RET_UNSAFE,
 	SEV_RET_UNSUPPORTED,
+	SEV_RET_INVALID_PARAM,
+	SEV_RET_RESOURCE_LIMIT,
+	SEV_RET_SECURE_DATA_INVALID,
 	SEV_RET_MAX,
 } sev_ret_code;
 
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 25b4fa00bad1..4a0217832464 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -33,31 +33,48 @@
 #define CLONE_NEWNET		0x40000000	/* New network namespace */
 #define CLONE_IO		0x80000000	/* Clone io context */
 
+/* Flags for the clone3() syscall. */
+#define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
+
 #ifndef __ASSEMBLY__
 /**
  * struct clone_args - arguments for the clone3 syscall
- * @flags:       Flags for the new process as listed above.
- *               All flags are valid except for CSIGNAL and
- *               CLONE_DETACHED.
- * @pidfd:       If CLONE_PIDFD is set, a pidfd will be
- *               returned in this argument.
- * @child_tid:   If CLONE_CHILD_SETTID is set, the TID of the
- *               child process will be returned in the child's
- *               memory.
- * @parent_tid:  If CLONE_PARENT_SETTID is set, the TID of
- *               the child process will be returned in the
- *               parent's memory.
- * @exit_signal: The exit_signal the parent process will be
- *               sent when the child exits.
- * @stack:       Specify the location of the stack for the
- *               child process.
- *               Note, @stack is expected to point to the
- *               lowest address. The stack direction will be
- *               determined by the kernel and set up
- *               appropriately based on @stack_size.
- * @stack_size:  The size of the stack for the child process.
- * @tls:         If CLONE_SETTLS is set, the tls descriptor
- *               is set to tls.
+ * @flags:        Flags for the new process as listed above.
+ *                All flags are valid except for CSIGNAL and
+ *                CLONE_DETACHED.
+ * @pidfd:        If CLONE_PIDFD is set, a pidfd will be
+ *                returned in this argument.
+ * @child_tid:    If CLONE_CHILD_SETTID is set, the TID of the
+ *                child process will be returned in the child's
+ *                memory.
+ * @parent_tid:   If CLONE_PARENT_SETTID is set, the TID of
+ *                the child process will be returned in the
+ *                parent's memory.
+ * @exit_signal:  The exit_signal the parent process will be
+ *                sent when the child exits.
+ * @stack:        Specify the location of the stack for the
+ *                child process.
+ *                Note, @stack is expected to point to the
+ *                lowest address. The stack direction will be
+ *                determined by the kernel and set up
+ *                appropriately based on @stack_size.
+ * @stack_size:   The size of the stack for the child process.
+ * @tls:          If CLONE_SETTLS is set, the tls descriptor
+ *                is set to tls.
+ * @set_tid:      Pointer to an array of type *pid_t. The size
+ *                of the array is defined using @set_tid_size.
+ *                This array is used to select PIDs/TIDs for
+ *                newly created processes. The first element in
+ *                this defines the PID in the most nested PID
+ *                namespace. Each additional element in the array
+ *                defines the PID in the parent PID namespace of
+ *                the original PID namespace. If the array has
+ *                less entries than the number of currently
+ *                nested PID namespaces only the PIDs in the
+ *                corresponding namespaces are set.
+ * @set_tid_size: This defines the size of the array referenced
+ *                in @set_tid. This cannot be larger than the
+ *                kernel's limit of nested PID namespaces.
  *
  * The structure is versioned by size and thus extensible.
  * New struct members must go at the end of the struct and
@@ -72,10 +89,13 @@ struct clone_args {
 	__aligned_u64 stack;
 	__aligned_u64 stack_size;
 	__aligned_u64 tls;
+	__aligned_u64 set_tid;
+	__aligned_u64 set_tid_size;
 };
 #endif
 
 #define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
+#define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */
 
 /*
  * Scheduling policies
diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h
index c6d035fa1b6c..6f5af1a84213 100644
--- a/include/uapi/linux/sed-opal.h
+++ b/include/uapi/linux/sed-opal.h
@@ -113,6 +113,25 @@ struct opal_shadow_mbr {
 	__u64 size;
 };
 
+/* Opal table operations */
+enum opal_table_ops {
+	OPAL_READ_TABLE,
+	OPAL_WRITE_TABLE,
+};
+
+#define OPAL_UID_LENGTH 8
+struct opal_read_write_table {
+	struct opal_key key;
+	const __u64 data;
+	const __u8 table_uid[OPAL_UID_LENGTH];
+	__u64 offset;
+	__u64 size;
+#define OPAL_TABLE_READ (1 << OPAL_READ_TABLE)
+#define OPAL_TABLE_WRITE (1 << OPAL_WRITE_TABLE)
+	__u64 flags;
+	__u64 priv;
+};
+
 #define IOC_OPAL_SAVE		    _IOW('p', 220, struct opal_lock_unlock)
 #define IOC_OPAL_LOCK_UNLOCK	    _IOW('p', 221, struct opal_lock_unlock)
 #define IOC_OPAL_TAKE_OWNERSHIP	    _IOW('p', 222, struct opal_key)
@@ -128,5 +147,6 @@ struct opal_shadow_mbr {
 #define IOC_OPAL_PSID_REVERT_TPR    _IOW('p', 232, struct opal_key)
 #define IOC_OPAL_MBR_DONE           _IOW('p', 233, struct opal_mbr_done)
 #define IOC_OPAL_WRITE_SHADOW_MBR   _IOW('p', 234, struct opal_shadow_mbr)
+#define IOC_OPAL_GENERIC_TABLE_RW   _IOW('p', 235, struct opal_read_write_table)
 
 #endif /* _UAPI_SED_OPAL_H */
diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h
index 7b35e98d3c58..ad80a5c885d5 100644
--- a/include/uapi/linux/stat.h
+++ b/include/uapi/linux/stat.h
@@ -167,8 +167,8 @@ struct statx {
 #define STATX_ATTR_APPEND		0x00000020 /* [I] File is append-only */
 #define STATX_ATTR_NODUMP		0x00000040 /* [I] File is not to be dumped */
 #define STATX_ATTR_ENCRYPTED		0x00000800 /* [I] File requires key to decrypt in fs */
-
 #define STATX_ATTR_AUTOMOUNT		0x00001000 /* Dir: Automount trigger */
+#define STATX_ATTR_VERITY		0x00100000 /* [I] Verity protected file */
 
 
 #endif /* _UAPI_LINUX_STAT_H */
diff --git a/include/xen/interface/xen-mca.h b/include/xen/interface/xen-mca.h
index 73a4ea714d93..7483a78d2425 100644
--- a/include/xen/interface/xen-mca.h
+++ b/include/xen/interface/xen-mca.h
@@ -183,7 +183,6 @@ struct mc_info {
 DEFINE_GUEST_HANDLE_STRUCT(mc_info);
 
 #define __MC_MSR_ARRAYSIZE 8
-#define __MC_MSR_MCGCAP 0
 #define __MC_NMSRS 1
 #define MC_NCAPS 7
 struct mcinfo_logical_cpu {
@@ -332,7 +331,11 @@ struct xen_mc {
 };
 DEFINE_GUEST_HANDLE_STRUCT(xen_mc);
 
-/* Fields are zero when not available */
+/*
+ * Fields are zero when not available. Also, this struct is shared with
+ * userspace mcelog and thus must keep existing fields at current offsets.
+ * Only add new fields to the end of the structure
+ */
 struct xen_mce {
 	__u64 status;
 	__u64 misc;
@@ -353,6 +356,9 @@ struct xen_mce {
 	__u32 socketid;	/* CPU socket ID */
 	__u32 apicid;	/* CPU initial apic ID */
 	__u64 mcgcap;	/* MCGCAP MSR: machine check capabilities of CPU */
+	__u64 synd;	/* MCA_SYND MSR: only valid on SMCA systems */
+	__u64 ipid;	/* MCA_IPID MSR: only valid on SMCA systems */
+	__u64 ppin;	/* Protected Processor Inventory Number */
 };
 
 /*
diff --git a/init/Kconfig b/init/Kconfig
index b4daad2bac23..67a602ee17f1 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -785,6 +785,10 @@ config ARCH_SUPPORTS_NUMA_BALANCING
 config ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 	bool
 
+config CC_HAS_INT128
+	def_bool y
+	depends on !$(cc-option,-D__SIZEOF_INT128__=0)
+
 #
 # For architectures that know their GCC __int128 support is sound
 #
@@ -1548,6 +1552,7 @@ config AIO
 config IO_URING
 	bool "Enable IO uring support" if EXPERT
 	select ANON_INODES
+	select IO_WQ
 	default y
 	help
 	  This option enables support for the io_uring interface, enabling
diff --git a/init/initramfs.c b/init/initramfs.c
index c47dad0884f7..8ec1be4d7d51 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -10,6 +10,7 @@
 #include <linux/syscalls.h>
 #include <linux/utime.h>
 #include <linux/file.h>
+#include <linux/memblock.h>
 
 static ssize_t __init xwrite(int fd, const char *p, size_t count)
 {
@@ -529,6 +530,13 @@ extern unsigned long __initramfs_size;
 
 void __weak free_initrd_mem(unsigned long start, unsigned long end)
 {
+#ifdef CONFIG_ARCH_KEEP_MEMBLOCK
+	unsigned long aligned_start = ALIGN_DOWN(start, PAGE_SIZE);
+	unsigned long aligned_end = ALIGN(end, PAGE_SIZE);
+
+	memblock_free(__pa(aligned_start), aligned_end - aligned_start);
+#endif
+
 	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
 			"initrd");
 }
diff --git a/kernel/Makefile b/kernel/Makefile
index daad787fb795..f0902a7bd1b3 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -115,6 +115,8 @@ obj-$(CONFIG_TORTURE_TEST) += torture.o
 obj-$(CONFIG_HAS_IOMEM) += iomem.o
 obj-$(CONFIG_RSEQ) += rseq.o
 
+obj-$(CONFIG_SYSCTL_KUNIT_TEST) += sysctl-test.o
+
 obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o
 KASAN_SANITIZE_stackleak.o := n
 KCOV_INSTRUMENT_stackleak.o := n
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 5e28718928ca..cada974c9f4e 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -317,7 +317,7 @@ BPF_CALL_0(bpf_get_current_cgroup_id)
 {
 	struct cgroup *cgrp = task_dfl_cgroup(current);
 
-	return cgrp->kn->id.id;
+	return cgroup_id(cgrp);
 }
 
 const struct bpf_func_proto bpf_get_current_cgroup_id_proto = {
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index addd6fdceec8..2ba750725cb2 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -569,7 +569,7 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
 		return;
 
 	storage->key.attach_type = type;
-	storage->key.cgroup_inode_id = cgroup->kn->id.id;
+	storage->key.cgroup_inode_id = cgroup_id(cgroup);
 
 	map = storage->map;
 
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 809e34a3c017..90d1710fef6c 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -231,9 +231,10 @@ int cgroup_migrate(struct task_struct *leader, bool threadgroup,
 
 int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
 		       bool threadgroup);
-struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup)
+struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
+					     bool *locked)
 	__acquires(&cgroup_threadgroup_rwsem);
-void cgroup_procs_write_finish(struct task_struct *task)
+void cgroup_procs_write_finish(struct task_struct *task, bool locked)
 	__releases(&cgroup_threadgroup_rwsem);
 
 void cgroup_lock_and_drain_offline(struct cgroup *cgrp);
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 7f83f4121d8d..09f3a413f6f8 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -495,12 +495,13 @@ static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of,
 	struct task_struct *task;
 	const struct cred *cred, *tcred;
 	ssize_t ret;
+	bool locked;
 
 	cgrp = cgroup_kn_lock_live(of->kn, false);
 	if (!cgrp)
 		return -ENODEV;
 
-	task = cgroup_procs_write_start(buf, threadgroup);
+	task = cgroup_procs_write_start(buf, threadgroup, &locked);
 	ret = PTR_ERR_OR_ZERO(task);
 	if (ret)
 		goto out_unlock;
@@ -522,7 +523,7 @@ static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of,
 	ret = cgroup_attach_task(cgrp, task, threadgroup);
 
 out_finish:
-	cgroup_procs_write_finish(task);
+	cgroup_procs_write_finish(task, locked);
 out_unlock:
 	cgroup_kn_unlock(of->kn);
 
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index ef4242e5d4bc..735af8f15f95 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -899,8 +899,7 @@ static void css_set_move_task(struct task_struct *task,
 		/*
 		 * We are synchronized through cgroup_threadgroup_rwsem
 		 * against PF_EXITING setting such that we can't race
-		 * against cgroup_exit() changing the css_set to
-		 * init_css_set and dropping the old one.
+		 * against cgroup_exit()/cgroup_free() dropping the css_set.
 		 */
 		WARN_ON_ONCE(task->flags & PF_EXITING);
 
@@ -1309,10 +1308,7 @@ static void cgroup_exit_root_id(struct cgroup_root *root)
 
 void cgroup_free_root(struct cgroup_root *root)
 {
-	if (root) {
-		idr_destroy(&root->cgroup_idr);
-		kfree(root);
-	}
+	kfree(root);
 }
 
 static void cgroup_destroy_root(struct cgroup_root *root)
@@ -1374,6 +1370,8 @@ current_cgns_cgroup_from_root(struct cgroup_root *root)
 	cset = current->nsproxy->cgroup_ns->root_cset;
 	if (cset == &init_css_set) {
 		res = &root->cgrp;
+	} else if (root == &cgrp_dfl_root) {
+		res = cset->dfl_cgrp;
 	} else {
 		struct cgrp_cset_link *link;
 
@@ -1430,9 +1428,8 @@ struct cgroup *task_cgroup_from_root(struct task_struct *task,
 				     struct cgroup_root *root)
 {
 	/*
-	 * No need to lock the task - since we hold cgroup_mutex the
-	 * task can't change groups, so the only thing that can happen
-	 * is that it exits and its css is set back to init_css_set.
+	 * No need to lock the task - since we hold css_set_lock the
+	 * task can't change groups.
 	 */
 	return cset_cgroup_from_root(task_css_set(task), root);
 }
@@ -1883,65 +1880,6 @@ static int cgroup_reconfigure(struct fs_context *fc)
 	return 0;
 }
 
-/*
- * To reduce the fork() overhead for systems that are not actually using
- * their cgroups capability, we don't maintain the lists running through
- * each css_set to its tasks until we see the list actually used - in other
- * words after the first mount.
- */
-static bool use_task_css_set_links __read_mostly;
-
-void cgroup_enable_task_cg_lists(void)
-{
-	struct task_struct *p, *g;
-
-	/*
-	 * We need tasklist_lock because RCU is not safe against
-	 * while_each_thread(). Besides, a forking task that has passed
-	 * cgroup_post_fork() without seeing use_task_css_set_links = 1
-	 * is not guaranteed to have its child immediately visible in the
-	 * tasklist if we walk through it with RCU.
-	 */
-	read_lock(&tasklist_lock);
-	spin_lock_irq(&css_set_lock);
-
-	if (use_task_css_set_links)
-		goto out_unlock;
-
-	use_task_css_set_links = true;
-
-	do_each_thread(g, p) {
-		WARN_ON_ONCE(!list_empty(&p->cg_list) ||
-			     task_css_set(p) != &init_css_set);
-
-		/*
-		 * We should check if the process is exiting, otherwise
-		 * it will race with cgroup_exit() in that the list
-		 * entry won't be deleted though the process has exited.
-		 * Do it while holding siglock so that we don't end up
-		 * racing against cgroup_exit().
-		 *
-		 * Interrupts were already disabled while acquiring
-		 * the css_set_lock, so we do not need to disable it
-		 * again when acquiring the sighand->siglock here.
-		 */
-		spin_lock(&p->sighand->siglock);
-		if (!(p->flags & PF_EXITING)) {
-			struct css_set *cset = task_css_set(p);
-
-			if (!css_set_populated(cset))
-				css_set_update_populated(cset, true);
-			list_add_tail(&p->cg_list, &cset->tasks);
-			get_css_set(cset);
-			cset->nr_tasks++;
-		}
-		spin_unlock(&p->sighand->siglock);
-	} while_each_thread(g, p);
-out_unlock:
-	spin_unlock_irq(&css_set_lock);
-	read_unlock(&tasklist_lock);
-}
-
 static void init_cgroup_housekeeping(struct cgroup *cgrp)
 {
 	struct cgroup_subsys *ss;
@@ -1976,7 +1914,6 @@ void init_cgroup_root(struct cgroup_fs_context *ctx)
 	atomic_set(&root->nr_cgrps, 1);
 	cgrp->root = root;
 	init_cgroup_housekeeping(cgrp);
-	idr_init(&root->cgroup_idr);
 
 	root->flags = ctx->flags;
 	if (ctx->release_agent)
@@ -1997,12 +1934,6 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 
 	lockdep_assert_held(&cgroup_mutex);
 
-	ret = cgroup_idr_alloc(&root->cgroup_idr, root_cgrp, 1, 2, GFP_KERNEL);
-	if (ret < 0)
-		goto out;
-	root_cgrp->id = ret;
-	root_cgrp->ancestor_ids[0] = ret;
-
 	ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release,
 			      0, GFP_KERNEL);
 	if (ret)
@@ -2035,6 +1966,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 		goto exit_root_id;
 	}
 	root_cgrp->kn = root->kf_root->kn;
+	WARN_ON_ONCE(cgroup_ino(root_cgrp) != 1);
+	root_cgrp->ancestor_ids[0] = cgroup_id(root_cgrp);
 
 	ret = css_populate_dir(&root_cgrp->self);
 	if (ret)
@@ -2188,13 +2121,6 @@ static int cgroup_init_fs_context(struct fs_context *fc)
 	if (!ctx)
 		return -ENOMEM;
 
-	/*
-	 * The first time anyone tries to mount a cgroup, enable the list
-	 * linking each css_set to its tasks and fix up all existing tasks.
-	 */
-	if (!use_task_css_set_links)
-		cgroup_enable_task_cg_lists();
-
 	ctx->ns = current->nsproxy->cgroup_ns;
 	get_cgroup_ns(ctx->ns);
 	fc->fs_private = &ctx->kfc;
@@ -2372,9 +2298,8 @@ static void cgroup_migrate_add_task(struct task_struct *task,
 	if (task->flags & PF_EXITING)
 		return;
 
-	/* leave @task alone if post_fork() hasn't linked it yet */
-	if (list_empty(&task->cg_list))
-		return;
+	/* cgroup_threadgroup_rwsem protects racing against forks */
+	WARN_ON_ONCE(list_empty(&task->cg_list));
 
 	cset = task_css_set(task);
 	if (!cset->mg_src_cgrp)
@@ -2825,7 +2750,8 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
 	return ret;
 }
 
-struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup)
+struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
+					     bool *locked)
 	__acquires(&cgroup_threadgroup_rwsem)
 {
 	struct task_struct *tsk;
@@ -2834,7 +2760,21 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup)
 	if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
 		return ERR_PTR(-EINVAL);
 
-	percpu_down_write(&cgroup_threadgroup_rwsem);
+	/*
+	 * If we migrate a single thread, we don't care about threadgroup
+	 * stability. If the thread is `current`, it won't exit(2) under our
+	 * hands or change PID through exec(2). We exclude
+	 * cgroup_update_dfl_csses and other cgroup_{proc,thread}s_write
+	 * callers by cgroup_mutex.
+	 * Therefore, we can skip the global lock.
+	 */
+	lockdep_assert_held(&cgroup_mutex);
+	if (pid || threadgroup) {
+		percpu_down_write(&cgroup_threadgroup_rwsem);
+		*locked = true;
+	} else {
+		*locked = false;
+	}
 
 	rcu_read_lock();
 	if (pid) {
@@ -2865,13 +2805,16 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup)
 	goto out_unlock_rcu;
 
 out_unlock_threadgroup:
-	percpu_up_write(&cgroup_threadgroup_rwsem);
+	if (*locked) {
+		percpu_up_write(&cgroup_threadgroup_rwsem);
+		*locked = false;
+	}
 out_unlock_rcu:
 	rcu_read_unlock();
 	return tsk;
 }
 
-void cgroup_procs_write_finish(struct task_struct *task)
+void cgroup_procs_write_finish(struct task_struct *task, bool locked)
 	__releases(&cgroup_threadgroup_rwsem)
 {
 	struct cgroup_subsys *ss;
@@ -2880,7 +2823,8 @@ void cgroup_procs_write_finish(struct task_struct *task)
 	/* release reference from cgroup_procs_write_start() */
 	put_task_struct(task);
 
-	percpu_up_write(&cgroup_threadgroup_rwsem);
+	if (locked)
+		percpu_up_write(&cgroup_threadgroup_rwsem);
 	for_each_subsys(ss, ssid)
 		if (ss->post_attach)
 			ss->post_attach();
@@ -3601,22 +3545,22 @@ static int cpu_stat_show(struct seq_file *seq, void *v)
 #ifdef CONFIG_PSI
 static int cgroup_io_pressure_show(struct seq_file *seq, void *v)
 {
-	struct cgroup *cgroup = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup->id == 1 ? &psi_system : &cgroup->psi;
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi;
 
 	return psi_show(seq, psi, PSI_IO);
 }
 static int cgroup_memory_pressure_show(struct seq_file *seq, void *v)
 {
-	struct cgroup *cgroup = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup->id == 1 ? &psi_system : &cgroup->psi;
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi;
 
 	return psi_show(seq, psi, PSI_MEM);
 }
 static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
 {
-	struct cgroup *cgroup = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup->id == 1 ? &psi_system : &cgroup->psi;
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi;
 
 	return psi_show(seq, psi, PSI_CPU);
 }
@@ -4568,9 +4512,6 @@ repeat:
 void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
 			 struct css_task_iter *it)
 {
-	/* no one should try to iterate before mounting cgroups */
-	WARN_ON_ONCE(!use_task_css_set_links);
-
 	memset(it, 0, sizeof(*it));
 
 	spin_lock_irq(&css_set_lock);
@@ -4755,12 +4696,13 @@ static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
 	struct cgroup *src_cgrp, *dst_cgrp;
 	struct task_struct *task;
 	ssize_t ret;
+	bool locked;
 
 	dst_cgrp = cgroup_kn_lock_live(of->kn, false);
 	if (!dst_cgrp)
 		return -ENODEV;
 
-	task = cgroup_procs_write_start(buf, true);
+	task = cgroup_procs_write_start(buf, true, &locked);
 	ret = PTR_ERR_OR_ZERO(task);
 	if (ret)
 		goto out_unlock;
@@ -4778,7 +4720,7 @@ static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
 	ret = cgroup_attach_task(dst_cgrp, task, true);
 
 out_finish:
-	cgroup_procs_write_finish(task);
+	cgroup_procs_write_finish(task, locked);
 out_unlock:
 	cgroup_kn_unlock(of->kn);
 
@@ -4796,6 +4738,7 @@ static ssize_t cgroup_threads_write(struct kernfs_open_file *of,
 	struct cgroup *src_cgrp, *dst_cgrp;
 	struct task_struct *task;
 	ssize_t ret;
+	bool locked;
 
 	buf = strstrip(buf);
 
@@ -4803,7 +4746,7 @@ static ssize_t cgroup_threads_write(struct kernfs_open_file *of,
 	if (!dst_cgrp)
 		return -ENODEV;
 
-	task = cgroup_procs_write_start(buf, false);
+	task = cgroup_procs_write_start(buf, false, &locked);
 	ret = PTR_ERR_OR_ZERO(task);
 	if (ret)
 		goto out_unlock;
@@ -4827,7 +4770,7 @@ static ssize_t cgroup_threads_write(struct kernfs_open_file *of,
 	ret = cgroup_attach_task(dst_cgrp, task, false);
 
 out_finish:
-	cgroup_procs_write_finish(task);
+	cgroup_procs_write_finish(task, locked);
 out_unlock:
 	cgroup_kn_unlock(of->kn);
 
@@ -5037,9 +4980,6 @@ static void css_release_work_fn(struct work_struct *work)
 			tcgrp->nr_dying_descendants--;
 		spin_unlock_irq(&css_set_lock);
 
-		cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
-		cgrp->id = -1;
-
 		/*
 		 * There are two control paths which try to determine
 		 * cgroup from dentry without going through kernfs -
@@ -5204,10 +5144,12 @@ err_free_css:
  * it isn't associated with its kernfs_node and doesn't have the control
  * mask applied.
  */
-static struct cgroup *cgroup_create(struct cgroup *parent)
+static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
+				    umode_t mode)
 {
 	struct cgroup_root *root = parent->root;
 	struct cgroup *cgrp, *tcgrp;
+	struct kernfs_node *kn;
 	int level = parent->level + 1;
 	int ret;
 
@@ -5227,15 +5169,13 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 			goto out_cancel_ref;
 	}
 
-	/*
-	 * Temporarily set the pointer to NULL, so idr_find() won't return
-	 * a half-baked cgroup.
-	 */
-	cgrp->id = cgroup_idr_alloc(&root->cgroup_idr, NULL, 2, 0, GFP_KERNEL);
-	if (cgrp->id < 0) {
-		ret = -ENOMEM;
+	/* create the directory */
+	kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
+	if (IS_ERR(kn)) {
+		ret = PTR_ERR(kn);
 		goto out_stat_exit;
 	}
+	cgrp->kn = kn;
 
 	init_cgroup_housekeeping(cgrp);
 
@@ -5245,7 +5185,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 
 	ret = psi_cgroup_alloc(cgrp);
 	if (ret)
-		goto out_idr_free;
+		goto out_kernfs_remove;
 
 	ret = cgroup_bpf_inherit(cgrp);
 	if (ret)
@@ -5269,7 +5209,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 
 	spin_lock_irq(&css_set_lock);
 	for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
-		cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;
+		cgrp->ancestor_ids[tcgrp->level] = cgroup_id(tcgrp);
 
 		if (tcgrp != cgrp) {
 			tcgrp->nr_descendants++;
@@ -5299,12 +5239,6 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 	cgroup_get_live(parent);
 
 	/*
-	 * @cgrp is now fully operational.  If something fails after this
-	 * point, it'll be released via the normal destruction path.
-	 */
-	cgroup_idr_replace(&root->cgroup_idr, cgrp, cgrp->id);
-
-	/*
 	 * On the default hierarchy, a child doesn't automatically inherit
 	 * subtree_control from the parent.  Each is configured manually.
 	 */
@@ -5317,8 +5251,8 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 
 out_psi_free:
 	psi_cgroup_free(cgrp);
-out_idr_free:
-	cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
+out_kernfs_remove:
+	kernfs_remove(cgrp->kn);
 out_stat_exit:
 	if (cgroup_on_dfl(parent))
 		cgroup_rstat_exit(cgrp);
@@ -5355,7 +5289,6 @@ fail:
 int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode)
 {
 	struct cgroup *parent, *cgrp;
-	struct kernfs_node *kn;
 	int ret;
 
 	/* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */
@@ -5371,27 +5304,19 @@ int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode)
 		goto out_unlock;
 	}
 
-	cgrp = cgroup_create(parent);
+	cgrp = cgroup_create(parent, name, mode);
 	if (IS_ERR(cgrp)) {
 		ret = PTR_ERR(cgrp);
 		goto out_unlock;
 	}
 
-	/* create the directory */
-	kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
-	if (IS_ERR(kn)) {
-		ret = PTR_ERR(kn);
-		goto out_destroy;
-	}
-	cgrp->kn = kn;
-
 	/*
 	 * This extra ref will be put in cgroup_free_fn() and guarantees
 	 * that @cgrp->kn is always accessible.
 	 */
-	kernfs_get(kn);
+	kernfs_get(cgrp->kn);
 
-	ret = cgroup_kn_set_ugid(kn);
+	ret = cgroup_kn_set_ugid(cgrp->kn);
 	if (ret)
 		goto out_destroy;
 
@@ -5406,7 +5331,7 @@ int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode)
 	TRACE_CGROUP_PATH(mkdir, cgrp);
 
 	/* let's create and online css's */
-	kernfs_activate(kn);
+	kernfs_activate(cgrp->kn);
 
 	ret = 0;
 	goto out_unlock;
@@ -5836,12 +5761,11 @@ static int __init cgroup_wq_init(void)
 }
 core_initcall(cgroup_wq_init);
 
-void cgroup_path_from_kernfs_id(const union kernfs_node_id *id,
-					char *buf, size_t buflen)
+void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen)
 {
 	struct kernfs_node *kn;
 
-	kn = kernfs_get_node_by_id(cgrp_dfl_root.kf_root, id);
+	kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id);
 	if (!kn)
 		return;
 	kernfs_path(kn, buf, buflen);
@@ -6002,62 +5926,38 @@ void cgroup_cancel_fork(struct task_struct *child)
 void cgroup_post_fork(struct task_struct *child)
 {
 	struct cgroup_subsys *ss;
+	struct css_set *cset;
 	int i;
 
+	spin_lock_irq(&css_set_lock);
+
+	WARN_ON_ONCE(!list_empty(&child->cg_list));
+	cset = task_css_set(current); /* current is @child's parent */
+	get_css_set(cset);
+	cset->nr_tasks++;
+	css_set_move_task(child, NULL, cset, false);
+
 	/*
-	 * This may race against cgroup_enable_task_cg_lists().  As that
-	 * function sets use_task_css_set_links before grabbing
-	 * tasklist_lock and we just went through tasklist_lock to add
-	 * @child, it's guaranteed that either we see the set
-	 * use_task_css_set_links or cgroup_enable_task_cg_lists() sees
-	 * @child during its iteration.
-	 *
-	 * If we won the race, @child is associated with %current's
-	 * css_set.  Grabbing css_set_lock guarantees both that the
-	 * association is stable, and, on completion of the parent's
-	 * migration, @child is visible in the source of migration or
-	 * already in the destination cgroup.  This guarantee is necessary
-	 * when implementing operations which need to migrate all tasks of
-	 * a cgroup to another.
-	 *
-	 * Note that if we lose to cgroup_enable_task_cg_lists(), @child
-	 * will remain in init_css_set.  This is safe because all tasks are
-	 * in the init_css_set before cg_links is enabled and there's no
-	 * operation which transfers all tasks out of init_css_set.
+	 * If the cgroup has to be frozen, the new task has too.  Let's set
+	 * the JOBCTL_TRAP_FREEZE jobctl bit to get the task into the
+	 * frozen state.
 	 */
-	if (use_task_css_set_links) {
-		struct css_set *cset;
-
-		spin_lock_irq(&css_set_lock);
-		cset = task_css_set(current);
-		if (list_empty(&child->cg_list)) {
-			get_css_set(cset);
-			cset->nr_tasks++;
-			css_set_move_task(child, NULL, cset, false);
-		}
+	if (unlikely(cgroup_task_freeze(child))) {
+		spin_lock(&child->sighand->siglock);
+		WARN_ON_ONCE(child->frozen);
+		child->jobctl |= JOBCTL_TRAP_FREEZE;
+		spin_unlock(&child->sighand->siglock);
 
 		/*
-		 * If the cgroup has to be frozen, the new task has too.
-		 * Let's set the JOBCTL_TRAP_FREEZE jobctl bit to get
-		 * the task into the frozen state.
+		 * Calling cgroup_update_frozen() isn't required here,
+		 * because it will be called anyway a bit later from
+		 * do_freezer_trap(). So we avoid cgroup's transient switch
+		 * from the frozen state and back.
 		 */
-		if (unlikely(cgroup_task_freeze(child))) {
-			spin_lock(&child->sighand->siglock);
-			WARN_ON_ONCE(child->frozen);
-			child->jobctl |= JOBCTL_TRAP_FREEZE;
-			spin_unlock(&child->sighand->siglock);
-
-			/*
-			 * Calling cgroup_update_frozen() isn't required here,
-			 * because it will be called anyway a bit later
-			 * from do_freezer_trap(). So we avoid cgroup's
-			 * transient switch from the frozen state and back.
-			 */
-		}
-
-		spin_unlock_irq(&css_set_lock);
 	}
 
+	spin_unlock_irq(&css_set_lock);
+
 	/*
 	 * Call ss->fork().  This must happen after @child is linked on
 	 * css_set; otherwise, @child might change state between ->fork()
@@ -6072,20 +5972,8 @@ void cgroup_post_fork(struct task_struct *child)
  * cgroup_exit - detach cgroup from exiting task
  * @tsk: pointer to task_struct of exiting process
  *
- * Description: Detach cgroup from @tsk and release it.
+ * Description: Detach cgroup from @tsk.
  *
- * Note that cgroups marked notify_on_release force every task in
- * them to take the global cgroup_mutex mutex when exiting.
- * This could impact scaling on very large systems.  Be reluctant to
- * use notify_on_release cgroups where very high task exit scaling
- * is required on large systems.
- *
- * We set the exiting tasks cgroup to the root cgroup (top_cgroup).  We
- * call cgroup_exit() while the task is still competent to handle
- * notify_on_release(), then leave the task attached to the root cgroup in
- * each hierarchy for the remainder of its exit.  No need to bother with
- * init_css_set refcnting.  init_css_set never goes away and we can't race
- * with migration path - PF_EXITING is visible to migration path.
  */
 void cgroup_exit(struct task_struct *tsk)
 {
@@ -6093,26 +5981,19 @@ void cgroup_exit(struct task_struct *tsk)
 	struct css_set *cset;
 	int i;
 
-	/*
-	 * Unlink from @tsk from its css_set.  As migration path can't race
-	 * with us, we can check css_set and cg_list without synchronization.
-	 */
-	cset = task_css_set(tsk);
+	spin_lock_irq(&css_set_lock);
 
-	if (!list_empty(&tsk->cg_list)) {
-		spin_lock_irq(&css_set_lock);
-		css_set_move_task(tsk, cset, NULL, false);
-		list_add_tail(&tsk->cg_list, &cset->dying_tasks);
-		cset->nr_tasks--;
+	WARN_ON_ONCE(list_empty(&tsk->cg_list));
+	cset = task_css_set(tsk);
+	css_set_move_task(tsk, cset, NULL, false);
+	list_add_tail(&tsk->cg_list, &cset->dying_tasks);
+	cset->nr_tasks--;
 
-		WARN_ON_ONCE(cgroup_task_frozen(tsk));
-		if (unlikely(cgroup_task_freeze(tsk)))
-			cgroup_update_frozen(task_dfl_cgroup(tsk));
+	WARN_ON_ONCE(cgroup_task_frozen(tsk));
+	if (unlikely(cgroup_task_freeze(tsk)))
+		cgroup_update_frozen(task_dfl_cgroup(tsk));
 
-		spin_unlock_irq(&css_set_lock);
-	} else {
-		get_css_set(cset);
-	}
+	spin_unlock_irq(&css_set_lock);
 
 	/* see cgroup_post_fork() for details */
 	do_each_subsys_mask(ss, i, have_exit_callback) {
@@ -6129,12 +6010,10 @@ void cgroup_release(struct task_struct *task)
 		ss->release(task);
 	} while_each_subsys_mask();
 
-	if (use_task_css_set_links) {
-		spin_lock_irq(&css_set_lock);
-		css_set_skip_task_iters(task_css_set(task), task);
-		list_del_init(&task->cg_list);
-		spin_unlock_irq(&css_set_lock);
-	}
+	spin_lock_irq(&css_set_lock);
+	css_set_skip_task_iters(task_css_set(task), task);
+	list_del_init(&task->cg_list);
+	spin_unlock_irq(&css_set_lock);
 }
 
 void cgroup_free(struct task_struct *task)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index c87ee6412b36..58f5073acff7 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -929,8 +929,6 @@ static void rebuild_root_domains(void)
 	lockdep_assert_cpus_held();
 	lockdep_assert_held(&sched_domains_mutex);
 
-	cgroup_enable_task_cg_lists();
-
 	rcu_read_lock();
 
 	/*
diff --git a/kernel/cgroup/freezer.c b/kernel/cgroup/freezer.c
index 8cf010680678..3984dd6b8ddb 100644
--- a/kernel/cgroup/freezer.c
+++ b/kernel/cgroup/freezer.c
@@ -231,6 +231,15 @@ void cgroup_freezer_migrate_task(struct task_struct *task,
 		return;
 
 	/*
+	 * It's not necessary to do changes if both of the src and dst cgroups
+	 * are not freezing and task is not frozen.
+	 */
+	if (!test_bit(CGRP_FREEZE, &src->flags) &&
+	    !test_bit(CGRP_FREEZE, &dst->flags) &&
+	    !task->frozen)
+		return;
+
+	/*
 	 * Adjust counters of freezing and frozen tasks.
 	 * Note, that if the task is frozen, but the destination cgroup is not
 	 * frozen, we bump both counters to keep them balanced.
diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c
index 8e513a573fe9..138059eb730d 100644
--- a/kernel/cgroup/pids.c
+++ b/kernel/cgroup/pids.c
@@ -45,7 +45,7 @@ struct pids_cgroup {
 	 * %PIDS_MAX = (%PID_MAX_LIMIT + 1).
 	 */
 	atomic64_t			counter;
-	int64_t				limit;
+	atomic64_t			limit;
 
 	/* Handle for "pids.events" */
 	struct cgroup_file		events_file;
@@ -73,8 +73,8 @@ pids_css_alloc(struct cgroup_subsys_state *parent)
 	if (!pids)
 		return ERR_PTR(-ENOMEM);
 
-	pids->limit = PIDS_MAX;
 	atomic64_set(&pids->counter, 0);
+	atomic64_set(&pids->limit, PIDS_MAX);
 	atomic64_set(&pids->events_limit, 0);
 	return &pids->css;
 }
@@ -146,13 +146,14 @@ static int pids_try_charge(struct pids_cgroup *pids, int num)
 
 	for (p = pids; parent_pids(p); p = parent_pids(p)) {
 		int64_t new = atomic64_add_return(num, &p->counter);
+		int64_t limit = atomic64_read(&p->limit);
 
 		/*
 		 * Since new is capped to the maximum number of pid_t, if
 		 * p->limit is %PIDS_MAX then we know that this test will never
 		 * fail.
 		 */
-		if (new > p->limit)
+		if (new > limit)
 			goto revert;
 	}
 
@@ -277,7 +278,7 @@ set_limit:
 	 * Limit updates don't need to be mutex'd, since it isn't
 	 * critical that any racing fork()s follow the new limit.
 	 */
-	pids->limit = limit;
+	atomic64_set(&pids->limit, limit);
 	return nbytes;
 }
 
@@ -285,7 +286,7 @@ static int pids_max_show(struct seq_file *sf, void *v)
 {
 	struct cgroup_subsys_state *css = seq_css(sf);
 	struct pids_cgroup *pids = css_pids(css);
-	int64_t limit = pids->limit;
+	int64_t limit = atomic64_read(&pids->limit);
 
 	if (limit >= PIDS_MAX)
 		seq_printf(sf, "%s\n", PIDS_MAX_STR);
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index ca19b4c8acf5..b48b22d4deb6 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -304,44 +304,48 @@ void __init cgroup_rstat_boot(void)
  * Functions for cgroup basic resource statistics implemented on top of
  * rstat.
  */
-static void cgroup_base_stat_accumulate(struct cgroup_base_stat *dst_bstat,
-					struct cgroup_base_stat *src_bstat)
+static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat,
+				 struct cgroup_base_stat *src_bstat)
 {
 	dst_bstat->cputime.utime += src_bstat->cputime.utime;
 	dst_bstat->cputime.stime += src_bstat->cputime.stime;
 	dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime;
 }
 
+static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat,
+				 struct cgroup_base_stat *src_bstat)
+{
+	dst_bstat->cputime.utime -= src_bstat->cputime.utime;
+	dst_bstat->cputime.stime -= src_bstat->cputime.stime;
+	dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime;
+}
+
 static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
 {
 	struct cgroup *parent = cgroup_parent(cgrp);
 	struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
-	struct task_cputime *last_cputime = &rstatc->last_bstat.cputime;
-	struct task_cputime cputime;
-	struct cgroup_base_stat delta;
+	struct cgroup_base_stat cur, delta;
 	unsigned seq;
 
 	/* fetch the current per-cpu values */
 	do {
 		seq = __u64_stats_fetch_begin(&rstatc->bsync);
-		cputime = rstatc->bstat.cputime;
+		cur.cputime = rstatc->bstat.cputime;
 	} while (__u64_stats_fetch_retry(&rstatc->bsync, seq));
 
-	/* calculate the delta to propgate */
-	delta.cputime.utime = cputime.utime - last_cputime->utime;
-	delta.cputime.stime = cputime.stime - last_cputime->stime;
-	delta.cputime.sum_exec_runtime = cputime.sum_exec_runtime -
-					 last_cputime->sum_exec_runtime;
-	*last_cputime = cputime;
-
-	/* transfer the pending stat into delta */
-	cgroup_base_stat_accumulate(&delta, &cgrp->pending_bstat);
-	memset(&cgrp->pending_bstat, 0, sizeof(cgrp->pending_bstat));
-
-	/* propagate delta into the global stat and the parent's pending */
-	cgroup_base_stat_accumulate(&cgrp->bstat, &delta);
-	if (parent)
-		cgroup_base_stat_accumulate(&parent->pending_bstat, &delta);
+	/* propagate percpu delta to global */
+	delta = cur;
+	cgroup_base_stat_sub(&delta, &rstatc->last_bstat);
+	cgroup_base_stat_add(&cgrp->bstat, &delta);
+	cgroup_base_stat_add(&rstatc->last_bstat, &delta);
+
+	/* propagate global delta to parent */
+	if (parent) {
+		delta = cgrp->bstat;
+		cgroup_base_stat_sub(&delta, &cgrp->last_bstat);
+		cgroup_base_stat_add(&parent->bstat, &delta);
+		cgroup_base_stat_add(&cgrp->last_bstat, &delta);
+	}
 }
 
 static struct cgroup_rstat_cpu *
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 099002d84f46..a26170469543 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -161,7 +161,7 @@ static inline void dump_entry_trace(struct dma_debug_entry *entry)
 {
 #ifdef CONFIG_STACKTRACE
 	if (entry) {
-		pr_warning("Mapped at:\n");
+		pr_warn("Mapped at:\n");
 		stack_trace_print(entry->stack_entries, entry->stack_len, 0);
 	}
 #endif
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 8402b29c280f..0b67c04e531b 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -16,12 +16,11 @@
 #include <linux/swiotlb.h>
 
 /*
- * Most architectures use ZONE_DMA for the first 16 Megabytes, but
- * some use it for entirely different regions:
+ * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
+ * it for entirely different regions. In that case the arch code needs to
+ * override the variable below for dma-direct to work properly.
  */
-#ifndef ARCH_ZONE_DMA_BITS
-#define ARCH_ZONE_DMA_BITS 24
-#endif
+unsigned int zone_dma_bits __ro_after_init = 24;
 
 static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size)
 {
@@ -69,7 +68,7 @@ static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 	 * Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding
 	 * zones.
 	 */
-	if (*phys_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))
+	if (*phys_mask <= DMA_BIT_MASK(zone_dma_bits))
 		return GFP_DMA;
 	if (*phys_mask <= DMA_BIT_MASK(32))
 		return GFP_DMA32;
@@ -395,7 +394,7 @@ int dma_direct_supported(struct device *dev, u64 mask)
 	u64 min_mask;
 
 	if (IS_ENABLED(CONFIG_ZONE_DMA))
-		min_mask = DMA_BIT_MASK(ARCH_ZONE_DMA_BITS);
+		min_mask = DMA_BIT_MASK(zone_dma_bits);
 	else
 		min_mask = DMA_BIT_MASK(32);
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 834640057c93..5de0b801bc7b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5029,6 +5029,24 @@ static void _perf_event_reset(struct perf_event *event)
 	perf_event_update_userpage(event);
 }
 
+/* Assume it's not an event with inherit set. */
+u64 perf_event_pause(struct perf_event *event, bool reset)
+{
+	struct perf_event_context *ctx;
+	u64 count;
+
+	ctx = perf_event_ctx_lock(event);
+	WARN_ON_ONCE(event->attr.inherit);
+	_perf_event_disable(event);
+	count = local64_read(&event->count);
+	if (reset)
+		local64_set(&event->count, 0);
+	perf_event_ctx_unlock(event, ctx);
+
+	return count;
+}
+EXPORT_SYMBOL_GPL(perf_event_pause);
+
 /*
  * Holding the top-level event's child_mutex means that any
  * descendant process that has inherited this event will block
@@ -5106,16 +5124,11 @@ static int perf_event_check_period(struct perf_event *event, u64 value)
 	return event->pmu->check_period(event, value);
 }
 
-static int perf_event_period(struct perf_event *event, u64 __user *arg)
+static int _perf_event_period(struct perf_event *event, u64 value)
 {
-	u64 value;
-
 	if (!is_sampling_event(event))
 		return -EINVAL;
 
-	if (copy_from_user(&value, arg, sizeof(value)))
-		return -EFAULT;
-
 	if (!value)
 		return -EINVAL;
 
@@ -5133,6 +5146,19 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 	return 0;
 }
 
+int perf_event_period(struct perf_event *event, u64 value)
+{
+	struct perf_event_context *ctx;
+	int ret;
+
+	ctx = perf_event_ctx_lock(event);
+	ret = _perf_event_period(event, value);
+	perf_event_ctx_unlock(event, ctx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(perf_event_period);
+
 static const struct file_operations perf_fops;
 
 static inline int perf_fget_light(int fd, struct fd *p)
@@ -5176,8 +5202,14 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon
 		return _perf_event_refresh(event, arg);
 
 	case PERF_EVENT_IOC_PERIOD:
-		return perf_event_period(event, (u64 __user *)arg);
+	{
+		u64 value;
 
+		if (copy_from_user(&value, (u64 __user *)arg, sizeof(value)))
+			return -EFAULT;
+
+		return _perf_event_period(event, value);
+	}
 	case PERF_EVENT_IOC_ID:
 	{
 		u64 id = primary_event_id(event);
diff --git a/kernel/exit.c b/kernel/exit.c
index a46a50d67002..f2d20ab74422 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1457,7 +1457,7 @@ repeat:
 	 */
 	wo->notask_error = -ECHILD;
 	if ((wo->wo_type < PIDTYPE_MAX) &&
-	   (!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type])))
+	   (!wo->wo_pid || !pid_has_task(wo->wo_pid, wo->wo_type)))
 		goto notask;
 
 	set_current_state(TASK_INTERRUPTIBLE);
diff --git a/kernel/fork.c b/kernel/fork.c
index 13b38794efb5..35f91ee91057 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1517,6 +1517,11 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
 	spin_lock_irq(&current->sighand->siglock);
 	memcpy(sig->action, current->sighand->action, sizeof(sig->action));
 	spin_unlock_irq(&current->sighand->siglock);
+
+	/* Reset all signal handler not set to SIG_IGN to SIG_DFL. */
+	if (clone_flags & CLONE_CLEAR_SIGHAND)
+		flush_signal_handlers(tsk, 0);
+
 	return 0;
 }
 
@@ -1695,12 +1700,68 @@ static int pidfd_release(struct inode *inode, struct file *file)
 }
 
 #ifdef CONFIG_PROC_FS
+/**
+ * pidfd_show_fdinfo - print information about a pidfd
+ * @m: proc fdinfo file
+ * @f: file referencing a pidfd
+ *
+ * Pid:
+ * This function will print the pid that a given pidfd refers to in the
+ * pid namespace of the procfs instance.
+ * If the pid namespace of the process is not a descendant of the pid
+ * namespace of the procfs instance 0 will be shown as its pid. This is
+ * similar to calling getppid() on a process whose parent is outside of
+ * its pid namespace.
+ *
+ * NSpid:
+ * If pid namespaces are supported then this function will also print
+ * the pid of a given pidfd refers to for all descendant pid namespaces
+ * starting from the current pid namespace of the instance, i.e. the
+ * Pid field and the first entry in the NSpid field will be identical.
+ * If the pid namespace of the process is not a descendant of the pid
+ * namespace of the procfs instance 0 will be shown as its first NSpid
+ * entry and no others will be shown.
+ * Note that this differs from the Pid and NSpid fields in
+ * /proc/<pid>/status where Pid and NSpid are always shown relative to
+ * the  pid namespace of the procfs instance. The difference becomes
+ * obvious when sending around a pidfd between pid namespaces from a
+ * different branch of the tree, i.e. where no ancestoral relation is
+ * present between the pid namespaces:
+ * - create two new pid namespaces ns1 and ns2 in the initial pid
+ *   namespace (also take care to create new mount namespaces in the
+ *   new pid namespace and mount procfs)
+ * - create a process with a pidfd in ns1
+ * - send pidfd from ns1 to ns2
+ * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid
+ *   have exactly one entry, which is 0
+ */
 static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
 {
-	struct pid_namespace *ns = proc_pid_ns(file_inode(m->file));
 	struct pid *pid = f->private_data;
+	struct pid_namespace *ns;
+	pid_t nr = -1;
+
+	if (likely(pid_has_task(pid, PIDTYPE_PID))) {
+		ns = proc_pid_ns(file_inode(m->file));
+		nr = pid_nr_ns(pid, ns);
+	}
+
+	seq_put_decimal_ll(m, "Pid:\t", nr);
+
+#ifdef CONFIG_PID_NS
+	seq_put_decimal_ll(m, "\nNSpid:\t", nr);
+	if (nr > 0) {
+		int i;
 
-	seq_put_decimal_ull(m, "Pid:\t", pid_nr_ns(pid, ns));
+		/* If nr is non-zero it means that 'pid' is valid and that
+		 * ns, i.e. the pid namespace associated with the procfs
+		 * instance, is in the pid namespace hierarchy of pid.
+		 * Start at one below the already printed level.
+		 */
+		for (i = ns->level + 1; i <= pid->level; i++)
+			seq_put_decimal_ll(m, "\t", pid->numbers[i].nr);
+	}
+#endif
 	seq_putc(m, '\n');
 }
 #endif
@@ -2026,7 +2087,8 @@ static __latent_entropy struct task_struct *copy_process(
 	stackleak_task_init(p);
 
 	if (pid != &init_struct_pid) {
-		pid = alloc_pid(p->nsproxy->pid_ns_for_children);
+		pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid,
+				args->set_tid_size);
 		if (IS_ERR(pid)) {
 			retval = PTR_ERR(pid);
 			goto bad_fork_cleanup_thread;
@@ -2529,6 +2591,7 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 {
 	int err;
 	struct clone_args args;
+	pid_t *kset_tid = kargs->set_tid;
 
 	if (unlikely(usize > PAGE_SIZE))
 		return -E2BIG;
@@ -2539,6 +2602,15 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 	if (err)
 		return err;
 
+	if (unlikely(args.set_tid_size > MAX_PID_NS_LEVEL))
+		return -EINVAL;
+
+	if (unlikely(!args.set_tid && args.set_tid_size > 0))
+		return -EINVAL;
+
+	if (unlikely(args.set_tid && args.set_tid_size == 0))
+		return -EINVAL;
+
 	/*
 	 * Verify that higher 32bits of exit_signal are unset and that
 	 * it is a valid signal
@@ -2556,8 +2628,16 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 		.stack		= args.stack,
 		.stack_size	= args.stack_size,
 		.tls		= args.tls,
+		.set_tid_size	= args.set_tid_size,
 	};
 
+	if (args.set_tid &&
+		copy_from_user(kset_tid, u64_to_user_ptr(args.set_tid),
+			(kargs->set_tid_size * sizeof(pid_t))))
+		return -EFAULT;
+
+	kargs->set_tid = kset_tid;
+
 	return 0;
 }
 
@@ -2591,11 +2671,8 @@ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs)
 
 static bool clone3_args_valid(struct kernel_clone_args *kargs)
 {
-	/*
-	 * All lower bits of the flag word are taken.
-	 * Verify that no other unknown flags are passed along.
-	 */
-	if (kargs->flags & ~CLONE_LEGACY_FLAGS)
+	/* Verify that no unknown flags are passed along. */
+	if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND))
 		return false;
 
 	/*
@@ -2605,6 +2682,10 @@ static bool clone3_args_valid(struct kernel_clone_args *kargs)
 	if (kargs->flags & (CLONE_DETACHED | CSIGNAL))
 		return false;
 
+	if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) ==
+	    (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND))
+		return false;
+
 	if ((kargs->flags & (CLONE_THREAD | CLONE_PARENT)) &&
 	    kargs->exit_signal)
 		return false;
@@ -2631,6 +2712,9 @@ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size)
 	int err;
 
 	struct kernel_clone_args kargs;
+	pid_t set_tid[MAX_PID_NS_LEVEL];
+
+	kargs.set_tid = set_tid;
 
 	err = copy_clone_args_from_user(&kargs, uargs, size);
 	if (err)
diff --git a/kernel/livepatch/Makefile b/kernel/livepatch/Makefile
index cf9b5bcdb952..cf03d4bdfc66 100644
--- a/kernel/livepatch/Makefile
+++ b/kernel/livepatch/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_LIVEPATCH) += livepatch.o
 
-livepatch-objs := core.o patch.o shadow.o transition.o
+livepatch-objs := core.o patch.o shadow.o state.o transition.o
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index ab4a4606d19b..c3512e7e0801 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -22,6 +22,7 @@
 #include <asm/cacheflush.h>
 #include "core.h"
 #include "patch.h"
+#include "state.h"
 #include "transition.h"
 
 /*
@@ -632,7 +633,7 @@ static void klp_free_objects_dynamic(struct klp_patch *patch)
  * The operation must be completed by calling klp_free_patch_finish()
  * outside klp_mutex.
  */
-void klp_free_patch_start(struct klp_patch *patch)
+static void klp_free_patch_start(struct klp_patch *patch)
 {
 	if (!list_empty(&patch->list))
 		list_del(&patch->list);
@@ -677,6 +678,23 @@ static void klp_free_patch_work_fn(struct work_struct *work)
 	klp_free_patch_finish(patch);
 }
 
+void klp_free_patch_async(struct klp_patch *patch)
+{
+	klp_free_patch_start(patch);
+	schedule_work(&patch->free_work);
+}
+
+void klp_free_replaced_patches_async(struct klp_patch *new_patch)
+{
+	struct klp_patch *old_patch, *tmp_patch;
+
+	klp_for_each_patch_safe(old_patch, tmp_patch) {
+		if (old_patch == new_patch)
+			return;
+		klp_free_patch_async(old_patch);
+	}
+}
+
 static int klp_init_func(struct klp_object *obj, struct klp_func *func)
 {
 	if (!func->old_name)
@@ -992,6 +1010,13 @@ int klp_enable_patch(struct klp_patch *patch)
 
 	mutex_lock(&klp_mutex);
 
+	if (!klp_is_patch_compatible(patch)) {
+		pr_err("Livepatch patch (%s) is not compatible with the already installed livepatches.\n",
+			patch->mod->name);
+		mutex_unlock(&klp_mutex);
+		return -EINVAL;
+	}
+
 	ret = klp_init_patch_early(patch);
 	if (ret) {
 		mutex_unlock(&klp_mutex);
@@ -1022,12 +1047,13 @@ err:
 EXPORT_SYMBOL_GPL(klp_enable_patch);
 
 /*
- * This function removes replaced patches.
+ * This function unpatches objects from the replaced livepatches.
  *
  * We could be pretty aggressive here. It is called in the situation where
- * these structures are no longer accessible. All functions are redirected
- * by the klp_transition_patch. They use either a new code or they are in
- * the original code because of the special nop function patches.
+ * these structures are no longer accessed from the ftrace handler.
+ * All functions are redirected by the klp_transition_patch. They
+ * use either a new code or they are in the original code because
+ * of the special nop function patches.
  *
  * The only exception is when the transition was forced. In this case,
  * klp_ftrace_handler() might still see the replaced patch on the stack.
@@ -1035,18 +1061,16 @@ EXPORT_SYMBOL_GPL(klp_enable_patch);
  * thanks to RCU. We only have to keep the patches on the system. Also
  * this is handled transparently by patch->module_put.
  */
-void klp_discard_replaced_patches(struct klp_patch *new_patch)
+void klp_unpatch_replaced_patches(struct klp_patch *new_patch)
 {
-	struct klp_patch *old_patch, *tmp_patch;
+	struct klp_patch *old_patch;
 
-	klp_for_each_patch_safe(old_patch, tmp_patch) {
+	klp_for_each_patch(old_patch) {
 		if (old_patch == new_patch)
 			return;
 
 		old_patch->enabled = false;
 		klp_unpatch_objects(old_patch);
-		klp_free_patch_start(old_patch);
-		schedule_work(&old_patch->free_work);
 	}
 }
 
diff --git a/kernel/livepatch/core.h b/kernel/livepatch/core.h
index ec43a40b853f..38209c7361b6 100644
--- a/kernel/livepatch/core.h
+++ b/kernel/livepatch/core.h
@@ -13,8 +13,9 @@ extern struct list_head klp_patches;
 #define klp_for_each_patch(patch)	\
 	list_for_each_entry(patch, &klp_patches, list)
 
-void klp_free_patch_start(struct klp_patch *patch);
-void klp_discard_replaced_patches(struct klp_patch *new_patch);
+void klp_free_patch_async(struct klp_patch *patch);
+void klp_free_replaced_patches_async(struct klp_patch *new_patch);
+void klp_unpatch_replaced_patches(struct klp_patch *new_patch);
 void klp_discard_nops(struct klp_patch *new_patch);
 
 static inline bool klp_is_object_loaded(struct klp_object *obj)
diff --git a/kernel/livepatch/state.c b/kernel/livepatch/state.c
new file mode 100644
index 000000000000..7ee19476de9d
--- /dev/null
+++ b/kernel/livepatch/state.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * system_state.c - State of the system modified by livepatches
+ *
+ * Copyright (C) 2019 SUSE
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/livepatch.h>
+#include "core.h"
+#include "state.h"
+#include "transition.h"
+
+#define klp_for_each_state(patch, state)		\
+	for (state = patch->states; state && state->id; state++)
+
+/**
+ * klp_get_state() - get information about system state modified by
+ *	the given patch
+ * @patch:	livepatch that modifies the given system state
+ * @id:		custom identifier of the modified system state
+ *
+ * Checks whether the given patch modifies the given system state.
+ *
+ * The function can be called either from pre/post (un)patch
+ * callbacks or from the kernel code added by the livepatch.
+ *
+ * Return: pointer to struct klp_state when found, otherwise NULL.
+ */
+struct klp_state *klp_get_state(struct klp_patch *patch, unsigned long id)
+{
+	struct klp_state *state;
+
+	klp_for_each_state(patch, state) {
+		if (state->id == id)
+			return state;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(klp_get_state);
+
+/**
+ * klp_get_prev_state() - get information about system state modified by
+ *	the already installed livepatches
+ * @id:		custom identifier of the modified system state
+ *
+ * Checks whether already installed livepatches modify the given
+ * system state.
+ *
+ * The same system state can be modified by more non-cumulative
+ * livepatches. It is expected that the latest livepatch has
+ * the most up-to-date information.
+ *
+ * The function can be called only during transition when a new
+ * livepatch is being enabled or when such a transition is reverted.
+ * It is typically called only from from pre/post (un)patch
+ * callbacks.
+ *
+ * Return: pointer to the latest struct klp_state from already
+ *	installed livepatches, NULL when not found.
+ */
+struct klp_state *klp_get_prev_state(unsigned long id)
+{
+	struct klp_patch *patch;
+	struct klp_state *state, *last_state = NULL;
+
+	if (WARN_ON_ONCE(!klp_transition_patch))
+		return NULL;
+
+	klp_for_each_patch(patch) {
+		if (patch == klp_transition_patch)
+			goto out;
+
+		state = klp_get_state(patch, id);
+		if (state)
+			last_state = state;
+	}
+
+out:
+	return last_state;
+}
+EXPORT_SYMBOL_GPL(klp_get_prev_state);
+
+/* Check if the patch is able to deal with the existing system state. */
+static bool klp_is_state_compatible(struct klp_patch *patch,
+				    struct klp_state *old_state)
+{
+	struct klp_state *state;
+
+	state = klp_get_state(patch, old_state->id);
+
+	/* A cumulative livepatch must handle all already modified states. */
+	if (!state)
+		return !patch->replace;
+
+	return state->version >= old_state->version;
+}
+
+/*
+ * Check that the new livepatch will not break the existing system states.
+ * Cumulative patches must handle all already modified states.
+ * Non-cumulative patches can touch already modified states.
+ */
+bool klp_is_patch_compatible(struct klp_patch *patch)
+{
+	struct klp_patch *old_patch;
+	struct klp_state *old_state;
+
+	klp_for_each_patch(old_patch) {
+		klp_for_each_state(old_patch, old_state) {
+			if (!klp_is_state_compatible(patch, old_state))
+				return false;
+		}
+	}
+
+	return true;
+}
diff --git a/kernel/livepatch/state.h b/kernel/livepatch/state.h
new file mode 100644
index 000000000000..49d9c16e8762
--- /dev/null
+++ b/kernel/livepatch/state.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LIVEPATCH_STATE_H
+#define _LIVEPATCH_STATE_H
+
+#include <linux/livepatch.h>
+
+bool klp_is_patch_compatible(struct klp_patch *patch);
+
+#endif /* _LIVEPATCH_STATE_H */
diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index cdf318d86dd6..f6310f848f34 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -78,7 +78,7 @@ static void klp_complete_transition(void)
 		 klp_target_state == KLP_PATCHED ? "patching" : "unpatching");
 
 	if (klp_transition_patch->replace && klp_target_state == KLP_PATCHED) {
-		klp_discard_replaced_patches(klp_transition_patch);
+		klp_unpatch_replaced_patches(klp_transition_patch);
 		klp_discard_nops(klp_transition_patch);
 	}
 
@@ -446,14 +446,14 @@ void klp_try_complete_transition(void)
 	klp_complete_transition();
 
 	/*
-	 * It would make more sense to free the patch in
+	 * It would make more sense to free the unused patches in
 	 * klp_complete_transition() but it is called also
 	 * from klp_cancel_transition().
 	 */
-	if (!patch->enabled) {
-		klp_free_patch_start(patch);
-		schedule_work(&patch->free_work);
-	}
+	if (!patch->enabled)
+		klp_free_patch_async(patch);
+	else if (patch->replace)
+		klp_free_replaced_patches_async(patch);
 }
 
 /*
diff --git a/kernel/module.c b/kernel/module.c
index ff2d7359a418..acf7962936c4 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3222,7 +3222,7 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 #endif
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 	/* sechdrs[0].sh_size is always zero */
-	mod->ftrace_callsites = section_objs(info, "__mcount_loc",
+	mod->ftrace_callsites = section_objs(info, FTRACE_CALLSITE_SECTION,
 					     sizeof(*mod->ftrace_callsites),
 					     &mod->num_ftrace_callsites);
 #endif
diff --git a/kernel/pid.c b/kernel/pid.c
index 0a9f2e437217..2278e249141d 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -157,7 +157,8 @@ void free_pid(struct pid *pid)
 	call_rcu(&pid->rcu, delayed_put_pid);
 }
 
-struct pid *alloc_pid(struct pid_namespace *ns)
+struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
+		      size_t set_tid_size)
 {
 	struct pid *pid;
 	enum pid_type type;
@@ -166,6 +167,17 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 	struct upid *upid;
 	int retval = -ENOMEM;
 
+	/*
+	 * set_tid_size contains the size of the set_tid array. Starting at
+	 * the most nested currently active PID namespace it tells alloc_pid()
+	 * which PID to set for a process in that most nested PID namespace
+	 * up to set_tid_size PID namespaces. It does not have to set the PID
+	 * for a process in all nested PID namespaces but set_tid_size must
+	 * never be greater than the current ns->level + 1.
+	 */
+	if (set_tid_size > ns->level + 1)
+		return ERR_PTR(-EINVAL);
+
 	pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
 	if (!pid)
 		return ERR_PTR(retval);
@@ -174,24 +186,54 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 	pid->level = ns->level;
 
 	for (i = ns->level; i >= 0; i--) {
-		int pid_min = 1;
+		int tid = 0;
+
+		if (set_tid_size) {
+			tid = set_tid[ns->level - i];
+
+			retval = -EINVAL;
+			if (tid < 1 || tid >= pid_max)
+				goto out_free;
+			/*
+			 * Also fail if a PID != 1 is requested and
+			 * no PID 1 exists.
+			 */
+			if (tid != 1 && !tmp->child_reaper)
+				goto out_free;
+			retval = -EPERM;
+			if (!ns_capable(tmp->user_ns, CAP_SYS_ADMIN))
+				goto out_free;
+			set_tid_size--;
+		}
 
 		idr_preload(GFP_KERNEL);
 		spin_lock_irq(&pidmap_lock);
 
-		/*
-		 * init really needs pid 1, but after reaching the maximum
-		 * wrap back to RESERVED_PIDS
-		 */
-		if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS)
-			pid_min = RESERVED_PIDS;
-
-		/*
-		 * Store a null pointer so find_pid_ns does not find
-		 * a partially initialized PID (see below).
-		 */
-		nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min,
-				      pid_max, GFP_ATOMIC);
+		if (tid) {
+			nr = idr_alloc(&tmp->idr, NULL, tid,
+				       tid + 1, GFP_ATOMIC);
+			/*
+			 * If ENOSPC is returned it means that the PID is
+			 * alreay in use. Return EEXIST in that case.
+			 */
+			if (nr == -ENOSPC)
+				nr = -EEXIST;
+		} else {
+			int pid_min = 1;
+			/*
+			 * init really needs pid 1, but after reaching the
+			 * maximum wrap back to RESERVED_PIDS
+			 */
+			if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS)
+				pid_min = RESERVED_PIDS;
+
+			/*
+			 * Store a null pointer so find_pid_ns does not find
+			 * a partially initialized PID (see below).
+			 */
+			nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min,
+					      pid_max, GFP_ATOMIC);
+		}
 		spin_unlock_irq(&pidmap_lock);
 		idr_preload_end();
 
@@ -299,7 +341,7 @@ static void __change_pid(struct task_struct *task, enum pid_type type,
 	*pid_ptr = new;
 
 	for (tmp = PIDTYPE_MAX; --tmp >= 0; )
-		if (!hlist_empty(&pid->tasks[tmp]))
+		if (pid_has_task(pid, tmp))
 			return;
 
 	free_pid(pid);
@@ -497,7 +539,7 @@ static int pidfd_create(struct pid *pid)
  */
 SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
 {
-	int fd, ret;
+	int fd;
 	struct pid *p;
 
 	if (flags)
@@ -510,13 +552,11 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
 	if (!p)
 		return -ESRCH;
 
-	ret = 0;
-	rcu_read_lock();
-	if (!pid_task(p, PIDTYPE_TGID))
-		ret = -EINVAL;
-	rcu_read_unlock();
+	if (pid_has_task(p, PIDTYPE_TGID))
+		fd = pidfd_create(p);
+	else
+		fd = -EINVAL;
 
-	fd = ret ?: pidfd_create(p);
 	put_pid(p);
 	return fd;
 }
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index a6a79f85c81a..d40017e79ebe 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -26,8 +26,6 @@
 
 static DEFINE_MUTEX(pid_caches_mutex);
 static struct kmem_cache *pid_ns_cachep;
-/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */
-#define MAX_PID_NS_LEVEL 32
 /* Write once array, filled from the beginning. */
 static struct kmem_cache *pid_cache[MAX_PID_NS_LEVEL];
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 44123b4d14e8..80b60ca7767f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -16,6 +16,7 @@
 #include <asm/tlb.h>
 
 #include "../workqueue_internal.h"
+#include "../../fs/io-wq.h"
 #include "../smpboot.h"
 
 #include "pelt.h"
@@ -4112,9 +4113,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
 	 * we disable preemption to avoid it calling schedule() again
 	 * in the possible wakeup of a kworker.
 	 */
-	if (tsk->flags & PF_WQ_WORKER) {
+	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
 		preempt_disable();
-		wq_worker_sleeping(tsk);
+		if (tsk->flags & PF_WQ_WORKER)
+			wq_worker_sleeping(tsk);
+		else
+			io_wq_worker_sleeping(tsk);
 		preempt_enable_no_resched();
 	}
 
@@ -4131,8 +4135,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
 
 static void sched_update_worker(struct task_struct *tsk)
 {
-	if (tsk->flags & PF_WQ_WORKER)
-		wq_worker_running(tsk);
+	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
+		if (tsk->flags & PF_WQ_WORKER)
+			wq_worker_running(tsk);
+		else
+			io_wq_worker_running(tsk);
+	}
 }
 
 asmlinkage __visible void __sched schedule(void)
diff --git a/kernel/sysctl-test.c b/kernel/sysctl-test.c
new file mode 100644
index 000000000000..2a63241a8453
--- /dev/null
+++ b/kernel/sysctl-test.c
@@ -0,0 +1,392 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnit test of proc sysctl.
+ */
+
+#include <kunit/test.h>
+#include <linux/sysctl.h>
+
+#define KUNIT_PROC_READ 0
+#define KUNIT_PROC_WRITE 1
+
+static int i_zero;
+static int i_one_hundred = 100;
+
+/*
+ * Test that proc_dointvec will not try to use a NULL .data field even when the
+ * length is non-zero.
+ */
+static void sysctl_test_api_dointvec_null_tbl_data(struct kunit *test)
+{
+	struct ctl_table null_data_table = {
+		.procname = "foo",
+		/*
+		 * Here we are testing that proc_dointvec behaves correctly when
+		 * we give it a NULL .data field. Normally this would point to a
+		 * piece of memory where the value would be stored.
+		 */
+		.data		= NULL,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &i_zero,
+		.extra2         = &i_one_hundred,
+	};
+	/*
+	 * proc_dointvec expects a buffer in user space, so we allocate one. We
+	 * also need to cast it to __user so sparse doesn't get mad.
+	 */
+	void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int),
+							   GFP_USER);
+	size_t len;
+	loff_t pos;
+
+	/*
+	 * We don't care what the starting length is since proc_dointvec should
+	 * not try to read because .data is NULL.
+	 */
+	len = 1234;
+	KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&null_data_table,
+					       KUNIT_PROC_READ, buffer, &len,
+					       &pos));
+	KUNIT_EXPECT_EQ(test, (size_t)0, len);
+
+	/*
+	 * See above.
+	 */
+	len = 1234;
+	KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&null_data_table,
+					       KUNIT_PROC_WRITE, buffer, &len,
+					       &pos));
+	KUNIT_EXPECT_EQ(test, (size_t)0, len);
+}
+
+/*
+ * Similar to the previous test, we create a struct ctrl_table that has a .data
+ * field that proc_dointvec cannot do anything with; however, this time it is
+ * because we tell proc_dointvec that the size is 0.
+ */
+static void sysctl_test_api_dointvec_table_maxlen_unset(struct kunit *test)
+{
+	int data = 0;
+	struct ctl_table data_maxlen_unset_table = {
+		.procname = "foo",
+		.data		= &data,
+		/*
+		 * So .data is no longer NULL, but we tell proc_dointvec its
+		 * length is 0, so it still shouldn't try to use it.
+		 */
+		.maxlen		= 0,
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &i_zero,
+		.extra2         = &i_one_hundred,
+	};
+	void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int),
+							   GFP_USER);
+	size_t len;
+	loff_t pos;
+
+	/*
+	 * As before, we don't care what buffer length is because proc_dointvec
+	 * cannot do anything because its internal .data buffer has zero length.
+	 */
+	len = 1234;
+	KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&data_maxlen_unset_table,
+					       KUNIT_PROC_READ, buffer, &len,
+					       &pos));
+	KUNIT_EXPECT_EQ(test, (size_t)0, len);
+
+	/*
+	 * See previous comment.
+	 */
+	len = 1234;
+	KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&data_maxlen_unset_table,
+					       KUNIT_PROC_WRITE, buffer, &len,
+					       &pos));
+	KUNIT_EXPECT_EQ(test, (size_t)0, len);
+}
+
+/*
+ * Here we provide a valid struct ctl_table, but we try to read and write from
+ * it using a buffer of zero length, so it should still fail in a similar way as
+ * before.
+ */
+static void sysctl_test_api_dointvec_table_len_is_zero(struct kunit *test)
+{
+	int data = 0;
+	/* Good table. */
+	struct ctl_table table = {
+		.procname = "foo",
+		.data		= &data,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &i_zero,
+		.extra2         = &i_one_hundred,
+	};
+	void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int),
+							   GFP_USER);
+	/*
+	 * However, now our read/write buffer has zero length.
+	 */
+	size_t len = 0;
+	loff_t pos;
+
+	KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ, buffer,
+					       &len, &pos));
+	KUNIT_EXPECT_EQ(test, (size_t)0, len);
+
+	KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_WRITE, buffer,
+					       &len, &pos));
+	KUNIT_EXPECT_EQ(test, (size_t)0, len);
+}
+
+/*
+ * Test that proc_dointvec refuses to read when the file position is non-zero.
+ */
+static void sysctl_test_api_dointvec_table_read_but_position_set(
+		struct kunit *test)
+{
+	int data = 0;
+	/* Good table. */
+	struct ctl_table table = {
+		.procname = "foo",
+		.data		= &data,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &i_zero,
+		.extra2         = &i_one_hundred,
+	};
+	void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int),
+							   GFP_USER);
+	/*
+	 * We don't care about our buffer length because we start off with a
+	 * non-zero file position.
+	 */
+	size_t len = 1234;
+	/*
+	 * proc_dointvec should refuse to read into the buffer since the file
+	 * pos is non-zero.
+	 */
+	loff_t pos = 1;
+
+	KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ, buffer,
+					       &len, &pos));
+	KUNIT_EXPECT_EQ(test, (size_t)0, len);
+}
+
+/*
+ * Test that we can read a two digit number in a sufficiently size buffer.
+ * Nothing fancy.
+ */
+static void sysctl_test_dointvec_read_happy_single_positive(struct kunit *test)
+{
+	int data = 0;
+	/* Good table. */
+	struct ctl_table table = {
+		.procname = "foo",
+		.data		= &data,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &i_zero,
+		.extra2         = &i_one_hundred,
+	};
+	size_t len = 4;
+	loff_t pos = 0;
+	char *buffer = kunit_kzalloc(test, len, GFP_USER);
+	char __user *user_buffer = (char __user *)buffer;
+	/* Store 13 in the data field. */
+	*((int *)table.data) = 13;
+
+	KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ,
+					       user_buffer, &len, &pos));
+	KUNIT_ASSERT_EQ(test, (size_t)3, len);
+	buffer[len] = '\0';
+	/* And we read 13 back out. */
+	KUNIT_EXPECT_STREQ(test, "13\n", buffer);
+}
+
+/*
+ * Same as previous test, just now with negative numbers.
+ */
+static void sysctl_test_dointvec_read_happy_single_negative(struct kunit *test)
+{
+	int data = 0;
+	/* Good table. */
+	struct ctl_table table = {
+		.procname = "foo",
+		.data		= &data,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &i_zero,
+		.extra2         = &i_one_hundred,
+	};
+	size_t len = 5;
+	loff_t pos = 0;
+	char *buffer = kunit_kzalloc(test, len, GFP_USER);
+	char __user *user_buffer = (char __user *)buffer;
+	*((int *)table.data) = -16;
+
+	KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ,
+					       user_buffer, &len, &pos));
+	KUNIT_ASSERT_EQ(test, (size_t)4, len);
+	buffer[len] = '\0';
+	KUNIT_EXPECT_STREQ(test, "-16\n", (char *)buffer);
+}
+
+/*
+ * Test that a simple positive write works.
+ */
+static void sysctl_test_dointvec_write_happy_single_positive(struct kunit *test)
+{
+	int data = 0;
+	/* Good table. */
+	struct ctl_table table = {
+		.procname = "foo",
+		.data		= &data,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &i_zero,
+		.extra2         = &i_one_hundred,
+	};
+	char input[] = "9";
+	size_t len = sizeof(input) - 1;
+	loff_t pos = 0;
+	char *buffer = kunit_kzalloc(test, len, GFP_USER);
+	char __user *user_buffer = (char __user *)buffer;
+
+	memcpy(buffer, input, len);
+
+	KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_WRITE,
+					       user_buffer, &len, &pos));
+	KUNIT_EXPECT_EQ(test, sizeof(input) - 1, len);
+	KUNIT_EXPECT_EQ(test, sizeof(input) - 1, (size_t)pos);
+	KUNIT_EXPECT_EQ(test, 9, *((int *)table.data));
+}
+
+/*
+ * Same as previous test, but now with negative numbers.
+ */
+static void sysctl_test_dointvec_write_happy_single_negative(struct kunit *test)
+{
+	int data = 0;
+	struct ctl_table table = {
+		.procname = "foo",
+		.data		= &data,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &i_zero,
+		.extra2         = &i_one_hundred,
+	};
+	char input[] = "-9";
+	size_t len = sizeof(input) - 1;
+	loff_t pos = 0;
+	char *buffer = kunit_kzalloc(test, len, GFP_USER);
+	char __user *user_buffer = (char __user *)buffer;
+
+	memcpy(buffer, input, len);
+
+	KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_WRITE,
+					       user_buffer, &len, &pos));
+	KUNIT_EXPECT_EQ(test, sizeof(input) - 1, len);
+	KUNIT_EXPECT_EQ(test, sizeof(input) - 1, (size_t)pos);
+	KUNIT_EXPECT_EQ(test, -9, *((int *)table.data));
+}
+
+/*
+ * Test that writing a value smaller than the minimum possible value is not
+ * allowed.
+ */
+static void sysctl_test_api_dointvec_write_single_less_int_min(
+		struct kunit *test)
+{
+	int data = 0;
+	struct ctl_table table = {
+		.procname = "foo",
+		.data		= &data,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &i_zero,
+		.extra2         = &i_one_hundred,
+	};
+	size_t max_len = 32, len = max_len;
+	loff_t pos = 0;
+	char *buffer = kunit_kzalloc(test, max_len, GFP_USER);
+	char __user *user_buffer = (char __user *)buffer;
+	unsigned long abs_of_less_than_min = (unsigned long)INT_MAX
+					     - (INT_MAX + INT_MIN) + 1;
+
+	/*
+	 * We use this rigmarole to create a string that contains a value one
+	 * less than the minimum accepted value.
+	 */
+	KUNIT_ASSERT_LT(test,
+			(size_t)snprintf(buffer, max_len, "-%lu",
+					 abs_of_less_than_min),
+			max_len);
+
+	KUNIT_EXPECT_EQ(test, -EINVAL, proc_dointvec(&table, KUNIT_PROC_WRITE,
+						     user_buffer, &len, &pos));
+	KUNIT_EXPECT_EQ(test, max_len, len);
+	KUNIT_EXPECT_EQ(test, 0, *((int *)table.data));
+}
+
+/*
+ * Test that writing the maximum possible value works.
+ */
+static void sysctl_test_api_dointvec_write_single_greater_int_max(
+		struct kunit *test)
+{
+	int data = 0;
+	struct ctl_table table = {
+		.procname = "foo",
+		.data		= &data,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &i_zero,
+		.extra2         = &i_one_hundred,
+	};
+	size_t max_len = 32, len = max_len;
+	loff_t pos = 0;
+	char *buffer = kunit_kzalloc(test, max_len, GFP_USER);
+	char __user *user_buffer = (char __user *)buffer;
+	unsigned long greater_than_max = (unsigned long)INT_MAX + 1;
+
+	KUNIT_ASSERT_GT(test, greater_than_max, (unsigned long)INT_MAX);
+	KUNIT_ASSERT_LT(test, (size_t)snprintf(buffer, max_len, "%lu",
+					       greater_than_max),
+			max_len);
+	KUNIT_EXPECT_EQ(test, -EINVAL, proc_dointvec(&table, KUNIT_PROC_WRITE,
+						     user_buffer, &len, &pos));
+	KUNIT_ASSERT_EQ(test, max_len, len);
+	KUNIT_EXPECT_EQ(test, 0, *((int *)table.data));
+}
+
+static struct kunit_case sysctl_test_cases[] = {
+	KUNIT_CASE(sysctl_test_api_dointvec_null_tbl_data),
+	KUNIT_CASE(sysctl_test_api_dointvec_table_maxlen_unset),
+	KUNIT_CASE(sysctl_test_api_dointvec_table_len_is_zero),
+	KUNIT_CASE(sysctl_test_api_dointvec_table_read_but_position_set),
+	KUNIT_CASE(sysctl_test_dointvec_read_happy_single_positive),
+	KUNIT_CASE(sysctl_test_dointvec_read_happy_single_negative),
+	KUNIT_CASE(sysctl_test_dointvec_write_happy_single_positive),
+	KUNIT_CASE(sysctl_test_dointvec_write_happy_single_negative),
+	KUNIT_CASE(sysctl_test_api_dointvec_write_single_less_int_min),
+	KUNIT_CASE(sysctl_test_api_dointvec_write_single_greater_int_max),
+	{}
+};
+
+static struct kunit_suite sysctl_test_suite = {
+	.name = "sysctl_test",
+	.test_cases = sysctl_test_cases,
+};
+
+kunit_test_suite(sysctl_test_suite);
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 2d6e93ab0478..475e29498bca 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -64,8 +64,7 @@ static void blk_unregister_tracepoints(void);
  * Send out a notify message.
  */
 static void trace_note(struct blk_trace *bt, pid_t pid, int action,
-		       const void *data, size_t len,
-		       union kernfs_node_id *cgid)
+		       const void *data, size_t len, u64 cgid)
 {
 	struct blk_io_trace *t;
 	struct ring_buffer_event *event = NULL;
@@ -73,7 +72,7 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
 	int pc = 0;
 	int cpu = smp_processor_id();
 	bool blk_tracer = blk_tracer_enabled;
-	ssize_t cgid_len = cgid ? sizeof(*cgid) : 0;
+	ssize_t cgid_len = cgid ? sizeof(cgid) : 0;
 
 	if (blk_tracer) {
 		buffer = blk_tr->trace_buffer.buffer;
@@ -100,8 +99,8 @@ record_it:
 		t->pid = pid;
 		t->cpu = cpu;
 		t->pdu_len = len + cgid_len;
-		if (cgid)
-			memcpy((void *)t + sizeof(*t), cgid, cgid_len);
+		if (cgid_len)
+			memcpy((void *)t + sizeof(*t), &cgid, cgid_len);
 		memcpy((void *) t + sizeof(*t) + cgid_len, data, len);
 
 		if (blk_tracer)
@@ -122,7 +121,7 @@ static void trace_note_tsk(struct task_struct *tsk)
 	spin_lock_irqsave(&running_trace_lock, flags);
 	list_for_each_entry(bt, &running_trace_list, running_list) {
 		trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm,
-			   sizeof(tsk->comm), NULL);
+			   sizeof(tsk->comm), 0);
 	}
 	spin_unlock_irqrestore(&running_trace_lock, flags);
 }
@@ -139,7 +138,7 @@ static void trace_note_time(struct blk_trace *bt)
 	words[1] = now.tv_nsec;
 
 	local_irq_save(flags);
-	trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words), NULL);
+	trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words), 0);
 	local_irq_restore(flags);
 }
 
@@ -172,9 +171,9 @@ void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg,
 		blkcg = NULL;
 #ifdef CONFIG_BLK_CGROUP
 	trace_note(bt, 0, BLK_TN_MESSAGE, buf, n,
-		blkcg ? cgroup_get_kernfs_id(blkcg->css.cgroup) : NULL);
+		   blkcg ? cgroup_id(blkcg->css.cgroup) : 1);
 #else
-	trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, NULL);
+	trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, 0);
 #endif
 	local_irq_restore(flags);
 }
@@ -212,7 +211,7 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
  */
 static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 		     int op, int op_flags, u32 what, int error, int pdu_len,
-		     void *pdu_data, union kernfs_node_id *cgid)
+		     void *pdu_data, u64 cgid)
 {
 	struct task_struct *tsk = current;
 	struct ring_buffer_event *event = NULL;
@@ -223,7 +222,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	pid_t pid;
 	int cpu, pc = 0;
 	bool blk_tracer = blk_tracer_enabled;
-	ssize_t cgid_len = cgid ? sizeof(*cgid) : 0;
+	ssize_t cgid_len = cgid ? sizeof(cgid) : 0;
 
 	if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer))
 		return;
@@ -294,7 +293,7 @@ record_it:
 		t->pdu_len = pdu_len + cgid_len;
 
 		if (cgid_len)
-			memcpy((void *)t + sizeof(*t), cgid, cgid_len);
+			memcpy((void *)t + sizeof(*t), &cgid, cgid_len);
 		if (pdu_len)
 			memcpy((void *)t + sizeof(*t) + cgid_len, pdu_data, pdu_len);
 
@@ -751,31 +750,29 @@ void blk_trace_shutdown(struct request_queue *q)
 }
 
 #ifdef CONFIG_BLK_CGROUP
-static union kernfs_node_id *
-blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
+static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
 {
 	struct blk_trace *bt = q->blk_trace;
 
 	if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
-		return NULL;
+		return 0;
 
 	if (!bio->bi_blkg)
-		return NULL;
-	return cgroup_get_kernfs_id(bio_blkcg(bio)->css.cgroup);
+		return 0;
+	return cgroup_id(bio_blkcg(bio)->css.cgroup);
 }
 #else
-static union kernfs_node_id *
-blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
+u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
 {
-	return NULL;
+	return 0;
 }
 #endif
 
-static union kernfs_node_id *
+static u64
 blk_trace_request_get_cgid(struct request_queue *q, struct request *rq)
 {
 	if (!rq->bio)
-		return NULL;
+		return 0;
 	/* Use the first bio */
 	return blk_trace_bio_get_cgid(q, rq->bio);
 }
@@ -797,8 +794,7 @@ blk_trace_request_get_cgid(struct request_queue *q, struct request *rq)
  *
  **/
 static void blk_add_trace_rq(struct request *rq, int error,
-			     unsigned int nr_bytes, u32 what,
-			     union kernfs_node_id *cgid)
+			     unsigned int nr_bytes, u32 what, u64 cgid)
 {
 	struct blk_trace *bt = rq->q->blk_trace;
 
@@ -913,7 +909,7 @@ static void blk_add_trace_getrq(void *ignore,
 
 		if (bt)
 			__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0,
-					NULL, NULL);
+					NULL, 0);
 	}
 }
 
@@ -929,7 +925,7 @@ static void blk_add_trace_sleeprq(void *ignore,
 
 		if (bt)
 			__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ,
-					0, 0, NULL, NULL);
+					0, 0, NULL, 0);
 	}
 }
 
@@ -938,7 +934,7 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q)
 	struct blk_trace *bt = q->blk_trace;
 
 	if (bt)
-		__blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, NULL);
+		__blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0);
 }
 
 static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
@@ -955,7 +951,7 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
 		else
 			what = BLK_TA_UNPLUG_TIMER;
 
-		__blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, NULL);
+		__blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0);
 	}
 }
 
@@ -1172,19 +1168,17 @@ const struct blk_io_trace *te_blk_io_trace(const struct trace_entry *ent)
 
 static inline const void *pdu_start(const struct trace_entry *ent, bool has_cg)
 {
-	return (void *)(te_blk_io_trace(ent) + 1) +
-		(has_cg ? sizeof(union kernfs_node_id) : 0);
+	return (void *)(te_blk_io_trace(ent) + 1) + (has_cg ? sizeof(u64) : 0);
 }
 
-static inline const void *cgid_start(const struct trace_entry *ent)
+static inline u64 t_cgid(const struct trace_entry *ent)
 {
-	return (void *)(te_blk_io_trace(ent) + 1);
+	return *(u64 *)(te_blk_io_trace(ent) + 1);
 }
 
 static inline int pdu_real_len(const struct trace_entry *ent, bool has_cg)
 {
-	return te_blk_io_trace(ent)->pdu_len -
-			(has_cg ? sizeof(union kernfs_node_id) : 0);
+	return te_blk_io_trace(ent)->pdu_len - (has_cg ? sizeof(u64) : 0);
 }
 
 static inline u32 t_action(const struct trace_entry *ent)
@@ -1257,7 +1251,7 @@ static void blk_log_action(struct trace_iterator *iter, const char *act,
 
 	fill_rwbs(rwbs, t);
 	if (has_cg) {
-		const union kernfs_node_id *id = cgid_start(iter->ent);
+		u64 id = t_cgid(iter->ent);
 
 		if (blk_tracer_flags.val & TRACE_BLK_OPT_CGNAME) {
 			char blkcg_name_buf[NAME_MAX + 1] = "<...>";
@@ -1267,11 +1261,25 @@ static void blk_log_action(struct trace_iterator *iter, const char *act,
 			trace_seq_printf(&iter->seq, "%3d,%-3d %s %2s %3s ",
 				 MAJOR(t->device), MINOR(t->device),
 				 blkcg_name_buf, act, rwbs);
-		} else
+		} else {
+			/*
+			 * The cgid portion used to be "INO,GEN".  Userland
+			 * builds a FILEID_INO32_GEN fid out of them and
+			 * opens the cgroup using open_by_handle_at(2).
+			 * While 32bit ino setups are still the same, 64bit
+			 * ones now use the 64bit ino as the whole ID and
+			 * no longer use generation.
+			 *
+			 * Regarldess of the content, always output
+			 * "LOW32,HIGH32" so that FILEID_INO32_GEN fid can
+			 * be mapped back to @id on both 64 and 32bit ino
+			 * setups.  See __kernfs_fh_to_dentry().
+			 */
 			trace_seq_printf(&iter->seq,
-				 "%3d,%-3d %x,%-x %2s %3s ",
+				 "%3d,%-3d %llx,%-llx %2s %3s ",
 				 MAJOR(t->device), MINOR(t->device),
-				 id->ino, id->generation, act, rwbs);
+				 id & U32_MAX, id >> 32, act, rwbs);
+		}
 	} else
 		trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ",
 				 MAJOR(t->device), MINOR(t->device), act, rwbs);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f296d89be757..5259d4dea675 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2494,14 +2494,14 @@ struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter)
 }
 
 static int
-ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec)
+ftrace_nop_initialize(struct module *mod, struct dyn_ftrace *rec)
 {
 	int ret;
 
 	if (unlikely(ftrace_disabled))
 		return 0;
 
-	ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR);
+	ret = ftrace_init_nop(mod, rec);
 	if (ret) {
 		ftrace_bug_type = FTRACE_BUG_INIT;
 		ftrace_bug(ret, rec);
@@ -2943,7 +2943,7 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
 			 * to the NOP instructions.
 			 */
 			if (!__is_defined(CC_USING_NOP_MCOUNT) &&
-			    !ftrace_code_disable(mod, p))
+			    !ftrace_nop_initialize(mod, p))
 				break;
 
 			update_cnt++;
diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c
index 80e0b2aca703..2e9a4746ea85 100644
--- a/kernel/trace/trace_benchmark.c
+++ b/kernel/trace/trace_benchmark.c
@@ -178,14 +178,14 @@ static int benchmark_event_kthread(void *arg)
 int trace_benchmark_reg(void)
 {
 	if (!ok_to_run) {
-		pr_warning("trace benchmark cannot be started via kernel command line\n");
+		pr_warn("trace benchmark cannot be started via kernel command line\n");
 		return -EBUSY;
 	}
 
 	bm_event_thread = kthread_run(benchmark_event_kthread,
 				      NULL, "event_benchmark");
 	if (IS_ERR(bm_event_thread)) {
-		pr_warning("trace benchmark failed to create kernel thread\n");
+		pr_warn("trace benchmark failed to create kernel thread\n");
 		return PTR_ERR(bm_event_thread);
 	}
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index bc2e09a8ea61..914b845ad4ff 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -248,7 +248,7 @@ struct workqueue_struct {
 	struct list_head	flusher_overflow; /* WQ: flush overflow list */
 
 	struct list_head	maydays;	/* MD: pwqs requesting rescue */
-	struct worker		*rescuer;	/* I: rescue worker */
+	struct worker		*rescuer;	/* MD: rescue worker */
 
 	int			nr_drainers;	/* WQ: drain in progress */
 	int			saved_max_active; /* WQ: saved pwq max_active */
@@ -355,6 +355,7 @@ EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq);
 
 static int worker_thread(void *__worker);
 static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
+static void show_pwq(struct pool_workqueue *pwq);
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/workqueue.h>
@@ -425,7 +426,8 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
  * ignored.
  */
 #define for_each_pwq(pwq, wq)						\
-	list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node)		\
+	list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node,		\
+				lockdep_is_held(&wq->mutex))		\
 		if (({ assert_rcu_or_wq_mutex(wq); false; })) { }	\
 		else
 
@@ -2532,8 +2534,14 @@ repeat:
 			 */
 			if (need_to_create_worker(pool)) {
 				spin_lock(&wq_mayday_lock);
-				get_pwq(pwq);
-				list_move_tail(&pwq->mayday_node, &wq->maydays);
+				/*
+				 * Queue iff we aren't racing destruction
+				 * and somebody else hasn't queued it already.
+				 */
+				if (wq->rescuer && list_empty(&pwq->mayday_node)) {
+					get_pwq(pwq);
+					list_add_tail(&pwq->mayday_node, &wq->maydays);
+				}
 				spin_unlock(&wq_mayday_lock);
 			}
 		}
@@ -4314,6 +4322,22 @@ err_destroy:
 }
 EXPORT_SYMBOL_GPL(alloc_workqueue);
 
+static bool pwq_busy(struct pool_workqueue *pwq)
+{
+	int i;
+
+	for (i = 0; i < WORK_NR_COLORS; i++)
+		if (pwq->nr_in_flight[i])
+			return true;
+
+	if ((pwq != pwq->wq->dfl_pwq) && (pwq->refcnt > 1))
+		return true;
+	if (pwq->nr_active || !list_empty(&pwq->delayed_works))
+		return true;
+
+	return false;
+}
+
 /**
  * destroy_workqueue - safely terminate a workqueue
  * @wq: target workqueue
@@ -4325,31 +4349,51 @@ void destroy_workqueue(struct workqueue_struct *wq)
 	struct pool_workqueue *pwq;
 	int node;
 
+	/*
+	 * Remove it from sysfs first so that sanity check failure doesn't
+	 * lead to sysfs name conflicts.
+	 */
+	workqueue_sysfs_unregister(wq);
+
 	/* drain it before proceeding with destruction */
 	drain_workqueue(wq);
 
-	/* sanity checks */
-	mutex_lock(&wq->mutex);
-	for_each_pwq(pwq, wq) {
-		int i;
+	/* kill rescuer, if sanity checks fail, leave it w/o rescuer */
+	if (wq->rescuer) {
+		struct worker *rescuer = wq->rescuer;
 
-		for (i = 0; i < WORK_NR_COLORS; i++) {
-			if (WARN_ON(pwq->nr_in_flight[i])) {
-				mutex_unlock(&wq->mutex);
-				show_workqueue_state();
-				return;
-			}
-		}
+		/* this prevents new queueing */
+		spin_lock_irq(&wq_mayday_lock);
+		wq->rescuer = NULL;
+		spin_unlock_irq(&wq_mayday_lock);
+
+		/* rescuer will empty maydays list before exiting */
+		kthread_stop(rescuer->task);
+		kfree(rescuer);
+	}
 
-		if (WARN_ON((pwq != wq->dfl_pwq) && (pwq->refcnt > 1)) ||
-		    WARN_ON(pwq->nr_active) ||
-		    WARN_ON(!list_empty(&pwq->delayed_works))) {
+	/*
+	 * Sanity checks - grab all the locks so that we wait for all
+	 * in-flight operations which may do put_pwq().
+	 */
+	mutex_lock(&wq_pool_mutex);
+	mutex_lock(&wq->mutex);
+	for_each_pwq(pwq, wq) {
+		spin_lock_irq(&pwq->pool->lock);
+		if (WARN_ON(pwq_busy(pwq))) {
+			pr_warning("%s: %s has the following busy pwq\n",
+				   __func__, wq->name);
+			show_pwq(pwq);
+			spin_unlock_irq(&pwq->pool->lock);
 			mutex_unlock(&wq->mutex);
+			mutex_unlock(&wq_pool_mutex);
 			show_workqueue_state();
 			return;
 		}
+		spin_unlock_irq(&pwq->pool->lock);
 	}
 	mutex_unlock(&wq->mutex);
+	mutex_unlock(&wq_pool_mutex);
 
 	/*
 	 * wq list is used to freeze wq, remove from list after
@@ -4359,11 +4403,6 @@ void destroy_workqueue(struct workqueue_struct *wq)
 	list_del_rcu(&wq->list);
 	mutex_unlock(&wq_pool_mutex);
 
-	workqueue_sysfs_unregister(wq);
-
-	if (wq->rescuer)
-		kthread_stop(wq->rescuer->task);
-
 	if (!(wq->flags & WQ_UNBOUND)) {
 		wq_unregister_lockdep(wq);
 		/*
@@ -4638,7 +4677,8 @@ static void show_pwq(struct pool_workqueue *pwq)
 	pr_info("  pwq %d:", pool->id);
 	pr_cont_pool_info(pool);
 
-	pr_cont(" active=%d/%d%s\n", pwq->nr_active, pwq->max_active,
+	pr_cont(" active=%d/%d refcnt=%d%s\n",
+		pwq->nr_active, pwq->max_active, pwq->refcnt,
 		!list_empty(&pwq->mayday_node) ? " MAYDAY" : "");
 
 	hash_for_each(pool->busy_hash, bkt, worker, hentry) {
@@ -4657,7 +4697,7 @@ static void show_pwq(struct pool_workqueue *pwq)
 
 			pr_cont("%s %d%s:%ps", comma ? "," : "",
 				task_pid_nr(worker->task),
-				worker == pwq->wq->rescuer ? "(RESCUER)" : "",
+				worker->rescue_wq ? "(RESCUER)" : "",
 				worker->current_func);
 			list_for_each_entry(work, &worker->scheduled, entry)
 				pr_cont_work(false, work);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 93d97f9b0157..ecde997db751 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -164,6 +164,15 @@ config DYNAMIC_DEBUG
 	  See Documentation/admin-guide/dynamic-debug-howto.rst for additional
 	  information.
 
+config SYMBOLIC_ERRNAME
+	bool "Support symbolic error names in printf"
+	default y if PRINTK
+	help
+	  If you say Y here, the kernel's printf implementation will
+	  be able to print symbolic error names such as ENOSPC instead
+	  of the number 28. It makes the kernel image slightly larger
+	  (about 3KB), but can make the kernel logs easier to read.
+
 endmenu # "printk and dmesg options"
 
 menu "Compile-time checks and compiler options"
@@ -1664,6 +1673,8 @@ config PROVIDE_OHCI1394_DMA_INIT
 
 	  See Documentation/debugging-via-ohci1394.txt for more information.
 
+source "lib/kunit/Kconfig"
+
 menuconfig RUNTIME_TESTING_MENU
 	bool "Runtime Testing"
 	def_bool y
@@ -1948,6 +1959,35 @@ config TEST_SYSCTL
 
 	  If unsure, say N.
 
+config SYSCTL_KUNIT_TEST
+	bool "KUnit test for sysctl"
+	depends on KUNIT
+	help
+	  This builds the proc sysctl unit test, which runs on boot.
+	  Tests the API contract and implementation correctness of sysctl.
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
+config LIST_KUNIT_TEST
+	bool "KUnit Test for Kernel Linked-list structures"
+	depends on KUNIT
+	help
+	  This builds the linked list KUnit test suite.
+	  It tests that the API and basic functionality of the list_head type
+	  and associated macros.
+
+	  KUnit tests run during boot and output the results to the debug log
+	  in TAP format (http://testanything.org/). Only useful for kernel devs
+	  running the KUnit test harness, and not intended for inclusion into a
+	  production build.
+
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
 config TEST_UDELAY
 	tristate "udelay test driver"
 	help
diff --git a/lib/Makefile b/lib/Makefile
index c5892807e06f..b7f0ea999d48 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -26,8 +26,7 @@ endif
 
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o timerqueue.o xarray.o \
-	 idr.o extable.o \
-	 sha1.o chacha.o irq_regs.o argv_split.o \
+	 idr.o extable.o sha1.o irq_regs.o argv_split.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
@@ -92,6 +91,8 @@ obj-$(CONFIG_TEST_MEMINIT) += test_meminit.o
 
 obj-$(CONFIG_TEST_LIVEPATCH) += livepatch/
 
+obj-$(CONFIG_KUNIT) += kunit/
+
 ifeq ($(CONFIG_DEBUG_KOBJECT),y)
 CFLAGS_kobject.o += -DDEBUG
 CFLAGS_kobject_uevent.o += -DDEBUG
@@ -181,6 +182,7 @@ lib-$(CONFIG_GENERIC_BUG) += bug.o
 obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
 
 obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o
+obj-$(CONFIG_SYMBOLIC_ERRNAME) += errname.o
 
 obj-$(CONFIG_NLATTR) += nlattr.o
 
@@ -290,3 +292,6 @@ obj-$(CONFIG_GENERIC_LIB_MULDI3) += muldi3.o
 obj-$(CONFIG_GENERIC_LIB_CMPDI2) += cmpdi2.o
 obj-$(CONFIG_GENERIC_LIB_UCMPDI2) += ucmpdi2.o
 obj-$(CONFIG_OBJAGG) += objagg.o
+
+# KUnit tests
+obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o
diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
index 075f3788bbe4..f08d9c56f712 100644
--- a/lib/cpu_rmap.c
+++ b/lib/cpu_rmap.c
@@ -255,7 +255,7 @@ irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
 
 	rc = cpu_rmap_update(glue->rmap, glue->index, mask);
 	if (rc)
-		pr_warning("irq_cpu_rmap_notify: update failed: %d\n", rc);
+		pr_warn("irq_cpu_rmap_notify: update failed: %d\n", rc);
 }
 
 /**
diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig
new file mode 100644
index 000000000000..0b2c4fce26d9
--- /dev/null
+++ b/lib/crypto/Kconfig
@@ -0,0 +1,130 @@
+# SPDX-License-Identifier: GPL-2.0
+
+comment "Crypto library routines"
+
+config CRYPTO_LIB_AES
+	tristate
+
+config CRYPTO_LIB_ARC4
+	tristate
+
+config CRYPTO_ARCH_HAVE_LIB_BLAKE2S
+	tristate
+	help
+	  Declares whether the architecture provides an arch-specific
+	  accelerated implementation of the Blake2s library interface,
+	  either builtin or as a module.
+
+config CRYPTO_LIB_BLAKE2S_GENERIC
+	tristate
+	help
+	  This symbol can be depended upon by arch implementations of the
+	  Blake2s library interface that require the generic code as a
+	  fallback, e.g., for SIMD implementations. If no arch specific
+	  implementation is enabled, this implementation serves the users
+	  of CRYPTO_LIB_BLAKE2S.
+
+config CRYPTO_LIB_BLAKE2S
+	tristate "BLAKE2s hash function library"
+	depends on CRYPTO_ARCH_HAVE_LIB_BLAKE2S || !CRYPTO_ARCH_HAVE_LIB_BLAKE2S
+	select CRYPTO_LIB_BLAKE2S_GENERIC if CRYPTO_ARCH_HAVE_LIB_BLAKE2S=n
+	help
+	  Enable the Blake2s library interface. This interface may be fulfilled
+	  by either the generic implementation or an arch-specific one, if one
+	  is available and enabled.
+
+config CRYPTO_ARCH_HAVE_LIB_CHACHA
+	tristate
+	help
+	  Declares whether the architecture provides an arch-specific
+	  accelerated implementation of the ChaCha library interface,
+	  either builtin or as a module.
+
+config CRYPTO_LIB_CHACHA_GENERIC
+	tristate
+	select CRYPTO_ALGAPI
+	help
+	  This symbol can be depended upon by arch implementations of the
+	  ChaCha library interface that require the generic code as a
+	  fallback, e.g., for SIMD implementations. If no arch specific
+	  implementation is enabled, this implementation serves the users
+	  of CRYPTO_LIB_CHACHA.
+
+config CRYPTO_LIB_CHACHA
+	tristate "ChaCha library interface"
+	depends on CRYPTO_ARCH_HAVE_LIB_CHACHA || !CRYPTO_ARCH_HAVE_LIB_CHACHA
+	select CRYPTO_LIB_CHACHA_GENERIC if CRYPTO_ARCH_HAVE_LIB_CHACHA=n
+	help
+	  Enable the ChaCha library interface. This interface may be fulfilled
+	  by either the generic implementation or an arch-specific one, if one
+	  is available and enabled.
+
+config CRYPTO_ARCH_HAVE_LIB_CURVE25519
+	tristate
+	help
+	  Declares whether the architecture provides an arch-specific
+	  accelerated implementation of the Curve25519 library interface,
+	  either builtin or as a module.
+
+config CRYPTO_LIB_CURVE25519_GENERIC
+	tristate
+	help
+	  This symbol can be depended upon by arch implementations of the
+	  Curve25519 library interface that require the generic code as a
+	  fallback, e.g., for SIMD implementations. If no arch specific
+	  implementation is enabled, this implementation serves the users
+	  of CRYPTO_LIB_CURVE25519.
+
+config CRYPTO_LIB_CURVE25519
+	tristate "Curve25519 scalar multiplication library"
+	depends on CRYPTO_ARCH_HAVE_LIB_CURVE25519 || !CRYPTO_ARCH_HAVE_LIB_CURVE25519
+	select CRYPTO_LIB_CURVE25519_GENERIC if CRYPTO_ARCH_HAVE_LIB_CURVE25519=n
+	help
+	  Enable the Curve25519 library interface. This interface may be
+	  fulfilled by either the generic implementation or an arch-specific
+	  one, if one is available and enabled.
+
+config CRYPTO_LIB_DES
+	tristate
+
+config CRYPTO_LIB_POLY1305_RSIZE
+	int
+	default 2 if MIPS
+	default 4 if X86_64
+	default 9 if ARM || ARM64
+	default 1
+
+config CRYPTO_ARCH_HAVE_LIB_POLY1305
+	tristate
+	help
+	  Declares whether the architecture provides an arch-specific
+	  accelerated implementation of the Poly1305 library interface,
+	  either builtin or as a module.
+
+config CRYPTO_LIB_POLY1305_GENERIC
+	tristate
+	help
+	  This symbol can be depended upon by arch implementations of the
+	  Poly1305 library interface that require the generic code as a
+	  fallback, e.g., for SIMD implementations. If no arch specific
+	  implementation is enabled, this implementation serves the users
+	  of CRYPTO_LIB_POLY1305.
+
+config CRYPTO_LIB_POLY1305
+	tristate "Poly1305 library interface"
+	depends on CRYPTO_ARCH_HAVE_LIB_POLY1305 || !CRYPTO_ARCH_HAVE_LIB_POLY1305
+	select CRYPTO_LIB_POLY1305_GENERIC if CRYPTO_ARCH_HAVE_LIB_POLY1305=n
+	help
+	  Enable the Poly1305 library interface. This interface may be fulfilled
+	  by either the generic implementation or an arch-specific one, if one
+	  is available and enabled.
+
+config CRYPTO_LIB_CHACHA20POLY1305
+	tristate "ChaCha20-Poly1305 AEAD support (8-byte nonce library version)"
+	depends on CRYPTO_ARCH_HAVE_LIB_CHACHA || !CRYPTO_ARCH_HAVE_LIB_CHACHA
+	depends on CRYPTO_ARCH_HAVE_LIB_POLY1305 || !CRYPTO_ARCH_HAVE_LIB_POLY1305
+	select CRYPTO_LIB_CHACHA
+	select CRYPTO_LIB_POLY1305
+
+config CRYPTO_LIB_SHA256
+	tristate
diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index cbe0b6a6450d..34a701ab8b92 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -1,13 +1,39 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-$(CONFIG_CRYPTO_LIB_AES) += libaes.o
-libaes-y := aes.o
+# chacha is used by the /dev/random driver which is always builtin
+obj-y						+= chacha.o
+obj-$(CONFIG_CRYPTO_LIB_CHACHA_GENERIC)		+= libchacha.o
 
-obj-$(CONFIG_CRYPTO_LIB_ARC4) += libarc4.o
-libarc4-y := arc4.o
+obj-$(CONFIG_CRYPTO_LIB_AES)			+= libaes.o
+libaes-y					:= aes.o
 
-obj-$(CONFIG_CRYPTO_LIB_DES) += libdes.o
-libdes-y := des.o
+obj-$(CONFIG_CRYPTO_LIB_ARC4)			+= libarc4.o
+libarc4-y					:= arc4.o
 
-obj-$(CONFIG_CRYPTO_LIB_SHA256) += libsha256.o
-libsha256-y := sha256.o
+obj-$(CONFIG_CRYPTO_LIB_BLAKE2S_GENERIC)	+= libblake2s-generic.o
+libblake2s-generic-y				+= blake2s-generic.o
+
+obj-$(CONFIG_CRYPTO_LIB_BLAKE2S)		+= libblake2s.o
+libblake2s-y					+= blake2s.o
+
+obj-$(CONFIG_CRYPTO_LIB_CHACHA20POLY1305)	+= libchacha20poly1305.o
+libchacha20poly1305-y				+= chacha20poly1305.o
+
+obj-$(CONFIG_CRYPTO_LIB_CURVE25519_GENERIC)	+= libcurve25519.o
+libcurve25519-y					:= curve25519-fiat32.o
+libcurve25519-$(CONFIG_ARCH_SUPPORTS_INT128)	:= curve25519-hacl64.o
+libcurve25519-y					+= curve25519.o
+
+obj-$(CONFIG_CRYPTO_LIB_DES)			+= libdes.o
+libdes-y					:= des.o
+
+obj-$(CONFIG_CRYPTO_LIB_POLY1305_GENERIC)	+= libpoly1305.o
+libpoly1305-y					:= poly1305.o
+
+obj-$(CONFIG_CRYPTO_LIB_SHA256)			+= libsha256.o
+libsha256-y					:= sha256.o
+
+ifneq ($(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS),y)
+libblake2s-y					+= blake2s-selftest.o
+libchacha20poly1305-y				+= chacha20poly1305-selftest.o
+endif
diff --git a/lib/crypto/blake2s-generic.c b/lib/crypto/blake2s-generic.c
new file mode 100644
index 000000000000..04ff8df24513
--- /dev/null
+++ b/lib/crypto/blake2s-generic.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This is an implementation of the BLAKE2s hash and PRF functions.
+ *
+ * Information: https://blake2.net/
+ *
+ */
+
+#include <crypto/internal/blake2s.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/bug.h>
+#include <asm/unaligned.h>
+
+static const u8 blake2s_sigma[10][16] = {
+	{ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 },
+	{ 14, 10, 4, 8, 9, 15, 13, 6, 1, 12, 0, 2, 11, 7, 5, 3 },
+	{ 11, 8, 12, 0, 5, 2, 15, 13, 10, 14, 3, 6, 7, 1, 9, 4 },
+	{ 7, 9, 3, 1, 13, 12, 11, 14, 2, 6, 5, 10, 4, 0, 15, 8 },
+	{ 9, 0, 5, 7, 2, 4, 10, 15, 14, 1, 11, 12, 6, 8, 3, 13 },
+	{ 2, 12, 6, 10, 0, 11, 8, 3, 4, 13, 7, 5, 15, 14, 1, 9 },
+	{ 12, 5, 1, 15, 14, 13, 4, 10, 0, 7, 6, 3, 9, 2, 8, 11 },
+	{ 13, 11, 7, 14, 12, 1, 3, 9, 5, 0, 15, 4, 8, 6, 2, 10 },
+	{ 6, 15, 14, 9, 11, 3, 0, 8, 12, 2, 13, 7, 1, 4, 10, 5 },
+	{ 10, 2, 8, 4, 7, 6, 1, 5, 15, 11, 9, 14, 3, 12, 13, 0 },
+};
+
+static inline void blake2s_increment_counter(struct blake2s_state *state,
+					     const u32 inc)
+{
+	state->t[0] += inc;
+	state->t[1] += (state->t[0] < inc);
+}
+
+void blake2s_compress_generic(struct blake2s_state *state,const u8 *block,
+			      size_t nblocks, const u32 inc)
+{
+	u32 m[16];
+	u32 v[16];
+	int i;
+
+	WARN_ON(IS_ENABLED(DEBUG) &&
+		(nblocks > 1 && inc != BLAKE2S_BLOCK_SIZE));
+
+	while (nblocks > 0) {
+		blake2s_increment_counter(state, inc);
+		memcpy(m, block, BLAKE2S_BLOCK_SIZE);
+		le32_to_cpu_array(m, ARRAY_SIZE(m));
+		memcpy(v, state->h, 32);
+		v[ 8] = BLAKE2S_IV0;
+		v[ 9] = BLAKE2S_IV1;
+		v[10] = BLAKE2S_IV2;
+		v[11] = BLAKE2S_IV3;
+		v[12] = BLAKE2S_IV4 ^ state->t[0];
+		v[13] = BLAKE2S_IV5 ^ state->t[1];
+		v[14] = BLAKE2S_IV6 ^ state->f[0];
+		v[15] = BLAKE2S_IV7 ^ state->f[1];
+
+#define G(r, i, a, b, c, d) do { \
+	a += b + m[blake2s_sigma[r][2 * i + 0]]; \
+	d = ror32(d ^ a, 16); \
+	c += d; \
+	b = ror32(b ^ c, 12); \
+	a += b + m[blake2s_sigma[r][2 * i + 1]]; \
+	d = ror32(d ^ a, 8); \
+	c += d; \
+	b = ror32(b ^ c, 7); \
+} while (0)
+
+#define ROUND(r) do { \
+	G(r, 0, v[0], v[ 4], v[ 8], v[12]); \
+	G(r, 1, v[1], v[ 5], v[ 9], v[13]); \
+	G(r, 2, v[2], v[ 6], v[10], v[14]); \
+	G(r, 3, v[3], v[ 7], v[11], v[15]); \
+	G(r, 4, v[0], v[ 5], v[10], v[15]); \
+	G(r, 5, v[1], v[ 6], v[11], v[12]); \
+	G(r, 6, v[2], v[ 7], v[ 8], v[13]); \
+	G(r, 7, v[3], v[ 4], v[ 9], v[14]); \
+} while (0)
+		ROUND(0);
+		ROUND(1);
+		ROUND(2);
+		ROUND(3);
+		ROUND(4);
+		ROUND(5);
+		ROUND(6);
+		ROUND(7);
+		ROUND(8);
+		ROUND(9);
+
+#undef G
+#undef ROUND
+
+		for (i = 0; i < 8; ++i)
+			state->h[i] ^= v[i] ^ v[i + 8];
+
+		block += BLAKE2S_BLOCK_SIZE;
+		--nblocks;
+	}
+}
+
+EXPORT_SYMBOL(blake2s_compress_generic);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("BLAKE2s hash function");
+MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
diff --git a/lib/crypto/blake2s-selftest.c b/lib/crypto/blake2s-selftest.c
new file mode 100644
index 000000000000..79ef404a990d
--- /dev/null
+++ b/lib/crypto/blake2s-selftest.c
@@ -0,0 +1,622 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <crypto/blake2s.h>
+#include <linux/string.h>
+
+/*
+ * blake2s_testvecs[] generated with the program below (using libb2-dev and
+ * libssl-dev [OpenSSL])
+ *
+ * #include <blake2.h>
+ * #include <stdint.h>
+ * #include <stdio.h>
+ *
+ * #include <openssl/evp.h>
+ * #include <openssl/hmac.h>
+ *
+ * #define BLAKE2S_TESTVEC_COUNT	256
+ *
+ * static void print_vec(const uint8_t vec[], int len)
+ * {
+ *	int i;
+ *
+ *	printf("  { ");
+ *	for (i = 0; i < len; i++) {
+ *		if (i && (i % 12) == 0)
+ *			printf("\n    ");
+ *		printf("0x%02x, ", vec[i]);
+ *	}
+ *	printf("},\n");
+ * }
+ *
+ * int main(void)
+ * {
+ *	uint8_t key[BLAKE2S_KEYBYTES];
+ *	uint8_t buf[BLAKE2S_TESTVEC_COUNT];
+ *	uint8_t hash[BLAKE2S_OUTBYTES];
+ *	int i, j;
+ *
+ *	key[0] = key[1] = 1;
+ *	for (i = 2; i < BLAKE2S_KEYBYTES; ++i)
+ *		key[i] = key[i - 2] + key[i - 1];
+ *
+ *	for (i = 0; i < BLAKE2S_TESTVEC_COUNT; ++i)
+ *		buf[i] = (uint8_t)i;
+ *
+ *	printf("static const u8 blake2s_testvecs[][BLAKE2S_HASH_SIZE] __initconst = {\n");
+ *
+ *	for (i = 0; i < BLAKE2S_TESTVEC_COUNT; ++i) {
+ *		int outlen = 1 + i % BLAKE2S_OUTBYTES;
+ *		int keylen = (13 * i) % (BLAKE2S_KEYBYTES + 1);
+ *
+ *		blake2s(hash, buf, key + BLAKE2S_KEYBYTES - keylen, outlen, i,
+ *			keylen);
+ *		print_vec(hash, outlen);
+ *	}
+ *	printf("};\n\n");
+ *
+ *	printf("static const u8 blake2s_hmac_testvecs[][BLAKE2S_HASH_SIZE] __initconst = {\n");
+ *
+ *	HMAC(EVP_blake2s256(), key, sizeof(key), buf, sizeof(buf), hash, NULL);
+ *	print_vec(hash, BLAKE2S_OUTBYTES);
+ *
+ *	HMAC(EVP_blake2s256(), buf, sizeof(buf), key, sizeof(key), hash, NULL);
+ *	print_vec(hash, BLAKE2S_OUTBYTES);
+ *
+ *	printf("};\n");
+ *
+ *	return 0;
+ *}
+ */
+static const u8 blake2s_testvecs[][BLAKE2S_HASH_SIZE] __initconst = {
+  { 0xa1, },
+  { 0x7c, 0x89, },
+  { 0x74, 0x0e, 0xd4, },
+  { 0x47, 0x0c, 0x21, 0x15, },
+  { 0x18, 0xd6, 0x9c, 0xa6, 0xc4, },
+  { 0x13, 0x5d, 0x16, 0x63, 0x2e, 0xf9, },
+  { 0x2c, 0xb5, 0x04, 0xb7, 0x99, 0xe2, 0x73, },
+  { 0x9a, 0x0f, 0xd2, 0x39, 0xd6, 0x68, 0x1b, 0x92, },
+  { 0xc8, 0xde, 0x7a, 0xea, 0x2f, 0xf4, 0xd2, 0xe3, 0x2b, },
+  { 0x5b, 0xf9, 0x43, 0x52, 0x0c, 0x12, 0xba, 0xb5, 0x93, 0x9f, },
+  { 0xc6, 0x2c, 0x4e, 0x80, 0xfc, 0x32, 0x5b, 0x33, 0xb8, 0xb8, 0x0a, },
+  { 0xa7, 0x5c, 0xfd, 0x3a, 0xcc, 0xbf, 0x90, 0xca, 0xb7, 0x97, 0xde, 0xd8, },
+  { 0x66, 0xca, 0x3c, 0xc4, 0x19, 0xef, 0x92, 0x66, 0x3f, 0x21, 0x8f, 0xda,
+    0xb7, },
+  { 0xba, 0xe5, 0xbb, 0x30, 0x25, 0x94, 0x6d, 0xc3, 0x89, 0x09, 0xc4, 0x25,
+    0x52, 0x3e, },
+  { 0xa2, 0xef, 0x0e, 0x52, 0x0b, 0x5f, 0xa2, 0x01, 0x6d, 0x0a, 0x25, 0xbc,
+    0x57, 0xe2, 0x27, },
+  { 0x4f, 0xe0, 0xf9, 0x52, 0x12, 0xda, 0x84, 0xb7, 0xab, 0xae, 0xb0, 0xa6,
+    0x47, 0x2a, 0xc7, 0xf5, },
+  { 0x56, 0xe7, 0xa8, 0x1c, 0x4c, 0xca, 0xed, 0x90, 0x31, 0xec, 0x87, 0x43,
+    0xe7, 0x72, 0x08, 0xec, 0xbe, },
+  { 0x7e, 0xdf, 0x80, 0x1c, 0x93, 0x33, 0xfd, 0x53, 0x44, 0xba, 0xfd, 0x96,
+    0xe1, 0xbb, 0xb5, 0x65, 0xa5, 0x00, },
+  { 0xec, 0x6b, 0xed, 0xf7, 0x7b, 0x62, 0x1d, 0x7d, 0xf4, 0x82, 0xf3, 0x1e,
+    0x18, 0xff, 0x2b, 0xc4, 0x06, 0x20, 0x2a, },
+  { 0x74, 0x98, 0xd7, 0x68, 0x63, 0xed, 0x87, 0xe4, 0x5d, 0x8d, 0x9e, 0x1d,
+    0xfd, 0x2a, 0xbb, 0x86, 0xac, 0xe9, 0x2a, 0x89, },
+  { 0x89, 0xc3, 0x88, 0xce, 0x2b, 0x33, 0x1e, 0x10, 0xd1, 0x37, 0x20, 0x86,
+    0x28, 0x43, 0x70, 0xd9, 0xfb, 0x96, 0xd9, 0xb5, 0xd3, },
+  { 0xcb, 0x56, 0x74, 0x41, 0x8d, 0x80, 0x01, 0x9a, 0x6b, 0x38, 0xe1, 0x41,
+    0xad, 0x9c, 0x62, 0x74, 0xce, 0x35, 0xd5, 0x6c, 0x89, 0x6e, },
+  { 0x79, 0xaf, 0x94, 0x59, 0x99, 0x26, 0xe1, 0xc9, 0x34, 0xfe, 0x7c, 0x22,
+    0xf7, 0x43, 0xd7, 0x65, 0xd4, 0x48, 0x18, 0xac, 0x3d, 0xfd, 0x93, },
+  { 0x85, 0x0d, 0xff, 0xb8, 0x3e, 0x87, 0x41, 0xb0, 0x95, 0xd3, 0x3d, 0x00,
+    0x47, 0x55, 0x9e, 0xd2, 0x69, 0xea, 0xbf, 0xe9, 0x7a, 0x2d, 0x61, 0x45, },
+  { 0x03, 0xe0, 0x85, 0xec, 0x54, 0xb5, 0x16, 0x53, 0xa8, 0xc4, 0x71, 0xe9,
+    0x6a, 0xe7, 0xcb, 0xc4, 0x15, 0x02, 0xfc, 0x34, 0xa4, 0xa4, 0x28, 0x13,
+    0xd1, },
+  { 0xe3, 0x34, 0x4b, 0xe1, 0xd0, 0x4b, 0x55, 0x61, 0x8f, 0xc0, 0x24, 0x05,
+    0xe6, 0xe0, 0x3d, 0x70, 0x24, 0x4d, 0xda, 0xb8, 0x91, 0x05, 0x29, 0x07,
+    0x01, 0x3e, },
+  { 0x61, 0xff, 0x01, 0x72, 0xb1, 0x4d, 0xf6, 0xfe, 0xd1, 0xd1, 0x08, 0x74,
+    0xe6, 0x91, 0x44, 0xeb, 0x61, 0xda, 0x40, 0xaf, 0xfc, 0x8c, 0x91, 0x6b,
+    0xec, 0x13, 0xed, },
+  { 0xd4, 0x40, 0xd2, 0xa0, 0x7f, 0xc1, 0x58, 0x0c, 0x85, 0xa0, 0x86, 0xc7,
+    0x86, 0xb9, 0x61, 0xc9, 0xea, 0x19, 0x86, 0x1f, 0xab, 0x07, 0xce, 0x37,
+    0x72, 0x67, 0x09, 0xfc, },
+  { 0x9e, 0xf8, 0x18, 0x67, 0x93, 0x10, 0x9b, 0x39, 0x75, 0xe8, 0x8b, 0x38,
+    0x82, 0x7d, 0xb8, 0xb7, 0xa5, 0xaf, 0xe6, 0x6a, 0x22, 0x5e, 0x1f, 0x9c,
+    0x95, 0x29, 0x19, 0xf2, 0x4b, },
+  { 0xc8, 0x62, 0x25, 0xf5, 0x98, 0xc9, 0xea, 0xe5, 0x29, 0x3a, 0xd3, 0x22,
+    0xeb, 0xeb, 0x07, 0x7c, 0x15, 0x07, 0xee, 0x15, 0x61, 0xbb, 0x05, 0x30,
+    0x99, 0x7f, 0x11, 0xf6, 0x0a, 0x1d, },
+  { 0x68, 0x70, 0xf7, 0x90, 0xa1, 0x8b, 0x1f, 0x0f, 0xbb, 0xce, 0xd2, 0x0e,
+    0x33, 0x1f, 0x7f, 0xa9, 0x78, 0xa8, 0xa6, 0x81, 0x66, 0xab, 0x8d, 0xcd,
+    0x58, 0x55, 0x3a, 0x0b, 0x7a, 0xdb, 0xb5, },
+  { 0xdd, 0x35, 0xd2, 0xb4, 0xf6, 0xc7, 0xea, 0xab, 0x64, 0x24, 0x4e, 0xfe,
+    0xe5, 0x3d, 0x4e, 0x95, 0x8b, 0x6d, 0x6c, 0xbc, 0xb0, 0xf8, 0x88, 0x61,
+    0x09, 0xb7, 0x78, 0xa3, 0x31, 0xfe, 0xd9, 0x2f, },
+  { 0x0a, },
+  { 0x6e, 0xd4, },
+  { 0x64, 0xe9, 0xd1, },
+  { 0x30, 0xdd, 0x71, 0xef, },
+  { 0x11, 0xb5, 0x0c, 0x87, 0xc9, },
+  { 0x06, 0x1c, 0x6d, 0x04, 0x82, 0xd0, },
+  { 0x5c, 0x42, 0x0b, 0xee, 0xc5, 0x9c, 0xb2, },
+  { 0xe8, 0x29, 0xd6, 0xb4, 0x5d, 0xf7, 0x2b, 0x93, },
+  { 0x18, 0xca, 0x27, 0x72, 0x43, 0x39, 0x16, 0xbc, 0x6a, },
+  { 0x39, 0x8f, 0xfd, 0x64, 0xf5, 0x57, 0x23, 0xb0, 0x45, 0xf8, },
+  { 0xbb, 0x3a, 0x78, 0x6b, 0x02, 0x1d, 0x0b, 0x16, 0xe3, 0xb2, 0x9a, },
+  { 0xb8, 0xb4, 0x0b, 0xe5, 0xd4, 0x1d, 0x0d, 0x85, 0x49, 0x91, 0x35, 0xfa, },
+  { 0x6d, 0x48, 0x2a, 0x0c, 0x42, 0x08, 0xbd, 0xa9, 0x78, 0x6f, 0x18, 0xaf,
+    0xe2, },
+  { 0x10, 0x45, 0xd4, 0x58, 0x88, 0xec, 0x4e, 0x1e, 0xf6, 0x14, 0x92, 0x64,
+    0x7e, 0xb0, },
+  { 0x8b, 0x0b, 0x95, 0xee, 0x92, 0xc6, 0x3b, 0x91, 0xf1, 0x1e, 0xeb, 0x51,
+    0x98, 0x0a, 0x8d, },
+  { 0xa3, 0x50, 0x4d, 0xa5, 0x1d, 0x03, 0x68, 0xe9, 0x57, 0x78, 0xd6, 0x04,
+    0xf1, 0xc3, 0x94, 0xd8, },
+  { 0xb8, 0x66, 0x6e, 0xdd, 0x46, 0x15, 0xae, 0x3d, 0x83, 0x7e, 0xcf, 0xe7,
+    0x2c, 0xe8, 0x8f, 0xc7, 0x34, },
+  { 0x2e, 0xc0, 0x1f, 0x29, 0xea, 0xf6, 0xb9, 0xe2, 0xc2, 0x93, 0xeb, 0x41,
+    0x0d, 0xf0, 0x0a, 0x13, 0x0e, 0xa2, },
+  { 0x71, 0xb8, 0x33, 0xa9, 0x1b, 0xac, 0xf1, 0xb5, 0x42, 0x8f, 0x5e, 0x81,
+    0x34, 0x43, 0xb7, 0xa4, 0x18, 0x5c, 0x47, },
+  { 0xda, 0x45, 0xb8, 0x2e, 0x82, 0x1e, 0xc0, 0x59, 0x77, 0x9d, 0xfa, 0xb4,
+    0x1c, 0x5e, 0xa0, 0x2b, 0x33, 0x96, 0x5a, 0x58, },
+  { 0xe3, 0x09, 0x05, 0xa9, 0xeb, 0x48, 0x13, 0xad, 0x71, 0x88, 0x81, 0x9a,
+    0x3e, 0x2c, 0xe1, 0x23, 0x99, 0x13, 0x35, 0x9f, 0xb5, },
+  { 0xb7, 0x86, 0x2d, 0x16, 0xe1, 0x04, 0x00, 0x47, 0x47, 0x61, 0x31, 0xfb,
+    0x14, 0xac, 0xd8, 0xe9, 0xe3, 0x49, 0xbd, 0xf7, 0x9c, 0x3f, },
+  { 0x7f, 0xd9, 0x95, 0xa8, 0xa7, 0xa0, 0xcc, 0xba, 0xef, 0xb1, 0x0a, 0xa9,
+    0x21, 0x62, 0x08, 0x0f, 0x1b, 0xff, 0x7b, 0x9d, 0xae, 0xb2, 0x95, },
+  { 0x85, 0x99, 0xea, 0x33, 0xe0, 0x56, 0xff, 0x13, 0xc6, 0x61, 0x8c, 0xf9,
+    0x57, 0x05, 0x03, 0x11, 0xf9, 0xfb, 0x3a, 0xf7, 0xce, 0xbb, 0x52, 0x30, },
+  { 0xb2, 0x72, 0x9c, 0xf8, 0x77, 0x4e, 0x8f, 0x6b, 0x01, 0x6c, 0xff, 0x4e,
+    0x4f, 0x02, 0xd2, 0xbc, 0xeb, 0x51, 0x28, 0x99, 0x50, 0xab, 0xc4, 0x42,
+    0xe3, },
+  { 0x8b, 0x0a, 0xb5, 0x90, 0x8f, 0xf5, 0x7b, 0xdd, 0xba, 0x47, 0x37, 0xc9,
+    0x2a, 0xd5, 0x4b, 0x25, 0x08, 0x8b, 0x02, 0x17, 0xa7, 0x9e, 0x6b, 0x6e,
+    0xe3, 0x90, },
+  { 0x90, 0xdd, 0xf7, 0x75, 0xa7, 0xa3, 0x99, 0x5e, 0x5b, 0x7d, 0x75, 0xc3,
+    0x39, 0x6b, 0xa0, 0xe2, 0x44, 0x53, 0xb1, 0x9e, 0xc8, 0xf1, 0x77, 0x10,
+    0x58, 0x06, 0x9a, },
+  { 0x99, 0x52, 0xf0, 0x49, 0xa8, 0x8c, 0xec, 0xa6, 0x97, 0x32, 0x13, 0xb5,
+    0xf7, 0xa3, 0x8e, 0xfb, 0x4b, 0x59, 0x31, 0x3d, 0x01, 0x59, 0x98, 0x5d,
+    0x53, 0x03, 0x1a, 0x39, },
+  { 0x9f, 0xe0, 0xc2, 0xe5, 0x5d, 0x93, 0xd6, 0x9b, 0x47, 0x8f, 0x9b, 0xe0,
+    0x26, 0x35, 0x84, 0x20, 0x1d, 0xc5, 0x53, 0x10, 0x0f, 0x22, 0xb9, 0xb5,
+    0xd4, 0x36, 0xb1, 0xac, 0x73, },
+  { 0x30, 0x32, 0x20, 0x3b, 0x10, 0x28, 0xec, 0x1f, 0x4f, 0x9b, 0x47, 0x59,
+    0xeb, 0x7b, 0xee, 0x45, 0xfb, 0x0c, 0x49, 0xd8, 0x3d, 0x69, 0xbd, 0x90,
+    0x2c, 0xf0, 0x9e, 0x8d, 0xbf, 0xd5, },
+  { 0x2a, 0x37, 0x73, 0x7f, 0xf9, 0x96, 0x19, 0xaa, 0x25, 0xd8, 0x13, 0x28,
+    0x01, 0x29, 0x89, 0xdf, 0x6e, 0x0c, 0x9b, 0x43, 0x44, 0x51, 0xe9, 0x75,
+    0x26, 0x0c, 0xb7, 0x87, 0x66, 0x0b, 0x5f, },
+  { 0x23, 0xdf, 0x96, 0x68, 0x91, 0x86, 0xd0, 0x93, 0x55, 0x33, 0x24, 0xf6,
+    0xba, 0x08, 0x75, 0x5b, 0x59, 0x11, 0x69, 0xb8, 0xb9, 0xe5, 0x2c, 0x77,
+    0x02, 0xf6, 0x47, 0xee, 0x81, 0xdd, 0xb9, 0x06, },
+  { 0x9d, },
+  { 0x9d, 0x7d, },
+  { 0xfd, 0xc3, 0xda, },
+  { 0xe8, 0x82, 0xcd, 0x21, },
+  { 0xc3, 0x1d, 0x42, 0x4c, 0x74, },
+  { 0xe9, 0xda, 0xf1, 0xa2, 0xe5, 0x7c, },
+  { 0x52, 0xb8, 0x6f, 0x81, 0x5c, 0x3a, 0x4c, },
+  { 0x5b, 0x39, 0x26, 0xfc, 0x92, 0x5e, 0xe0, 0x49, },
+  { 0x59, 0xe4, 0x7c, 0x93, 0x1c, 0xf9, 0x28, 0x93, 0xde, },
+  { 0xde, 0xdf, 0xb2, 0x43, 0x61, 0x0b, 0x86, 0x16, 0x4c, 0x2e, },
+  { 0x14, 0x8f, 0x75, 0x51, 0xaf, 0xb9, 0xee, 0x51, 0x5a, 0xae, 0x23, },
+  { 0x43, 0x5f, 0x50, 0xd5, 0x70, 0xb0, 0x5b, 0x87, 0xf5, 0xd9, 0xb3, 0x6d, },
+  { 0x66, 0x0a, 0x64, 0x93, 0x79, 0x71, 0x94, 0x40, 0xb7, 0x68, 0x2d, 0xd3,
+    0x63, },
+  { 0x15, 0x00, 0xc4, 0x0c, 0x7d, 0x1b, 0x10, 0xa9, 0x73, 0x1b, 0x90, 0x6f,
+    0xe6, 0xa9, },
+  { 0x34, 0x75, 0xf3, 0x86, 0x8f, 0x56, 0xcf, 0x2a, 0x0a, 0xf2, 0x62, 0x0a,
+    0xf6, 0x0e, 0x20, },
+  { 0xb1, 0xde, 0xc9, 0xf5, 0xdb, 0xf3, 0x2f, 0x4c, 0xd6, 0x41, 0x7d, 0x39,
+    0x18, 0x3e, 0xc7, 0xc3, },
+  { 0xc5, 0x89, 0xb2, 0xf8, 0xb8, 0xc0, 0xa3, 0xb9, 0x3b, 0x10, 0x6d, 0x7c,
+    0x92, 0xfc, 0x7f, 0x34, 0x41, },
+  { 0xc4, 0xd8, 0xef, 0xba, 0xef, 0xd2, 0xaa, 0xc5, 0x6c, 0x8e, 0x3e, 0xbb,
+    0x12, 0xfc, 0x0f, 0x72, 0xbf, 0x0f, },
+  { 0xdd, 0x91, 0xd1, 0x15, 0x9e, 0x7d, 0xf8, 0xc1, 0xb9, 0x14, 0x63, 0x96,
+    0xb5, 0xcb, 0x83, 0x1d, 0x35, 0x1c, 0xec, },
+  { 0xa9, 0xf8, 0x52, 0xc9, 0x67, 0x76, 0x2b, 0xad, 0xfb, 0xd8, 0x3a, 0xa6,
+    0x74, 0x02, 0xae, 0xb8, 0x25, 0x2c, 0x63, 0x49, },
+  { 0x77, 0x1f, 0x66, 0x70, 0xfd, 0x50, 0x29, 0xaa, 0xeb, 0xdc, 0xee, 0xba,
+    0x75, 0x98, 0xdc, 0x93, 0x12, 0x3f, 0xdc, 0x7c, 0x38, },
+  { 0xe2, 0xe1, 0x89, 0x5c, 0x37, 0x38, 0x6a, 0xa3, 0x40, 0xac, 0x3f, 0xb0,
+    0xca, 0xfc, 0xa7, 0xf3, 0xea, 0xf9, 0x0f, 0x5d, 0x8e, 0x39, },
+  { 0x0f, 0x67, 0xc8, 0x38, 0x01, 0xb1, 0xb7, 0xb8, 0xa2, 0xe7, 0x0a, 0x6d,
+    0xd2, 0x63, 0x69, 0x9e, 0xcc, 0xf0, 0xf2, 0xbe, 0x9b, 0x98, 0xdd, },
+  { 0x13, 0xe1, 0x36, 0x30, 0xfe, 0xc6, 0x01, 0x8a, 0xa1, 0x63, 0x96, 0x59,
+    0xc2, 0xa9, 0x68, 0x3f, 0x58, 0xd4, 0x19, 0x0c, 0x40, 0xf3, 0xde, 0x02, },
+  { 0xa3, 0x9e, 0xce, 0xda, 0x42, 0xee, 0x8c, 0x6c, 0x5a, 0x7d, 0xdc, 0x89,
+    0x02, 0x77, 0xdd, 0xe7, 0x95, 0xbb, 0xff, 0x0d, 0xa4, 0xb5, 0x38, 0x1e,
+    0xaf, },
+  { 0x9a, 0xf6, 0xb5, 0x9a, 0x4f, 0xa9, 0x4f, 0x2c, 0x35, 0x3c, 0x24, 0xdc,
+    0x97, 0x6f, 0xd9, 0xa1, 0x7d, 0x1a, 0x85, 0x0b, 0xf5, 0xda, 0x2e, 0xe7,
+    0xb1, 0x1d, },
+  { 0x84, 0x1e, 0x8e, 0x3d, 0x45, 0xa5, 0xf2, 0x27, 0xf3, 0x31, 0xfe, 0xb9,
+    0xfb, 0xc5, 0x45, 0x99, 0x99, 0xdd, 0x93, 0x43, 0x02, 0xee, 0x58, 0xaf,
+    0xee, 0x6a, 0xbe, },
+  { 0x07, 0x2f, 0xc0, 0xa2, 0x04, 0xc4, 0xab, 0x7c, 0x26, 0xbb, 0xa8, 0xd8,
+    0xe3, 0x1c, 0x75, 0x15, 0x64, 0x5d, 0x02, 0x6a, 0xf0, 0x86, 0xe9, 0xcd,
+    0x5c, 0xef, 0xa3, 0x25, },
+  { 0x2f, 0x3b, 0x1f, 0xb5, 0x91, 0x8f, 0x86, 0xe0, 0xdc, 0x31, 0x48, 0xb6,
+    0xa1, 0x8c, 0xfd, 0x75, 0xbb, 0x7d, 0x3d, 0xc1, 0xf0, 0x10, 0x9a, 0xd8,
+    0x4b, 0x0e, 0xe3, 0x94, 0x9f, },
+  { 0x29, 0xbb, 0x8f, 0x6c, 0xd1, 0xf2, 0xb6, 0xaf, 0xe5, 0xe3, 0x2d, 0xdc,
+    0x6f, 0xa4, 0x53, 0x88, 0xd8, 0xcf, 0x4d, 0x45, 0x42, 0x62, 0xdb, 0xdf,
+    0xf8, 0x45, 0xc2, 0x13, 0xec, 0x35, },
+  { 0x06, 0x3c, 0xe3, 0x2c, 0x15, 0xc6, 0x43, 0x03, 0x81, 0xfb, 0x08, 0x76,
+    0x33, 0xcb, 0x02, 0xc1, 0xba, 0x33, 0xe5, 0xe0, 0xd1, 0x92, 0xa8, 0x46,
+    0x28, 0x3f, 0x3e, 0x9d, 0x2c, 0x44, 0x54, },
+  { 0xea, 0xbb, 0x96, 0xf8, 0xd1, 0x8b, 0x04, 0x11, 0x40, 0x78, 0x42, 0x02,
+    0x19, 0xd1, 0xbc, 0x65, 0x92, 0xd3, 0xc3, 0xd6, 0xd9, 0x19, 0xe7, 0xc3,
+    0x40, 0x97, 0xbd, 0xd4, 0xed, 0xfa, 0x5e, 0x28, },
+  { 0x02, },
+  { 0x52, 0xa8, },
+  { 0x38, 0x25, 0x0d, },
+  { 0xe3, 0x04, 0xd4, 0x92, },
+  { 0x97, 0xdb, 0xf7, 0x81, 0xca, },
+  { 0x8a, 0x56, 0x9d, 0x62, 0x56, 0xcc, },
+  { 0xa1, 0x8e, 0x3c, 0x72, 0x8f, 0x63, 0x03, },
+  { 0xf7, 0xf3, 0x39, 0x09, 0x0a, 0xa1, 0xbb, 0x23, },
+  { 0x6b, 0x03, 0xc0, 0xe9, 0xd9, 0x83, 0x05, 0x22, 0x01, },
+  { 0x1b, 0x4b, 0xf5, 0xd6, 0x4f, 0x05, 0x75, 0x91, 0x4c, 0x7f, },
+  { 0x4c, 0x8c, 0x25, 0x20, 0x21, 0xcb, 0xc2, 0x4b, 0x3a, 0x5b, 0x8d, },
+  { 0x56, 0xe2, 0x77, 0xa0, 0xb6, 0x9f, 0x81, 0xec, 0x83, 0x75, 0xc4, 0xf9, },
+  { 0x71, 0x70, 0x0f, 0xad, 0x4d, 0x35, 0x81, 0x9d, 0x88, 0x69, 0xf9, 0xaa,
+    0xd3, },
+  { 0x50, 0x6e, 0x86, 0x6e, 0x43, 0xc0, 0xc2, 0x44, 0xc2, 0xe2, 0xa0, 0x1c,
+    0xb7, 0x9a, },
+  { 0xe4, 0x7e, 0x72, 0xc6, 0x12, 0x8e, 0x7c, 0xfc, 0xbd, 0xe2, 0x08, 0x31,
+    0x3d, 0x47, 0x3d, },
+  { 0x08, 0x97, 0x5b, 0x80, 0xae, 0xc4, 0x1d, 0x50, 0x77, 0xdf, 0x1f, 0xd0,
+    0x24, 0xf0, 0x17, 0xc0, },
+  { 0x01, 0xb6, 0x29, 0xf4, 0xaf, 0x78, 0x5f, 0xb6, 0x91, 0xdd, 0x76, 0x76,
+    0xd2, 0xfd, 0x0c, 0x47, 0x40, },
+  { 0xa1, 0xd8, 0x09, 0x97, 0x7a, 0xa6, 0xc8, 0x94, 0xf6, 0x91, 0x7b, 0xae,
+    0x2b, 0x9f, 0x0d, 0x83, 0x48, 0xf7, },
+  { 0x12, 0xd5, 0x53, 0x7d, 0x9a, 0xb0, 0xbe, 0xd9, 0xed, 0xe9, 0x9e, 0xee,
+    0x61, 0x5b, 0x42, 0xf2, 0xc0, 0x73, 0xc0, },
+  { 0xd5, 0x77, 0xd6, 0x5c, 0x6e, 0xa5, 0x69, 0x2b, 0x3b, 0x8c, 0xd6, 0x7d,
+    0x1d, 0xbe, 0x2c, 0xa1, 0x02, 0x21, 0xcd, 0x29, },
+  { 0xa4, 0x98, 0x80, 0xca, 0x22, 0xcf, 0x6a, 0xab, 0x5e, 0x40, 0x0d, 0x61,
+    0x08, 0x21, 0xef, 0xc0, 0x6c, 0x52, 0xb4, 0xb0, 0x53, },
+  { 0xbf, 0xaf, 0x8f, 0x3b, 0x7a, 0x97, 0x33, 0xe5, 0xca, 0x07, 0x37, 0xfd,
+    0x15, 0xdf, 0xce, 0x26, 0x2a, 0xb1, 0xa7, 0x0b, 0xb3, 0xac, },
+  { 0x16, 0x22, 0xe1, 0xbc, 0x99, 0x4e, 0x01, 0xf0, 0xfa, 0xff, 0x8f, 0xa5,
+    0x0c, 0x61, 0xb0, 0xad, 0xcc, 0xb1, 0xe1, 0x21, 0x46, 0xfa, 0x2e, },
+  { 0x11, 0x5b, 0x0b, 0x2b, 0xe6, 0x14, 0xc1, 0xd5, 0x4d, 0x71, 0x5e, 0x17,
+    0xea, 0x23, 0xdd, 0x6c, 0xbd, 0x1d, 0xbe, 0x12, 0x1b, 0xee, 0x4c, 0x1a, },
+  { 0x40, 0x88, 0x22, 0xf3, 0x20, 0x6c, 0xed, 0xe1, 0x36, 0x34, 0x62, 0x2c,
+    0x98, 0x83, 0x52, 0xe2, 0x25, 0xee, 0xe9, 0xf5, 0xe1, 0x17, 0xf0, 0x5c,
+    0xae, },
+  { 0xc3, 0x76, 0x37, 0xde, 0x95, 0x8c, 0xca, 0x2b, 0x0c, 0x23, 0xe7, 0xb5,
+    0x38, 0x70, 0x61, 0xcc, 0xff, 0xd3, 0x95, 0x7b, 0xf3, 0xff, 0x1f, 0x9d,
+    0x59, 0x00, },
+  { 0x0c, 0x19, 0x52, 0x05, 0x22, 0x53, 0xcb, 0x48, 0xd7, 0x10, 0x0e, 0x7e,
+    0x14, 0x69, 0xb5, 0xa2, 0x92, 0x43, 0xa3, 0x9e, 0x4b, 0x8f, 0x51, 0x2c,
+    0x5a, 0x2c, 0x3b, },
+  { 0xe1, 0x9d, 0x70, 0x70, 0x28, 0xec, 0x86, 0x40, 0x55, 0x33, 0x56, 0xda,
+    0x88, 0xca, 0xee, 0xc8, 0x6a, 0x20, 0xb1, 0xe5, 0x3d, 0x57, 0xf8, 0x3c,
+    0x10, 0x07, 0x2a, 0xc4, },
+  { 0x0b, 0xae, 0xf1, 0xc4, 0x79, 0xee, 0x1b, 0x3d, 0x27, 0x35, 0x8d, 0x14,
+    0xd6, 0xae, 0x4e, 0x3c, 0xe9, 0x53, 0x50, 0xb5, 0xcc, 0x0c, 0xf7, 0xdf,
+    0xee, 0xa1, 0x74, 0xd6, 0x71, },
+  { 0xe6, 0xa4, 0xf4, 0x99, 0x98, 0xb9, 0x80, 0xea, 0x96, 0x7f, 0x4f, 0x33,
+    0xcf, 0x74, 0x25, 0x6f, 0x17, 0x6c, 0xbf, 0xf5, 0x5c, 0x38, 0xd0, 0xff,
+    0x96, 0xcb, 0x13, 0xf9, 0xdf, 0xfd, },
+  { 0xbe, 0x92, 0xeb, 0xba, 0x44, 0x2c, 0x24, 0x74, 0xd4, 0x03, 0x27, 0x3c,
+    0x5d, 0x5b, 0x03, 0x30, 0x87, 0x63, 0x69, 0xe0, 0xb8, 0x94, 0xf4, 0x44,
+    0x7e, 0xad, 0xcd, 0x20, 0x12, 0x16, 0x79, },
+  { 0x30, 0xf1, 0xc4, 0x8e, 0x05, 0x90, 0x2a, 0x97, 0x63, 0x94, 0x46, 0xff,
+    0xce, 0xd8, 0x67, 0xa7, 0xac, 0x33, 0x8c, 0x95, 0xb7, 0xcd, 0xa3, 0x23,
+    0x98, 0x9d, 0x76, 0x6c, 0x9d, 0xa8, 0xd6, 0x8a, },
+  { 0xbe, },
+  { 0x17, 0x6c, },
+  { 0x1a, 0x42, 0x4f, },
+  { 0xba, 0xaf, 0xb7, 0x65, },
+  { 0xc2, 0x63, 0x43, 0x6a, 0xea, },
+  { 0xe4, 0x4d, 0xad, 0xf2, 0x0b, 0x02, },
+  { 0x04, 0xc7, 0xc4, 0x7f, 0xa9, 0x2b, 0xce, },
+  { 0x66, 0xf6, 0x67, 0xcb, 0x03, 0x53, 0xc8, 0xf1, },
+  { 0x56, 0xa3, 0x60, 0x78, 0xc9, 0x5f, 0x70, 0x1b, 0x5e, },
+  { 0x99, 0xff, 0x81, 0x7c, 0x13, 0x3c, 0x29, 0x79, 0x4b, 0x65, },
+  { 0x51, 0x10, 0x50, 0x93, 0x01, 0x93, 0xb7, 0x01, 0xc9, 0x18, 0xb7, },
+  { 0x8e, 0x3c, 0x42, 0x1e, 0x5e, 0x7d, 0xc1, 0x50, 0x70, 0x1f, 0x00, 0x98, },
+  { 0x5f, 0xd9, 0x9b, 0xc8, 0xd7, 0xb2, 0x72, 0x62, 0x1a, 0x1e, 0xba, 0x92,
+    0xe9, },
+  { 0x70, 0x2b, 0xba, 0xfe, 0xad, 0x5d, 0x96, 0x3f, 0x27, 0xc2, 0x41, 0x6d,
+    0xc4, 0xb3, },
+  { 0xae, 0xe0, 0xd5, 0xd4, 0xc7, 0xae, 0x15, 0x5e, 0xdc, 0xdd, 0x33, 0x60,
+    0xd7, 0xd3, 0x5e, },
+  { 0x79, 0x8e, 0xbc, 0x9e, 0x20, 0xb9, 0x19, 0x4b, 0x63, 0x80, 0xf3, 0x16,
+    0xaf, 0x39, 0xbd, 0x92, },
+  { 0xc2, 0x0e, 0x85, 0xa0, 0x0b, 0x9a, 0xb0, 0xec, 0xde, 0x38, 0xd3, 0x10,
+    0xd9, 0xa7, 0x66, 0x27, 0xcf, },
+  { 0x0e, 0x3b, 0x75, 0x80, 0x67, 0x14, 0x0c, 0x02, 0x90, 0xd6, 0xb3, 0x02,
+    0x81, 0xf6, 0xa6, 0x87, 0xce, 0x58, },
+  { 0x79, 0xb5, 0xe9, 0x5d, 0x52, 0x4d, 0xf7, 0x59, 0xf4, 0x2e, 0x27, 0xdd,
+    0xb3, 0xed, 0x57, 0x5b, 0x82, 0xea, 0x6f, },
+  { 0xa2, 0x97, 0xf5, 0x80, 0x02, 0x3d, 0xde, 0xa3, 0xf9, 0xf6, 0xab, 0xe3,
+    0x57, 0x63, 0x7b, 0x9b, 0x10, 0x42, 0x6f, 0xf2, },
+  { 0x12, 0x7a, 0xfc, 0xb7, 0x67, 0x06, 0x0c, 0x78, 0x1a, 0xfe, 0x88, 0x4f,
+    0xc6, 0xac, 0x52, 0x96, 0x64, 0x28, 0x97, 0x84, 0x06, },
+  { 0xc5, 0x04, 0x44, 0x6b, 0xb2, 0xa5, 0xa4, 0x66, 0xe1, 0x76, 0xa2, 0x51,
+    0xf9, 0x59, 0x69, 0x97, 0x56, 0x0b, 0xbf, 0x50, 0xb3, 0x34, },
+  { 0x21, 0x32, 0x6b, 0x42, 0xb5, 0xed, 0x71, 0x8d, 0xf7, 0x5a, 0x35, 0xe3,
+    0x90, 0xe2, 0xee, 0xaa, 0x89, 0xf6, 0xc9, 0x9c, 0x4d, 0x73, 0xf4, },
+  { 0x4c, 0xa6, 0x09, 0xf4, 0x48, 0xe7, 0x46, 0xbc, 0x49, 0xfc, 0xe5, 0xda,
+    0xd1, 0x87, 0x13, 0x17, 0x4c, 0x59, 0x71, 0x26, 0x5b, 0x2c, 0x42, 0xb7, },
+  { 0x13, 0x63, 0xf3, 0x40, 0x02, 0xe5, 0xa3, 0x3a, 0x5e, 0x8e, 0xf8, 0xb6,
+    0x8a, 0x49, 0x60, 0x76, 0x34, 0x72, 0x94, 0x73, 0xf6, 0xd9, 0x21, 0x6a,
+    0x26, },
+  { 0xdf, 0x75, 0x16, 0x10, 0x1b, 0x5e, 0x81, 0xc3, 0xc8, 0xde, 0x34, 0x24,
+    0xb0, 0x98, 0xeb, 0x1b, 0x8f, 0xa1, 0x9b, 0x05, 0xee, 0xa5, 0xe9, 0x35,
+    0xf4, 0x1d, },
+  { 0xcd, 0x21, 0x93, 0x6e, 0x5b, 0xa0, 0x26, 0x2b, 0x21, 0x0e, 0xa0, 0xb9,
+    0x1c, 0xb5, 0xbb, 0xb8, 0xf8, 0x1e, 0xff, 0x5c, 0xa8, 0xf9, 0x39, 0x46,
+    0x4e, 0x29, 0x26, },
+  { 0x73, 0x7f, 0x0e, 0x3b, 0x0b, 0x5c, 0xf9, 0x60, 0xaa, 0x88, 0xa1, 0x09,
+    0xb1, 0x5d, 0x38, 0x7b, 0x86, 0x8f, 0x13, 0x7a, 0x8d, 0x72, 0x7a, 0x98,
+    0x1a, 0x5b, 0xff, 0xc9, },
+  { 0xd3, 0x3c, 0x61, 0x71, 0x44, 0x7e, 0x31, 0x74, 0x98, 0x9d, 0x9a, 0xd2,
+    0x27, 0xf3, 0x46, 0x43, 0x42, 0x51, 0xd0, 0x5f, 0xe9, 0x1c, 0x5c, 0x69,
+    0xbf, 0xf6, 0xbe, 0x3c, 0x40, },
+  { 0x31, 0x99, 0x31, 0x9f, 0xaa, 0x43, 0x2e, 0x77, 0x3e, 0x74, 0x26, 0x31,
+    0x5e, 0x61, 0xf1, 0x87, 0xe2, 0xeb, 0x9b, 0xcd, 0xd0, 0x3a, 0xee, 0x20,
+    0x7e, 0x10, 0x0a, 0x0b, 0x7e, 0xfa, },
+  { 0xa4, 0x27, 0x80, 0x67, 0x81, 0x2a, 0xa7, 0x62, 0xf7, 0x6e, 0xda, 0xd4,
+    0x5c, 0x39, 0x74, 0xad, 0x7e, 0xbe, 0xad, 0xa5, 0x84, 0x7f, 0xa9, 0x30,
+    0x5d, 0xdb, 0xe2, 0x05, 0x43, 0xf7, 0x1b, },
+  { 0x0b, 0x37, 0xd8, 0x02, 0xe1, 0x83, 0xd6, 0x80, 0xf2, 0x35, 0xc2, 0xb0,
+    0x37, 0xef, 0xef, 0x5e, 0x43, 0x93, 0xf0, 0x49, 0x45, 0x0a, 0xef, 0xb5,
+    0x76, 0x70, 0x12, 0x44, 0xc4, 0xdb, 0xf5, 0x7a, },
+  { 0x1f, },
+  { 0x82, 0x60, },
+  { 0xcc, 0xe3, 0x08, },
+  { 0x56, 0x17, 0xe4, 0x59, },
+  { 0xe2, 0xd7, 0x9e, 0xc4, 0x4c, },
+  { 0xb2, 0xad, 0xd3, 0x78, 0x58, 0x5a, },
+  { 0xce, 0x43, 0xb4, 0x02, 0x96, 0xab, 0x3c, },
+  { 0xe6, 0x05, 0x1a, 0x73, 0x22, 0x32, 0xbb, 0x77, },
+  { 0x23, 0xe7, 0xda, 0xfe, 0x2c, 0xef, 0x8c, 0x22, 0xec, },
+  { 0xe9, 0x8e, 0x55, 0x38, 0xd1, 0xd7, 0x35, 0x23, 0x98, 0xc7, },
+  { 0xb5, 0x81, 0x1a, 0xe5, 0xb5, 0xa5, 0xd9, 0x4d, 0xca, 0x41, 0xe7, },
+  { 0x41, 0x16, 0x16, 0x95, 0x8d, 0x9e, 0x0c, 0xea, 0x8c, 0x71, 0x9a, 0xc1, },
+  { 0x7c, 0x33, 0xc0, 0xa4, 0x00, 0x62, 0xea, 0x60, 0x67, 0xe4, 0x20, 0xbc,
+    0x5b, },
+  { 0xdb, 0xb1, 0xdc, 0xfd, 0x08, 0xc0, 0xde, 0x82, 0xd1, 0xde, 0x38, 0xc0,
+    0x90, 0x48, },
+  { 0x37, 0x18, 0x2e, 0x0d, 0x61, 0xaa, 0x61, 0xd7, 0x86, 0x20, 0x16, 0x60,
+    0x04, 0xd9, 0xd5, },
+  { 0xb0, 0xcf, 0x2c, 0x4c, 0x5e, 0x5b, 0x4f, 0x2a, 0x23, 0x25, 0x58, 0x47,
+    0xe5, 0x31, 0x06, 0x70, },
+  { 0x91, 0xa0, 0xa3, 0x86, 0x4e, 0xe0, 0x72, 0x38, 0x06, 0x67, 0x59, 0x5c,
+    0x70, 0x25, 0xdb, 0x33, 0x27, },
+  { 0x44, 0x58, 0x66, 0xb8, 0x58, 0xc7, 0x13, 0xed, 0x4c, 0xc0, 0xf4, 0x9a,
+    0x1e, 0x67, 0x75, 0x33, 0xb6, 0xb8, },
+  { 0x7f, 0x98, 0x4a, 0x8e, 0x50, 0xa2, 0x5c, 0xcd, 0x59, 0xde, 0x72, 0xb3,
+    0x9d, 0xc3, 0x09, 0x8a, 0xab, 0x56, 0xf1, },
+  { 0x80, 0x96, 0x49, 0x1a, 0x59, 0xa2, 0xc5, 0xd5, 0xa7, 0x20, 0x8a, 0xb7,
+    0x27, 0x62, 0x84, 0x43, 0xc6, 0xe1, 0x1b, 0x5d, },
+  { 0x6b, 0xb7, 0x2b, 0x26, 0x62, 0x14, 0x70, 0x19, 0x3d, 0x4d, 0xac, 0xac,
+    0x63, 0x58, 0x5e, 0x94, 0xb5, 0xb7, 0xe8, 0xe8, 0xa2, },
+  { 0x20, 0xa8, 0xc0, 0xfd, 0x63, 0x3d, 0x6e, 0x98, 0xcf, 0x0c, 0x49, 0x98,
+    0xe4, 0x5a, 0xfe, 0x8c, 0xaa, 0x70, 0x82, 0x1c, 0x7b, 0x74, },
+  { 0xc8, 0xe8, 0xdd, 0xdf, 0x69, 0x30, 0x01, 0xc2, 0x0f, 0x7e, 0x2f, 0x11,
+    0xcc, 0x3e, 0x17, 0xa5, 0x69, 0x40, 0x3f, 0x0e, 0x79, 0x7f, 0xcf, },
+  { 0xdb, 0x61, 0xc0, 0xe2, 0x2e, 0x49, 0x07, 0x31, 0x1d, 0x91, 0x42, 0x8a,
+    0xfc, 0x5e, 0xd3, 0xf8, 0x56, 0x1f, 0x2b, 0x73, 0xfd, 0x9f, 0xb2, 0x8e, },
+  { 0x0c, 0x89, 0x55, 0x0c, 0x1f, 0x59, 0x2c, 0x9d, 0x1b, 0x29, 0x1d, 0x41,
+    0x1d, 0xe6, 0x47, 0x8f, 0x8c, 0x2b, 0xea, 0x8f, 0xf0, 0xff, 0x21, 0x70,
+    0x88, },
+  { 0x12, 0x18, 0x95, 0xa6, 0x59, 0xb1, 0x31, 0x24, 0x45, 0x67, 0x55, 0xa4,
+    0x1a, 0x2d, 0x48, 0x67, 0x1b, 0x43, 0x88, 0x2d, 0x8e, 0xa0, 0x70, 0xb3,
+    0xc6, 0xbb, },
+  { 0xe7, 0xb1, 0x1d, 0xb2, 0x76, 0x4d, 0x68, 0x68, 0x68, 0x23, 0x02, 0x55,
+    0x3a, 0xe2, 0xe5, 0xd5, 0x4b, 0x43, 0xf9, 0x34, 0x77, 0x5c, 0xa1, 0xf5,
+    0x55, 0xfd, 0x4f, },
+  { 0x8c, 0x87, 0x5a, 0x08, 0x3a, 0x73, 0xad, 0x61, 0xe1, 0xe7, 0x99, 0x7e,
+    0xf0, 0x5d, 0xe9, 0x5d, 0x16, 0x43, 0x80, 0x2f, 0xd0, 0x66, 0x34, 0xe2,
+    0x42, 0x64, 0x3b, 0x1a, },
+  { 0x39, 0xc1, 0x99, 0xcf, 0x22, 0xbf, 0x16, 0x8f, 0x9f, 0x80, 0x7f, 0x95,
+    0x0a, 0x05, 0x67, 0x27, 0xe7, 0x15, 0xdf, 0x9d, 0xb2, 0xfe, 0x1c, 0xb5,
+    0x1d, 0x60, 0x8f, 0x8a, 0x1d, },
+  { 0x9b, 0x6e, 0x08, 0x09, 0x06, 0x73, 0xab, 0x68, 0x02, 0x62, 0x1a, 0xe4,
+    0xd4, 0xdf, 0xc7, 0x02, 0x4c, 0x6a, 0x5f, 0xfd, 0x23, 0xac, 0xae, 0x6d,
+    0x43, 0xa4, 0x7a, 0x50, 0x60, 0x3c, },
+  { 0x1d, 0xb4, 0xc6, 0xe1, 0xb1, 0x4b, 0xe3, 0xf2, 0xe2, 0x1a, 0x73, 0x1b,
+    0xa0, 0x92, 0xa7, 0xf5, 0xff, 0x8f, 0x8b, 0x5d, 0xdf, 0xa8, 0x04, 0xb3,
+    0xb0, 0xf7, 0xcc, 0x12, 0xfa, 0x35, 0x46, },
+  { 0x49, 0x45, 0x97, 0x11, 0x0f, 0x1c, 0x60, 0x8e, 0xe8, 0x47, 0x30, 0xcf,
+    0x60, 0xa8, 0x71, 0xc5, 0x1b, 0xe9, 0x39, 0x4d, 0x49, 0xb6, 0x12, 0x1f,
+    0x24, 0xab, 0x37, 0xff, 0x83, 0xc2, 0xe1, 0x3a, },
+  { 0x60, },
+  { 0x24, 0x26, },
+  { 0x47, 0xeb, 0xc9, },
+  { 0x4a, 0xd0, 0xbc, 0xf0, },
+  { 0x8e, 0x2b, 0xc9, 0x85, 0x3c, },
+  { 0xa2, 0x07, 0x15, 0xb8, 0x12, 0x74, },
+  { 0x0f, 0xdb, 0x5b, 0x33, 0x69, 0xfe, 0x4b, },
+  { 0xa2, 0x86, 0x54, 0xf4, 0xfd, 0xb2, 0xd4, 0xe6, },
+  { 0xbb, 0x84, 0x78, 0x49, 0x27, 0x8e, 0x61, 0xda, 0x60, },
+  { 0x04, 0xc3, 0xcd, 0xaa, 0x8f, 0xa7, 0x03, 0xc9, 0xf9, 0xb6, },
+  { 0xf8, 0x27, 0x1d, 0x61, 0xdc, 0x21, 0x42, 0xdd, 0xad, 0x92, 0x40, },
+  { 0x12, 0x87, 0xdf, 0xc2, 0x41, 0x45, 0x5a, 0x36, 0x48, 0x5b, 0x51, 0x2b, },
+  { 0xbb, 0x37, 0x5d, 0x1f, 0xf1, 0x68, 0x7a, 0xc4, 0xa5, 0xd2, 0xa4, 0x91,
+    0x8d, },
+  { 0x5b, 0x27, 0xd1, 0x04, 0x54, 0x52, 0x9f, 0xa3, 0x47, 0x86, 0x33, 0x33,
+    0xbf, 0xa0, },
+  { 0xcf, 0x04, 0xea, 0xf8, 0x03, 0x2a, 0x43, 0xff, 0xa6, 0x68, 0x21, 0x4c,
+    0xd5, 0x4b, 0xed, },
+  { 0xaf, 0xb8, 0xbc, 0x63, 0x0f, 0x18, 0x4d, 0xe2, 0x7a, 0xdd, 0x46, 0x44,
+    0xc8, 0x24, 0x0a, 0xb7, },
+  { 0x3e, 0xdc, 0x36, 0xe4, 0x89, 0xb1, 0xfa, 0xc6, 0x40, 0x93, 0x2e, 0x75,
+    0xb2, 0x15, 0xd1, 0xb1, 0x10, },
+  { 0x6c, 0xd8, 0x20, 0x3b, 0x82, 0x79, 0xf9, 0xc8, 0xbc, 0x9d, 0xe0, 0x35,
+    0xbe, 0x1b, 0x49, 0x1a, 0xbc, 0x3a, },
+  { 0x78, 0x65, 0x2c, 0xbe, 0x35, 0x67, 0xdc, 0x78, 0xd4, 0x41, 0xf6, 0xc9,
+    0xde, 0xde, 0x1f, 0x18, 0x13, 0x31, 0x11, },
+  { 0x8a, 0x7f, 0xb1, 0x33, 0x8f, 0x0c, 0x3c, 0x0a, 0x06, 0x61, 0xf0, 0x47,
+    0x29, 0x1b, 0x29, 0xbc, 0x1c, 0x47, 0xef, 0x7a, },
+  { 0x65, 0x91, 0xf1, 0xe6, 0xb3, 0x96, 0xd3, 0x8c, 0xc2, 0x4a, 0x59, 0x35,
+    0x72, 0x8e, 0x0b, 0x9a, 0x87, 0xca, 0x34, 0x7b, 0x63, },
+  { 0x5f, 0x08, 0x87, 0x80, 0x56, 0x25, 0x89, 0x77, 0x61, 0x8c, 0x64, 0xa1,
+    0x59, 0x6d, 0x59, 0x62, 0xe8, 0x4a, 0xc8, 0x58, 0x99, 0xd1, },
+  { 0x23, 0x87, 0x1d, 0xed, 0x6f, 0xf2, 0x91, 0x90, 0xe2, 0xfe, 0x43, 0x21,
+    0xaf, 0x97, 0xc6, 0xbc, 0xd7, 0x15, 0xc7, 0x2d, 0x08, 0x77, 0x91, },
+  { 0x90, 0x47, 0x9a, 0x9e, 0x3a, 0xdf, 0xf3, 0xc9, 0x4c, 0x1e, 0xa7, 0xd4,
+    0x6a, 0x32, 0x90, 0xfe, 0xb7, 0xb6, 0x7b, 0xfa, 0x96, 0x61, 0xfb, 0xa4, },
+  { 0xb1, 0x67, 0x60, 0x45, 0xb0, 0x96, 0xc5, 0x15, 0x9f, 0x4d, 0x26, 0xd7,
+    0x9d, 0xf1, 0xf5, 0x6d, 0x21, 0x00, 0x94, 0x31, 0x64, 0x94, 0xd3, 0xa7,
+    0xd3, },
+  { 0x02, 0x3e, 0xaf, 0xf3, 0x79, 0x73, 0xa5, 0xf5, 0xcc, 0x7a, 0x7f, 0xfb,
+    0x79, 0x2b, 0x85, 0x8c, 0x88, 0x72, 0x06, 0xbe, 0xfe, 0xaf, 0xc1, 0x16,
+    0xa6, 0xd6, },
+  { 0x2a, 0xb0, 0x1a, 0xe5, 0xaa, 0x6e, 0xb3, 0xae, 0x53, 0x85, 0x33, 0x80,
+    0x75, 0xae, 0x30, 0xe6, 0xb8, 0x72, 0x42, 0xf6, 0x25, 0x4f, 0x38, 0x88,
+    0x55, 0xd1, 0xa9, },
+  { 0x90, 0xd8, 0x0c, 0xc0, 0x93, 0x4b, 0x4f, 0x9e, 0x65, 0x6c, 0xa1, 0x54,
+    0xa6, 0xf6, 0x6e, 0xca, 0xd2, 0xbb, 0x7e, 0x6a, 0x1c, 0xd3, 0xce, 0x46,
+    0xef, 0xb0, 0x00, 0x8d, },
+  { 0xed, 0x9c, 0x49, 0xcd, 0xc2, 0xde, 0x38, 0x0e, 0xe9, 0x98, 0x6c, 0xc8,
+    0x90, 0x9e, 0x3c, 0xd4, 0xd3, 0xeb, 0x88, 0x32, 0xc7, 0x28, 0xe3, 0x94,
+    0x1c, 0x9f, 0x8b, 0xf3, 0xcb, },
+  { 0xac, 0xe7, 0x92, 0x16, 0xb4, 0x14, 0xa0, 0xe4, 0x04, 0x79, 0xa2, 0xf4,
+    0x31, 0xe6, 0x0c, 0x26, 0xdc, 0xbf, 0x2f, 0x69, 0x1b, 0x55, 0x94, 0x67,
+    0xda, 0x0c, 0xd7, 0x32, 0x1f, 0xef, },
+  { 0x68, 0x63, 0x85, 0x57, 0x95, 0x9e, 0x42, 0x27, 0x41, 0x43, 0x42, 0x02,
+    0xa5, 0x78, 0xa7, 0xc6, 0x43, 0xc1, 0x6a, 0xba, 0x70, 0x80, 0xcd, 0x04,
+    0xb6, 0x78, 0x76, 0x29, 0xf3, 0xe8, 0xa0, },
+  { 0xe6, 0xac, 0x8d, 0x9d, 0xf0, 0xc0, 0xf7, 0xf7, 0xe3, 0x3e, 0x4e, 0x28,
+    0x0f, 0x59, 0xb2, 0x67, 0x9e, 0x84, 0x34, 0x42, 0x96, 0x30, 0x2b, 0xca,
+    0x49, 0xb6, 0xc5, 0x9a, 0x84, 0x59, 0xa7, 0x81, },
+  { 0x7e, },
+  { 0x1e, 0x21, },
+  { 0x26, 0xd3, 0xdd, },
+  { 0x2c, 0xd4, 0xb3, 0x3d, },
+  { 0x86, 0x7b, 0x76, 0x3c, 0xf0, },
+  { 0x12, 0xc3, 0x70, 0x1d, 0x55, 0x18, },
+  { 0x96, 0xc2, 0xbd, 0x61, 0x55, 0xf4, 0x24, },
+  { 0x20, 0x51, 0xf7, 0x86, 0x58, 0x8f, 0x07, 0x2a, },
+  { 0x93, 0x15, 0xa8, 0x1d, 0xda, 0x97, 0xee, 0x0e, 0x6c, },
+  { 0x39, 0x93, 0xdf, 0xd5, 0x0e, 0xca, 0xdc, 0x7a, 0x92, 0xce, },
+  { 0x60, 0xd5, 0xfd, 0xf5, 0x1b, 0x26, 0x82, 0x26, 0x73, 0x02, 0xbc, },
+  { 0x98, 0xf2, 0x34, 0xe1, 0xf5, 0xfb, 0x00, 0xac, 0x10, 0x4a, 0x38, 0x9f, },
+  { 0xda, 0x3a, 0x92, 0x8a, 0xd0, 0xcd, 0x12, 0xcd, 0x15, 0xbb, 0xab, 0x77,
+    0x66, },
+  { 0xa2, 0x92, 0x1a, 0xe5, 0xca, 0x0c, 0x30, 0x75, 0xeb, 0xaf, 0x00, 0x31,
+    0x55, 0x66, },
+  { 0x06, 0xea, 0xfd, 0x3e, 0x86, 0x38, 0x62, 0x4e, 0xa9, 0x12, 0xa4, 0x12,
+    0x43, 0xbf, 0xa1, },
+  { 0xe4, 0x71, 0x7b, 0x94, 0xdb, 0xa0, 0xd2, 0xff, 0x9b, 0xeb, 0xad, 0x8e,
+    0x95, 0x8a, 0xc5, 0xed, },
+  { 0x25, 0x5a, 0x77, 0x71, 0x41, 0x0e, 0x7a, 0xe9, 0xed, 0x0c, 0x10, 0xef,
+    0xf6, 0x2b, 0x3a, 0xba, 0x60, },
+  { 0xee, 0xe2, 0xa3, 0x67, 0x64, 0x1d, 0xc6, 0x04, 0xc4, 0xe1, 0x68, 0xd2,
+    0x6e, 0xd2, 0x91, 0x75, 0x53, 0x07, },
+  { 0xe0, 0xf6, 0x4d, 0x8f, 0x68, 0xfc, 0x06, 0x7e, 0x18, 0x79, 0x7f, 0x2b,
+    0x6d, 0xef, 0x46, 0x7f, 0xab, 0xb2, 0xad, },
+  { 0x3d, 0x35, 0x88, 0x9f, 0x2e, 0xcf, 0x96, 0x45, 0x07, 0x60, 0x71, 0x94,
+    0x00, 0x8d, 0xbf, 0xf4, 0xef, 0x46, 0x2e, 0x3c, },
+  { 0x43, 0xcf, 0x98, 0xf7, 0x2d, 0xf4, 0x17, 0xe7, 0x8c, 0x05, 0x2d, 0x9b,
+    0x24, 0xfb, 0x4d, 0xea, 0x4a, 0xec, 0x01, 0x25, 0x29, },
+  { 0x8e, 0x73, 0x9a, 0x78, 0x11, 0xfe, 0x48, 0xa0, 0x3b, 0x1a, 0x26, 0xdf,
+    0x25, 0xe9, 0x59, 0x1c, 0x70, 0x07, 0x9f, 0xdc, 0xa0, 0xa6, },
+  { 0xe8, 0x47, 0x71, 0xc7, 0x3e, 0xdf, 0xb5, 0x13, 0xb9, 0x85, 0x13, 0xa8,
+    0x54, 0x47, 0x6e, 0x59, 0x96, 0x09, 0x13, 0x5f, 0x82, 0x16, 0x0b, },
+  { 0xfb, 0xc0, 0x8c, 0x03, 0x21, 0xb3, 0xc4, 0xb5, 0x43, 0x32, 0x6c, 0xea,
+    0x7f, 0xa8, 0x43, 0x91, 0xe8, 0x4e, 0x3f, 0xbf, 0x45, 0x58, 0x6a, 0xa3, },
+  { 0x55, 0xf8, 0xf3, 0x00, 0x76, 0x09, 0xef, 0x69, 0x5d, 0xd2, 0x8a, 0xf2,
+    0x65, 0xc3, 0xcb, 0x9b, 0x43, 0xfd, 0xb1, 0x7e, 0x7f, 0xa1, 0x94, 0xb0,
+    0xd7, },
+  { 0xaa, 0x13, 0xc1, 0x51, 0x40, 0x6d, 0x8d, 0x4c, 0x0a, 0x95, 0x64, 0x7b,
+    0xd1, 0x96, 0xb6, 0x56, 0xb4, 0x5b, 0xcf, 0xd6, 0xd9, 0x15, 0x97, 0xdd,
+    0xb6, 0xef, },
+  { 0xaf, 0xb7, 0x36, 0xb0, 0x04, 0xdb, 0xd7, 0x9c, 0x9a, 0x44, 0xc4, 0xf6,
+    0x1f, 0x12, 0x21, 0x2d, 0x59, 0x30, 0x54, 0xab, 0x27, 0x61, 0xa3, 0x57,
+    0xef, 0xf8, 0x53, },
+  { 0x97, 0x34, 0x45, 0x3e, 0xce, 0x7c, 0x35, 0xa2, 0xda, 0x9f, 0x4b, 0x46,
+    0x6c, 0x11, 0x67, 0xff, 0x2f, 0x76, 0x58, 0x15, 0x71, 0xfa, 0x44, 0x89,
+    0x89, 0xfd, 0xf7, 0x99, },
+  { 0x1f, 0xb1, 0x62, 0xeb, 0x83, 0xc5, 0x9c, 0x89, 0xf9, 0x2c, 0xd2, 0x03,
+    0x61, 0xbc, 0xbb, 0xa5, 0x74, 0x0e, 0x9b, 0x7e, 0x82, 0x3e, 0x70, 0x0a,
+    0xa9, 0x8f, 0x2b, 0x59, 0xfb, },
+  { 0xf8, 0xca, 0x5e, 0x3a, 0x4f, 0x9e, 0x10, 0x69, 0x10, 0xd5, 0x4c, 0xeb,
+    0x1a, 0x0f, 0x3c, 0x6a, 0x98, 0xf5, 0xb0, 0x97, 0x5b, 0x37, 0x2f, 0x0d,
+    0xbd, 0x42, 0x4b, 0x69, 0xa1, 0x82, },
+  { 0x12, 0x8c, 0x6d, 0x52, 0x08, 0xef, 0x74, 0xb2, 0xe6, 0xaa, 0xd3, 0xb0,
+    0x26, 0xb0, 0xd9, 0x94, 0xb6, 0x11, 0x45, 0x0e, 0x36, 0x71, 0x14, 0x2d,
+    0x41, 0x8c, 0x21, 0x53, 0x31, 0xe9, 0x68, },
+  { 0xee, 0xea, 0x0d, 0x89, 0x47, 0x7e, 0x72, 0xd1, 0xd8, 0xce, 0x58, 0x4c,
+    0x94, 0x1f, 0x0d, 0x51, 0x08, 0xa3, 0xb6, 0x3d, 0xe7, 0x82, 0x46, 0x92,
+    0xd6, 0x98, 0x6b, 0x07, 0x10, 0x65, 0x52, 0x65, },
+};
+
+static const u8 blake2s_hmac_testvecs[][BLAKE2S_HASH_SIZE] __initconst = {
+  { 0xce, 0xe1, 0x57, 0x69, 0x82, 0xdc, 0xbf, 0x43, 0xad, 0x56, 0x4c, 0x70,
+    0xed, 0x68, 0x16, 0x96, 0xcf, 0xa4, 0x73, 0xe8, 0xe8, 0xfc, 0x32, 0x79,
+    0x08, 0x0a, 0x75, 0x82, 0xda, 0x3f, 0x05, 0x11, },
+  { 0x77, 0x2f, 0x0c, 0x71, 0x41, 0xf4, 0x4b, 0x2b, 0xb3, 0xc6, 0xb6, 0xf9,
+    0x60, 0xde, 0xe4, 0x52, 0x38, 0x66, 0xe8, 0xbf, 0x9b, 0x96, 0xc4, 0x9f,
+    0x60, 0xd9, 0x24, 0x37, 0x99, 0xd6, 0xec, 0x31, },
+};
+
+bool __init blake2s_selftest(void)
+{
+	u8 key[BLAKE2S_KEY_SIZE];
+	u8 buf[ARRAY_SIZE(blake2s_testvecs)];
+	u8 hash[BLAKE2S_HASH_SIZE];
+	struct blake2s_state state;
+	bool success = true;
+	int i, l;
+
+	key[0] = key[1] = 1;
+	for (i = 2; i < sizeof(key); ++i)
+		key[i] = key[i - 2] + key[i - 1];
+
+	for (i = 0; i < sizeof(buf); ++i)
+		buf[i] = (u8)i;
+
+	for (i = l = 0; i < ARRAY_SIZE(blake2s_testvecs); l = (l + 37) % ++i) {
+		int outlen = 1 + i % BLAKE2S_HASH_SIZE;
+		int keylen = (13 * i) % (BLAKE2S_KEY_SIZE + 1);
+
+		blake2s(hash, buf, key + BLAKE2S_KEY_SIZE - keylen, outlen, i,
+			keylen);
+		if (memcmp(hash, blake2s_testvecs[i], outlen)) {
+			pr_err("blake2s self-test %d: FAIL\n", i + 1);
+			success = false;
+		}
+
+		if (!keylen)
+			blake2s_init(&state, outlen);
+		else
+			blake2s_init_key(&state, outlen,
+					 key + BLAKE2S_KEY_SIZE - keylen,
+					 keylen);
+
+		blake2s_update(&state, buf, l);
+		blake2s_update(&state, buf + l, i - l);
+		blake2s_final(&state, hash);
+		if (memcmp(hash, blake2s_testvecs[i], outlen)) {
+			pr_err("blake2s init/update/final self-test %d: FAIL\n",
+			       i + 1);
+			success = false;
+		}
+	}
+
+	if (success) {
+		blake2s256_hmac(hash, buf, key, sizeof(buf), sizeof(key));
+		success &= !memcmp(hash, blake2s_hmac_testvecs[0], BLAKE2S_HASH_SIZE);
+
+		blake2s256_hmac(hash, key, buf, sizeof(key), sizeof(buf));
+		success &= !memcmp(hash, blake2s_hmac_testvecs[1], BLAKE2S_HASH_SIZE);
+
+		if (!success)
+			pr_err("blake2s256_hmac self-test: FAIL\n");
+	}
+
+	return success;
+}
diff --git a/lib/crypto/blake2s.c b/lib/crypto/blake2s.c
new file mode 100644
index 000000000000..41025a30c524
--- /dev/null
+++ b/lib/crypto/blake2s.c
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This is an implementation of the BLAKE2s hash and PRF functions.
+ *
+ * Information: https://blake2.net/
+ *
+ */
+
+#include <crypto/internal/blake2s.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/bug.h>
+#include <asm/unaligned.h>
+
+bool blake2s_selftest(void);
+
+void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen)
+{
+	const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen;
+
+	if (unlikely(!inlen))
+		return;
+	if (inlen > fill) {
+		memcpy(state->buf + state->buflen, in, fill);
+		if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S))
+			blake2s_compress_arch(state, state->buf, 1,
+					      BLAKE2S_BLOCK_SIZE);
+		else
+			blake2s_compress_generic(state, state->buf, 1,
+						 BLAKE2S_BLOCK_SIZE);
+		state->buflen = 0;
+		in += fill;
+		inlen -= fill;
+	}
+	if (inlen > BLAKE2S_BLOCK_SIZE) {
+		const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE);
+		/* Hash one less (full) block than strictly possible */
+		if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S))
+			blake2s_compress_arch(state, in, nblocks - 1,
+					      BLAKE2S_BLOCK_SIZE);
+		else
+			blake2s_compress_generic(state, in, nblocks - 1,
+						 BLAKE2S_BLOCK_SIZE);
+		in += BLAKE2S_BLOCK_SIZE * (nblocks - 1);
+		inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1);
+	}
+	memcpy(state->buf + state->buflen, in, inlen);
+	state->buflen += inlen;
+}
+EXPORT_SYMBOL(blake2s_update);
+
+void blake2s_final(struct blake2s_state *state, u8 *out)
+{
+	WARN_ON(IS_ENABLED(DEBUG) && !out);
+	blake2s_set_lastblock(state);
+	memset(state->buf + state->buflen, 0,
+	       BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */
+	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S))
+		blake2s_compress_arch(state, state->buf, 1, state->buflen);
+	else
+		blake2s_compress_generic(state, state->buf, 1, state->buflen);
+	cpu_to_le32_array(state->h, ARRAY_SIZE(state->h));
+	memcpy(out, state->h, state->outlen);
+	memzero_explicit(state, sizeof(*state));
+}
+EXPORT_SYMBOL(blake2s_final);
+
+void blake2s256_hmac(u8 *out, const u8 *in, const u8 *key, const size_t inlen,
+		     const size_t keylen)
+{
+	struct blake2s_state state;
+	u8 x_key[BLAKE2S_BLOCK_SIZE] __aligned(__alignof__(u32)) = { 0 };
+	u8 i_hash[BLAKE2S_HASH_SIZE] __aligned(__alignof__(u32));
+	int i;
+
+	if (keylen > BLAKE2S_BLOCK_SIZE) {
+		blake2s_init(&state, BLAKE2S_HASH_SIZE);
+		blake2s_update(&state, key, keylen);
+		blake2s_final(&state, x_key);
+	} else
+		memcpy(x_key, key, keylen);
+
+	for (i = 0; i < BLAKE2S_BLOCK_SIZE; ++i)
+		x_key[i] ^= 0x36;
+
+	blake2s_init(&state, BLAKE2S_HASH_SIZE);
+	blake2s_update(&state, x_key, BLAKE2S_BLOCK_SIZE);
+	blake2s_update(&state, in, inlen);
+	blake2s_final(&state, i_hash);
+
+	for (i = 0; i < BLAKE2S_BLOCK_SIZE; ++i)
+		x_key[i] ^= 0x5c ^ 0x36;
+
+	blake2s_init(&state, BLAKE2S_HASH_SIZE);
+	blake2s_update(&state, x_key, BLAKE2S_BLOCK_SIZE);
+	blake2s_update(&state, i_hash, BLAKE2S_HASH_SIZE);
+	blake2s_final(&state, i_hash);
+
+	memcpy(out, i_hash, BLAKE2S_HASH_SIZE);
+	memzero_explicit(x_key, BLAKE2S_BLOCK_SIZE);
+	memzero_explicit(i_hash, BLAKE2S_HASH_SIZE);
+}
+EXPORT_SYMBOL(blake2s256_hmac);
+
+static int __init mod_init(void)
+{
+	if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) &&
+	    WARN_ON(!blake2s_selftest()))
+		return -ENODEV;
+	return 0;
+}
+
+static void __exit mod_exit(void)
+{
+}
+
+module_init(mod_init);
+module_exit(mod_exit);
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("BLAKE2s hash function");
+MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
diff --git a/lib/chacha.c b/lib/crypto/chacha.c
index c7c9826564d3..65ead6b0c7e0 100644
--- a/lib/chacha.c
+++ b/lib/crypto/chacha.c
@@ -5,9 +5,11 @@
  * Copyright (C) 2015 Martin Willi
  */
 
+#include <linux/bug.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/bitops.h>
+#include <linux/string.h>
 #include <linux/cryptohash.h>
 #include <asm/unaligned.h>
 #include <crypto/chacha.h>
@@ -72,7 +74,7 @@ static void chacha_permute(u32 *x, int nrounds)
  * The caller has already converted the endianness of the input.  This function
  * also handles incrementing the block counter in the input matrix.
  */
-void chacha_block(u32 *state, u8 *stream, int nrounds)
+void chacha_block_generic(u32 *state, u8 *stream, int nrounds)
 {
 	u32 x[16];
 	int i;
@@ -86,11 +88,11 @@ void chacha_block(u32 *state, u8 *stream, int nrounds)
 
 	state[12]++;
 }
-EXPORT_SYMBOL(chacha_block);
+EXPORT_SYMBOL(chacha_block_generic);
 
 /**
- * hchacha_block - abbreviated ChaCha core, for XChaCha
- * @in: input state matrix (16 32-bit words)
+ * hchacha_block_generic - abbreviated ChaCha core, for XChaCha
+ * @state: input state matrix (16 32-bit words)
  * @out: output (8 32-bit words)
  * @nrounds: number of rounds (20 or 12; 20 is recommended)
  *
@@ -99,15 +101,15 @@ EXPORT_SYMBOL(chacha_block);
  * skips the final addition of the initial state, and outputs only certain words
  * of the state.  It should not be used for streaming directly.
  */
-void hchacha_block(const u32 *in, u32 *out, int nrounds)
+void hchacha_block_generic(const u32 *state, u32 *stream, int nrounds)
 {
 	u32 x[16];
 
-	memcpy(x, in, 64);
+	memcpy(x, state, 64);
 
 	chacha_permute(x, nrounds);
 
-	memcpy(&out[0], &x[0], 16);
-	memcpy(&out[4], &x[12], 16);
+	memcpy(&stream[0], &x[0], 16);
+	memcpy(&stream[4], &x[12], 16);
 }
-EXPORT_SYMBOL(hchacha_block);
+EXPORT_SYMBOL(hchacha_block_generic);
diff --git a/lib/crypto/chacha20poly1305-selftest.c b/lib/crypto/chacha20poly1305-selftest.c
new file mode 100644
index 000000000000..465de46dbdef
--- /dev/null
+++ b/lib/crypto/chacha20poly1305-selftest.c
@@ -0,0 +1,7393 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <crypto/chacha20poly1305.h>
+#include <crypto/poly1305.h>
+
+#include <asm/unaligned.h>
+#include <linux/bug.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+struct chacha20poly1305_testvec {
+	const u8 *input, *output, *assoc, *nonce, *key;
+	size_t ilen, alen, nlen;
+	bool failure;
+};
+
+/* The first of these are the ChaCha20-Poly1305 AEAD test vectors from RFC7539
+ * 2.8.2. After they are generated by reference implementations. And the final
+ * marked ones are taken from wycheproof, but we only do these for the encrypt
+ * side, because mostly we're stressing the primitives rather than the actual
+ * chapoly construction.
+ */
+
+static const u8 enc_input001[] __initconst = {
+	0x49, 0x6e, 0x74, 0x65, 0x72, 0x6e, 0x65, 0x74,
+	0x2d, 0x44, 0x72, 0x61, 0x66, 0x74, 0x73, 0x20,
+	0x61, 0x72, 0x65, 0x20, 0x64, 0x72, 0x61, 0x66,
+	0x74, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65,
+	0x6e, 0x74, 0x73, 0x20, 0x76, 0x61, 0x6c, 0x69,
+	0x64, 0x20, 0x66, 0x6f, 0x72, 0x20, 0x61, 0x20,
+	0x6d, 0x61, 0x78, 0x69, 0x6d, 0x75, 0x6d, 0x20,
+	0x6f, 0x66, 0x20, 0x73, 0x69, 0x78, 0x20, 0x6d,
+	0x6f, 0x6e, 0x74, 0x68, 0x73, 0x20, 0x61, 0x6e,
+	0x64, 0x20, 0x6d, 0x61, 0x79, 0x20, 0x62, 0x65,
+	0x20, 0x75, 0x70, 0x64, 0x61, 0x74, 0x65, 0x64,
+	0x2c, 0x20, 0x72, 0x65, 0x70, 0x6c, 0x61, 0x63,
+	0x65, 0x64, 0x2c, 0x20, 0x6f, 0x72, 0x20, 0x6f,
+	0x62, 0x73, 0x6f, 0x6c, 0x65, 0x74, 0x65, 0x64,
+	0x20, 0x62, 0x79, 0x20, 0x6f, 0x74, 0x68, 0x65,
+	0x72, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65,
+	0x6e, 0x74, 0x73, 0x20, 0x61, 0x74, 0x20, 0x61,
+	0x6e, 0x79, 0x20, 0x74, 0x69, 0x6d, 0x65, 0x2e,
+	0x20, 0x49, 0x74, 0x20, 0x69, 0x73, 0x20, 0x69,
+	0x6e, 0x61, 0x70, 0x70, 0x72, 0x6f, 0x70, 0x72,
+	0x69, 0x61, 0x74, 0x65, 0x20, 0x74, 0x6f, 0x20,
+	0x75, 0x73, 0x65, 0x20, 0x49, 0x6e, 0x74, 0x65,
+	0x72, 0x6e, 0x65, 0x74, 0x2d, 0x44, 0x72, 0x61,
+	0x66, 0x74, 0x73, 0x20, 0x61, 0x73, 0x20, 0x72,
+	0x65, 0x66, 0x65, 0x72, 0x65, 0x6e, 0x63, 0x65,
+	0x20, 0x6d, 0x61, 0x74, 0x65, 0x72, 0x69, 0x61,
+	0x6c, 0x20, 0x6f, 0x72, 0x20, 0x74, 0x6f, 0x20,
+	0x63, 0x69, 0x74, 0x65, 0x20, 0x74, 0x68, 0x65,
+	0x6d, 0x20, 0x6f, 0x74, 0x68, 0x65, 0x72, 0x20,
+	0x74, 0x68, 0x61, 0x6e, 0x20, 0x61, 0x73, 0x20,
+	0x2f, 0xe2, 0x80, 0x9c, 0x77, 0x6f, 0x72, 0x6b,
+	0x20, 0x69, 0x6e, 0x20, 0x70, 0x72, 0x6f, 0x67,
+	0x72, 0x65, 0x73, 0x73, 0x2e, 0x2f, 0xe2, 0x80,
+	0x9d
+};
+static const u8 enc_output001[] __initconst = {
+	0x64, 0xa0, 0x86, 0x15, 0x75, 0x86, 0x1a, 0xf4,
+	0x60, 0xf0, 0x62, 0xc7, 0x9b, 0xe6, 0x43, 0xbd,
+	0x5e, 0x80, 0x5c, 0xfd, 0x34, 0x5c, 0xf3, 0x89,
+	0xf1, 0x08, 0x67, 0x0a, 0xc7, 0x6c, 0x8c, 0xb2,
+	0x4c, 0x6c, 0xfc, 0x18, 0x75, 0x5d, 0x43, 0xee,
+	0xa0, 0x9e, 0xe9, 0x4e, 0x38, 0x2d, 0x26, 0xb0,
+	0xbd, 0xb7, 0xb7, 0x3c, 0x32, 0x1b, 0x01, 0x00,
+	0xd4, 0xf0, 0x3b, 0x7f, 0x35, 0x58, 0x94, 0xcf,
+	0x33, 0x2f, 0x83, 0x0e, 0x71, 0x0b, 0x97, 0xce,
+	0x98, 0xc8, 0xa8, 0x4a, 0xbd, 0x0b, 0x94, 0x81,
+	0x14, 0xad, 0x17, 0x6e, 0x00, 0x8d, 0x33, 0xbd,
+	0x60, 0xf9, 0x82, 0xb1, 0xff, 0x37, 0xc8, 0x55,
+	0x97, 0x97, 0xa0, 0x6e, 0xf4, 0xf0, 0xef, 0x61,
+	0xc1, 0x86, 0x32, 0x4e, 0x2b, 0x35, 0x06, 0x38,
+	0x36, 0x06, 0x90, 0x7b, 0x6a, 0x7c, 0x02, 0xb0,
+	0xf9, 0xf6, 0x15, 0x7b, 0x53, 0xc8, 0x67, 0xe4,
+	0xb9, 0x16, 0x6c, 0x76, 0x7b, 0x80, 0x4d, 0x46,
+	0xa5, 0x9b, 0x52, 0x16, 0xcd, 0xe7, 0xa4, 0xe9,
+	0x90, 0x40, 0xc5, 0xa4, 0x04, 0x33, 0x22, 0x5e,
+	0xe2, 0x82, 0xa1, 0xb0, 0xa0, 0x6c, 0x52, 0x3e,
+	0xaf, 0x45, 0x34, 0xd7, 0xf8, 0x3f, 0xa1, 0x15,
+	0x5b, 0x00, 0x47, 0x71, 0x8c, 0xbc, 0x54, 0x6a,
+	0x0d, 0x07, 0x2b, 0x04, 0xb3, 0x56, 0x4e, 0xea,
+	0x1b, 0x42, 0x22, 0x73, 0xf5, 0x48, 0x27, 0x1a,
+	0x0b, 0xb2, 0x31, 0x60, 0x53, 0xfa, 0x76, 0x99,
+	0x19, 0x55, 0xeb, 0xd6, 0x31, 0x59, 0x43, 0x4e,
+	0xce, 0xbb, 0x4e, 0x46, 0x6d, 0xae, 0x5a, 0x10,
+	0x73, 0xa6, 0x72, 0x76, 0x27, 0x09, 0x7a, 0x10,
+	0x49, 0xe6, 0x17, 0xd9, 0x1d, 0x36, 0x10, 0x94,
+	0xfa, 0x68, 0xf0, 0xff, 0x77, 0x98, 0x71, 0x30,
+	0x30, 0x5b, 0xea, 0xba, 0x2e, 0xda, 0x04, 0xdf,
+	0x99, 0x7b, 0x71, 0x4d, 0x6c, 0x6f, 0x2c, 0x29,
+	0xa6, 0xad, 0x5c, 0xb4, 0x02, 0x2b, 0x02, 0x70,
+	0x9b, 0xee, 0xad, 0x9d, 0x67, 0x89, 0x0c, 0xbb,
+	0x22, 0x39, 0x23, 0x36, 0xfe, 0xa1, 0x85, 0x1f,
+	0x38
+};
+static const u8 enc_assoc001[] __initconst = {
+	0xf3, 0x33, 0x88, 0x86, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x4e, 0x91
+};
+static const u8 enc_nonce001[] __initconst = {
+	0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08
+};
+static const u8 enc_key001[] __initconst = {
+	0x1c, 0x92, 0x40, 0xa5, 0xeb, 0x55, 0xd3, 0x8a,
+	0xf3, 0x33, 0x88, 0x86, 0x04, 0xf6, 0xb5, 0xf0,
+	0x47, 0x39, 0x17, 0xc1, 0x40, 0x2b, 0x80, 0x09,
+	0x9d, 0xca, 0x5c, 0xbc, 0x20, 0x70, 0x75, 0xc0
+};
+
+static const u8 enc_input002[] __initconst = { };
+static const u8 enc_output002[] __initconst = {
+	0xea, 0xe0, 0x1e, 0x9e, 0x2c, 0x91, 0xaa, 0xe1,
+	0xdb, 0x5d, 0x99, 0x3f, 0x8a, 0xf7, 0x69, 0x92
+};
+static const u8 enc_assoc002[] __initconst = { };
+static const u8 enc_nonce002[] __initconst = {
+	0xca, 0xbf, 0x33, 0x71, 0x32, 0x45, 0x77, 0x8e
+};
+static const u8 enc_key002[] __initconst = {
+	0x4c, 0xf5, 0x96, 0x83, 0x38, 0xe6, 0xae, 0x7f,
+	0x2d, 0x29, 0x25, 0x76, 0xd5, 0x75, 0x27, 0x86,
+	0x91, 0x9a, 0x27, 0x7a, 0xfb, 0x46, 0xc5, 0xef,
+	0x94, 0x81, 0x79, 0x57, 0x14, 0x59, 0x40, 0x68
+};
+
+static const u8 enc_input003[] __initconst = { };
+static const u8 enc_output003[] __initconst = {
+	0xdd, 0x6b, 0x3b, 0x82, 0xce, 0x5a, 0xbd, 0xd6,
+	0xa9, 0x35, 0x83, 0xd8, 0x8c, 0x3d, 0x85, 0x77
+};
+static const u8 enc_assoc003[] __initconst = {
+	0x33, 0x10, 0x41, 0x12, 0x1f, 0xf3, 0xd2, 0x6b
+};
+static const u8 enc_nonce003[] __initconst = {
+	0x3d, 0x86, 0xb5, 0x6b, 0xc8, 0xa3, 0x1f, 0x1d
+};
+static const u8 enc_key003[] __initconst = {
+	0x2d, 0xb0, 0x5d, 0x40, 0xc8, 0xed, 0x44, 0x88,
+	0x34, 0xd1, 0x13, 0xaf, 0x57, 0xa1, 0xeb, 0x3a,
+	0x2a, 0x80, 0x51, 0x36, 0xec, 0x5b, 0xbc, 0x08,
+	0x93, 0x84, 0x21, 0xb5, 0x13, 0x88, 0x3c, 0x0d
+};
+
+static const u8 enc_input004[] __initconst = {
+	0xa4
+};
+static const u8 enc_output004[] __initconst = {
+	0xb7, 0x1b, 0xb0, 0x73, 0x59, 0xb0, 0x84, 0xb2,
+	0x6d, 0x8e, 0xab, 0x94, 0x31, 0xa1, 0xae, 0xac,
+	0x89
+};
+static const u8 enc_assoc004[] __initconst = {
+	0x6a, 0xe2, 0xad, 0x3f, 0x88, 0x39, 0x5a, 0x40
+};
+static const u8 enc_nonce004[] __initconst = {
+	0xd2, 0x32, 0x1f, 0x29, 0x28, 0xc6, 0xc4, 0xc4
+};
+static const u8 enc_key004[] __initconst = {
+	0x4b, 0x28, 0x4b, 0xa3, 0x7b, 0xbe, 0xe9, 0xf8,
+	0x31, 0x80, 0x82, 0xd7, 0xd8, 0xe8, 0xb5, 0xa1,
+	0xe2, 0x18, 0x18, 0x8a, 0x9c, 0xfa, 0xa3, 0x3d,
+	0x25, 0x71, 0x3e, 0x40, 0xbc, 0x54, 0x7a, 0x3e
+};
+
+static const u8 enc_input005[] __initconst = {
+	0x2d
+};
+static const u8 enc_output005[] __initconst = {
+	0xbf, 0xe1, 0x5b, 0x0b, 0xdb, 0x6b, 0xf5, 0x5e,
+	0x6c, 0x5d, 0x84, 0x44, 0x39, 0x81, 0xc1, 0x9c,
+	0xac
+};
+static const u8 enc_assoc005[] __initconst = { };
+static const u8 enc_nonce005[] __initconst = {
+	0x20, 0x1c, 0xaa, 0x5f, 0x9c, 0xbf, 0x92, 0x30
+};
+static const u8 enc_key005[] __initconst = {
+	0x66, 0xca, 0x9c, 0x23, 0x2a, 0x4b, 0x4b, 0x31,
+	0x0e, 0x92, 0x89, 0x8b, 0xf4, 0x93, 0xc7, 0x87,
+	0x98, 0xa3, 0xd8, 0x39, 0xf8, 0xf4, 0xa7, 0x01,
+	0xc0, 0x2e, 0x0a, 0xa6, 0x7e, 0x5a, 0x78, 0x87
+};
+
+static const u8 enc_input006[] __initconst = {
+	0x33, 0x2f, 0x94, 0xc1, 0xa4, 0xef, 0xcc, 0x2a,
+	0x5b, 0xa6, 0xe5, 0x8f, 0x1d, 0x40, 0xf0, 0x92,
+	0x3c, 0xd9, 0x24, 0x11, 0xa9, 0x71, 0xf9, 0x37,
+	0x14, 0x99, 0xfa, 0xbe, 0xe6, 0x80, 0xde, 0x50,
+	0xc9, 0x96, 0xd4, 0xb0, 0xec, 0x9e, 0x17, 0xec,
+	0xd2, 0x5e, 0x72, 0x99, 0xfc, 0x0a, 0xe1, 0xcb,
+	0x48, 0xd2, 0x85, 0xdd, 0x2f, 0x90, 0xe0, 0x66,
+	0x3b, 0xe6, 0x20, 0x74, 0xbe, 0x23, 0x8f, 0xcb,
+	0xb4, 0xe4, 0xda, 0x48, 0x40, 0xa6, 0xd1, 0x1b,
+	0xc7, 0x42, 0xce, 0x2f, 0x0c, 0xa6, 0x85, 0x6e,
+	0x87, 0x37, 0x03, 0xb1, 0x7c, 0x25, 0x96, 0xa3,
+	0x05, 0xd8, 0xb0, 0xf4, 0xed, 0xea, 0xc2, 0xf0,
+	0x31, 0x98, 0x6c, 0xd1, 0x14, 0x25, 0xc0, 0xcb,
+	0x01, 0x74, 0xd0, 0x82, 0xf4, 0x36, 0xf5, 0x41,
+	0xd5, 0xdc, 0xca, 0xc5, 0xbb, 0x98, 0xfe, 0xfc,
+	0x69, 0x21, 0x70, 0xd8, 0xa4, 0x4b, 0xc8, 0xde,
+	0x8f
+};
+static const u8 enc_output006[] __initconst = {
+	0x8b, 0x06, 0xd3, 0x31, 0xb0, 0x93, 0x45, 0xb1,
+	0x75, 0x6e, 0x26, 0xf9, 0x67, 0xbc, 0x90, 0x15,
+	0x81, 0x2c, 0xb5, 0xf0, 0xc6, 0x2b, 0xc7, 0x8c,
+	0x56, 0xd1, 0xbf, 0x69, 0x6c, 0x07, 0xa0, 0xda,
+	0x65, 0x27, 0xc9, 0x90, 0x3d, 0xef, 0x4b, 0x11,
+	0x0f, 0x19, 0x07, 0xfd, 0x29, 0x92, 0xd9, 0xc8,
+	0xf7, 0x99, 0x2e, 0x4a, 0xd0, 0xb8, 0x2c, 0xdc,
+	0x93, 0xf5, 0x9e, 0x33, 0x78, 0xd1, 0x37, 0xc3,
+	0x66, 0xd7, 0x5e, 0xbc, 0x44, 0xbf, 0x53, 0xa5,
+	0xbc, 0xc4, 0xcb, 0x7b, 0x3a, 0x8e, 0x7f, 0x02,
+	0xbd, 0xbb, 0xe7, 0xca, 0xa6, 0x6c, 0x6b, 0x93,
+	0x21, 0x93, 0x10, 0x61, 0xe7, 0x69, 0xd0, 0x78,
+	0xf3, 0x07, 0x5a, 0x1a, 0x8f, 0x73, 0xaa, 0xb1,
+	0x4e, 0xd3, 0xda, 0x4f, 0xf3, 0x32, 0xe1, 0x66,
+	0x3e, 0x6c, 0xc6, 0x13, 0xba, 0x06, 0x5b, 0xfc,
+	0x6a, 0xe5, 0x6f, 0x60, 0xfb, 0x07, 0x40, 0xb0,
+	0x8c, 0x9d, 0x84, 0x43, 0x6b, 0xc1, 0xf7, 0x8d,
+	0x8d, 0x31, 0xf7, 0x7a, 0x39, 0x4d, 0x8f, 0x9a,
+	0xeb
+};
+static const u8 enc_assoc006[] __initconst = {
+	0x70, 0xd3, 0x33, 0xf3, 0x8b, 0x18, 0x0b
+};
+static const u8 enc_nonce006[] __initconst = {
+	0xdf, 0x51, 0x84, 0x82, 0x42, 0x0c, 0x75, 0x9c
+};
+static const u8 enc_key006[] __initconst = {
+	0x68, 0x7b, 0x8d, 0x8e, 0xe3, 0xc4, 0xdd, 0xae,
+	0xdf, 0x72, 0x7f, 0x53, 0x72, 0x25, 0x1e, 0x78,
+	0x91, 0xcb, 0x69, 0x76, 0x1f, 0x49, 0x93, 0xf9,
+	0x6f, 0x21, 0xcc, 0x39, 0x9c, 0xad, 0xb1, 0x01
+};
+
+static const u8 enc_input007[] __initconst = {
+	0x9b, 0x18, 0xdb, 0xdd, 0x9a, 0x0f, 0x3e, 0xa5,
+	0x15, 0x17, 0xde, 0xdf, 0x08, 0x9d, 0x65, 0x0a,
+	0x67, 0x30, 0x12, 0xe2, 0x34, 0x77, 0x4b, 0xc1,
+	0xd9, 0xc6, 0x1f, 0xab, 0xc6, 0x18, 0x50, 0x17,
+	0xa7, 0x9d, 0x3c, 0xa6, 0xc5, 0x35, 0x8c, 0x1c,
+	0xc0, 0xa1, 0x7c, 0x9f, 0x03, 0x89, 0xca, 0xe1,
+	0xe6, 0xe9, 0xd4, 0xd3, 0x88, 0xdb, 0xb4, 0x51,
+	0x9d, 0xec, 0xb4, 0xfc, 0x52, 0xee, 0x6d, 0xf1,
+	0x75, 0x42, 0xc6, 0xfd, 0xbd, 0x7a, 0x8e, 0x86,
+	0xfc, 0x44, 0xb3, 0x4f, 0xf3, 0xea, 0x67, 0x5a,
+	0x41, 0x13, 0xba, 0xb0, 0xdc, 0xe1, 0xd3, 0x2a,
+	0x7c, 0x22, 0xb3, 0xca, 0xac, 0x6a, 0x37, 0x98,
+	0x3e, 0x1d, 0x40, 0x97, 0xf7, 0x9b, 0x1d, 0x36,
+	0x6b, 0xb3, 0x28, 0xbd, 0x60, 0x82, 0x47, 0x34,
+	0xaa, 0x2f, 0x7d, 0xe9, 0xa8, 0x70, 0x81, 0x57,
+	0xd4, 0xb9, 0x77, 0x0a, 0x9d, 0x29, 0xa7, 0x84,
+	0x52, 0x4f, 0xc2, 0x4a, 0x40, 0x3b, 0x3c, 0xd4,
+	0xc9, 0x2a, 0xdb, 0x4a, 0x53, 0xc4, 0xbe, 0x80,
+	0xe9, 0x51, 0x7f, 0x8f, 0xc7, 0xa2, 0xce, 0x82,
+	0x5c, 0x91, 0x1e, 0x74, 0xd9, 0xd0, 0xbd, 0xd5,
+	0xf3, 0xfd, 0xda, 0x4d, 0x25, 0xb4, 0xbb, 0x2d,
+	0xac, 0x2f, 0x3d, 0x71, 0x85, 0x7b, 0xcf, 0x3c,
+	0x7b, 0x3e, 0x0e, 0x22, 0x78, 0x0c, 0x29, 0xbf,
+	0xe4, 0xf4, 0x57, 0xb3, 0xcb, 0x49, 0xa0, 0xfc,
+	0x1e, 0x05, 0x4e, 0x16, 0xbc, 0xd5, 0xa8, 0xa3,
+	0xee, 0x05, 0x35, 0xc6, 0x7c, 0xab, 0x60, 0x14,
+	0x55, 0x1a, 0x8e, 0xc5, 0x88, 0x5d, 0xd5, 0x81,
+	0xc2, 0x81, 0xa5, 0xc4, 0x60, 0xdb, 0xaf, 0x77,
+	0x91, 0xe1, 0xce, 0xa2, 0x7e, 0x7f, 0x42, 0xe3,
+	0xb0, 0x13, 0x1c, 0x1f, 0x25, 0x60, 0x21, 0xe2,
+	0x40, 0x5f, 0x99, 0xb7, 0x73, 0xec, 0x9b, 0x2b,
+	0xf0, 0x65, 0x11, 0xc8, 0xd0, 0x0a, 0x9f, 0xd3
+};
+static const u8 enc_output007[] __initconst = {
+	0x85, 0x04, 0xc2, 0xed, 0x8d, 0xfd, 0x97, 0x5c,
+	0xd2, 0xb7, 0xe2, 0xc1, 0x6b, 0xa3, 0xba, 0xf8,
+	0xc9, 0x50, 0xc3, 0xc6, 0xa5, 0xe3, 0xa4, 0x7c,
+	0xc3, 0x23, 0x49, 0x5e, 0xa9, 0xb9, 0x32, 0xeb,
+	0x8a, 0x7c, 0xca, 0xe5, 0xec, 0xfb, 0x7c, 0xc0,
+	0xcb, 0x7d, 0xdc, 0x2c, 0x9d, 0x92, 0x55, 0x21,
+	0x0a, 0xc8, 0x43, 0x63, 0x59, 0x0a, 0x31, 0x70,
+	0x82, 0x67, 0x41, 0x03, 0xf8, 0xdf, 0xf2, 0xac,
+	0xa7, 0x02, 0xd4, 0xd5, 0x8a, 0x2d, 0xc8, 0x99,
+	0x19, 0x66, 0xd0, 0xf6, 0x88, 0x2c, 0x77, 0xd9,
+	0xd4, 0x0d, 0x6c, 0xbd, 0x98, 0xde, 0xe7, 0x7f,
+	0xad, 0x7e, 0x8a, 0xfb, 0xe9, 0x4b, 0xe5, 0xf7,
+	0xe5, 0x50, 0xa0, 0x90, 0x3f, 0xd6, 0x22, 0x53,
+	0xe3, 0xfe, 0x1b, 0xcc, 0x79, 0x3b, 0xec, 0x12,
+	0x47, 0x52, 0xa7, 0xd6, 0x04, 0xe3, 0x52, 0xe6,
+	0x93, 0x90, 0x91, 0x32, 0x73, 0x79, 0xb8, 0xd0,
+	0x31, 0xde, 0x1f, 0x9f, 0x2f, 0x05, 0x38, 0x54,
+	0x2f, 0x35, 0x04, 0x39, 0xe0, 0xa7, 0xba, 0xc6,
+	0x52, 0xf6, 0x37, 0x65, 0x4c, 0x07, 0xa9, 0x7e,
+	0xb3, 0x21, 0x6f, 0x74, 0x8c, 0xc9, 0xde, 0xdb,
+	0x65, 0x1b, 0x9b, 0xaa, 0x60, 0xb1, 0x03, 0x30,
+	0x6b, 0xb2, 0x03, 0xc4, 0x1c, 0x04, 0xf8, 0x0f,
+	0x64, 0xaf, 0x46, 0xe4, 0x65, 0x99, 0x49, 0xe2,
+	0xea, 0xce, 0x78, 0x00, 0xd8, 0x8b, 0xd5, 0x2e,
+	0xcf, 0xfc, 0x40, 0x49, 0xe8, 0x58, 0xdc, 0x34,
+	0x9c, 0x8c, 0x61, 0xbf, 0x0a, 0x8e, 0xec, 0x39,
+	0xa9, 0x30, 0x05, 0x5a, 0xd2, 0x56, 0x01, 0xc7,
+	0xda, 0x8f, 0x4e, 0xbb, 0x43, 0xa3, 0x3a, 0xf9,
+	0x15, 0x2a, 0xd0, 0xa0, 0x7a, 0x87, 0x34, 0x82,
+	0xfe, 0x8a, 0xd1, 0x2d, 0x5e, 0xc7, 0xbf, 0x04,
+	0x53, 0x5f, 0x3b, 0x36, 0xd4, 0x25, 0x5c, 0x34,
+	0x7a, 0x8d, 0xd5, 0x05, 0xce, 0x72, 0xca, 0xef,
+	0x7a, 0x4b, 0xbc, 0xb0, 0x10, 0x5c, 0x96, 0x42,
+	0x3a, 0x00, 0x98, 0xcd, 0x15, 0xe8, 0xb7, 0x53
+};
+static const u8 enc_assoc007[] __initconst = { };
+static const u8 enc_nonce007[] __initconst = {
+	0xde, 0x7b, 0xef, 0xc3, 0x65, 0x1b, 0x68, 0xb0
+};
+static const u8 enc_key007[] __initconst = {
+	0x8d, 0xb8, 0x91, 0x48, 0xf0, 0xe7, 0x0a, 0xbd,
+	0xf9, 0x3f, 0xcd, 0xd9, 0xa0, 0x1e, 0x42, 0x4c,
+	0xe7, 0xde, 0x25, 0x3d, 0xa3, 0xd7, 0x05, 0x80,
+	0x8d, 0xf2, 0x82, 0xac, 0x44, 0x16, 0x51, 0x01
+};
+
+static const u8 enc_input008[] __initconst = {
+	0xc3, 0x09, 0x94, 0x62, 0xe6, 0x46, 0x2e, 0x10,
+	0xbe, 0x00, 0xe4, 0xfc, 0xf3, 0x40, 0xa3, 0xe2,
+	0x0f, 0xc2, 0x8b, 0x28, 0xdc, 0xba, 0xb4, 0x3c,
+	0xe4, 0x21, 0x58, 0x61, 0xcd, 0x8b, 0xcd, 0xfb,
+	0xac, 0x94, 0xa1, 0x45, 0xf5, 0x1c, 0xe1, 0x12,
+	0xe0, 0x3b, 0x67, 0x21, 0x54, 0x5e, 0x8c, 0xaa,
+	0xcf, 0xdb, 0xb4, 0x51, 0xd4, 0x13, 0xda, 0xe6,
+	0x83, 0x89, 0xb6, 0x92, 0xe9, 0x21, 0x76, 0xa4,
+	0x93, 0x7d, 0x0e, 0xfd, 0x96, 0x36, 0x03, 0x91,
+	0x43, 0x5c, 0x92, 0x49, 0x62, 0x61, 0x7b, 0xeb,
+	0x43, 0x89, 0xb8, 0x12, 0x20, 0x43, 0xd4, 0x47,
+	0x06, 0x84, 0xee, 0x47, 0xe9, 0x8a, 0x73, 0x15,
+	0x0f, 0x72, 0xcf, 0xed, 0xce, 0x96, 0xb2, 0x7f,
+	0x21, 0x45, 0x76, 0xeb, 0x26, 0x28, 0x83, 0x6a,
+	0xad, 0xaa, 0xa6, 0x81, 0xd8, 0x55, 0xb1, 0xa3,
+	0x85, 0xb3, 0x0c, 0xdf, 0xf1, 0x69, 0x2d, 0x97,
+	0x05, 0x2a, 0xbc, 0x7c, 0x7b, 0x25, 0xf8, 0x80,
+	0x9d, 0x39, 0x25, 0xf3, 0x62, 0xf0, 0x66, 0x5e,
+	0xf4, 0xa0, 0xcf, 0xd8, 0xfd, 0x4f, 0xb1, 0x1f,
+	0x60, 0x3a, 0x08, 0x47, 0xaf, 0xe1, 0xf6, 0x10,
+	0x77, 0x09, 0xa7, 0x27, 0x8f, 0x9a, 0x97, 0x5a,
+	0x26, 0xfa, 0xfe, 0x41, 0x32, 0x83, 0x10, 0xe0,
+	0x1d, 0xbf, 0x64, 0x0d, 0xf4, 0x1c, 0x32, 0x35,
+	0xe5, 0x1b, 0x36, 0xef, 0xd4, 0x4a, 0x93, 0x4d,
+	0x00, 0x7c, 0xec, 0x02, 0x07, 0x8b, 0x5d, 0x7d,
+	0x1b, 0x0e, 0xd1, 0xa6, 0xa5, 0x5d, 0x7d, 0x57,
+	0x88, 0xa8, 0xcc, 0x81, 0xb4, 0x86, 0x4e, 0xb4,
+	0x40, 0xe9, 0x1d, 0xc3, 0xb1, 0x24, 0x3e, 0x7f,
+	0xcc, 0x8a, 0x24, 0x9b, 0xdf, 0x6d, 0xf0, 0x39,
+	0x69, 0x3e, 0x4c, 0xc0, 0x96, 0xe4, 0x13, 0xda,
+	0x90, 0xda, 0xf4, 0x95, 0x66, 0x8b, 0x17, 0x17,
+	0xfe, 0x39, 0x43, 0x25, 0xaa, 0xda, 0xa0, 0x43,
+	0x3c, 0xb1, 0x41, 0x02, 0xa3, 0xf0, 0xa7, 0x19,
+	0x59, 0xbc, 0x1d, 0x7d, 0x6c, 0x6d, 0x91, 0x09,
+	0x5c, 0xb7, 0x5b, 0x01, 0xd1, 0x6f, 0x17, 0x21,
+	0x97, 0xbf, 0x89, 0x71, 0xa5, 0xb0, 0x6e, 0x07,
+	0x45, 0xfd, 0x9d, 0xea, 0x07, 0xf6, 0x7a, 0x9f,
+	0x10, 0x18, 0x22, 0x30, 0x73, 0xac, 0xd4, 0x6b,
+	0x72, 0x44, 0xed, 0xd9, 0x19, 0x9b, 0x2d, 0x4a,
+	0x41, 0xdd, 0xd1, 0x85, 0x5e, 0x37, 0x19, 0xed,
+	0xd2, 0x15, 0x8f, 0x5e, 0x91, 0xdb, 0x33, 0xf2,
+	0xe4, 0xdb, 0xff, 0x98, 0xfb, 0xa3, 0xb5, 0xca,
+	0x21, 0x69, 0x08, 0xe7, 0x8a, 0xdf, 0x90, 0xff,
+	0x3e, 0xe9, 0x20, 0x86, 0x3c, 0xe9, 0xfc, 0x0b,
+	0xfe, 0x5c, 0x61, 0xaa, 0x13, 0x92, 0x7f, 0x7b,
+	0xec, 0xe0, 0x6d, 0xa8, 0x23, 0x22, 0xf6, 0x6b,
+	0x77, 0xc4, 0xfe, 0x40, 0x07, 0x3b, 0xb6, 0xf6,
+	0x8e, 0x5f, 0xd4, 0xb9, 0xb7, 0x0f, 0x21, 0x04,
+	0xef, 0x83, 0x63, 0x91, 0x69, 0x40, 0xa3, 0x48,
+	0x5c, 0xd2, 0x60, 0xf9, 0x4f, 0x6c, 0x47, 0x8b,
+	0x3b, 0xb1, 0x9f, 0x8e, 0xee, 0x16, 0x8a, 0x13,
+	0xfc, 0x46, 0x17, 0xc3, 0xc3, 0x32, 0x56, 0xf8,
+	0x3c, 0x85, 0x3a, 0xb6, 0x3e, 0xaa, 0x89, 0x4f,
+	0xb3, 0xdf, 0x38, 0xfd, 0xf1, 0xe4, 0x3a, 0xc0,
+	0xe6, 0x58, 0xb5, 0x8f, 0xc5, 0x29, 0xa2, 0x92,
+	0x4a, 0xb6, 0xa0, 0x34, 0x7f, 0xab, 0xb5, 0x8a,
+	0x90, 0xa1, 0xdb, 0x4d, 0xca, 0xb6, 0x2c, 0x41,
+	0x3c, 0xf7, 0x2b, 0x21, 0xc3, 0xfd, 0xf4, 0x17,
+	0x5c, 0xb5, 0x33, 0x17, 0x68, 0x2b, 0x08, 0x30,
+	0xf3, 0xf7, 0x30, 0x3c, 0x96, 0xe6, 0x6a, 0x20,
+	0x97, 0xe7, 0x4d, 0x10, 0x5f, 0x47, 0x5f, 0x49,
+	0x96, 0x09, 0xf0, 0x27, 0x91, 0xc8, 0xf8, 0x5a,
+	0x2e, 0x79, 0xb5, 0xe2, 0xb8, 0xe8, 0xb9, 0x7b,
+	0xd5, 0x10, 0xcb, 0xff, 0x5d, 0x14, 0x73, 0xf3
+};
+static const u8 enc_output008[] __initconst = {
+	0x14, 0xf6, 0x41, 0x37, 0xa6, 0xd4, 0x27, 0xcd,
+	0xdb, 0x06, 0x3e, 0x9a, 0x4e, 0xab, 0xd5, 0xb1,
+	0x1e, 0x6b, 0xd2, 0xbc, 0x11, 0xf4, 0x28, 0x93,
+	0x63, 0x54, 0xef, 0xbb, 0x5e, 0x1d, 0x3a, 0x1d,
+	0x37, 0x3c, 0x0a, 0x6c, 0x1e, 0xc2, 0xd1, 0x2c,
+	0xb5, 0xa3, 0xb5, 0x7b, 0xb8, 0x8f, 0x25, 0xa6,
+	0x1b, 0x61, 0x1c, 0xec, 0x28, 0x58, 0x26, 0xa4,
+	0xa8, 0x33, 0x28, 0x25, 0x5c, 0x45, 0x05, 0xe5,
+	0x6c, 0x99, 0xe5, 0x45, 0xc4, 0xa2, 0x03, 0x84,
+	0x03, 0x73, 0x1e, 0x8c, 0x49, 0xac, 0x20, 0xdd,
+	0x8d, 0xb3, 0xc4, 0xf5, 0xe7, 0x4f, 0xf1, 0xed,
+	0xa1, 0x98, 0xde, 0xa4, 0x96, 0xdd, 0x2f, 0xab,
+	0xab, 0x97, 0xcf, 0x3e, 0xd2, 0x9e, 0xb8, 0x13,
+	0x07, 0x28, 0x29, 0x19, 0xaf, 0xfd, 0xf2, 0x49,
+	0x43, 0xea, 0x49, 0x26, 0x91, 0xc1, 0x07, 0xd6,
+	0xbb, 0x81, 0x75, 0x35, 0x0d, 0x24, 0x7f, 0xc8,
+	0xda, 0xd4, 0xb7, 0xeb, 0xe8, 0x5c, 0x09, 0xa2,
+	0x2f, 0xdc, 0x28, 0x7d, 0x3a, 0x03, 0xfa, 0x94,
+	0xb5, 0x1d, 0x17, 0x99, 0x36, 0xc3, 0x1c, 0x18,
+	0x34, 0xe3, 0x9f, 0xf5, 0x55, 0x7c, 0xb0, 0x60,
+	0x9d, 0xff, 0xac, 0xd4, 0x61, 0xf2, 0xad, 0xf8,
+	0xce, 0xc7, 0xbe, 0x5c, 0xd2, 0x95, 0xa8, 0x4b,
+	0x77, 0x13, 0x19, 0x59, 0x26, 0xc9, 0xb7, 0x8f,
+	0x6a, 0xcb, 0x2d, 0x37, 0x91, 0xea, 0x92, 0x9c,
+	0x94, 0x5b, 0xda, 0x0b, 0xce, 0xfe, 0x30, 0x20,
+	0xf8, 0x51, 0xad, 0xf2, 0xbe, 0xe7, 0xc7, 0xff,
+	0xb3, 0x33, 0x91, 0x6a, 0xc9, 0x1a, 0x41, 0xc9,
+	0x0f, 0xf3, 0x10, 0x0e, 0xfd, 0x53, 0xff, 0x6c,
+	0x16, 0x52, 0xd9, 0xf3, 0xf7, 0x98, 0x2e, 0xc9,
+	0x07, 0x31, 0x2c, 0x0c, 0x72, 0xd7, 0xc5, 0xc6,
+	0x08, 0x2a, 0x7b, 0xda, 0xbd, 0x7e, 0x02, 0xea,
+	0x1a, 0xbb, 0xf2, 0x04, 0x27, 0x61, 0x28, 0x8e,
+	0xf5, 0x04, 0x03, 0x1f, 0x4c, 0x07, 0x55, 0x82,
+	0xec, 0x1e, 0xd7, 0x8b, 0x2f, 0x65, 0x56, 0xd1,
+	0xd9, 0x1e, 0x3c, 0xe9, 0x1f, 0x5e, 0x98, 0x70,
+	0x38, 0x4a, 0x8c, 0x49, 0xc5, 0x43, 0xa0, 0xa1,
+	0x8b, 0x74, 0x9d, 0x4c, 0x62, 0x0d, 0x10, 0x0c,
+	0xf4, 0x6c, 0x8f, 0xe0, 0xaa, 0x9a, 0x8d, 0xb7,
+	0xe0, 0xbe, 0x4c, 0x87, 0xf1, 0x98, 0x2f, 0xcc,
+	0xed, 0xc0, 0x52, 0x29, 0xdc, 0x83, 0xf8, 0xfc,
+	0x2c, 0x0e, 0xa8, 0x51, 0x4d, 0x80, 0x0d, 0xa3,
+	0xfe, 0xd8, 0x37, 0xe7, 0x41, 0x24, 0xfc, 0xfb,
+	0x75, 0xe3, 0x71, 0x7b, 0x57, 0x45, 0xf5, 0x97,
+	0x73, 0x65, 0x63, 0x14, 0x74, 0xb8, 0x82, 0x9f,
+	0xf8, 0x60, 0x2f, 0x8a, 0xf2, 0x4e, 0xf1, 0x39,
+	0xda, 0x33, 0x91, 0xf8, 0x36, 0xe0, 0x8d, 0x3f,
+	0x1f, 0x3b, 0x56, 0xdc, 0xa0, 0x8f, 0x3c, 0x9d,
+	0x71, 0x52, 0xa7, 0xb8, 0xc0, 0xa5, 0xc6, 0xa2,
+	0x73, 0xda, 0xf4, 0x4b, 0x74, 0x5b, 0x00, 0x3d,
+	0x99, 0xd7, 0x96, 0xba, 0xe6, 0xe1, 0xa6, 0x96,
+	0x38, 0xad, 0xb3, 0xc0, 0xd2, 0xba, 0x91, 0x6b,
+	0xf9, 0x19, 0xdd, 0x3b, 0xbe, 0xbe, 0x9c, 0x20,
+	0x50, 0xba, 0xa1, 0xd0, 0xce, 0x11, 0xbd, 0x95,
+	0xd8, 0xd1, 0xdd, 0x33, 0x85, 0x74, 0xdc, 0xdb,
+	0x66, 0x76, 0x44, 0xdc, 0x03, 0x74, 0x48, 0x35,
+	0x98, 0xb1, 0x18, 0x47, 0x94, 0x7d, 0xff, 0x62,
+	0xe4, 0x58, 0x78, 0xab, 0xed, 0x95, 0x36, 0xd9,
+	0x84, 0x91, 0x82, 0x64, 0x41, 0xbb, 0x58, 0xe6,
+	0x1c, 0x20, 0x6d, 0x15, 0x6b, 0x13, 0x96, 0xe8,
+	0x35, 0x7f, 0xdc, 0x40, 0x2c, 0xe9, 0xbc, 0x8a,
+	0x4f, 0x92, 0xec, 0x06, 0x2d, 0x50, 0xdf, 0x93,
+	0x5d, 0x65, 0x5a, 0xa8, 0xfc, 0x20, 0x50, 0x14,
+	0xa9, 0x8a, 0x7e, 0x1d, 0x08, 0x1f, 0xe2, 0x99,
+	0xd0, 0xbe, 0xfb, 0x3a, 0x21, 0x9d, 0xad, 0x86,
+	0x54, 0xfd, 0x0d, 0x98, 0x1c, 0x5a, 0x6f, 0x1f,
+	0x9a, 0x40, 0xcd, 0xa2, 0xff, 0x6a, 0xf1, 0x54
+};
+static const u8 enc_assoc008[] __initconst = { };
+static const u8 enc_nonce008[] __initconst = {
+	0x0e, 0x0d, 0x57, 0xbb, 0x7b, 0x40, 0x54, 0x02
+};
+static const u8 enc_key008[] __initconst = {
+	0xf2, 0xaa, 0x4f, 0x99, 0xfd, 0x3e, 0xa8, 0x53,
+	0xc1, 0x44, 0xe9, 0x81, 0x18, 0xdc, 0xf5, 0xf0,
+	0x3e, 0x44, 0x15, 0x59, 0xe0, 0xc5, 0x44, 0x86,
+	0xc3, 0x91, 0xa8, 0x75, 0xc0, 0x12, 0x46, 0xba
+};
+
+static const u8 enc_input009[] __initconst = {
+	0xe6, 0xc3, 0xdb, 0x63, 0x55, 0x15, 0xe3, 0x5b,
+	0xb7, 0x4b, 0x27, 0x8b, 0x5a, 0xdd, 0xc2, 0xe8,
+	0x3a, 0x6b, 0xd7, 0x81, 0x96, 0x35, 0x97, 0xca,
+	0xd7, 0x68, 0xe8, 0xef, 0xce, 0xab, 0xda, 0x09,
+	0x6e, 0xd6, 0x8e, 0xcb, 0x55, 0xb5, 0xe1, 0xe5,
+	0x57, 0xfd, 0xc4, 0xe3, 0xe0, 0x18, 0x4f, 0x85,
+	0xf5, 0x3f, 0x7e, 0x4b, 0x88, 0xc9, 0x52, 0x44,
+	0x0f, 0xea, 0xaf, 0x1f, 0x71, 0x48, 0x9f, 0x97,
+	0x6d, 0xb9, 0x6f, 0x00, 0xa6, 0xde, 0x2b, 0x77,
+	0x8b, 0x15, 0xad, 0x10, 0xa0, 0x2b, 0x7b, 0x41,
+	0x90, 0x03, 0x2d, 0x69, 0xae, 0xcc, 0x77, 0x7c,
+	0xa5, 0x9d, 0x29, 0x22, 0xc2, 0xea, 0xb4, 0x00,
+	0x1a, 0xd2, 0x7a, 0x98, 0x8a, 0xf9, 0xf7, 0x82,
+	0xb0, 0xab, 0xd8, 0xa6, 0x94, 0x8d, 0x58, 0x2f,
+	0x01, 0x9e, 0x00, 0x20, 0xfc, 0x49, 0xdc, 0x0e,
+	0x03, 0xe8, 0x45, 0x10, 0xd6, 0xa8, 0xda, 0x55,
+	0x10, 0x9a, 0xdf, 0x67, 0x22, 0x8b, 0x43, 0xab,
+	0x00, 0xbb, 0x02, 0xc8, 0xdd, 0x7b, 0x97, 0x17,
+	0xd7, 0x1d, 0x9e, 0x02, 0x5e, 0x48, 0xde, 0x8e,
+	0xcf, 0x99, 0x07, 0x95, 0x92, 0x3c, 0x5f, 0x9f,
+	0xc5, 0x8a, 0xc0, 0x23, 0xaa, 0xd5, 0x8c, 0x82,
+	0x6e, 0x16, 0x92, 0xb1, 0x12, 0x17, 0x07, 0xc3,
+	0xfb, 0x36, 0xf5, 0x6c, 0x35, 0xd6, 0x06, 0x1f,
+	0x9f, 0xa7, 0x94, 0xa2, 0x38, 0x63, 0x9c, 0xb0,
+	0x71, 0xb3, 0xa5, 0xd2, 0xd8, 0xba, 0x9f, 0x08,
+	0x01, 0xb3, 0xff, 0x04, 0x97, 0x73, 0x45, 0x1b,
+	0xd5, 0xa9, 0x9c, 0x80, 0xaf, 0x04, 0x9a, 0x85,
+	0xdb, 0x32, 0x5b, 0x5d, 0x1a, 0xc1, 0x36, 0x28,
+	0x10, 0x79, 0xf1, 0x3c, 0xbf, 0x1a, 0x41, 0x5c,
+	0x4e, 0xdf, 0xb2, 0x7c, 0x79, 0x3b, 0x7a, 0x62,
+	0x3d, 0x4b, 0xc9, 0x9b, 0x2a, 0x2e, 0x7c, 0xa2,
+	0xb1, 0x11, 0x98, 0xa7, 0x34, 0x1a, 0x00, 0xf3,
+	0xd1, 0xbc, 0x18, 0x22, 0xba, 0x02, 0x56, 0x62,
+	0x31, 0x10, 0x11, 0x6d, 0xe0, 0x54, 0x9d, 0x40,
+	0x1f, 0x26, 0x80, 0x41, 0xca, 0x3f, 0x68, 0x0f,
+	0x32, 0x1d, 0x0a, 0x8e, 0x79, 0xd8, 0xa4, 0x1b,
+	0x29, 0x1c, 0x90, 0x8e, 0xc5, 0xe3, 0xb4, 0x91,
+	0x37, 0x9a, 0x97, 0x86, 0x99, 0xd5, 0x09, 0xc5,
+	0xbb, 0xa3, 0x3f, 0x21, 0x29, 0x82, 0x14, 0x5c,
+	0xab, 0x25, 0xfb, 0xf2, 0x4f, 0x58, 0x26, 0xd4,
+	0x83, 0xaa, 0x66, 0x89, 0x67, 0x7e, 0xc0, 0x49,
+	0xe1, 0x11, 0x10, 0x7f, 0x7a, 0xda, 0x29, 0x04,
+	0xff, 0xf0, 0xcb, 0x09, 0x7c, 0x9d, 0xfa, 0x03,
+	0x6f, 0x81, 0x09, 0x31, 0x60, 0xfb, 0x08, 0xfa,
+	0x74, 0xd3, 0x64, 0x44, 0x7c, 0x55, 0x85, 0xec,
+	0x9c, 0x6e, 0x25, 0xb7, 0x6c, 0xc5, 0x37, 0xb6,
+	0x83, 0x87, 0x72, 0x95, 0x8b, 0x9d, 0xe1, 0x69,
+	0x5c, 0x31, 0x95, 0x42, 0xa6, 0x2c, 0xd1, 0x36,
+	0x47, 0x1f, 0xec, 0x54, 0xab, 0xa2, 0x1c, 0xd8,
+	0x00, 0xcc, 0xbc, 0x0d, 0x65, 0xe2, 0x67, 0xbf,
+	0xbc, 0xea, 0xee, 0x9e, 0xe4, 0x36, 0x95, 0xbe,
+	0x73, 0xd9, 0xa6, 0xd9, 0x0f, 0xa0, 0xcc, 0x82,
+	0x76, 0x26, 0xad, 0x5b, 0x58, 0x6c, 0x4e, 0xab,
+	0x29, 0x64, 0xd3, 0xd9, 0xa9, 0x08, 0x8c, 0x1d,
+	0xa1, 0x4f, 0x80, 0xd8, 0x3f, 0x94, 0xfb, 0xd3,
+	0x7b, 0xfc, 0xd1, 0x2b, 0xc3, 0x21, 0xeb, 0xe5,
+	0x1c, 0x84, 0x23, 0x7f, 0x4b, 0xfa, 0xdb, 0x34,
+	0x18, 0xa2, 0xc2, 0xe5, 0x13, 0xfe, 0x6c, 0x49,
+	0x81, 0xd2, 0x73, 0xe7, 0xe2, 0xd7, 0xe4, 0x4f,
+	0x4b, 0x08, 0x6e, 0xb1, 0x12, 0x22, 0x10, 0x9d,
+	0xac, 0x51, 0x1e, 0x17, 0xd9, 0x8a, 0x0b, 0x42,
+	0x88, 0x16, 0x81, 0x37, 0x7c, 0x6a, 0xf7, 0xef,
+	0x2d, 0xe3, 0xd9, 0xf8, 0x5f, 0xe0, 0x53, 0x27,
+	0x74, 0xb9, 0xe2, 0xd6, 0x1c, 0x80, 0x2c, 0x52,
+	0x65
+};
+static const u8 enc_output009[] __initconst = {
+	0xfd, 0x81, 0x8d, 0xd0, 0x3d, 0xb4, 0xd5, 0xdf,
+	0xd3, 0x42, 0x47, 0x5a, 0x6d, 0x19, 0x27, 0x66,
+	0x4b, 0x2e, 0x0c, 0x27, 0x9c, 0x96, 0x4c, 0x72,
+	0x02, 0xa3, 0x65, 0xc3, 0xb3, 0x6f, 0x2e, 0xbd,
+	0x63, 0x8a, 0x4a, 0x5d, 0x29, 0xa2, 0xd0, 0x28,
+	0x48, 0xc5, 0x3d, 0x98, 0xa3, 0xbc, 0xe0, 0xbe,
+	0x3b, 0x3f, 0xe6, 0x8a, 0xa4, 0x7f, 0x53, 0x06,
+	0xfa, 0x7f, 0x27, 0x76, 0x72, 0x31, 0xa1, 0xf5,
+	0xd6, 0x0c, 0x52, 0x47, 0xba, 0xcd, 0x4f, 0xd7,
+	0xeb, 0x05, 0x48, 0x0d, 0x7c, 0x35, 0x4a, 0x09,
+	0xc9, 0x76, 0x71, 0x02, 0xa3, 0xfb, 0xb7, 0x1a,
+	0x65, 0xb7, 0xed, 0x98, 0xc6, 0x30, 0x8a, 0x00,
+	0xae, 0xa1, 0x31, 0xe5, 0xb5, 0x9e, 0x6d, 0x62,
+	0xda, 0xda, 0x07, 0x0f, 0x38, 0x38, 0xd3, 0xcb,
+	0xc1, 0xb0, 0xad, 0xec, 0x72, 0xec, 0xb1, 0xa2,
+	0x7b, 0x59, 0xf3, 0x3d, 0x2b, 0xef, 0xcd, 0x28,
+	0x5b, 0x83, 0xcc, 0x18, 0x91, 0x88, 0xb0, 0x2e,
+	0xf9, 0x29, 0x31, 0x18, 0xf9, 0x4e, 0xe9, 0x0a,
+	0x91, 0x92, 0x9f, 0xae, 0x2d, 0xad, 0xf4, 0xe6,
+	0x1a, 0xe2, 0xa4, 0xee, 0x47, 0x15, 0xbf, 0x83,
+	0x6e, 0xd7, 0x72, 0x12, 0x3b, 0x2d, 0x24, 0xe9,
+	0xb2, 0x55, 0xcb, 0x3c, 0x10, 0xf0, 0x24, 0x8a,
+	0x4a, 0x02, 0xea, 0x90, 0x25, 0xf0, 0xb4, 0x79,
+	0x3a, 0xef, 0x6e, 0xf5, 0x52, 0xdf, 0xb0, 0x0a,
+	0xcd, 0x24, 0x1c, 0xd3, 0x2e, 0x22, 0x74, 0xea,
+	0x21, 0x6f, 0xe9, 0xbd, 0xc8, 0x3e, 0x36, 0x5b,
+	0x19, 0xf1, 0xca, 0x99, 0x0a, 0xb4, 0xa7, 0x52,
+	0x1a, 0x4e, 0xf2, 0xad, 0x8d, 0x56, 0x85, 0xbb,
+	0x64, 0x89, 0xba, 0x26, 0xf9, 0xc7, 0xe1, 0x89,
+	0x19, 0x22, 0x77, 0xc3, 0xa8, 0xfc, 0xff, 0xad,
+	0xfe, 0xb9, 0x48, 0xae, 0x12, 0x30, 0x9f, 0x19,
+	0xfb, 0x1b, 0xef, 0x14, 0x87, 0x8a, 0x78, 0x71,
+	0xf3, 0xf4, 0xb7, 0x00, 0x9c, 0x1d, 0xb5, 0x3d,
+	0x49, 0x00, 0x0c, 0x06, 0xd4, 0x50, 0xf9, 0x54,
+	0x45, 0xb2, 0x5b, 0x43, 0xdb, 0x6d, 0xcf, 0x1a,
+	0xe9, 0x7a, 0x7a, 0xcf, 0xfc, 0x8a, 0x4e, 0x4d,
+	0x0b, 0x07, 0x63, 0x28, 0xd8, 0xe7, 0x08, 0x95,
+	0xdf, 0xa6, 0x72, 0x93, 0x2e, 0xbb, 0xa0, 0x42,
+	0x89, 0x16, 0xf1, 0xd9, 0x0c, 0xf9, 0xa1, 0x16,
+	0xfd, 0xd9, 0x03, 0xb4, 0x3b, 0x8a, 0xf5, 0xf6,
+	0xe7, 0x6b, 0x2e, 0x8e, 0x4c, 0x3d, 0xe2, 0xaf,
+	0x08, 0x45, 0x03, 0xff, 0x09, 0xb6, 0xeb, 0x2d,
+	0xc6, 0x1b, 0x88, 0x94, 0xac, 0x3e, 0xf1, 0x9f,
+	0x0e, 0x0e, 0x2b, 0xd5, 0x00, 0x4d, 0x3f, 0x3b,
+	0x53, 0xae, 0xaf, 0x1c, 0x33, 0x5f, 0x55, 0x6e,
+	0x8d, 0xaf, 0x05, 0x7a, 0x10, 0x34, 0xc9, 0xf4,
+	0x66, 0xcb, 0x62, 0x12, 0xa6, 0xee, 0xe8, 0x1c,
+	0x5d, 0x12, 0x86, 0xdb, 0x6f, 0x1c, 0x33, 0xc4,
+	0x1c, 0xda, 0x82, 0x2d, 0x3b, 0x59, 0xfe, 0xb1,
+	0xa4, 0x59, 0x41, 0x86, 0xd0, 0xef, 0xae, 0xfb,
+	0xda, 0x6d, 0x11, 0xb8, 0xca, 0xe9, 0x6e, 0xff,
+	0xf7, 0xa9, 0xd9, 0x70, 0x30, 0xfc, 0x53, 0xe2,
+	0xd7, 0xa2, 0x4e, 0xc7, 0x91, 0xd9, 0x07, 0x06,
+	0xaa, 0xdd, 0xb0, 0x59, 0x28, 0x1d, 0x00, 0x66,
+	0xc5, 0x54, 0xc2, 0xfc, 0x06, 0xda, 0x05, 0x90,
+	0x52, 0x1d, 0x37, 0x66, 0xee, 0xf0, 0xb2, 0x55,
+	0x8a, 0x5d, 0xd2, 0x38, 0x86, 0x94, 0x9b, 0xfc,
+	0x10, 0x4c, 0xa1, 0xb9, 0x64, 0x3e, 0x44, 0xb8,
+	0x5f, 0xb0, 0x0c, 0xec, 0xe0, 0xc9, 0xe5, 0x62,
+	0x75, 0x3f, 0x09, 0xd5, 0xf5, 0xd9, 0x26, 0xba,
+	0x9e, 0xd2, 0xf4, 0xb9, 0x48, 0x0a, 0xbc, 0xa2,
+	0xd6, 0x7c, 0x36, 0x11, 0x7d, 0x26, 0x81, 0x89,
+	0xcf, 0xa4, 0xad, 0x73, 0x0e, 0xee, 0xcc, 0x06,
+	0xa9, 0xdb, 0xb1, 0xfd, 0xfb, 0x09, 0x7f, 0x90,
+	0x42, 0x37, 0x2f, 0xe1, 0x9c, 0x0f, 0x6f, 0xcf,
+	0x43, 0xb5, 0xd9, 0x90, 0xe1, 0x85, 0xf5, 0xa8,
+	0xae
+};
+static const u8 enc_assoc009[] __initconst = {
+	0x5a, 0x27, 0xff, 0xeb, 0xdf, 0x84, 0xb2, 0x9e,
+	0xef
+};
+static const u8 enc_nonce009[] __initconst = {
+	0xef, 0x2d, 0x63, 0xee, 0x6b, 0x80, 0x8b, 0x78
+};
+static const u8 enc_key009[] __initconst = {
+	0xea, 0xbc, 0x56, 0x99, 0xe3, 0x50, 0xff, 0xc5,
+	0xcc, 0x1a, 0xd7, 0xc1, 0x57, 0x72, 0xea, 0x86,
+	0x5b, 0x89, 0x88, 0x61, 0x3d, 0x2f, 0x9b, 0xb2,
+	0xe7, 0x9c, 0xec, 0x74, 0x6e, 0x3e, 0xf4, 0x3b
+};
+
+static const u8 enc_input010[] __initconst = {
+	0x42, 0x93, 0xe4, 0xeb, 0x97, 0xb0, 0x57, 0xbf,
+	0x1a, 0x8b, 0x1f, 0xe4, 0x5f, 0x36, 0x20, 0x3c,
+	0xef, 0x0a, 0xa9, 0x48, 0x5f, 0x5f, 0x37, 0x22,
+	0x3a, 0xde, 0xe3, 0xae, 0xbe, 0xad, 0x07, 0xcc,
+	0xb1, 0xf6, 0xf5, 0xf9, 0x56, 0xdd, 0xe7, 0x16,
+	0x1e, 0x7f, 0xdf, 0x7a, 0x9e, 0x75, 0xb7, 0xc7,
+	0xbe, 0xbe, 0x8a, 0x36, 0x04, 0xc0, 0x10, 0xf4,
+	0x95, 0x20, 0x03, 0xec, 0xdc, 0x05, 0xa1, 0x7d,
+	0xc4, 0xa9, 0x2c, 0x82, 0xd0, 0xbc, 0x8b, 0xc5,
+	0xc7, 0x45, 0x50, 0xf6, 0xa2, 0x1a, 0xb5, 0x46,
+	0x3b, 0x73, 0x02, 0xa6, 0x83, 0x4b, 0x73, 0x82,
+	0x58, 0x5e, 0x3b, 0x65, 0x2f, 0x0e, 0xfd, 0x2b,
+	0x59, 0x16, 0xce, 0xa1, 0x60, 0x9c, 0xe8, 0x3a,
+	0x99, 0xed, 0x8d, 0x5a, 0xcf, 0xf6, 0x83, 0xaf,
+	0xba, 0xd7, 0x73, 0x73, 0x40, 0x97, 0x3d, 0xca,
+	0xef, 0x07, 0x57, 0xe6, 0xd9, 0x70, 0x0e, 0x95,
+	0xae, 0xa6, 0x8d, 0x04, 0xcc, 0xee, 0xf7, 0x09,
+	0x31, 0x77, 0x12, 0xa3, 0x23, 0x97, 0x62, 0xb3,
+	0x7b, 0x32, 0xfb, 0x80, 0x14, 0x48, 0x81, 0xc3,
+	0xe5, 0xea, 0x91, 0x39, 0x52, 0x81, 0xa2, 0x4f,
+	0xe4, 0xb3, 0x09, 0xff, 0xde, 0x5e, 0xe9, 0x58,
+	0x84, 0x6e, 0xf9, 0x3d, 0xdf, 0x25, 0xea, 0xad,
+	0xae, 0xe6, 0x9a, 0xd1, 0x89, 0x55, 0xd3, 0xde,
+	0x6c, 0x52, 0xdb, 0x70, 0xfe, 0x37, 0xce, 0x44,
+	0x0a, 0xa8, 0x25, 0x5f, 0x92, 0xc1, 0x33, 0x4a,
+	0x4f, 0x9b, 0x62, 0x35, 0xff, 0xce, 0xc0, 0xa9,
+	0x60, 0xce, 0x52, 0x00, 0x97, 0x51, 0x35, 0x26,
+	0x2e, 0xb9, 0x36, 0xa9, 0x87, 0x6e, 0x1e, 0xcc,
+	0x91, 0x78, 0x53, 0x98, 0x86, 0x5b, 0x9c, 0x74,
+	0x7d, 0x88, 0x33, 0xe1, 0xdf, 0x37, 0x69, 0x2b,
+	0xbb, 0xf1, 0x4d, 0xf4, 0xd1, 0xf1, 0x39, 0x93,
+	0x17, 0x51, 0x19, 0xe3, 0x19, 0x1e, 0x76, 0x37,
+	0x25, 0xfb, 0x09, 0x27, 0x6a, 0xab, 0x67, 0x6f,
+	0x14, 0x12, 0x64, 0xe7, 0xc4, 0x07, 0xdf, 0x4d,
+	0x17, 0xbb, 0x6d, 0xe0, 0xe9, 0xb9, 0xab, 0xca,
+	0x10, 0x68, 0xaf, 0x7e, 0xb7, 0x33, 0x54, 0x73,
+	0x07, 0x6e, 0xf7, 0x81, 0x97, 0x9c, 0x05, 0x6f,
+	0x84, 0x5f, 0xd2, 0x42, 0xfb, 0x38, 0xcf, 0xd1,
+	0x2f, 0x14, 0x30, 0x88, 0x98, 0x4d, 0x5a, 0xa9,
+	0x76, 0xd5, 0x4f, 0x3e, 0x70, 0x6c, 0x85, 0x76,
+	0xd7, 0x01, 0xa0, 0x1a, 0xc8, 0x4e, 0xaa, 0xac,
+	0x78, 0xfe, 0x46, 0xde, 0x6a, 0x05, 0x46, 0xa7,
+	0x43, 0x0c, 0xb9, 0xde, 0xb9, 0x68, 0xfb, 0xce,
+	0x42, 0x99, 0x07, 0x4d, 0x0b, 0x3b, 0x5a, 0x30,
+	0x35, 0xa8, 0xf9, 0x3a, 0x73, 0xef, 0x0f, 0xdb,
+	0x1e, 0x16, 0x42, 0xc4, 0xba, 0xae, 0x58, 0xaa,
+	0xf8, 0xe5, 0x75, 0x2f, 0x1b, 0x15, 0x5c, 0xfd,
+	0x0a, 0x97, 0xd0, 0xe4, 0x37, 0x83, 0x61, 0x5f,
+	0x43, 0xa6, 0xc7, 0x3f, 0x38, 0x59, 0xe6, 0xeb,
+	0xa3, 0x90, 0xc3, 0xaa, 0xaa, 0x5a, 0xd3, 0x34,
+	0xd4, 0x17, 0xc8, 0x65, 0x3e, 0x57, 0xbc, 0x5e,
+	0xdd, 0x9e, 0xb7, 0xf0, 0x2e, 0x5b, 0xb2, 0x1f,
+	0x8a, 0x08, 0x0d, 0x45, 0x91, 0x0b, 0x29, 0x53,
+	0x4f, 0x4c, 0x5a, 0x73, 0x56, 0xfe, 0xaf, 0x41,
+	0x01, 0x39, 0x0a, 0x24, 0x3c, 0x7e, 0xbe, 0x4e,
+	0x53, 0xf3, 0xeb, 0x06, 0x66, 0x51, 0x28, 0x1d,
+	0xbd, 0x41, 0x0a, 0x01, 0xab, 0x16, 0x47, 0x27,
+	0x47, 0x47, 0xf7, 0xcb, 0x46, 0x0a, 0x70, 0x9e,
+	0x01, 0x9c, 0x09, 0xe1, 0x2a, 0x00, 0x1a, 0xd8,
+	0xd4, 0x79, 0x9d, 0x80, 0x15, 0x8e, 0x53, 0x2a,
+	0x65, 0x83, 0x78, 0x3e, 0x03, 0x00, 0x07, 0x12,
+	0x1f, 0x33, 0x3e, 0x7b, 0x13, 0x37, 0xf1, 0xc3,
+	0xef, 0xb7, 0xc1, 0x20, 0x3c, 0x3e, 0x67, 0x66,
+	0x5d, 0x88, 0xa7, 0x7d, 0x33, 0x50, 0x77, 0xb0,
+	0x28, 0x8e, 0xe7, 0x2c, 0x2e, 0x7a, 0xf4, 0x3c,
+	0x8d, 0x74, 0x83, 0xaf, 0x8e, 0x87, 0x0f, 0xe4,
+	0x50, 0xff, 0x84, 0x5c, 0x47, 0x0c, 0x6a, 0x49,
+	0xbf, 0x42, 0x86, 0x77, 0x15, 0x48, 0xa5, 0x90,
+	0x5d, 0x93, 0xd6, 0x2a, 0x11, 0xd5, 0xd5, 0x11,
+	0xaa, 0xce, 0xe7, 0x6f, 0xa5, 0xb0, 0x09, 0x2c,
+	0x8d, 0xd3, 0x92, 0xf0, 0x5a, 0x2a, 0xda, 0x5b,
+	0x1e, 0xd5, 0x9a, 0xc4, 0xc4, 0xf3, 0x49, 0x74,
+	0x41, 0xca, 0xe8, 0xc1, 0xf8, 0x44, 0xd6, 0x3c,
+	0xae, 0x6c, 0x1d, 0x9a, 0x30, 0x04, 0x4d, 0x27,
+	0x0e, 0xb1, 0x5f, 0x59, 0xa2, 0x24, 0xe8, 0xe1,
+	0x98, 0xc5, 0x6a, 0x4c, 0xfe, 0x41, 0xd2, 0x27,
+	0x42, 0x52, 0xe1, 0xe9, 0x7d, 0x62, 0xe4, 0x88,
+	0x0f, 0xad, 0xb2, 0x70, 0xcb, 0x9d, 0x4c, 0x27,
+	0x2e, 0x76, 0x1e, 0x1a, 0x63, 0x65, 0xf5, 0x3b,
+	0xf8, 0x57, 0x69, 0xeb, 0x5b, 0x38, 0x26, 0x39,
+	0x33, 0x25, 0x45, 0x3e, 0x91, 0xb8, 0xd8, 0xc7,
+	0xd5, 0x42, 0xc0, 0x22, 0x31, 0x74, 0xf4, 0xbc,
+	0x0c, 0x23, 0xf1, 0xca, 0xc1, 0x8d, 0xd7, 0xbe,
+	0xc9, 0x62, 0xe4, 0x08, 0x1a, 0xcf, 0x36, 0xd5,
+	0xfe, 0x55, 0x21, 0x59, 0x91, 0x87, 0x87, 0xdf,
+	0x06, 0xdb, 0xdf, 0x96, 0x45, 0x58, 0xda, 0x05,
+	0xcd, 0x50, 0x4d, 0xd2, 0x7d, 0x05, 0x18, 0x73,
+	0x6a, 0x8d, 0x11, 0x85, 0xa6, 0x88, 0xe8, 0xda,
+	0xe6, 0x30, 0x33, 0xa4, 0x89, 0x31, 0x75, 0xbe,
+	0x69, 0x43, 0x84, 0x43, 0x50, 0x87, 0xdd, 0x71,
+	0x36, 0x83, 0xc3, 0x78, 0x74, 0x24, 0x0a, 0xed,
+	0x7b, 0xdb, 0xa4, 0x24, 0x0b, 0xb9, 0x7e, 0x5d,
+	0xff, 0xde, 0xb1, 0xef, 0x61, 0x5a, 0x45, 0x33,
+	0xf6, 0x17, 0x07, 0x08, 0x98, 0x83, 0x92, 0x0f,
+	0x23, 0x6d, 0xe6, 0xaa, 0x17, 0x54, 0xad, 0x6a,
+	0xc8, 0xdb, 0x26, 0xbe, 0xb8, 0xb6, 0x08, 0xfa,
+	0x68, 0xf1, 0xd7, 0x79, 0x6f, 0x18, 0xb4, 0x9e,
+	0x2d, 0x3f, 0x1b, 0x64, 0xaf, 0x8d, 0x06, 0x0e,
+	0x49, 0x28, 0xe0, 0x5d, 0x45, 0x68, 0x13, 0x87,
+	0xfa, 0xde, 0x40, 0x7b, 0xd2, 0xc3, 0x94, 0xd5,
+	0xe1, 0xd9, 0xc2, 0xaf, 0x55, 0x89, 0xeb, 0xb4,
+	0x12, 0x59, 0xa8, 0xd4, 0xc5, 0x29, 0x66, 0x38,
+	0xe6, 0xac, 0x22, 0x22, 0xd9, 0x64, 0x9b, 0x34,
+	0x0a, 0x32, 0x9f, 0xc2, 0xbf, 0x17, 0x6c, 0x3f,
+	0x71, 0x7a, 0x38, 0x6b, 0x98, 0xfb, 0x49, 0x36,
+	0x89, 0xc9, 0xe2, 0xd6, 0xc7, 0x5d, 0xd0, 0x69,
+	0x5f, 0x23, 0x35, 0xc9, 0x30, 0xe2, 0xfd, 0x44,
+	0x58, 0x39, 0xd7, 0x97, 0xfb, 0x5c, 0x00, 0xd5,
+	0x4f, 0x7a, 0x1a, 0x95, 0x8b, 0x62, 0x4b, 0xce,
+	0xe5, 0x91, 0x21, 0x7b, 0x30, 0x00, 0xd6, 0xdd,
+	0x6d, 0x02, 0x86, 0x49, 0x0f, 0x3c, 0x1a, 0x27,
+	0x3c, 0xd3, 0x0e, 0x71, 0xf2, 0xff, 0xf5, 0x2f,
+	0x87, 0xac, 0x67, 0x59, 0x81, 0xa3, 0xf7, 0xf8,
+	0xd6, 0x11, 0x0c, 0x84, 0xa9, 0x03, 0xee, 0x2a,
+	0xc4, 0xf3, 0x22, 0xab, 0x7c, 0xe2, 0x25, 0xf5,
+	0x67, 0xa3, 0xe4, 0x11, 0xe0, 0x59, 0xb3, 0xca,
+	0x87, 0xa0, 0xae, 0xc9, 0xa6, 0x62, 0x1b, 0x6e,
+	0x4d, 0x02, 0x6b, 0x07, 0x9d, 0xfd, 0xd0, 0x92,
+	0x06, 0xe1, 0xb2, 0x9a, 0x4a, 0x1f, 0x1f, 0x13,
+	0x49, 0x99, 0x97, 0x08, 0xde, 0x7f, 0x98, 0xaf,
+	0x51, 0x98, 0xee, 0x2c, 0xcb, 0xf0, 0x0b, 0xc6,
+	0xb6, 0xb7, 0x2d, 0x9a, 0xb1, 0xac, 0xa6, 0xe3,
+	0x15, 0x77, 0x9d, 0x6b, 0x1a, 0xe4, 0xfc, 0x8b,
+	0xf2, 0x17, 0x59, 0x08, 0x04, 0x58, 0x81, 0x9d,
+	0x1b, 0x1b, 0x69, 0x55, 0xc2, 0xb4, 0x3c, 0x1f,
+	0x50, 0xf1, 0x7f, 0x77, 0x90, 0x4c, 0x66, 0x40,
+	0x5a, 0xc0, 0x33, 0x1f, 0xcb, 0x05, 0x6d, 0x5c,
+	0x06, 0x87, 0x52, 0xa2, 0x8f, 0x26, 0xd5, 0x4f
+};
+static const u8 enc_output010[] __initconst = {
+	0xe5, 0x26, 0xa4, 0x3d, 0xbd, 0x33, 0xd0, 0x4b,
+	0x6f, 0x05, 0xa7, 0x6e, 0x12, 0x7a, 0xd2, 0x74,
+	0xa6, 0xdd, 0xbd, 0x95, 0xeb, 0xf9, 0xa4, 0xf1,
+	0x59, 0x93, 0x91, 0x70, 0xd9, 0xfe, 0x9a, 0xcd,
+	0x53, 0x1f, 0x3a, 0xab, 0xa6, 0x7c, 0x9f, 0xa6,
+	0x9e, 0xbd, 0x99, 0xd9, 0xb5, 0x97, 0x44, 0xd5,
+	0x14, 0x48, 0x4d, 0x9d, 0xc0, 0xd0, 0x05, 0x96,
+	0xeb, 0x4c, 0x78, 0x55, 0x09, 0x08, 0x01, 0x02,
+	0x30, 0x90, 0x7b, 0x96, 0x7a, 0x7b, 0x5f, 0x30,
+	0x41, 0x24, 0xce, 0x68, 0x61, 0x49, 0x86, 0x57,
+	0x82, 0xdd, 0x53, 0x1c, 0x51, 0x28, 0x2b, 0x53,
+	0x6e, 0x2d, 0xc2, 0x20, 0x4c, 0xdd, 0x8f, 0x65,
+	0x10, 0x20, 0x50, 0xdd, 0x9d, 0x50, 0xe5, 0x71,
+	0x40, 0x53, 0x69, 0xfc, 0x77, 0x48, 0x11, 0xb9,
+	0xde, 0xa4, 0x8d, 0x58, 0xe4, 0xa6, 0x1a, 0x18,
+	0x47, 0x81, 0x7e, 0xfc, 0xdd, 0xf6, 0xef, 0xce,
+	0x2f, 0x43, 0x68, 0xd6, 0x06, 0xe2, 0x74, 0x6a,
+	0xad, 0x90, 0xf5, 0x37, 0xf3, 0x3d, 0x82, 0x69,
+	0x40, 0xe9, 0x6b, 0xa7, 0x3d, 0xa8, 0x1e, 0xd2,
+	0x02, 0x7c, 0xb7, 0x9b, 0xe4, 0xda, 0x8f, 0x95,
+	0x06, 0xc5, 0xdf, 0x73, 0xa3, 0x20, 0x9a, 0x49,
+	0xde, 0x9c, 0xbc, 0xee, 0x14, 0x3f, 0x81, 0x5e,
+	0xf8, 0x3b, 0x59, 0x3c, 0xe1, 0x68, 0x12, 0x5a,
+	0x3a, 0x76, 0x3a, 0x3f, 0xf7, 0x87, 0x33, 0x0a,
+	0x01, 0xb8, 0xd4, 0xed, 0xb6, 0xbe, 0x94, 0x5e,
+	0x70, 0x40, 0x56, 0x67, 0x1f, 0x50, 0x44, 0x19,
+	0xce, 0x82, 0x70, 0x10, 0x87, 0x13, 0x20, 0x0b,
+	0x4c, 0x5a, 0xb6, 0xf6, 0xa7, 0xae, 0x81, 0x75,
+	0x01, 0x81, 0xe6, 0x4b, 0x57, 0x7c, 0xdd, 0x6d,
+	0xf8, 0x1c, 0x29, 0x32, 0xf7, 0xda, 0x3c, 0x2d,
+	0xf8, 0x9b, 0x25, 0x6e, 0x00, 0xb4, 0xf7, 0x2f,
+	0xf7, 0x04, 0xf7, 0xa1, 0x56, 0xac, 0x4f, 0x1a,
+	0x64, 0xb8, 0x47, 0x55, 0x18, 0x7b, 0x07, 0x4d,
+	0xbd, 0x47, 0x24, 0x80, 0x5d, 0xa2, 0x70, 0xc5,
+	0xdd, 0x8e, 0x82, 0xd4, 0xeb, 0xec, 0xb2, 0x0c,
+	0x39, 0xd2, 0x97, 0xc1, 0xcb, 0xeb, 0xf4, 0x77,
+	0x59, 0xb4, 0x87, 0xef, 0xcb, 0x43, 0x2d, 0x46,
+	0x54, 0xd1, 0xa7, 0xd7, 0x15, 0x99, 0x0a, 0x43,
+	0xa1, 0xe0, 0x99, 0x33, 0x71, 0xc1, 0xed, 0xfe,
+	0x72, 0x46, 0x33, 0x8e, 0x91, 0x08, 0x9f, 0xc8,
+	0x2e, 0xca, 0xfa, 0xdc, 0x59, 0xd5, 0xc3, 0x76,
+	0x84, 0x9f, 0xa3, 0x37, 0x68, 0xc3, 0xf0, 0x47,
+	0x2c, 0x68, 0xdb, 0x5e, 0xc3, 0x49, 0x4c, 0xe8,
+	0x92, 0x85, 0xe2, 0x23, 0xd3, 0x3f, 0xad, 0x32,
+	0xe5, 0x2b, 0x82, 0xd7, 0x8f, 0x99, 0x0a, 0x59,
+	0x5c, 0x45, 0xd9, 0xb4, 0x51, 0x52, 0xc2, 0xae,
+	0xbf, 0x80, 0xcf, 0xc9, 0xc9, 0x51, 0x24, 0x2a,
+	0x3b, 0x3a, 0x4d, 0xae, 0xeb, 0xbd, 0x22, 0xc3,
+	0x0e, 0x0f, 0x59, 0x25, 0x92, 0x17, 0xe9, 0x74,
+	0xc7, 0x8b, 0x70, 0x70, 0x36, 0x55, 0x95, 0x75,
+	0x4b, 0xad, 0x61, 0x2b, 0x09, 0xbc, 0x82, 0xf2,
+	0x6e, 0x94, 0x43, 0xae, 0xc3, 0xd5, 0xcd, 0x8e,
+	0xfe, 0x5b, 0x9a, 0x88, 0x43, 0x01, 0x75, 0xb2,
+	0x23, 0x09, 0xf7, 0x89, 0x83, 0xe7, 0xfa, 0xf9,
+	0xb4, 0x9b, 0xf8, 0xef, 0xbd, 0x1c, 0x92, 0xc1,
+	0xda, 0x7e, 0xfe, 0x05, 0xba, 0x5a, 0xcd, 0x07,
+	0x6a, 0x78, 0x9e, 0x5d, 0xfb, 0x11, 0x2f, 0x79,
+	0x38, 0xb6, 0xc2, 0x5b, 0x6b, 0x51, 0xb4, 0x71,
+	0xdd, 0xf7, 0x2a, 0xe4, 0xf4, 0x72, 0x76, 0xad,
+	0xc2, 0xdd, 0x64, 0x5d, 0x79, 0xb6, 0xf5, 0x7a,
+	0x77, 0x20, 0x05, 0x3d, 0x30, 0x06, 0xd4, 0x4c,
+	0x0a, 0x2c, 0x98, 0x5a, 0xb9, 0xd4, 0x98, 0xa9,
+	0x3f, 0xc6, 0x12, 0xea, 0x3b, 0x4b, 0xc5, 0x79,
+	0x64, 0x63, 0x6b, 0x09, 0x54, 0x3b, 0x14, 0x27,
+	0xba, 0x99, 0x80, 0xc8, 0x72, 0xa8, 0x12, 0x90,
+	0x29, 0xba, 0x40, 0x54, 0x97, 0x2b, 0x7b, 0xfe,
+	0xeb, 0xcd, 0x01, 0x05, 0x44, 0x72, 0xdb, 0x99,
+	0xe4, 0x61, 0xc9, 0x69, 0xd6, 0xb9, 0x28, 0xd1,
+	0x05, 0x3e, 0xf9, 0x0b, 0x49, 0x0a, 0x49, 0xe9,
+	0x8d, 0x0e, 0xa7, 0x4a, 0x0f, 0xaf, 0x32, 0xd0,
+	0xe0, 0xb2, 0x3a, 0x55, 0x58, 0xfe, 0x5c, 0x28,
+	0x70, 0x51, 0x23, 0xb0, 0x7b, 0x6a, 0x5f, 0x1e,
+	0xb8, 0x17, 0xd7, 0x94, 0x15, 0x8f, 0xee, 0x20,
+	0xc7, 0x42, 0x25, 0x3e, 0x9a, 0x14, 0xd7, 0x60,
+	0x72, 0x39, 0x47, 0x48, 0xa9, 0xfe, 0xdd, 0x47,
+	0x0a, 0xb1, 0xe6, 0x60, 0x28, 0x8c, 0x11, 0x68,
+	0xe1, 0xff, 0xd7, 0xce, 0xc8, 0xbe, 0xb3, 0xfe,
+	0x27, 0x30, 0x09, 0x70, 0xd7, 0xfa, 0x02, 0x33,
+	0x3a, 0x61, 0x2e, 0xc7, 0xff, 0xa4, 0x2a, 0xa8,
+	0x6e, 0xb4, 0x79, 0x35, 0x6d, 0x4c, 0x1e, 0x38,
+	0xf8, 0xee, 0xd4, 0x84, 0x4e, 0x6e, 0x28, 0xa7,
+	0xce, 0xc8, 0xc1, 0xcf, 0x80, 0x05, 0xf3, 0x04,
+	0xef, 0xc8, 0x18, 0x28, 0x2e, 0x8d, 0x5e, 0x0c,
+	0xdf, 0xb8, 0x5f, 0x96, 0xe8, 0xc6, 0x9c, 0x2f,
+	0xe5, 0xa6, 0x44, 0xd7, 0xe7, 0x99, 0x44, 0x0c,
+	0xec, 0xd7, 0x05, 0x60, 0x97, 0xbb, 0x74, 0x77,
+	0x58, 0xd5, 0xbb, 0x48, 0xde, 0x5a, 0xb2, 0x54,
+	0x7f, 0x0e, 0x46, 0x70, 0x6a, 0x6f, 0x78, 0xa5,
+	0x08, 0x89, 0x05, 0x4e, 0x7e, 0xa0, 0x69, 0xb4,
+	0x40, 0x60, 0x55, 0x77, 0x75, 0x9b, 0x19, 0xf2,
+	0xd5, 0x13, 0x80, 0x77, 0xf9, 0x4b, 0x3f, 0x1e,
+	0xee, 0xe6, 0x76, 0x84, 0x7b, 0x8c, 0xe5, 0x27,
+	0xa8, 0x0a, 0x91, 0x01, 0x68, 0x71, 0x8a, 0x3f,
+	0x06, 0xab, 0xf6, 0xa9, 0xa5, 0xe6, 0x72, 0x92,
+	0xe4, 0x67, 0xe2, 0xa2, 0x46, 0x35, 0x84, 0x55,
+	0x7d, 0xca, 0xa8, 0x85, 0xd0, 0xf1, 0x3f, 0xbe,
+	0xd7, 0x34, 0x64, 0xfc, 0xae, 0xe3, 0xe4, 0x04,
+	0x9f, 0x66, 0x02, 0xb9, 0x88, 0x10, 0xd9, 0xc4,
+	0x4c, 0x31, 0x43, 0x7a, 0x93, 0xe2, 0x9b, 0x56,
+	0x43, 0x84, 0xdc, 0xdc, 0xde, 0x1d, 0xa4, 0x02,
+	0x0e, 0xc2, 0xef, 0xc3, 0xf8, 0x78, 0xd1, 0xb2,
+	0x6b, 0x63, 0x18, 0xc9, 0xa9, 0xe5, 0x72, 0xd8,
+	0xf3, 0xb9, 0xd1, 0x8a, 0xc7, 0x1a, 0x02, 0x27,
+	0x20, 0x77, 0x10, 0xe5, 0xc8, 0xd4, 0x4a, 0x47,
+	0xe5, 0xdf, 0x5f, 0x01, 0xaa, 0xb0, 0xd4, 0x10,
+	0xbb, 0x69, 0xe3, 0x36, 0xc8, 0xe1, 0x3d, 0x43,
+	0xfb, 0x86, 0xcd, 0xcc, 0xbf, 0xf4, 0x88, 0xe0,
+	0x20, 0xca, 0xb7, 0x1b, 0xf1, 0x2f, 0x5c, 0xee,
+	0xd4, 0xd3, 0xa3, 0xcc, 0xa4, 0x1e, 0x1c, 0x47,
+	0xfb, 0xbf, 0xfc, 0xa2, 0x41, 0x55, 0x9d, 0xf6,
+	0x5a, 0x5e, 0x65, 0x32, 0x34, 0x7b, 0x52, 0x8d,
+	0xd5, 0xd0, 0x20, 0x60, 0x03, 0xab, 0x3f, 0x8c,
+	0xd4, 0x21, 0xea, 0x2a, 0xd9, 0xc4, 0xd0, 0xd3,
+	0x65, 0xd8, 0x7a, 0x13, 0x28, 0x62, 0x32, 0x4b,
+	0x2c, 0x87, 0x93, 0xa8, 0xb4, 0x52, 0x45, 0x09,
+	0x44, 0xec, 0xec, 0xc3, 0x17, 0xdb, 0x9a, 0x4d,
+	0x5c, 0xa9, 0x11, 0xd4, 0x7d, 0xaf, 0x9e, 0xf1,
+	0x2d, 0xb2, 0x66, 0xc5, 0x1d, 0xed, 0xb7, 0xcd,
+	0x0b, 0x25, 0x5e, 0x30, 0x47, 0x3f, 0x40, 0xf4,
+	0xa1, 0xa0, 0x00, 0x94, 0x10, 0xc5, 0x6a, 0x63,
+	0x1a, 0xd5, 0x88, 0x92, 0x8e, 0x82, 0x39, 0x87,
+	0x3c, 0x78, 0x65, 0x58, 0x42, 0x75, 0x5b, 0xdd,
+	0x77, 0x3e, 0x09, 0x4e, 0x76, 0x5b, 0xe6, 0x0e,
+	0x4d, 0x38, 0xb2, 0xc0, 0xb8, 0x95, 0x01, 0x7a,
+	0x10, 0xe0, 0xfb, 0x07, 0xf2, 0xab, 0x2d, 0x8c,
+	0x32, 0xed, 0x2b, 0xc0, 0x46, 0xc2, 0xf5, 0x38,
+	0x83, 0xf0, 0x17, 0xec, 0xc1, 0x20, 0x6a, 0x9a,
+	0x0b, 0x00, 0xa0, 0x98, 0x22, 0x50, 0x23, 0xd5,
+	0x80, 0x6b, 0xf6, 0x1f, 0xc3, 0xcc, 0x97, 0xc9,
+	0x24, 0x9f, 0xf3, 0xaf, 0x43, 0x14, 0xd5, 0xa0
+};
+static const u8 enc_assoc010[] __initconst = {
+	0xd2, 0xa1, 0x70, 0xdb, 0x7a, 0xf8, 0xfa, 0x27,
+	0xba, 0x73, 0x0f, 0xbf, 0x3d, 0x1e, 0x82, 0xb2
+};
+static const u8 enc_nonce010[] __initconst = {
+	0xdb, 0x92, 0x0f, 0x7f, 0x17, 0x54, 0x0c, 0x30
+};
+static const u8 enc_key010[] __initconst = {
+	0x47, 0x11, 0xeb, 0x86, 0x2b, 0x2c, 0xab, 0x44,
+	0x34, 0xda, 0x7f, 0x57, 0x03, 0x39, 0x0c, 0xaf,
+	0x2c, 0x14, 0xfd, 0x65, 0x23, 0xe9, 0x8e, 0x74,
+	0xd5, 0x08, 0x68, 0x08, 0xe7, 0xb4, 0x72, 0xd7
+};
+
+static const u8 enc_input011[] __initconst = {
+	0x7a, 0x57, 0xf2, 0xc7, 0x06, 0x3f, 0x50, 0x7b,
+	0x36, 0x1a, 0x66, 0x5c, 0xb9, 0x0e, 0x5e, 0x3b,
+	0x45, 0x60, 0xbe, 0x9a, 0x31, 0x9f, 0xff, 0x5d,
+	0x66, 0x34, 0xb4, 0xdc, 0xfb, 0x9d, 0x8e, 0xee,
+	0x6a, 0x33, 0xa4, 0x07, 0x3c, 0xf9, 0x4c, 0x30,
+	0xa1, 0x24, 0x52, 0xf9, 0x50, 0x46, 0x88, 0x20,
+	0x02, 0x32, 0x3a, 0x0e, 0x99, 0x63, 0xaf, 0x1f,
+	0x15, 0x28, 0x2a, 0x05, 0xff, 0x57, 0x59, 0x5e,
+	0x18, 0xa1, 0x1f, 0xd0, 0x92, 0x5c, 0x88, 0x66,
+	0x1b, 0x00, 0x64, 0xa5, 0x93, 0x8d, 0x06, 0x46,
+	0xb0, 0x64, 0x8b, 0x8b, 0xef, 0x99, 0x05, 0x35,
+	0x85, 0xb3, 0xf3, 0x33, 0xbb, 0xec, 0x66, 0xb6,
+	0x3d, 0x57, 0x42, 0xe3, 0xb4, 0xc6, 0xaa, 0xb0,
+	0x41, 0x2a, 0xb9, 0x59, 0xa9, 0xf6, 0x3e, 0x15,
+	0x26, 0x12, 0x03, 0x21, 0x4c, 0x74, 0x43, 0x13,
+	0x2a, 0x03, 0x27, 0x09, 0xb4, 0xfb, 0xe7, 0xb7,
+	0x40, 0xff, 0x5e, 0xce, 0x48, 0x9a, 0x60, 0xe3,
+	0x8b, 0x80, 0x8c, 0x38, 0x2d, 0xcb, 0x93, 0x37,
+	0x74, 0x05, 0x52, 0x6f, 0x73, 0x3e, 0xc3, 0xbc,
+	0xca, 0x72, 0x0a, 0xeb, 0xf1, 0x3b, 0xa0, 0x95,
+	0xdc, 0x8a, 0xc4, 0xa9, 0xdc, 0xca, 0x44, 0xd8,
+	0x08, 0x63, 0x6a, 0x36, 0xd3, 0x3c, 0xb8, 0xac,
+	0x46, 0x7d, 0xfd, 0xaa, 0xeb, 0x3e, 0x0f, 0x45,
+	0x8f, 0x49, 0xda, 0x2b, 0xf2, 0x12, 0xbd, 0xaf,
+	0x67, 0x8a, 0x63, 0x48, 0x4b, 0x55, 0x5f, 0x6d,
+	0x8c, 0xb9, 0x76, 0x34, 0x84, 0xae, 0xc2, 0xfc,
+	0x52, 0x64, 0x82, 0xf7, 0xb0, 0x06, 0xf0, 0x45,
+	0x73, 0x12, 0x50, 0x30, 0x72, 0xea, 0x78, 0x9a,
+	0xa8, 0xaf, 0xb5, 0xe3, 0xbb, 0x77, 0x52, 0xec,
+	0x59, 0x84, 0xbf, 0x6b, 0x8f, 0xce, 0x86, 0x5e,
+	0x1f, 0x23, 0xe9, 0xfb, 0x08, 0x86, 0xf7, 0x10,
+	0xb9, 0xf2, 0x44, 0x96, 0x44, 0x63, 0xa9, 0xa8,
+	0x78, 0x00, 0x23, 0xd6, 0xc7, 0xe7, 0x6e, 0x66,
+	0x4f, 0xcc, 0xee, 0x15, 0xb3, 0xbd, 0x1d, 0xa0,
+	0xe5, 0x9c, 0x1b, 0x24, 0x2c, 0x4d, 0x3c, 0x62,
+	0x35, 0x9c, 0x88, 0x59, 0x09, 0xdd, 0x82, 0x1b,
+	0xcf, 0x0a, 0x83, 0x6b, 0x3f, 0xae, 0x03, 0xc4,
+	0xb4, 0xdd, 0x7e, 0x5b, 0x28, 0x76, 0x25, 0x96,
+	0xd9, 0xc9, 0x9d, 0x5f, 0x86, 0xfa, 0xf6, 0xd7,
+	0xd2, 0xe6, 0x76, 0x1d, 0x0f, 0xa1, 0xdc, 0x74,
+	0x05, 0x1b, 0x1d, 0xe0, 0xcd, 0x16, 0xb0, 0xa8,
+	0x8a, 0x34, 0x7b, 0x15, 0x11, 0x77, 0xe5, 0x7b,
+	0x7e, 0x20, 0xf7, 0xda, 0x38, 0xda, 0xce, 0x70,
+	0xe9, 0xf5, 0x6c, 0xd9, 0xbe, 0x0c, 0x4c, 0x95,
+	0x4c, 0xc2, 0x9b, 0x34, 0x55, 0x55, 0xe1, 0xf3,
+	0x46, 0x8e, 0x48, 0x74, 0x14, 0x4f, 0x9d, 0xc9,
+	0xf5, 0xe8, 0x1a, 0xf0, 0x11, 0x4a, 0xc1, 0x8d,
+	0xe0, 0x93, 0xa0, 0xbe, 0x09, 0x1c, 0x2b, 0x4e,
+	0x0f, 0xb2, 0x87, 0x8b, 0x84, 0xfe, 0x92, 0x32,
+	0x14, 0xd7, 0x93, 0xdf, 0xe7, 0x44, 0xbc, 0xc5,
+	0xae, 0x53, 0x69, 0xd8, 0xb3, 0x79, 0x37, 0x80,
+	0xe3, 0x17, 0x5c, 0xec, 0x53, 0x00, 0x9a, 0xe3,
+	0x8e, 0xdc, 0x38, 0xb8, 0x66, 0xf0, 0xd3, 0xad,
+	0x1d, 0x02, 0x96, 0x86, 0x3e, 0x9d, 0x3b, 0x5d,
+	0xa5, 0x7f, 0x21, 0x10, 0xf1, 0x1f, 0x13, 0x20,
+	0xf9, 0x57, 0x87, 0x20, 0xf5, 0x5f, 0xf1, 0x17,
+	0x48, 0x0a, 0x51, 0x5a, 0xcd, 0x19, 0x03, 0xa6,
+	0x5a, 0xd1, 0x12, 0x97, 0xe9, 0x48, 0xe2, 0x1d,
+	0x83, 0x75, 0x50, 0xd9, 0x75, 0x7d, 0x6a, 0x82,
+	0xa1, 0xf9, 0x4e, 0x54, 0x87, 0x89, 0xc9, 0x0c,
+	0xb7, 0x5b, 0x6a, 0x91, 0xc1, 0x9c, 0xb2, 0xa9,
+	0xdc, 0x9a, 0xa4, 0x49, 0x0a, 0x6d, 0x0d, 0xbb,
+	0xde, 0x86, 0x44, 0xdd, 0x5d, 0x89, 0x2b, 0x96,
+	0x0f, 0x23, 0x95, 0xad, 0xcc, 0xa2, 0xb3, 0xb9,
+	0x7e, 0x74, 0x38, 0xba, 0x9f, 0x73, 0xae, 0x5f,
+	0xf8, 0x68, 0xa2, 0xe0, 0xa9, 0xce, 0xbd, 0x40,
+	0xd4, 0x4c, 0x6b, 0xd2, 0x56, 0x62, 0xb0, 0xcc,
+	0x63, 0x7e, 0x5b, 0xd3, 0xae, 0xd1, 0x75, 0xce,
+	0xbb, 0xb4, 0x5b, 0xa8, 0xf8, 0xb4, 0xac, 0x71,
+	0x75, 0xaa, 0xc9, 0x9f, 0xbb, 0x6c, 0xad, 0x0f,
+	0x55, 0x5d, 0xe8, 0x85, 0x7d, 0xf9, 0x21, 0x35,
+	0xea, 0x92, 0x85, 0x2b, 0x00, 0xec, 0x84, 0x90,
+	0x0a, 0x63, 0x96, 0xe4, 0x6b, 0xa9, 0x77, 0xb8,
+	0x91, 0xf8, 0x46, 0x15, 0x72, 0x63, 0x70, 0x01,
+	0x40, 0xa3, 0xa5, 0x76, 0x62, 0x2b, 0xbf, 0xf1,
+	0xe5, 0x8d, 0x9f, 0xa3, 0xfa, 0x9b, 0x03, 0xbe,
+	0xfe, 0x65, 0x6f, 0xa2, 0x29, 0x0d, 0x54, 0xb4,
+	0x71, 0xce, 0xa9, 0xd6, 0x3d, 0x88, 0xf9, 0xaf,
+	0x6b, 0xa8, 0x9e, 0xf4, 0x16, 0x96, 0x36, 0xb9,
+	0x00, 0xdc, 0x10, 0xab, 0xb5, 0x08, 0x31, 0x1f,
+	0x00, 0xb1, 0x3c, 0xd9, 0x38, 0x3e, 0xc6, 0x04,
+	0xa7, 0x4e, 0xe8, 0xae, 0xed, 0x98, 0xc2, 0xf7,
+	0xb9, 0x00, 0x5f, 0x8c, 0x60, 0xd1, 0xe5, 0x15,
+	0xf7, 0xae, 0x1e, 0x84, 0x88, 0xd1, 0xf6, 0xbc,
+	0x3a, 0x89, 0x35, 0x22, 0x83, 0x7c, 0xca, 0xf0,
+	0x33, 0x82, 0x4c, 0x79, 0x3c, 0xfd, 0xb1, 0xae,
+	0x52, 0x62, 0x55, 0xd2, 0x41, 0x60, 0xc6, 0xbb,
+	0xfa, 0x0e, 0x59, 0xd6, 0xa8, 0xfe, 0x5d, 0xed,
+	0x47, 0x3d, 0xe0, 0xea, 0x1f, 0x6e, 0x43, 0x51,
+	0xec, 0x10, 0x52, 0x56, 0x77, 0x42, 0x6b, 0x52,
+	0x87, 0xd8, 0xec, 0xe0, 0xaa, 0x76, 0xa5, 0x84,
+	0x2a, 0x22, 0x24, 0xfd, 0x92, 0x40, 0x88, 0xd5,
+	0x85, 0x1c, 0x1f, 0x6b, 0x47, 0xa0, 0xc4, 0xe4,
+	0xef, 0xf4, 0xea, 0xd7, 0x59, 0xac, 0x2a, 0x9e,
+	0x8c, 0xfa, 0x1f, 0x42, 0x08, 0xfe, 0x4f, 0x74,
+	0xa0, 0x26, 0xf5, 0xb3, 0x84, 0xf6, 0x58, 0x5f,
+	0x26, 0x66, 0x3e, 0xd7, 0xe4, 0x22, 0x91, 0x13,
+	0xc8, 0xac, 0x25, 0x96, 0x23, 0xd8, 0x09, 0xea,
+	0x45, 0x75, 0x23, 0xb8, 0x5f, 0xc2, 0x90, 0x8b,
+	0x09, 0xc4, 0xfc, 0x47, 0x6c, 0x6d, 0x0a, 0xef,
+	0x69, 0xa4, 0x38, 0x19, 0xcf, 0x7d, 0xf9, 0x09,
+	0x73, 0x9b, 0x60, 0x5a, 0xf7, 0x37, 0xb5, 0xfe,
+	0x9f, 0xe3, 0x2b, 0x4c, 0x0d, 0x6e, 0x19, 0xf1,
+	0xd6, 0xc0, 0x70, 0xf3, 0x9d, 0x22, 0x3c, 0xf9,
+	0x49, 0xce, 0x30, 0x8e, 0x44, 0xb5, 0x76, 0x15,
+	0x8f, 0x52, 0xfd, 0xa5, 0x04, 0xb8, 0x55, 0x6a,
+	0x36, 0x59, 0x7c, 0xc4, 0x48, 0xb8, 0xd7, 0xab,
+	0x05, 0x66, 0xe9, 0x5e, 0x21, 0x6f, 0x6b, 0x36,
+	0x29, 0xbb, 0xe9, 0xe3, 0xa2, 0x9a, 0xa8, 0xcd,
+	0x55, 0x25, 0x11, 0xba, 0x5a, 0x58, 0xa0, 0xde,
+	0xae, 0x19, 0x2a, 0x48, 0x5a, 0xff, 0x36, 0xcd,
+	0x6d, 0x16, 0x7a, 0x73, 0x38, 0x46, 0xe5, 0x47,
+	0x59, 0xc8, 0xa2, 0xf6, 0xe2, 0x6c, 0x83, 0xc5,
+	0x36, 0x2c, 0x83, 0x7d, 0xb4, 0x01, 0x05, 0x69,
+	0xe7, 0xaf, 0x5c, 0xc4, 0x64, 0x82, 0x12, 0x21,
+	0xef, 0xf7, 0xd1, 0x7d, 0xb8, 0x8d, 0x8c, 0x98,
+	0x7c, 0x5f, 0x7d, 0x92, 0x88, 0xb9, 0x94, 0x07,
+	0x9c, 0xd8, 0xe9, 0x9c, 0x17, 0x38, 0xe3, 0x57,
+	0x6c, 0xe0, 0xdc, 0xa5, 0x92, 0x42, 0xb3, 0xbd,
+	0x50, 0xa2, 0x7e, 0xb5, 0xb1, 0x52, 0x72, 0x03,
+	0x97, 0xd8, 0xaa, 0x9a, 0x1e, 0x75, 0x41, 0x11,
+	0xa3, 0x4f, 0xcc, 0xd4, 0xe3, 0x73, 0xad, 0x96,
+	0xdc, 0x47, 0x41, 0x9f, 0xb0, 0xbe, 0x79, 0x91,
+	0xf5, 0xb6, 0x18, 0xfe, 0xc2, 0x83, 0x18, 0x7d,
+	0x73, 0xd9, 0x4f, 0x83, 0x84, 0x03, 0xb3, 0xf0,
+	0x77, 0x66, 0x3d, 0x83, 0x63, 0x2e, 0x2c, 0xf9,
+	0xdd, 0xa6, 0x1f, 0x89, 0x82, 0xb8, 0x23, 0x42,
+	0xeb, 0xe2, 0xca, 0x70, 0x82, 0x61, 0x41, 0x0a,
+	0x6d, 0x5f, 0x75, 0xc5, 0xe2, 0xc4, 0x91, 0x18,
+	0x44, 0x22, 0xfa, 0x34, 0x10, 0xf5, 0x20, 0xdc,
+	0xb7, 0xdd, 0x2a, 0x20, 0x77, 0xf5, 0xf9, 0xce,
+	0xdb, 0xa0, 0x0a, 0x52, 0x2a, 0x4e, 0xdd, 0xcc,
+	0x97, 0xdf, 0x05, 0xe4, 0x5e, 0xb7, 0xaa, 0xf0,
+	0xe2, 0x80, 0xff, 0xba, 0x1a, 0x0f, 0xac, 0xdf,
+	0x02, 0x32, 0xe6, 0xf7, 0xc7, 0x17, 0x13, 0xb7,
+	0xfc, 0x98, 0x48, 0x8c, 0x0d, 0x82, 0xc9, 0x80,
+	0x7a, 0xe2, 0x0a, 0xc5, 0xb4, 0xde, 0x7c, 0x3c,
+	0x79, 0x81, 0x0e, 0x28, 0x65, 0x79, 0x67, 0x82,
+	0x69, 0x44, 0x66, 0x09, 0xf7, 0x16, 0x1a, 0xf9,
+	0x7d, 0x80, 0xa1, 0x79, 0x14, 0xa9, 0xc8, 0x20,
+	0xfb, 0xa2, 0x46, 0xbe, 0x08, 0x35, 0x17, 0x58,
+	0xc1, 0x1a, 0xda, 0x2a, 0x6b, 0x2e, 0x1e, 0xe6,
+	0x27, 0x55, 0x7b, 0x19, 0xe2, 0xfb, 0x64, 0xfc,
+	0x5e, 0x15, 0x54, 0x3c, 0xe7, 0xc2, 0x11, 0x50,
+	0x30, 0xb8, 0x72, 0x03, 0x0b, 0x1a, 0x9f, 0x86,
+	0x27, 0x11, 0x5c, 0x06, 0x2b, 0xbd, 0x75, 0x1a,
+	0x0a, 0xda, 0x01, 0xfa, 0x5c, 0x4a, 0xc1, 0x80,
+	0x3a, 0x6e, 0x30, 0xc8, 0x2c, 0xeb, 0x56, 0xec,
+	0x89, 0xfa, 0x35, 0x7b, 0xb2, 0xf0, 0x97, 0x08,
+	0x86, 0x53, 0xbe, 0xbd, 0x40, 0x41, 0x38, 0x1c,
+	0xb4, 0x8b, 0x79, 0x2e, 0x18, 0x96, 0x94, 0xde,
+	0xe8, 0xca, 0xe5, 0x9f, 0x92, 0x9f, 0x15, 0x5d,
+	0x56, 0x60, 0x5c, 0x09, 0xf9, 0x16, 0xf4, 0x17,
+	0x0f, 0xf6, 0x4c, 0xda, 0xe6, 0x67, 0x89, 0x9f,
+	0xca, 0x6c, 0xe7, 0x9b, 0x04, 0x62, 0x0e, 0x26,
+	0xa6, 0x52, 0xbd, 0x29, 0xff, 0xc7, 0xa4, 0x96,
+	0xe6, 0x6a, 0x02, 0xa5, 0x2e, 0x7b, 0xfe, 0x97,
+	0x68, 0x3e, 0x2e, 0x5f, 0x3b, 0x0f, 0x36, 0xd6,
+	0x98, 0x19, 0x59, 0x48, 0xd2, 0xc6, 0xe1, 0x55,
+	0x1a, 0x6e, 0xd6, 0xed, 0x2c, 0xba, 0xc3, 0x9e,
+	0x64, 0xc9, 0x95, 0x86, 0x35, 0x5e, 0x3e, 0x88,
+	0x69, 0x99, 0x4b, 0xee, 0xbe, 0x9a, 0x99, 0xb5,
+	0x6e, 0x58, 0xae, 0xdd, 0x22, 0xdb, 0xdd, 0x6b,
+	0xfc, 0xaf, 0x90, 0xa3, 0x3d, 0xa4, 0xc1, 0x15,
+	0x92, 0x18, 0x8d, 0xd2, 0x4b, 0x7b, 0x06, 0xd1,
+	0x37, 0xb5, 0xe2, 0x7c, 0x2c, 0xf0, 0x25, 0xe4,
+	0x94, 0x2a, 0xbd, 0xe3, 0x82, 0x70, 0x78, 0xa3,
+	0x82, 0x10, 0x5a, 0x90, 0xd7, 0xa4, 0xfa, 0xaf,
+	0x1a, 0x88, 0x59, 0xdc, 0x74, 0x12, 0xb4, 0x8e,
+	0xd7, 0x19, 0x46, 0xf4, 0x84, 0x69, 0x9f, 0xbb,
+	0x70, 0xa8, 0x4c, 0x52, 0x81, 0xa9, 0xff, 0x76,
+	0x1c, 0xae, 0xd8, 0x11, 0x3d, 0x7f, 0x7d, 0xc5,
+	0x12, 0x59, 0x28, 0x18, 0xc2, 0xa2, 0xb7, 0x1c,
+	0x88, 0xf8, 0xd6, 0x1b, 0xa6, 0x7d, 0x9e, 0xde,
+	0x29, 0xf8, 0xed, 0xff, 0xeb, 0x92, 0x24, 0x4f,
+	0x05, 0xaa, 0xd9, 0x49, 0xba, 0x87, 0x59, 0x51,
+	0xc9, 0x20, 0x5c, 0x9b, 0x74, 0xcf, 0x03, 0xd9,
+	0x2d, 0x34, 0xc7, 0x5b, 0xa5, 0x40, 0xb2, 0x99,
+	0xf5, 0xcb, 0xb4, 0xf6, 0xb7, 0x72, 0x4a, 0xd6,
+	0xbd, 0xb0, 0xf3, 0x93, 0xe0, 0x1b, 0xa8, 0x04,
+	0x1e, 0x35, 0xd4, 0x80, 0x20, 0xf4, 0x9c, 0x31,
+	0x6b, 0x45, 0xb9, 0x15, 0xb0, 0x5e, 0xdd, 0x0a,
+	0x33, 0x9c, 0x83, 0xcd, 0x58, 0x89, 0x50, 0x56,
+	0xbb, 0x81, 0x00, 0x91, 0x32, 0xf3, 0x1b, 0x3e,
+	0xcf, 0x45, 0xe1, 0xf9, 0xe1, 0x2c, 0x26, 0x78,
+	0x93, 0x9a, 0x60, 0x46, 0xc9, 0xb5, 0x5e, 0x6a,
+	0x28, 0x92, 0x87, 0x3f, 0x63, 0x7b, 0xdb, 0xf7,
+	0xd0, 0x13, 0x9d, 0x32, 0x40, 0x5e, 0xcf, 0xfb,
+	0x79, 0x68, 0x47, 0x4c, 0xfd, 0x01, 0x17, 0xe6,
+	0x97, 0x93, 0x78, 0xbb, 0xa6, 0x27, 0xa3, 0xe8,
+	0x1a, 0xe8, 0x94, 0x55, 0x7d, 0x08, 0xe5, 0xdc,
+	0x66, 0xa3, 0x69, 0xc8, 0xca, 0xc5, 0xa1, 0x84,
+	0x55, 0xde, 0x08, 0x91, 0x16, 0x3a, 0x0c, 0x86,
+	0xab, 0x27, 0x2b, 0x64, 0x34, 0x02, 0x6c, 0x76,
+	0x8b, 0xc6, 0xaf, 0xcc, 0xe1, 0xd6, 0x8c, 0x2a,
+	0x18, 0x3d, 0xa6, 0x1b, 0x37, 0x75, 0x45, 0x73,
+	0xc2, 0x75, 0xd7, 0x53, 0x78, 0x3a, 0xd6, 0xe8,
+	0x29, 0xd2, 0x4a, 0xa8, 0x1e, 0x82, 0xf6, 0xb6,
+	0x81, 0xde, 0x21, 0xed, 0x2b, 0x56, 0xbb, 0xf2,
+	0xd0, 0x57, 0xc1, 0x7c, 0xd2, 0x6a, 0xd2, 0x56,
+	0xf5, 0x13, 0x5f, 0x1c, 0x6a, 0x0b, 0x74, 0xfb,
+	0xe9, 0xfe, 0x9e, 0xea, 0x95, 0xb2, 0x46, 0xab,
+	0x0a, 0xfc, 0xfd, 0xf3, 0xbb, 0x04, 0x2b, 0x76,
+	0x1b, 0xa4, 0x74, 0xb0, 0xc1, 0x78, 0xc3, 0x69,
+	0xe2, 0xb0, 0x01, 0xe1, 0xde, 0x32, 0x4c, 0x8d,
+	0x1a, 0xb3, 0x38, 0x08, 0xd5, 0xfc, 0x1f, 0xdc,
+	0x0e, 0x2c, 0x9c, 0xb1, 0xa1, 0x63, 0x17, 0x22,
+	0xf5, 0x6c, 0x93, 0x70, 0x74, 0x00, 0xf8, 0x39,
+	0x01, 0x94, 0xd1, 0x32, 0x23, 0x56, 0x5d, 0xa6,
+	0x02, 0x76, 0x76, 0x93, 0xce, 0x2f, 0x19, 0xe9,
+	0x17, 0x52, 0xae, 0x6e, 0x2c, 0x6d, 0x61, 0x7f,
+	0x3b, 0xaa, 0xe0, 0x52, 0x85, 0xc5, 0x65, 0xc1,
+	0xbb, 0x8e, 0x5b, 0x21, 0xd5, 0xc9, 0x78, 0x83,
+	0x07, 0x97, 0x4c, 0x62, 0x61, 0x41, 0xd4, 0xfc,
+	0xc9, 0x39, 0xe3, 0x9b, 0xd0, 0xcc, 0x75, 0xc4,
+	0x97, 0xe6, 0xdd, 0x2a, 0x5f, 0xa6, 0xe8, 0x59,
+	0x6c, 0x98, 0xb9, 0x02, 0xe2, 0xa2, 0xd6, 0x68,
+	0xee, 0x3b, 0x1d, 0xe3, 0x4d, 0x5b, 0x30, 0xef,
+	0x03, 0xf2, 0xeb, 0x18, 0x57, 0x36, 0xe8, 0xa1,
+	0xf4, 0x47, 0xfb, 0xcb, 0x8f, 0xcb, 0xc8, 0xf3,
+	0x4f, 0x74, 0x9d, 0x9d, 0xb1, 0x8d, 0x14, 0x44,
+	0xd9, 0x19, 0xb4, 0x54, 0x4f, 0x75, 0x19, 0x09,
+	0xa0, 0x75, 0xbc, 0x3b, 0x82, 0xc6, 0x3f, 0xb8,
+	0x83, 0x19, 0x6e, 0xd6, 0x37, 0xfe, 0x6e, 0x8a,
+	0x4e, 0xe0, 0x4a, 0xab, 0x7b, 0xc8, 0xb4, 0x1d,
+	0xf4, 0xed, 0x27, 0x03, 0x65, 0xa2, 0xa1, 0xae,
+	0x11, 0xe7, 0x98, 0x78, 0x48, 0x91, 0xd2, 0xd2,
+	0xd4, 0x23, 0x78, 0x50, 0xb1, 0x5b, 0x85, 0x10,
+	0x8d, 0xca, 0x5f, 0x0f, 0x71, 0xae, 0x72, 0x9a,
+	0xf6, 0x25, 0x19, 0x60, 0x06, 0xf7, 0x10, 0x34,
+	0x18, 0x0d, 0xc9, 0x9f, 0x7b, 0x0c, 0x9b, 0x8f,
+	0x91, 0x1b, 0x9f, 0xcd, 0x10, 0xee, 0x75, 0xf9,
+	0x97, 0x66, 0xfc, 0x4d, 0x33, 0x6e, 0x28, 0x2b,
+	0x92, 0x85, 0x4f, 0xab, 0x43, 0x8d, 0x8f, 0x7d,
+	0x86, 0xa7, 0xc7, 0xd8, 0xd3, 0x0b, 0x8b, 0x57,
+	0xb6, 0x1d, 0x95, 0x0d, 0xe9, 0xbc, 0xd9, 0x03,
+	0xd9, 0x10, 0x19, 0xc3, 0x46, 0x63, 0x55, 0x87,
+	0x61, 0x79, 0x6c, 0x95, 0x0e, 0x9c, 0xdd, 0xca,
+	0xc3, 0xf3, 0x64, 0xf0, 0x7d, 0x76, 0xb7, 0x53,
+	0x67, 0x2b, 0x1e, 0x44, 0x56, 0x81, 0xea, 0x8f,
+	0x5c, 0x42, 0x16, 0xb8, 0x28, 0xeb, 0x1b, 0x61,
+	0x10, 0x1e, 0xbf, 0xec, 0xa8
+};
+static const u8 enc_output011[] __initconst = {
+	0x6a, 0xfc, 0x4b, 0x25, 0xdf, 0xc0, 0xe4, 0xe8,
+	0x17, 0x4d, 0x4c, 0xc9, 0x7e, 0xde, 0x3a, 0xcc,
+	0x3c, 0xba, 0x6a, 0x77, 0x47, 0xdb, 0xe3, 0x74,
+	0x7a, 0x4d, 0x5f, 0x8d, 0x37, 0x55, 0x80, 0x73,
+	0x90, 0x66, 0x5d, 0x3a, 0x7d, 0x5d, 0x86, 0x5e,
+	0x8d, 0xfd, 0x83, 0xff, 0x4e, 0x74, 0x6f, 0xf9,
+	0xe6, 0x70, 0x17, 0x70, 0x3e, 0x96, 0xa7, 0x7e,
+	0xcb, 0xab, 0x8f, 0x58, 0x24, 0x9b, 0x01, 0xfd,
+	0xcb, 0xe6, 0x4d, 0x9b, 0xf0, 0x88, 0x94, 0x57,
+	0x66, 0xef, 0x72, 0x4c, 0x42, 0x6e, 0x16, 0x19,
+	0x15, 0xea, 0x70, 0x5b, 0xac, 0x13, 0xdb, 0x9f,
+	0x18, 0xe2, 0x3c, 0x26, 0x97, 0xbc, 0xdc, 0x45,
+	0x8c, 0x6c, 0x24, 0x69, 0x9c, 0xf7, 0x65, 0x1e,
+	0x18, 0x59, 0x31, 0x7c, 0xe4, 0x73, 0xbc, 0x39,
+	0x62, 0xc6, 0x5c, 0x9f, 0xbf, 0xfa, 0x90, 0x03,
+	0xc9, 0x72, 0x26, 0xb6, 0x1b, 0xc2, 0xb7, 0x3f,
+	0xf2, 0x13, 0x77, 0xf2, 0x8d, 0xb9, 0x47, 0xd0,
+	0x53, 0xdd, 0xc8, 0x91, 0x83, 0x8b, 0xb1, 0xce,
+	0xa3, 0xfe, 0xcd, 0xd9, 0xdd, 0x92, 0x7b, 0xdb,
+	0xb8, 0xfb, 0xc9, 0x2d, 0x01, 0x59, 0x39, 0x52,
+	0xad, 0x1b, 0xec, 0xcf, 0xd7, 0x70, 0x13, 0x21,
+	0xf5, 0x47, 0xaa, 0x18, 0x21, 0x5c, 0xc9, 0x9a,
+	0xd2, 0x6b, 0x05, 0x9c, 0x01, 0xa1, 0xda, 0x35,
+	0x5d, 0xb3, 0x70, 0xe6, 0xa9, 0x80, 0x8b, 0x91,
+	0xb7, 0xb3, 0x5f, 0x24, 0x9a, 0xb7, 0xd1, 0x6b,
+	0xa1, 0x1c, 0x50, 0xba, 0x49, 0xe0, 0xee, 0x2e,
+	0x75, 0xac, 0x69, 0xc0, 0xeb, 0x03, 0xdd, 0x19,
+	0xe5, 0xf6, 0x06, 0xdd, 0xc3, 0xd7, 0x2b, 0x07,
+	0x07, 0x30, 0xa7, 0x19, 0x0c, 0xbf, 0xe6, 0x18,
+	0xcc, 0xb1, 0x01, 0x11, 0x85, 0x77, 0x1d, 0x96,
+	0xa7, 0xa3, 0x00, 0x84, 0x02, 0xa2, 0x83, 0x68,
+	0xda, 0x17, 0x27, 0xc8, 0x7f, 0x23, 0xb7, 0xf4,
+	0x13, 0x85, 0xcf, 0xdd, 0x7a, 0x7d, 0x24, 0x57,
+	0xfe, 0x05, 0x93, 0xf5, 0x74, 0xce, 0xed, 0x0c,
+	0x20, 0x98, 0x8d, 0x92, 0x30, 0xa1, 0x29, 0x23,
+	0x1a, 0xa0, 0x4f, 0x69, 0x56, 0x4c, 0xe1, 0xc8,
+	0xce, 0xf6, 0x9a, 0x0c, 0xa4, 0xfa, 0x04, 0xf6,
+	0x62, 0x95, 0xf2, 0xfa, 0xc7, 0x40, 0x68, 0x40,
+	0x8f, 0x41, 0xda, 0xb4, 0x26, 0x6f, 0x70, 0xab,
+	0x40, 0x61, 0xa4, 0x0e, 0x75, 0xfb, 0x86, 0xeb,
+	0x9d, 0x9a, 0x1f, 0xec, 0x76, 0x99, 0xe7, 0xea,
+	0xaa, 0x1e, 0x2d, 0xb5, 0xd4, 0xa6, 0x1a, 0xb8,
+	0x61, 0x0a, 0x1d, 0x16, 0x5b, 0x98, 0xc2, 0x31,
+	0x40, 0xe7, 0x23, 0x1d, 0x66, 0x99, 0xc8, 0xc0,
+	0xd7, 0xce, 0xf3, 0x57, 0x40, 0x04, 0x3f, 0xfc,
+	0xea, 0xb3, 0xfc, 0xd2, 0xd3, 0x99, 0xa4, 0x94,
+	0x69, 0xa0, 0xef, 0xd1, 0x85, 0xb3, 0xa6, 0xb1,
+	0x28, 0xbf, 0x94, 0x67, 0x22, 0xc3, 0x36, 0x46,
+	0xf8, 0xd2, 0x0f, 0x5f, 0xf4, 0x59, 0x80, 0xe6,
+	0x2d, 0x43, 0x08, 0x7d, 0x19, 0x09, 0x97, 0xa7,
+	0x4c, 0x3d, 0x8d, 0xba, 0x65, 0x62, 0xa3, 0x71,
+	0x33, 0x29, 0x62, 0xdb, 0xc1, 0x33, 0x34, 0x1a,
+	0x63, 0x33, 0x16, 0xb6, 0x64, 0x7e, 0xab, 0x33,
+	0xf0, 0xe6, 0x26, 0x68, 0xba, 0x1d, 0x2e, 0x38,
+	0x08, 0xe6, 0x02, 0xd3, 0x25, 0x2c, 0x47, 0x23,
+	0x58, 0x34, 0x0f, 0x9d, 0x63, 0x4f, 0x63, 0xbb,
+	0x7f, 0x3b, 0x34, 0x38, 0xa7, 0xb5, 0x8d, 0x65,
+	0xd9, 0x9f, 0x79, 0x55, 0x3e, 0x4d, 0xe7, 0x73,
+	0xd8, 0xf6, 0x98, 0x97, 0x84, 0x60, 0x9c, 0xc8,
+	0xa9, 0x3c, 0xf6, 0xdc, 0x12, 0x5c, 0xe1, 0xbb,
+	0x0b, 0x8b, 0x98, 0x9c, 0x9d, 0x26, 0x7c, 0x4a,
+	0xe6, 0x46, 0x36, 0x58, 0x21, 0x4a, 0xee, 0xca,
+	0xd7, 0x3b, 0xc2, 0x6c, 0x49, 0x2f, 0xe5, 0xd5,
+	0x03, 0x59, 0x84, 0x53, 0xcb, 0xfe, 0x92, 0x71,
+	0x2e, 0x7c, 0x21, 0xcc, 0x99, 0x85, 0x7f, 0xb8,
+	0x74, 0x90, 0x13, 0x42, 0x3f, 0xe0, 0x6b, 0x1d,
+	0xf2, 0x4d, 0x54, 0xd4, 0xfc, 0x3a, 0x05, 0xe6,
+	0x74, 0xaf, 0xa6, 0xa0, 0x2a, 0x20, 0x23, 0x5d,
+	0x34, 0x5c, 0xd9, 0x3e, 0x4e, 0xfa, 0x93, 0xe7,
+	0xaa, 0xe9, 0x6f, 0x08, 0x43, 0x67, 0x41, 0xc5,
+	0xad, 0xfb, 0x31, 0x95, 0x82, 0x73, 0x32, 0xd8,
+	0xa6, 0xa3, 0xed, 0x0e, 0x2d, 0xf6, 0x5f, 0xfd,
+	0x80, 0xa6, 0x7a, 0xe0, 0xdf, 0x78, 0x15, 0x29,
+	0x74, 0x33, 0xd0, 0x9e, 0x83, 0x86, 0x72, 0x22,
+	0x57, 0x29, 0xb9, 0x9e, 0x5d, 0xd3, 0x1a, 0xb5,
+	0x96, 0x72, 0x41, 0x3d, 0xf1, 0x64, 0x43, 0x67,
+	0xee, 0xaa, 0x5c, 0xd3, 0x9a, 0x96, 0x13, 0x11,
+	0x5d, 0xf3, 0x0c, 0x87, 0x82, 0x1e, 0x41, 0x9e,
+	0xd0, 0x27, 0xd7, 0x54, 0x3b, 0x67, 0x73, 0x09,
+	0x91, 0xe9, 0xd5, 0x36, 0xa7, 0xb5, 0x55, 0xe4,
+	0xf3, 0x21, 0x51, 0x49, 0x22, 0x07, 0x55, 0x4f,
+	0x44, 0x4b, 0xd2, 0x15, 0x93, 0x17, 0x2a, 0xfa,
+	0x4d, 0x4a, 0x57, 0xdb, 0x4c, 0xa6, 0xeb, 0xec,
+	0x53, 0x25, 0x6c, 0x21, 0xed, 0x00, 0x4c, 0x3b,
+	0xca, 0x14, 0x57, 0xa9, 0xd6, 0x6a, 0xcd, 0x8d,
+	0x5e, 0x74, 0xac, 0x72, 0xc1, 0x97, 0xe5, 0x1b,
+	0x45, 0x4e, 0xda, 0xfc, 0xcc, 0x40, 0xe8, 0x48,
+	0x88, 0x0b, 0xa3, 0xe3, 0x8d, 0x83, 0x42, 0xc3,
+	0x23, 0xfd, 0x68, 0xb5, 0x8e, 0xf1, 0x9d, 0x63,
+	0x77, 0xe9, 0xa3, 0x8e, 0x8c, 0x26, 0x6b, 0xbd,
+	0x72, 0x73, 0x35, 0x0c, 0x03, 0xf8, 0x43, 0x78,
+	0x52, 0x71, 0x15, 0x1f, 0x71, 0x5d, 0x6e, 0xed,
+	0xb9, 0xcc, 0x86, 0x30, 0xdb, 0x2b, 0xd3, 0x82,
+	0x88, 0x23, 0x71, 0x90, 0x53, 0x5c, 0xa9, 0x2f,
+	0x76, 0x01, 0xb7, 0x9a, 0xfe, 0x43, 0x55, 0xa3,
+	0x04, 0x9b, 0x0e, 0xe4, 0x59, 0xdf, 0xc9, 0xe9,
+	0xb1, 0xea, 0x29, 0x28, 0x3c, 0x5c, 0xae, 0x72,
+	0x84, 0xb6, 0xc6, 0xeb, 0x0c, 0x27, 0x07, 0x74,
+	0x90, 0x0d, 0x31, 0xb0, 0x00, 0x77, 0xe9, 0x40,
+	0x70, 0x6f, 0x68, 0xa7, 0xfd, 0x06, 0xec, 0x4b,
+	0xc0, 0xb7, 0xac, 0xbc, 0x33, 0xb7, 0x6d, 0x0a,
+	0xbd, 0x12, 0x1b, 0x59, 0xcb, 0xdd, 0x32, 0xf5,
+	0x1d, 0x94, 0x57, 0x76, 0x9e, 0x0c, 0x18, 0x98,
+	0x71, 0xd7, 0x2a, 0xdb, 0x0b, 0x7b, 0xa7, 0x71,
+	0xb7, 0x67, 0x81, 0x23, 0x96, 0xae, 0xb9, 0x7e,
+	0x32, 0x43, 0x92, 0x8a, 0x19, 0xa0, 0xc4, 0xd4,
+	0x3b, 0x57, 0xf9, 0x4a, 0x2c, 0xfb, 0x51, 0x46,
+	0xbb, 0xcb, 0x5d, 0xb3, 0xef, 0x13, 0x93, 0x6e,
+	0x68, 0x42, 0x54, 0x57, 0xd3, 0x6a, 0x3a, 0x8f,
+	0x9d, 0x66, 0xbf, 0xbd, 0x36, 0x23, 0xf5, 0x93,
+	0x83, 0x7b, 0x9c, 0xc0, 0xdd, 0xc5, 0x49, 0xc0,
+	0x64, 0xed, 0x07, 0x12, 0xb3, 0xe6, 0xe4, 0xe5,
+	0x38, 0x95, 0x23, 0xb1, 0xa0, 0x3b, 0x1a, 0x61,
+	0xda, 0x17, 0xac, 0xc3, 0x58, 0xdd, 0x74, 0x64,
+	0x22, 0x11, 0xe8, 0x32, 0x1d, 0x16, 0x93, 0x85,
+	0x99, 0xa5, 0x9c, 0x34, 0x55, 0xb1, 0xe9, 0x20,
+	0x72, 0xc9, 0x28, 0x7b, 0x79, 0x00, 0xa1, 0xa6,
+	0xa3, 0x27, 0x40, 0x18, 0x8a, 0x54, 0xe0, 0xcc,
+	0xe8, 0x4e, 0x8e, 0x43, 0x96, 0xe7, 0x3f, 0xc8,
+	0xe9, 0xb2, 0xf9, 0xc9, 0xda, 0x04, 0x71, 0x50,
+	0x47, 0xe4, 0xaa, 0xce, 0xa2, 0x30, 0xc8, 0xe4,
+	0xac, 0xc7, 0x0d, 0x06, 0x2e, 0xe6, 0xe8, 0x80,
+	0x36, 0x29, 0x9e, 0x01, 0xb8, 0xc3, 0xf0, 0xa0,
+	0x5d, 0x7a, 0xca, 0x4d, 0xa0, 0x57, 0xbd, 0x2a,
+	0x45, 0xa7, 0x7f, 0x9c, 0x93, 0x07, 0x8f, 0x35,
+	0x67, 0x92, 0xe3, 0xe9, 0x7f, 0xa8, 0x61, 0x43,
+	0x9e, 0x25, 0x4f, 0x33, 0x76, 0x13, 0x6e, 0x12,
+	0xb9, 0xdd, 0xa4, 0x7c, 0x08, 0x9f, 0x7c, 0xe7,
+	0x0a, 0x8d, 0x84, 0x06, 0xa4, 0x33, 0x17, 0x34,
+	0x5e, 0x10, 0x7c, 0xc0, 0xa8, 0x3d, 0x1f, 0x42,
+	0x20, 0x51, 0x65, 0x5d, 0x09, 0xc3, 0xaa, 0xc0,
+	0xc8, 0x0d, 0xf0, 0x79, 0xbc, 0x20, 0x1b, 0x95,
+	0xe7, 0x06, 0x7d, 0x47, 0x20, 0x03, 0x1a, 0x74,
+	0xdd, 0xe2, 0xd4, 0xae, 0x38, 0x71, 0x9b, 0xf5,
+	0x80, 0xec, 0x08, 0x4e, 0x56, 0xba, 0x76, 0x12,
+	0x1a, 0xdf, 0x48, 0xf3, 0xae, 0xb3, 0xe6, 0xe6,
+	0xbe, 0xc0, 0x91, 0x2e, 0x01, 0xb3, 0x01, 0x86,
+	0xa2, 0xb9, 0x52, 0xd1, 0x21, 0xae, 0xd4, 0x97,
+	0x1d, 0xef, 0x41, 0x12, 0x95, 0x3d, 0x48, 0x45,
+	0x1c, 0x56, 0x32, 0x8f, 0xb8, 0x43, 0xbb, 0x19,
+	0xf3, 0xca, 0xe9, 0xeb, 0x6d, 0x84, 0xbe, 0x86,
+	0x06, 0xe2, 0x36, 0xb2, 0x62, 0x9d, 0xd3, 0x4c,
+	0x48, 0x18, 0x54, 0x13, 0x4e, 0xcf, 0xfd, 0xba,
+	0x84, 0xb9, 0x30, 0x53, 0xcf, 0xfb, 0xb9, 0x29,
+	0x8f, 0xdc, 0x9f, 0xef, 0x60, 0x0b, 0x64, 0xf6,
+	0x8b, 0xee, 0xa6, 0x91, 0xc2, 0x41, 0x6c, 0xf6,
+	0xfa, 0x79, 0x67, 0x4b, 0xc1, 0x3f, 0xaf, 0x09,
+	0x81, 0xd4, 0x5d, 0xcb, 0x09, 0xdf, 0x36, 0x31,
+	0xc0, 0x14, 0x3c, 0x7c, 0x0e, 0x65, 0x95, 0x99,
+	0x6d, 0xa3, 0xf4, 0xd7, 0x38, 0xee, 0x1a, 0x2b,
+	0x37, 0xe2, 0xa4, 0x3b, 0x4b, 0xd0, 0x65, 0xca,
+	0xf8, 0xc3, 0xe8, 0x15, 0x20, 0xef, 0xf2, 0x00,
+	0xfd, 0x01, 0x09, 0xc5, 0xc8, 0x17, 0x04, 0x93,
+	0xd0, 0x93, 0x03, 0x55, 0xc5, 0xfe, 0x32, 0xa3,
+	0x3e, 0x28, 0x2d, 0x3b, 0x93, 0x8a, 0xcc, 0x07,
+	0x72, 0x80, 0x8b, 0x74, 0x16, 0x24, 0xbb, 0xda,
+	0x94, 0x39, 0x30, 0x8f, 0xb1, 0xcd, 0x4a, 0x90,
+	0x92, 0x7c, 0x14, 0x8f, 0x95, 0x4e, 0xac, 0x9b,
+	0xd8, 0x8f, 0x1a, 0x87, 0xa4, 0x32, 0x27, 0x8a,
+	0xba, 0xf7, 0x41, 0xcf, 0x84, 0x37, 0x19, 0xe6,
+	0x06, 0xf5, 0x0e, 0xcf, 0x36, 0xf5, 0x9e, 0x6c,
+	0xde, 0xbc, 0xff, 0x64, 0x7e, 0x4e, 0x59, 0x57,
+	0x48, 0xfe, 0x14, 0xf7, 0x9c, 0x93, 0x5d, 0x15,
+	0xad, 0xcc, 0x11, 0xb1, 0x17, 0x18, 0xb2, 0x7e,
+	0xcc, 0xab, 0xe9, 0xce, 0x7d, 0x77, 0x5b, 0x51,
+	0x1b, 0x1e, 0x20, 0xa8, 0x32, 0x06, 0x0e, 0x75,
+	0x93, 0xac, 0xdb, 0x35, 0x37, 0x1f, 0xe9, 0x19,
+	0x1d, 0xb4, 0x71, 0x97, 0xd6, 0x4e, 0x2c, 0x08,
+	0xa5, 0x13, 0xf9, 0x0e, 0x7e, 0x78, 0x6e, 0x14,
+	0xe0, 0xa9, 0xb9, 0x96, 0x4c, 0x80, 0x82, 0xba,
+	0x17, 0xb3, 0x9d, 0x69, 0xb0, 0x84, 0x46, 0xff,
+	0xf9, 0x52, 0x79, 0x94, 0x58, 0x3a, 0x62, 0x90,
+	0x15, 0x35, 0x71, 0x10, 0x37, 0xed, 0xa1, 0x8e,
+	0x53, 0x6e, 0xf4, 0x26, 0x57, 0x93, 0x15, 0x93,
+	0xf6, 0x81, 0x2c, 0x5a, 0x10, 0xda, 0x92, 0xad,
+	0x2f, 0xdb, 0x28, 0x31, 0x2d, 0x55, 0x04, 0xd2,
+	0x06, 0x28, 0x8c, 0x1e, 0xdc, 0xea, 0x54, 0xac,
+	0xff, 0xb7, 0x6c, 0x30, 0x15, 0xd4, 0xb4, 0x0d,
+	0x00, 0x93, 0x57, 0xdd, 0xd2, 0x07, 0x07, 0x06,
+	0xd9, 0x43, 0x9b, 0xcd, 0x3a, 0xf4, 0x7d, 0x4c,
+	0x36, 0x5d, 0x23, 0xa2, 0xcc, 0x57, 0x40, 0x91,
+	0xe9, 0x2c, 0x2f, 0x2c, 0xd5, 0x30, 0x9b, 0x17,
+	0xb0, 0xc9, 0xf7, 0xa7, 0x2f, 0xd1, 0x93, 0x20,
+	0x6b, 0xc6, 0xc1, 0xe4, 0x6f, 0xcb, 0xd1, 0xe7,
+	0x09, 0x0f, 0x9e, 0xdc, 0xaa, 0x9f, 0x2f, 0xdf,
+	0x56, 0x9f, 0xd4, 0x33, 0x04, 0xaf, 0xd3, 0x6c,
+	0x58, 0x61, 0xf0, 0x30, 0xec, 0xf2, 0x7f, 0xf2,
+	0x9c, 0xdf, 0x39, 0xbb, 0x6f, 0xa2, 0x8c, 0x7e,
+	0xc4, 0x22, 0x51, 0x71, 0xc0, 0x4d, 0x14, 0x1a,
+	0xc4, 0xcd, 0x04, 0xd9, 0x87, 0x08, 0x50, 0x05,
+	0xcc, 0xaf, 0xf6, 0xf0, 0x8f, 0x92, 0x54, 0x58,
+	0xc2, 0xc7, 0x09, 0x7a, 0x59, 0x02, 0x05, 0xe8,
+	0xb0, 0x86, 0xd9, 0xbf, 0x7b, 0x35, 0x51, 0x4d,
+	0xaf, 0x08, 0x97, 0x2c, 0x65, 0xda, 0x2a, 0x71,
+	0x3a, 0xa8, 0x51, 0xcc, 0xf2, 0x73, 0x27, 0xc3,
+	0xfd, 0x62, 0xcf, 0xe3, 0xb2, 0xca, 0xcb, 0xbe,
+	0x1a, 0x0a, 0xa1, 0x34, 0x7b, 0x77, 0xc4, 0x62,
+	0x68, 0x78, 0x5f, 0x94, 0x07, 0x04, 0x65, 0x16,
+	0x4b, 0x61, 0xcb, 0xff, 0x75, 0x26, 0x50, 0x66,
+	0x1f, 0x6e, 0x93, 0xf8, 0xc5, 0x51, 0xeb, 0xa4,
+	0x4a, 0x48, 0x68, 0x6b, 0xe2, 0x5e, 0x44, 0xb2,
+	0x50, 0x2c, 0x6c, 0xae, 0x79, 0x4e, 0x66, 0x35,
+	0x81, 0x50, 0xac, 0xbc, 0x3f, 0xb1, 0x0c, 0xf3,
+	0x05, 0x3c, 0x4a, 0xa3, 0x6c, 0x2a, 0x79, 0xb4,
+	0xb7, 0xab, 0xca, 0xc7, 0x9b, 0x8e, 0xcd, 0x5f,
+	0x11, 0x03, 0xcb, 0x30, 0xa3, 0xab, 0xda, 0xfe,
+	0x64, 0xb9, 0xbb, 0xd8, 0x5e, 0x3a, 0x1a, 0x56,
+	0xe5, 0x05, 0x48, 0x90, 0x1e, 0x61, 0x69, 0x1b,
+	0x22, 0xe6, 0x1a, 0x3c, 0x75, 0xad, 0x1f, 0x37,
+	0x28, 0xdc, 0xe4, 0x6d, 0xbd, 0x42, 0xdc, 0xd3,
+	0xc8, 0xb6, 0x1c, 0x48, 0xfe, 0x94, 0x77, 0x7f,
+	0xbd, 0x62, 0xac, 0xa3, 0x47, 0x27, 0xcf, 0x5f,
+	0xd9, 0xdb, 0xaf, 0xec, 0xf7, 0x5e, 0xc1, 0xb0,
+	0x9d, 0x01, 0x26, 0x99, 0x7e, 0x8f, 0x03, 0x70,
+	0xb5, 0x42, 0xbe, 0x67, 0x28, 0x1b, 0x7c, 0xbd,
+	0x61, 0x21, 0x97, 0xcc, 0x5c, 0xe1, 0x97, 0x8f,
+	0x8d, 0xde, 0x2b, 0xaa, 0xa7, 0x71, 0x1d, 0x1e,
+	0x02, 0x73, 0x70, 0x58, 0x32, 0x5b, 0x1d, 0x67,
+	0x3d, 0xe0, 0x74, 0x4f, 0x03, 0xf2, 0x70, 0x51,
+	0x79, 0xf1, 0x61, 0x70, 0x15, 0x74, 0x9d, 0x23,
+	0x89, 0xde, 0xac, 0xfd, 0xde, 0xd0, 0x1f, 0xc3,
+	0x87, 0x44, 0x35, 0x4b, 0xe5, 0xb0, 0x60, 0xc5,
+	0x22, 0xe4, 0x9e, 0xca, 0xeb, 0xd5, 0x3a, 0x09,
+	0x45, 0xa4, 0xdb, 0xfa, 0x3f, 0xeb, 0x1b, 0xc7,
+	0xc8, 0x14, 0x99, 0x51, 0x92, 0x10, 0xed, 0xed,
+	0x28, 0xe0, 0xa1, 0xf8, 0x26, 0xcf, 0xcd, 0xcb,
+	0x63, 0xa1, 0x3b, 0xe3, 0xdf, 0x7e, 0xfe, 0xa6,
+	0xf0, 0x81, 0x9a, 0xbf, 0x55, 0xde, 0x54, 0xd5,
+	0x56, 0x60, 0x98, 0x10, 0x68, 0xf4, 0x38, 0x96,
+	0x8e, 0x6f, 0x1d, 0x44, 0x7f, 0xd6, 0x2f, 0xfe,
+	0x55, 0xfb, 0x0c, 0x7e, 0x67, 0xe2, 0x61, 0x44,
+	0xed, 0xf2, 0x35, 0x30, 0x5d, 0xe9, 0xc7, 0xd6,
+	0x6d, 0xe0, 0xa0, 0xed, 0xf3, 0xfc, 0xd8, 0x3e,
+	0x0a, 0x7b, 0xcd, 0xaf, 0x65, 0x68, 0x18, 0xc0,
+	0xec, 0x04, 0x1c, 0x74, 0x6d, 0xe2, 0x6e, 0x79,
+	0xd4, 0x11, 0x2b, 0x62, 0xd5, 0x27, 0xad, 0x4f,
+	0x01, 0x59, 0x73, 0xcc, 0x6a, 0x53, 0xfb, 0x2d,
+	0xd5, 0x4e, 0x99, 0x21, 0x65, 0x4d, 0xf5, 0x82,
+	0xf7, 0xd8, 0x42, 0xce, 0x6f, 0x3d, 0x36, 0x47,
+	0xf1, 0x05, 0x16, 0xe8, 0x1b, 0x6a, 0x8f, 0x93,
+	0xf2, 0x8f, 0x37, 0x40, 0x12, 0x28, 0xa3, 0xe6,
+	0xb9, 0x17, 0x4a, 0x1f, 0xb1, 0xd1, 0x66, 0x69,
+	0x86, 0xc4, 0xfc, 0x97, 0xae, 0x3f, 0x8f, 0x1e,
+	0x2b, 0xdf, 0xcd, 0xf9, 0x3c
+};
+static const u8 enc_assoc011[] __initconst = {
+	0xd6, 0x31, 0xda, 0x5d, 0x42, 0x5e, 0xd7
+};
+static const u8 enc_nonce011[] __initconst = {
+	0xfd, 0x87, 0xd4, 0xd8, 0x62, 0xfd, 0xec, 0xaa
+};
+static const u8 enc_key011[] __initconst = {
+	0x35, 0x4e, 0xb5, 0x70, 0x50, 0x42, 0x8a, 0x85,
+	0xf2, 0xfb, 0xed, 0x7b, 0xd0, 0x9e, 0x97, 0xca,
+	0xfa, 0x98, 0x66, 0x63, 0xee, 0x37, 0xcc, 0x52,
+	0xfe, 0xd1, 0xdf, 0x95, 0x15, 0x34, 0x29, 0x38
+};
+
+static const u8 enc_input012[] __initconst = {
+	0x74, 0xa6, 0x3e, 0xe4, 0xb1, 0xcb, 0xaf, 0xb0,
+	0x40, 0xe5, 0x0f, 0x9e, 0xf1, 0xf2, 0x89, 0xb5,
+	0x42, 0x34, 0x8a, 0xa1, 0x03, 0xb7, 0xe9, 0x57,
+	0x46, 0xbe, 0x20, 0xe4, 0x6e, 0xb0, 0xeb, 0xff,
+	0xea, 0x07, 0x7e, 0xef, 0xe2, 0x55, 0x9f, 0xe5,
+	0x78, 0x3a, 0xb7, 0x83, 0xc2, 0x18, 0x40, 0x7b,
+	0xeb, 0xcd, 0x81, 0xfb, 0x90, 0x12, 0x9e, 0x46,
+	0xa9, 0xd6, 0x4a, 0xba, 0xb0, 0x62, 0xdb, 0x6b,
+	0x99, 0xc4, 0xdb, 0x54, 0x4b, 0xb8, 0xa5, 0x71,
+	0xcb, 0xcd, 0x63, 0x32, 0x55, 0xfb, 0x31, 0xf0,
+	0x38, 0xf5, 0xbe, 0x78, 0xe4, 0x45, 0xce, 0x1b,
+	0x6a, 0x5b, 0x0e, 0xf4, 0x16, 0xe4, 0xb1, 0x3d,
+	0xf6, 0x63, 0x7b, 0xa7, 0x0c, 0xde, 0x6f, 0x8f,
+	0x74, 0xdf, 0xe0, 0x1e, 0x9d, 0xce, 0x8f, 0x24,
+	0xef, 0x23, 0x35, 0x33, 0x7b, 0x83, 0x34, 0x23,
+	0x58, 0x74, 0x14, 0x77, 0x1f, 0xc2, 0x4f, 0x4e,
+	0xc6, 0x89, 0xf9, 0x52, 0x09, 0x37, 0x64, 0x14,
+	0xc4, 0x01, 0x6b, 0x9d, 0x77, 0xe8, 0x90, 0x5d,
+	0xa8, 0x4a, 0x2a, 0xef, 0x5c, 0x7f, 0xeb, 0xbb,
+	0xb2, 0xc6, 0x93, 0x99, 0x66, 0xdc, 0x7f, 0xd4,
+	0x9e, 0x2a, 0xca, 0x8d, 0xdb, 0xe7, 0x20, 0xcf,
+	0xe4, 0x73, 0xae, 0x49, 0x7d, 0x64, 0x0f, 0x0e,
+	0x28, 0x46, 0xa9, 0xa8, 0x32, 0xe4, 0x0e, 0xf6,
+	0x51, 0x53, 0xb8, 0x3c, 0xb1, 0xff, 0xa3, 0x33,
+	0x41, 0x75, 0xff, 0xf1, 0x6f, 0xf1, 0xfb, 0xbb,
+	0x83, 0x7f, 0x06, 0x9b, 0xe7, 0x1b, 0x0a, 0xe0,
+	0x5c, 0x33, 0x60, 0x5b, 0xdb, 0x5b, 0xed, 0xfe,
+	0xa5, 0x16, 0x19, 0x72, 0xa3, 0x64, 0x23, 0x00,
+	0x02, 0xc7, 0xf3, 0x6a, 0x81, 0x3e, 0x44, 0x1d,
+	0x79, 0x15, 0x5f, 0x9a, 0xde, 0xe2, 0xfd, 0x1b,
+	0x73, 0xc1, 0xbc, 0x23, 0xba, 0x31, 0xd2, 0x50,
+	0xd5, 0xad, 0x7f, 0x74, 0xa7, 0xc9, 0xf8, 0x3e,
+	0x2b, 0x26, 0x10, 0xf6, 0x03, 0x36, 0x74, 0xe4,
+	0x0e, 0x6a, 0x72, 0xb7, 0x73, 0x0a, 0x42, 0x28,
+	0xc2, 0xad, 0x5e, 0x03, 0xbe, 0xb8, 0x0b, 0xa8,
+	0x5b, 0xd4, 0xb8, 0xba, 0x52, 0x89, 0xb1, 0x9b,
+	0xc1, 0xc3, 0x65, 0x87, 0xed, 0xa5, 0xf4, 0x86,
+	0xfd, 0x41, 0x80, 0x91, 0x27, 0x59, 0x53, 0x67,
+	0x15, 0x78, 0x54, 0x8b, 0x2d, 0x3d, 0xc7, 0xff,
+	0x02, 0x92, 0x07, 0x5f, 0x7a, 0x4b, 0x60, 0x59,
+	0x3c, 0x6f, 0x5c, 0xd8, 0xec, 0x95, 0xd2, 0xfe,
+	0xa0, 0x3b, 0xd8, 0x3f, 0xd1, 0x69, 0xa6, 0xd6,
+	0x41, 0xb2, 0xf4, 0x4d, 0x12, 0xf4, 0x58, 0x3e,
+	0x66, 0x64, 0x80, 0x31, 0x9b, 0xa8, 0x4c, 0x8b,
+	0x07, 0xb2, 0xec, 0x66, 0x94, 0x66, 0x47, 0x50,
+	0x50, 0x5f, 0x18, 0x0b, 0x0e, 0xd6, 0xc0, 0x39,
+	0x21, 0x13, 0x9e, 0x33, 0xbc, 0x79, 0x36, 0x02,
+	0x96, 0x70, 0xf0, 0x48, 0x67, 0x2f, 0x26, 0xe9,
+	0x6d, 0x10, 0xbb, 0xd6, 0x3f, 0xd1, 0x64, 0x7a,
+	0x2e, 0xbe, 0x0c, 0x61, 0xf0, 0x75, 0x42, 0x38,
+	0x23, 0xb1, 0x9e, 0x9f, 0x7c, 0x67, 0x66, 0xd9,
+	0x58, 0x9a, 0xf1, 0xbb, 0x41, 0x2a, 0x8d, 0x65,
+	0x84, 0x94, 0xfc, 0xdc, 0x6a, 0x50, 0x64, 0xdb,
+	0x56, 0x33, 0x76, 0x00, 0x10, 0xed, 0xbe, 0xd2,
+	0x12, 0xf6, 0xf6, 0x1b, 0xa2, 0x16, 0xde, 0xae,
+	0x31, 0x95, 0xdd, 0xb1, 0x08, 0x7e, 0x4e, 0xee,
+	0xe7, 0xf9, 0xa5, 0xfb, 0x5b, 0x61, 0x43, 0x00,
+	0x40, 0xf6, 0x7e, 0x02, 0x04, 0x32, 0x4e, 0x0c,
+	0xe2, 0x66, 0x0d, 0xd7, 0x07, 0x98, 0x0e, 0xf8,
+	0x72, 0x34, 0x6d, 0x95, 0x86, 0xd7, 0xcb, 0x31,
+	0x54, 0x47, 0xd0, 0x38, 0x29, 0x9c, 0x5a, 0x68,
+	0xd4, 0x87, 0x76, 0xc9, 0xe7, 0x7e, 0xe3, 0xf4,
+	0x81, 0x6d, 0x18, 0xcb, 0xc9, 0x05, 0xaf, 0xa0,
+	0xfb, 0x66, 0xf7, 0xf1, 0x1c, 0xc6, 0x14, 0x11,
+	0x4f, 0x2b, 0x79, 0x42, 0x8b, 0xbc, 0xac, 0xe7,
+	0x6c, 0xfe, 0x0f, 0x58, 0xe7, 0x7c, 0x78, 0x39,
+	0x30, 0xb0, 0x66, 0x2c, 0x9b, 0x6d, 0x3a, 0xe1,
+	0xcf, 0xc9, 0xa4, 0x0e, 0x6d, 0x6d, 0x8a, 0xa1,
+	0x3a, 0xe7, 0x28, 0xd4, 0x78, 0x4c, 0xa6, 0xa2,
+	0x2a, 0xa6, 0x03, 0x30, 0xd7, 0xa8, 0x25, 0x66,
+	0x87, 0x2f, 0x69, 0x5c, 0x4e, 0xdd, 0xa5, 0x49,
+	0x5d, 0x37, 0x4a, 0x59, 0xc4, 0xaf, 0x1f, 0xa2,
+	0xe4, 0xf8, 0xa6, 0x12, 0x97, 0xd5, 0x79, 0xf5,
+	0xe2, 0x4a, 0x2b, 0x5f, 0x61, 0xe4, 0x9e, 0xe3,
+	0xee, 0xb8, 0xa7, 0x5b, 0x2f, 0xf4, 0x9e, 0x6c,
+	0xfb, 0xd1, 0xc6, 0x56, 0x77, 0xba, 0x75, 0xaa,
+	0x3d, 0x1a, 0xa8, 0x0b, 0xb3, 0x68, 0x24, 0x00,
+	0x10, 0x7f, 0xfd, 0xd7, 0xa1, 0x8d, 0x83, 0x54,
+	0x4f, 0x1f, 0xd8, 0x2a, 0xbe, 0x8a, 0x0c, 0x87,
+	0xab, 0xa2, 0xde, 0xc3, 0x39, 0xbf, 0x09, 0x03,
+	0xa5, 0xf3, 0x05, 0x28, 0xe1, 0xe1, 0xee, 0x39,
+	0x70, 0x9c, 0xd8, 0x81, 0x12, 0x1e, 0x02, 0x40,
+	0xd2, 0x6e, 0xf0, 0xeb, 0x1b, 0x3d, 0x22, 0xc6,
+	0xe5, 0xe3, 0xb4, 0x5a, 0x98, 0xbb, 0xf0, 0x22,
+	0x28, 0x8d, 0xe5, 0xd3, 0x16, 0x48, 0x24, 0xa5,
+	0xe6, 0x66, 0x0c, 0xf9, 0x08, 0xf9, 0x7e, 0x1e,
+	0xe1, 0x28, 0x26, 0x22, 0xc7, 0xc7, 0x0a, 0x32,
+	0x47, 0xfa, 0xa3, 0xbe, 0x3c, 0xc4, 0xc5, 0x53,
+	0x0a, 0xd5, 0x94, 0x4a, 0xd7, 0x93, 0xd8, 0x42,
+	0x99, 0xb9, 0x0a, 0xdb, 0x56, 0xf7, 0xb9, 0x1c,
+	0x53, 0x4f, 0xfa, 0xd3, 0x74, 0xad, 0xd9, 0x68,
+	0xf1, 0x1b, 0xdf, 0x61, 0xc6, 0x5e, 0xa8, 0x48,
+	0xfc, 0xd4, 0x4a, 0x4c, 0x3c, 0x32, 0xf7, 0x1c,
+	0x96, 0x21, 0x9b, 0xf9, 0xa3, 0xcc, 0x5a, 0xce,
+	0xd5, 0xd7, 0x08, 0x24, 0xf6, 0x1c, 0xfd, 0xdd,
+	0x38, 0xc2, 0x32, 0xe9, 0xb8, 0xe7, 0xb6, 0xfa,
+	0x9d, 0x45, 0x13, 0x2c, 0x83, 0xfd, 0x4a, 0x69,
+	0x82, 0xcd, 0xdc, 0xb3, 0x76, 0x0c, 0x9e, 0xd8,
+	0xf4, 0x1b, 0x45, 0x15, 0xb4, 0x97, 0xe7, 0x58,
+	0x34, 0xe2, 0x03, 0x29, 0x5a, 0xbf, 0xb6, 0xe0,
+	0x5d, 0x13, 0xd9, 0x2b, 0xb4, 0x80, 0xb2, 0x45,
+	0x81, 0x6a, 0x2e, 0x6c, 0x89, 0x7d, 0xee, 0xbb,
+	0x52, 0xdd, 0x1f, 0x18, 0xe7, 0x13, 0x6b, 0x33,
+	0x0e, 0xea, 0x36, 0x92, 0x77, 0x7b, 0x6d, 0x9c,
+	0x5a, 0x5f, 0x45, 0x7b, 0x7b, 0x35, 0x62, 0x23,
+	0xd1, 0xbf, 0x0f, 0xd0, 0x08, 0x1b, 0x2b, 0x80,
+	0x6b, 0x7e, 0xf1, 0x21, 0x47, 0xb0, 0x57, 0xd1,
+	0x98, 0x72, 0x90, 0x34, 0x1c, 0x20, 0x04, 0xff,
+	0x3d, 0x5c, 0xee, 0x0e, 0x57, 0x5f, 0x6f, 0x24,
+	0x4e, 0x3c, 0xea, 0xfc, 0xa5, 0xa9, 0x83, 0xc9,
+	0x61, 0xb4, 0x51, 0x24, 0xf8, 0x27, 0x5e, 0x46,
+	0x8c, 0xb1, 0x53, 0x02, 0x96, 0x35, 0xba, 0xb8,
+	0x4c, 0x71, 0xd3, 0x15, 0x59, 0x35, 0x22, 0x20,
+	0xad, 0x03, 0x9f, 0x66, 0x44, 0x3b, 0x9c, 0x35,
+	0x37, 0x1f, 0x9b, 0xbb, 0xf3, 0xdb, 0x35, 0x63,
+	0x30, 0x64, 0xaa, 0xa2, 0x06, 0xa8, 0x5d, 0xbb,
+	0xe1, 0x9f, 0x70, 0xec, 0x82, 0x11, 0x06, 0x36,
+	0xec, 0x8b, 0x69, 0x66, 0x24, 0x44, 0xc9, 0x4a,
+	0x57, 0xbb, 0x9b, 0x78, 0x13, 0xce, 0x9c, 0x0c,
+	0xba, 0x92, 0x93, 0x63, 0xb8, 0xe2, 0x95, 0x0f,
+	0x0f, 0x16, 0x39, 0x52, 0xfd, 0x3a, 0x6d, 0x02,
+	0x4b, 0xdf, 0x13, 0xd3, 0x2a, 0x22, 0xb4, 0x03,
+	0x7c, 0x54, 0x49, 0x96, 0x68, 0x54, 0x10, 0xfa,
+	0xef, 0xaa, 0x6c, 0xe8, 0x22, 0xdc, 0x71, 0x16,
+	0x13, 0x1a, 0xf6, 0x28, 0xe5, 0x6d, 0x77, 0x3d,
+	0xcd, 0x30, 0x63, 0xb1, 0x70, 0x52, 0xa1, 0xc5,
+	0x94, 0x5f, 0xcf, 0xe8, 0xb8, 0x26, 0x98, 0xf7,
+	0x06, 0xa0, 0x0a, 0x70, 0xfa, 0x03, 0x80, 0xac,
+	0xc1, 0xec, 0xd6, 0x4c, 0x54, 0xd7, 0xfe, 0x47,
+	0xb6, 0x88, 0x4a, 0xf7, 0x71, 0x24, 0xee, 0xf3,
+	0xd2, 0xc2, 0x4a, 0x7f, 0xfe, 0x61, 0xc7, 0x35,
+	0xc9, 0x37, 0x67, 0xcb, 0x24, 0x35, 0xda, 0x7e,
+	0xca, 0x5f, 0xf3, 0x8d, 0xd4, 0x13, 0x8e, 0xd6,
+	0xcb, 0x4d, 0x53, 0x8f, 0x53, 0x1f, 0xc0, 0x74,
+	0xf7, 0x53, 0xb9, 0x5e, 0x23, 0x37, 0xba, 0x6e,
+	0xe3, 0x9d, 0x07, 0x55, 0x25, 0x7b, 0xe6, 0x2a,
+	0x64, 0xd1, 0x32, 0xdd, 0x54, 0x1b, 0x4b, 0xc0,
+	0xe1, 0xd7, 0x69, 0x58, 0xf8, 0x93, 0x29, 0xc4,
+	0xdd, 0x23, 0x2f, 0xa5, 0xfc, 0x9d, 0x7e, 0xf8,
+	0xd4, 0x90, 0xcd, 0x82, 0x55, 0xdc, 0x16, 0x16,
+	0x9f, 0x07, 0x52, 0x9b, 0x9d, 0x25, 0xed, 0x32,
+	0xc5, 0x7b, 0xdf, 0xf6, 0x83, 0x46, 0x3d, 0x65,
+	0xb7, 0xef, 0x87, 0x7a, 0x12, 0x69, 0x8f, 0x06,
+	0x7c, 0x51, 0x15, 0x4a, 0x08, 0xe8, 0xac, 0x9a,
+	0x0c, 0x24, 0xa7, 0x27, 0xd8, 0x46, 0x2f, 0xe7,
+	0x01, 0x0e, 0x1c, 0xc6, 0x91, 0xb0, 0x6e, 0x85,
+	0x65, 0xf0, 0x29, 0x0d, 0x2e, 0x6b, 0x3b, 0xfb,
+	0x4b, 0xdf, 0xe4, 0x80, 0x93, 0x03, 0x66, 0x46,
+	0x3e, 0x8a, 0x6e, 0xf3, 0x5e, 0x4d, 0x62, 0x0e,
+	0x49, 0x05, 0xaf, 0xd4, 0xf8, 0x21, 0x20, 0x61,
+	0x1d, 0x39, 0x17, 0xf4, 0x61, 0x47, 0x95, 0xfb,
+	0x15, 0x2e, 0xb3, 0x4f, 0xd0, 0x5d, 0xf5, 0x7d,
+	0x40, 0xda, 0x90, 0x3c, 0x6b, 0xcb, 0x17, 0x00,
+	0x13, 0x3b, 0x64, 0x34, 0x1b, 0xf0, 0xf2, 0xe5,
+	0x3b, 0xb2, 0xc7, 0xd3, 0x5f, 0x3a, 0x44, 0xa6,
+	0x9b, 0xb7, 0x78, 0x0e, 0x42, 0x5d, 0x4c, 0xc1,
+	0xe9, 0xd2, 0xcb, 0xb7, 0x78, 0xd1, 0xfe, 0x9a,
+	0xb5, 0x07, 0xe9, 0xe0, 0xbe, 0xe2, 0x8a, 0xa7,
+	0x01, 0x83, 0x00, 0x8c, 0x5c, 0x08, 0xe6, 0x63,
+	0x12, 0x92, 0xb7, 0xb7, 0xa6, 0x19, 0x7d, 0x38,
+	0x13, 0x38, 0x92, 0x87, 0x24, 0xf9, 0x48, 0xb3,
+	0x5e, 0x87, 0x6a, 0x40, 0x39, 0x5c, 0x3f, 0xed,
+	0x8f, 0xee, 0xdb, 0x15, 0x82, 0x06, 0xda, 0x49,
+	0x21, 0x2b, 0xb5, 0xbf, 0x32, 0x7c, 0x9f, 0x42,
+	0x28, 0x63, 0xcf, 0xaf, 0x1e, 0xf8, 0xc6, 0xa0,
+	0xd1, 0x02, 0x43, 0x57, 0x62, 0xec, 0x9b, 0x0f,
+	0x01, 0x9e, 0x71, 0xd8, 0x87, 0x9d, 0x01, 0xc1,
+	0x58, 0x77, 0xd9, 0xaf, 0xb1, 0x10, 0x7e, 0xdd,
+	0xa6, 0x50, 0x96, 0xe5, 0xf0, 0x72, 0x00, 0x6d,
+	0x4b, 0xf8, 0x2a, 0x8f, 0x19, 0xf3, 0x22, 0x88,
+	0x11, 0x4a, 0x8b, 0x7c, 0xfd, 0xb7, 0xed, 0xe1,
+	0xf6, 0x40, 0x39, 0xe0, 0xe9, 0xf6, 0x3d, 0x25,
+	0xe6, 0x74, 0x3c, 0x58, 0x57, 0x7f, 0xe1, 0x22,
+	0x96, 0x47, 0x31, 0x91, 0xba, 0x70, 0x85, 0x28,
+	0x6b, 0x9f, 0x6e, 0x25, 0xac, 0x23, 0x66, 0x2f,
+	0x29, 0x88, 0x28, 0xce, 0x8c, 0x5c, 0x88, 0x53,
+	0xd1, 0x3b, 0xcc, 0x6a, 0x51, 0xb2, 0xe1, 0x28,
+	0x3f, 0x91, 0xb4, 0x0d, 0x00, 0x3a, 0xe3, 0xf8,
+	0xc3, 0x8f, 0xd7, 0x96, 0x62, 0x0e, 0x2e, 0xfc,
+	0xc8, 0x6c, 0x77, 0xa6, 0x1d, 0x22, 0xc1, 0xb8,
+	0xe6, 0x61, 0xd7, 0x67, 0x36, 0x13, 0x7b, 0xbb,
+	0x9b, 0x59, 0x09, 0xa6, 0xdf, 0xf7, 0x6b, 0xa3,
+	0x40, 0x1a, 0xf5, 0x4f, 0xb4, 0xda, 0xd3, 0xf3,
+	0x81, 0x93, 0xc6, 0x18, 0xd9, 0x26, 0xee, 0xac,
+	0xf0, 0xaa, 0xdf, 0xc5, 0x9c, 0xca, 0xc2, 0xa2,
+	0xcc, 0x7b, 0x5c, 0x24, 0xb0, 0xbc, 0xd0, 0x6a,
+	0x4d, 0x89, 0x09, 0xb8, 0x07, 0xfe, 0x87, 0xad,
+	0x0a, 0xea, 0xb8, 0x42, 0xf9, 0x5e, 0xb3, 0x3e,
+	0x36, 0x4c, 0xaf, 0x75, 0x9e, 0x1c, 0xeb, 0xbd,
+	0xbc, 0xbb, 0x80, 0x40, 0xa7, 0x3a, 0x30, 0xbf,
+	0xa8, 0x44, 0xf4, 0xeb, 0x38, 0xad, 0x29, 0xba,
+	0x23, 0xed, 0x41, 0x0c, 0xea, 0xd2, 0xbb, 0x41,
+	0x18, 0xd6, 0xb9, 0xba, 0x65, 0x2b, 0xa3, 0x91,
+	0x6d, 0x1f, 0xa9, 0xf4, 0xd1, 0x25, 0x8d, 0x4d,
+	0x38, 0xff, 0x64, 0xa0, 0xec, 0xde, 0xa6, 0xb6,
+	0x79, 0xab, 0x8e, 0x33, 0x6c, 0x47, 0xde, 0xaf,
+	0x94, 0xa4, 0xa5, 0x86, 0x77, 0x55, 0x09, 0x92,
+	0x81, 0x31, 0x76, 0xc7, 0x34, 0x22, 0x89, 0x8e,
+	0x3d, 0x26, 0x26, 0xd7, 0xfc, 0x1e, 0x16, 0x72,
+	0x13, 0x33, 0x63, 0xd5, 0x22, 0xbe, 0xb8, 0x04,
+	0x34, 0x84, 0x41, 0xbb, 0x80, 0xd0, 0x9f, 0x46,
+	0x48, 0x07, 0xa7, 0xfc, 0x2b, 0x3a, 0x75, 0x55,
+	0x8c, 0xc7, 0x6a, 0xbd, 0x7e, 0x46, 0x08, 0x84,
+	0x0f, 0xd5, 0x74, 0xc0, 0x82, 0x8e, 0xaa, 0x61,
+	0x05, 0x01, 0xb2, 0x47, 0x6e, 0x20, 0x6a, 0x2d,
+	0x58, 0x70, 0x48, 0x32, 0xa7, 0x37, 0xd2, 0xb8,
+	0x82, 0x1a, 0x51, 0xb9, 0x61, 0xdd, 0xfd, 0x9d,
+	0x6b, 0x0e, 0x18, 0x97, 0xf8, 0x45, 0x5f, 0x87,
+	0x10, 0xcf, 0x34, 0x72, 0x45, 0x26, 0x49, 0x70,
+	0xe7, 0xa3, 0x78, 0xe0, 0x52, 0x89, 0x84, 0x94,
+	0x83, 0x82, 0xc2, 0x69, 0x8f, 0xe3, 0xe1, 0x3f,
+	0x60, 0x74, 0x88, 0xc4, 0xf7, 0x75, 0x2c, 0xfb,
+	0xbd, 0xb6, 0xc4, 0x7e, 0x10, 0x0a, 0x6c, 0x90,
+	0x04, 0x9e, 0xc3, 0x3f, 0x59, 0x7c, 0xce, 0x31,
+	0x18, 0x60, 0x57, 0x73, 0x46, 0x94, 0x7d, 0x06,
+	0xa0, 0x6d, 0x44, 0xec, 0xa2, 0x0a, 0x9e, 0x05,
+	0x15, 0xef, 0xca, 0x5c, 0xbf, 0x00, 0xeb, 0xf7,
+	0x3d, 0x32, 0xd4, 0xa5, 0xef, 0x49, 0x89, 0x5e,
+	0x46, 0xb0, 0xa6, 0x63, 0x5b, 0x8a, 0x73, 0xae,
+	0x6f, 0xd5, 0x9d, 0xf8, 0x4f, 0x40, 0xb5, 0xb2,
+	0x6e, 0xd3, 0xb6, 0x01, 0xa9, 0x26, 0xa2, 0x21,
+	0xcf, 0x33, 0x7a, 0x3a, 0xa4, 0x23, 0x13, 0xb0,
+	0x69, 0x6a, 0xee, 0xce, 0xd8, 0x9d, 0x01, 0x1d,
+	0x50, 0xc1, 0x30, 0x6c, 0xb1, 0xcd, 0xa0, 0xf0,
+	0xf0, 0xa2, 0x64, 0x6f, 0xbb, 0xbf, 0x5e, 0xe6,
+	0xab, 0x87, 0xb4, 0x0f, 0x4f, 0x15, 0xaf, 0xb5,
+	0x25, 0xa1, 0xb2, 0xd0, 0x80, 0x2c, 0xfb, 0xf9,
+	0xfe, 0xd2, 0x33, 0xbb, 0x76, 0xfe, 0x7c, 0xa8,
+	0x66, 0xf7, 0xe7, 0x85, 0x9f, 0x1f, 0x85, 0x57,
+	0x88, 0xe1, 0xe9, 0x63, 0xe4, 0xd8, 0x1c, 0xa1,
+	0xfb, 0xda, 0x44, 0x05, 0x2e, 0x1d, 0x3a, 0x1c,
+	0xff, 0xc8, 0x3b, 0xc0, 0xfe, 0xda, 0x22, 0x0b,
+	0x43, 0xd6, 0x88, 0x39, 0x4c, 0x4a, 0xa6, 0x69,
+	0x18, 0x93, 0x42, 0x4e, 0xb5, 0xcc, 0x66, 0x0d,
+	0x09, 0xf8, 0x1e, 0x7c, 0xd3, 0x3c, 0x99, 0x0d,
+	0x50, 0x1d, 0x62, 0xe9, 0x57, 0x06, 0xbf, 0x19,
+	0x88, 0xdd, 0xad, 0x7b, 0x4f, 0xf9, 0xc7, 0x82,
+	0x6d, 0x8d, 0xc8, 0xc4, 0xc5, 0x78, 0x17, 0x20,
+	0x15, 0xc5, 0x52, 0x41, 0xcf, 0x5b, 0xd6, 0x7f,
+	0x94, 0x02, 0x41, 0xe0, 0x40, 0x22, 0x03, 0x5e,
+	0xd1, 0x53, 0xd4, 0x86, 0xd3, 0x2c, 0x9f, 0x0f,
+	0x96, 0xe3, 0x6b, 0x9a, 0x76, 0x32, 0x06, 0x47,
+	0x4b, 0x11, 0xb3, 0xdd, 0x03, 0x65, 0xbd, 0x9b,
+	0x01, 0xda, 0x9c, 0xb9, 0x7e, 0x3f, 0x6a, 0xc4,
+	0x7b, 0xea, 0xd4, 0x3c, 0xb9, 0xfb, 0x5c, 0x6b,
+	0x64, 0x33, 0x52, 0xba, 0x64, 0x78, 0x8f, 0xa4,
+	0xaf, 0x7a, 0x61, 0x8d, 0xbc, 0xc5, 0x73, 0xe9,
+	0x6b, 0x58, 0x97, 0x4b, 0xbf, 0x63, 0x22, 0xd3,
+	0x37, 0x02, 0x54, 0xc5, 0xb9, 0x16, 0x4a, 0xf0,
+	0x19, 0xd8, 0x94, 0x57, 0xb8, 0x8a, 0xb3, 0x16,
+	0x3b, 0xd0, 0x84, 0x8e, 0x67, 0xa6, 0xa3, 0x7d,
+	0x78, 0xec, 0x00
+};
+static const u8 enc_output012[] __initconst = {
+	0x52, 0x34, 0xb3, 0x65, 0x3b, 0xb7, 0xe5, 0xd3,
+	0xab, 0x49, 0x17, 0x60, 0xd2, 0x52, 0x56, 0xdf,
+	0xdf, 0x34, 0x56, 0x82, 0xe2, 0xbe, 0xe5, 0xe1,
+	0x28, 0xd1, 0x4e, 0x5f, 0x4f, 0x01, 0x7d, 0x3f,
+	0x99, 0x6b, 0x30, 0x6e, 0x1a, 0x7c, 0x4c, 0x8e,
+	0x62, 0x81, 0xae, 0x86, 0x3f, 0x6b, 0xd0, 0xb5,
+	0xa9, 0xcf, 0x50, 0xf1, 0x02, 0x12, 0xa0, 0x0b,
+	0x24, 0xe9, 0xe6, 0x72, 0x89, 0x2c, 0x52, 0x1b,
+	0x34, 0x38, 0xf8, 0x75, 0x5f, 0xa0, 0x74, 0xe2,
+	0x99, 0xdd, 0xa6, 0x4b, 0x14, 0x50, 0x4e, 0xf1,
+	0xbe, 0xd6, 0x9e, 0xdb, 0xb2, 0x24, 0x27, 0x74,
+	0x12, 0x4a, 0x78, 0x78, 0x17, 0xa5, 0x58, 0x8e,
+	0x2f, 0xf9, 0xf4, 0x8d, 0xee, 0x03, 0x88, 0xae,
+	0xb8, 0x29, 0xa1, 0x2f, 0x4b, 0xee, 0x92, 0xbd,
+	0x87, 0xb3, 0xce, 0x34, 0x21, 0x57, 0x46, 0x04,
+	0x49, 0x0c, 0x80, 0xf2, 0x01, 0x13, 0xa1, 0x55,
+	0xb3, 0xff, 0x44, 0x30, 0x3c, 0x1c, 0xd0, 0xef,
+	0xbc, 0x18, 0x74, 0x26, 0xad, 0x41, 0x5b, 0x5b,
+	0x3e, 0x9a, 0x7a, 0x46, 0x4f, 0x16, 0xd6, 0x74,
+	0x5a, 0xb7, 0x3a, 0x28, 0x31, 0xd8, 0xae, 0x26,
+	0xac, 0x50, 0x53, 0x86, 0xf2, 0x56, 0xd7, 0x3f,
+	0x29, 0xbc, 0x45, 0x68, 0x8e, 0xcb, 0x98, 0x64,
+	0xdd, 0xc9, 0xba, 0xb8, 0x4b, 0x7b, 0x82, 0xdd,
+	0x14, 0xa7, 0xcb, 0x71, 0x72, 0x00, 0x5c, 0xad,
+	0x7b, 0x6a, 0x89, 0xa4, 0x3d, 0xbf, 0xb5, 0x4b,
+	0x3e, 0x7c, 0x5a, 0xcf, 0xb8, 0xa1, 0xc5, 0x6e,
+	0xc8, 0xb6, 0x31, 0x57, 0x7b, 0xdf, 0xa5, 0x7e,
+	0xb1, 0xd6, 0x42, 0x2a, 0x31, 0x36, 0xd1, 0xd0,
+	0x3f, 0x7a, 0xe5, 0x94, 0xd6, 0x36, 0xa0, 0x6f,
+	0xb7, 0x40, 0x7d, 0x37, 0xc6, 0x55, 0x7c, 0x50,
+	0x40, 0x6d, 0x29, 0x89, 0xe3, 0x5a, 0xae, 0x97,
+	0xe7, 0x44, 0x49, 0x6e, 0xbd, 0x81, 0x3d, 0x03,
+	0x93, 0x06, 0x12, 0x06, 0xe2, 0x41, 0x12, 0x4a,
+	0xf1, 0x6a, 0xa4, 0x58, 0xa2, 0xfb, 0xd2, 0x15,
+	0xba, 0xc9, 0x79, 0xc9, 0xce, 0x5e, 0x13, 0xbb,
+	0xf1, 0x09, 0x04, 0xcc, 0xfd, 0xe8, 0x51, 0x34,
+	0x6a, 0xe8, 0x61, 0x88, 0xda, 0xed, 0x01, 0x47,
+	0x84, 0xf5, 0x73, 0x25, 0xf9, 0x1c, 0x42, 0x86,
+	0x07, 0xf3, 0x5b, 0x1a, 0x01, 0xb3, 0xeb, 0x24,
+	0x32, 0x8d, 0xf6, 0xed, 0x7c, 0x4b, 0xeb, 0x3c,
+	0x36, 0x42, 0x28, 0xdf, 0xdf, 0xb6, 0xbe, 0xd9,
+	0x8c, 0x52, 0xd3, 0x2b, 0x08, 0x90, 0x8c, 0xe7,
+	0x98, 0x31, 0xe2, 0x32, 0x8e, 0xfc, 0x11, 0x48,
+	0x00, 0xa8, 0x6a, 0x42, 0x4a, 0x02, 0xc6, 0x4b,
+	0x09, 0xf1, 0xe3, 0x49, 0xf3, 0x45, 0x1f, 0x0e,
+	0xbc, 0x56, 0xe2, 0xe4, 0xdf, 0xfb, 0xeb, 0x61,
+	0xfa, 0x24, 0xc1, 0x63, 0x75, 0xbb, 0x47, 0x75,
+	0xaf, 0xe1, 0x53, 0x16, 0x96, 0x21, 0x85, 0x26,
+	0x11, 0xb3, 0x76, 0xe3, 0x23, 0xa1, 0x6b, 0x74,
+	0x37, 0xd0, 0xde, 0x06, 0x90, 0x71, 0x5d, 0x43,
+	0x88, 0x9b, 0x00, 0x54, 0xa6, 0x75, 0x2f, 0xa1,
+	0xc2, 0x0b, 0x73, 0x20, 0x1d, 0xb6, 0x21, 0x79,
+	0x57, 0x3f, 0xfa, 0x09, 0xbe, 0x8a, 0x33, 0xc3,
+	0x52, 0xf0, 0x1d, 0x82, 0x31, 0xd1, 0x55, 0xb5,
+	0x6c, 0x99, 0x25, 0xcf, 0x5c, 0x32, 0xce, 0xe9,
+	0x0d, 0xfa, 0x69, 0x2c, 0xd5, 0x0d, 0xc5, 0x6d,
+	0x86, 0xd0, 0x0c, 0x3b, 0x06, 0x50, 0x79, 0xe8,
+	0xc3, 0xae, 0x04, 0xe6, 0xcd, 0x51, 0xe4, 0x26,
+	0x9b, 0x4f, 0x7e, 0xa6, 0x0f, 0xab, 0xd8, 0xe5,
+	0xde, 0xa9, 0x00, 0x95, 0xbe, 0xa3, 0x9d, 0x5d,
+	0xb2, 0x09, 0x70, 0x18, 0x1c, 0xf0, 0xac, 0x29,
+	0x23, 0x02, 0x29, 0x28, 0xd2, 0x74, 0x35, 0x57,
+	0x62, 0x0f, 0x24, 0xea, 0x5e, 0x33, 0xc2, 0x92,
+	0xf3, 0x78, 0x4d, 0x30, 0x1e, 0xa1, 0x99, 0xa9,
+	0x82, 0xb0, 0x42, 0x31, 0x8d, 0xad, 0x8a, 0xbc,
+	0xfc, 0xd4, 0x57, 0x47, 0x3e, 0xb4, 0x50, 0xdd,
+	0x6e, 0x2c, 0x80, 0x4d, 0x22, 0xf1, 0xfb, 0x57,
+	0xc4, 0xdd, 0x17, 0xe1, 0x8a, 0x36, 0x4a, 0xb3,
+	0x37, 0xca, 0xc9, 0x4e, 0xab, 0xd5, 0x69, 0xc4,
+	0xf4, 0xbc, 0x0b, 0x3b, 0x44, 0x4b, 0x29, 0x9c,
+	0xee, 0xd4, 0x35, 0x22, 0x21, 0xb0, 0x1f, 0x27,
+	0x64, 0xa8, 0x51, 0x1b, 0xf0, 0x9f, 0x19, 0x5c,
+	0xfb, 0x5a, 0x64, 0x74, 0x70, 0x45, 0x09, 0xf5,
+	0x64, 0xfe, 0x1a, 0x2d, 0xc9, 0x14, 0x04, 0x14,
+	0xcf, 0xd5, 0x7d, 0x60, 0xaf, 0x94, 0x39, 0x94,
+	0xe2, 0x7d, 0x79, 0x82, 0xd0, 0x65, 0x3b, 0x6b,
+	0x9c, 0x19, 0x84, 0xb4, 0x6d, 0xb3, 0x0c, 0x99,
+	0xc0, 0x56, 0xa8, 0xbd, 0x73, 0xce, 0x05, 0x84,
+	0x3e, 0x30, 0xaa, 0xc4, 0x9b, 0x1b, 0x04, 0x2a,
+	0x9f, 0xd7, 0x43, 0x2b, 0x23, 0xdf, 0xbf, 0xaa,
+	0xd5, 0xc2, 0x43, 0x2d, 0x70, 0xab, 0xdc, 0x75,
+	0xad, 0xac, 0xf7, 0xc0, 0xbe, 0x67, 0xb2, 0x74,
+	0xed, 0x67, 0x10, 0x4a, 0x92, 0x60, 0xc1, 0x40,
+	0x50, 0x19, 0x8a, 0x8a, 0x8c, 0x09, 0x0e, 0x72,
+	0xe1, 0x73, 0x5e, 0xe8, 0x41, 0x85, 0x63, 0x9f,
+	0x3f, 0xd7, 0x7d, 0xc4, 0xfb, 0x22, 0x5d, 0x92,
+	0x6c, 0xb3, 0x1e, 0xe2, 0x50, 0x2f, 0x82, 0xa8,
+	0x28, 0xc0, 0xb5, 0xd7, 0x5f, 0x68, 0x0d, 0x2c,
+	0x2d, 0xaf, 0x7e, 0xfa, 0x2e, 0x08, 0x0f, 0x1f,
+	0x70, 0x9f, 0xe9, 0x19, 0x72, 0x55, 0xf8, 0xfb,
+	0x51, 0xd2, 0x33, 0x5d, 0xa0, 0xd3, 0x2b, 0x0a,
+	0x6c, 0xbc, 0x4e, 0xcf, 0x36, 0x4d, 0xdc, 0x3b,
+	0xe9, 0x3e, 0x81, 0x7c, 0x61, 0xdb, 0x20, 0x2d,
+	0x3a, 0xc3, 0xb3, 0x0c, 0x1e, 0x00, 0xb9, 0x7c,
+	0xf5, 0xca, 0x10, 0x5f, 0x3a, 0x71, 0xb3, 0xe4,
+	0x20, 0xdb, 0x0c, 0x2a, 0x98, 0x63, 0x45, 0x00,
+	0x58, 0xf6, 0x68, 0xe4, 0x0b, 0xda, 0x13, 0x3b,
+	0x60, 0x5c, 0x76, 0xdb, 0xb9, 0x97, 0x71, 0xe4,
+	0xd9, 0xb7, 0xdb, 0xbd, 0x68, 0xc7, 0x84, 0x84,
+	0xaa, 0x7c, 0x68, 0x62, 0x5e, 0x16, 0xfc, 0xba,
+	0x72, 0xaa, 0x9a, 0xa9, 0xeb, 0x7c, 0x75, 0x47,
+	0x97, 0x7e, 0xad, 0xe2, 0xd9, 0x91, 0xe8, 0xe4,
+	0xa5, 0x31, 0xd7, 0x01, 0x8e, 0xa2, 0x11, 0x88,
+	0x95, 0xb9, 0xf2, 0x9b, 0xd3, 0x7f, 0x1b, 0x81,
+	0x22, 0xf7, 0x98, 0x60, 0x0a, 0x64, 0xa6, 0xc1,
+	0xf6, 0x49, 0xc7, 0xe3, 0x07, 0x4d, 0x94, 0x7a,
+	0xcf, 0x6e, 0x68, 0x0c, 0x1b, 0x3f, 0x6e, 0x2e,
+	0xee, 0x92, 0xfa, 0x52, 0xb3, 0x59, 0xf8, 0xf1,
+	0x8f, 0x6a, 0x66, 0xa3, 0x82, 0x76, 0x4a, 0x07,
+	0x1a, 0xc7, 0xdd, 0xf5, 0xda, 0x9c, 0x3c, 0x24,
+	0xbf, 0xfd, 0x42, 0xa1, 0x10, 0x64, 0x6a, 0x0f,
+	0x89, 0xee, 0x36, 0xa5, 0xce, 0x99, 0x48, 0x6a,
+	0xf0, 0x9f, 0x9e, 0x69, 0xa4, 0x40, 0x20, 0xe9,
+	0x16, 0x15, 0xf7, 0xdb, 0x75, 0x02, 0xcb, 0xe9,
+	0x73, 0x8b, 0x3b, 0x49, 0x2f, 0xf0, 0xaf, 0x51,
+	0x06, 0x5c, 0xdf, 0x27, 0x27, 0x49, 0x6a, 0xd1,
+	0xcc, 0xc7, 0xb5, 0x63, 0xb5, 0xfc, 0xb8, 0x5c,
+	0x87, 0x7f, 0x84, 0xb4, 0xcc, 0x14, 0xa9, 0x53,
+	0xda, 0xa4, 0x56, 0xf8, 0xb6, 0x1b, 0xcc, 0x40,
+	0x27, 0x52, 0x06, 0x5a, 0x13, 0x81, 0xd7, 0x3a,
+	0xd4, 0x3b, 0xfb, 0x49, 0x65, 0x31, 0x33, 0xb2,
+	0xfa, 0xcd, 0xad, 0x58, 0x4e, 0x2b, 0xae, 0xd2,
+	0x20, 0xfb, 0x1a, 0x48, 0xb4, 0x3f, 0x9a, 0xd8,
+	0x7a, 0x35, 0x4a, 0xc8, 0xee, 0x88, 0x5e, 0x07,
+	0x66, 0x54, 0xb9, 0xec, 0x9f, 0xa3, 0xe3, 0xb9,
+	0x37, 0xaa, 0x49, 0x76, 0x31, 0xda, 0x74, 0x2d,
+	0x3c, 0xa4, 0x65, 0x10, 0x32, 0x38, 0xf0, 0xde,
+	0xd3, 0x99, 0x17, 0xaa, 0x71, 0xaa, 0x8f, 0x0f,
+	0x8c, 0xaf, 0xa2, 0xf8, 0x5d, 0x64, 0xba, 0x1d,
+	0xa3, 0xef, 0x96, 0x73, 0xe8, 0xa1, 0x02, 0x8d,
+	0x0c, 0x6d, 0xb8, 0x06, 0x90, 0xb8, 0x08, 0x56,
+	0x2c, 0xa7, 0x06, 0xc9, 0xc2, 0x38, 0xdb, 0x7c,
+	0x63, 0xb1, 0x57, 0x8e, 0xea, 0x7c, 0x79, 0xf3,
+	0x49, 0x1d, 0xfe, 0x9f, 0xf3, 0x6e, 0xb1, 0x1d,
+	0xba, 0x19, 0x80, 0x1a, 0x0a, 0xd3, 0xb0, 0x26,
+	0x21, 0x40, 0xb1, 0x7c, 0xf9, 0x4d, 0x8d, 0x10,
+	0xc1, 0x7e, 0xf4, 0xf6, 0x3c, 0xa8, 0xfd, 0x7c,
+	0xa3, 0x92, 0xb2, 0x0f, 0xaa, 0xcc, 0xa6, 0x11,
+	0xfe, 0x04, 0xe3, 0xd1, 0x7a, 0x32, 0x89, 0xdf,
+	0x0d, 0xc4, 0x8f, 0x79, 0x6b, 0xca, 0x16, 0x7c,
+	0x6e, 0xf9, 0xad, 0x0f, 0xf6, 0xfe, 0x27, 0xdb,
+	0xc4, 0x13, 0x70, 0xf1, 0x62, 0x1a, 0x4f, 0x79,
+	0x40, 0xc9, 0x9b, 0x8b, 0x21, 0xea, 0x84, 0xfa,
+	0xf5, 0xf1, 0x89, 0xce, 0xb7, 0x55, 0x0a, 0x80,
+	0x39, 0x2f, 0x55, 0x36, 0x16, 0x9c, 0x7b, 0x08,
+	0xbd, 0x87, 0x0d, 0xa5, 0x32, 0xf1, 0x52, 0x7c,
+	0xe8, 0x55, 0x60, 0x5b, 0xd7, 0x69, 0xe4, 0xfc,
+	0xfa, 0x12, 0x85, 0x96, 0xea, 0x50, 0x28, 0xab,
+	0x8a, 0xf7, 0xbb, 0x0e, 0x53, 0x74, 0xca, 0xa6,
+	0x27, 0x09, 0xc2, 0xb5, 0xde, 0x18, 0x14, 0xd9,
+	0xea, 0xe5, 0x29, 0x1c, 0x40, 0x56, 0xcf, 0xd7,
+	0xae, 0x05, 0x3f, 0x65, 0xaf, 0x05, 0x73, 0xe2,
+	0x35, 0x96, 0x27, 0x07, 0x14, 0xc0, 0xad, 0x33,
+	0xf1, 0xdc, 0x44, 0x7a, 0x89, 0x17, 0x77, 0xd2,
+	0x9c, 0x58, 0x60, 0xf0, 0x3f, 0x7b, 0x2d, 0x2e,
+	0x57, 0x95, 0x54, 0x87, 0xed, 0xf2, 0xc7, 0x4c,
+	0xf0, 0xae, 0x56, 0x29, 0x19, 0x7d, 0x66, 0x4b,
+	0x9b, 0x83, 0x84, 0x42, 0x3b, 0x01, 0x25, 0x66,
+	0x8e, 0x02, 0xde, 0xb9, 0x83, 0x54, 0x19, 0xf6,
+	0x9f, 0x79, 0x0d, 0x67, 0xc5, 0x1d, 0x7a, 0x44,
+	0x02, 0x98, 0xa7, 0x16, 0x1c, 0x29, 0x0d, 0x74,
+	0xff, 0x85, 0x40, 0x06, 0xef, 0x2c, 0xa9, 0xc6,
+	0xf5, 0x53, 0x07, 0x06, 0xae, 0xe4, 0xfa, 0x5f,
+	0xd8, 0x39, 0x4d, 0xf1, 0x9b, 0x6b, 0xd9, 0x24,
+	0x84, 0xfe, 0x03, 0x4c, 0xb2, 0x3f, 0xdf, 0xa1,
+	0x05, 0x9e, 0x50, 0x14, 0x5a, 0xd9, 0x1a, 0xa2,
+	0xa7, 0xfa, 0xfa, 0x17, 0xf7, 0x78, 0xd6, 0xb5,
+	0x92, 0x61, 0x91, 0xac, 0x36, 0xfa, 0x56, 0x0d,
+	0x38, 0x32, 0x18, 0x85, 0x08, 0x58, 0x37, 0xf0,
+	0x4b, 0xdb, 0x59, 0xe7, 0xa4, 0x34, 0xc0, 0x1b,
+	0x01, 0xaf, 0x2d, 0xde, 0xa1, 0xaa, 0x5d, 0xd3,
+	0xec, 0xe1, 0xd4, 0xf7, 0xe6, 0x54, 0x68, 0xf0,
+	0x51, 0x97, 0xa7, 0x89, 0xea, 0x24, 0xad, 0xd3,
+	0x6e, 0x47, 0x93, 0x8b, 0x4b, 0xb4, 0xf7, 0x1c,
+	0x42, 0x06, 0x67, 0xe8, 0x99, 0xf6, 0xf5, 0x7b,
+	0x85, 0xb5, 0x65, 0xb5, 0xb5, 0xd2, 0x37, 0xf5,
+	0xf3, 0x02, 0xa6, 0x4d, 0x11, 0xa7, 0xdc, 0x51,
+	0x09, 0x7f, 0xa0, 0xd8, 0x88, 0x1c, 0x13, 0x71,
+	0xae, 0x9c, 0xb7, 0x7b, 0x34, 0xd6, 0x4e, 0x68,
+	0x26, 0x83, 0x51, 0xaf, 0x1d, 0xee, 0x8b, 0xbb,
+	0x69, 0x43, 0x2b, 0x9e, 0x8a, 0xbc, 0x02, 0x0e,
+	0xa0, 0x1b, 0xe0, 0xa8, 0x5f, 0x6f, 0xaf, 0x1b,
+	0x8f, 0xe7, 0x64, 0x71, 0x74, 0x11, 0x7e, 0xa8,
+	0xd8, 0xf9, 0x97, 0x06, 0xc3, 0xb6, 0xfb, 0xfb,
+	0xb7, 0x3d, 0x35, 0x9d, 0x3b, 0x52, 0xed, 0x54,
+	0xca, 0xf4, 0x81, 0x01, 0x2d, 0x1b, 0xc3, 0xa7,
+	0x00, 0x3d, 0x1a, 0x39, 0x54, 0xe1, 0xf6, 0xff,
+	0xed, 0x6f, 0x0b, 0x5a, 0x68, 0xda, 0x58, 0xdd,
+	0xa9, 0xcf, 0x5c, 0x4a, 0xe5, 0x09, 0x4e, 0xde,
+	0x9d, 0xbc, 0x3e, 0xee, 0x5a, 0x00, 0x3b, 0x2c,
+	0x87, 0x10, 0x65, 0x60, 0xdd, 0xd7, 0x56, 0xd1,
+	0x4c, 0x64, 0x45, 0xe4, 0x21, 0xec, 0x78, 0xf8,
+	0x25, 0x7a, 0x3e, 0x16, 0x5d, 0x09, 0x53, 0x14,
+	0xbe, 0x4f, 0xae, 0x87, 0xd8, 0xd1, 0xaa, 0x3c,
+	0xf6, 0x3e, 0xa4, 0x70, 0x8c, 0x5e, 0x70, 0xa4,
+	0xb3, 0x6b, 0x66, 0x73, 0xd3, 0xbf, 0x31, 0x06,
+	0x19, 0x62, 0x93, 0x15, 0xf2, 0x86, 0xe4, 0x52,
+	0x7e, 0x53, 0x4c, 0x12, 0x38, 0xcc, 0x34, 0x7d,
+	0x57, 0xf6, 0x42, 0x93, 0x8a, 0xc4, 0xee, 0x5c,
+	0x8a, 0xe1, 0x52, 0x8f, 0x56, 0x64, 0xf6, 0xa6,
+	0xd1, 0x91, 0x57, 0x70, 0xcd, 0x11, 0x76, 0xf5,
+	0x59, 0x60, 0x60, 0x3c, 0xc1, 0xc3, 0x0b, 0x7f,
+	0x58, 0x1a, 0x50, 0x91, 0xf1, 0x68, 0x8f, 0x6e,
+	0x74, 0x74, 0xa8, 0x51, 0x0b, 0xf7, 0x7a, 0x98,
+	0x37, 0xf2, 0x0a, 0x0e, 0xa4, 0x97, 0x04, 0xb8,
+	0x9b, 0xfd, 0xa0, 0xea, 0xf7, 0x0d, 0xe1, 0xdb,
+	0x03, 0xf0, 0x31, 0x29, 0xf8, 0xdd, 0x6b, 0x8b,
+	0x5d, 0xd8, 0x59, 0xa9, 0x29, 0xcf, 0x9a, 0x79,
+	0x89, 0x19, 0x63, 0x46, 0x09, 0x79, 0x6a, 0x11,
+	0xda, 0x63, 0x68, 0x48, 0x77, 0x23, 0xfb, 0x7d,
+	0x3a, 0x43, 0xcb, 0x02, 0x3b, 0x7a, 0x6d, 0x10,
+	0x2a, 0x9e, 0xac, 0xf1, 0xd4, 0x19, 0xf8, 0x23,
+	0x64, 0x1d, 0x2c, 0x5f, 0xf2, 0xb0, 0x5c, 0x23,
+	0x27, 0xf7, 0x27, 0x30, 0x16, 0x37, 0xb1, 0x90,
+	0xab, 0x38, 0xfb, 0x55, 0xcd, 0x78, 0x58, 0xd4,
+	0x7d, 0x43, 0xf6, 0x45, 0x5e, 0x55, 0x8d, 0xb1,
+	0x02, 0x65, 0x58, 0xb4, 0x13, 0x4b, 0x36, 0xf7,
+	0xcc, 0xfe, 0x3d, 0x0b, 0x82, 0xe2, 0x12, 0x11,
+	0xbb, 0xe6, 0xb8, 0x3a, 0x48, 0x71, 0xc7, 0x50,
+	0x06, 0x16, 0x3a, 0xe6, 0x7c, 0x05, 0xc7, 0xc8,
+	0x4d, 0x2f, 0x08, 0x6a, 0x17, 0x9a, 0x95, 0x97,
+	0x50, 0x68, 0xdc, 0x28, 0x18, 0xc4, 0x61, 0x38,
+	0xb9, 0xe0, 0x3e, 0x78, 0xdb, 0x29, 0xe0, 0x9f,
+	0x52, 0xdd, 0xf8, 0x4f, 0x91, 0xc1, 0xd0, 0x33,
+	0xa1, 0x7a, 0x8e, 0x30, 0x13, 0x82, 0x07, 0x9f,
+	0xd3, 0x31, 0x0f, 0x23, 0xbe, 0x32, 0x5a, 0x75,
+	0xcf, 0x96, 0xb2, 0xec, 0xb5, 0x32, 0xac, 0x21,
+	0xd1, 0x82, 0x33, 0xd3, 0x15, 0x74, 0xbd, 0x90,
+	0xf1, 0x2c, 0xe6, 0x5f, 0x8d, 0xe3, 0x02, 0xe8,
+	0xe9, 0xc4, 0xca, 0x96, 0xeb, 0x0e, 0xbc, 0x91,
+	0xf4, 0xb9, 0xea, 0xd9, 0x1b, 0x75, 0xbd, 0xe1,
+	0xac, 0x2a, 0x05, 0x37, 0x52, 0x9b, 0x1b, 0x3f,
+	0x5a, 0xdc, 0x21, 0xc3, 0x98, 0xbb, 0xaf, 0xa3,
+	0xf2, 0x00, 0xbf, 0x0d, 0x30, 0x89, 0x05, 0xcc,
+	0xa5, 0x76, 0xf5, 0x06, 0xf0, 0xc6, 0x54, 0x8a,
+	0x5d, 0xd4, 0x1e, 0xc1, 0xf2, 0xce, 0xb0, 0x62,
+	0xc8, 0xfc, 0x59, 0x42, 0x9a, 0x90, 0x60, 0x55,
+	0xfe, 0x88, 0xa5, 0x8b, 0xb8, 0x33, 0x0c, 0x23,
+	0x24, 0x0d, 0x15, 0x70, 0x37, 0x1e, 0x3d, 0xf6,
+	0xd2, 0xea, 0x92, 0x10, 0xb2, 0xc4, 0x51, 0xac,
+	0xf2, 0xac, 0xf3, 0x6b, 0x6c, 0xaa, 0xcf, 0x12,
+	0xc5, 0x6c, 0x90, 0x50, 0xb5, 0x0c, 0xfc, 0x1a,
+	0x15, 0x52, 0xe9, 0x26, 0xc6, 0x52, 0xa4, 0xe7,
+	0x81, 0x69, 0xe1, 0xe7, 0x9e, 0x30, 0x01, 0xec,
+	0x84, 0x89, 0xb2, 0x0d, 0x66, 0xdd, 0xce, 0x28,
+	0x5c, 0xec, 0x98, 0x46, 0x68, 0x21, 0x9f, 0x88,
+	0x3f, 0x1f, 0x42, 0x77, 0xce, 0xd0, 0x61, 0xd4,
+	0x20, 0xa7, 0xff, 0x53, 0xad, 0x37, 0xd0, 0x17,
+	0x35, 0xc9, 0xfc, 0xba, 0x0a, 0x78, 0x3f, 0xf2,
+	0xcc, 0x86, 0x89, 0xe8, 0x4b, 0x3c, 0x48, 0x33,
+	0x09, 0x7f, 0xc6, 0xc0, 0xdd, 0xb8, 0xfd, 0x7a,
+	0x66, 0x66, 0x65, 0xeb, 0x47, 0xa7, 0x04, 0x28,
+	0xa3, 0x19, 0x8e, 0xa9, 0xb1, 0x13, 0x67, 0x62,
+	0x70, 0xcf, 0xd6
+};
+static const u8 enc_assoc012[] __initconst = {
+	0xb1, 0x69, 0x83, 0x87, 0x30, 0xaa, 0x5d, 0xb8,
+	0x77, 0xe8, 0x21, 0xff, 0x06, 0x59, 0x35, 0xce,
+	0x75, 0xfe, 0x38, 0xef, 0xb8, 0x91, 0x43, 0x8c,
+	0xcf, 0x70, 0xdd, 0x0a, 0x68, 0xbf, 0xd4, 0xbc,
+	0x16, 0x76, 0x99, 0x36, 0x1e, 0x58, 0x79, 0x5e,
+	0xd4, 0x29, 0xf7, 0x33, 0x93, 0x48, 0xdb, 0x5f,
+	0x01, 0xae, 0x9c, 0xb6, 0xe4, 0x88, 0x6d, 0x2b,
+	0x76, 0x75, 0xe0, 0xf3, 0x74, 0xe2, 0xc9
+};
+static const u8 enc_nonce012[] __initconst = {
+	0x05, 0xa3, 0x93, 0xed, 0x30, 0xc5, 0xa2, 0x06
+};
+static const u8 enc_key012[] __initconst = {
+	0xb3, 0x35, 0x50, 0x03, 0x54, 0x2e, 0x40, 0x5e,
+	0x8f, 0x59, 0x8e, 0xc5, 0x90, 0xd5, 0x27, 0x2d,
+	0xba, 0x29, 0x2e, 0xcb, 0x1b, 0x70, 0x44, 0x1e,
+	0x65, 0x91, 0x6e, 0x2a, 0x79, 0x22, 0xda, 0x64
+};
+
+/* wycheproof - misc */
+static const u8 enc_input053[] __initconst = {
+	0x25, 0x6d, 0x40, 0x88, 0x80, 0x94, 0x17, 0x83,
+	0x55, 0xd3, 0x04, 0x84, 0x64, 0x43, 0xfe, 0xe8,
+	0xdf, 0x99, 0x47, 0x03, 0x03, 0xfb, 0x3b, 0x7b,
+	0x80, 0xe0, 0x30, 0xbe, 0xeb, 0xd3, 0x29, 0xbe
+};
+static const u8 enc_output053[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0xe6, 0xd3, 0xd7, 0x32, 0x4a, 0x1c, 0xbb, 0xa7,
+	0x77, 0xbb, 0xb0, 0xec, 0xdd, 0xa3, 0x78, 0x07
+};
+static const u8 enc_assoc053[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
+};
+static const u8 enc_nonce053[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key053[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input054[] __initconst = {
+	0x25, 0x6d, 0x40, 0x88, 0x80, 0x94, 0x17, 0x83,
+	0x55, 0xd3, 0x04, 0x84, 0x64, 0x43, 0xfe, 0xe8,
+	0xdf, 0x99, 0x47, 0x03, 0x03, 0xfb, 0x3b, 0x7b,
+	0x80, 0xe0, 0x30, 0xbe, 0xeb, 0xd3, 0x29, 0xbe,
+	0xe3, 0xbc, 0xdb, 0x5b, 0x1e, 0xde, 0xfc, 0xfe,
+	0x8b, 0xcd, 0xa1, 0xb6, 0xa1, 0x5c, 0x8c, 0x2b,
+	0x08, 0x69, 0xff, 0xd2, 0xec, 0x5e, 0x26, 0xe5,
+	0x53, 0xb7, 0xb2, 0x27, 0xfe, 0x87, 0xfd, 0xbd
+};
+static const u8 enc_output054[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x06, 0x2d, 0xe6, 0x79, 0x5f, 0x27, 0x4f, 0xd2,
+	0xa3, 0x05, 0xd7, 0x69, 0x80, 0xbc, 0x9c, 0xce
+};
+static const u8 enc_assoc054[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
+};
+static const u8 enc_nonce054[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key054[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input055[] __initconst = {
+	0x25, 0x6d, 0x40, 0x88, 0x80, 0x94, 0x17, 0x83,
+	0x55, 0xd3, 0x04, 0x84, 0x64, 0x43, 0xfe, 0xe8,
+	0xdf, 0x99, 0x47, 0x03, 0x03, 0xfb, 0x3b, 0x7b,
+	0x80, 0xe0, 0x30, 0xbe, 0xeb, 0xd3, 0x29, 0xbe,
+	0xe3, 0xbc, 0xdb, 0x5b, 0x1e, 0xde, 0xfc, 0xfe,
+	0x8b, 0xcd, 0xa1, 0xb6, 0xa1, 0x5c, 0x8c, 0x2b,
+	0x08, 0x69, 0xff, 0xd2, 0xec, 0x5e, 0x26, 0xe5,
+	0x53, 0xb7, 0xb2, 0x27, 0xfe, 0x87, 0xfd, 0xbd,
+	0x7a, 0xda, 0x44, 0x42, 0x42, 0x69, 0xbf, 0xfa,
+	0x55, 0x27, 0xf2, 0x70, 0xac, 0xf6, 0x85, 0x02,
+	0xb7, 0x4c, 0x5a, 0xe2, 0xe6, 0x0c, 0x05, 0x80,
+	0x98, 0x1a, 0x49, 0x38, 0x45, 0x93, 0x92, 0xc4,
+	0x9b, 0xb2, 0xf2, 0x84, 0xb6, 0x46, 0xef, 0xc7,
+	0xf3, 0xf0, 0xb1, 0x36, 0x1d, 0xc3, 0x48, 0xed,
+	0x77, 0xd3, 0x0b, 0xc5, 0x76, 0x92, 0xed, 0x38,
+	0xfb, 0xac, 0x01, 0x88, 0x38, 0x04, 0x88, 0xc7
+};
+static const u8 enc_output055[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0xd8, 0xb4, 0x79, 0x02, 0xba, 0xae, 0xaf, 0xb3,
+	0x42, 0x03, 0x05, 0x15, 0x29, 0xaf, 0x28, 0x2e
+};
+static const u8 enc_assoc055[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
+};
+static const u8 enc_nonce055[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key055[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input056[] __initconst = {
+	0xda, 0x92, 0xbf, 0x77, 0x7f, 0x6b, 0xe8, 0x7c,
+	0xaa, 0x2c, 0xfb, 0x7b, 0x9b, 0xbc, 0x01, 0x17,
+	0x20, 0x66, 0xb8, 0xfc, 0xfc, 0x04, 0xc4, 0x84,
+	0x7f, 0x1f, 0xcf, 0x41, 0x14, 0x2c, 0xd6, 0x41
+};
+static const u8 enc_output056[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xb3, 0x89, 0x1c, 0x84, 0x9c, 0xb5, 0x2c, 0x27,
+	0x74, 0x7e, 0xdf, 0xcf, 0x31, 0x21, 0x3b, 0xb6
+};
+static const u8 enc_assoc056[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce056[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key056[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input057[] __initconst = {
+	0xda, 0x92, 0xbf, 0x77, 0x7f, 0x6b, 0xe8, 0x7c,
+	0xaa, 0x2c, 0xfb, 0x7b, 0x9b, 0xbc, 0x01, 0x17,
+	0x20, 0x66, 0xb8, 0xfc, 0xfc, 0x04, 0xc4, 0x84,
+	0x7f, 0x1f, 0xcf, 0x41, 0x14, 0x2c, 0xd6, 0x41,
+	0x1c, 0x43, 0x24, 0xa4, 0xe1, 0x21, 0x03, 0x01,
+	0x74, 0x32, 0x5e, 0x49, 0x5e, 0xa3, 0x73, 0xd4,
+	0xf7, 0x96, 0x00, 0x2d, 0x13, 0xa1, 0xd9, 0x1a,
+	0xac, 0x48, 0x4d, 0xd8, 0x01, 0x78, 0x02, 0x42
+};
+static const u8 enc_output057[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xf0, 0xc1, 0x2d, 0x26, 0xef, 0x03, 0x02, 0x9b,
+	0x62, 0xc0, 0x08, 0xda, 0x27, 0xc5, 0xdc, 0x68
+};
+static const u8 enc_assoc057[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce057[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key057[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input058[] __initconst = {
+	0xda, 0x92, 0xbf, 0x77, 0x7f, 0x6b, 0xe8, 0x7c,
+	0xaa, 0x2c, 0xfb, 0x7b, 0x9b, 0xbc, 0x01, 0x17,
+	0x20, 0x66, 0xb8, 0xfc, 0xfc, 0x04, 0xc4, 0x84,
+	0x7f, 0x1f, 0xcf, 0x41, 0x14, 0x2c, 0xd6, 0x41,
+	0x1c, 0x43, 0x24, 0xa4, 0xe1, 0x21, 0x03, 0x01,
+	0x74, 0x32, 0x5e, 0x49, 0x5e, 0xa3, 0x73, 0xd4,
+	0xf7, 0x96, 0x00, 0x2d, 0x13, 0xa1, 0xd9, 0x1a,
+	0xac, 0x48, 0x4d, 0xd8, 0x01, 0x78, 0x02, 0x42,
+	0x85, 0x25, 0xbb, 0xbd, 0xbd, 0x96, 0x40, 0x05,
+	0xaa, 0xd8, 0x0d, 0x8f, 0x53, 0x09, 0x7a, 0xfd,
+	0x48, 0xb3, 0xa5, 0x1d, 0x19, 0xf3, 0xfa, 0x7f,
+	0x67, 0xe5, 0xb6, 0xc7, 0xba, 0x6c, 0x6d, 0x3b,
+	0x64, 0x4d, 0x0d, 0x7b, 0x49, 0xb9, 0x10, 0x38,
+	0x0c, 0x0f, 0x4e, 0xc9, 0xe2, 0x3c, 0xb7, 0x12,
+	0x88, 0x2c, 0xf4, 0x3a, 0x89, 0x6d, 0x12, 0xc7,
+	0x04, 0x53, 0xfe, 0x77, 0xc7, 0xfb, 0x77, 0x38
+};
+static const u8 enc_output058[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xee, 0x65, 0x78, 0x30, 0x01, 0xc2, 0x56, 0x91,
+	0xfa, 0x28, 0xd0, 0xf5, 0xf1, 0xc1, 0xd7, 0x62
+};
+static const u8 enc_assoc058[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce058[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key058[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input059[] __initconst = {
+	0x25, 0x6d, 0x40, 0x08, 0x80, 0x94, 0x17, 0x03,
+	0x55, 0xd3, 0x04, 0x04, 0x64, 0x43, 0xfe, 0x68,
+	0xdf, 0x99, 0x47, 0x83, 0x03, 0xfb, 0x3b, 0xfb,
+	0x80, 0xe0, 0x30, 0x3e, 0xeb, 0xd3, 0x29, 0x3e
+};
+static const u8 enc_output059[] __initconst = {
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x79, 0xba, 0x7a, 0x29, 0xf5, 0xa7, 0xbb, 0x75,
+	0x79, 0x7a, 0xf8, 0x7a, 0x61, 0x01, 0x29, 0xa4
+};
+static const u8 enc_assoc059[] __initconst = {
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80
+};
+static const u8 enc_nonce059[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key059[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input060[] __initconst = {
+	0x25, 0x6d, 0x40, 0x08, 0x80, 0x94, 0x17, 0x03,
+	0x55, 0xd3, 0x04, 0x04, 0x64, 0x43, 0xfe, 0x68,
+	0xdf, 0x99, 0x47, 0x83, 0x03, 0xfb, 0x3b, 0xfb,
+	0x80, 0xe0, 0x30, 0x3e, 0xeb, 0xd3, 0x29, 0x3e,
+	0xe3, 0xbc, 0xdb, 0xdb, 0x1e, 0xde, 0xfc, 0x7e,
+	0x8b, 0xcd, 0xa1, 0x36, 0xa1, 0x5c, 0x8c, 0xab,
+	0x08, 0x69, 0xff, 0x52, 0xec, 0x5e, 0x26, 0x65,
+	0x53, 0xb7, 0xb2, 0xa7, 0xfe, 0x87, 0xfd, 0x3d
+};
+static const u8 enc_output060[] __initconst = {
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x36, 0xb1, 0x74, 0x38, 0x19, 0xe1, 0xb9, 0xba,
+	0x15, 0x51, 0xe8, 0xed, 0x92, 0x2a, 0x95, 0x9a
+};
+static const u8 enc_assoc060[] __initconst = {
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80
+};
+static const u8 enc_nonce060[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key060[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input061[] __initconst = {
+	0x25, 0x6d, 0x40, 0x08, 0x80, 0x94, 0x17, 0x03,
+	0x55, 0xd3, 0x04, 0x04, 0x64, 0x43, 0xfe, 0x68,
+	0xdf, 0x99, 0x47, 0x83, 0x03, 0xfb, 0x3b, 0xfb,
+	0x80, 0xe0, 0x30, 0x3e, 0xeb, 0xd3, 0x29, 0x3e,
+	0xe3, 0xbc, 0xdb, 0xdb, 0x1e, 0xde, 0xfc, 0x7e,
+	0x8b, 0xcd, 0xa1, 0x36, 0xa1, 0x5c, 0x8c, 0xab,
+	0x08, 0x69, 0xff, 0x52, 0xec, 0x5e, 0x26, 0x65,
+	0x53, 0xb7, 0xb2, 0xa7, 0xfe, 0x87, 0xfd, 0x3d,
+	0x7a, 0xda, 0x44, 0xc2, 0x42, 0x69, 0xbf, 0x7a,
+	0x55, 0x27, 0xf2, 0xf0, 0xac, 0xf6, 0x85, 0x82,
+	0xb7, 0x4c, 0x5a, 0x62, 0xe6, 0x0c, 0x05, 0x00,
+	0x98, 0x1a, 0x49, 0xb8, 0x45, 0x93, 0x92, 0x44,
+	0x9b, 0xb2, 0xf2, 0x04, 0xb6, 0x46, 0xef, 0x47,
+	0xf3, 0xf0, 0xb1, 0xb6, 0x1d, 0xc3, 0x48, 0x6d,
+	0x77, 0xd3, 0x0b, 0x45, 0x76, 0x92, 0xed, 0xb8,
+	0xfb, 0xac, 0x01, 0x08, 0x38, 0x04, 0x88, 0x47
+};
+static const u8 enc_output061[] __initconst = {
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0xfe, 0xac, 0x49, 0x55, 0x55, 0x4e, 0x80, 0x6f,
+	0x3a, 0x19, 0x02, 0xe2, 0x44, 0x32, 0xc0, 0x8a
+};
+static const u8 enc_assoc061[] __initconst = {
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80
+};
+static const u8 enc_nonce061[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key061[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input062[] __initconst = {
+	0xda, 0x92, 0xbf, 0xf7, 0x7f, 0x6b, 0xe8, 0xfc,
+	0xaa, 0x2c, 0xfb, 0xfb, 0x9b, 0xbc, 0x01, 0x97,
+	0x20, 0x66, 0xb8, 0x7c, 0xfc, 0x04, 0xc4, 0x04,
+	0x7f, 0x1f, 0xcf, 0xc1, 0x14, 0x2c, 0xd6, 0xc1
+};
+static const u8 enc_output062[] __initconst = {
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0x20, 0xa3, 0x79, 0x8d, 0xf1, 0x29, 0x2c, 0x59,
+	0x72, 0xbf, 0x97, 0x41, 0xae, 0xc3, 0x8a, 0x19
+};
+static const u8 enc_assoc062[] __initconst = {
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f
+};
+static const u8 enc_nonce062[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key062[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input063[] __initconst = {
+	0xda, 0x92, 0xbf, 0xf7, 0x7f, 0x6b, 0xe8, 0xfc,
+	0xaa, 0x2c, 0xfb, 0xfb, 0x9b, 0xbc, 0x01, 0x97,
+	0x20, 0x66, 0xb8, 0x7c, 0xfc, 0x04, 0xc4, 0x04,
+	0x7f, 0x1f, 0xcf, 0xc1, 0x14, 0x2c, 0xd6, 0xc1,
+	0x1c, 0x43, 0x24, 0x24, 0xe1, 0x21, 0x03, 0x81,
+	0x74, 0x32, 0x5e, 0xc9, 0x5e, 0xa3, 0x73, 0x54,
+	0xf7, 0x96, 0x00, 0xad, 0x13, 0xa1, 0xd9, 0x9a,
+	0xac, 0x48, 0x4d, 0x58, 0x01, 0x78, 0x02, 0xc2
+};
+static const u8 enc_output063[] __initconst = {
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xc0, 0x3d, 0x9f, 0x67, 0x35, 0x4a, 0x97, 0xb2,
+	0xf0, 0x74, 0xf7, 0x55, 0x15, 0x57, 0xe4, 0x9c
+};
+static const u8 enc_assoc063[] __initconst = {
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f
+};
+static const u8 enc_nonce063[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key063[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input064[] __initconst = {
+	0xda, 0x92, 0xbf, 0xf7, 0x7f, 0x6b, 0xe8, 0xfc,
+	0xaa, 0x2c, 0xfb, 0xfb, 0x9b, 0xbc, 0x01, 0x97,
+	0x20, 0x66, 0xb8, 0x7c, 0xfc, 0x04, 0xc4, 0x04,
+	0x7f, 0x1f, 0xcf, 0xc1, 0x14, 0x2c, 0xd6, 0xc1,
+	0x1c, 0x43, 0x24, 0x24, 0xe1, 0x21, 0x03, 0x81,
+	0x74, 0x32, 0x5e, 0xc9, 0x5e, 0xa3, 0x73, 0x54,
+	0xf7, 0x96, 0x00, 0xad, 0x13, 0xa1, 0xd9, 0x9a,
+	0xac, 0x48, 0x4d, 0x58, 0x01, 0x78, 0x02, 0xc2,
+	0x85, 0x25, 0xbb, 0x3d, 0xbd, 0x96, 0x40, 0x85,
+	0xaa, 0xd8, 0x0d, 0x0f, 0x53, 0x09, 0x7a, 0x7d,
+	0x48, 0xb3, 0xa5, 0x9d, 0x19, 0xf3, 0xfa, 0xff,
+	0x67, 0xe5, 0xb6, 0x47, 0xba, 0x6c, 0x6d, 0xbb,
+	0x64, 0x4d, 0x0d, 0xfb, 0x49, 0xb9, 0x10, 0xb8,
+	0x0c, 0x0f, 0x4e, 0x49, 0xe2, 0x3c, 0xb7, 0x92,
+	0x88, 0x2c, 0xf4, 0xba, 0x89, 0x6d, 0x12, 0x47,
+	0x04, 0x53, 0xfe, 0xf7, 0xc7, 0xfb, 0x77, 0xb8
+};
+static const u8 enc_output064[] __initconst = {
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xc8, 0x6d, 0xa8, 0xdd, 0x65, 0x22, 0x86, 0xd5,
+	0x02, 0x13, 0xd3, 0x28, 0xd6, 0x3e, 0x40, 0x06
+};
+static const u8 enc_assoc064[] __initconst = {
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f,
+	0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f
+};
+static const u8 enc_nonce064[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key064[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input065[] __initconst = {
+	0x5a, 0x92, 0xbf, 0x77, 0xff, 0x6b, 0xe8, 0x7c,
+	0x2a, 0x2c, 0xfb, 0x7b, 0x1b, 0xbc, 0x01, 0x17,
+	0xa0, 0x66, 0xb8, 0xfc, 0x7c, 0x04, 0xc4, 0x84,
+	0xff, 0x1f, 0xcf, 0x41, 0x94, 0x2c, 0xd6, 0x41
+};
+static const u8 enc_output065[] __initconst = {
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0xbe, 0xde, 0x90, 0x83, 0xce, 0xb3, 0x6d, 0xdf,
+	0xe5, 0xfa, 0x81, 0x1f, 0x95, 0x47, 0x1c, 0x67
+};
+static const u8 enc_assoc065[] __initconst = {
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce065[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key065[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input066[] __initconst = {
+	0x5a, 0x92, 0xbf, 0x77, 0xff, 0x6b, 0xe8, 0x7c,
+	0x2a, 0x2c, 0xfb, 0x7b, 0x1b, 0xbc, 0x01, 0x17,
+	0xa0, 0x66, 0xb8, 0xfc, 0x7c, 0x04, 0xc4, 0x84,
+	0xff, 0x1f, 0xcf, 0x41, 0x94, 0x2c, 0xd6, 0x41,
+	0x9c, 0x43, 0x24, 0xa4, 0x61, 0x21, 0x03, 0x01,
+	0xf4, 0x32, 0x5e, 0x49, 0xde, 0xa3, 0x73, 0xd4,
+	0x77, 0x96, 0x00, 0x2d, 0x93, 0xa1, 0xd9, 0x1a,
+	0x2c, 0x48, 0x4d, 0xd8, 0x81, 0x78, 0x02, 0x42
+};
+static const u8 enc_output066[] __initconst = {
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x30, 0x08, 0x74, 0xbb, 0x06, 0x92, 0xb6, 0x89,
+	0xde, 0xad, 0x9a, 0xe1, 0x5b, 0x06, 0x73, 0x90
+};
+static const u8 enc_assoc066[] __initconst = {
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce066[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key066[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input067[] __initconst = {
+	0x5a, 0x92, 0xbf, 0x77, 0xff, 0x6b, 0xe8, 0x7c,
+	0x2a, 0x2c, 0xfb, 0x7b, 0x1b, 0xbc, 0x01, 0x17,
+	0xa0, 0x66, 0xb8, 0xfc, 0x7c, 0x04, 0xc4, 0x84,
+	0xff, 0x1f, 0xcf, 0x41, 0x94, 0x2c, 0xd6, 0x41,
+	0x9c, 0x43, 0x24, 0xa4, 0x61, 0x21, 0x03, 0x01,
+	0xf4, 0x32, 0x5e, 0x49, 0xde, 0xa3, 0x73, 0xd4,
+	0x77, 0x96, 0x00, 0x2d, 0x93, 0xa1, 0xd9, 0x1a,
+	0x2c, 0x48, 0x4d, 0xd8, 0x81, 0x78, 0x02, 0x42,
+	0x05, 0x25, 0xbb, 0xbd, 0x3d, 0x96, 0x40, 0x05,
+	0x2a, 0xd8, 0x0d, 0x8f, 0xd3, 0x09, 0x7a, 0xfd,
+	0xc8, 0xb3, 0xa5, 0x1d, 0x99, 0xf3, 0xfa, 0x7f,
+	0xe7, 0xe5, 0xb6, 0xc7, 0x3a, 0x6c, 0x6d, 0x3b,
+	0xe4, 0x4d, 0x0d, 0x7b, 0xc9, 0xb9, 0x10, 0x38,
+	0x8c, 0x0f, 0x4e, 0xc9, 0x62, 0x3c, 0xb7, 0x12,
+	0x08, 0x2c, 0xf4, 0x3a, 0x09, 0x6d, 0x12, 0xc7,
+	0x84, 0x53, 0xfe, 0x77, 0x47, 0xfb, 0x77, 0x38
+};
+static const u8 enc_output067[] __initconst = {
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x99, 0xca, 0xd8, 0x5f, 0x45, 0xca, 0x40, 0x94,
+	0x2d, 0x0d, 0x4d, 0x5e, 0x95, 0x0a, 0xde, 0x22
+};
+static const u8 enc_assoc067[] __initconst = {
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff,
+	0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce067[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key067[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input068[] __initconst = {
+	0x25, 0x6d, 0x40, 0x88, 0x7f, 0x6b, 0xe8, 0x7c,
+	0x55, 0xd3, 0x04, 0x84, 0x9b, 0xbc, 0x01, 0x17,
+	0xdf, 0x99, 0x47, 0x03, 0xfc, 0x04, 0xc4, 0x84,
+	0x80, 0xe0, 0x30, 0xbe, 0x14, 0x2c, 0xd6, 0x41
+};
+static const u8 enc_output068[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x8b, 0xbe, 0x14, 0x52, 0x72, 0xe7, 0xc2, 0xd9,
+	0xa1, 0x89, 0x1a, 0x3a, 0xb0, 0x98, 0x3d, 0x9d
+};
+static const u8 enc_assoc068[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce068[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key068[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input069[] __initconst = {
+	0x25, 0x6d, 0x40, 0x88, 0x7f, 0x6b, 0xe8, 0x7c,
+	0x55, 0xd3, 0x04, 0x84, 0x9b, 0xbc, 0x01, 0x17,
+	0xdf, 0x99, 0x47, 0x03, 0xfc, 0x04, 0xc4, 0x84,
+	0x80, 0xe0, 0x30, 0xbe, 0x14, 0x2c, 0xd6, 0x41,
+	0xe3, 0xbc, 0xdb, 0x5b, 0xe1, 0x21, 0x03, 0x01,
+	0x8b, 0xcd, 0xa1, 0xb6, 0x5e, 0xa3, 0x73, 0xd4,
+	0x08, 0x69, 0xff, 0xd2, 0x13, 0xa1, 0xd9, 0x1a,
+	0x53, 0xb7, 0xb2, 0x27, 0x01, 0x78, 0x02, 0x42
+};
+static const u8 enc_output069[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x3b, 0x41, 0x86, 0x19, 0x13, 0xa8, 0xf6, 0xde,
+	0x7f, 0x61, 0xe2, 0x25, 0x63, 0x1b, 0xc3, 0x82
+};
+static const u8 enc_assoc069[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce069[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key069[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input070[] __initconst = {
+	0x25, 0x6d, 0x40, 0x88, 0x7f, 0x6b, 0xe8, 0x7c,
+	0x55, 0xd3, 0x04, 0x84, 0x9b, 0xbc, 0x01, 0x17,
+	0xdf, 0x99, 0x47, 0x03, 0xfc, 0x04, 0xc4, 0x84,
+	0x80, 0xe0, 0x30, 0xbe, 0x14, 0x2c, 0xd6, 0x41,
+	0xe3, 0xbc, 0xdb, 0x5b, 0xe1, 0x21, 0x03, 0x01,
+	0x8b, 0xcd, 0xa1, 0xb6, 0x5e, 0xa3, 0x73, 0xd4,
+	0x08, 0x69, 0xff, 0xd2, 0x13, 0xa1, 0xd9, 0x1a,
+	0x53, 0xb7, 0xb2, 0x27, 0x01, 0x78, 0x02, 0x42,
+	0x7a, 0xda, 0x44, 0x42, 0xbd, 0x96, 0x40, 0x05,
+	0x55, 0x27, 0xf2, 0x70, 0x53, 0x09, 0x7a, 0xfd,
+	0xb7, 0x4c, 0x5a, 0xe2, 0x19, 0xf3, 0xfa, 0x7f,
+	0x98, 0x1a, 0x49, 0x38, 0xba, 0x6c, 0x6d, 0x3b,
+	0x9b, 0xb2, 0xf2, 0x84, 0x49, 0xb9, 0x10, 0x38,
+	0xf3, 0xf0, 0xb1, 0x36, 0xe2, 0x3c, 0xb7, 0x12,
+	0x77, 0xd3, 0x0b, 0xc5, 0x89, 0x6d, 0x12, 0xc7,
+	0xfb, 0xac, 0x01, 0x88, 0xc7, 0xfb, 0x77, 0x38
+};
+static const u8 enc_output070[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x84, 0x28, 0xbc, 0xf0, 0x23, 0xec, 0x6b, 0xf3,
+	0x1f, 0xd9, 0xef, 0xb2, 0x03, 0xff, 0x08, 0x71
+};
+static const u8 enc_assoc070[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce070[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key070[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input071[] __initconst = {
+	0xda, 0x92, 0xbf, 0x77, 0x80, 0x94, 0x17, 0x83,
+	0xaa, 0x2c, 0xfb, 0x7b, 0x64, 0x43, 0xfe, 0xe8,
+	0x20, 0x66, 0xb8, 0xfc, 0x03, 0xfb, 0x3b, 0x7b,
+	0x7f, 0x1f, 0xcf, 0x41, 0xeb, 0xd3, 0x29, 0xbe
+};
+static const u8 enc_output071[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0x13, 0x9f, 0xdf, 0x64, 0x74, 0xea, 0x24, 0xf5,
+	0x49, 0xb0, 0x75, 0x82, 0x5f, 0x2c, 0x76, 0x20
+};
+static const u8 enc_assoc071[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00
+};
+static const u8 enc_nonce071[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key071[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input072[] __initconst = {
+	0xda, 0x92, 0xbf, 0x77, 0x80, 0x94, 0x17, 0x83,
+	0xaa, 0x2c, 0xfb, 0x7b, 0x64, 0x43, 0xfe, 0xe8,
+	0x20, 0x66, 0xb8, 0xfc, 0x03, 0xfb, 0x3b, 0x7b,
+	0x7f, 0x1f, 0xcf, 0x41, 0xeb, 0xd3, 0x29, 0xbe,
+	0x1c, 0x43, 0x24, 0xa4, 0x1e, 0xde, 0xfc, 0xfe,
+	0x74, 0x32, 0x5e, 0x49, 0xa1, 0x5c, 0x8c, 0x2b,
+	0xf7, 0x96, 0x00, 0x2d, 0xec, 0x5e, 0x26, 0xe5,
+	0xac, 0x48, 0x4d, 0xd8, 0xfe, 0x87, 0xfd, 0xbd
+};
+static const u8 enc_output072[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xbb, 0xad, 0x8d, 0x86, 0x3b, 0x83, 0x5a, 0x8e,
+	0x86, 0x64, 0xfd, 0x1d, 0x45, 0x66, 0xb6, 0xb4
+};
+static const u8 enc_assoc072[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00
+};
+static const u8 enc_nonce072[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key072[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - misc */
+static const u8 enc_input073[] __initconst = {
+	0xda, 0x92, 0xbf, 0x77, 0x80, 0x94, 0x17, 0x83,
+	0xaa, 0x2c, 0xfb, 0x7b, 0x64, 0x43, 0xfe, 0xe8,
+	0x20, 0x66, 0xb8, 0xfc, 0x03, 0xfb, 0x3b, 0x7b,
+	0x7f, 0x1f, 0xcf, 0x41, 0xeb, 0xd3, 0x29, 0xbe,
+	0x1c, 0x43, 0x24, 0xa4, 0x1e, 0xde, 0xfc, 0xfe,
+	0x74, 0x32, 0x5e, 0x49, 0xa1, 0x5c, 0x8c, 0x2b,
+	0xf7, 0x96, 0x00, 0x2d, 0xec, 0x5e, 0x26, 0xe5,
+	0xac, 0x48, 0x4d, 0xd8, 0xfe, 0x87, 0xfd, 0xbd,
+	0x85, 0x25, 0xbb, 0xbd, 0x42, 0x69, 0xbf, 0xfa,
+	0xaa, 0xd8, 0x0d, 0x8f, 0xac, 0xf6, 0x85, 0x02,
+	0x48, 0xb3, 0xa5, 0x1d, 0xe6, 0x0c, 0x05, 0x80,
+	0x67, 0xe5, 0xb6, 0xc7, 0x45, 0x93, 0x92, 0xc4,
+	0x64, 0x4d, 0x0d, 0x7b, 0xb6, 0x46, 0xef, 0xc7,
+	0x0c, 0x0f, 0x4e, 0xc9, 0x1d, 0xc3, 0x48, 0xed,
+	0x88, 0x2c, 0xf4, 0x3a, 0x76, 0x92, 0xed, 0x38,
+	0x04, 0x53, 0xfe, 0x77, 0x38, 0x04, 0x88, 0xc7
+};
+static const u8 enc_output073[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0x42, 0xf2, 0x35, 0x42, 0x97, 0x84, 0x9a, 0x51,
+	0x1d, 0x53, 0xe5, 0x57, 0x17, 0x72, 0xf7, 0x1f
+};
+static const u8 enc_assoc073[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00
+};
+static const u8 enc_nonce073[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00
+};
+static const u8 enc_key073[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - checking for int overflows */
+static const u8 enc_input076[] __initconst = {
+	0x1b, 0x99, 0x6f, 0x9a, 0x3c, 0xcc, 0x67, 0x85,
+	0xde, 0x22, 0xff, 0x5b, 0x8a, 0xdd, 0x95, 0x02,
+	0xce, 0x03, 0xa0, 0xfa, 0xf5, 0x99, 0x2a, 0x09,
+	0x52, 0x2c, 0xdd, 0x12, 0x06, 0xd2, 0x20, 0xb8,
+	0xf8, 0xbd, 0x07, 0xd1, 0xf1, 0xf5, 0xa1, 0xbd,
+	0x9a, 0x71, 0xd1, 0x1c, 0x7f, 0x57, 0x9b, 0x85,
+	0x58, 0x18, 0xc0, 0x8d, 0x4d, 0xe0, 0x36, 0x39,
+	0x31, 0x83, 0xb7, 0xf5, 0x90, 0xb3, 0x35, 0xae,
+	0xd8, 0xde, 0x5b, 0x57, 0xb1, 0x3c, 0x5f, 0xed,
+	0xe2, 0x44, 0x1c, 0x3e, 0x18, 0x4a, 0xa9, 0xd4,
+	0x6e, 0x61, 0x59, 0x85, 0x06, 0xb3, 0xe1, 0x1c,
+	0x43, 0xc6, 0x2c, 0xbc, 0xac, 0xec, 0xed, 0x33,
+	0x19, 0x08, 0x75, 0xb0, 0x12, 0x21, 0x8b, 0x19,
+	0x30, 0xfb, 0x7c, 0x38, 0xec, 0x45, 0xac, 0x11,
+	0xc3, 0x53, 0xd0, 0xcf, 0x93, 0x8d, 0xcc, 0xb9,
+	0xef, 0xad, 0x8f, 0xed, 0xbe, 0x46, 0xda, 0xa5
+};
+static const u8 enc_output076[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x4b, 0x0b, 0xda, 0x8a, 0xd0, 0x43, 0x83, 0x0d,
+	0x83, 0x19, 0xab, 0x82, 0xc5, 0x0c, 0x76, 0x63
+};
+static const u8 enc_assoc076[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce076[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x07, 0xb4, 0xf0
+};
+static const u8 enc_key076[] __initconst = {
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30
+};
+
+/* wycheproof - checking for int overflows */
+static const u8 enc_input077[] __initconst = {
+	0x86, 0xcb, 0xac, 0xae, 0x4d, 0x3f, 0x74, 0xae,
+	0x01, 0x21, 0x3e, 0x05, 0x51, 0xcc, 0x15, 0x16,
+	0x0e, 0xa1, 0xbe, 0x84, 0x08, 0xe3, 0xd5, 0xd7,
+	0x4f, 0x01, 0x46, 0x49, 0x95, 0xa6, 0x9e, 0x61,
+	0x76, 0xcb, 0x9e, 0x02, 0xb2, 0x24, 0x7e, 0xd2,
+	0x99, 0x89, 0x2f, 0x91, 0x82, 0xa4, 0x5c, 0xaf,
+	0x4c, 0x69, 0x40, 0x56, 0x11, 0x76, 0x6e, 0xdf,
+	0xaf, 0xdc, 0x28, 0x55, 0x19, 0xea, 0x30, 0x48,
+	0x0c, 0x44, 0xf0, 0x5e, 0x78, 0x1e, 0xac, 0xf8,
+	0xfc, 0xec, 0xc7, 0x09, 0x0a, 0xbb, 0x28, 0xfa,
+	0x5f, 0xd5, 0x85, 0xac, 0x8c, 0xda, 0x7e, 0x87,
+	0x72, 0xe5, 0x94, 0xe4, 0xce, 0x6c, 0x88, 0x32,
+	0x81, 0x93, 0x2e, 0x0f, 0x89, 0xf8, 0x77, 0xa1,
+	0xf0, 0x4d, 0x9c, 0x32, 0xb0, 0x6c, 0xf9, 0x0b,
+	0x0e, 0x76, 0x2b, 0x43, 0x0c, 0x4d, 0x51, 0x7c,
+	0x97, 0x10, 0x70, 0x68, 0xf4, 0x98, 0xef, 0x7f
+};
+static const u8 enc_output077[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x4b, 0xc9, 0x8f, 0x72, 0xc4, 0x94, 0xc2, 0xa4,
+	0x3c, 0x2b, 0x15, 0xa1, 0x04, 0x3f, 0x1c, 0xfa
+};
+static const u8 enc_assoc077[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce077[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x20, 0xfb, 0x66
+};
+static const u8 enc_key077[] __initconst = {
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30
+};
+
+/* wycheproof - checking for int overflows */
+static const u8 enc_input078[] __initconst = {
+	0xfa, 0xb1, 0xcd, 0xdf, 0x4f, 0xe1, 0x98, 0xef,
+	0x63, 0xad, 0xd8, 0x81, 0xd6, 0xea, 0xd6, 0xc5,
+	0x76, 0x37, 0xbb, 0xe9, 0x20, 0x18, 0xca, 0x7c,
+	0x0b, 0x96, 0xfb, 0xa0, 0x87, 0x1e, 0x93, 0x2d,
+	0xb1, 0xfb, 0xf9, 0x07, 0x61, 0xbe, 0x25, 0xdf,
+	0x8d, 0xfa, 0xf9, 0x31, 0xce, 0x57, 0x57, 0xe6,
+	0x17, 0xb3, 0xd7, 0xa9, 0xf0, 0xbf, 0x0f, 0xfe,
+	0x5d, 0x59, 0x1a, 0x33, 0xc1, 0x43, 0xb8, 0xf5,
+	0x3f, 0xd0, 0xb5, 0xa1, 0x96, 0x09, 0xfd, 0x62,
+	0xe5, 0xc2, 0x51, 0xa4, 0x28, 0x1a, 0x20, 0x0c,
+	0xfd, 0xc3, 0x4f, 0x28, 0x17, 0x10, 0x40, 0x6f,
+	0x4e, 0x37, 0x62, 0x54, 0x46, 0xff, 0x6e, 0xf2,
+	0x24, 0x91, 0x3d, 0xeb, 0x0d, 0x89, 0xaf, 0x33,
+	0x71, 0x28, 0xe3, 0xd1, 0x55, 0xd1, 0x6d, 0x3e,
+	0xc3, 0x24, 0x60, 0x41, 0x43, 0x21, 0x43, 0xe9,
+	0xab, 0x3a, 0x6d, 0x2c, 0xcc, 0x2f, 0x4d, 0x62
+};
+static const u8 enc_output078[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xf7, 0xe9, 0xe1, 0x51, 0xb0, 0x25, 0x33, 0xc7,
+	0x46, 0x58, 0xbf, 0xc7, 0x73, 0x7c, 0x68, 0x0d
+};
+static const u8 enc_assoc078[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce078[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0xbb, 0x90
+};
+static const u8 enc_key078[] __initconst = {
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30
+};
+
+/* wycheproof - checking for int overflows */
+static const u8 enc_input079[] __initconst = {
+	0x22, 0x72, 0x02, 0xbe, 0x7f, 0x35, 0x15, 0xe9,
+	0xd1, 0xc0, 0x2e, 0xea, 0x2f, 0x19, 0x50, 0xb6,
+	0x48, 0x1b, 0x04, 0x8a, 0x4c, 0x91, 0x50, 0x6c,
+	0xb4, 0x0d, 0x50, 0x4e, 0x6c, 0x94, 0x9f, 0x82,
+	0xd1, 0x97, 0xc2, 0x5a, 0xd1, 0x7d, 0xc7, 0x21,
+	0x65, 0x11, 0x25, 0x78, 0x2a, 0xc7, 0xa7, 0x12,
+	0x47, 0xfe, 0xae, 0xf3, 0x2f, 0x1f, 0x25, 0x0c,
+	0xe4, 0xbb, 0x8f, 0x79, 0xac, 0xaa, 0x17, 0x9d,
+	0x45, 0xa7, 0xb0, 0x54, 0x5f, 0x09, 0x24, 0x32,
+	0x5e, 0xfa, 0x87, 0xd5, 0xe4, 0x41, 0xd2, 0x84,
+	0x78, 0xc6, 0x1f, 0x22, 0x23, 0xee, 0x67, 0xc3,
+	0xb4, 0x1f, 0x43, 0x94, 0x53, 0x5e, 0x2a, 0x24,
+	0x36, 0x9a, 0x2e, 0x16, 0x61, 0x3c, 0x45, 0x94,
+	0x90, 0xc1, 0x4f, 0xb1, 0xd7, 0x55, 0xfe, 0x53,
+	0xfb, 0xe1, 0xee, 0x45, 0xb1, 0xb2, 0x1f, 0x71,
+	0x62, 0xe2, 0xfc, 0xaa, 0x74, 0x2a, 0xbe, 0xfd
+};
+static const u8 enc_output079[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x79, 0x5b, 0xcf, 0xf6, 0x47, 0xc5, 0x53, 0xc2,
+	0xe4, 0xeb, 0x6e, 0x0e, 0xaf, 0xd9, 0xe0, 0x4e
+};
+static const u8 enc_assoc079[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce079[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x70, 0x48, 0x4a
+};
+static const u8 enc_key079[] __initconst = {
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30
+};
+
+/* wycheproof - checking for int overflows */
+static const u8 enc_input080[] __initconst = {
+	0xfa, 0xe5, 0x83, 0x45, 0xc1, 0x6c, 0xb0, 0xf5,
+	0xcc, 0x53, 0x7f, 0x2b, 0x1b, 0x34, 0x69, 0xc9,
+	0x69, 0x46, 0x3b, 0x3e, 0xa7, 0x1b, 0xcf, 0x6b,
+	0x98, 0xd6, 0x69, 0xa8, 0xe6, 0x0e, 0x04, 0xfc,
+	0x08, 0xd5, 0xfd, 0x06, 0x9c, 0x36, 0x26, 0x38,
+	0xe3, 0x40, 0x0e, 0xf4, 0xcb, 0x24, 0x2e, 0x27,
+	0xe2, 0x24, 0x5e, 0x68, 0xcb, 0x9e, 0xc5, 0x83,
+	0xda, 0x53, 0x40, 0xb1, 0x2e, 0xdf, 0x42, 0x3b,
+	0x73, 0x26, 0xad, 0x20, 0xfe, 0xeb, 0x57, 0xda,
+	0xca, 0x2e, 0x04, 0x67, 0xa3, 0x28, 0x99, 0xb4,
+	0x2d, 0xf8, 0xe5, 0x6d, 0x84, 0xe0, 0x06, 0xbc,
+	0x8a, 0x7a, 0xcc, 0x73, 0x1e, 0x7c, 0x1f, 0x6b,
+	0xec, 0xb5, 0x71, 0x9f, 0x70, 0x77, 0xf0, 0xd4,
+	0xf4, 0xc6, 0x1a, 0xb1, 0x1e, 0xba, 0xc1, 0x00,
+	0x18, 0x01, 0xce, 0x33, 0xc4, 0xe4, 0xa7, 0x7d,
+	0x83, 0x1d, 0x3c, 0xe3, 0x4e, 0x84, 0x10, 0xe1
+};
+static const u8 enc_output080[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x19, 0x46, 0xd6, 0x53, 0x96, 0x0f, 0x94, 0x7a,
+	0x74, 0xd3, 0xe8, 0x09, 0x3c, 0xf4, 0x85, 0x02
+};
+static const u8 enc_assoc080[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce080[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x93, 0x2f, 0x40
+};
+static const u8 enc_key080[] __initconst = {
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30
+};
+
+/* wycheproof - checking for int overflows */
+static const u8 enc_input081[] __initconst = {
+	0xeb, 0xb2, 0x16, 0xdd, 0xd7, 0xca, 0x70, 0x92,
+	0x15, 0xf5, 0x03, 0xdf, 0x9c, 0xe6, 0x3c, 0x5c,
+	0xd2, 0x19, 0x4e, 0x7d, 0x90, 0x99, 0xe8, 0xa9,
+	0x0b, 0x2a, 0xfa, 0xad, 0x5e, 0xba, 0x35, 0x06,
+	0x99, 0x25, 0xa6, 0x03, 0xfd, 0xbc, 0x34, 0x1a,
+	0xae, 0xd4, 0x15, 0x05, 0xb1, 0x09, 0x41, 0xfa,
+	0x38, 0x56, 0xa7, 0xe2, 0x47, 0xb1, 0x04, 0x07,
+	0x09, 0x74, 0x6c, 0xfc, 0x20, 0x96, 0xca, 0xa6,
+	0x31, 0xb2, 0xff, 0xf4, 0x1c, 0x25, 0x05, 0x06,
+	0xd8, 0x89, 0xc1, 0xc9, 0x06, 0x71, 0xad, 0xe8,
+	0x53, 0xee, 0x63, 0x94, 0xc1, 0x91, 0x92, 0xa5,
+	0xcf, 0x37, 0x10, 0xd1, 0x07, 0x30, 0x99, 0xe5,
+	0xbc, 0x94, 0x65, 0x82, 0xfc, 0x0f, 0xab, 0x9f,
+	0x54, 0x3c, 0x71, 0x6a, 0xe2, 0x48, 0x6a, 0x86,
+	0x83, 0xfd, 0xca, 0x39, 0xd2, 0xe1, 0x4f, 0x23,
+	0xd0, 0x0a, 0x58, 0x26, 0x64, 0xf4, 0xec, 0xb1
+};
+static const u8 enc_output081[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x36, 0xc3, 0x00, 0x29, 0x85, 0xdd, 0x21, 0xba,
+	0xf8, 0x95, 0xd6, 0x33, 0x57, 0x3f, 0x12, 0xc0
+};
+static const u8 enc_assoc081[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce081[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0xe2, 0x93, 0x35
+};
+static const u8 enc_key081[] __initconst = {
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
+	0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30
+};
+
+/* wycheproof - checking for int overflows */
+static const u8 enc_input082[] __initconst = {
+	0x40, 0x8a, 0xe6, 0xef, 0x1c, 0x7e, 0xf0, 0xfb,
+	0x2c, 0x2d, 0x61, 0x08, 0x16, 0xfc, 0x78, 0x49,
+	0xef, 0xa5, 0x8f, 0x78, 0x27, 0x3f, 0x5f, 0x16,
+	0x6e, 0xa6, 0x5f, 0x81, 0xb5, 0x75, 0x74, 0x7d,
+	0x03, 0x5b, 0x30, 0x40, 0xfe, 0xde, 0x1e, 0xb9,
+	0x45, 0x97, 0x88, 0x66, 0x97, 0x88, 0x40, 0x8e,
+	0x00, 0x41, 0x3b, 0x3e, 0x37, 0x6d, 0x15, 0x2d,
+	0x20, 0x4a, 0xa2, 0xb7, 0xa8, 0x35, 0x58, 0xfc,
+	0xd4, 0x8a, 0x0e, 0xf7, 0xa2, 0x6b, 0x1c, 0xd6,
+	0xd3, 0x5d, 0x23, 0xb3, 0xf5, 0xdf, 0xe0, 0xca,
+	0x77, 0xa4, 0xce, 0x32, 0xb9, 0x4a, 0xbf, 0x83,
+	0xda, 0x2a, 0xef, 0xca, 0xf0, 0x68, 0x38, 0x08,
+	0x79, 0xe8, 0x9f, 0xb0, 0xa3, 0x82, 0x95, 0x95,
+	0xcf, 0x44, 0xc3, 0x85, 0x2a, 0xe2, 0xcc, 0x66,
+	0x2b, 0x68, 0x9f, 0x93, 0x55, 0xd9, 0xc1, 0x83,
+	0x80, 0x1f, 0x6a, 0xcc, 0x31, 0x3f, 0x89, 0x07
+};
+static const u8 enc_output082[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x65, 0x14, 0x51, 0x8e, 0x0a, 0x26, 0x41, 0x42,
+	0xe0, 0xb7, 0x35, 0x1f, 0x96, 0x7f, 0xc2, 0xae
+};
+static const u8 enc_assoc082[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce082[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x0e, 0xf7, 0xd5
+};
+static const u8 enc_key082[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - checking for int overflows */
+static const u8 enc_input083[] __initconst = {
+	0x0a, 0x0a, 0x24, 0x49, 0x9b, 0xca, 0xde, 0x58,
+	0xcf, 0x15, 0x76, 0xc3, 0x12, 0xac, 0xa9, 0x84,
+	0x71, 0x8c, 0xb4, 0xcc, 0x7e, 0x01, 0x53, 0xf5,
+	0xa9, 0x01, 0x58, 0x10, 0x85, 0x96, 0x44, 0xdf,
+	0xc0, 0x21, 0x17, 0x4e, 0x0b, 0x06, 0x0a, 0x39,
+	0x74, 0x48, 0xde, 0x8b, 0x48, 0x4a, 0x86, 0x03,
+	0xbe, 0x68, 0x0a, 0x69, 0x34, 0xc0, 0x90, 0x6f,
+	0x30, 0xdd, 0x17, 0xea, 0xe2, 0xd4, 0xc5, 0xfa,
+	0xa7, 0x77, 0xf8, 0xca, 0x53, 0x37, 0x0e, 0x08,
+	0x33, 0x1b, 0x88, 0xc3, 0x42, 0xba, 0xc9, 0x59,
+	0x78, 0x7b, 0xbb, 0x33, 0x93, 0x0e, 0x3b, 0x56,
+	0xbe, 0x86, 0xda, 0x7f, 0x2a, 0x6e, 0xb1, 0xf9,
+	0x40, 0x89, 0xd1, 0xd1, 0x81, 0x07, 0x4d, 0x43,
+	0x02, 0xf8, 0xe0, 0x55, 0x2d, 0x0d, 0xe1, 0xfa,
+	0xb3, 0x06, 0xa2, 0x1b, 0x42, 0xd4, 0xc3, 0xba,
+	0x6e, 0x6f, 0x0c, 0xbc, 0xc8, 0x1e, 0x87, 0x7a
+};
+static const u8 enc_output083[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x4c, 0x19, 0x4d, 0xa6, 0xa9, 0x9f, 0xd6, 0x5b,
+	0x40, 0xe9, 0xca, 0xd7, 0x98, 0xf4, 0x4b, 0x19
+};
+static const u8 enc_assoc083[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce083[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x3d, 0xfc, 0xe4
+};
+static const u8 enc_key083[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - checking for int overflows */
+static const u8 enc_input084[] __initconst = {
+	0x4a, 0x0a, 0xaf, 0xf8, 0x49, 0x47, 0x29, 0x18,
+	0x86, 0x91, 0x70, 0x13, 0x40, 0xf3, 0xce, 0x2b,
+	0x8a, 0x78, 0xee, 0xd3, 0xa0, 0xf0, 0x65, 0x99,
+	0x4b, 0x72, 0x48, 0x4e, 0x79, 0x91, 0xd2, 0x5c,
+	0x29, 0xaa, 0x07, 0x5e, 0xb1, 0xfc, 0x16, 0xde,
+	0x93, 0xfe, 0x06, 0x90, 0x58, 0x11, 0x2a, 0xb2,
+	0x84, 0xa3, 0xed, 0x18, 0x78, 0x03, 0x26, 0xd1,
+	0x25, 0x8a, 0x47, 0x22, 0x2f, 0xa6, 0x33, 0xd8,
+	0xb2, 0x9f, 0x3b, 0xd9, 0x15, 0x0b, 0x23, 0x9b,
+	0x15, 0x46, 0xc2, 0xbb, 0x9b, 0x9f, 0x41, 0x0f,
+	0xeb, 0xea, 0xd3, 0x96, 0x00, 0x0e, 0xe4, 0x77,
+	0x70, 0x15, 0x32, 0xc3, 0xd0, 0xf5, 0xfb, 0xf8,
+	0x95, 0xd2, 0x80, 0x19, 0x6d, 0x2f, 0x73, 0x7c,
+	0x5e, 0x9f, 0xec, 0x50, 0xd9, 0x2b, 0xb0, 0xdf,
+	0x5d, 0x7e, 0x51, 0x3b, 0xe5, 0xb8, 0xea, 0x97,
+	0x13, 0x10, 0xd5, 0xbf, 0x16, 0xba, 0x7a, 0xee
+};
+static const u8 enc_output084[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xc8, 0xae, 0x77, 0x88, 0xcd, 0x28, 0x74, 0xab,
+	0xc1, 0x38, 0x54, 0x1e, 0x11, 0xfd, 0x05, 0x87
+};
+static const u8 enc_assoc084[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce084[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0x84, 0x86, 0xa8
+};
+static const u8 enc_key084[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - checking for int overflows */
+static const u8 enc_input085[] __initconst = {
+	0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0x78, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09,
+	0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8,
+	0x9f, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca,
+	0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64,
+	0x9c, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39,
+	0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4,
+	0x47, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2,
+	0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73,
+	0xd4, 0xd2, 0x06, 0x61, 0x6f, 0x92, 0x93, 0xf6,
+	0x5b, 0x45, 0xdb, 0xbc, 0x74, 0xe7, 0xc2, 0xed,
+	0xfb, 0xcb, 0xbf, 0x1c, 0xfb, 0x67, 0x9b, 0xb7,
+	0x39, 0xa5, 0x86, 0x2d, 0xe2, 0xbc, 0xb9, 0x37,
+	0xf7, 0x4d, 0x5b, 0xf8, 0x67, 0x1c, 0x5a, 0x8a,
+	0x50, 0x92, 0xf6, 0x1d, 0x54, 0xc9, 0xaa, 0x5b
+};
+static const u8 enc_output085[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x93, 0x3a, 0x51, 0x63, 0xc7, 0xf6, 0x23, 0x68,
+	0x32, 0x7b, 0x3f, 0xbc, 0x10, 0x36, 0xc9, 0x43
+};
+static const u8 enc_assoc085[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce085[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key085[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input093[] __initconst = {
+	0x00, 0x52, 0x35, 0xd2, 0xa9, 0x19, 0xf2, 0x8d,
+	0x3d, 0xb7, 0x66, 0x4a, 0x34, 0xae, 0x6b, 0x44,
+	0x4d, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09,
+	0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8,
+	0x5b, 0x8b, 0x94, 0x50, 0x9e, 0x2b, 0x74, 0xa3,
+	0x6d, 0x34, 0x6e, 0x33, 0xd5, 0x72, 0x65, 0x9b,
+	0xa9, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39,
+	0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4,
+	0x83, 0xdc, 0xe9, 0xf3, 0x07, 0x3e, 0xfa, 0xdb,
+	0x7d, 0x23, 0xb8, 0x7a, 0xce, 0x35, 0x16, 0x8c
+};
+static const u8 enc_output093[] __initconst = {
+	0x00, 0x39, 0xe2, 0xfd, 0x2f, 0xd3, 0x12, 0x14,
+	0x9e, 0x98, 0x98, 0x80, 0x88, 0x48, 0x13, 0xe7,
+	0xca, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x3b, 0x0e, 0x86, 0x9a, 0xaa, 0x8e, 0xa4, 0x96,
+	0x32, 0xff, 0xff, 0x37, 0xb9, 0xe8, 0xce, 0x00,
+	0xca, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x3b, 0x0e, 0x86, 0x9a, 0xaa, 0x8e, 0xa4, 0x96,
+	0x32, 0xff, 0xff, 0x37, 0xb9, 0xe8, 0xce, 0x00,
+	0xa5, 0x19, 0xac, 0x1a, 0x35, 0xb4, 0xa5, 0x77,
+	0x87, 0x51, 0x0a, 0xf7, 0x8d, 0x8d, 0x20, 0x0a
+};
+static const u8 enc_assoc093[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce093[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key093[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input094[] __initconst = {
+	0xd3, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0xe5, 0xda, 0x78, 0x76, 0x6f, 0xa1, 0x92, 0x90,
+	0xc0, 0x31, 0xf7, 0x52, 0x08, 0x50, 0x67, 0x45,
+	0xae, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca,
+	0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64,
+	0x49, 0x6d, 0xde, 0xb0, 0x55, 0x09, 0xc6, 0xef,
+	0xff, 0xab, 0x75, 0xeb, 0x2d, 0xf4, 0xab, 0x09,
+	0x76, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2,
+	0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73,
+	0x01, 0x49, 0xef, 0x50, 0x4b, 0x71, 0xb1, 0x20,
+	0xca, 0x4f, 0xf3, 0x95, 0x19, 0xc2, 0xc2, 0x10
+};
+static const u8 enc_output094[] __initconst = {
+	0xd3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x62, 0x18, 0xb2, 0x7f, 0x83, 0xb8, 0xb4, 0x66,
+	0x02, 0xf6, 0xe1, 0xd8, 0x34, 0x20, 0x7b, 0x02,
+	0xce, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x2a, 0x64, 0x16, 0xce, 0xdb, 0x1c, 0xdd, 0x29,
+	0x6e, 0xf5, 0xd7, 0xd6, 0x92, 0xda, 0xff, 0x02,
+	0xce, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x2a, 0x64, 0x16, 0xce, 0xdb, 0x1c, 0xdd, 0x29,
+	0x6e, 0xf5, 0xd7, 0xd6, 0x92, 0xda, 0xff, 0x02,
+	0x30, 0x2f, 0xe8, 0x2a, 0xb0, 0xa0, 0x9a, 0xf6,
+	0x44, 0x00, 0xd0, 0x15, 0xae, 0x83, 0xd9, 0xcc
+};
+static const u8 enc_assoc094[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce094[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key094[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input095[] __initconst = {
+	0xe9, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0x6d, 0xf1, 0x39, 0x4e, 0xdc, 0x53, 0x9b, 0x5b,
+	0x3a, 0x09, 0x57, 0xbe, 0x0f, 0xb8, 0x59, 0x46,
+	0x80, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca,
+	0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64,
+	0xd1, 0x76, 0x9f, 0xe8, 0x06, 0xbb, 0xfe, 0xb6,
+	0xf5, 0x90, 0x95, 0x0f, 0x2e, 0xac, 0x9e, 0x0a,
+	0x58, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2,
+	0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73,
+	0x99, 0x52, 0xae, 0x08, 0x18, 0xc3, 0x89, 0x79,
+	0xc0, 0x74, 0x13, 0x71, 0x1a, 0x9a, 0xf7, 0x13
+};
+static const u8 enc_output095[] __initconst = {
+	0xe9, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xea, 0x33, 0xf3, 0x47, 0x30, 0x4a, 0xbd, 0xad,
+	0xf8, 0xce, 0x41, 0x34, 0x33, 0xc8, 0x45, 0x01,
+	0xe0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xb2, 0x7f, 0x57, 0x96, 0x88, 0xae, 0xe5, 0x70,
+	0x64, 0xce, 0x37, 0x32, 0x91, 0x82, 0xca, 0x01,
+	0xe0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xb2, 0x7f, 0x57, 0x96, 0x88, 0xae, 0xe5, 0x70,
+	0x64, 0xce, 0x37, 0x32, 0x91, 0x82, 0xca, 0x01,
+	0x98, 0xa7, 0xe8, 0x36, 0xe0, 0xee, 0x4d, 0x02,
+	0x35, 0x00, 0xd0, 0x55, 0x7e, 0xc2, 0xcb, 0xe0
+};
+static const u8 enc_assoc095[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce095[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key095[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input096[] __initconst = {
+	0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0x64, 0xf9, 0x0f, 0x5b, 0x26, 0x92, 0xb8, 0x60,
+	0xd4, 0x59, 0x6f, 0xf4, 0xb3, 0x40, 0x2c, 0x5c,
+	0x00, 0xb9, 0xbb, 0x53, 0x70, 0x7a, 0xa6, 0x67,
+	0xd3, 0x56, 0xfe, 0x50, 0xc7, 0x19, 0x96, 0x94,
+	0x03, 0x35, 0x61, 0xe7, 0xca, 0xca, 0x6d, 0x94,
+	0x1d, 0xc3, 0xcd, 0x69, 0x14, 0xad, 0x69, 0x04
+};
+static const u8 enc_output096[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xe3, 0x3b, 0xc5, 0x52, 0xca, 0x8b, 0x9e, 0x96,
+	0x16, 0x9e, 0x79, 0x7e, 0x8f, 0x30, 0x30, 0x1b,
+	0x60, 0x3c, 0xa9, 0x99, 0x44, 0xdf, 0x76, 0x52,
+	0x8c, 0x9d, 0x6f, 0x54, 0xab, 0x83, 0x3d, 0x0f,
+	0x60, 0x3c, 0xa9, 0x99, 0x44, 0xdf, 0x76, 0x52,
+	0x8c, 0x9d, 0x6f, 0x54, 0xab, 0x83, 0x3d, 0x0f,
+	0x6a, 0xb8, 0xdc, 0xe2, 0xc5, 0x9d, 0xa4, 0x73,
+	0x71, 0x30, 0xb0, 0x25, 0x2f, 0x68, 0xa8, 0xd8
+};
+static const u8 enc_assoc096[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce096[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key096[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input097[] __initconst = {
+	0x68, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0xb0, 0x8f, 0x25, 0x67, 0x5b, 0x9b, 0xcb, 0xf6,
+	0xe3, 0x84, 0x07, 0xde, 0x2e, 0xc7, 0x5a, 0x47,
+	0x9f, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca,
+	0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64,
+	0x2d, 0x2a, 0xf7, 0xcd, 0x6b, 0x08, 0x05, 0x01,
+	0xd3, 0x1b, 0xa5, 0x4f, 0xb2, 0xeb, 0x75, 0x96,
+	0x47, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2,
+	0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73,
+	0x65, 0x0e, 0xc6, 0x2d, 0x75, 0x70, 0x72, 0xce,
+	0xe6, 0xff, 0x23, 0x31, 0x86, 0xdd, 0x1c, 0x8f
+};
+static const u8 enc_output097[] __initconst = {
+	0x68, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x37, 0x4d, 0xef, 0x6e, 0xb7, 0x82, 0xed, 0x00,
+	0x21, 0x43, 0x11, 0x54, 0x12, 0xb7, 0x46, 0x00,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x4e, 0x23, 0x3f, 0xb3, 0xe5, 0x1d, 0x1e, 0xc7,
+	0x42, 0x45, 0x07, 0x72, 0x0d, 0xc5, 0x21, 0x9d,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x4e, 0x23, 0x3f, 0xb3, 0xe5, 0x1d, 0x1e, 0xc7,
+	0x42, 0x45, 0x07, 0x72, 0x0d, 0xc5, 0x21, 0x9d,
+	0x04, 0x4d, 0xea, 0x60, 0x88, 0x80, 0x41, 0x2b,
+	0xfd, 0xff, 0xcf, 0x35, 0x57, 0x9e, 0x9b, 0x26
+};
+static const u8 enc_assoc097[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce097[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key097[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input098[] __initconst = {
+	0x6d, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0xa1, 0x61, 0xb5, 0xab, 0x04, 0x09, 0x00, 0x62,
+	0x9e, 0xfe, 0xff, 0x78, 0xd7, 0xd8, 0x6b, 0x45,
+	0x9f, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca,
+	0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64,
+	0xc6, 0xf8, 0x07, 0x8c, 0xc8, 0xef, 0x12, 0xa0,
+	0xff, 0x65, 0x7d, 0x6d, 0x08, 0xdb, 0x10, 0xb8,
+	0x47, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2,
+	0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73,
+	0x8e, 0xdc, 0x36, 0x6c, 0xd6, 0x97, 0x65, 0x6f,
+	0xca, 0x81, 0xfb, 0x13, 0x3c, 0xed, 0x79, 0xa1
+};
+static const u8 enc_output098[] __initconst = {
+	0x6d, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x26, 0xa3, 0x7f, 0xa2, 0xe8, 0x10, 0x26, 0x94,
+	0x5c, 0x39, 0xe9, 0xf2, 0xeb, 0xa8, 0x77, 0x02,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xa5, 0xf1, 0xcf, 0xf2, 0x46, 0xfa, 0x09, 0x66,
+	0x6e, 0x3b, 0xdf, 0x50, 0xb7, 0xf5, 0x44, 0xb3,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xa5, 0xf1, 0xcf, 0xf2, 0x46, 0xfa, 0x09, 0x66,
+	0x6e, 0x3b, 0xdf, 0x50, 0xb7, 0xf5, 0x44, 0xb3,
+	0x1e, 0x6b, 0xea, 0x63, 0x14, 0x54, 0x2e, 0x2e,
+	0xf9, 0xff, 0xcf, 0x45, 0x0b, 0x2e, 0x98, 0x2b
+};
+static const u8 enc_assoc098[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce098[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key098[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input099[] __initconst = {
+	0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0xfc, 0x01, 0xb8, 0x91, 0xe5, 0xf0, 0xf9, 0x12,
+	0x8d, 0x7d, 0x1c, 0x57, 0x91, 0x92, 0xb6, 0x98,
+	0x63, 0x41, 0x44, 0x15, 0xb6, 0x99, 0x68, 0x95,
+	0x9a, 0x72, 0x91, 0xb7, 0xa5, 0xaf, 0x13, 0x48,
+	0x60, 0xcd, 0x9e, 0xa1, 0x0c, 0x29, 0xa3, 0x66,
+	0x54, 0xe7, 0xa2, 0x8e, 0x76, 0x1b, 0xec, 0xd8
+};
+static const u8 enc_output099[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x7b, 0xc3, 0x72, 0x98, 0x09, 0xe9, 0xdf, 0xe4,
+	0x4f, 0xba, 0x0a, 0xdd, 0xad, 0xe2, 0xaa, 0xdf,
+	0x03, 0xc4, 0x56, 0xdf, 0x82, 0x3c, 0xb8, 0xa0,
+	0xc5, 0xb9, 0x00, 0xb3, 0xc9, 0x35, 0xb8, 0xd3,
+	0x03, 0xc4, 0x56, 0xdf, 0x82, 0x3c, 0xb8, 0xa0,
+	0xc5, 0xb9, 0x00, 0xb3, 0xc9, 0x35, 0xb8, 0xd3,
+	0xed, 0x20, 0x17, 0xc8, 0xdb, 0xa4, 0x77, 0x56,
+	0x29, 0x04, 0x9d, 0x78, 0x6e, 0x3b, 0xce, 0xb1
+};
+static const u8 enc_assoc099[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce099[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key099[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input100[] __initconst = {
+	0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0x6b, 0x6d, 0xc9, 0xd2, 0x1a, 0x81, 0x9e, 0x70,
+	0xb5, 0x77, 0xf4, 0x41, 0x37, 0xd3, 0xd6, 0xbd,
+	0x13, 0x35, 0xf5, 0xeb, 0x44, 0x49, 0x40, 0x77,
+	0xb2, 0x64, 0x49, 0xa5, 0x4b, 0x6c, 0x7c, 0x75,
+	0x10, 0xb9, 0x2f, 0x5f, 0xfe, 0xf9, 0x8b, 0x84,
+	0x7c, 0xf1, 0x7a, 0x9c, 0x98, 0xd8, 0x83, 0xe5
+};
+static const u8 enc_output100[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xec, 0xaf, 0x03, 0xdb, 0xf6, 0x98, 0xb8, 0x86,
+	0x77, 0xb0, 0xe2, 0xcb, 0x0b, 0xa3, 0xca, 0xfa,
+	0x73, 0xb0, 0xe7, 0x21, 0x70, 0xec, 0x90, 0x42,
+	0xed, 0xaf, 0xd8, 0xa1, 0x27, 0xf6, 0xd7, 0xee,
+	0x73, 0xb0, 0xe7, 0x21, 0x70, 0xec, 0x90, 0x42,
+	0xed, 0xaf, 0xd8, 0xa1, 0x27, 0xf6, 0xd7, 0xee,
+	0x07, 0x3f, 0x17, 0xcb, 0x67, 0x78, 0x64, 0x59,
+	0x25, 0x04, 0x9d, 0x88, 0x22, 0xcb, 0xca, 0xb6
+};
+static const u8 enc_assoc100[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce100[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key100[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input101[] __initconst = {
+	0xff, 0xcb, 0x2b, 0x11, 0x06, 0xf8, 0x23, 0x4c,
+	0x5e, 0x99, 0xd4, 0xdb, 0x4c, 0x70, 0x48, 0xde,
+	0x32, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09,
+	0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8,
+	0x16, 0xe9, 0x88, 0x4a, 0x11, 0x4f, 0x0e, 0x92,
+	0x66, 0xce, 0xa3, 0x88, 0x5f, 0xe3, 0x6b, 0x9f,
+	0xd6, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39,
+	0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4,
+	0xce, 0xbe, 0xf5, 0xe9, 0x88, 0x5a, 0x80, 0xea,
+	0x76, 0xd9, 0x75, 0xc1, 0x44, 0xa4, 0x18, 0x88
+};
+static const u8 enc_output101[] __initconst = {
+	0xff, 0xa0, 0xfc, 0x3e, 0x80, 0x32, 0xc3, 0xd5,
+	0xfd, 0xb6, 0x2a, 0x11, 0xf0, 0x96, 0x30, 0x7d,
+	0xb5, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x76, 0x6c, 0x9a, 0x80, 0x25, 0xea, 0xde, 0xa7,
+	0x39, 0x05, 0x32, 0x8c, 0x33, 0x79, 0xc0, 0x04,
+	0xb5, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x76, 0x6c, 0x9a, 0x80, 0x25, 0xea, 0xde, 0xa7,
+	0x39, 0x05, 0x32, 0x8c, 0x33, 0x79, 0xc0, 0x04,
+	0x8b, 0x9b, 0xb4, 0xb4, 0x86, 0x12, 0x89, 0x65,
+	0x8c, 0x69, 0x6a, 0x83, 0x40, 0x15, 0x04, 0x05
+};
+static const u8 enc_assoc101[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce101[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key101[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input102[] __initconst = {
+	0x6f, 0x9e, 0x70, 0xed, 0x3b, 0x8b, 0xac, 0xa0,
+	0x26, 0xe4, 0x6a, 0x5a, 0x09, 0x43, 0x15, 0x8d,
+	0x21, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09,
+	0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8,
+	0x0c, 0x61, 0x2c, 0x5e, 0x8d, 0x89, 0xa8, 0x73,
+	0xdb, 0xca, 0xad, 0x5b, 0x73, 0x46, 0x42, 0x9b,
+	0xc5, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39,
+	0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4,
+	0xd4, 0x36, 0x51, 0xfd, 0x14, 0x9c, 0x26, 0x0b,
+	0xcb, 0xdd, 0x7b, 0x12, 0x68, 0x01, 0x31, 0x8c
+};
+static const u8 enc_output102[] __initconst = {
+	0x6f, 0xf5, 0xa7, 0xc2, 0xbd, 0x41, 0x4c, 0x39,
+	0x85, 0xcb, 0x94, 0x90, 0xb5, 0xa5, 0x6d, 0x2e,
+	0xa6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x6c, 0xe4, 0x3e, 0x94, 0xb9, 0x2c, 0x78, 0x46,
+	0x84, 0x01, 0x3c, 0x5f, 0x1f, 0xdc, 0xe9, 0x00,
+	0xa6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x6c, 0xe4, 0x3e, 0x94, 0xb9, 0x2c, 0x78, 0x46,
+	0x84, 0x01, 0x3c, 0x5f, 0x1f, 0xdc, 0xe9, 0x00,
+	0x8b, 0x3b, 0xbd, 0x51, 0x64, 0x44, 0x59, 0x56,
+	0x8d, 0x81, 0xca, 0x1f, 0xa7, 0x2c, 0xe4, 0x04
+};
+static const u8 enc_assoc102[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce102[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key102[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input103[] __initconst = {
+	0x41, 0x2b, 0x08, 0x0a, 0x3e, 0x19, 0xc1, 0x0d,
+	0x44, 0xa1, 0xaf, 0x1e, 0xab, 0xde, 0xb4, 0xce,
+	0x35, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09,
+	0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8,
+	0x6b, 0x83, 0x94, 0x33, 0x09, 0x21, 0x48, 0x6c,
+	0xa1, 0x1d, 0x29, 0x1c, 0x3e, 0x97, 0xee, 0x9a,
+	0xd1, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39,
+	0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4,
+	0xb3, 0xd4, 0xe9, 0x90, 0x90, 0x34, 0xc6, 0x14,
+	0xb1, 0x0a, 0xff, 0x55, 0x25, 0xd0, 0x9d, 0x8d
+};
+static const u8 enc_output103[] __initconst = {
+	0x41, 0x40, 0xdf, 0x25, 0xb8, 0xd3, 0x21, 0x94,
+	0xe7, 0x8e, 0x51, 0xd4, 0x17, 0x38, 0xcc, 0x6d,
+	0xb2, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x0b, 0x06, 0x86, 0xf9, 0x3d, 0x84, 0x98, 0x59,
+	0xfe, 0xd6, 0xb8, 0x18, 0x52, 0x0d, 0x45, 0x01,
+	0xb2, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x0b, 0x06, 0x86, 0xf9, 0x3d, 0x84, 0x98, 0x59,
+	0xfe, 0xd6, 0xb8, 0x18, 0x52, 0x0d, 0x45, 0x01,
+	0x86, 0xfb, 0xab, 0x2b, 0x4a, 0x94, 0xf4, 0x7a,
+	0xa5, 0x6f, 0x0a, 0xea, 0x65, 0xd1, 0x10, 0x08
+};
+static const u8 enc_assoc103[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce103[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key103[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input104[] __initconst = {
+	0xb2, 0x47, 0xa7, 0x47, 0x23, 0x49, 0x1a, 0xac,
+	0xac, 0xaa, 0xd7, 0x09, 0xc9, 0x1e, 0x93, 0x2b,
+	0x31, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09,
+	0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8,
+	0x9a, 0xde, 0x04, 0xe7, 0x5b, 0xb7, 0x01, 0xd9,
+	0x66, 0x06, 0x01, 0xb3, 0x47, 0x65, 0xde, 0x98,
+	0xd5, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39,
+	0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4,
+	0x42, 0x89, 0x79, 0x44, 0xc2, 0xa2, 0x8f, 0xa1,
+	0x76, 0x11, 0xd7, 0xfa, 0x5c, 0x22, 0xad, 0x8f
+};
+static const u8 enc_output104[] __initconst = {
+	0xb2, 0x2c, 0x70, 0x68, 0xa5, 0x83, 0xfa, 0x35,
+	0x0f, 0x85, 0x29, 0xc3, 0x75, 0xf8, 0xeb, 0x88,
+	0xb6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xfa, 0x5b, 0x16, 0x2d, 0x6f, 0x12, 0xd1, 0xec,
+	0x39, 0xcd, 0x90, 0xb7, 0x2b, 0xff, 0x75, 0x03,
+	0xb6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xfa, 0x5b, 0x16, 0x2d, 0x6f, 0x12, 0xd1, 0xec,
+	0x39, 0xcd, 0x90, 0xb7, 0x2b, 0xff, 0x75, 0x03,
+	0xa0, 0x19, 0xac, 0x2e, 0xd6, 0x67, 0xe1, 0x7d,
+	0xa1, 0x6f, 0x0a, 0xfa, 0x19, 0x61, 0x0d, 0x0d
+};
+static const u8 enc_assoc104[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce104[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key104[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input105[] __initconst = {
+	0x74, 0x0f, 0x9e, 0x49, 0xf6, 0x10, 0xef, 0xa5,
+	0x85, 0xb6, 0x59, 0xca, 0x6e, 0xd8, 0xb4, 0x99,
+	0x2d, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09,
+	0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8,
+	0x41, 0x2d, 0x96, 0xaf, 0xbe, 0x80, 0xec, 0x3e,
+	0x79, 0xd4, 0x51, 0xb0, 0x0a, 0x2d, 0xb2, 0x9a,
+	0xc9, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39,
+	0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4,
+	0x99, 0x7a, 0xeb, 0x0c, 0x27, 0x95, 0x62, 0x46,
+	0x69, 0xc3, 0x87, 0xf9, 0x11, 0x6a, 0xc1, 0x8d
+};
+static const u8 enc_output105[] __initconst = {
+	0x74, 0x64, 0x49, 0x66, 0x70, 0xda, 0x0f, 0x3c,
+	0x26, 0x99, 0xa7, 0x00, 0xd2, 0x3e, 0xcc, 0x3a,
+	0xaa, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x21, 0xa8, 0x84, 0x65, 0x8a, 0x25, 0x3c, 0x0b,
+	0x26, 0x1f, 0xc0, 0xb4, 0x66, 0xb7, 0x19, 0x01,
+	0xaa, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x21, 0xa8, 0x84, 0x65, 0x8a, 0x25, 0x3c, 0x0b,
+	0x26, 0x1f, 0xc0, 0xb4, 0x66, 0xb7, 0x19, 0x01,
+	0x73, 0x6e, 0x18, 0x18, 0x16, 0x96, 0xa5, 0x88,
+	0x9c, 0x31, 0x59, 0xfa, 0xab, 0xab, 0x20, 0xfd
+};
+static const u8 enc_assoc105[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce105[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key105[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input106[] __initconst = {
+	0xad, 0xba, 0x5d, 0x10, 0x5b, 0xc8, 0xaa, 0x06,
+	0x2c, 0x23, 0x36, 0xcb, 0x88, 0x9d, 0xdb, 0xd5,
+	0x37, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09,
+	0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8,
+	0x17, 0x7c, 0x5f, 0xfe, 0x28, 0x75, 0xf4, 0x68,
+	0xf6, 0xc2, 0x96, 0x57, 0x48, 0xf3, 0x59, 0x9a,
+	0xd3, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39,
+	0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4,
+	0xcf, 0x2b, 0x22, 0x5d, 0xb1, 0x60, 0x7a, 0x10,
+	0xe6, 0xd5, 0x40, 0x1e, 0x53, 0xb4, 0x2a, 0x8d
+};
+static const u8 enc_output106[] __initconst = {
+	0xad, 0xd1, 0x8a, 0x3f, 0xdd, 0x02, 0x4a, 0x9f,
+	0x8f, 0x0c, 0xc8, 0x01, 0x34, 0x7b, 0xa3, 0x76,
+	0xb0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x77, 0xf9, 0x4d, 0x34, 0x1c, 0xd0, 0x24, 0x5d,
+	0xa9, 0x09, 0x07, 0x53, 0x24, 0x69, 0xf2, 0x01,
+	0xb0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x77, 0xf9, 0x4d, 0x34, 0x1c, 0xd0, 0x24, 0x5d,
+	0xa9, 0x09, 0x07, 0x53, 0x24, 0x69, 0xf2, 0x01,
+	0xba, 0xd5, 0x8f, 0x10, 0xa9, 0x1e, 0x6a, 0x88,
+	0x9a, 0xba, 0x32, 0xfd, 0x17, 0xd8, 0x33, 0x1a
+};
+static const u8 enc_assoc106[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce106[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key106[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input107[] __initconst = {
+	0xfe, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0xc0, 0x01, 0xed, 0xc5, 0xda, 0x44, 0x2e, 0x71,
+	0x9b, 0xce, 0x9a, 0xbe, 0x27, 0x3a, 0xf1, 0x44,
+	0xb4, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca,
+	0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64,
+	0x48, 0x02, 0x5f, 0x41, 0xfa, 0x4e, 0x33, 0x6c,
+	0x78, 0x69, 0x57, 0xa2, 0xa7, 0xc4, 0x93, 0x0a,
+	0x6c, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2,
+	0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73,
+	0x00, 0x26, 0x6e, 0xa1, 0xe4, 0x36, 0x44, 0xa3,
+	0x4d, 0x8d, 0xd1, 0xdc, 0x93, 0xf2, 0xfa, 0x13
+};
+static const u8 enc_output107[] __initconst = {
+	0xfe, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x47, 0xc3, 0x27, 0xcc, 0x36, 0x5d, 0x08, 0x87,
+	0x59, 0x09, 0x8c, 0x34, 0x1b, 0x4a, 0xed, 0x03,
+	0xd4, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x2b, 0x0b, 0x97, 0x3f, 0x74, 0x5b, 0x28, 0xaa,
+	0xe9, 0x37, 0xf5, 0x9f, 0x18, 0xea, 0xc7, 0x01,
+	0xd4, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x2b, 0x0b, 0x97, 0x3f, 0x74, 0x5b, 0x28, 0xaa,
+	0xe9, 0x37, 0xf5, 0x9f, 0x18, 0xea, 0xc7, 0x01,
+	0xd6, 0x8c, 0xe1, 0x74, 0x07, 0x9a, 0xdd, 0x02,
+	0x8d, 0xd0, 0x5c, 0xf8, 0x14, 0x63, 0x04, 0x88
+};
+static const u8 enc_assoc107[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce107[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key107[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input108[] __initconst = {
+	0xb5, 0x13, 0xb0, 0x6a, 0xb9, 0xac, 0x14, 0x43,
+	0x5a, 0xcb, 0x8a, 0xa3, 0xa3, 0x7a, 0xfd, 0xb6,
+	0x54, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09,
+	0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8,
+	0x61, 0x95, 0x01, 0x93, 0xb1, 0xbf, 0x03, 0x11,
+	0xff, 0x11, 0x79, 0x89, 0xae, 0xd9, 0xa9, 0x99,
+	0xb0, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39,
+	0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4,
+	0xb9, 0xc2, 0x7c, 0x30, 0x28, 0xaa, 0x8d, 0x69,
+	0xef, 0x06, 0xaf, 0xc0, 0xb5, 0x9e, 0xda, 0x8e
+};
+static const u8 enc_output108[] __initconst = {
+	0xb5, 0x78, 0x67, 0x45, 0x3f, 0x66, 0xf4, 0xda,
+	0xf9, 0xe4, 0x74, 0x69, 0x1f, 0x9c, 0x85, 0x15,
+	0xd3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x01, 0x10, 0x13, 0x59, 0x85, 0x1a, 0xd3, 0x24,
+	0xa0, 0xda, 0xe8, 0x8d, 0xc2, 0x43, 0x02, 0x02,
+	0xd3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x01, 0x10, 0x13, 0x59, 0x85, 0x1a, 0xd3, 0x24,
+	0xa0, 0xda, 0xe8, 0x8d, 0xc2, 0x43, 0x02, 0x02,
+	0xaa, 0x48, 0xa3, 0x88, 0x7d, 0x4b, 0x05, 0x96,
+	0x99, 0xc2, 0xfd, 0xf9, 0xc6, 0x78, 0x7e, 0x0a
+};
+static const u8 enc_assoc108[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce108[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key108[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input109[] __initconst = {
+	0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0xd4, 0xf1, 0x09, 0xe8, 0x14, 0xce, 0xa8, 0x5a,
+	0x08, 0xc0, 0x11, 0xd8, 0x50, 0xdd, 0x1d, 0xcb,
+	0xcf, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca,
+	0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64,
+	0x53, 0x40, 0xb8, 0x5a, 0x9a, 0xa0, 0x82, 0x96,
+	0xb7, 0x7a, 0x5f, 0xc3, 0x96, 0x1f, 0x66, 0x0f,
+	0x17, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2,
+	0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73,
+	0x1b, 0x64, 0x89, 0xba, 0x84, 0xd8, 0xf5, 0x59,
+	0x82, 0x9e, 0xd9, 0xbd, 0xa2, 0x29, 0x0f, 0x16
+};
+static const u8 enc_output109[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x53, 0x33, 0xc3, 0xe1, 0xf8, 0xd7, 0x8e, 0xac,
+	0xca, 0x07, 0x07, 0x52, 0x6c, 0xad, 0x01, 0x8c,
+	0xaf, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x30, 0x49, 0x70, 0x24, 0x14, 0xb5, 0x99, 0x50,
+	0x26, 0x24, 0xfd, 0xfe, 0x29, 0x31, 0x32, 0x04,
+	0xaf, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x30, 0x49, 0x70, 0x24, 0x14, 0xb5, 0x99, 0x50,
+	0x26, 0x24, 0xfd, 0xfe, 0x29, 0x31, 0x32, 0x04,
+	0xb9, 0x36, 0xa8, 0x17, 0xf2, 0x21, 0x1a, 0xf1,
+	0x29, 0xe2, 0xcf, 0x16, 0x0f, 0xd4, 0x2b, 0xcb
+};
+static const u8 enc_assoc109[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce109[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key109[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input110[] __initconst = {
+	0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0xdf, 0x4c, 0x62, 0x03, 0x2d, 0x41, 0x19, 0xb5,
+	0x88, 0x47, 0x7e, 0x99, 0x92, 0x5a, 0x56, 0xd9,
+	0xd6, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca,
+	0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64,
+	0xfa, 0x84, 0xf0, 0x64, 0x55, 0x36, 0x42, 0x1b,
+	0x2b, 0xb9, 0x24, 0x6e, 0xc2, 0x19, 0xed, 0x0b,
+	0x0e, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2,
+	0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73,
+	0xb2, 0xa0, 0xc1, 0x84, 0x4b, 0x4e, 0x35, 0xd4,
+	0x1e, 0x5d, 0xa2, 0x10, 0xf6, 0x2f, 0x84, 0x12
+};
+static const u8 enc_output110[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x58, 0x8e, 0xa8, 0x0a, 0xc1, 0x58, 0x3f, 0x43,
+	0x4a, 0x80, 0x68, 0x13, 0xae, 0x2a, 0x4a, 0x9e,
+	0xb6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x99, 0x8d, 0x38, 0x1a, 0xdb, 0x23, 0x59, 0xdd,
+	0xba, 0xe7, 0x86, 0x53, 0x7d, 0x37, 0xb9, 0x00,
+	0xb6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x99, 0x8d, 0x38, 0x1a, 0xdb, 0x23, 0x59, 0xdd,
+	0xba, 0xe7, 0x86, 0x53, 0x7d, 0x37, 0xb9, 0x00,
+	0x9f, 0x7a, 0xc4, 0x35, 0x1f, 0x6b, 0x91, 0xe6,
+	0x30, 0x97, 0xa7, 0x13, 0x11, 0x5d, 0x05, 0xbe
+};
+static const u8 enc_assoc110[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce110[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key110[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input111[] __initconst = {
+	0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0x13, 0xf8, 0x0a, 0x00, 0x6d, 0xc1, 0xbb, 0xda,
+	0xd6, 0x39, 0xa9, 0x2f, 0xc7, 0xec, 0xa6, 0x55,
+	0xf7, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca,
+	0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64,
+	0x63, 0x48, 0xb8, 0xfd, 0x29, 0xbf, 0x96, 0xd5,
+	0x63, 0xa5, 0x17, 0xe2, 0x7d, 0x7b, 0xfc, 0x0f,
+	0x2f, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2,
+	0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73,
+	0x2b, 0x6c, 0x89, 0x1d, 0x37, 0xc7, 0xe1, 0x1a,
+	0x56, 0x41, 0x91, 0x9c, 0x49, 0x4d, 0x95, 0x16
+};
+static const u8 enc_output111[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x94, 0x3a, 0xc0, 0x09, 0x81, 0xd8, 0x9d, 0x2c,
+	0x14, 0xfe, 0xbf, 0xa5, 0xfb, 0x9c, 0xba, 0x12,
+	0x97, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x41, 0x70, 0x83, 0xa7, 0xaa, 0x8d, 0x13,
+	0xf2, 0xfb, 0xb5, 0xdf, 0xc2, 0x55, 0xa8, 0x04,
+	0x97, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x00, 0x41, 0x70, 0x83, 0xa7, 0xaa, 0x8d, 0x13,
+	0xf2, 0xfb, 0xb5, 0xdf, 0xc2, 0x55, 0xa8, 0x04,
+	0x9a, 0x18, 0xa8, 0x28, 0x07, 0x02, 0x69, 0xf4,
+	0x47, 0x00, 0xd0, 0x09, 0xe7, 0x17, 0x1c, 0xc9
+};
+static const u8 enc_assoc111[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce111[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key111[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input112[] __initconst = {
+	0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0x82, 0xe5, 0x9b, 0x45, 0x82, 0x91, 0x50, 0x38,
+	0xf9, 0x33, 0x81, 0x1e, 0x65, 0x2d, 0xc6, 0x6a,
+	0xfc, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca,
+	0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64,
+	0xb6, 0x71, 0xc8, 0xca, 0xc2, 0x70, 0xc2, 0x65,
+	0xa0, 0xac, 0x2f, 0x53, 0x57, 0x99, 0x88, 0x0a,
+	0x24, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2,
+	0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73,
+	0xfe, 0x55, 0xf9, 0x2a, 0xdc, 0x08, 0xb5, 0xaa,
+	0x95, 0x48, 0xa9, 0x2d, 0x63, 0xaf, 0xe1, 0x13
+};
+static const u8 enc_output112[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x05, 0x27, 0x51, 0x4c, 0x6e, 0x88, 0x76, 0xce,
+	0x3b, 0xf4, 0x97, 0x94, 0x59, 0x5d, 0xda, 0x2d,
+	0x9c, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xd5, 0x78, 0x00, 0xb4, 0x4c, 0x65, 0xd9, 0xa3,
+	0x31, 0xf2, 0x8d, 0x6e, 0xe8, 0xb7, 0xdc, 0x01,
+	0x9c, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xd5, 0x78, 0x00, 0xb4, 0x4c, 0x65, 0xd9, 0xa3,
+	0x31, 0xf2, 0x8d, 0x6e, 0xe8, 0xb7, 0xdc, 0x01,
+	0xb4, 0x36, 0xa8, 0x2b, 0x93, 0xd5, 0x55, 0xf7,
+	0x43, 0x00, 0xd0, 0x19, 0x9b, 0xa7, 0x18, 0xce
+};
+static const u8 enc_assoc112[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce112[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key112[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input113[] __initconst = {
+	0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0xf1, 0xd1, 0x28, 0x87, 0xb7, 0x21, 0x69, 0x86,
+	0xa1, 0x2d, 0x79, 0x09, 0x8b, 0x6d, 0xe6, 0x0f,
+	0xc0, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca,
+	0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64,
+	0xa7, 0xc7, 0x58, 0x99, 0xf3, 0xe6, 0x0a, 0xf1,
+	0xfc, 0xb6, 0xc7, 0x30, 0x7d, 0x87, 0x59, 0x0f,
+	0x18, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2,
+	0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73,
+	0xef, 0xe3, 0x69, 0x79, 0xed, 0x9e, 0x7d, 0x3e,
+	0xc9, 0x52, 0x41, 0x4e, 0x49, 0xb1, 0x30, 0x16
+};
+static const u8 enc_output113[] __initconst = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x76, 0x13, 0xe2, 0x8e, 0x5b, 0x38, 0x4f, 0x70,
+	0x63, 0xea, 0x6f, 0x83, 0xb7, 0x1d, 0xfa, 0x48,
+	0xa0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xc4, 0xce, 0x90, 0xe7, 0x7d, 0xf3, 0x11, 0x37,
+	0x6d, 0xe8, 0x65, 0x0d, 0xc2, 0xa9, 0x0d, 0x04,
+	0xa0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xc4, 0xce, 0x90, 0xe7, 0x7d, 0xf3, 0x11, 0x37,
+	0x6d, 0xe8, 0x65, 0x0d, 0xc2, 0xa9, 0x0d, 0x04,
+	0xce, 0x54, 0xa8, 0x2e, 0x1f, 0xa9, 0x42, 0xfa,
+	0x3f, 0x00, 0xd0, 0x29, 0x4f, 0x37, 0x15, 0xd3
+};
+static const u8 enc_assoc113[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce113[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key113[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input114[] __initconst = {
+	0xcb, 0xf1, 0xda, 0x9e, 0x0b, 0xa9, 0x37, 0x73,
+	0x74, 0xe6, 0x9e, 0x1c, 0x0e, 0x60, 0x0c, 0xfc,
+	0x34, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09,
+	0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8,
+	0xbe, 0x3f, 0xa6, 0x6b, 0x6c, 0xe7, 0x80, 0x8a,
+	0xa3, 0xe4, 0x59, 0x49, 0xf9, 0x44, 0x64, 0x9f,
+	0xd0, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39,
+	0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4,
+	0x66, 0x68, 0xdb, 0xc8, 0xf5, 0xf2, 0x0e, 0xf2,
+	0xb3, 0xf3, 0x8f, 0x00, 0xe2, 0x03, 0x17, 0x88
+};
+static const u8 enc_output114[] __initconst = {
+	0xcb, 0x9a, 0x0d, 0xb1, 0x8d, 0x63, 0xd7, 0xea,
+	0xd7, 0xc9, 0x60, 0xd6, 0xb2, 0x86, 0x74, 0x5f,
+	0xb3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xde, 0xba, 0xb4, 0xa1, 0x58, 0x42, 0x50, 0xbf,
+	0xfc, 0x2f, 0xc8, 0x4d, 0x95, 0xde, 0xcf, 0x04,
+	0xb3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xde, 0xba, 0xb4, 0xa1, 0x58, 0x42, 0x50, 0xbf,
+	0xfc, 0x2f, 0xc8, 0x4d, 0x95, 0xde, 0xcf, 0x04,
+	0x23, 0x83, 0xab, 0x0b, 0x79, 0x92, 0x05, 0x69,
+	0x9b, 0x51, 0x0a, 0xa7, 0x09, 0xbf, 0x31, 0xf1
+};
+static const u8 enc_assoc114[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce114[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key114[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input115[] __initconst = {
+	0x8f, 0x27, 0x86, 0x94, 0xc4, 0xe9, 0xda, 0xeb,
+	0xd5, 0x8d, 0x3e, 0x5b, 0x96, 0x6e, 0x8b, 0x68,
+	0x42, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09,
+	0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8,
+	0x06, 0x53, 0xe7, 0xa3, 0x31, 0x71, 0x88, 0x33,
+	0xac, 0xc3, 0xb9, 0xad, 0xff, 0x1c, 0x31, 0x98,
+	0xa6, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39,
+	0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4,
+	0xde, 0x04, 0x9a, 0x00, 0xa8, 0x64, 0x06, 0x4b,
+	0xbc, 0xd4, 0x6f, 0xe4, 0xe4, 0x5b, 0x42, 0x8f
+};
+static const u8 enc_output115[] __initconst = {
+	0x8f, 0x4c, 0x51, 0xbb, 0x42, 0x23, 0x3a, 0x72,
+	0x76, 0xa2, 0xc0, 0x91, 0x2a, 0x88, 0xf3, 0xcb,
+	0xc5, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x66, 0xd6, 0xf5, 0x69, 0x05, 0xd4, 0x58, 0x06,
+	0xf3, 0x08, 0x28, 0xa9, 0x93, 0x86, 0x9a, 0x03,
+	0xc5, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x66, 0xd6, 0xf5, 0x69, 0x05, 0xd4, 0x58, 0x06,
+	0xf3, 0x08, 0x28, 0xa9, 0x93, 0x86, 0x9a, 0x03,
+	0x8b, 0xfb, 0xab, 0x17, 0xa9, 0xe0, 0xb8, 0x74,
+	0x8b, 0x51, 0x0a, 0xe7, 0xd9, 0xfd, 0x23, 0x05
+};
+static const u8 enc_assoc115[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce115[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key115[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input116[] __initconst = {
+	0xd5, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0x9a, 0x22, 0xd7, 0x0a, 0x48, 0xe2, 0x4f, 0xdd,
+	0xcd, 0xd4, 0x41, 0x9d, 0xe6, 0x4c, 0x8f, 0x44,
+	0xfc, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca,
+	0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64,
+	0x77, 0xb5, 0xc9, 0x07, 0xd9, 0xc9, 0xe1, 0xea,
+	0x51, 0x85, 0x1a, 0x20, 0x4a, 0xad, 0x9f, 0x0a,
+	0x24, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2,
+	0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73,
+	0x3f, 0x91, 0xf8, 0xe7, 0xc7, 0xb1, 0x96, 0x25,
+	0x64, 0x61, 0x9c, 0x5e, 0x7e, 0x9b, 0xf6, 0x13
+};
+static const u8 enc_output116[] __initconst = {
+	0xd5, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x1d, 0xe0, 0x1d, 0x03, 0xa4, 0xfb, 0x69, 0x2b,
+	0x0f, 0x13, 0x57, 0x17, 0xda, 0x3c, 0x93, 0x03,
+	0x9c, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x14, 0xbc, 0x01, 0x79, 0x57, 0xdc, 0xfa, 0x2c,
+	0xc0, 0xdb, 0xb8, 0x1d, 0xf5, 0x83, 0xcb, 0x01,
+	0x9c, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x14, 0xbc, 0x01, 0x79, 0x57, 0xdc, 0xfa, 0x2c,
+	0xc0, 0xdb, 0xb8, 0x1d, 0xf5, 0x83, 0xcb, 0x01,
+	0x49, 0xbc, 0x6e, 0x9f, 0xc5, 0x1c, 0x4d, 0x50,
+	0x30, 0x36, 0x64, 0x4d, 0x84, 0x27, 0x73, 0xd2
+};
+static const u8 enc_assoc116[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce116[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key116[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input117[] __initconst = {
+	0xdb, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0x75, 0xd5, 0x64, 0x3a, 0xa5, 0xaf, 0x93, 0x4d,
+	0x8c, 0xce, 0x39, 0x2c, 0xc3, 0xee, 0xdb, 0x47,
+	0xc0, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca,
+	0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64,
+	0x60, 0x1b, 0x5a, 0xd2, 0x06, 0x7f, 0x28, 0x06,
+	0x6a, 0x8f, 0x32, 0x81, 0x71, 0x5b, 0xa8, 0x08,
+	0x18, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2,
+	0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73,
+	0x28, 0x3f, 0x6b, 0x32, 0x18, 0x07, 0x5f, 0xc9,
+	0x5f, 0x6b, 0xb4, 0xff, 0x45, 0x6d, 0xc1, 0x11
+};
+static const u8 enc_output117[] __initconst = {
+	0xdb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xf2, 0x17, 0xae, 0x33, 0x49, 0xb6, 0xb5, 0xbb,
+	0x4e, 0x09, 0x2f, 0xa6, 0xff, 0x9e, 0xc7, 0x00,
+	0xa0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x03, 0x12, 0x92, 0xac, 0x88, 0x6a, 0x33, 0xc0,
+	0xfb, 0xd1, 0x90, 0xbc, 0xce, 0x75, 0xfc, 0x03,
+	0xa0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0x03, 0x12, 0x92, 0xac, 0x88, 0x6a, 0x33, 0xc0,
+	0xfb, 0xd1, 0x90, 0xbc, 0xce, 0x75, 0xfc, 0x03,
+	0x63, 0xda, 0x6e, 0xa2, 0x51, 0xf0, 0x39, 0x53,
+	0x2c, 0x36, 0x64, 0x5d, 0x38, 0xb7, 0x6f, 0xd7
+};
+static const u8 enc_assoc117[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce117[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key117[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+/* wycheproof - edge case intermediate sums in poly1305 */
+static const u8 enc_input118[] __initconst = {
+	0x93, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66,
+	0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c,
+	0x62, 0x48, 0x39, 0x60, 0x42, 0x16, 0xe4, 0x03,
+	0xeb, 0xcc, 0x6a, 0xf5, 0x59, 0xec, 0x8b, 0x43,
+	0x97, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca,
+	0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64,
+	0xd8, 0xc8, 0xc3, 0xfa, 0x1a, 0x9e, 0x47, 0x4a,
+	0xbe, 0x52, 0xd0, 0x2c, 0x81, 0x87, 0xe9, 0x0f,
+	0x4f, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2,
+	0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73,
+	0x90, 0xec, 0xf2, 0x1a, 0x04, 0xe6, 0x30, 0x85,
+	0x8b, 0xb6, 0x56, 0x52, 0xb5, 0xb1, 0x80, 0x16
+};
+static const u8 enc_output118[] __initconst = {
+	0x93, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xe5, 0x8a, 0xf3, 0x69, 0xae, 0x0f, 0xc2, 0xf5,
+	0x29, 0x0b, 0x7c, 0x7f, 0x65, 0x9c, 0x97, 0x04,
+	0xf7, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xbb, 0xc1, 0x0b, 0x84, 0x94, 0x8b, 0x5c, 0x8c,
+	0x2f, 0x0c, 0x72, 0x11, 0x3e, 0xa9, 0xbd, 0x04,
+	0xf7, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xbb, 0xc1, 0x0b, 0x84, 0x94, 0x8b, 0x5c, 0x8c,
+	0x2f, 0x0c, 0x72, 0x11, 0x3e, 0xa9, 0xbd, 0x04,
+	0x73, 0xeb, 0x27, 0x24, 0xb5, 0xc4, 0x05, 0xf0,
+	0x4d, 0x00, 0xd0, 0xf1, 0x58, 0x40, 0xa1, 0xc1
+};
+static const u8 enc_assoc118[] __initconst = {
+	0xff, 0xff, 0xff, 0xff
+};
+static const u8 enc_nonce118[] __initconst = {
+	0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52
+};
+static const u8 enc_key118[] __initconst = {
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f
+};
+
+static const struct chacha20poly1305_testvec
+chacha20poly1305_enc_vectors[] __initconst = {
+	{ enc_input001, enc_output001, enc_assoc001, enc_nonce001, enc_key001,
+	  sizeof(enc_input001), sizeof(enc_assoc001), sizeof(enc_nonce001) },
+	{ enc_input002, enc_output002, enc_assoc002, enc_nonce002, enc_key002,
+	  sizeof(enc_input002), sizeof(enc_assoc002), sizeof(enc_nonce002) },
+	{ enc_input003, enc_output003, enc_assoc003, enc_nonce003, enc_key003,
+	  sizeof(enc_input003), sizeof(enc_assoc003), sizeof(enc_nonce003) },
+	{ enc_input004, enc_output004, enc_assoc004, enc_nonce004, enc_key004,
+	  sizeof(enc_input004), sizeof(enc_assoc004), sizeof(enc_nonce004) },
+	{ enc_input005, enc_output005, enc_assoc005, enc_nonce005, enc_key005,
+	  sizeof(enc_input005), sizeof(enc_assoc005), sizeof(enc_nonce005) },
+	{ enc_input006, enc_output006, enc_assoc006, enc_nonce006, enc_key006,
+	  sizeof(enc_input006), sizeof(enc_assoc006), sizeof(enc_nonce006) },
+	{ enc_input007, enc_output007, enc_assoc007, enc_nonce007, enc_key007,
+	  sizeof(enc_input007), sizeof(enc_assoc007), sizeof(enc_nonce007) },
+	{ enc_input008, enc_output008, enc_assoc008, enc_nonce008, enc_key008,
+	  sizeof(enc_input008), sizeof(enc_assoc008), sizeof(enc_nonce008) },
+	{ enc_input009, enc_output009, enc_assoc009, enc_nonce009, enc_key009,
+	  sizeof(enc_input009), sizeof(enc_assoc009), sizeof(enc_nonce009) },
+	{ enc_input010, enc_output010, enc_assoc010, enc_nonce010, enc_key010,
+	  sizeof(enc_input010), sizeof(enc_assoc010), sizeof(enc_nonce010) },
+	{ enc_input011, enc_output011, enc_assoc011, enc_nonce011, enc_key011,
+	  sizeof(enc_input011), sizeof(enc_assoc011), sizeof(enc_nonce011) },
+	{ enc_input012, enc_output012, enc_assoc012, enc_nonce012, enc_key012,
+	  sizeof(enc_input012), sizeof(enc_assoc012), sizeof(enc_nonce012) },
+	{ enc_input053, enc_output053, enc_assoc053, enc_nonce053, enc_key053,
+	  sizeof(enc_input053), sizeof(enc_assoc053), sizeof(enc_nonce053) },
+	{ enc_input054, enc_output054, enc_assoc054, enc_nonce054, enc_key054,
+	  sizeof(enc_input054), sizeof(enc_assoc054), sizeof(enc_nonce054) },
+	{ enc_input055, enc_output055, enc_assoc055, enc_nonce055, enc_key055,
+	  sizeof(enc_input055), sizeof(enc_assoc055), sizeof(enc_nonce055) },
+	{ enc_input056, enc_output056, enc_assoc056, enc_nonce056, enc_key056,
+	  sizeof(enc_input056), sizeof(enc_assoc056), sizeof(enc_nonce056) },
+	{ enc_input057, enc_output057, enc_assoc057, enc_nonce057, enc_key057,
+	  sizeof(enc_input057), sizeof(enc_assoc057), sizeof(enc_nonce057) },
+	{ enc_input058, enc_output058, enc_assoc058, enc_nonce058, enc_key058,
+	  sizeof(enc_input058), sizeof(enc_assoc058), sizeof(enc_nonce058) },
+	{ enc_input059, enc_output059, enc_assoc059, enc_nonce059, enc_key059,
+	  sizeof(enc_input059), sizeof(enc_assoc059), sizeof(enc_nonce059) },
+	{ enc_input060, enc_output060, enc_assoc060, enc_nonce060, enc_key060,
+	  sizeof(enc_input060), sizeof(enc_assoc060), sizeof(enc_nonce060) },
+	{ enc_input061, enc_output061, enc_assoc061, enc_nonce061, enc_key061,
+	  sizeof(enc_input061), sizeof(enc_assoc061), sizeof(enc_nonce061) },
+	{ enc_input062, enc_output062, enc_assoc062, enc_nonce062, enc_key062,
+	  sizeof(enc_input062), sizeof(enc_assoc062), sizeof(enc_nonce062) },
+	{ enc_input063, enc_output063, enc_assoc063, enc_nonce063, enc_key063,
+	  sizeof(enc_input063), sizeof(enc_assoc063), sizeof(enc_nonce063) },
+	{ enc_input064, enc_output064, enc_assoc064, enc_nonce064, enc_key064,
+	  sizeof(enc_input064), sizeof(enc_assoc064), sizeof(enc_nonce064) },
+	{ enc_input065, enc_output065, enc_assoc065, enc_nonce065, enc_key065,
+	  sizeof(enc_input065), sizeof(enc_assoc065), sizeof(enc_nonce065) },
+	{ enc_input066, enc_output066, enc_assoc066, enc_nonce066, enc_key066,
+	  sizeof(enc_input066), sizeof(enc_assoc066), sizeof(enc_nonce066) },
+	{ enc_input067, enc_output067, enc_assoc067, enc_nonce067, enc_key067,
+	  sizeof(enc_input067), sizeof(enc_assoc067), sizeof(enc_nonce067) },
+	{ enc_input068, enc_output068, enc_assoc068, enc_nonce068, enc_key068,
+	  sizeof(enc_input068), sizeof(enc_assoc068), sizeof(enc_nonce068) },
+	{ enc_input069, enc_output069, enc_assoc069, enc_nonce069, enc_key069,
+	  sizeof(enc_input069), sizeof(enc_assoc069), sizeof(enc_nonce069) },
+	{ enc_input070, enc_output070, enc_assoc070, enc_nonce070, enc_key070,
+	  sizeof(enc_input070), sizeof(enc_assoc070), sizeof(enc_nonce070) },
+	{ enc_input071, enc_output071, enc_assoc071, enc_nonce071, enc_key071,
+	  sizeof(enc_input071), sizeof(enc_assoc071), sizeof(enc_nonce071) },
+	{ enc_input072, enc_output072, enc_assoc072, enc_nonce072, enc_key072,
+	  sizeof(enc_input072), sizeof(enc_assoc072), sizeof(enc_nonce072) },
+	{ enc_input073, enc_output073, enc_assoc073, enc_nonce073, enc_key073,
+	  sizeof(enc_input073), sizeof(enc_assoc073), sizeof(enc_nonce073) },
+	{ enc_input076, enc_output076, enc_assoc076, enc_nonce076, enc_key076,
+	  sizeof(enc_input076), sizeof(enc_assoc076), sizeof(enc_nonce076) },
+	{ enc_input077, enc_output077, enc_assoc077, enc_nonce077, enc_key077,
+	  sizeof(enc_input077), sizeof(enc_assoc077), sizeof(enc_nonce077) },
+	{ enc_input078, enc_output078, enc_assoc078, enc_nonce078, enc_key078,
+	  sizeof(enc_input078), sizeof(enc_assoc078), sizeof(enc_nonce078) },
+	{ enc_input079, enc_output079, enc_assoc079, enc_nonce079, enc_key079,
+	  sizeof(enc_input079), sizeof(enc_assoc079), sizeof(enc_nonce079) },
+	{ enc_input080, enc_output080, enc_assoc080, enc_nonce080, enc_key080,
+	  sizeof(enc_input080), sizeof(enc_assoc080), sizeof(enc_nonce080) },
+	{ enc_input081, enc_output081, enc_assoc081, enc_nonce081, enc_key081,
+	  sizeof(enc_input081), sizeof(enc_assoc081), sizeof(enc_nonce081) },
+	{ enc_input082, enc_output082, enc_assoc082, enc_nonce082, enc_key082,
+	  sizeof(enc_input082), sizeof(enc_assoc082), sizeof(enc_nonce082) },
+	{ enc_input083, enc_output083, enc_assoc083, enc_nonce083, enc_key083,
+	  sizeof(enc_input083), sizeof(enc_assoc083), sizeof(enc_nonce083) },
+	{ enc_input084, enc_output084, enc_assoc084, enc_nonce084, enc_key084,
+	  sizeof(enc_input084), sizeof(enc_assoc084), sizeof(enc_nonce084) },
+	{ enc_input085, enc_output085, enc_assoc085, enc_nonce085, enc_key085,
+	  sizeof(enc_input085), sizeof(enc_assoc085), sizeof(enc_nonce085) },
+	{ enc_input093, enc_output093, enc_assoc093, enc_nonce093, enc_key093,
+	  sizeof(enc_input093), sizeof(enc_assoc093), sizeof(enc_nonce093) },
+	{ enc_input094, enc_output094, enc_assoc094, enc_nonce094, enc_key094,
+	  sizeof(enc_input094), sizeof(enc_assoc094), sizeof(enc_nonce094) },
+	{ enc_input095, enc_output095, enc_assoc095, enc_nonce095, enc_key095,
+	  sizeof(enc_input095), sizeof(enc_assoc095), sizeof(enc_nonce095) },
+	{ enc_input096, enc_output096, enc_assoc096, enc_nonce096, enc_key096,
+	  sizeof(enc_input096), sizeof(enc_assoc096), sizeof(enc_nonce096) },
+	{ enc_input097, enc_output097, enc_assoc097, enc_nonce097, enc_key097,
+	  sizeof(enc_input097), sizeof(enc_assoc097), sizeof(enc_nonce097) },
+	{ enc_input098, enc_output098, enc_assoc098, enc_nonce098, enc_key098,
+	  sizeof(enc_input098), sizeof(enc_assoc098), sizeof(enc_nonce098) },
+	{ enc_input099, enc_output099, enc_assoc099, enc_nonce099, enc_key099,
+	  sizeof(enc_input099), sizeof(enc_assoc099), sizeof(enc_nonce099) },
+	{ enc_input100, enc_output100, enc_assoc100, enc_nonce100, enc_key100,
+	  sizeof(enc_input100), sizeof(enc_assoc100), sizeof(enc_nonce100) },
+	{ enc_input101, enc_output101, enc_assoc101, enc_nonce101, enc_key101,
+	  sizeof(enc_input101), sizeof(enc_assoc101), sizeof(enc_nonce101) },
+	{ enc_input102, enc_output102, enc_assoc102, enc_nonce102, enc_key102,
+	  sizeof(enc_input102), sizeof(enc_assoc102), sizeof(enc_nonce102) },
+	{ enc_input103, enc_output103, enc_assoc103, enc_nonce103, enc_key103,
+	  sizeof(enc_input103), sizeof(enc_assoc103), sizeof(enc_nonce103) },
+	{ enc_input104, enc_output104, enc_assoc104, enc_nonce104, enc_key104,
+	  sizeof(enc_input104), sizeof(enc_assoc104), sizeof(enc_nonce104) },
+	{ enc_input105, enc_output105, enc_assoc105, enc_nonce105, enc_key105,
+	  sizeof(enc_input105), sizeof(enc_assoc105), sizeof(enc_nonce105) },
+	{ enc_input106, enc_output106, enc_assoc106, enc_nonce106, enc_key106,
+	  sizeof(enc_input106), sizeof(enc_assoc106), sizeof(enc_nonce106) },
+	{ enc_input107, enc_output107, enc_assoc107, enc_nonce107, enc_key107,
+	  sizeof(enc_input107), sizeof(enc_assoc107), sizeof(enc_nonce107) },
+	{ enc_input108, enc_output108, enc_assoc108, enc_nonce108, enc_key108,
+	  sizeof(enc_input108), sizeof(enc_assoc108), sizeof(enc_nonce108) },
+	{ enc_input109, enc_output109, enc_assoc109, enc_nonce109, enc_key109,
+	  sizeof(enc_input109), sizeof(enc_assoc109), sizeof(enc_nonce109) },
+	{ enc_input110, enc_output110, enc_assoc110, enc_nonce110, enc_key110,
+	  sizeof(enc_input110), sizeof(enc_assoc110), sizeof(enc_nonce110) },
+	{ enc_input111, enc_output111, enc_assoc111, enc_nonce111, enc_key111,
+	  sizeof(enc_input111), sizeof(enc_assoc111), sizeof(enc_nonce111) },
+	{ enc_input112, enc_output112, enc_assoc112, enc_nonce112, enc_key112,
+	  sizeof(enc_input112), sizeof(enc_assoc112), sizeof(enc_nonce112) },
+	{ enc_input113, enc_output113, enc_assoc113, enc_nonce113, enc_key113,
+	  sizeof(enc_input113), sizeof(enc_assoc113), sizeof(enc_nonce113) },
+	{ enc_input114, enc_output114, enc_assoc114, enc_nonce114, enc_key114,
+	  sizeof(enc_input114), sizeof(enc_assoc114), sizeof(enc_nonce114) },
+	{ enc_input115, enc_output115, enc_assoc115, enc_nonce115, enc_key115,
+	  sizeof(enc_input115), sizeof(enc_assoc115), sizeof(enc_nonce115) },
+	{ enc_input116, enc_output116, enc_assoc116, enc_nonce116, enc_key116,
+	  sizeof(enc_input116), sizeof(enc_assoc116), sizeof(enc_nonce116) },
+	{ enc_input117, enc_output117, enc_assoc117, enc_nonce117, enc_key117,
+	  sizeof(enc_input117), sizeof(enc_assoc117), sizeof(enc_nonce117) },
+	{ enc_input118, enc_output118, enc_assoc118, enc_nonce118, enc_key118,
+	  sizeof(enc_input118), sizeof(enc_assoc118), sizeof(enc_nonce118) }
+};
+
+static const u8 dec_input001[] __initconst = {
+	0x64, 0xa0, 0x86, 0x15, 0x75, 0x86, 0x1a, 0xf4,
+	0x60, 0xf0, 0x62, 0xc7, 0x9b, 0xe6, 0x43, 0xbd,
+	0x5e, 0x80, 0x5c, 0xfd, 0x34, 0x5c, 0xf3, 0x89,
+	0xf1, 0x08, 0x67, 0x0a, 0xc7, 0x6c, 0x8c, 0xb2,
+	0x4c, 0x6c, 0xfc, 0x18, 0x75, 0x5d, 0x43, 0xee,
+	0xa0, 0x9e, 0xe9, 0x4e, 0x38, 0x2d, 0x26, 0xb0,
+	0xbd, 0xb7, 0xb7, 0x3c, 0x32, 0x1b, 0x01, 0x00,
+	0xd4, 0xf0, 0x3b, 0x7f, 0x35, 0x58, 0x94, 0xcf,
+	0x33, 0x2f, 0x83, 0x0e, 0x71, 0x0b, 0x97, 0xce,
+	0x98, 0xc8, 0xa8, 0x4a, 0xbd, 0x0b, 0x94, 0x81,
+	0x14, 0xad, 0x17, 0x6e, 0x00, 0x8d, 0x33, 0xbd,
+	0x60, 0xf9, 0x82, 0xb1, 0xff, 0x37, 0xc8, 0x55,
+	0x97, 0x97, 0xa0, 0x6e, 0xf4, 0xf0, 0xef, 0x61,
+	0xc1, 0x86, 0x32, 0x4e, 0x2b, 0x35, 0x06, 0x38,
+	0x36, 0x06, 0x90, 0x7b, 0x6a, 0x7c, 0x02, 0xb0,
+	0xf9, 0xf6, 0x15, 0x7b, 0x53, 0xc8, 0x67, 0xe4,
+	0xb9, 0x16, 0x6c, 0x76, 0x7b, 0x80, 0x4d, 0x46,
+	0xa5, 0x9b, 0x52, 0x16, 0xcd, 0xe7, 0xa4, 0xe9,
+	0x90, 0x40, 0xc5, 0xa4, 0x04, 0x33, 0x22, 0x5e,
+	0xe2, 0x82, 0xa1, 0xb0, 0xa0, 0x6c, 0x52, 0x3e,
+	0xaf, 0x45, 0x34, 0xd7, 0xf8, 0x3f, 0xa1, 0x15,
+	0x5b, 0x00, 0x47, 0x71, 0x8c, 0xbc, 0x54, 0x6a,
+	0x0d, 0x07, 0x2b, 0x04, 0xb3, 0x56, 0x4e, 0xea,
+	0x1b, 0x42, 0x22, 0x73, 0xf5, 0x48, 0x27, 0x1a,
+	0x0b, 0xb2, 0x31, 0x60, 0x53, 0xfa, 0x76, 0x99,
+	0x19, 0x55, 0xeb, 0xd6, 0x31, 0x59, 0x43, 0x4e,
+	0xce, 0xbb, 0x4e, 0x46, 0x6d, 0xae, 0x5a, 0x10,
+	0x73, 0xa6, 0x72, 0x76, 0x27, 0x09, 0x7a, 0x10,
+	0x49, 0xe6, 0x17, 0xd9, 0x1d, 0x36, 0x10, 0x94,
+	0xfa, 0x68, 0xf0, 0xff, 0x77, 0x98, 0x71, 0x30,
+	0x30, 0x5b, 0xea, 0xba, 0x2e, 0xda, 0x04, 0xdf,
+	0x99, 0x7b, 0x71, 0x4d, 0x6c, 0x6f, 0x2c, 0x29,
+	0xa6, 0xad, 0x5c, 0xb4, 0x02, 0x2b, 0x02, 0x70,
+	0x9b, 0xee, 0xad, 0x9d, 0x67, 0x89, 0x0c, 0xbb,
+	0x22, 0x39, 0x23, 0x36, 0xfe, 0xa1, 0x85, 0x1f,
+	0x38
+};
+static const u8 dec_output001[] __initconst = {
+	0x49, 0x6e, 0x74, 0x65, 0x72, 0x6e, 0x65, 0x74,
+	0x2d, 0x44, 0x72, 0x61, 0x66, 0x74, 0x73, 0x20,
+	0x61, 0x72, 0x65, 0x20, 0x64, 0x72, 0x61, 0x66,
+	0x74, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65,
+	0x6e, 0x74, 0x73, 0x20, 0x76, 0x61, 0x6c, 0x69,
+	0x64, 0x20, 0x66, 0x6f, 0x72, 0x20, 0x61, 0x20,
+	0x6d, 0x61, 0x78, 0x69, 0x6d, 0x75, 0x6d, 0x20,
+	0x6f, 0x66, 0x20, 0x73, 0x69, 0x78, 0x20, 0x6d,
+	0x6f, 0x6e, 0x74, 0x68, 0x73, 0x20, 0x61, 0x6e,
+	0x64, 0x20, 0x6d, 0x61, 0x79, 0x20, 0x62, 0x65,
+	0x20, 0x75, 0x70, 0x64, 0x61, 0x74, 0x65, 0x64,
+	0x2c, 0x20, 0x72, 0x65, 0x70, 0x6c, 0x61, 0x63,
+	0x65, 0x64, 0x2c, 0x20, 0x6f, 0x72, 0x20, 0x6f,
+	0x62, 0x73, 0x6f, 0x6c, 0x65, 0x74, 0x65, 0x64,
+	0x20, 0x62, 0x79, 0x20, 0x6f, 0x74, 0x68, 0x65,
+	0x72, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65,
+	0x6e, 0x74, 0x73, 0x20, 0x61, 0x74, 0x20, 0x61,
+	0x6e, 0x79, 0x20, 0x74, 0x69, 0x6d, 0x65, 0x2e,
+	0x20, 0x49, 0x74, 0x20, 0x69, 0x73, 0x20, 0x69,
+	0x6e, 0x61, 0x70, 0x70, 0x72, 0x6f, 0x70, 0x72,
+	0x69, 0x61, 0x74, 0x65, 0x20, 0x74, 0x6f, 0x20,
+	0x75, 0x73, 0x65, 0x20, 0x49, 0x6e, 0x74, 0x65,
+	0x72, 0x6e, 0x65, 0x74, 0x2d, 0x44, 0x72, 0x61,
+	0x66, 0x74, 0x73, 0x20, 0x61, 0x73, 0x20, 0x72,
+	0x65, 0x66, 0x65, 0x72, 0x65, 0x6e, 0x63, 0x65,
+	0x20, 0x6d, 0x61, 0x74, 0x65, 0x72, 0x69, 0x61,
+	0x6c, 0x20, 0x6f, 0x72, 0x20, 0x74, 0x6f, 0x20,
+	0x63, 0x69, 0x74, 0x65, 0x20, 0x74, 0x68, 0x65,
+	0x6d, 0x20, 0x6f, 0x74, 0x68, 0x65, 0x72, 0x20,
+	0x74, 0x68, 0x61, 0x6e, 0x20, 0x61, 0x73, 0x20,
+	0x2f, 0xe2, 0x80, 0x9c, 0x77, 0x6f, 0x72, 0x6b,
+	0x20, 0x69, 0x6e, 0x20, 0x70, 0x72, 0x6f, 0x67,
+	0x72, 0x65, 0x73, 0x73, 0x2e, 0x2f, 0xe2, 0x80,
+	0x9d
+};
+static const u8 dec_assoc001[] __initconst = {
+	0xf3, 0x33, 0x88, 0x86, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x4e, 0x91
+};
+static const u8 dec_nonce001[] __initconst = {
+	0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08
+};
+static const u8 dec_key001[] __initconst = {
+	0x1c, 0x92, 0x40, 0xa5, 0xeb, 0x55, 0xd3, 0x8a,
+	0xf3, 0x33, 0x88, 0x86, 0x04, 0xf6, 0xb5, 0xf0,
+	0x47, 0x39, 0x17, 0xc1, 0x40, 0x2b, 0x80, 0x09,
+	0x9d, 0xca, 0x5c, 0xbc, 0x20, 0x70, 0x75, 0xc0
+};
+
+static const u8 dec_input002[] __initconst = {
+	0xea, 0xe0, 0x1e, 0x9e, 0x2c, 0x91, 0xaa, 0xe1,
+	0xdb, 0x5d, 0x99, 0x3f, 0x8a, 0xf7, 0x69, 0x92
+};
+static const u8 dec_output002[] __initconst = { };
+static const u8 dec_assoc002[] __initconst = { };
+static const u8 dec_nonce002[] __initconst = {
+	0xca, 0xbf, 0x33, 0x71, 0x32, 0x45, 0x77, 0x8e
+};
+static const u8 dec_key002[] __initconst = {
+	0x4c, 0xf5, 0x96, 0x83, 0x38, 0xe6, 0xae, 0x7f,
+	0x2d, 0x29, 0x25, 0x76, 0xd5, 0x75, 0x27, 0x86,
+	0x91, 0x9a, 0x27, 0x7a, 0xfb, 0x46, 0xc5, 0xef,
+	0x94, 0x81, 0x79, 0x57, 0x14, 0x59, 0x40, 0x68
+};
+
+static const u8 dec_input003[] __initconst = {
+	0xdd, 0x6b, 0x3b, 0x82, 0xce, 0x5a, 0xbd, 0xd6,
+	0xa9, 0x35, 0x83, 0xd8, 0x8c, 0x3d, 0x85, 0x77
+};
+static const u8 dec_output003[] __initconst = { };
+static const u8 dec_assoc003[] __initconst = {
+	0x33, 0x10, 0x41, 0x12, 0x1f, 0xf3, 0xd2, 0x6b
+};
+static const u8 dec_nonce003[] __initconst = {
+	0x3d, 0x86, 0xb5, 0x6b, 0xc8, 0xa3, 0x1f, 0x1d
+};
+static const u8 dec_key003[] __initconst = {
+	0x2d, 0xb0, 0x5d, 0x40, 0xc8, 0xed, 0x44, 0x88,
+	0x34, 0xd1, 0x13, 0xaf, 0x57, 0xa1, 0xeb, 0x3a,
+	0x2a, 0x80, 0x51, 0x36, 0xec, 0x5b, 0xbc, 0x08,
+	0x93, 0x84, 0x21, 0xb5, 0x13, 0x88, 0x3c, 0x0d
+};
+
+static const u8 dec_input004[] __initconst = {
+	0xb7, 0x1b, 0xb0, 0x73, 0x59, 0xb0, 0x84, 0xb2,
+	0x6d, 0x8e, 0xab, 0x94, 0x31, 0xa1, 0xae, 0xac,
+	0x89
+};
+static const u8 dec_output004[] __initconst = {
+	0xa4
+};
+static const u8 dec_assoc004[] __initconst = {
+	0x6a, 0xe2, 0xad, 0x3f, 0x88, 0x39, 0x5a, 0x40
+};
+static const u8 dec_nonce004[] __initconst = {
+	0xd2, 0x32, 0x1f, 0x29, 0x28, 0xc6, 0xc4, 0xc4
+};
+static const u8 dec_key004[] __initconst = {
+	0x4b, 0x28, 0x4b, 0xa3, 0x7b, 0xbe, 0xe9, 0xf8,
+	0x31, 0x80, 0x82, 0xd7, 0xd8, 0xe8, 0xb5, 0xa1,
+	0xe2, 0x18, 0x18, 0x8a, 0x9c, 0xfa, 0xa3, 0x3d,
+	0x25, 0x71, 0x3e, 0x40, 0xbc, 0x54, 0x7a, 0x3e
+};
+
+static const u8 dec_input005[] __initconst = {
+	0xbf, 0xe1, 0x5b, 0x0b, 0xdb, 0x6b, 0xf5, 0x5e,
+	0x6c, 0x5d, 0x84, 0x44, 0x39, 0x81, 0xc1, 0x9c,
+	0xac
+};
+static const u8 dec_output005[] __initconst = {
+	0x2d
+};
+static const u8 dec_assoc005[] __initconst = { };
+static const u8 dec_nonce005[] __initconst = {
+	0x20, 0x1c, 0xaa, 0x5f, 0x9c, 0xbf, 0x92, 0x30
+};
+static const u8 dec_key005[] __initconst = {
+	0x66, 0xca, 0x9c, 0x23, 0x2a, 0x4b, 0x4b, 0x31,
+	0x0e, 0x92, 0x89, 0x8b, 0xf4, 0x93, 0xc7, 0x87,
+	0x98, 0xa3, 0xd8, 0x39, 0xf8, 0xf4, 0xa7, 0x01,
+	0xc0, 0x2e, 0x0a, 0xa6, 0x7e, 0x5a, 0x78, 0x87
+};
+
+static const u8 dec_input006[] __initconst = {
+	0x8b, 0x06, 0xd3, 0x31, 0xb0, 0x93, 0x45, 0xb1,
+	0x75, 0x6e, 0x26, 0xf9, 0x67, 0xbc, 0x90, 0x15,
+	0x81, 0x2c, 0xb5, 0xf0, 0xc6, 0x2b, 0xc7, 0x8c,
+	0x56, 0xd1, 0xbf, 0x69, 0x6c, 0x07, 0xa0, 0xda,
+	0x65, 0x27, 0xc9, 0x90, 0x3d, 0xef, 0x4b, 0x11,
+	0x0f, 0x19, 0x07, 0xfd, 0x29, 0x92, 0xd9, 0xc8,
+	0xf7, 0x99, 0x2e, 0x4a, 0xd0, 0xb8, 0x2c, 0xdc,
+	0x93, 0xf5, 0x9e, 0x33, 0x78, 0xd1, 0x37, 0xc3,
+	0x66, 0xd7, 0x5e, 0xbc, 0x44, 0xbf, 0x53, 0xa5,
+	0xbc, 0xc4, 0xcb, 0x7b, 0x3a, 0x8e, 0x7f, 0x02,
+	0xbd, 0xbb, 0xe7, 0xca, 0xa6, 0x6c, 0x6b, 0x93,
+	0x21, 0x93, 0x10, 0x61, 0xe7, 0x69, 0xd0, 0x78,
+	0xf3, 0x07, 0x5a, 0x1a, 0x8f, 0x73, 0xaa, 0xb1,
+	0x4e, 0xd3, 0xda, 0x4f, 0xf3, 0x32, 0xe1, 0x66,
+	0x3e, 0x6c, 0xc6, 0x13, 0xba, 0x06, 0x5b, 0xfc,
+	0x6a, 0xe5, 0x6f, 0x60, 0xfb, 0x07, 0x40, 0xb0,
+	0x8c, 0x9d, 0x84, 0x43, 0x6b, 0xc1, 0xf7, 0x8d,
+	0x8d, 0x31, 0xf7, 0x7a, 0x39, 0x4d, 0x8f, 0x9a,
+	0xeb
+};
+static const u8 dec_output006[] __initconst = {
+	0x33, 0x2f, 0x94, 0xc1, 0xa4, 0xef, 0xcc, 0x2a,
+	0x5b, 0xa6, 0xe5, 0x8f, 0x1d, 0x40, 0xf0, 0x92,
+	0x3c, 0xd9, 0x24, 0x11, 0xa9, 0x71, 0xf9, 0x37,
+	0x14, 0x99, 0xfa, 0xbe, 0xe6, 0x80, 0xde, 0x50,
+	0xc9, 0x96, 0xd4, 0xb0, 0xec, 0x9e, 0x17, 0xec,
+	0xd2, 0x5e, 0x72, 0x99, 0xfc, 0x0a, 0xe1, 0xcb,
+	0x48, 0xd2, 0x85, 0xdd, 0x2f, 0x90, 0xe0, 0x66,
+	0x3b, 0xe6, 0x20, 0x74, 0xbe, 0x23, 0x8f, 0xcb,
+	0xb4, 0xe4, 0xda, 0x48, 0x40, 0xa6, 0xd1, 0x1b,
+	0xc7, 0x42, 0xce, 0x2f, 0x0c, 0xa6, 0x85, 0x6e,
+	0x87, 0x37, 0x03, 0xb1, 0x7c, 0x25, 0x96, 0xa3,
+	0x05, 0xd8, 0xb0, 0xf4, 0xed, 0xea, 0xc2, 0xf0,
+	0x31, 0x98, 0x6c, 0xd1, 0x14, 0x25, 0xc0, 0xcb,
+	0x01, 0x74, 0xd0, 0x82, 0xf4, 0x36, 0xf5, 0x41,
+	0xd5, 0xdc, 0xca, 0xc5, 0xbb, 0x98, 0xfe, 0xfc,
+	0x69, 0x21, 0x70, 0xd8, 0xa4, 0x4b, 0xc8, 0xde,
+	0x8f
+};
+static const u8 dec_assoc006[] __initconst = {
+	0x70, 0xd3, 0x33, 0xf3, 0x8b, 0x18, 0x0b
+};
+static const u8 dec_nonce006[] __initconst = {
+	0xdf, 0x51, 0x84, 0x82, 0x42, 0x0c, 0x75, 0x9c
+};
+static const u8 dec_key006[] __initconst = {
+	0x68, 0x7b, 0x8d, 0x8e, 0xe3, 0xc4, 0xdd, 0xae,
+	0xdf, 0x72, 0x7f, 0x53, 0x72, 0x25, 0x1e, 0x78,
+	0x91, 0xcb, 0x69, 0x76, 0x1f, 0x49, 0x93, 0xf9,
+	0x6f, 0x21, 0xcc, 0x39, 0x9c, 0xad, 0xb1, 0x01
+};
+
+static const u8 dec_input007[] __initconst = {
+	0x85, 0x04, 0xc2, 0xed, 0x8d, 0xfd, 0x97, 0x5c,
+	0xd2, 0xb7, 0xe2, 0xc1, 0x6b, 0xa3, 0xba, 0xf8,
+	0xc9, 0x50, 0xc3, 0xc6, 0xa5, 0xe3, 0xa4, 0x7c,
+	0xc3, 0x23, 0x49, 0x5e, 0xa9, 0xb9, 0x32, 0xeb,
+	0x8a, 0x7c, 0xca, 0xe5, 0xec, 0xfb, 0x7c, 0xc0,
+	0xcb, 0x7d, 0xdc, 0x2c, 0x9d, 0x92, 0x55, 0x21,
+	0x0a, 0xc8, 0x43, 0x63, 0x59, 0x0a, 0x31, 0x70,
+	0x82, 0x67, 0x41, 0x03, 0xf8, 0xdf, 0xf2, 0xac,
+	0xa7, 0x02, 0xd4, 0xd5, 0x8a, 0x2d, 0xc8, 0x99,
+	0x19, 0x66, 0xd0, 0xf6, 0x88, 0x2c, 0x77, 0xd9,
+	0xd4, 0x0d, 0x6c, 0xbd, 0x98, 0xde, 0xe7, 0x7f,
+	0xad, 0x7e, 0x8a, 0xfb, 0xe9, 0x4b, 0xe5, 0xf7,
+	0xe5, 0x50, 0xa0, 0x90, 0x3f, 0xd6, 0x22, 0x53,
+	0xe3, 0xfe, 0x1b, 0xcc, 0x79, 0x3b, 0xec, 0x12,
+	0x47, 0x52, 0xa7, 0xd6, 0x04, 0xe3, 0x52, 0xe6,
+	0x93, 0x90, 0x91, 0x32, 0x73, 0x79, 0xb8, 0xd0,
+	0x31, 0xde, 0x1f, 0x9f, 0x2f, 0x05, 0x38, 0x54,
+	0x2f, 0x35, 0x04, 0x39, 0xe0, 0xa7, 0xba, 0xc6,
+	0x52, 0xf6, 0x37, 0x65, 0x4c, 0x07, 0xa9, 0x7e,
+	0xb3, 0x21, 0x6f, 0x74, 0x8c, 0xc9, 0xde, 0xdb,
+	0x65, 0x1b, 0x9b, 0xaa, 0x60, 0xb1, 0x03, 0x30,
+	0x6b, 0xb2, 0x03, 0xc4, 0x1c, 0x04, 0xf8, 0x0f,
+	0x64, 0xaf, 0x46, 0xe4, 0x65, 0x99, 0x49, 0xe2,
+	0xea, 0xce, 0x78, 0x00, 0xd8, 0x8b, 0xd5, 0x2e,
+	0xcf, 0xfc, 0x40, 0x49, 0xe8, 0x58, 0xdc, 0x34,
+	0x9c, 0x8c, 0x61, 0xbf, 0x0a, 0x8e, 0xec, 0x39,
+	0xa9, 0x30, 0x05, 0x5a, 0xd2, 0x56, 0x01, 0xc7,
+	0xda, 0x8f, 0x4e, 0xbb, 0x43, 0xa3, 0x3a, 0xf9,
+	0x15, 0x2a, 0xd0, 0xa0, 0x7a, 0x87, 0x34, 0x82,
+	0xfe, 0x8a, 0xd1, 0x2d, 0x5e, 0xc7, 0xbf, 0x04,
+	0x53, 0x5f, 0x3b, 0x36, 0xd4, 0x25, 0x5c, 0x34,
+	0x7a, 0x8d, 0xd5, 0x05, 0xce, 0x72, 0xca, 0xef,
+	0x7a, 0x4b, 0xbc, 0xb0, 0x10, 0x5c, 0x96, 0x42,
+	0x3a, 0x00, 0x98, 0xcd, 0x15, 0xe8, 0xb7, 0x53
+};
+static const u8 dec_output007[] __initconst = {
+	0x9b, 0x18, 0xdb, 0xdd, 0x9a, 0x0f, 0x3e, 0xa5,
+	0x15, 0x17, 0xde, 0xdf, 0x08, 0x9d, 0x65, 0x0a,
+	0x67, 0x30, 0x12, 0xe2, 0x34, 0x77, 0x4b, 0xc1,
+	0xd9, 0xc6, 0x1f, 0xab, 0xc6, 0x18, 0x50, 0x17,
+	0xa7, 0x9d, 0x3c, 0xa6, 0xc5, 0x35, 0x8c, 0x1c,
+	0xc0, 0xa1, 0x7c, 0x9f, 0x03, 0x89, 0xca, 0xe1,
+	0xe6, 0xe9, 0xd4, 0xd3, 0x88, 0xdb, 0xb4, 0x51,
+	0x9d, 0xec, 0xb4, 0xfc, 0x52, 0xee, 0x6d, 0xf1,
+	0x75, 0x42, 0xc6, 0xfd, 0xbd, 0x7a, 0x8e, 0x86,
+	0xfc, 0x44, 0xb3, 0x4f, 0xf3, 0xea, 0x67, 0x5a,
+	0x41, 0x13, 0xba, 0xb0, 0xdc, 0xe1, 0xd3, 0x2a,
+	0x7c, 0x22, 0xb3, 0xca, 0xac, 0x6a, 0x37, 0x98,
+	0x3e, 0x1d, 0x40, 0x97, 0xf7, 0x9b, 0x1d, 0x36,
+	0x6b, 0xb3, 0x28, 0xbd, 0x60, 0x82, 0x47, 0x34,
+	0xaa, 0x2f, 0x7d, 0xe9, 0xa8, 0x70, 0x81, 0x57,
+	0xd4, 0xb9, 0x77, 0x0a, 0x9d, 0x29, 0xa7, 0x84,
+	0x52, 0x4f, 0xc2, 0x4a, 0x40, 0x3b, 0x3c, 0xd4,
+	0xc9, 0x2a, 0xdb, 0x4a, 0x53, 0xc4, 0xbe, 0x80,
+	0xe9, 0x51, 0x7f, 0x8f, 0xc7, 0xa2, 0xce, 0x82,
+	0x5c, 0x91, 0x1e, 0x74, 0xd9, 0xd0, 0xbd, 0xd5,
+	0xf3, 0xfd, 0xda, 0x4d, 0x25, 0xb4, 0xbb, 0x2d,
+	0xac, 0x2f, 0x3d, 0x71, 0x85, 0x7b, 0xcf, 0x3c,
+	0x7b, 0x3e, 0x0e, 0x22, 0x78, 0x0c, 0x29, 0xbf,
+	0xe4, 0xf4, 0x57, 0xb3, 0xcb, 0x49, 0xa0, 0xfc,
+	0x1e, 0x05, 0x4e, 0x16, 0xbc, 0xd5, 0xa8, 0xa3,
+	0xee, 0x05, 0x35, 0xc6, 0x7c, 0xab, 0x60, 0x14,
+	0x55, 0x1a, 0x8e, 0xc5, 0x88, 0x5d, 0xd5, 0x81,
+	0xc2, 0x81, 0xa5, 0xc4, 0x60, 0xdb, 0xaf, 0x77,
+	0x91, 0xe1, 0xce, 0xa2, 0x7e, 0x7f, 0x42, 0xe3,
+	0xb0, 0x13, 0x1c, 0x1f, 0x25, 0x60, 0x21, 0xe2,
+	0x40, 0x5f, 0x99, 0xb7, 0x73, 0xec, 0x9b, 0x2b,
+	0xf0, 0x65, 0x11, 0xc8, 0xd0, 0x0a, 0x9f, 0xd3
+};
+static const u8 dec_assoc007[] __initconst = { };
+static const u8 dec_nonce007[] __initconst = {
+	0xde, 0x7b, 0xef, 0xc3, 0x65, 0x1b, 0x68, 0xb0
+};
+static const u8 dec_key007[] __initconst = {
+	0x8d, 0xb8, 0x91, 0x48, 0xf0, 0xe7, 0x0a, 0xbd,
+	0xf9, 0x3f, 0xcd, 0xd9, 0xa0, 0x1e, 0x42, 0x4c,
+	0xe7, 0xde, 0x25, 0x3d, 0xa3, 0xd7, 0x05, 0x80,
+	0x8d, 0xf2, 0x82, 0xac, 0x44, 0x16, 0x51, 0x01
+};
+
+static const u8 dec_input008[] __initconst = {
+	0x14, 0xf6, 0x41, 0x37, 0xa6, 0xd4, 0x27, 0xcd,
+	0xdb, 0x06, 0x3e, 0x9a, 0x4e, 0xab, 0xd5, 0xb1,
+	0x1e, 0x6b, 0xd2, 0xbc, 0x11, 0xf4, 0x28, 0x93,
+	0x63, 0x54, 0xef, 0xbb, 0x5e, 0x1d, 0x3a, 0x1d,
+	0x37, 0x3c, 0x0a, 0x6c, 0x1e, 0xc2, 0xd1, 0x2c,
+	0xb5, 0xa3, 0xb5, 0x7b, 0xb8, 0x8f, 0x25, 0xa6,
+	0x1b, 0x61, 0x1c, 0xec, 0x28, 0x58, 0x26, 0xa4,
+	0xa8, 0x33, 0x28, 0x25, 0x5c, 0x45, 0x05, 0xe5,
+	0x6c, 0x99, 0xe5, 0x45, 0xc4, 0xa2, 0x03, 0x84,
+	0x03, 0x73, 0x1e, 0x8c, 0x49, 0xac, 0x20, 0xdd,
+	0x8d, 0xb3, 0xc4, 0xf5, 0xe7, 0x4f, 0xf1, 0xed,
+	0xa1, 0x98, 0xde, 0xa4, 0x96, 0xdd, 0x2f, 0xab,
+	0xab, 0x97, 0xcf, 0x3e, 0xd2, 0x9e, 0xb8, 0x13,
+	0x07, 0x28, 0x29, 0x19, 0xaf, 0xfd, 0xf2, 0x49,
+	0x43, 0xea, 0x49, 0x26, 0x91, 0xc1, 0x07, 0xd6,
+	0xbb, 0x81, 0x75, 0x35, 0x0d, 0x24, 0x7f, 0xc8,
+	0xda, 0xd4, 0xb7, 0xeb, 0xe8, 0x5c, 0x09, 0xa2,
+	0x2f, 0xdc, 0x28, 0x7d, 0x3a, 0x03, 0xfa, 0x94,
+	0xb5, 0x1d, 0x17, 0x99, 0x36, 0xc3, 0x1c, 0x18,
+	0x34, 0xe3, 0x9f, 0xf5, 0x55, 0x7c, 0xb0, 0x60,
+	0x9d, 0xff, 0xac, 0xd4, 0x61, 0xf2, 0xad, 0xf8,
+	0xce, 0xc7, 0xbe, 0x5c, 0xd2, 0x95, 0xa8, 0x4b,
+	0x77, 0x13, 0x19, 0x59, 0x26, 0xc9, 0xb7, 0x8f,
+	0x6a, 0xcb, 0x2d, 0x37, 0x91, 0xea, 0x92, 0x9c,
+	0x94, 0x5b, 0xda, 0x0b, 0xce, 0xfe, 0x30, 0x20,
+	0xf8, 0x51, 0xad, 0xf2, 0xbe, 0xe7, 0xc7, 0xff,
+	0xb3, 0x33, 0x91, 0x6a, 0xc9, 0x1a, 0x41, 0xc9,
+	0x0f, 0xf3, 0x10, 0x0e, 0xfd, 0x53, 0xff, 0x6c,
+	0x16, 0x52, 0xd9, 0xf3, 0xf7, 0x98, 0x2e, 0xc9,
+	0x07, 0x31, 0x2c, 0x0c, 0x72, 0xd7, 0xc5, 0xc6,
+	0x08, 0x2a, 0x7b, 0xda, 0xbd, 0x7e, 0x02, 0xea,
+	0x1a, 0xbb, 0xf2, 0x04, 0x27, 0x61, 0x28, 0x8e,
+	0xf5, 0x04, 0x03, 0x1f, 0x4c, 0x07, 0x55, 0x82,
+	0xec, 0x1e, 0xd7, 0x8b, 0x2f, 0x65, 0x56, 0xd1,
+	0xd9, 0x1e, 0x3c, 0xe9, 0x1f, 0x5e, 0x98, 0x70,
+	0x38, 0x4a, 0x8c, 0x49, 0xc5, 0x43, 0xa0, 0xa1,
+	0x8b, 0x74, 0x9d, 0x4c, 0x62, 0x0d, 0x10, 0x0c,
+	0xf4, 0x6c, 0x8f, 0xe0, 0xaa, 0x9a, 0x8d, 0xb7,
+	0xe0, 0xbe, 0x4c, 0x87, 0xf1, 0x98, 0x2f, 0xcc,
+	0xed, 0xc0, 0x52, 0x29, 0xdc, 0x83, 0xf8, 0xfc,
+	0x2c, 0x0e, 0xa8, 0x51, 0x4d, 0x80, 0x0d, 0xa3,
+	0xfe, 0xd8, 0x37, 0xe7, 0x41, 0x24, 0xfc, 0xfb,
+	0x75, 0xe3, 0x71, 0x7b, 0x57, 0x45, 0xf5, 0x97,
+	0x73, 0x65, 0x63, 0x14, 0x74, 0xb8, 0x82, 0x9f,
+	0xf8, 0x60, 0x2f, 0x8a, 0xf2, 0x4e, 0xf1, 0x39,
+	0xda, 0x33, 0x91, 0xf8, 0x36, 0xe0, 0x8d, 0x3f,
+	0x1f, 0x3b, 0x56, 0xdc, 0xa0, 0x8f, 0x3c, 0x9d,
+	0x71, 0x52, 0xa7, 0xb8, 0xc0, 0xa5, 0xc6, 0xa2,
+	0x73, 0xda, 0xf4, 0x4b, 0x74, 0x5b, 0x00, 0x3d,
+	0x99, 0xd7, 0x96, 0xba, 0xe6, 0xe1, 0xa6, 0x96,
+	0x38, 0xad, 0xb3, 0xc0, 0xd2, 0xba, 0x91, 0x6b,
+	0xf9, 0x19, 0xdd, 0x3b, 0xbe, 0xbe, 0x9c, 0x20,
+	0x50, 0xba, 0xa1, 0xd0, 0xce, 0x11, 0xbd, 0x95,
+	0xd8, 0xd1, 0xdd, 0x33, 0x85, 0x74, 0xdc, 0xdb,
+	0x66, 0x76, 0x44, 0xdc, 0x03, 0x74, 0x48, 0x35,
+	0x98, 0xb1, 0x18, 0x47, 0x94, 0x7d, 0xff, 0x62,
+	0xe4, 0x58, 0x78, 0xab, 0xed, 0x95, 0x36, 0xd9,
+	0x84, 0x91, 0x82, 0x64, 0x41, 0xbb, 0x58, 0xe6,
+	0x1c, 0x20, 0x6d, 0x15, 0x6b, 0x13, 0x96, 0xe8,
+	0x35, 0x7f, 0xdc, 0x40, 0x2c, 0xe9, 0xbc, 0x8a,
+	0x4f, 0x92, 0xec, 0x06, 0x2d, 0x50, 0xdf, 0x93,
+	0x5d, 0x65, 0x5a, 0xa8, 0xfc, 0x20, 0x50, 0x14,
+	0xa9, 0x8a, 0x7e, 0x1d, 0x08, 0x1f, 0xe2, 0x99,
+	0xd0, 0xbe, 0xfb, 0x3a, 0x21, 0x9d, 0xad, 0x86,
+	0x54, 0xfd, 0x0d, 0x98, 0x1c, 0x5a, 0x6f, 0x1f,
+	0x9a, 0x40, 0xcd, 0xa2, 0xff, 0x6a, 0xf1, 0x54
+};
+static const u8 dec_output008[] __initconst = {
+	0xc3, 0x09, 0x94, 0x62, 0xe6, 0x46, 0x2e, 0x10,
+	0xbe, 0x00, 0xe4, 0xfc, 0xf3, 0x40, 0xa3, 0xe2,
+	0x0f, 0xc2, 0x8b, 0x28, 0xdc, 0xba, 0xb4, 0x3c,
+	0xe4, 0x21, 0x58, 0x61, 0xcd, 0x8b, 0xcd, 0xfb,
+	0xac, 0x94, 0xa1, 0x45, 0xf5, 0x1c, 0xe1, 0x12,
+	0xe0, 0x3b, 0x67, 0x21, 0x54, 0x5e, 0x8c, 0xaa,
+	0xcf, 0xdb, 0xb4, 0x51, 0xd4, 0x13, 0xda, 0xe6,
+	0x83, 0x89, 0xb6, 0x92, 0xe9, 0x21, 0x76, 0xa4,
+	0x93, 0x7d, 0x0e, 0xfd, 0x96, 0x36, 0x03, 0x91,
+	0x43, 0x5c, 0x92, 0x49, 0x62, 0x61, 0x7b, 0xeb,
+	0x43, 0x89, 0xb8, 0x12, 0x20, 0x43, 0xd4, 0x47,
+	0x06, 0x84, 0xee, 0x47, 0xe9, 0x8a, 0x73, 0x15,
+	0x0f, 0x72, 0xcf, 0xed, 0xce, 0x96, 0xb2, 0x7f,
+	0x21, 0x45, 0x76, 0xeb, 0x26, 0x28, 0x83, 0x6a,
+	0xad, 0xaa, 0xa6, 0x81, 0xd8, 0x55, 0xb1, 0xa3,
+	0x85, 0xb3, 0x0c, 0xdf, 0xf1, 0x69, 0x2d, 0x97,
+	0x05, 0x2a, 0xbc, 0x7c, 0x7b, 0x25, 0xf8, 0x80,
+	0x9d, 0x39, 0x25, 0xf3, 0x62, 0xf0, 0x66, 0x5e,
+	0xf4, 0xa0, 0xcf, 0xd8, 0xfd, 0x4f, 0xb1, 0x1f,
+	0x60, 0x3a, 0x08, 0x47, 0xaf, 0xe1, 0xf6, 0x10,
+	0x77, 0x09, 0xa7, 0x27, 0x8f, 0x9a, 0x97, 0x5a,
+	0x26, 0xfa, 0xfe, 0x41, 0x32, 0x83, 0x10, 0xe0,
+	0x1d, 0xbf, 0x64, 0x0d, 0xf4, 0x1c, 0x32, 0x35,
+	0xe5, 0x1b, 0x36, 0xef, 0xd4, 0x4a, 0x93, 0x4d,
+	0x00, 0x7c, 0xec, 0x02, 0x07, 0x8b, 0x5d, 0x7d,
+	0x1b, 0x0e, 0xd1, 0xa6, 0xa5, 0x5d, 0x7d, 0x57,
+	0x88, 0xa8, 0xcc, 0x81, 0xb4, 0x86, 0x4e, 0xb4,
+	0x40, 0xe9, 0x1d, 0xc3, 0xb1, 0x24, 0x3e, 0x7f,
+	0xcc, 0x8a, 0x24, 0x9b, 0xdf, 0x6d, 0xf0, 0x39,
+	0x69, 0x3e, 0x4c, 0xc0, 0x96, 0xe4, 0x13, 0xda,
+	0x90, 0xda, 0xf4, 0x95, 0x66, 0x8b, 0x17, 0x17,
+	0xfe, 0x39, 0x43, 0x25, 0xaa, 0xda, 0xa0, 0x43,
+	0x3c, 0xb1, 0x41, 0x02, 0xa3, 0xf0, 0xa7, 0x19,
+	0x59, 0xbc, 0x1d, 0x7d, 0x6c, 0x6d, 0x91, 0x09,
+	0x5c, 0xb7, 0x5b, 0x01, 0xd1, 0x6f, 0x17, 0x21,
+	0x97, 0xbf, 0x89, 0x71, 0xa5, 0xb0, 0x6e, 0x07,
+	0x45, 0xfd, 0x9d, 0xea, 0x07, 0xf6, 0x7a, 0x9f,
+	0x10, 0x18, 0x22, 0x30, 0x73, 0xac, 0xd4, 0x6b,
+	0x72, 0x44, 0xed, 0xd9, 0x19, 0x9b, 0x2d, 0x4a,
+	0x41, 0xdd, 0xd1, 0x85, 0x5e, 0x37, 0x19, 0xed,
+	0xd2, 0x15, 0x8f, 0x5e, 0x91, 0xdb, 0x33, 0xf2,
+	0xe4, 0xdb, 0xff, 0x98, 0xfb, 0xa3, 0xb5, 0xca,
+	0x21, 0x69, 0x08, 0xe7, 0x8a, 0xdf, 0x90, 0xff,
+	0x3e, 0xe9, 0x20, 0x86, 0x3c, 0xe9, 0xfc, 0x0b,
+	0xfe, 0x5c, 0x61, 0xaa, 0x13, 0x92, 0x7f, 0x7b,
+	0xec, 0xe0, 0x6d, 0xa8, 0x23, 0x22, 0xf6, 0x6b,
+	0x77, 0xc4, 0xfe, 0x40, 0x07, 0x3b, 0xb6, 0xf6,
+	0x8e, 0x5f, 0xd4, 0xb9, 0xb7, 0x0f, 0x21, 0x04,
+	0xef, 0x83, 0x63, 0x91, 0x69, 0x40, 0xa3, 0x48,
+	0x5c, 0xd2, 0x60, 0xf9, 0x4f, 0x6c, 0x47, 0x8b,
+	0x3b, 0xb1, 0x9f, 0x8e, 0xee, 0x16, 0x8a, 0x13,
+	0xfc, 0x46, 0x17, 0xc3, 0xc3, 0x32, 0x56, 0xf8,
+	0x3c, 0x85, 0x3a, 0xb6, 0x3e, 0xaa, 0x89, 0x4f,
+	0xb3, 0xdf, 0x38, 0xfd, 0xf1, 0xe4, 0x3a, 0xc0,
+	0xe6, 0x58, 0xb5, 0x8f, 0xc5, 0x29, 0xa2, 0x92,
+	0x4a, 0xb6, 0xa0, 0x34, 0x7f, 0xab, 0xb5, 0x8a,
+	0x90, 0xa1, 0xdb, 0x4d, 0xca, 0xb6, 0x2c, 0x41,
+	0x3c, 0xf7, 0x2b, 0x21, 0xc3, 0xfd, 0xf4, 0x17,
+	0x5c, 0xb5, 0x33, 0x17, 0x68, 0x2b, 0x08, 0x30,
+	0xf3, 0xf7, 0x30, 0x3c, 0x96, 0xe6, 0x6a, 0x20,
+	0x97, 0xe7, 0x4d, 0x10, 0x5f, 0x47, 0x5f, 0x49,
+	0x96, 0x09, 0xf0, 0x27, 0x91, 0xc8, 0xf8, 0x5a,
+	0x2e, 0x79, 0xb5, 0xe2, 0xb8, 0xe8, 0xb9, 0x7b,
+	0xd5, 0x10, 0xcb, 0xff, 0x5d, 0x14, 0x73, 0xf3
+};
+static const u8 dec_assoc008[] __initconst = { };
+static const u8 dec_nonce008[] __initconst = {
+	0x0e, 0x0d, 0x57, 0xbb, 0x7b, 0x40, 0x54, 0x02
+};
+static const u8 dec_key008[] __initconst = {
+	0xf2, 0xaa, 0x4f, 0x99, 0xfd, 0x3e, 0xa8, 0x53,
+	0xc1, 0x44, 0xe9, 0x81, 0x18, 0xdc, 0xf5, 0xf0,
+	0x3e, 0x44, 0x15, 0x59, 0xe0, 0xc5, 0x44, 0x86,
+	0xc3, 0x91, 0xa8, 0x75, 0xc0, 0x12, 0x46, 0xba
+};
+
+static const u8 dec_input009[] __initconst = {
+	0xfd, 0x81, 0x8d, 0xd0, 0x3d, 0xb4, 0xd5, 0xdf,
+	0xd3, 0x42, 0x47, 0x5a, 0x6d, 0x19, 0x27, 0x66,
+	0x4b, 0x2e, 0x0c, 0x27, 0x9c, 0x96, 0x4c, 0x72,
+	0x02, 0xa3, 0x65, 0xc3, 0xb3, 0x6f, 0x2e, 0xbd,
+	0x63, 0x8a, 0x4a, 0x5d, 0x29, 0xa2, 0xd0, 0x28,
+	0x48, 0xc5, 0x3d, 0x98, 0xa3, 0xbc, 0xe0, 0xbe,
+	0x3b, 0x3f, 0xe6, 0x8a, 0xa4, 0x7f, 0x53, 0x06,
+	0xfa, 0x7f, 0x27, 0x76, 0x72, 0x31, 0xa1, 0xf5,
+	0xd6, 0x0c, 0x52, 0x47, 0xba, 0xcd, 0x4f, 0xd7,
+	0xeb, 0x05, 0x48, 0x0d, 0x7c, 0x35, 0x4a, 0x09,
+	0xc9, 0x76, 0x71, 0x02, 0xa3, 0xfb, 0xb7, 0x1a,
+	0x65, 0xb7, 0xed, 0x98, 0xc6, 0x30, 0x8a, 0x00,
+	0xae, 0xa1, 0x31, 0xe5, 0xb5, 0x9e, 0x6d, 0x62,
+	0xda, 0xda, 0x07, 0x0f, 0x38, 0x38, 0xd3, 0xcb,
+	0xc1, 0xb0, 0xad, 0xec, 0x72, 0xec, 0xb1, 0xa2,
+	0x7b, 0x59, 0xf3, 0x3d, 0x2b, 0xef, 0xcd, 0x28,
+	0x5b, 0x83, 0xcc, 0x18, 0x91, 0x88, 0xb0, 0x2e,
+	0xf9, 0x29, 0x31, 0x18, 0xf9, 0x4e, 0xe9, 0x0a,
+	0x91, 0x92, 0x9f, 0xae, 0x2d, 0xad, 0xf4, 0xe6,
+	0x1a, 0xe2, 0xa4, 0xee, 0x47, 0x15, 0xbf, 0x83,
+	0x6e, 0xd7, 0x72, 0x12, 0x3b, 0x2d, 0x24, 0xe9,
+	0xb2, 0x55, 0xcb, 0x3c, 0x10, 0xf0, 0x24, 0x8a,
+	0x4a, 0x02, 0xea, 0x90, 0x25, 0xf0, 0xb4, 0x79,
+	0x3a, 0xef, 0x6e, 0xf5, 0x52, 0xdf, 0xb0, 0x0a,
+	0xcd, 0x24, 0x1c, 0xd3, 0x2e, 0x22, 0x74, 0xea,
+	0x21, 0x6f, 0xe9, 0xbd, 0xc8, 0x3e, 0x36, 0x5b,
+	0x19, 0xf1, 0xca, 0x99, 0x0a, 0xb4, 0xa7, 0x52,
+	0x1a, 0x4e, 0xf2, 0xad, 0x8d, 0x56, 0x85, 0xbb,
+	0x64, 0x89, 0xba, 0x26, 0xf9, 0xc7, 0xe1, 0x89,
+	0x19, 0x22, 0x77, 0xc3, 0xa8, 0xfc, 0xff, 0xad,
+	0xfe, 0xb9, 0x48, 0xae, 0x12, 0x30, 0x9f, 0x19,
+	0xfb, 0x1b, 0xef, 0x14, 0x87, 0x8a, 0x78, 0x71,
+	0xf3, 0xf4, 0xb7, 0x00, 0x9c, 0x1d, 0xb5, 0x3d,
+	0x49, 0x00, 0x0c, 0x06, 0xd4, 0x50, 0xf9, 0x54,
+	0x45, 0xb2, 0x5b, 0x43, 0xdb, 0x6d, 0xcf, 0x1a,
+	0xe9, 0x7a, 0x7a, 0xcf, 0xfc, 0x8a, 0x4e, 0x4d,
+	0x0b, 0x07, 0x63, 0x28, 0xd8, 0xe7, 0x08, 0x95,
+	0xdf, 0xa6, 0x72, 0x93, 0x2e, 0xbb, 0xa0, 0x42,
+	0x89, 0x16, 0xf1, 0xd9, 0x0c, 0xf9, 0xa1, 0x16,
+	0xfd, 0xd9, 0x03, 0xb4, 0x3b, 0x8a, 0xf5, 0xf6,
+	0xe7, 0x6b, 0x2e, 0x8e, 0x4c, 0x3d, 0xe2, 0xaf,
+	0x08, 0x45, 0x03, 0xff, 0x09, 0xb6, 0xeb, 0x2d,
+	0xc6, 0x1b, 0x88, 0x94, 0xac, 0x3e, 0xf1, 0x9f,
+	0x0e, 0x0e, 0x2b, 0xd5, 0x00, 0x4d, 0x3f, 0x3b,
+	0x53, 0xae, 0xaf, 0x1c, 0x33, 0x5f, 0x55, 0x6e,
+	0x8d, 0xaf, 0x05, 0x7a, 0x10, 0x34, 0xc9, 0xf4,
+	0x66, 0xcb, 0x62, 0x12, 0xa6, 0xee, 0xe8, 0x1c,
+	0x5d, 0x12, 0x86, 0xdb, 0x6f, 0x1c, 0x33, 0xc4,
+	0x1c, 0xda, 0x82, 0x2d, 0x3b, 0x59, 0xfe, 0xb1,
+	0xa4, 0x59, 0x41, 0x86, 0xd0, 0xef, 0xae, 0xfb,
+	0xda, 0x6d, 0x11, 0xb8, 0xca, 0xe9, 0x6e, 0xff,
+	0xf7, 0xa9, 0xd9, 0x70, 0x30, 0xfc, 0x53, 0xe2,
+	0xd7, 0xa2, 0x4e, 0xc7, 0x91, 0xd9, 0x07, 0x06,
+	0xaa, 0xdd, 0xb0, 0x59, 0x28, 0x1d, 0x00, 0x66,
+	0xc5, 0x54, 0xc2, 0xfc, 0x06, 0xda, 0x05, 0x90,
+	0x52, 0x1d, 0x37, 0x66, 0xee, 0xf0, 0xb2, 0x55,
+	0x8a, 0x5d, 0xd2, 0x38, 0x86, 0x94, 0x9b, 0xfc,
+	0x10, 0x4c, 0xa1, 0xb9, 0x64, 0x3e, 0x44, 0xb8,
+	0x5f, 0xb0, 0x0c, 0xec, 0xe0, 0xc9, 0xe5, 0x62,
+	0x75, 0x3f, 0x09, 0xd5, 0xf5, 0xd9, 0x26, 0xba,
+	0x9e, 0xd2, 0xf4, 0xb9, 0x48, 0x0a, 0xbc, 0xa2,
+	0xd6, 0x7c, 0x36, 0x11, 0x7d, 0x26, 0x81, 0x89,
+	0xcf, 0xa4, 0xad, 0x73, 0x0e, 0xee, 0xcc, 0x06,
+	0xa9, 0xdb, 0xb1, 0xfd, 0xfb, 0x09, 0x7f, 0x90,
+	0x42, 0x37, 0x2f, 0xe1, 0x9c, 0x0f, 0x6f, 0xcf,
+	0x43, 0xb5, 0xd9, 0x90, 0xe1, 0x85, 0xf5, 0xa8,
+	0xae
+};
+static const u8 dec_output009[] __initconst = {
+	0xe6, 0xc3, 0xdb, 0x63, 0x55, 0x15, 0xe3, 0x5b,
+	0xb7, 0x4b, 0x27, 0x8b, 0x5a, 0xdd, 0xc2, 0xe8,
+	0x3a, 0x6b, 0xd7, 0x81, 0x96, 0x35, 0x97, 0xca,
+	0xd7, 0x68, 0xe8, 0xef, 0xce, 0xab, 0xda, 0x09,
+	0x6e, 0xd6, 0x8e, 0xcb, 0x55, 0xb5, 0xe1, 0xe5,
+	0x57, 0xfd, 0xc4, 0xe3, 0xe0, 0x18, 0x4f, 0x85,
+	0xf5, 0x3f, 0x7e, 0x4b, 0x88, 0xc9, 0x52, 0x44,
+	0x0f, 0xea, 0xaf, 0x1f, 0x71, 0x48, 0x9f, 0x97,
+	0x6d, 0xb9, 0x6f, 0x00, 0xa6, 0xde, 0x2b, 0x77,
+	0x8b, 0x15, 0xad, 0x10, 0xa0, 0x2b, 0x7b, 0x41,
+	0x90, 0x03, 0x2d, 0x69, 0xae, 0xcc, 0x77, 0x7c,
+	0xa5, 0x9d, 0x29, 0x22, 0xc2, 0xea, 0xb4, 0x00,
+	0x1a, 0xd2, 0x7a, 0x98, 0x8a, 0xf9, 0xf7, 0x82,
+	0xb0, 0xab, 0xd8, 0xa6, 0x94, 0x8d, 0x58, 0x2f,
+	0x01, 0x9e, 0x00, 0x20, 0xfc, 0x49, 0xdc, 0x0e,
+	0x03, 0xe8, 0x45, 0x10, 0xd6, 0xa8, 0xda, 0x55,
+	0x10, 0x9a, 0xdf, 0x67, 0x22, 0x8b, 0x43, 0xab,
+	0x00, 0xbb, 0x02, 0xc8, 0xdd, 0x7b, 0x97, 0x17,
+	0xd7, 0x1d, 0x9e, 0x02, 0x5e, 0x48, 0xde, 0x8e,
+	0xcf, 0x99, 0x07, 0x95, 0x92, 0x3c, 0x5f, 0x9f,
+	0xc5, 0x8a, 0xc0, 0x23, 0xaa, 0xd5, 0x8c, 0x82,
+	0x6e, 0x16, 0x92, 0xb1, 0x12, 0x17, 0x07, 0xc3,
+	0xfb, 0x36, 0xf5, 0x6c, 0x35, 0xd6, 0x06, 0x1f,
+	0x9f, 0xa7, 0x94, 0xa2, 0x38, 0x63, 0x9c, 0xb0,
+	0x71, 0xb3, 0xa5, 0xd2, 0xd8, 0xba, 0x9f, 0x08,
+	0x01, 0xb3, 0xff, 0x04, 0x97, 0x73, 0x45, 0x1b,
+	0xd5, 0xa9, 0x9c, 0x80, 0xaf, 0x04, 0x9a, 0x85,
+	0xdb, 0x32, 0x5b, 0x5d, 0x1a, 0xc1, 0x36, 0x28,
+	0x10, 0x79, 0xf1, 0x3c, 0xbf, 0x1a, 0x41, 0x5c,
+	0x4e, 0xdf, 0xb2, 0x7c, 0x79, 0x3b, 0x7a, 0x62,
+	0x3d, 0x4b, 0xc9, 0x9b, 0x2a, 0x2e, 0x7c, 0xa2,
+	0xb1, 0x11, 0x98, 0xa7, 0x34, 0x1a, 0x00, 0xf3,
+	0xd1, 0xbc, 0x18, 0x22, 0xba, 0x02, 0x56, 0x62,
+	0x31, 0x10, 0x11, 0x6d, 0xe0, 0x54, 0x9d, 0x40,
+	0x1f, 0x26, 0x80, 0x41, 0xca, 0x3f, 0x68, 0x0f,
+	0x32, 0x1d, 0x0a, 0x8e, 0x79, 0xd8, 0xa4, 0x1b,
+	0x29, 0x1c, 0x90, 0x8e, 0xc5, 0xe3, 0xb4, 0x91,
+	0x37, 0x9a, 0x97, 0x86, 0x99, 0xd5, 0x09, 0xc5,
+	0xbb, 0xa3, 0x3f, 0x21, 0x29, 0x82, 0x14, 0x5c,
+	0xab, 0x25, 0xfb, 0xf2, 0x4f, 0x58, 0x26, 0xd4,
+	0x83, 0xaa, 0x66, 0x89, 0x67, 0x7e, 0xc0, 0x49,
+	0xe1, 0x11, 0x10, 0x7f, 0x7a, 0xda, 0x29, 0x04,
+	0xff, 0xf0, 0xcb, 0x09, 0x7c, 0x9d, 0xfa, 0x03,
+	0x6f, 0x81, 0x09, 0x31, 0x60, 0xfb, 0x08, 0xfa,
+	0x74, 0xd3, 0x64, 0x44, 0x7c, 0x55, 0x85, 0xec,
+	0x9c, 0x6e, 0x25, 0xb7, 0x6c, 0xc5, 0x37, 0xb6,
+	0x83, 0x87, 0x72, 0x95, 0x8b, 0x9d, 0xe1, 0x69,
+	0x5c, 0x31, 0x95, 0x42, 0xa6, 0x2c, 0xd1, 0x36,
+	0x47, 0x1f, 0xec, 0x54, 0xab, 0xa2, 0x1c, 0xd8,
+	0x00, 0xcc, 0xbc, 0x0d, 0x65, 0xe2, 0x67, 0xbf,
+	0xbc, 0xea, 0xee, 0x9e, 0xe4, 0x36, 0x95, 0xbe,
+	0x73, 0xd9, 0xa6, 0xd9, 0x0f, 0xa0, 0xcc, 0x82,
+	0x76, 0x26, 0xad, 0x5b, 0x58, 0x6c, 0x4e, 0xab,
+	0x29, 0x64, 0xd3, 0xd9, 0xa9, 0x08, 0x8c, 0x1d,
+	0xa1, 0x4f, 0x80, 0xd8, 0x3f, 0x94, 0xfb, 0xd3,
+	0x7b, 0xfc, 0xd1, 0x2b, 0xc3, 0x21, 0xeb, 0xe5,
+	0x1c, 0x84, 0x23, 0x7f, 0x4b, 0xfa, 0xdb, 0x34,
+	0x18, 0xa2, 0xc2, 0xe5, 0x13, 0xfe, 0x6c, 0x49,
+	0x81, 0xd2, 0x73, 0xe7, 0xe2, 0xd7, 0xe4, 0x4f,
+	0x4b, 0x08, 0x6e, 0xb1, 0x12, 0x22, 0x10, 0x9d,
+	0xac, 0x51, 0x1e, 0x17, 0xd9, 0x8a, 0x0b, 0x42,
+	0x88, 0x16, 0x81, 0x37, 0x7c, 0x6a, 0xf7, 0xef,
+	0x2d, 0xe3, 0xd9, 0xf8, 0x5f, 0xe0, 0x53, 0x27,
+	0x74, 0xb9, 0xe2, 0xd6, 0x1c, 0x80, 0x2c, 0x52,
+	0x65
+};
+static const u8 dec_assoc009[] __initconst = {
+	0x5a, 0x27, 0xff, 0xeb, 0xdf, 0x84, 0xb2, 0x9e,
+	0xef
+};
+static const u8 dec_nonce009[] __initconst = {
+	0xef, 0x2d, 0x63, 0xee, 0x6b, 0x80, 0x8b, 0x78
+};
+static const u8 dec_key009[] __initconst = {
+	0xea, 0xbc, 0x56, 0x99, 0xe3, 0x50, 0xff, 0xc5,
+	0xcc, 0x1a, 0xd7, 0xc1, 0x57, 0x72, 0xea, 0x86,
+	0x5b, 0x89, 0x88, 0x61, 0x3d, 0x2f, 0x9b, 0xb2,
+	0xe7, 0x9c, 0xec, 0x74, 0x6e, 0x3e, 0xf4, 0x3b
+};
+
+static const u8 dec_input010[] __initconst = {
+	0xe5, 0x26, 0xa4, 0x3d, 0xbd, 0x33, 0xd0, 0x4b,
+	0x6f, 0x05, 0xa7, 0x6e, 0x12, 0x7a, 0xd2, 0x74,
+	0xa6, 0xdd, 0xbd, 0x95, 0xeb, 0xf9, 0xa4, 0xf1,
+	0x59, 0x93, 0x91, 0x70, 0xd9, 0xfe, 0x9a, 0xcd,
+	0x53, 0x1f, 0x3a, 0xab, 0xa6, 0x7c, 0x9f, 0xa6,
+	0x9e, 0xbd, 0x99, 0xd9, 0xb5, 0x97, 0x44, 0xd5,
+	0x14, 0x48, 0x4d, 0x9d, 0xc0, 0xd0, 0x05, 0x96,
+	0xeb, 0x4c, 0x78, 0x55, 0x09, 0x08, 0x01, 0x02,
+	0x30, 0x90, 0x7b, 0x96, 0x7a, 0x7b, 0x5f, 0x30,
+	0x41, 0x24, 0xce, 0x68, 0x61, 0x49, 0x86, 0x57,
+	0x82, 0xdd, 0x53, 0x1c, 0x51, 0x28, 0x2b, 0x53,
+	0x6e, 0x2d, 0xc2, 0x20, 0x4c, 0xdd, 0x8f, 0x65,
+	0x10, 0x20, 0x50, 0xdd, 0x9d, 0x50, 0xe5, 0x71,
+	0x40, 0x53, 0x69, 0xfc, 0x77, 0x48, 0x11, 0xb9,
+	0xde, 0xa4, 0x8d, 0x58, 0xe4, 0xa6, 0x1a, 0x18,
+	0x47, 0x81, 0x7e, 0xfc, 0xdd, 0xf6, 0xef, 0xce,
+	0x2f, 0x43, 0x68, 0xd6, 0x06, 0xe2, 0x74, 0x6a,
+	0xad, 0x90, 0xf5, 0x37, 0xf3, 0x3d, 0x82, 0x69,
+	0x40, 0xe9, 0x6b, 0xa7, 0x3d, 0xa8, 0x1e, 0xd2,
+	0x02, 0x7c, 0xb7, 0x9b, 0xe4, 0xda, 0x8f, 0x95,
+	0x06, 0xc5, 0xdf, 0x73, 0xa3, 0x20, 0x9a, 0x49,
+	0xde, 0x9c, 0xbc, 0xee, 0x14, 0x3f, 0x81, 0x5e,
+	0xf8, 0x3b, 0x59, 0x3c, 0xe1, 0x68, 0x12, 0x5a,
+	0x3a, 0x76, 0x3a, 0x3f, 0xf7, 0x87, 0x33, 0x0a,
+	0x01, 0xb8, 0xd4, 0xed, 0xb6, 0xbe, 0x94, 0x5e,
+	0x70, 0x40, 0x56, 0x67, 0x1f, 0x50, 0x44, 0x19,
+	0xce, 0x82, 0x70, 0x10, 0x87, 0x13, 0x20, 0x0b,
+	0x4c, 0x5a, 0xb6, 0xf6, 0xa7, 0xae, 0x81, 0x75,
+	0x01, 0x81, 0xe6, 0x4b, 0x57, 0x7c, 0xdd, 0x6d,
+	0xf8, 0x1c, 0x29, 0x32, 0xf7, 0xda, 0x3c, 0x2d,
+	0xf8, 0x9b, 0x25, 0x6e, 0x00, 0xb4, 0xf7, 0x2f,
+	0xf7, 0x04, 0xf7, 0xa1, 0x56, 0xac, 0x4f, 0x1a,
+	0x64, 0xb8, 0x47, 0x55, 0x18, 0x7b, 0x07, 0x4d,
+	0xbd, 0x47, 0x24, 0x80, 0x5d, 0xa2, 0x70, 0xc5,
+	0xdd, 0x8e, 0x82, 0xd4, 0xeb, 0xec, 0xb2, 0x0c,
+	0x39, 0xd2, 0x97, 0xc1, 0xcb, 0xeb, 0xf4, 0x77,
+	0x59, 0xb4, 0x87, 0xef, 0xcb, 0x43, 0x2d, 0x46,
+	0x54, 0xd1, 0xa7, 0xd7, 0x15, 0x99, 0x0a, 0x43,
+	0xa1, 0xe0, 0x99, 0x33, 0x71, 0xc1, 0xed, 0xfe,
+	0x72, 0x46, 0x33, 0x8e, 0x91, 0x08, 0x9f, 0xc8,
+	0x2e, 0xca, 0xfa, 0xdc, 0x59, 0xd5, 0xc3, 0x76,
+	0x84, 0x9f, 0xa3, 0x37, 0x68, 0xc3, 0xf0, 0x47,
+	0x2c, 0x68, 0xdb, 0x5e, 0xc3, 0x49, 0x4c, 0xe8,
+	0x92, 0x85, 0xe2, 0x23, 0xd3, 0x3f, 0xad, 0x32,
+	0xe5, 0x2b, 0x82, 0xd7, 0x8f, 0x99, 0x0a, 0x59,
+	0x5c, 0x45, 0xd9, 0xb4, 0x51, 0x52, 0xc2, 0xae,
+	0xbf, 0x80, 0xcf, 0xc9, 0xc9, 0x51, 0x24, 0x2a,
+	0x3b, 0x3a, 0x4d, 0xae, 0xeb, 0xbd, 0x22, 0xc3,
+	0x0e, 0x0f, 0x59, 0x25, 0x92, 0x17, 0xe9, 0x74,
+	0xc7, 0x8b, 0x70, 0x70, 0x36, 0x55, 0x95, 0x75,
+	0x4b, 0xad, 0x61, 0x2b, 0x09, 0xbc, 0x82, 0xf2,
+	0x6e, 0x94, 0x43, 0xae, 0xc3, 0xd5, 0xcd, 0x8e,
+	0xfe, 0x5b, 0x9a, 0x88, 0x43, 0x01, 0x75, 0xb2,
+	0x23, 0x09, 0xf7, 0x89, 0x83, 0xe7, 0xfa, 0xf9,
+	0xb4, 0x9b, 0xf8, 0xef, 0xbd, 0x1c, 0x92, 0xc1,
+	0xda, 0x7e, 0xfe, 0x05, 0xba, 0x5a, 0xcd, 0x07,
+	0x6a, 0x78, 0x9e, 0x5d, 0xfb, 0x11, 0x2f, 0x79,
+	0x38, 0xb6, 0xc2, 0x5b, 0x6b, 0x51, 0xb4, 0x71,
+	0xdd, 0xf7, 0x2a, 0xe4, 0xf4, 0x72, 0x76, 0xad,
+	0xc2, 0xdd, 0x64, 0x5d, 0x79, 0xb6, 0xf5, 0x7a,
+	0x77, 0x20, 0x05, 0x3d, 0x30, 0x06, 0xd4, 0x4c,
+	0x0a, 0x2c, 0x98, 0x5a, 0xb9, 0xd4, 0x98, 0xa9,
+	0x3f, 0xc6, 0x12, 0xea, 0x3b, 0x4b, 0xc5, 0x79,
+	0x64, 0x63, 0x6b, 0x09, 0x54, 0x3b, 0x14, 0x27,
+	0xba, 0x99, 0x80, 0xc8, 0x72, 0xa8, 0x12, 0x90,
+	0x29, 0xba, 0x40, 0x54, 0x97, 0x2b, 0x7b, 0xfe,
+	0xeb, 0xcd, 0x01, 0x05, 0x44, 0x72, 0xdb, 0x99,
+	0xe4, 0x61, 0xc9, 0x69, 0xd6, 0xb9, 0x28, 0xd1,
+	0x05, 0x3e, 0xf9, 0x0b, 0x49, 0x0a, 0x49, 0xe9,
+	0x8d, 0x0e, 0xa7, 0x4a, 0x0f, 0xaf, 0x32, 0xd0,
+	0xe0, 0xb2, 0x3a, 0x55, 0x58, 0xfe, 0x5c, 0x28,
+	0x70, 0x51, 0x23, 0xb0, 0x7b, 0x6a, 0x5f, 0x1e,
+	0xb8, 0x17, 0xd7, 0x94, 0x15, 0x8f, 0xee, 0x20,
+	0xc7, 0x42, 0x25, 0x3e, 0x9a, 0x14, 0xd7, 0x60,
+	0x72, 0x39, 0x47, 0x48, 0xa9, 0xfe, 0xdd, 0x47,
+	0x0a, 0xb1, 0xe6, 0x60, 0x28, 0x8c, 0x11, 0x68,
+	0xe1, 0xff, 0xd7, 0xce, 0xc8, 0xbe, 0xb3, 0xfe,
+	0x27, 0x30, 0x09, 0x70, 0xd7, 0xfa, 0x02, 0x33,
+	0x3a, 0x61, 0x2e, 0xc7, 0xff, 0xa4, 0x2a, 0xa8,
+	0x6e, 0xb4, 0x79, 0x35, 0x6d, 0x4c, 0x1e, 0x38,
+	0xf8, 0xee, 0xd4, 0x84, 0x4e, 0x6e, 0x28, 0xa7,
+	0xce, 0xc8, 0xc1, 0xcf, 0x80, 0x05, 0xf3, 0x04,
+	0xef, 0xc8, 0x18, 0x28, 0x2e, 0x8d, 0x5e, 0x0c,
+	0xdf, 0xb8, 0x5f, 0x96, 0xe8, 0xc6, 0x9c, 0x2f,
+	0xe5, 0xa6, 0x44, 0xd7, 0xe7, 0x99, 0x44, 0x0c,
+	0xec, 0xd7, 0x05, 0x60, 0x97, 0xbb, 0x74, 0x77,
+	0x58, 0xd5, 0xbb, 0x48, 0xde, 0x5a, 0xb2, 0x54,
+	0x7f, 0x0e, 0x46, 0x70, 0x6a, 0x6f, 0x78, 0xa5,
+	0x08, 0x89, 0x05, 0x4e, 0x7e, 0xa0, 0x69, 0xb4,
+	0x40, 0x60, 0x55, 0x77, 0x75, 0x9b, 0x19, 0xf2,
+	0xd5, 0x13, 0x80, 0x77, 0xf9, 0x4b, 0x3f, 0x1e,
+	0xee, 0xe6, 0x76, 0x84, 0x7b, 0x8c, 0xe5, 0x27,
+	0xa8, 0x0a, 0x91, 0x01, 0x68, 0x71, 0x8a, 0x3f,
+	0x06, 0xab, 0xf6, 0xa9, 0xa5, 0xe6, 0x72, 0x92,
+	0xe4, 0x67, 0xe2, 0xa2, 0x46, 0x35, 0x84, 0x55,
+	0x7d, 0xca, 0xa8, 0x85, 0xd0, 0xf1, 0x3f, 0xbe,
+	0xd7, 0x34, 0x64, 0xfc, 0xae, 0xe3, 0xe4, 0x04,
+	0x9f, 0x66, 0x02, 0xb9, 0x88, 0x10, 0xd9, 0xc4,
+	0x4c, 0x31, 0x43, 0x7a, 0x93, 0xe2, 0x9b, 0x56,
+	0x43, 0x84, 0xdc, 0xdc, 0xde, 0x1d, 0xa4, 0x02,
+	0x0e, 0xc2, 0xef, 0xc3, 0xf8, 0x78, 0xd1, 0xb2,
+	0x6b, 0x63, 0x18, 0xc9, 0xa9, 0xe5, 0x72, 0xd8,
+	0xf3, 0xb9, 0xd1, 0x8a, 0xc7, 0x1a, 0x02, 0x27,
+	0x20, 0x77, 0x10, 0xe5, 0xc8, 0xd4, 0x4a, 0x47,
+	0xe5, 0xdf, 0x5f, 0x01, 0xaa, 0xb0, 0xd4, 0x10,
+	0xbb, 0x69, 0xe3, 0x36, 0xc8, 0xe1, 0x3d, 0x43,
+	0xfb, 0x86, 0xcd, 0xcc, 0xbf, 0xf4, 0x88, 0xe0,
+	0x20, 0xca, 0xb7, 0x1b, 0xf1, 0x2f, 0x5c, 0xee,
+	0xd4, 0xd3, 0xa3, 0xcc, 0xa4, 0x1e, 0x1c, 0x47,
+	0xfb, 0xbf, 0xfc, 0xa2, 0x41, 0x55, 0x9d, 0xf6,
+	0x5a, 0x5e, 0x65, 0x32, 0x34, 0x7b, 0x52, 0x8d,
+	0xd5, 0xd0, 0x20, 0x60, 0x03, 0xab, 0x3f, 0x8c,
+	0xd4, 0x21, 0xea, 0x2a, 0xd9, 0xc4, 0xd0, 0xd3,
+	0x65, 0xd8, 0x7a, 0x13, 0x28, 0x62, 0x32, 0x4b,
+	0x2c, 0x87, 0x93, 0xa8, 0xb4, 0x52, 0x45, 0x09,
+	0x44, 0xec, 0xec, 0xc3, 0x17, 0xdb, 0x9a, 0x4d,
+	0x5c, 0xa9, 0x11, 0xd4, 0x7d, 0xaf, 0x9e, 0xf1,
+	0x2d, 0xb2, 0x66, 0xc5, 0x1d, 0xed, 0xb7, 0xcd,
+	0x0b, 0x25, 0x5e, 0x30, 0x47, 0x3f, 0x40, 0xf4,
+	0xa1, 0xa0, 0x00, 0x94, 0x10, 0xc5, 0x6a, 0x63,
+	0x1a, 0xd5, 0x88, 0x92, 0x8e, 0x82, 0x39, 0x87,
+	0x3c, 0x78, 0x65, 0x58, 0x42, 0x75, 0x5b, 0xdd,
+	0x77, 0x3e, 0x09, 0x4e, 0x76, 0x5b, 0xe6, 0x0e,
+	0x4d, 0x38, 0xb2, 0xc0, 0xb8, 0x95, 0x01, 0x7a,
+	0x10, 0xe0, 0xfb, 0x07, 0xf2, 0xab, 0x2d, 0x8c,
+	0x32, 0xed, 0x2b, 0xc0, 0x46, 0xc2, 0xf5, 0x38,
+	0x83, 0xf0, 0x17, 0xec, 0xc1, 0x20, 0x6a, 0x9a,
+	0x0b, 0x00, 0xa0, 0x98, 0x22, 0x50, 0x23, 0xd5,
+	0x80, 0x6b, 0xf6, 0x1f, 0xc3, 0xcc, 0x97, 0xc9,
+	0x24, 0x9f, 0xf3, 0xaf, 0x43, 0x14, 0xd5, 0xa0
+};
+static const u8 dec_output010[] __initconst = {
+	0x42, 0x93, 0xe4, 0xeb, 0x97, 0xb0, 0x57, 0xbf,
+	0x1a, 0x8b, 0x1f, 0xe4, 0x5f, 0x36, 0x20, 0x3c,
+	0xef, 0x0a, 0xa9, 0x48, 0x5f, 0x5f, 0x37, 0x22,
+	0x3a, 0xde, 0xe3, 0xae, 0xbe, 0xad, 0x07, 0xcc,
+	0xb1, 0xf6, 0xf5, 0xf9, 0x56, 0xdd, 0xe7, 0x16,
+	0x1e, 0x7f, 0xdf, 0x7a, 0x9e, 0x75, 0xb7, 0xc7,
+	0xbe, 0xbe, 0x8a, 0x36, 0x04, 0xc0, 0x10, 0xf4,
+	0x95, 0x20, 0x03, 0xec, 0xdc, 0x05, 0xa1, 0x7d,
+	0xc4, 0xa9, 0x2c, 0x82, 0xd0, 0xbc, 0x8b, 0xc5,
+	0xc7, 0x45, 0x50, 0xf6, 0xa2, 0x1a, 0xb5, 0x46,
+	0x3b, 0x73, 0x02, 0xa6, 0x83, 0x4b, 0x73, 0x82,
+	0x58, 0x5e, 0x3b, 0x65, 0x2f, 0x0e, 0xfd, 0x2b,
+	0x59, 0x16, 0xce, 0xa1, 0x60, 0x9c, 0xe8, 0x3a,
+	0x99, 0xed, 0x8d, 0x5a, 0xcf, 0xf6, 0x83, 0xaf,
+	0xba, 0xd7, 0x73, 0x73, 0x40, 0x97, 0x3d, 0xca,
+	0xef, 0x07, 0x57, 0xe6, 0xd9, 0x70, 0x0e, 0x95,
+	0xae, 0xa6, 0x8d, 0x04, 0xcc, 0xee, 0xf7, 0x09,
+	0x31, 0x77, 0x12, 0xa3, 0x23, 0x97, 0x62, 0xb3,
+	0x7b, 0x32, 0xfb, 0x80, 0x14, 0x48, 0x81, 0xc3,
+	0xe5, 0xea, 0x91, 0x39, 0x52, 0x81, 0xa2, 0x4f,
+	0xe4, 0xb3, 0x09, 0xff, 0xde, 0x5e, 0xe9, 0x58,
+	0x84, 0x6e, 0xf9, 0x3d, 0xdf, 0x25, 0xea, 0xad,
+	0xae, 0xe6, 0x9a, 0xd1, 0x89, 0x55, 0xd3, 0xde,
+	0x6c, 0x52, 0xdb, 0x70, 0xfe, 0x37, 0xce, 0x44,
+	0x0a, 0xa8, 0x25, 0x5f, 0x92, 0xc1, 0x33, 0x4a,
+	0x4f, 0x9b, 0x62, 0x35, 0xff, 0xce, 0xc0, 0xa9,
+	0x60, 0xce, 0x52, 0x00, 0x97, 0x51, 0x35, 0x26,
+	0x2e, 0xb9, 0x36, 0xa9, 0x87, 0x6e, 0x1e, 0xcc,
+	0x91, 0x78, 0x53, 0x98, 0x86, 0x5b, 0x9c, 0x74,
+	0x7d, 0x88, 0x33, 0xe1, 0xdf, 0x37, 0x69, 0x2b,
+	0xbb, 0xf1, 0x4d, 0xf4, 0xd1, 0xf1, 0x39, 0x93,
+	0x17, 0x51, 0x19, 0xe3, 0x19, 0x1e, 0x76, 0x37,
+	0x25, 0xfb, 0x09, 0x27, 0x6a, 0xab, 0x67, 0x6f,
+	0x14, 0x12, 0x64, 0xe7, 0xc4, 0x07, 0xdf, 0x4d,
+	0x17, 0xbb, 0x6d, 0xe0, 0xe9, 0xb9, 0xab, 0xca,
+	0x10, 0x68, 0xaf, 0x7e, 0xb7, 0x33, 0x54, 0x73,
+	0x07, 0x6e, 0xf7, 0x81, 0x97, 0x9c, 0x05, 0x6f,
+	0x84, 0x5f, 0xd2, 0x42, 0xfb, 0x38, 0xcf, 0xd1,
+	0x2f, 0x14, 0x30, 0x88, 0x98, 0x4d, 0x5a, 0xa9,
+	0x76, 0xd5, 0x4f, 0x3e, 0x70, 0x6c, 0x85, 0x76,
+	0xd7, 0x01, 0xa0, 0x1a, 0xc8, 0x4e, 0xaa, 0xac,
+	0x78, 0xfe, 0x46, 0xde, 0x6a, 0x05, 0x46, 0xa7,
+	0x43, 0x0c, 0xb9, 0xde, 0xb9, 0x68, 0xfb, 0xce,
+	0x42, 0x99, 0x07, 0x4d, 0x0b, 0x3b, 0x5a, 0x30,
+	0x35, 0xa8, 0xf9, 0x3a, 0x73, 0xef, 0x0f, 0xdb,
+	0x1e, 0x16, 0x42, 0xc4, 0xba, 0xae, 0x58, 0xaa,
+	0xf8, 0xe5, 0x75, 0x2f, 0x1b, 0x15, 0x5c, 0xfd,
+	0x0a, 0x97, 0xd0, 0xe4, 0x37, 0x83, 0x61, 0x5f,
+	0x43, 0xa6, 0xc7, 0x3f, 0x38, 0x59, 0xe6, 0xeb,
+	0xa3, 0x90, 0xc3, 0xaa, 0xaa, 0x5a, 0xd3, 0x34,
+	0xd4, 0x17, 0xc8, 0x65, 0x3e, 0x57, 0xbc, 0x5e,
+	0xdd, 0x9e, 0xb7, 0xf0, 0x2e, 0x5b, 0xb2, 0x1f,
+	0x8a, 0x08, 0x0d, 0x45, 0x91, 0x0b, 0x29, 0x53,
+	0x4f, 0x4c, 0x5a, 0x73, 0x56, 0xfe, 0xaf, 0x41,
+	0x01, 0x39, 0x0a, 0x24, 0x3c, 0x7e, 0xbe, 0x4e,
+	0x53, 0xf3, 0xeb, 0x06, 0x66, 0x51, 0x28, 0x1d,
+	0xbd, 0x41, 0x0a, 0x01, 0xab, 0x16, 0x47, 0x27,
+	0x47, 0x47, 0xf7, 0xcb, 0x46, 0x0a, 0x70, 0x9e,
+	0x01, 0x9c, 0x09, 0xe1, 0x2a, 0x00, 0x1a, 0xd8,
+	0xd4, 0x79, 0x9d, 0x80, 0x15, 0x8e, 0x53, 0x2a,
+	0x65, 0x83, 0x78, 0x3e, 0x03, 0x00, 0x07, 0x12,
+	0x1f, 0x33, 0x3e, 0x7b, 0x13, 0x37, 0xf1, 0xc3,
+	0xef, 0xb7, 0xc1, 0x20, 0x3c, 0x3e, 0x67, 0x66,
+	0x5d, 0x88, 0xa7, 0x7d, 0x33, 0x50, 0x77, 0xb0,
+	0x28, 0x8e, 0xe7, 0x2c, 0x2e, 0x7a, 0xf4, 0x3c,
+	0x8d, 0x74, 0x83, 0xaf, 0x8e, 0x87, 0x0f, 0xe4,
+	0x50, 0xff, 0x84, 0x5c, 0x47, 0x0c, 0x6a, 0x49,
+	0xbf, 0x42, 0x86, 0x77, 0x15, 0x48, 0xa5, 0x90,
+	0x5d, 0x93, 0xd6, 0x2a, 0x11, 0xd5, 0xd5, 0x11,
+	0xaa, 0xce, 0xe7, 0x6f, 0xa5, 0xb0, 0x09, 0x2c,
+	0x8d, 0xd3, 0x92, 0xf0, 0x5a, 0x2a, 0xda, 0x5b,
+	0x1e, 0xd5, 0x9a, 0xc4, 0xc4, 0xf3, 0x49, 0x74,
+	0x41, 0xca, 0xe8, 0xc1, 0xf8, 0x44, 0xd6, 0x3c,
+	0xae, 0x6c, 0x1d, 0x9a, 0x30, 0x04, 0x4d, 0x27,
+	0x0e, 0xb1, 0x5f, 0x59, 0xa2, 0x24, 0xe8, 0xe1,
+	0x98, 0xc5, 0x6a, 0x4c, 0xfe, 0x41, 0xd2, 0x27,
+	0x42, 0x52, 0xe1, 0xe9, 0x7d, 0x62, 0xe4, 0x88,
+	0x0f, 0xad, 0xb2, 0x70, 0xcb, 0x9d, 0x4c, 0x27,
+	0x2e, 0x76, 0x1e, 0x1a, 0x63, 0x65, 0xf5, 0x3b,
+	0xf8, 0x57, 0x69, 0xeb, 0x5b, 0x38, 0x26, 0x39,
+	0x33, 0x25, 0x45, 0x3e, 0x91, 0xb8, 0xd8, 0xc7,
+	0xd5, 0x42, 0xc0, 0x22, 0x31, 0x74, 0xf4, 0xbc,
+	0x0c, 0x23, 0xf1, 0xca, 0xc1, 0x8d, 0xd7, 0xbe,
+	0xc9, 0x62, 0xe4, 0x08, 0x1a, 0xcf, 0x36, 0xd5,
+	0xfe, 0x55, 0x21, 0x59, 0x91, 0x87, 0x87, 0xdf,
+	0x06, 0xdb, 0xdf, 0x96, 0x45, 0x58, 0xda, 0x05,
+	0xcd, 0x50, 0x4d, 0xd2, 0x7d, 0x05, 0x18, 0x73,
+	0x6a, 0x8d, 0x11, 0x85, 0xa6, 0x88, 0xe8, 0xda,
+	0xe6, 0x30, 0x33, 0xa4, 0x89, 0x31, 0x75, 0xbe,
+	0x69, 0x43, 0x84, 0x43, 0x50, 0x87, 0xdd, 0x71,
+	0x36, 0x83, 0xc3, 0x78, 0x74, 0x24, 0x0a, 0xed,
+	0x7b, 0xdb, 0xa4, 0x24, 0x0b, 0xb9, 0x7e, 0x5d,
+	0xff, 0xde, 0xb1, 0xef, 0x61, 0x5a, 0x45, 0x33,
+	0xf6, 0x17, 0x07, 0x08, 0x98, 0x83, 0x92, 0x0f,
+	0x23, 0x6d, 0xe6, 0xaa, 0x17, 0x54, 0xad, 0x6a,
+	0xc8, 0xdb, 0x26, 0xbe, 0xb8, 0xb6, 0x08, 0xfa,
+	0x68, 0xf1, 0xd7, 0x79, 0x6f, 0x18, 0xb4, 0x9e,
+	0x2d, 0x3f, 0x1b, 0x64, 0xaf, 0x8d, 0x06, 0x0e,
+	0x49, 0x28, 0xe0, 0x5d, 0x45, 0x68, 0x13, 0x87,
+	0xfa, 0xde, 0x40, 0x7b, 0xd2, 0xc3, 0x94, 0xd5,
+	0xe1, 0xd9, 0xc2, 0xaf, 0x55, 0x89, 0xeb, 0xb4,
+	0x12, 0x59, 0xa8, 0xd4, 0xc5, 0x29, 0x66, 0x38,
+	0xe6, 0xac, 0x22, 0x22, 0xd9, 0x64, 0x9b, 0x34,
+	0x0a, 0x32, 0x9f, 0xc2, 0xbf, 0x17, 0x6c, 0x3f,
+	0x71, 0x7a, 0x38, 0x6b, 0x98, 0xfb, 0x49, 0x36,
+	0x89, 0xc9, 0xe2, 0xd6, 0xc7, 0x5d, 0xd0, 0x69,
+	0x5f, 0x23, 0x35, 0xc9, 0x30, 0xe2, 0xfd, 0x44,
+	0x58, 0x39, 0xd7, 0x97, 0xfb, 0x5c, 0x00, 0xd5,
+	0x4f, 0x7a, 0x1a, 0x95, 0x8b, 0x62, 0x4b, 0xce,
+	0xe5, 0x91, 0x21, 0x7b, 0x30, 0x00, 0xd6, 0xdd,
+	0x6d, 0x02, 0x86, 0x49, 0x0f, 0x3c, 0x1a, 0x27,
+	0x3c, 0xd3, 0x0e, 0x71, 0xf2, 0xff, 0xf5, 0x2f,
+	0x87, 0xac, 0x67, 0x59, 0x81, 0xa3, 0xf7, 0xf8,
+	0xd6, 0x11, 0x0c, 0x84, 0xa9, 0x03, 0xee, 0x2a,
+	0xc4, 0xf3, 0x22, 0xab, 0x7c, 0xe2, 0x25, 0xf5,
+	0x67, 0xa3, 0xe4, 0x11, 0xe0, 0x59, 0xb3, 0xca,
+	0x87, 0xa0, 0xae, 0xc9, 0xa6, 0x62, 0x1b, 0x6e,
+	0x4d, 0x02, 0x6b, 0x07, 0x9d, 0xfd, 0xd0, 0x92,
+	0x06, 0xe1, 0xb2, 0x9a, 0x4a, 0x1f, 0x1f, 0x13,
+	0x49, 0x99, 0x97, 0x08, 0xde, 0x7f, 0x98, 0xaf,
+	0x51, 0x98, 0xee, 0x2c, 0xcb, 0xf0, 0x0b, 0xc6,
+	0xb6, 0xb7, 0x2d, 0x9a, 0xb1, 0xac, 0xa6, 0xe3,
+	0x15, 0x77, 0x9d, 0x6b, 0x1a, 0xe4, 0xfc, 0x8b,
+	0xf2, 0x17, 0x59, 0x08, 0x04, 0x58, 0x81, 0x9d,
+	0x1b, 0x1b, 0x69, 0x55, 0xc2, 0xb4, 0x3c, 0x1f,
+	0x50, 0xf1, 0x7f, 0x77, 0x90, 0x4c, 0x66, 0x40,
+	0x5a, 0xc0, 0x33, 0x1f, 0xcb, 0x05, 0x6d, 0x5c,
+	0x06, 0x87, 0x52, 0xa2, 0x8f, 0x26, 0xd5, 0x4f
+};
+static const u8 dec_assoc010[] __initconst = {
+	0xd2, 0xa1, 0x70, 0xdb, 0x7a, 0xf8, 0xfa, 0x27,
+	0xba, 0x73, 0x0f, 0xbf, 0x3d, 0x1e, 0x82, 0xb2
+};
+static const u8 dec_nonce010[] __initconst = {
+	0xdb, 0x92, 0x0f, 0x7f, 0x17, 0x54, 0x0c, 0x30
+};
+static const u8 dec_key010[] __initconst = {
+	0x47, 0x11, 0xeb, 0x86, 0x2b, 0x2c, 0xab, 0x44,
+	0x34, 0xda, 0x7f, 0x57, 0x03, 0x39, 0x0c, 0xaf,
+	0x2c, 0x14, 0xfd, 0x65, 0x23, 0xe9, 0x8e, 0x74,
+	0xd5, 0x08, 0x68, 0x08, 0xe7, 0xb4, 0x72, 0xd7
+};
+
+static const u8 dec_input011[] __initconst = {
+	0x6a, 0xfc, 0x4b, 0x25, 0xdf, 0xc0, 0xe4, 0xe8,
+	0x17, 0x4d, 0x4c, 0xc9, 0x7e, 0xde, 0x3a, 0xcc,
+	0x3c, 0xba, 0x6a, 0x77, 0x47, 0xdb, 0xe3, 0x74,
+	0x7a, 0x4d, 0x5f, 0x8d, 0x37, 0x55, 0x80, 0x73,
+	0x90, 0x66, 0x5d, 0x3a, 0x7d, 0x5d, 0x86, 0x5e,
+	0x8d, 0xfd, 0x83, 0xff, 0x4e, 0x74, 0x6f, 0xf9,
+	0xe6, 0x70, 0x17, 0x70, 0x3e, 0x96, 0xa7, 0x7e,
+	0xcb, 0xab, 0x8f, 0x58, 0x24, 0x9b, 0x01, 0xfd,
+	0xcb, 0xe6, 0x4d, 0x9b, 0xf0, 0x88, 0x94, 0x57,
+	0x66, 0xef, 0x72, 0x4c, 0x42, 0x6e, 0x16, 0x19,
+	0x15, 0xea, 0x70, 0x5b, 0xac, 0x13, 0xdb, 0x9f,
+	0x18, 0xe2, 0x3c, 0x26, 0x97, 0xbc, 0xdc, 0x45,
+	0x8c, 0x6c, 0x24, 0x69, 0x9c, 0xf7, 0x65, 0x1e,
+	0x18, 0x59, 0x31, 0x7c, 0xe4, 0x73, 0xbc, 0x39,
+	0x62, 0xc6, 0x5c, 0x9f, 0xbf, 0xfa, 0x90, 0x03,
+	0xc9, 0x72, 0x26, 0xb6, 0x1b, 0xc2, 0xb7, 0x3f,
+	0xf2, 0x13, 0x77, 0xf2, 0x8d, 0xb9, 0x47, 0xd0,
+	0x53, 0xdd, 0xc8, 0x91, 0x83, 0x8b, 0xb1, 0xce,
+	0xa3, 0xfe, 0xcd, 0xd9, 0xdd, 0x92, 0x7b, 0xdb,
+	0xb8, 0xfb, 0xc9, 0x2d, 0x01, 0x59, 0x39, 0x52,
+	0xad, 0x1b, 0xec, 0xcf, 0xd7, 0x70, 0x13, 0x21,
+	0xf5, 0x47, 0xaa, 0x18, 0x21, 0x5c, 0xc9, 0x9a,
+	0xd2, 0x6b, 0x05, 0x9c, 0x01, 0xa1, 0xda, 0x35,
+	0x5d, 0xb3, 0x70, 0xe6, 0xa9, 0x80, 0x8b, 0x91,
+	0xb7, 0xb3, 0x5f, 0x24, 0x9a, 0xb7, 0xd1, 0x6b,
+	0xa1, 0x1c, 0x50, 0xba, 0x49, 0xe0, 0xee, 0x2e,
+	0x75, 0xac, 0x69, 0xc0, 0xeb, 0x03, 0xdd, 0x19,
+	0xe5, 0xf6, 0x06, 0xdd, 0xc3, 0xd7, 0x2b, 0x07,
+	0x07, 0x30, 0xa7, 0x19, 0x0c, 0xbf, 0xe6, 0x18,
+	0xcc, 0xb1, 0x01, 0x11, 0x85, 0x77, 0x1d, 0x96,
+	0xa7, 0xa3, 0x00, 0x84, 0x02, 0xa2, 0x83, 0x68,
+	0xda, 0x17, 0x27, 0xc8, 0x7f, 0x23, 0xb7, 0xf4,
+	0x13, 0x85, 0xcf, 0xdd, 0x7a, 0x7d, 0x24, 0x57,
+	0xfe, 0x05, 0x93, 0xf5, 0x74, 0xce, 0xed, 0x0c,
+	0x20, 0x98, 0x8d, 0x92, 0x30, 0xa1, 0x29, 0x23,
+	0x1a, 0xa0, 0x4f, 0x69, 0x56, 0x4c, 0xe1, 0xc8,
+	0xce, 0xf6, 0x9a, 0x0c, 0xa4, 0xfa, 0x04, 0xf6,
+	0x62, 0x95, 0xf2, 0xfa, 0xc7, 0x40, 0x68, 0x40,
+	0x8f, 0x41, 0xda, 0xb4, 0x26, 0x6f, 0x70, 0xab,
+	0x40, 0x61, 0xa4, 0x0e, 0x75, 0xfb, 0x86, 0xeb,
+	0x9d, 0x9a, 0x1f, 0xec, 0x76, 0x99, 0xe7, 0xea,
+	0xaa, 0x1e, 0x2d, 0xb5, 0xd4, 0xa6, 0x1a, 0xb8,
+	0x61, 0x0a, 0x1d, 0x16, 0x5b, 0x98, 0xc2, 0x31,
+	0x40, 0xe7, 0x23, 0x1d, 0x66, 0x99, 0xc8, 0xc0,
+	0xd7, 0xce, 0xf3, 0x57, 0x40, 0x04, 0x3f, 0xfc,
+	0xea, 0xb3, 0xfc, 0xd2, 0xd3, 0x99, 0xa4, 0x94,
+	0x69, 0xa0, 0xef, 0xd1, 0x85, 0xb3, 0xa6, 0xb1,
+	0x28, 0xbf, 0x94, 0x67, 0x22, 0xc3, 0x36, 0x46,
+	0xf8, 0xd2, 0x0f, 0x5f, 0xf4, 0x59, 0x80, 0xe6,
+	0x2d, 0x43, 0x08, 0x7d, 0x19, 0x09, 0x97, 0xa7,
+	0x4c, 0x3d, 0x8d, 0xba, 0x65, 0x62, 0xa3, 0x71,
+	0x33, 0x29, 0x62, 0xdb, 0xc1, 0x33, 0x34, 0x1a,
+	0x63, 0x33, 0x16, 0xb6, 0x64, 0x7e, 0xab, 0x33,
+	0xf0, 0xe6, 0x26, 0x68, 0xba, 0x1d, 0x2e, 0x38,
+	0x08, 0xe6, 0x02, 0xd3, 0x25, 0x2c, 0x47, 0x23,
+	0x58, 0x34, 0x0f, 0x9d, 0x63, 0x4f, 0x63, 0xbb,
+	0x7f, 0x3b, 0x34, 0x38, 0xa7, 0xb5, 0x8d, 0x65,
+	0xd9, 0x9f, 0x79, 0x55, 0x3e, 0x4d, 0xe7, 0x73,
+	0xd8, 0xf6, 0x98, 0x97, 0x84, 0x60, 0x9c, 0xc8,
+	0xa9, 0x3c, 0xf6, 0xdc, 0x12, 0x5c, 0xe1, 0xbb,
+	0x0b, 0x8b, 0x98, 0x9c, 0x9d, 0x26, 0x7c, 0x4a,
+	0xe6, 0x46, 0x36, 0x58, 0x21, 0x4a, 0xee, 0xca,
+	0xd7, 0x3b, 0xc2, 0x6c, 0x49, 0x2f, 0xe5, 0xd5,
+	0x03, 0x59, 0x84, 0x53, 0xcb, 0xfe, 0x92, 0x71,
+	0x2e, 0x7c, 0x21, 0xcc, 0x99, 0x85, 0x7f, 0xb8,
+	0x74, 0x90, 0x13, 0x42, 0x3f, 0xe0, 0x6b, 0x1d,
+	0xf2, 0x4d, 0x54, 0xd4, 0xfc, 0x3a, 0x05, 0xe6,
+	0x74, 0xaf, 0xa6, 0xa0, 0x2a, 0x20, 0x23, 0x5d,
+	0x34, 0x5c, 0xd9, 0x3e, 0x4e, 0xfa, 0x93, 0xe7,
+	0xaa, 0xe9, 0x6f, 0x08, 0x43, 0x67, 0x41, 0xc5,
+	0xad, 0xfb, 0x31, 0x95, 0x82, 0x73, 0x32, 0xd8,
+	0xa6, 0xa3, 0xed, 0x0e, 0x2d, 0xf6, 0x5f, 0xfd,
+	0x80, 0xa6, 0x7a, 0xe0, 0xdf, 0x78, 0x15, 0x29,
+	0x74, 0x33, 0xd0, 0x9e, 0x83, 0x86, 0x72, 0x22,
+	0x57, 0x29, 0xb9, 0x9e, 0x5d, 0xd3, 0x1a, 0xb5,
+	0x96, 0x72, 0x41, 0x3d, 0xf1, 0x64, 0x43, 0x67,
+	0xee, 0xaa, 0x5c, 0xd3, 0x9a, 0x96, 0x13, 0x11,
+	0x5d, 0xf3, 0x0c, 0x87, 0x82, 0x1e, 0x41, 0x9e,
+	0xd0, 0x27, 0xd7, 0x54, 0x3b, 0x67, 0x73, 0x09,
+	0x91, 0xe9, 0xd5, 0x36, 0xa7, 0xb5, 0x55, 0xe4,
+	0xf3, 0x21, 0x51, 0x49, 0x22, 0x07, 0x55, 0x4f,
+	0x44, 0x4b, 0xd2, 0x15, 0x93, 0x17, 0x2a, 0xfa,
+	0x4d, 0x4a, 0x57, 0xdb, 0x4c, 0xa6, 0xeb, 0xec,
+	0x53, 0x25, 0x6c, 0x21, 0xed, 0x00, 0x4c, 0x3b,
+	0xca, 0x14, 0x57, 0xa9, 0xd6, 0x6a, 0xcd, 0x8d,
+	0x5e, 0x74, 0xac, 0x72, 0xc1, 0x97, 0xe5, 0x1b,
+	0x45, 0x4e, 0xda, 0xfc, 0xcc, 0x40, 0xe8, 0x48,
+	0x88, 0x0b, 0xa3, 0xe3, 0x8d, 0x83, 0x42, 0xc3,
+	0x23, 0xfd, 0x68, 0xb5, 0x8e, 0xf1, 0x9d, 0x63,
+	0x77, 0xe9, 0xa3, 0x8e, 0x8c, 0x26, 0x6b, 0xbd,
+	0x72, 0x73, 0x35, 0x0c, 0x03, 0xf8, 0x43, 0x78,
+	0x52, 0x71, 0x15, 0x1f, 0x71, 0x5d, 0x6e, 0xed,
+	0xb9, 0xcc, 0x86, 0x30, 0xdb, 0x2b, 0xd3, 0x82,
+	0x88, 0x23, 0x71, 0x90, 0x53, 0x5c, 0xa9, 0x2f,
+	0x76, 0x01, 0xb7, 0x9a, 0xfe, 0x43, 0x55, 0xa3,
+	0x04, 0x9b, 0x0e, 0xe4, 0x59, 0xdf, 0xc9, 0xe9,
+	0xb1, 0xea, 0x29, 0x28, 0x3c, 0x5c, 0xae, 0x72,
+	0x84, 0xb6, 0xc6, 0xeb, 0x0c, 0x27, 0x07, 0x74,
+	0x90, 0x0d, 0x31, 0xb0, 0x00, 0x77, 0xe9, 0x40,
+	0x70, 0x6f, 0x68, 0xa7, 0xfd, 0x06, 0xec, 0x4b,
+	0xc0, 0xb7, 0xac, 0xbc, 0x33, 0xb7, 0x6d, 0x0a,
+	0xbd, 0x12, 0x1b, 0x59, 0xcb, 0xdd, 0x32, 0xf5,
+	0x1d, 0x94, 0x57, 0x76, 0x9e, 0x0c, 0x18, 0x98,
+	0x71, 0xd7, 0x2a, 0xdb, 0x0b, 0x7b, 0xa7, 0x71,
+	0xb7, 0x67, 0x81, 0x23, 0x96, 0xae, 0xb9, 0x7e,
+	0x32, 0x43, 0x92, 0x8a, 0x19, 0xa0, 0xc4, 0xd4,
+	0x3b, 0x57, 0xf9, 0x4a, 0x2c, 0xfb, 0x51, 0x46,
+	0xbb, 0xcb, 0x5d, 0xb3, 0xef, 0x13, 0x93, 0x6e,
+	0x68, 0x42, 0x54, 0x57, 0xd3, 0x6a, 0x3a, 0x8f,
+	0x9d, 0x66, 0xbf, 0xbd, 0x36, 0x23, 0xf5, 0x93,
+	0x83, 0x7b, 0x9c, 0xc0, 0xdd, 0xc5, 0x49, 0xc0,
+	0x64, 0xed, 0x07, 0x12, 0xb3, 0xe6, 0xe4, 0xe5,
+	0x38, 0x95, 0x23, 0xb1, 0xa0, 0x3b, 0x1a, 0x61,
+	0xda, 0x17, 0xac, 0xc3, 0x58, 0xdd, 0x74, 0x64,
+	0x22, 0x11, 0xe8, 0x32, 0x1d, 0x16, 0x93, 0x85,
+	0x99, 0xa5, 0x9c, 0x34, 0x55, 0xb1, 0xe9, 0x20,
+	0x72, 0xc9, 0x28, 0x7b, 0x79, 0x00, 0xa1, 0xa6,
+	0xa3, 0x27, 0x40, 0x18, 0x8a, 0x54, 0xe0, 0xcc,
+	0xe8, 0x4e, 0x8e, 0x43, 0x96, 0xe7, 0x3f, 0xc8,
+	0xe9, 0xb2, 0xf9, 0xc9, 0xda, 0x04, 0x71, 0x50,
+	0x47, 0xe4, 0xaa, 0xce, 0xa2, 0x30, 0xc8, 0xe4,
+	0xac, 0xc7, 0x0d, 0x06, 0x2e, 0xe6, 0xe8, 0x80,
+	0x36, 0x29, 0x9e, 0x01, 0xb8, 0xc3, 0xf0, 0xa0,
+	0x5d, 0x7a, 0xca, 0x4d, 0xa0, 0x57, 0xbd, 0x2a,
+	0x45, 0xa7, 0x7f, 0x9c, 0x93, 0x07, 0x8f, 0x35,
+	0x67, 0x92, 0xe3, 0xe9, 0x7f, 0xa8, 0x61, 0x43,
+	0x9e, 0x25, 0x4f, 0x33, 0x76, 0x13, 0x6e, 0x12,
+	0xb9, 0xdd, 0xa4, 0x7c, 0x08, 0x9f, 0x7c, 0xe7,
+	0x0a, 0x8d, 0x84, 0x06, 0xa4, 0x33, 0x17, 0x34,
+	0x5e, 0x10, 0x7c, 0xc0, 0xa8, 0x3d, 0x1f, 0x42,
+	0x20, 0x51, 0x65, 0x5d, 0x09, 0xc3, 0xaa, 0xc0,
+	0xc8, 0x0d, 0xf0, 0x79, 0xbc, 0x20, 0x1b, 0x95,
+	0xe7, 0x06, 0x7d, 0x47, 0x20, 0x03, 0x1a, 0x74,
+	0xdd, 0xe2, 0xd4, 0xae, 0x38, 0x71, 0x9b, 0xf5,
+	0x80, 0xec, 0x08, 0x4e, 0x56, 0xba, 0x76, 0x12,
+	0x1a, 0xdf, 0x48, 0xf3, 0xae, 0xb3, 0xe6, 0xe6,
+	0xbe, 0xc0, 0x91, 0x2e, 0x01, 0xb3, 0x01, 0x86,
+	0xa2, 0xb9, 0x52, 0xd1, 0x21, 0xae, 0xd4, 0x97,
+	0x1d, 0xef, 0x41, 0x12, 0x95, 0x3d, 0x48, 0x45,
+	0x1c, 0x56, 0x32, 0x8f, 0xb8, 0x43, 0xbb, 0x19,
+	0xf3, 0xca, 0xe9, 0xeb, 0x6d, 0x84, 0xbe, 0x86,
+	0x06, 0xe2, 0x36, 0xb2, 0x62, 0x9d, 0xd3, 0x4c,
+	0x48, 0x18, 0x54, 0x13, 0x4e, 0xcf, 0xfd, 0xba,
+	0x84, 0xb9, 0x30, 0x53, 0xcf, 0xfb, 0xb9, 0x29,
+	0x8f, 0xdc, 0x9f, 0xef, 0x60, 0x0b, 0x64, 0xf6,
+	0x8b, 0xee, 0xa6, 0x91, 0xc2, 0x41, 0x6c, 0xf6,
+	0xfa, 0x79, 0x67, 0x4b, 0xc1, 0x3f, 0xaf, 0x09,
+	0x81, 0xd4, 0x5d, 0xcb, 0x09, 0xdf, 0x36, 0x31,
+	0xc0, 0x14, 0x3c, 0x7c, 0x0e, 0x65, 0x95, 0x99,
+	0x6d, 0xa3, 0xf4, 0xd7, 0x38, 0xee, 0x1a, 0x2b,
+	0x37, 0xe2, 0xa4, 0x3b, 0x4b, 0xd0, 0x65, 0xca,
+	0xf8, 0xc3, 0xe8, 0x15, 0x20, 0xef, 0xf2, 0x00,
+	0xfd, 0x01, 0x09, 0xc5, 0xc8, 0x17, 0x04, 0x93,
+	0xd0, 0x93, 0x03, 0x55, 0xc5, 0xfe, 0x32, 0xa3,
+	0x3e, 0x28, 0x2d, 0x3b, 0x93, 0x8a, 0xcc, 0x07,
+	0x72, 0x80, 0x8b, 0x74, 0x16, 0x24, 0xbb, 0xda,
+	0x94, 0x39, 0x30, 0x8f, 0xb1, 0xcd, 0x4a, 0x90,
+	0x92, 0x7c, 0x14, 0x8f, 0x95, 0x4e, 0xac, 0x9b,
+	0xd8, 0x8f, 0x1a, 0x87, 0xa4, 0x32, 0x27, 0x8a,
+	0xba, 0xf7, 0x41, 0xcf, 0x84, 0x37, 0x19, 0xe6,
+	0x06, 0xf5, 0x0e, 0xcf, 0x36, 0xf5, 0x9e, 0x6c,
+	0xde, 0xbc, 0xff, 0x64, 0x7e, 0x4e, 0x59, 0x57,
+	0x48, 0xfe, 0x14, 0xf7, 0x9c, 0x93, 0x5d, 0x15,
+	0xad, 0xcc, 0x11, 0xb1, 0x17, 0x18, 0xb2, 0x7e,
+	0xcc, 0xab, 0xe9, 0xce, 0x7d, 0x77, 0x5b, 0x51,
+	0x1b, 0x1e, 0x20, 0xa8, 0x32, 0x06, 0x0e, 0x75,
+	0x93, 0xac, 0xdb, 0x35, 0x37, 0x1f, 0xe9, 0x19,
+	0x1d, 0xb4, 0x71, 0x97, 0xd6, 0x4e, 0x2c, 0x08,
+	0xa5, 0x13, 0xf9, 0x0e, 0x7e, 0x78, 0x6e, 0x14,
+	0xe0, 0xa9, 0xb9, 0x96, 0x4c, 0x80, 0x82, 0xba,
+	0x17, 0xb3, 0x9d, 0x69, 0xb0, 0x84, 0x46, 0xff,
+	0xf9, 0x52, 0x79, 0x94, 0x58, 0x3a, 0x62, 0x90,
+	0x15, 0x35, 0x71, 0x10, 0x37, 0xed, 0xa1, 0x8e,
+	0x53, 0x6e, 0xf4, 0x26, 0x57, 0x93, 0x15, 0x93,
+	0xf6, 0x81, 0x2c, 0x5a, 0x10, 0xda, 0x92, 0xad,
+	0x2f, 0xdb, 0x28, 0x31, 0x2d, 0x55, 0x04, 0xd2,
+	0x06, 0x28, 0x8c, 0x1e, 0xdc, 0xea, 0x54, 0xac,
+	0xff, 0xb7, 0x6c, 0x30, 0x15, 0xd4, 0xb4, 0x0d,
+	0x00, 0x93, 0x57, 0xdd, 0xd2, 0x07, 0x07, 0x06,
+	0xd9, 0x43, 0x9b, 0xcd, 0x3a, 0xf4, 0x7d, 0x4c,
+	0x36, 0x5d, 0x23, 0xa2, 0xcc, 0x57, 0x40, 0x91,
+	0xe9, 0x2c, 0x2f, 0x2c, 0xd5, 0x30, 0x9b, 0x17,
+	0xb0, 0xc9, 0xf7, 0xa7, 0x2f, 0xd1, 0x93, 0x20,
+	0x6b, 0xc6, 0xc1, 0xe4, 0x6f, 0xcb, 0xd1, 0xe7,
+	0x09, 0x0f, 0x9e, 0xdc, 0xaa, 0x9f, 0x2f, 0xdf,
+	0x56, 0x9f, 0xd4, 0x33, 0x04, 0xaf, 0xd3, 0x6c,
+	0x58, 0x61, 0xf0, 0x30, 0xec, 0xf2, 0x7f, 0xf2,
+	0x9c, 0xdf, 0x39, 0xbb, 0x6f, 0xa2, 0x8c, 0x7e,
+	0xc4, 0x22, 0x51, 0x71, 0xc0, 0x4d, 0x14, 0x1a,
+	0xc4, 0xcd, 0x04, 0xd9, 0x87, 0x08, 0x50, 0x05,
+	0xcc, 0xaf, 0xf6, 0xf0, 0x8f, 0x92, 0x54, 0x58,
+	0xc2, 0xc7, 0x09, 0x7a, 0x59, 0x02, 0x05, 0xe8,
+	0xb0, 0x86, 0xd9, 0xbf, 0x7b, 0x35, 0x51, 0x4d,
+	0xaf, 0x08, 0x97, 0x2c, 0x65, 0xda, 0x2a, 0x71,
+	0x3a, 0xa8, 0x51, 0xcc, 0xf2, 0x73, 0x27, 0xc3,
+	0xfd, 0x62, 0xcf, 0xe3, 0xb2, 0xca, 0xcb, 0xbe,
+	0x1a, 0x0a, 0xa1, 0x34, 0x7b, 0x77, 0xc4, 0x62,
+	0x68, 0x78, 0x5f, 0x94, 0x07, 0x04, 0x65, 0x16,
+	0x4b, 0x61, 0xcb, 0xff, 0x75, 0x26, 0x50, 0x66,
+	0x1f, 0x6e, 0x93, 0xf8, 0xc5, 0x51, 0xeb, 0xa4,
+	0x4a, 0x48, 0x68, 0x6b, 0xe2, 0x5e, 0x44, 0xb2,
+	0x50, 0x2c, 0x6c, 0xae, 0x79, 0x4e, 0x66, 0x35,
+	0x81, 0x50, 0xac, 0xbc, 0x3f, 0xb1, 0x0c, 0xf3,
+	0x05, 0x3c, 0x4a, 0xa3, 0x6c, 0x2a, 0x79, 0xb4,
+	0xb7, 0xab, 0xca, 0xc7, 0x9b, 0x8e, 0xcd, 0x5f,
+	0x11, 0x03, 0xcb, 0x30, 0xa3, 0xab, 0xda, 0xfe,
+	0x64, 0xb9, 0xbb, 0xd8, 0x5e, 0x3a, 0x1a, 0x56,
+	0xe5, 0x05, 0x48, 0x90, 0x1e, 0x61, 0x69, 0x1b,
+	0x22, 0xe6, 0x1a, 0x3c, 0x75, 0xad, 0x1f, 0x37,
+	0x28, 0xdc, 0xe4, 0x6d, 0xbd, 0x42, 0xdc, 0xd3,
+	0xc8, 0xb6, 0x1c, 0x48, 0xfe, 0x94, 0x77, 0x7f,
+	0xbd, 0x62, 0xac, 0xa3, 0x47, 0x27, 0xcf, 0x5f,
+	0xd9, 0xdb, 0xaf, 0xec, 0xf7, 0x5e, 0xc1, 0xb0,
+	0x9d, 0x01, 0x26, 0x99, 0x7e, 0x8f, 0x03, 0x70,
+	0xb5, 0x42, 0xbe, 0x67, 0x28, 0x1b, 0x7c, 0xbd,
+	0x61, 0x21, 0x97, 0xcc, 0x5c, 0xe1, 0x97, 0x8f,
+	0x8d, 0xde, 0x2b, 0xaa, 0xa7, 0x71, 0x1d, 0x1e,
+	0x02, 0x73, 0x70, 0x58, 0x32, 0x5b, 0x1d, 0x67,
+	0x3d, 0xe0, 0x74, 0x4f, 0x03, 0xf2, 0x70, 0x51,
+	0x79, 0xf1, 0x61, 0x70, 0x15, 0x74, 0x9d, 0x23,
+	0x89, 0xde, 0xac, 0xfd, 0xde, 0xd0, 0x1f, 0xc3,
+	0x87, 0x44, 0x35, 0x4b, 0xe5, 0xb0, 0x60, 0xc5,
+	0x22, 0xe4, 0x9e, 0xca, 0xeb, 0xd5, 0x3a, 0x09,
+	0x45, 0xa4, 0xdb, 0xfa, 0x3f, 0xeb, 0x1b, 0xc7,
+	0xc8, 0x14, 0x99, 0x51, 0x92, 0x10, 0xed, 0xed,
+	0x28, 0xe0, 0xa1, 0xf8, 0x26, 0xcf, 0xcd, 0xcb,
+	0x63, 0xa1, 0x3b, 0xe3, 0xdf, 0x7e, 0xfe, 0xa6,
+	0xf0, 0x81, 0x9a, 0xbf, 0x55, 0xde, 0x54, 0xd5,
+	0x56, 0x60, 0x98, 0x10, 0x68, 0xf4, 0x38, 0x96,
+	0x8e, 0x6f, 0x1d, 0x44, 0x7f, 0xd6, 0x2f, 0xfe,
+	0x55, 0xfb, 0x0c, 0x7e, 0x67, 0xe2, 0x61, 0x44,
+	0xed, 0xf2, 0x35, 0x30, 0x5d, 0xe9, 0xc7, 0xd6,
+	0x6d, 0xe0, 0xa0, 0xed, 0xf3, 0xfc, 0xd8, 0x3e,
+	0x0a, 0x7b, 0xcd, 0xaf, 0x65, 0x68, 0x18, 0xc0,
+	0xec, 0x04, 0x1c, 0x74, 0x6d, 0xe2, 0x6e, 0x79,
+	0xd4, 0x11, 0x2b, 0x62, 0xd5, 0x27, 0xad, 0x4f,
+	0x01, 0x59, 0x73, 0xcc, 0x6a, 0x53, 0xfb, 0x2d,
+	0xd5, 0x4e, 0x99, 0x21, 0x65, 0x4d, 0xf5, 0x82,
+	0xf7, 0xd8, 0x42, 0xce, 0x6f, 0x3d, 0x36, 0x47,
+	0xf1, 0x05, 0x16, 0xe8, 0x1b, 0x6a, 0x8f, 0x93,
+	0xf2, 0x8f, 0x37, 0x40, 0x12, 0x28, 0xa3, 0xe6,
+	0xb9, 0x17, 0x4a, 0x1f, 0xb1, 0xd1, 0x66, 0x69,
+	0x86, 0xc4, 0xfc, 0x97, 0xae, 0x3f, 0x8f, 0x1e,
+	0x2b, 0xdf, 0xcd, 0xf9, 0x3c
+};
+static const u8 dec_output011[] __initconst = {
+	0x7a, 0x57, 0xf2, 0xc7, 0x06, 0x3f, 0x50, 0x7b,
+	0x36, 0x1a, 0x66, 0x5c, 0xb9, 0x0e, 0x5e, 0x3b,
+	0x45, 0x60, 0xbe, 0x9a, 0x31, 0x9f, 0xff, 0x5d,
+	0x66, 0x34, 0xb4, 0xdc, 0xfb, 0x9d, 0x8e, 0xee,
+	0x6a, 0x33, 0xa4, 0x07, 0x3c, 0xf9, 0x4c, 0x30,
+	0xa1, 0x24, 0x52, 0xf9, 0x50, 0x46, 0x88, 0x20,
+	0x02, 0x32, 0x3a, 0x0e, 0x99, 0x63, 0xaf, 0x1f,
+	0x15, 0x28, 0x2a, 0x05, 0xff, 0x57, 0x59, 0x5e,
+	0x18, 0xa1, 0x1f, 0xd0, 0x92, 0x5c, 0x88, 0x66,
+	0x1b, 0x00, 0x64, 0xa5, 0x93, 0x8d, 0x06, 0x46,
+	0xb0, 0x64, 0x8b, 0x8b, 0xef, 0x99, 0x05, 0x35,
+	0x85, 0xb3, 0xf3, 0x33, 0xbb, 0xec, 0x66, 0xb6,
+	0x3d, 0x57, 0x42, 0xe3, 0xb4, 0xc6, 0xaa, 0xb0,
+	0x41, 0x2a, 0xb9, 0x59, 0xa9, 0xf6, 0x3e, 0x15,
+	0x26, 0x12, 0x03, 0x21, 0x4c, 0x74, 0x43, 0x13,
+	0x2a, 0x03, 0x27, 0x09, 0xb4, 0xfb, 0xe7, 0xb7,
+	0x40, 0xff, 0x5e, 0xce, 0x48, 0x9a, 0x60, 0xe3,
+	0x8b, 0x80, 0x8c, 0x38, 0x2d, 0xcb, 0x93, 0x37,
+	0x74, 0x05, 0x52, 0x6f, 0x73, 0x3e, 0xc3, 0xbc,
+	0xca, 0x72, 0x0a, 0xeb, 0xf1, 0x3b, 0xa0, 0x95,
+	0xdc, 0x8a, 0xc4, 0xa9, 0xdc, 0xca, 0x44, 0xd8,
+	0x08, 0x63, 0x6a, 0x36, 0xd3, 0x3c, 0xb8, 0xac,
+	0x46, 0x7d, 0xfd, 0xaa, 0xeb, 0x3e, 0x0f, 0x45,
+	0x8f, 0x49, 0xda, 0x2b, 0xf2, 0x12, 0xbd, 0xaf,
+	0x67, 0x8a, 0x63, 0x48, 0x4b, 0x55, 0x5f, 0x6d,
+	0x8c, 0xb9, 0x76, 0x34, 0x84, 0xae, 0xc2, 0xfc,
+	0x52, 0x64, 0x82, 0xf7, 0xb0, 0x06, 0xf0, 0x45,
+	0x73, 0x12, 0x50, 0x30, 0x72, 0xea, 0x78, 0x9a,
+	0xa8, 0xaf, 0xb5, 0xe3, 0xbb, 0x77, 0x52, 0xec,
+	0x59, 0x84, 0xbf, 0x6b, 0x8f, 0xce, 0x86, 0x5e,
+	0x1f, 0x23, 0xe9, 0xfb, 0x08, 0x86, 0xf7, 0x10,
+	0xb9, 0xf2, 0x44, 0x96, 0x44, 0x63, 0xa9, 0xa8,
+	0x78, 0x00, 0x23, 0xd6, 0xc7, 0xe7, 0x6e, 0x66,
+	0x4f, 0xcc, 0xee, 0x15, 0xb3, 0xbd, 0x1d, 0xa0,
+	0xe5, 0x9c, 0x1b, 0x24, 0x2c, 0x4d, 0x3c, 0x62,
+	0x35, 0x9c, 0x88, 0x59, 0x09, 0xdd, 0x82, 0x1b,
+	0xcf, 0x0a, 0x83, 0x6b, 0x3f, 0xae, 0x03, 0xc4,
+	0xb4, 0xdd, 0x7e, 0x5b, 0x28, 0x76, 0x25, 0x96,
+	0xd9, 0xc9, 0x9d, 0x5f, 0x86, 0xfa, 0xf6, 0xd7,
+	0xd2, 0xe6, 0x76, 0x1d, 0x0f, 0xa1, 0xdc, 0x74,
+	0x05, 0x1b, 0x1d, 0xe0, 0xcd, 0x16, 0xb0, 0xa8,
+	0x8a, 0x34, 0x7b, 0x15, 0x11, 0x77, 0xe5, 0x7b,
+	0x7e, 0x20, 0xf7, 0xda, 0x38, 0xda, 0xce, 0x70,
+	0xe9, 0xf5, 0x6c, 0xd9, 0xbe, 0x0c, 0x4c, 0x95,
+	0x4c, 0xc2, 0x9b, 0x34, 0x55, 0x55, 0xe1, 0xf3,
+	0x46, 0x8e, 0x48, 0x74, 0x14, 0x4f, 0x9d, 0xc9,
+	0xf5, 0xe8, 0x1a, 0xf0, 0x11, 0x4a, 0xc1, 0x8d,
+	0xe0, 0x93, 0xa0, 0xbe, 0x09, 0x1c, 0x2b, 0x4e,
+	0x0f, 0xb2, 0x87, 0x8b, 0x84, 0xfe, 0x92, 0x32,
+	0x14, 0xd7, 0x93, 0xdf, 0xe7, 0x44, 0xbc, 0xc5,
+	0xae, 0x53, 0x69, 0xd8, 0xb3, 0x79, 0x37, 0x80,
+	0xe3, 0x17, 0x5c, 0xec, 0x53, 0x00, 0x9a, 0xe3,
+	0x8e, 0xdc, 0x38, 0xb8, 0x66, 0xf0, 0xd3, 0xad,
+	0x1d, 0x02, 0x96, 0x86, 0x3e, 0x9d, 0x3b, 0x5d,
+	0xa5, 0x7f, 0x21, 0x10, 0xf1, 0x1f, 0x13, 0x20,
+	0xf9, 0x57, 0x87, 0x20, 0xf5, 0x5f, 0xf1, 0x17,
+	0x48, 0x0a, 0x51, 0x5a, 0xcd, 0x19, 0x03, 0xa6,
+	0x5a, 0xd1, 0x12, 0x97, 0xe9, 0x48, 0xe2, 0x1d,
+	0x83, 0x75, 0x50, 0xd9, 0x75, 0x7d, 0x6a, 0x82,
+	0xa1, 0xf9, 0x4e, 0x54, 0x87, 0x89, 0xc9, 0x0c,
+	0xb7, 0x5b, 0x6a, 0x91, 0xc1, 0x9c, 0xb2, 0xa9,
+	0xdc, 0x9a, 0xa4, 0x49, 0x0a, 0x6d, 0x0d, 0xbb,
+	0xde, 0x86, 0x44, 0xdd, 0x5d, 0x89, 0x2b, 0x96,
+	0x0f, 0x23, 0x95, 0xad, 0xcc, 0xa2, 0xb3, 0xb9,
+	0x7e, 0x74, 0x38, 0xba, 0x9f, 0x73, 0xae, 0x5f,
+	0xf8, 0x68, 0xa2, 0xe0, 0xa9, 0xce, 0xbd, 0x40,
+	0xd4, 0x4c, 0x6b, 0xd2, 0x56, 0x62, 0xb0, 0xcc,
+	0x63, 0x7e, 0x5b, 0xd3, 0xae, 0xd1, 0x75, 0xce,
+	0xbb, 0xb4, 0x5b, 0xa8, 0xf8, 0xb4, 0xac, 0x71,
+	0x75, 0xaa, 0xc9, 0x9f, 0xbb, 0x6c, 0xad, 0x0f,
+	0x55, 0x5d, 0xe8, 0x85, 0x7d, 0xf9, 0x21, 0x35,
+	0xea, 0x92, 0x85, 0x2b, 0x00, 0xec, 0x84, 0x90,
+	0x0a, 0x63, 0x96, 0xe4, 0x6b, 0xa9, 0x77, 0xb8,
+	0x91, 0xf8, 0x46, 0x15, 0x72, 0x63, 0x70, 0x01,
+	0x40, 0xa3, 0xa5, 0x76, 0x62, 0x2b, 0xbf, 0xf1,
+	0xe5, 0x8d, 0x9f, 0xa3, 0xfa, 0x9b, 0x03, 0xbe,
+	0xfe, 0x65, 0x6f, 0xa2, 0x29, 0x0d, 0x54, 0xb4,
+	0x71, 0xce, 0xa9, 0xd6, 0x3d, 0x88, 0xf9, 0xaf,
+	0x6b, 0xa8, 0x9e, 0xf4, 0x16, 0x96, 0x36, 0xb9,
+	0x00, 0xdc, 0x10, 0xab, 0xb5, 0x08, 0x31, 0x1f,
+	0x00, 0xb1, 0x3c, 0xd9, 0x38, 0x3e, 0xc6, 0x04,
+	0xa7, 0x4e, 0xe8, 0xae, 0xed, 0x98, 0xc2, 0xf7,
+	0xb9, 0x00, 0x5f, 0x8c, 0x60, 0xd1, 0xe5, 0x15,
+	0xf7, 0xae, 0x1e, 0x84, 0x88, 0xd1, 0xf6, 0xbc,
+	0x3a, 0x89, 0x35, 0x22, 0x83, 0x7c, 0xca, 0xf0,
+	0x33, 0x82, 0x4c, 0x79, 0x3c, 0xfd, 0xb1, 0xae,
+	0x52, 0x62, 0x55, 0xd2, 0x41, 0x60, 0xc6, 0xbb,
+	0xfa, 0x0e, 0x59, 0xd6, 0xa8, 0xfe, 0x5d, 0xed,
+	0x47, 0x3d, 0xe0, 0xea, 0x1f, 0x6e, 0x43, 0x51,
+	0xec, 0x10, 0x52, 0x56, 0x77, 0x42, 0x6b, 0x52,
+	0x87, 0xd8, 0xec, 0xe0, 0xaa, 0x76, 0xa5, 0x84,
+	0x2a, 0x22, 0x24, 0xfd, 0x92, 0x40, 0x88, 0xd5,
+	0x85, 0x1c, 0x1f, 0x6b, 0x47, 0xa0, 0xc4, 0xe4,
+	0xef, 0xf4, 0xea, 0xd7, 0x59, 0xac, 0x2a, 0x9e,
+	0x8c, 0xfa, 0x1f, 0x42, 0x08, 0xfe, 0x4f, 0x74,
+	0xa0, 0x26, 0xf5, 0xb3, 0x84, 0xf6, 0x58, 0x5f,
+	0x26, 0x66, 0x3e, 0xd7, 0xe4, 0x22, 0x91, 0x13,
+	0xc8, 0xac, 0x25, 0x96, 0x23, 0xd8, 0x09, 0xea,
+	0x45, 0x75, 0x23, 0xb8, 0x5f, 0xc2, 0x90, 0x8b,
+	0x09, 0xc4, 0xfc, 0x47, 0x6c, 0x6d, 0x0a, 0xef,
+	0x69, 0xa4, 0x38, 0x19, 0xcf, 0x7d, 0xf9, 0x09,
+	0x73, 0x9b, 0x60, 0x5a, 0xf7, 0x37, 0xb5, 0xfe,
+	0x9f, 0xe3, 0x2b, 0x4c, 0x0d, 0x6e, 0x19, 0xf1,
+	0xd6, 0xc0, 0x70, 0xf3, 0x9d, 0x22, 0x3c, 0xf9,
+	0x49, 0xce, 0x30, 0x8e, 0x44, 0xb5, 0x76, 0x15,
+	0x8f, 0x52, 0xfd, 0xa5, 0x04, 0xb8, 0x55, 0x6a,
+	0x36, 0x59, 0x7c, 0xc4, 0x48, 0xb8, 0xd7, 0xab,
+	0x05, 0x66, 0xe9, 0x5e, 0x21, 0x6f, 0x6b, 0x36,
+	0x29, 0xbb, 0xe9, 0xe3, 0xa2, 0x9a, 0xa8, 0xcd,
+	0x55, 0x25, 0x11, 0xba, 0x5a, 0x58, 0xa0, 0xde,
+	0xae, 0x19, 0x2a, 0x48, 0x5a, 0xff, 0x36, 0xcd,
+	0x6d, 0x16, 0x7a, 0x73, 0x38, 0x46, 0xe5, 0x47,
+	0x59, 0xc8, 0xa2, 0xf6, 0xe2, 0x6c, 0x83, 0xc5,
+	0x36, 0x2c, 0x83, 0x7d, 0xb4, 0x01, 0x05, 0x69,
+	0xe7, 0xaf, 0x5c, 0xc4, 0x64, 0x82, 0x12, 0x21,
+	0xef, 0xf7, 0xd1, 0x7d, 0xb8, 0x8d, 0x8c, 0x98,
+	0x7c, 0x5f, 0x7d, 0x92, 0x88, 0xb9, 0x94, 0x07,
+	0x9c, 0xd8, 0xe9, 0x9c, 0x17, 0x38, 0xe3, 0x57,
+	0x6c, 0xe0, 0xdc, 0xa5, 0x92, 0x42, 0xb3, 0xbd,
+	0x50, 0xa2, 0x7e, 0xb5, 0xb1, 0x52, 0x72, 0x03,
+	0x97, 0xd8, 0xaa, 0x9a, 0x1e, 0x75, 0x41, 0x11,
+	0xa3, 0x4f, 0xcc, 0xd4, 0xe3, 0x73, 0xad, 0x96,
+	0xdc, 0x47, 0x41, 0x9f, 0xb0, 0xbe, 0x79, 0x91,
+	0xf5, 0xb6, 0x18, 0xfe, 0xc2, 0x83, 0x18, 0x7d,
+	0x73, 0xd9, 0x4f, 0x83, 0x84, 0x03, 0xb3, 0xf0,
+	0x77, 0x66, 0x3d, 0x83, 0x63, 0x2e, 0x2c, 0xf9,
+	0xdd, 0xa6, 0x1f, 0x89, 0x82, 0xb8, 0x23, 0x42,
+	0xeb, 0xe2, 0xca, 0x70, 0x82, 0x61, 0x41, 0x0a,
+	0x6d, 0x5f, 0x75, 0xc5, 0xe2, 0xc4, 0x91, 0x18,
+	0x44, 0x22, 0xfa, 0x34, 0x10, 0xf5, 0x20, 0xdc,
+	0xb7, 0xdd, 0x2a, 0x20, 0x77, 0xf5, 0xf9, 0xce,
+	0xdb, 0xa0, 0x0a, 0x52, 0x2a, 0x4e, 0xdd, 0xcc,
+	0x97, 0xdf, 0x05, 0xe4, 0x5e, 0xb7, 0xaa, 0xf0,
+	0xe2, 0x80, 0xff, 0xba, 0x1a, 0x0f, 0xac, 0xdf,
+	0x02, 0x32, 0xe6, 0xf7, 0xc7, 0x17, 0x13, 0xb7,
+	0xfc, 0x98, 0x48, 0x8c, 0x0d, 0x82, 0xc9, 0x80,
+	0x7a, 0xe2, 0x0a, 0xc5, 0xb4, 0xde, 0x7c, 0x3c,
+	0x79, 0x81, 0x0e, 0x28, 0x65, 0x79, 0x67, 0x82,
+	0x69, 0x44, 0x66, 0x09, 0xf7, 0x16, 0x1a, 0xf9,
+	0x7d, 0x80, 0xa1, 0x79, 0x14, 0xa9, 0xc8, 0x20,
+	0xfb, 0xa2, 0x46, 0xbe, 0x08, 0x35, 0x17, 0x58,
+	0xc1, 0x1a, 0xda, 0x2a, 0x6b, 0x2e, 0x1e, 0xe6,
+	0x27, 0x55, 0x7b, 0x19, 0xe2, 0xfb, 0x64, 0xfc,
+	0x5e, 0x15, 0x54, 0x3c, 0xe7, 0xc2, 0x11, 0x50,
+	0x30, 0xb8, 0x72, 0x03, 0x0b, 0x1a, 0x9f, 0x86,
+	0x27, 0x11, 0x5c, 0x06, 0x2b, 0xbd, 0x75, 0x1a,
+	0x0a, 0xda, 0x01, 0xfa, 0x5c, 0x4a, 0xc1, 0x80,
+	0x3a, 0x6e, 0x30, 0xc8, 0x2c, 0xeb, 0x56, 0xec,
+	0x89, 0xfa, 0x35, 0x7b, 0xb2, 0xf0, 0x97, 0x08,
+	0x86, 0x53, 0xbe, 0xbd, 0x40, 0x41, 0x38, 0x1c,
+	0xb4, 0x8b, 0x79, 0x2e, 0x18, 0x96, 0x94, 0xde,
+	0xe8, 0xca, 0xe5, 0x9f, 0x92, 0x9f, 0x15, 0x5d,
+	0x56, 0x60, 0x5c, 0x09, 0xf9, 0x16, 0xf4, 0x17,
+	0x0f, 0xf6, 0x4c, 0xda, 0xe6, 0x67, 0x89, 0x9f,
+	0xca, 0x6c, 0xe7, 0x9b, 0x04, 0x62, 0x0e, 0x26,
+	0xa6, 0x52, 0xbd, 0x29, 0xff, 0xc7, 0xa4, 0x96,
+	0xe6, 0x6a, 0x02, 0xa5, 0x2e, 0x7b, 0xfe, 0x97,
+	0x68, 0x3e, 0x2e, 0x5f, 0x3b, 0x0f, 0x36, 0xd6,
+	0x98, 0x19, 0x59, 0x48, 0xd2, 0xc6, 0xe1, 0x55,
+	0x1a, 0x6e, 0xd6, 0xed, 0x2c, 0xba, 0xc3, 0x9e,
+	0x64, 0xc9, 0x95, 0x86, 0x35, 0x5e, 0x3e, 0x88,
+	0x69, 0x99, 0x4b, 0xee, 0xbe, 0x9a, 0x99, 0xb5,
+	0x6e, 0x58, 0xae, 0xdd, 0x22, 0xdb, 0xdd, 0x6b,
+	0xfc, 0xaf, 0x90, 0xa3, 0x3d, 0xa4, 0xc1, 0x15,
+	0x92, 0x18, 0x8d, 0xd2, 0x4b, 0x7b, 0x06, 0xd1,
+	0x37, 0xb5, 0xe2, 0x7c, 0x2c, 0xf0, 0x25, 0xe4,
+	0x94, 0x2a, 0xbd, 0xe3, 0x82, 0x70, 0x78, 0xa3,
+	0x82, 0x10, 0x5a, 0x90, 0xd7, 0xa4, 0xfa, 0xaf,
+	0x1a, 0x88, 0x59, 0xdc, 0x74, 0x12, 0xb4, 0x8e,
+	0xd7, 0x19, 0x46, 0xf4, 0x84, 0x69, 0x9f, 0xbb,
+	0x70, 0xa8, 0x4c, 0x52, 0x81, 0xa9, 0xff, 0x76,
+	0x1c, 0xae, 0xd8, 0x11, 0x3d, 0x7f, 0x7d, 0xc5,
+	0x12, 0x59, 0x28, 0x18, 0xc2, 0xa2, 0xb7, 0x1c,
+	0x88, 0xf8, 0xd6, 0x1b, 0xa6, 0x7d, 0x9e, 0xde,
+	0x29, 0xf8, 0xed, 0xff, 0xeb, 0x92, 0x24, 0x4f,
+	0x05, 0xaa, 0xd9, 0x49, 0xba, 0x87, 0x59, 0x51,
+	0xc9, 0x20, 0x5c, 0x9b, 0x74, 0xcf, 0x03, 0xd9,
+	0x2d, 0x34, 0xc7, 0x5b, 0xa5, 0x40, 0xb2, 0x99,
+	0xf5, 0xcb, 0xb4, 0xf6, 0xb7, 0x72, 0x4a, 0xd6,
+	0xbd, 0xb0, 0xf3, 0x93, 0xe0, 0x1b, 0xa8, 0x04,
+	0x1e, 0x35, 0xd4, 0x80, 0x20, 0xf4, 0x9c, 0x31,
+	0x6b, 0x45, 0xb9, 0x15, 0xb0, 0x5e, 0xdd, 0x0a,
+	0x33, 0x9c, 0x83, 0xcd, 0x58, 0x89, 0x50, 0x56,
+	0xbb, 0x81, 0x00, 0x91, 0x32, 0xf3, 0x1b, 0x3e,
+	0xcf, 0x45, 0xe1, 0xf9, 0xe1, 0x2c, 0x26, 0x78,
+	0x93, 0x9a, 0x60, 0x46, 0xc9, 0xb5, 0x5e, 0x6a,
+	0x28, 0x92, 0x87, 0x3f, 0x63, 0x7b, 0xdb, 0xf7,
+	0xd0, 0x13, 0x9d, 0x32, 0x40, 0x5e, 0xcf, 0xfb,
+	0x79, 0x68, 0x47, 0x4c, 0xfd, 0x01, 0x17, 0xe6,
+	0x97, 0x93, 0x78, 0xbb, 0xa6, 0x27, 0xa3, 0xe8,
+	0x1a, 0xe8, 0x94, 0x55, 0x7d, 0x08, 0xe5, 0xdc,
+	0x66, 0xa3, 0x69, 0xc8, 0xca, 0xc5, 0xa1, 0x84,
+	0x55, 0xde, 0x08, 0x91, 0x16, 0x3a, 0x0c, 0x86,
+	0xab, 0x27, 0x2b, 0x64, 0x34, 0x02, 0x6c, 0x76,
+	0x8b, 0xc6, 0xaf, 0xcc, 0xe1, 0xd6, 0x8c, 0x2a,
+	0x18, 0x3d, 0xa6, 0x1b, 0x37, 0x75, 0x45, 0x73,
+	0xc2, 0x75, 0xd7, 0x53, 0x78, 0x3a, 0xd6, 0xe8,
+	0x29, 0xd2, 0x4a, 0xa8, 0x1e, 0x82, 0xf6, 0xb6,
+	0x81, 0xde, 0x21, 0xed, 0x2b, 0x56, 0xbb, 0xf2,
+	0xd0, 0x57, 0xc1, 0x7c, 0xd2, 0x6a, 0xd2, 0x56,
+	0xf5, 0x13, 0x5f, 0x1c, 0x6a, 0x0b, 0x74, 0xfb,
+	0xe9, 0xfe, 0x9e, 0xea, 0x95, 0xb2, 0x46, 0xab,
+	0x0a, 0xfc, 0xfd, 0xf3, 0xbb, 0x04, 0x2b, 0x76,
+	0x1b, 0xa4, 0x74, 0xb0, 0xc1, 0x78, 0xc3, 0x69,
+	0xe2, 0xb0, 0x01, 0xe1, 0xde, 0x32, 0x4c, 0x8d,
+	0x1a, 0xb3, 0x38, 0x08, 0xd5, 0xfc, 0x1f, 0xdc,
+	0x0e, 0x2c, 0x9c, 0xb1, 0xa1, 0x63, 0x17, 0x22,
+	0xf5, 0x6c, 0x93, 0x70, 0x74, 0x00, 0xf8, 0x39,
+	0x01, 0x94, 0xd1, 0x32, 0x23, 0x56, 0x5d, 0xa6,
+	0x02, 0x76, 0x76, 0x93, 0xce, 0x2f, 0x19, 0xe9,
+	0x17, 0x52, 0xae, 0x6e, 0x2c, 0x6d, 0x61, 0x7f,
+	0x3b, 0xaa, 0xe0, 0x52, 0x85, 0xc5, 0x65, 0xc1,
+	0xbb, 0x8e, 0x5b, 0x21, 0xd5, 0xc9, 0x78, 0x83,
+	0x07, 0x97, 0x4c, 0x62, 0x61, 0x41, 0xd4, 0xfc,
+	0xc9, 0x39, 0xe3, 0x9b, 0xd0, 0xcc, 0x75, 0xc4,
+	0x97, 0xe6, 0xdd, 0x2a, 0x5f, 0xa6, 0xe8, 0x59,
+	0x6c, 0x98, 0xb9, 0x02, 0xe2, 0xa2, 0xd6, 0x68,
+	0xee, 0x3b, 0x1d, 0xe3, 0x4d, 0x5b, 0x30, 0xef,
+	0x03, 0xf2, 0xeb, 0x18, 0x57, 0x36, 0xe8, 0xa1,
+	0xf4, 0x47, 0xfb, 0xcb, 0x8f, 0xcb, 0xc8, 0xf3,
+	0x4f, 0x74, 0x9d, 0x9d, 0xb1, 0x8d, 0x14, 0x44,
+	0xd9, 0x19, 0xb4, 0x54, 0x4f, 0x75, 0x19, 0x09,
+	0xa0, 0x75, 0xbc, 0x3b, 0x82, 0xc6, 0x3f, 0xb8,
+	0x83, 0x19, 0x6e, 0xd6, 0x37, 0xfe, 0x6e, 0x8a,
+	0x4e, 0xe0, 0x4a, 0xab, 0x7b, 0xc8, 0xb4, 0x1d,
+	0xf4, 0xed, 0x27, 0x03, 0x65, 0xa2, 0xa1, 0xae,
+	0x11, 0xe7, 0x98, 0x78, 0x48, 0x91, 0xd2, 0xd2,
+	0xd4, 0x23, 0x78, 0x50, 0xb1, 0x5b, 0x85, 0x10,
+	0x8d, 0xca, 0x5f, 0x0f, 0x71, 0xae, 0x72, 0x9a,
+	0xf6, 0x25, 0x19, 0x60, 0x06, 0xf7, 0x10, 0x34,
+	0x18, 0x0d, 0xc9, 0x9f, 0x7b, 0x0c, 0x9b, 0x8f,
+	0x91, 0x1b, 0x9f, 0xcd, 0x10, 0xee, 0x75, 0xf9,
+	0x97, 0x66, 0xfc, 0x4d, 0x33, 0x6e, 0x28, 0x2b,
+	0x92, 0x85, 0x4f, 0xab, 0x43, 0x8d, 0x8f, 0x7d,
+	0x86, 0xa7, 0xc7, 0xd8, 0xd3, 0x0b, 0x8b, 0x57,
+	0xb6, 0x1d, 0x95, 0x0d, 0xe9, 0xbc, 0xd9, 0x03,
+	0xd9, 0x10, 0x19, 0xc3, 0x46, 0x63, 0x55, 0x87,
+	0x61, 0x79, 0x6c, 0x95, 0x0e, 0x9c, 0xdd, 0xca,
+	0xc3, 0xf3, 0x64, 0xf0, 0x7d, 0x76, 0xb7, 0x53,
+	0x67, 0x2b, 0x1e, 0x44, 0x56, 0x81, 0xea, 0x8f,
+	0x5c, 0x42, 0x16, 0xb8, 0x28, 0xeb, 0x1b, 0x61,
+	0x10, 0x1e, 0xbf, 0xec, 0xa8
+};
+static const u8 dec_assoc011[] __initconst = {
+	0xd6, 0x31, 0xda, 0x5d, 0x42, 0x5e, 0xd7
+};
+static const u8 dec_nonce011[] __initconst = {
+	0xfd, 0x87, 0xd4, 0xd8, 0x62, 0xfd, 0xec, 0xaa
+};
+static const u8 dec_key011[] __initconst = {
+	0x35, 0x4e, 0xb5, 0x70, 0x50, 0x42, 0x8a, 0x85,
+	0xf2, 0xfb, 0xed, 0x7b, 0xd0, 0x9e, 0x97, 0xca,
+	0xfa, 0x98, 0x66, 0x63, 0xee, 0x37, 0xcc, 0x52,
+	0xfe, 0xd1, 0xdf, 0x95, 0x15, 0x34, 0x29, 0x38
+};
+
+static const u8 dec_input012[] __initconst = {
+	0x52, 0x34, 0xb3, 0x65, 0x3b, 0xb7, 0xe5, 0xd3,
+	0xab, 0x49, 0x17, 0x60, 0xd2, 0x52, 0x56, 0xdf,
+	0xdf, 0x34, 0x56, 0x82, 0xe2, 0xbe, 0xe5, 0xe1,
+	0x28, 0xd1, 0x4e, 0x5f, 0x4f, 0x01, 0x7d, 0x3f,
+	0x99, 0x6b, 0x30, 0x6e, 0x1a, 0x7c, 0x4c, 0x8e,
+	0x62, 0x81, 0xae, 0x86, 0x3f, 0x6b, 0xd0, 0xb5,
+	0xa9, 0xcf, 0x50, 0xf1, 0x02, 0x12, 0xa0, 0x0b,
+	0x24, 0xe9, 0xe6, 0x72, 0x89, 0x2c, 0x52, 0x1b,
+	0x34, 0x38, 0xf8, 0x75, 0x5f, 0xa0, 0x74, 0xe2,
+	0x99, 0xdd, 0xa6, 0x4b, 0x14, 0x50, 0x4e, 0xf1,
+	0xbe, 0xd6, 0x9e, 0xdb, 0xb2, 0x24, 0x27, 0x74,
+	0x12, 0x4a, 0x78, 0x78, 0x17, 0xa5, 0x58, 0x8e,
+	0x2f, 0xf9, 0xf4, 0x8d, 0xee, 0x03, 0x88, 0xae,
+	0xb8, 0x29, 0xa1, 0x2f, 0x4b, 0xee, 0x92, 0xbd,
+	0x87, 0xb3, 0xce, 0x34, 0x21, 0x57, 0x46, 0x04,
+	0x49, 0x0c, 0x80, 0xf2, 0x01, 0x13, 0xa1, 0x55,
+	0xb3, 0xff, 0x44, 0x30, 0x3c, 0x1c, 0xd0, 0xef,
+	0xbc, 0x18, 0x74, 0x26, 0xad, 0x41, 0x5b, 0x5b,
+	0x3e, 0x9a, 0x7a, 0x46, 0x4f, 0x16, 0xd6, 0x74,
+	0x5a, 0xb7, 0x3a, 0x28, 0x31, 0xd8, 0xae, 0x26,
+	0xac, 0x50, 0x53, 0x86, 0xf2, 0x56, 0xd7, 0x3f,
+	0x29, 0xbc, 0x45, 0x68, 0x8e, 0xcb, 0x98, 0x64,
+	0xdd, 0xc9, 0xba, 0xb8, 0x4b, 0x7b, 0x82, 0xdd,
+	0x14, 0xa7, 0xcb, 0x71, 0x72, 0x00, 0x5c, 0xad,
+	0x7b, 0x6a, 0x89, 0xa4, 0x3d, 0xbf, 0xb5, 0x4b,
+	0x3e, 0x7c, 0x5a, 0xcf, 0xb8, 0xa1, 0xc5, 0x6e,
+	0xc8, 0xb6, 0x31, 0x57, 0x7b, 0xdf, 0xa5, 0x7e,
+	0xb1, 0xd6, 0x42, 0x2a, 0x31, 0x36, 0xd1, 0xd0,
+	0x3f, 0x7a, 0xe5, 0x94, 0xd6, 0x36, 0xa0, 0x6f,
+	0xb7, 0x40, 0x7d, 0x37, 0xc6, 0x55, 0x7c, 0x50,
+	0x40, 0x6d, 0x29, 0x89, 0xe3, 0x5a, 0xae, 0x97,
+	0xe7, 0x44, 0x49, 0x6e, 0xbd, 0x81, 0x3d, 0x03,
+	0x93, 0x06, 0x12, 0x06, 0xe2, 0x41, 0x12, 0x4a,
+	0xf1, 0x6a, 0xa4, 0x58, 0xa2, 0xfb, 0xd2, 0x15,
+	0xba, 0xc9, 0x79, 0xc9, 0xce, 0x5e, 0x13, 0xbb,
+	0xf1, 0x09, 0x04, 0xcc, 0xfd, 0xe8, 0x51, 0x34,
+	0x6a, 0xe8, 0x61, 0x88, 0xda, 0xed, 0x01, 0x47,
+	0x84, 0xf5, 0x73, 0x25, 0xf9, 0x1c, 0x42, 0x86,
+	0x07, 0xf3, 0x5b, 0x1a, 0x01, 0xb3, 0xeb, 0x24,
+	0x32, 0x8d, 0xf6, 0xed, 0x7c, 0x4b, 0xeb, 0x3c,
+	0x36, 0x42, 0x28, 0xdf, 0xdf, 0xb6, 0xbe, 0xd9,
+	0x8c, 0x52, 0xd3, 0x2b, 0x08, 0x90, 0x8c, 0xe7,
+	0x98, 0x31, 0xe2, 0x32, 0x8e, 0xfc, 0x11, 0x48,
+	0x00, 0xa8, 0x6a, 0x42, 0x4a, 0x02, 0xc6, 0x4b,
+	0x09, 0xf1, 0xe3, 0x49, 0xf3, 0x45, 0x1f, 0x0e,
+	0xbc, 0x56, 0xe2, 0xe4, 0xdf, 0xfb, 0xeb, 0x61,
+	0xfa, 0x24, 0xc1, 0x63, 0x75, 0xbb, 0x47, 0x75,
+	0xaf, 0xe1, 0x53, 0x16, 0x96, 0x21, 0x85, 0x26,
+	0x11, 0xb3, 0x76, 0xe3, 0x23, 0xa1, 0x6b, 0x74,
+	0x37, 0xd0, 0xde, 0x06, 0x90, 0x71, 0x5d, 0x43,
+	0x88, 0x9b, 0x00, 0x54, 0xa6, 0x75, 0x2f, 0xa1,
+	0xc2, 0x0b, 0x73, 0x20, 0x1d, 0xb6, 0x21, 0x79,
+	0x57, 0x3f, 0xfa, 0x09, 0xbe, 0x8a, 0x33, 0xc3,
+	0x52, 0xf0, 0x1d, 0x82, 0x31, 0xd1, 0x55, 0xb5,
+	0x6c, 0x99, 0x25, 0xcf, 0x5c, 0x32, 0xce, 0xe9,
+	0x0d, 0xfa, 0x69, 0x2c, 0xd5, 0x0d, 0xc5, 0x6d,
+	0x86, 0xd0, 0x0c, 0x3b, 0x06, 0x50, 0x79, 0xe8,
+	0xc3, 0xae, 0x04, 0xe6, 0xcd, 0x51, 0xe4, 0x26,
+	0x9b, 0x4f, 0x7e, 0xa6, 0x0f, 0xab, 0xd8, 0xe5,
+	0xde, 0xa9, 0x00, 0x95, 0xbe, 0xa3, 0x9d, 0x5d,
+	0xb2, 0x09, 0x70, 0x18, 0x1c, 0xf0, 0xac, 0x29,
+	0x23, 0x02, 0x29, 0x28, 0xd2, 0x74, 0x35, 0x57,
+	0x62, 0x0f, 0x24, 0xea, 0x5e, 0x33, 0xc2, 0x92,
+	0xf3, 0x78, 0x4d, 0x30, 0x1e, 0xa1, 0x99, 0xa9,
+	0x82, 0xb0, 0x42, 0x31, 0x8d, 0xad, 0x8a, 0xbc,
+	0xfc, 0xd4, 0x57, 0x47, 0x3e, 0xb4, 0x50, 0xdd,
+	0x6e, 0x2c, 0x80, 0x4d, 0x22, 0xf1, 0xfb, 0x57,
+	0xc4, 0xdd, 0x17, 0xe1, 0x8a, 0x36, 0x4a, 0xb3,
+	0x37, 0xca, 0xc9, 0x4e, 0xab, 0xd5, 0x69, 0xc4,
+	0xf4, 0xbc, 0x0b, 0x3b, 0x44, 0x4b, 0x29, 0x9c,
+	0xee, 0xd4, 0x35, 0x22, 0x21, 0xb0, 0x1f, 0x27,
+	0x64, 0xa8, 0x51, 0x1b, 0xf0, 0x9f, 0x19, 0x5c,
+	0xfb, 0x5a, 0x64, 0x74, 0x70, 0x45, 0x09, 0xf5,
+	0x64, 0xfe, 0x1a, 0x2d, 0xc9, 0x14, 0x04, 0x14,
+	0xcf, 0xd5, 0x7d, 0x60, 0xaf, 0x94, 0x39, 0x94,
+	0xe2, 0x7d, 0x79, 0x82, 0xd0, 0x65, 0x3b, 0x6b,
+	0x9c, 0x19, 0x84, 0xb4, 0x6d, 0xb3, 0x0c, 0x99,
+	0xc0, 0x56, 0xa8, 0xbd, 0x73, 0xce, 0x05, 0x84,
+	0x3e, 0x30, 0xaa, 0xc4, 0x9b, 0x1b, 0x04, 0x2a,
+	0x9f, 0xd7, 0x43, 0x2b, 0x23, 0xdf, 0xbf, 0xaa,
+	0xd5, 0xc2, 0x43, 0x2d, 0x70, 0xab, 0xdc, 0x75,
+	0xad, 0xac, 0xf7, 0xc0, 0xbe, 0x67, 0xb2, 0x74,
+	0xed, 0x67, 0x10, 0x4a, 0x92, 0x60, 0xc1, 0x40,
+	0x50, 0x19, 0x8a, 0x8a, 0x8c, 0x09, 0x0e, 0x72,
+	0xe1, 0x73, 0x5e, 0xe8, 0x41, 0x85, 0x63, 0x9f,
+	0x3f, 0xd7, 0x7d, 0xc4, 0xfb, 0x22, 0x5d, 0x92,
+	0x6c, 0xb3, 0x1e, 0xe2, 0x50, 0x2f, 0x82, 0xa8,
+	0x28, 0xc0, 0xb5, 0xd7, 0x5f, 0x68, 0x0d, 0x2c,
+	0x2d, 0xaf, 0x7e, 0xfa, 0x2e, 0x08, 0x0f, 0x1f,
+	0x70, 0x9f, 0xe9, 0x19, 0x72, 0x55, 0xf8, 0xfb,
+	0x51, 0xd2, 0x33, 0x5d, 0xa0, 0xd3, 0x2b, 0x0a,
+	0x6c, 0xbc, 0x4e, 0xcf, 0x36, 0x4d, 0xdc, 0x3b,
+	0xe9, 0x3e, 0x81, 0x7c, 0x61, 0xdb, 0x20, 0x2d,
+	0x3a, 0xc3, 0xb3, 0x0c, 0x1e, 0x00, 0xb9, 0x7c,
+	0xf5, 0xca, 0x10, 0x5f, 0x3a, 0x71, 0xb3, 0xe4,
+	0x20, 0xdb, 0x0c, 0x2a, 0x98, 0x63, 0x45, 0x00,
+	0x58, 0xf6, 0x68, 0xe4, 0x0b, 0xda, 0x13, 0x3b,
+	0x60, 0x5c, 0x76, 0xdb, 0xb9, 0x97, 0x71, 0xe4,
+	0xd9, 0xb7, 0xdb, 0xbd, 0x68, 0xc7, 0x84, 0x84,
+	0xaa, 0x7c, 0x68, 0x62, 0x5e, 0x16, 0xfc, 0xba,
+	0x72, 0xaa, 0x9a, 0xa9, 0xeb, 0x7c, 0x75, 0x47,
+	0x97, 0x7e, 0xad, 0xe2, 0xd9, 0x91, 0xe8, 0xe4,
+	0xa5, 0x31, 0xd7, 0x01, 0x8e, 0xa2, 0x11, 0x88,
+	0x95, 0xb9, 0xf2, 0x9b, 0xd3, 0x7f, 0x1b, 0x81,
+	0x22, 0xf7, 0x98, 0x60, 0x0a, 0x64, 0xa6, 0xc1,
+	0xf6, 0x49, 0xc7, 0xe3, 0x07, 0x4d, 0x94, 0x7a,
+	0xcf, 0x6e, 0x68, 0x0c, 0x1b, 0x3f, 0x6e, 0x2e,
+	0xee, 0x92, 0xfa, 0x52, 0xb3, 0x59, 0xf8, 0xf1,
+	0x8f, 0x6a, 0x66, 0xa3, 0x82, 0x76, 0x4a, 0x07,
+	0x1a, 0xc7, 0xdd, 0xf5, 0xda, 0x9c, 0x3c, 0x24,
+	0xbf, 0xfd, 0x42, 0xa1, 0x10, 0x64, 0x6a, 0x0f,
+	0x89, 0xee, 0x36, 0xa5, 0xce, 0x99, 0x48, 0x6a,
+	0xf0, 0x9f, 0x9e, 0x69, 0xa4, 0x40, 0x20, 0xe9,
+	0x16, 0x15, 0xf7, 0xdb, 0x75, 0x02, 0xcb, 0xe9,
+	0x73, 0x8b, 0x3b, 0x49, 0x2f, 0xf0, 0xaf, 0x51,
+	0x06, 0x5c, 0xdf, 0x27, 0x27, 0x49, 0x6a, 0xd1,
+	0xcc, 0xc7, 0xb5, 0x63, 0xb5, 0xfc, 0xb8, 0x5c,
+	0x87, 0x7f, 0x84, 0xb4, 0xcc, 0x14, 0xa9, 0x53,
+	0xda, 0xa4, 0x56, 0xf8, 0xb6, 0x1b, 0xcc, 0x40,
+	0x27, 0x52, 0x06, 0x5a, 0x13, 0x81, 0xd7, 0x3a,
+	0xd4, 0x3b, 0xfb, 0x49, 0x65, 0x31, 0x33, 0xb2,
+	0xfa, 0xcd, 0xad, 0x58, 0x4e, 0x2b, 0xae, 0xd2,
+	0x20, 0xfb, 0x1a, 0x48, 0xb4, 0x3f, 0x9a, 0xd8,
+	0x7a, 0x35, 0x4a, 0xc8, 0xee, 0x88, 0x5e, 0x07,
+	0x66, 0x54, 0xb9, 0xec, 0x9f, 0xa3, 0xe3, 0xb9,
+	0x37, 0xaa, 0x49, 0x76, 0x31, 0xda, 0x74, 0x2d,
+	0x3c, 0xa4, 0x65, 0x10, 0x32, 0x38, 0xf0, 0xde,
+	0xd3, 0x99, 0x17, 0xaa, 0x71, 0xaa, 0x8f, 0x0f,
+	0x8c, 0xaf, 0xa2, 0xf8, 0x5d, 0x64, 0xba, 0x1d,
+	0xa3, 0xef, 0x96, 0x73, 0xe8, 0xa1, 0x02, 0x8d,
+	0x0c, 0x6d, 0xb8, 0x06, 0x90, 0xb8, 0x08, 0x56,
+	0x2c, 0xa7, 0x06, 0xc9, 0xc2, 0x38, 0xdb, 0x7c,
+	0x63, 0xb1, 0x57, 0x8e, 0xea, 0x7c, 0x79, 0xf3,
+	0x49, 0x1d, 0xfe, 0x9f, 0xf3, 0x6e, 0xb1, 0x1d,
+	0xba, 0x19, 0x80, 0x1a, 0x0a, 0xd3, 0xb0, 0x26,
+	0x21, 0x40, 0xb1, 0x7c, 0xf9, 0x4d, 0x8d, 0x10,
+	0xc1, 0x7e, 0xf4, 0xf6, 0x3c, 0xa8, 0xfd, 0x7c,
+	0xa3, 0x92, 0xb2, 0x0f, 0xaa, 0xcc, 0xa6, 0x11,
+	0xfe, 0x04, 0xe3, 0xd1, 0x7a, 0x32, 0x89, 0xdf,
+	0x0d, 0xc4, 0x8f, 0x79, 0x6b, 0xca, 0x16, 0x7c,
+	0x6e, 0xf9, 0xad, 0x0f, 0xf6, 0xfe, 0x27, 0xdb,
+	0xc4, 0x13, 0x70, 0xf1, 0x62, 0x1a, 0x4f, 0x79,
+	0x40, 0xc9, 0x9b, 0x8b, 0x21, 0xea, 0x84, 0xfa,
+	0xf5, 0xf1, 0x89, 0xce, 0xb7, 0x55, 0x0a, 0x80,
+	0x39, 0x2f, 0x55, 0x36, 0x16, 0x9c, 0x7b, 0x08,
+	0xbd, 0x87, 0x0d, 0xa5, 0x32, 0xf1, 0x52, 0x7c,
+	0xe8, 0x55, 0x60, 0x5b, 0xd7, 0x69, 0xe4, 0xfc,
+	0xfa, 0x12, 0x85, 0x96, 0xea, 0x50, 0x28, 0xab,
+	0x8a, 0xf7, 0xbb, 0x0e, 0x53, 0x74, 0xca, 0xa6,
+	0x27, 0x09, 0xc2, 0xb5, 0xde, 0x18, 0x14, 0xd9,
+	0xea, 0xe5, 0x29, 0x1c, 0x40, 0x56, 0xcf, 0xd7,
+	0xae, 0x05, 0x3f, 0x65, 0xaf, 0x05, 0x73, 0xe2,
+	0x35, 0x96, 0x27, 0x07, 0x14, 0xc0, 0xad, 0x33,
+	0xf1, 0xdc, 0x44, 0x7a, 0x89, 0x17, 0x77, 0xd2,
+	0x9c, 0x58, 0x60, 0xf0, 0x3f, 0x7b, 0x2d, 0x2e,
+	0x57, 0x95, 0x54, 0x87, 0xed, 0xf2, 0xc7, 0x4c,
+	0xf0, 0xae, 0x56, 0x29, 0x19, 0x7d, 0x66, 0x4b,
+	0x9b, 0x83, 0x84, 0x42, 0x3b, 0x01, 0x25, 0x66,
+	0x8e, 0x02, 0xde, 0xb9, 0x83, 0x54, 0x19, 0xf6,
+	0x9f, 0x79, 0x0d, 0x67, 0xc5, 0x1d, 0x7a, 0x44,
+	0x02, 0x98, 0xa7, 0x16, 0x1c, 0x29, 0x0d, 0x74,
+	0xff, 0x85, 0x40, 0x06, 0xef, 0x2c, 0xa9, 0xc6,
+	0xf5, 0x53, 0x07, 0x06, 0xae, 0xe4, 0xfa, 0x5f,
+	0xd8, 0x39, 0x4d, 0xf1, 0x9b, 0x6b, 0xd9, 0x24,
+	0x84, 0xfe, 0x03, 0x4c, 0xb2, 0x3f, 0xdf, 0xa1,
+	0x05, 0x9e, 0x50, 0x14, 0x5a, 0xd9, 0x1a, 0xa2,
+	0xa7, 0xfa, 0xfa, 0x17, 0xf7, 0x78, 0xd6, 0xb5,
+	0x92, 0x61, 0x91, 0xac, 0x36, 0xfa, 0x56, 0x0d,
+	0x38, 0x32, 0x18, 0x85, 0x08, 0x58, 0x37, 0xf0,
+	0x4b, 0xdb, 0x59, 0xe7, 0xa4, 0x34, 0xc0, 0x1b,
+	0x01, 0xaf, 0x2d, 0xde, 0xa1, 0xaa, 0x5d, 0xd3,
+	0xec, 0xe1, 0xd4, 0xf7, 0xe6, 0x54, 0x68, 0xf0,
+	0x51, 0x97, 0xa7, 0x89, 0xea, 0x24, 0xad, 0xd3,
+	0x6e, 0x47, 0x93, 0x8b, 0x4b, 0xb4, 0xf7, 0x1c,
+	0x42, 0x06, 0x67, 0xe8, 0x99, 0xf6, 0xf5, 0x7b,
+	0x85, 0xb5, 0x65, 0xb5, 0xb5, 0xd2, 0x37, 0xf5,
+	0xf3, 0x02, 0xa6, 0x4d, 0x11, 0xa7, 0xdc, 0x51,
+	0x09, 0x7f, 0xa0, 0xd8, 0x88, 0x1c, 0x13, 0x71,
+	0xae, 0x9c, 0xb7, 0x7b, 0x34, 0xd6, 0x4e, 0x68,
+	0x26, 0x83, 0x51, 0xaf, 0x1d, 0xee, 0x8b, 0xbb,
+	0x69, 0x43, 0x2b, 0x9e, 0x8a, 0xbc, 0x02, 0x0e,
+	0xa0, 0x1b, 0xe0, 0xa8, 0x5f, 0x6f, 0xaf, 0x1b,
+	0x8f, 0xe7, 0x64, 0x71, 0x74, 0x11, 0x7e, 0xa8,
+	0xd8, 0xf9, 0x97, 0x06, 0xc3, 0xb6, 0xfb, 0xfb,
+	0xb7, 0x3d, 0x35, 0x9d, 0x3b, 0x52, 0xed, 0x54,
+	0xca, 0xf4, 0x81, 0x01, 0x2d, 0x1b, 0xc3, 0xa7,
+	0x00, 0x3d, 0x1a, 0x39, 0x54, 0xe1, 0xf6, 0xff,
+	0xed, 0x6f, 0x0b, 0x5a, 0x68, 0xda, 0x58, 0xdd,
+	0xa9, 0xcf, 0x5c, 0x4a, 0xe5, 0x09, 0x4e, 0xde,
+	0x9d, 0xbc, 0x3e, 0xee, 0x5a, 0x00, 0x3b, 0x2c,
+	0x87, 0x10, 0x65, 0x60, 0xdd, 0xd7, 0x56, 0xd1,
+	0x4c, 0x64, 0x45, 0xe4, 0x21, 0xec, 0x78, 0xf8,
+	0x25, 0x7a, 0x3e, 0x16, 0x5d, 0x09, 0x53, 0x14,
+	0xbe, 0x4f, 0xae, 0x87, 0xd8, 0xd1, 0xaa, 0x3c,
+	0xf6, 0x3e, 0xa4, 0x70, 0x8c, 0x5e, 0x70, 0xa4,
+	0xb3, 0x6b, 0x66, 0x73, 0xd3, 0xbf, 0x31, 0x06,
+	0x19, 0x62, 0x93, 0x15, 0xf2, 0x86, 0xe4, 0x52,
+	0x7e, 0x53, 0x4c, 0x12, 0x38, 0xcc, 0x34, 0x7d,
+	0x57, 0xf6, 0x42, 0x93, 0x8a, 0xc4, 0xee, 0x5c,
+	0x8a, 0xe1, 0x52, 0x8f, 0x56, 0x64, 0xf6, 0xa6,
+	0xd1, 0x91, 0x57, 0x70, 0xcd, 0x11, 0x76, 0xf5,
+	0x59, 0x60, 0x60, 0x3c, 0xc1, 0xc3, 0x0b, 0x7f,
+	0x58, 0x1a, 0x50, 0x91, 0xf1, 0x68, 0x8f, 0x6e,
+	0x74, 0x74, 0xa8, 0x51, 0x0b, 0xf7, 0x7a, 0x98,
+	0x37, 0xf2, 0x0a, 0x0e, 0xa4, 0x97, 0x04, 0xb8,
+	0x9b, 0xfd, 0xa0, 0xea, 0xf7, 0x0d, 0xe1, 0xdb,
+	0x03, 0xf0, 0x31, 0x29, 0xf8, 0xdd, 0x6b, 0x8b,
+	0x5d, 0xd8, 0x59, 0xa9, 0x29, 0xcf, 0x9a, 0x79,
+	0x89, 0x19, 0x63, 0x46, 0x09, 0x79, 0x6a, 0x11,
+	0xda, 0x63, 0x68, 0x48, 0x77, 0x23, 0xfb, 0x7d,
+	0x3a, 0x43, 0xcb, 0x02, 0x3b, 0x7a, 0x6d, 0x10,
+	0x2a, 0x9e, 0xac, 0xf1, 0xd4, 0x19, 0xf8, 0x23,
+	0x64, 0x1d, 0x2c, 0x5f, 0xf2, 0xb0, 0x5c, 0x23,
+	0x27, 0xf7, 0x27, 0x30, 0x16, 0x37, 0xb1, 0x90,
+	0xab, 0x38, 0xfb, 0x55, 0xcd, 0x78, 0x58, 0xd4,
+	0x7d, 0x43, 0xf6, 0x45, 0x5e, 0x55, 0x8d, 0xb1,
+	0x02, 0x65, 0x58, 0xb4, 0x13, 0x4b, 0x36, 0xf7,
+	0xcc, 0xfe, 0x3d, 0x0b, 0x82, 0xe2, 0x12, 0x11,
+	0xbb, 0xe6, 0xb8, 0x3a, 0x48, 0x71, 0xc7, 0x50,
+	0x06, 0x16, 0x3a, 0xe6, 0x7c, 0x05, 0xc7, 0xc8,
+	0x4d, 0x2f, 0x08, 0x6a, 0x17, 0x9a, 0x95, 0x97,
+	0x50, 0x68, 0xdc, 0x28, 0x18, 0xc4, 0x61, 0x38,
+	0xb9, 0xe0, 0x3e, 0x78, 0xdb, 0x29, 0xe0, 0x9f,
+	0x52, 0xdd, 0xf8, 0x4f, 0x91, 0xc1, 0xd0, 0x33,
+	0xa1, 0x7a, 0x8e, 0x30, 0x13, 0x82, 0x07, 0x9f,
+	0xd3, 0x31, 0x0f, 0x23, 0xbe, 0x32, 0x5a, 0x75,
+	0xcf, 0x96, 0xb2, 0xec, 0xb5, 0x32, 0xac, 0x21,
+	0xd1, 0x82, 0x33, 0xd3, 0x15, 0x74, 0xbd, 0x90,
+	0xf1, 0x2c, 0xe6, 0x5f, 0x8d, 0xe3, 0x02, 0xe8,
+	0xe9, 0xc4, 0xca, 0x96, 0xeb, 0x0e, 0xbc, 0x91,
+	0xf4, 0xb9, 0xea, 0xd9, 0x1b, 0x75, 0xbd, 0xe1,
+	0xac, 0x2a, 0x05, 0x37, 0x52, 0x9b, 0x1b, 0x3f,
+	0x5a, 0xdc, 0x21, 0xc3, 0x98, 0xbb, 0xaf, 0xa3,
+	0xf2, 0x00, 0xbf, 0x0d, 0x30, 0x89, 0x05, 0xcc,
+	0xa5, 0x76, 0xf5, 0x06, 0xf0, 0xc6, 0x54, 0x8a,
+	0x5d, 0xd4, 0x1e, 0xc1, 0xf2, 0xce, 0xb0, 0x62,
+	0xc8, 0xfc, 0x59, 0x42, 0x9a, 0x90, 0x60, 0x55,
+	0xfe, 0x88, 0xa5, 0x8b, 0xb8, 0x33, 0x0c, 0x23,
+	0x24, 0x0d, 0x15, 0x70, 0x37, 0x1e, 0x3d, 0xf6,
+	0xd2, 0xea, 0x92, 0x10, 0xb2, 0xc4, 0x51, 0xac,
+	0xf2, 0xac, 0xf3, 0x6b, 0x6c, 0xaa, 0xcf, 0x12,
+	0xc5, 0x6c, 0x90, 0x50, 0xb5, 0x0c, 0xfc, 0x1a,
+	0x15, 0x52, 0xe9, 0x26, 0xc6, 0x52, 0xa4, 0xe7,
+	0x81, 0x69, 0xe1, 0xe7, 0x9e, 0x30, 0x01, 0xec,
+	0x84, 0x89, 0xb2, 0x0d, 0x66, 0xdd, 0xce, 0x28,
+	0x5c, 0xec, 0x98, 0x46, 0x68, 0x21, 0x9f, 0x88,
+	0x3f, 0x1f, 0x42, 0x77, 0xce, 0xd0, 0x61, 0xd4,
+	0x20, 0xa7, 0xff, 0x53, 0xad, 0x37, 0xd0, 0x17,
+	0x35, 0xc9, 0xfc, 0xba, 0x0a, 0x78, 0x3f, 0xf2,
+	0xcc, 0x86, 0x89, 0xe8, 0x4b, 0x3c, 0x48, 0x33,
+	0x09, 0x7f, 0xc6, 0xc0, 0xdd, 0xb8, 0xfd, 0x7a,
+	0x66, 0x66, 0x65, 0xeb, 0x47, 0xa7, 0x04, 0x28,
+	0xa3, 0x19, 0x8e, 0xa9, 0xb1, 0x13, 0x67, 0x62,
+	0x70, 0xcf, 0xd6
+};
+static const u8 dec_output012[] __initconst = {
+	0x74, 0xa6, 0x3e, 0xe4, 0xb1, 0xcb, 0xaf, 0xb0,
+	0x40, 0xe5, 0x0f, 0x9e, 0xf1, 0xf2, 0x89, 0xb5,
+	0x42, 0x34, 0x8a, 0xa1, 0x03, 0xb7, 0xe9, 0x57,
+	0x46, 0xbe, 0x20, 0xe4, 0x6e, 0xb0, 0xeb, 0xff,
+	0xea, 0x07, 0x7e, 0xef, 0xe2, 0x55, 0x9f, 0xe5,
+	0x78, 0x3a, 0xb7, 0x83, 0xc2, 0x18, 0x40, 0x7b,
+	0xeb, 0xcd, 0x81, 0xfb, 0x90, 0x12, 0x9e, 0x46,
+	0xa9, 0xd6, 0x4a, 0xba, 0xb0, 0x62, 0xdb, 0x6b,
+	0x99, 0xc4, 0xdb, 0x54, 0x4b, 0xb8, 0xa5, 0x71,
+	0xcb, 0xcd, 0x63, 0x32, 0x55, 0xfb, 0x31, 0xf0,
+	0x38, 0xf5, 0xbe, 0x78, 0xe4, 0x45, 0xce, 0x1b,
+	0x6a, 0x5b, 0x0e, 0xf4, 0x16, 0xe4, 0xb1, 0x3d,
+	0xf6, 0x63, 0x7b, 0xa7, 0x0c, 0xde, 0x6f, 0x8f,
+	0x74, 0xdf, 0xe0, 0x1e, 0x9d, 0xce, 0x8f, 0x24,
+	0xef, 0x23, 0x35, 0x33, 0x7b, 0x83, 0x34, 0x23,
+	0x58, 0x74, 0x14, 0x77, 0x1f, 0xc2, 0x4f, 0x4e,
+	0xc6, 0x89, 0xf9, 0x52, 0x09, 0x37, 0x64, 0x14,
+	0xc4, 0x01, 0x6b, 0x9d, 0x77, 0xe8, 0x90, 0x5d,
+	0xa8, 0x4a, 0x2a, 0xef, 0x5c, 0x7f, 0xeb, 0xbb,
+	0xb2, 0xc6, 0x93, 0x99, 0x66, 0xdc, 0x7f, 0xd4,
+	0x9e, 0x2a, 0xca, 0x8d, 0xdb, 0xe7, 0x20, 0xcf,
+	0xe4, 0x73, 0xae, 0x49, 0x7d, 0x64, 0x0f, 0x0e,
+	0x28, 0x46, 0xa9, 0xa8, 0x32, 0xe4, 0x0e, 0xf6,
+	0x51, 0x53, 0xb8, 0x3c, 0xb1, 0xff, 0xa3, 0x33,
+	0x41, 0x75, 0xff, 0xf1, 0x6f, 0xf1, 0xfb, 0xbb,
+	0x83, 0x7f, 0x06, 0x9b, 0xe7, 0x1b, 0x0a, 0xe0,
+	0x5c, 0x33, 0x60, 0x5b, 0xdb, 0x5b, 0xed, 0xfe,
+	0xa5, 0x16, 0x19, 0x72, 0xa3, 0x64, 0x23, 0x00,
+	0x02, 0xc7, 0xf3, 0x6a, 0x81, 0x3e, 0x44, 0x1d,
+	0x79, 0x15, 0x5f, 0x9a, 0xde, 0xe2, 0xfd, 0x1b,
+	0x73, 0xc1, 0xbc, 0x23, 0xba, 0x31, 0xd2, 0x50,
+	0xd5, 0xad, 0x7f, 0x74, 0xa7, 0xc9, 0xf8, 0x3e,
+	0x2b, 0x26, 0x10, 0xf6, 0x03, 0x36, 0x74, 0xe4,
+	0x0e, 0x6a, 0x72, 0xb7, 0x73, 0x0a, 0x42, 0x28,
+	0xc2, 0xad, 0x5e, 0x03, 0xbe, 0xb8, 0x0b, 0xa8,
+	0x5b, 0xd4, 0xb8, 0xba, 0x52, 0x89, 0xb1, 0x9b,
+	0xc1, 0xc3, 0x65, 0x87, 0xed, 0xa5, 0xf4, 0x86,
+	0xfd, 0x41, 0x80, 0x91, 0x27, 0x59, 0x53, 0x67,
+	0x15, 0x78, 0x54, 0x8b, 0x2d, 0x3d, 0xc7, 0xff,
+	0x02, 0x92, 0x07, 0x5f, 0x7a, 0x4b, 0x60, 0x59,
+	0x3c, 0x6f, 0x5c, 0xd8, 0xec, 0x95, 0xd2, 0xfe,
+	0xa0, 0x3b, 0xd8, 0x3f, 0xd1, 0x69, 0xa6, 0xd6,
+	0x41, 0xb2, 0xf4, 0x4d, 0x12, 0xf4, 0x58, 0x3e,
+	0x66, 0x64, 0x80, 0x31, 0x9b, 0xa8, 0x4c, 0x8b,
+	0x07, 0xb2, 0xec, 0x66, 0x94, 0x66, 0x47, 0x50,
+	0x50, 0x5f, 0x18, 0x0b, 0x0e, 0xd6, 0xc0, 0x39,
+	0x21, 0x13, 0x9e, 0x33, 0xbc, 0x79, 0x36, 0x02,
+	0x96, 0x70, 0xf0, 0x48, 0x67, 0x2f, 0x26, 0xe9,
+	0x6d, 0x10, 0xbb, 0xd6, 0x3f, 0xd1, 0x64, 0x7a,
+	0x2e, 0xbe, 0x0c, 0x61, 0xf0, 0x75, 0x42, 0x38,
+	0x23, 0xb1, 0x9e, 0x9f, 0x7c, 0x67, 0x66, 0xd9,
+	0x58, 0x9a, 0xf1, 0xbb, 0x41, 0x2a, 0x8d, 0x65,
+	0x84, 0x94, 0xfc, 0xdc, 0x6a, 0x50, 0x64, 0xdb,
+	0x56, 0x33, 0x76, 0x00, 0x10, 0xed, 0xbe, 0xd2,
+	0x12, 0xf6, 0xf6, 0x1b, 0xa2, 0x16, 0xde, 0xae,
+	0x31, 0x95, 0xdd, 0xb1, 0x08, 0x7e, 0x4e, 0xee,
+	0xe7, 0xf9, 0xa5, 0xfb, 0x5b, 0x61, 0x43, 0x00,
+	0x40, 0xf6, 0x7e, 0x02, 0x04, 0x32, 0x4e, 0x0c,
+	0xe2, 0x66, 0x0d, 0xd7, 0x07, 0x98, 0x0e, 0xf8,
+	0x72, 0x34, 0x6d, 0x95, 0x86, 0xd7, 0xcb, 0x31,
+	0x54, 0x47, 0xd0, 0x38, 0x29, 0x9c, 0x5a, 0x68,
+	0xd4, 0x87, 0x76, 0xc9, 0xe7, 0x7e, 0xe3, 0xf4,
+	0x81, 0x6d, 0x18, 0xcb, 0xc9, 0x05, 0xaf, 0xa0,
+	0xfb, 0x66, 0xf7, 0xf1, 0x1c, 0xc6, 0x14, 0x11,
+	0x4f, 0x2b, 0x79, 0x42, 0x8b, 0xbc, 0xac, 0xe7,
+	0x6c, 0xfe, 0x0f, 0x58, 0xe7, 0x7c, 0x78, 0x39,
+	0x30, 0xb0, 0x66, 0x2c, 0x9b, 0x6d, 0x3a, 0xe1,
+	0xcf, 0xc9, 0xa4, 0x0e, 0x6d, 0x6d, 0x8a, 0xa1,
+	0x3a, 0xe7, 0x28, 0xd4, 0x78, 0x4c, 0xa6, 0xa2,
+	0x2a, 0xa6, 0x03, 0x30, 0xd7, 0xa8, 0x25, 0x66,
+	0x87, 0x2f, 0x69, 0x5c, 0x4e, 0xdd, 0xa5, 0x49,
+	0x5d, 0x37, 0x4a, 0x59, 0xc4, 0xaf, 0x1f, 0xa2,
+	0xe4, 0xf8, 0xa6, 0x12, 0x97, 0xd5, 0x79, 0xf5,
+	0xe2, 0x4a, 0x2b, 0x5f, 0x61, 0xe4, 0x9e, 0xe3,
+	0xee, 0xb8, 0xa7, 0x5b, 0x2f, 0xf4, 0x9e, 0x6c,
+	0xfb, 0xd1, 0xc6, 0x56, 0x77, 0xba, 0x75, 0xaa,
+	0x3d, 0x1a, 0xa8, 0x0b, 0xb3, 0x68, 0x24, 0x00,
+	0x10, 0x7f, 0xfd, 0xd7, 0xa1, 0x8d, 0x83, 0x54,
+	0x4f, 0x1f, 0xd8, 0x2a, 0xbe, 0x8a, 0x0c, 0x87,
+	0xab, 0xa2, 0xde, 0xc3, 0x39, 0xbf, 0x09, 0x03,
+	0xa5, 0xf3, 0x05, 0x28, 0xe1, 0xe1, 0xee, 0x39,
+	0x70, 0x9c, 0xd8, 0x81, 0x12, 0x1e, 0x02, 0x40,
+	0xd2, 0x6e, 0xf0, 0xeb, 0x1b, 0x3d, 0x22, 0xc6,
+	0xe5, 0xe3, 0xb4, 0x5a, 0x98, 0xbb, 0xf0, 0x22,
+	0x28, 0x8d, 0xe5, 0xd3, 0x16, 0x48, 0x24, 0xa5,
+	0xe6, 0x66, 0x0c, 0xf9, 0x08, 0xf9, 0x7e, 0x1e,
+	0xe1, 0x28, 0x26, 0x22, 0xc7, 0xc7, 0x0a, 0x32,
+	0x47, 0xfa, 0xa3, 0xbe, 0x3c, 0xc4, 0xc5, 0x53,
+	0x0a, 0xd5, 0x94, 0x4a, 0xd7, 0x93, 0xd8, 0x42,
+	0x99, 0xb9, 0x0a, 0xdb, 0x56, 0xf7, 0xb9, 0x1c,
+	0x53, 0x4f, 0xfa, 0xd3, 0x74, 0xad, 0xd9, 0x68,
+	0xf1, 0x1b, 0xdf, 0x61, 0xc6, 0x5e, 0xa8, 0x48,
+	0xfc, 0xd4, 0x4a, 0x4c, 0x3c, 0x32, 0xf7, 0x1c,
+	0x96, 0x21, 0x9b, 0xf9, 0xa3, 0xcc, 0x5a, 0xce,
+	0xd5, 0xd7, 0x08, 0x24, 0xf6, 0x1c, 0xfd, 0xdd,
+	0x38, 0xc2, 0x32, 0xe9, 0xb8, 0xe7, 0xb6, 0xfa,
+	0x9d, 0x45, 0x13, 0x2c, 0x83, 0xfd, 0x4a, 0x69,
+	0x82, 0xcd, 0xdc, 0xb3, 0x76, 0x0c, 0x9e, 0xd8,
+	0xf4, 0x1b, 0x45, 0x15, 0xb4, 0x97, 0xe7, 0x58,
+	0x34, 0xe2, 0x03, 0x29, 0x5a, 0xbf, 0xb6, 0xe0,
+	0x5d, 0x13, 0xd9, 0x2b, 0xb4, 0x80, 0xb2, 0x45,
+	0x81, 0x6a, 0x2e, 0x6c, 0x89, 0x7d, 0xee, 0xbb,
+	0x52, 0xdd, 0x1f, 0x18, 0xe7, 0x13, 0x6b, 0x33,
+	0x0e, 0xea, 0x36, 0x92, 0x77, 0x7b, 0x6d, 0x9c,
+	0x5a, 0x5f, 0x45, 0x7b, 0x7b, 0x35, 0x62, 0x23,
+	0xd1, 0xbf, 0x0f, 0xd0, 0x08, 0x1b, 0x2b, 0x80,
+	0x6b, 0x7e, 0xf1, 0x21, 0x47, 0xb0, 0x57, 0xd1,
+	0x98, 0x72, 0x90, 0x34, 0x1c, 0x20, 0x04, 0xff,
+	0x3d, 0x5c, 0xee, 0x0e, 0x57, 0x5f, 0x6f, 0x24,
+	0x4e, 0x3c, 0xea, 0xfc, 0xa5, 0xa9, 0x83, 0xc9,
+	0x61, 0xb4, 0x51, 0x24, 0xf8, 0x27, 0x5e, 0x46,
+	0x8c, 0xb1, 0x53, 0x02, 0x96, 0x35, 0xba, 0xb8,
+	0x4c, 0x71, 0xd3, 0x15, 0x59, 0x35, 0x22, 0x20,
+	0xad, 0x03, 0x9f, 0x66, 0x44, 0x3b, 0x9c, 0x35,
+	0x37, 0x1f, 0x9b, 0xbb, 0xf3, 0xdb, 0x35, 0x63,
+	0x30, 0x64, 0xaa, 0xa2, 0x06, 0xa8, 0x5d, 0xbb,
+	0xe1, 0x9f, 0x70, 0xec, 0x82, 0x11, 0x06, 0x36,
+	0xec, 0x8b, 0x69, 0x66, 0x24, 0x44, 0xc9, 0x4a,
+	0x57, 0xbb, 0x9b, 0x78, 0x13, 0xce, 0x9c, 0x0c,
+	0xba, 0x92, 0x93, 0x63, 0xb8, 0xe2, 0x95, 0x0f,
+	0x0f, 0x16, 0x39, 0x52, 0xfd, 0x3a, 0x6d, 0x02,
+	0x4b, 0xdf, 0x13, 0xd3, 0x2a, 0x22, 0xb4, 0x03,
+	0x7c, 0x54, 0x49, 0x96, 0x68, 0x54, 0x10, 0xfa,
+	0xef, 0xaa, 0x6c, 0xe8, 0x22, 0xdc, 0x71, 0x16,
+	0x13, 0x1a, 0xf6, 0x28, 0xe5, 0x6d, 0x77, 0x3d,
+	0xcd, 0x30, 0x63, 0xb1, 0x70, 0x52, 0xa1, 0xc5,
+	0x94, 0x5f, 0xcf, 0xe8, 0xb8, 0x26, 0x98, 0xf7,
+	0x06, 0xa0, 0x0a, 0x70, 0xfa, 0x03, 0x80, 0xac,
+	0xc1, 0xec, 0xd6, 0x4c, 0x54, 0xd7, 0xfe, 0x47,
+	0xb6, 0x88, 0x4a, 0xf7, 0x71, 0x24, 0xee, 0xf3,
+	0xd2, 0xc2, 0x4a, 0x7f, 0xfe, 0x61, 0xc7, 0x35,
+	0xc9, 0x37, 0x67, 0xcb, 0x24, 0x35, 0xda, 0x7e,
+	0xca, 0x5f, 0xf3, 0x8d, 0xd4, 0x13, 0x8e, 0xd6,
+	0xcb, 0x4d, 0x53, 0x8f, 0x53, 0x1f, 0xc0, 0x74,
+	0xf7, 0x53, 0xb9, 0x5e, 0x23, 0x37, 0xba, 0x6e,
+	0xe3, 0x9d, 0x07, 0x55, 0x25, 0x7b, 0xe6, 0x2a,
+	0x64, 0xd1, 0x32, 0xdd, 0x54, 0x1b, 0x4b, 0xc0,
+	0xe1, 0xd7, 0x69, 0x58, 0xf8, 0x93, 0x29, 0xc4,
+	0xdd, 0x23, 0x2f, 0xa5, 0xfc, 0x9d, 0x7e, 0xf8,
+	0xd4, 0x90, 0xcd, 0x82, 0x55, 0xdc, 0x16, 0x16,
+	0x9f, 0x07, 0x52, 0x9b, 0x9d, 0x25, 0xed, 0x32,
+	0xc5, 0x7b, 0xdf, 0xf6, 0x83, 0x46, 0x3d, 0x65,
+	0xb7, 0xef, 0x87, 0x7a, 0x12, 0x69, 0x8f, 0x06,
+	0x7c, 0x51, 0x15, 0x4a, 0x08, 0xe8, 0xac, 0x9a,
+	0x0c, 0x24, 0xa7, 0x27, 0xd8, 0x46, 0x2f, 0xe7,
+	0x01, 0x0e, 0x1c, 0xc6, 0x91, 0xb0, 0x6e, 0x85,
+	0x65, 0xf0, 0x29, 0x0d, 0x2e, 0x6b, 0x3b, 0xfb,
+	0x4b, 0xdf, 0xe4, 0x80, 0x93, 0x03, 0x66, 0x46,
+	0x3e, 0x8a, 0x6e, 0xf3, 0x5e, 0x4d, 0x62, 0x0e,
+	0x49, 0x05, 0xaf, 0xd4, 0xf8, 0x21, 0x20, 0x61,
+	0x1d, 0x39, 0x17, 0xf4, 0x61, 0x47, 0x95, 0xfb,
+	0x15, 0x2e, 0xb3, 0x4f, 0xd0, 0x5d, 0xf5, 0x7d,
+	0x40, 0xda, 0x90, 0x3c, 0x6b, 0xcb, 0x17, 0x00,
+	0x13, 0x3b, 0x64, 0x34, 0x1b, 0xf0, 0xf2, 0xe5,
+	0x3b, 0xb2, 0xc7, 0xd3, 0x5f, 0x3a, 0x44, 0xa6,
+	0x9b, 0xb7, 0x78, 0x0e, 0x42, 0x5d, 0x4c, 0xc1,
+	0xe9, 0xd2, 0xcb, 0xb7, 0x78, 0xd1, 0xfe, 0x9a,
+	0xb5, 0x07, 0xe9, 0xe0, 0xbe, 0xe2, 0x8a, 0xa7,
+	0x01, 0x83, 0x00, 0x8c, 0x5c, 0x08, 0xe6, 0x63,
+	0x12, 0x92, 0xb7, 0xb7, 0xa6, 0x19, 0x7d, 0x38,
+	0x13, 0x38, 0x92, 0x87, 0x24, 0xf9, 0x48, 0xb3,
+	0x5e, 0x87, 0x6a, 0x40, 0x39, 0x5c, 0x3f, 0xed,
+	0x8f, 0xee, 0xdb, 0x15, 0x82, 0x06, 0xda, 0x49,
+	0x21, 0x2b, 0xb5, 0xbf, 0x32, 0x7c, 0x9f, 0x42,
+	0x28, 0x63, 0xcf, 0xaf, 0x1e, 0xf8, 0xc6, 0xa0,
+	0xd1, 0x02, 0x43, 0x57, 0x62, 0xec, 0x9b, 0x0f,
+	0x01, 0x9e, 0x71, 0xd8, 0x87, 0x9d, 0x01, 0xc1,
+	0x58, 0x77, 0xd9, 0xaf, 0xb1, 0x10, 0x7e, 0xdd,
+	0xa6, 0x50, 0x96, 0xe5, 0xf0, 0x72, 0x00, 0x6d,
+	0x4b, 0xf8, 0x2a, 0x8f, 0x19, 0xf3, 0x22, 0x88,
+	0x11, 0x4a, 0x8b, 0x7c, 0xfd, 0xb7, 0xed, 0xe1,
+	0xf6, 0x40, 0x39, 0xe0, 0xe9, 0xf6, 0x3d, 0x25,
+	0xe6, 0x74, 0x3c, 0x58, 0x57, 0x7f, 0xe1, 0x22,
+	0x96, 0x47, 0x31, 0x91, 0xba, 0x70, 0x85, 0x28,
+	0x6b, 0x9f, 0x6e, 0x25, 0xac, 0x23, 0x66, 0x2f,
+	0x29, 0x88, 0x28, 0xce, 0x8c, 0x5c, 0x88, 0x53,
+	0xd1, 0x3b, 0xcc, 0x6a, 0x51, 0xb2, 0xe1, 0x28,
+	0x3f, 0x91, 0xb4, 0x0d, 0x00, 0x3a, 0xe3, 0xf8,
+	0xc3, 0x8f, 0xd7, 0x96, 0x62, 0x0e, 0x2e, 0xfc,
+	0xc8, 0x6c, 0x77, 0xa6, 0x1d, 0x22, 0xc1, 0xb8,
+	0xe6, 0x61, 0xd7, 0x67, 0x36, 0x13, 0x7b, 0xbb,
+	0x9b, 0x59, 0x09, 0xa6, 0xdf, 0xf7, 0x6b, 0xa3,
+	0x40, 0x1a, 0xf5, 0x4f, 0xb4, 0xda, 0xd3, 0xf3,
+	0x81, 0x93, 0xc6, 0x18, 0xd9, 0x26, 0xee, 0xac,
+	0xf0, 0xaa, 0xdf, 0xc5, 0x9c, 0xca, 0xc2, 0xa2,
+	0xcc, 0x7b, 0x5c, 0x24, 0xb0, 0xbc, 0xd0, 0x6a,
+	0x4d, 0x89, 0x09, 0xb8, 0x07, 0xfe, 0x87, 0xad,
+	0x0a, 0xea, 0xb8, 0x42, 0xf9, 0x5e, 0xb3, 0x3e,
+	0x36, 0x4c, 0xaf, 0x75, 0x9e, 0x1c, 0xeb, 0xbd,
+	0xbc, 0xbb, 0x80, 0x40, 0xa7, 0x3a, 0x30, 0xbf,
+	0xa8, 0x44, 0xf4, 0xeb, 0x38, 0xad, 0x29, 0xba,
+	0x23, 0xed, 0x41, 0x0c, 0xea, 0xd2, 0xbb, 0x41,
+	0x18, 0xd6, 0xb9, 0xba, 0x65, 0x2b, 0xa3, 0x91,
+	0x6d, 0x1f, 0xa9, 0xf4, 0xd1, 0x25, 0x8d, 0x4d,
+	0x38, 0xff, 0x64, 0xa0, 0xec, 0xde, 0xa6, 0xb6,
+	0x79, 0xab, 0x8e, 0x33, 0x6c, 0x47, 0xde, 0xaf,
+	0x94, 0xa4, 0xa5, 0x86, 0x77, 0x55, 0x09, 0x92,
+	0x81, 0x31, 0x76, 0xc7, 0x34, 0x22, 0x89, 0x8e,
+	0x3d, 0x26, 0x26, 0xd7, 0xfc, 0x1e, 0x16, 0x72,
+	0x13, 0x33, 0x63, 0xd5, 0x22, 0xbe, 0xb8, 0x04,
+	0x34, 0x84, 0x41, 0xbb, 0x80, 0xd0, 0x9f, 0x46,
+	0x48, 0x07, 0xa7, 0xfc, 0x2b, 0x3a, 0x75, 0x55,
+	0x8c, 0xc7, 0x6a, 0xbd, 0x7e, 0x46, 0x08, 0x84,
+	0x0f, 0xd5, 0x74, 0xc0, 0x82, 0x8e, 0xaa, 0x61,
+	0x05, 0x01, 0xb2, 0x47, 0x6e, 0x20, 0x6a, 0x2d,
+	0x58, 0x70, 0x48, 0x32, 0xa7, 0x37, 0xd2, 0xb8,
+	0x82, 0x1a, 0x51, 0xb9, 0x61, 0xdd, 0xfd, 0x9d,
+	0x6b, 0x0e, 0x18, 0x97, 0xf8, 0x45, 0x5f, 0x87,
+	0x10, 0xcf, 0x34, 0x72, 0x45, 0x26, 0x49, 0x70,
+	0xe7, 0xa3, 0x78, 0xe0, 0x52, 0x89, 0x84, 0x94,
+	0x83, 0x82, 0xc2, 0x69, 0x8f, 0xe3, 0xe1, 0x3f,
+	0x60, 0x74, 0x88, 0xc4, 0xf7, 0x75, 0x2c, 0xfb,
+	0xbd, 0xb6, 0xc4, 0x7e, 0x10, 0x0a, 0x6c, 0x90,
+	0x04, 0x9e, 0xc3, 0x3f, 0x59, 0x7c, 0xce, 0x31,
+	0x18, 0x60, 0x57, 0x73, 0x46, 0x94, 0x7d, 0x06,
+	0xa0, 0x6d, 0x44, 0xec, 0xa2, 0x0a, 0x9e, 0x05,
+	0x15, 0xef, 0xca, 0x5c, 0xbf, 0x00, 0xeb, 0xf7,
+	0x3d, 0x32, 0xd4, 0xa5, 0xef, 0x49, 0x89, 0x5e,
+	0x46, 0xb0, 0xa6, 0x63, 0x5b, 0x8a, 0x73, 0xae,
+	0x6f, 0xd5, 0x9d, 0xf8, 0x4f, 0x40, 0xb5, 0xb2,
+	0x6e, 0xd3, 0xb6, 0x01, 0xa9, 0x26, 0xa2, 0x21,
+	0xcf, 0x33, 0x7a, 0x3a, 0xa4, 0x23, 0x13, 0xb0,
+	0x69, 0x6a, 0xee, 0xce, 0xd8, 0x9d, 0x01, 0x1d,
+	0x50, 0xc1, 0x30, 0x6c, 0xb1, 0xcd, 0xa0, 0xf0,
+	0xf0, 0xa2, 0x64, 0x6f, 0xbb, 0xbf, 0x5e, 0xe6,
+	0xab, 0x87, 0xb4, 0x0f, 0x4f, 0x15, 0xaf, 0xb5,
+	0x25, 0xa1, 0xb2, 0xd0, 0x80, 0x2c, 0xfb, 0xf9,
+	0xfe, 0xd2, 0x33, 0xbb, 0x76, 0xfe, 0x7c, 0xa8,
+	0x66, 0xf7, 0xe7, 0x85, 0x9f, 0x1f, 0x85, 0x57,
+	0x88, 0xe1, 0xe9, 0x63, 0xe4, 0xd8, 0x1c, 0xa1,
+	0xfb, 0xda, 0x44, 0x05, 0x2e, 0x1d, 0x3a, 0x1c,
+	0xff, 0xc8, 0x3b, 0xc0, 0xfe, 0xda, 0x22, 0x0b,
+	0x43, 0xd6, 0x88, 0x39, 0x4c, 0x4a, 0xa6, 0x69,
+	0x18, 0x93, 0x42, 0x4e, 0xb5, 0xcc, 0x66, 0x0d,
+	0x09, 0xf8, 0x1e, 0x7c, 0xd3, 0x3c, 0x99, 0x0d,
+	0x50, 0x1d, 0x62, 0xe9, 0x57, 0x06, 0xbf, 0x19,
+	0x88, 0xdd, 0xad, 0x7b, 0x4f, 0xf9, 0xc7, 0x82,
+	0x6d, 0x8d, 0xc8, 0xc4, 0xc5, 0x78, 0x17, 0x20,
+	0x15, 0xc5, 0x52, 0x41, 0xcf, 0x5b, 0xd6, 0x7f,
+	0x94, 0x02, 0x41, 0xe0, 0x40, 0x22, 0x03, 0x5e,
+	0xd1, 0x53, 0xd4, 0x86, 0xd3, 0x2c, 0x9f, 0x0f,
+	0x96, 0xe3, 0x6b, 0x9a, 0x76, 0x32, 0x06, 0x47,
+	0x4b, 0x11, 0xb3, 0xdd, 0x03, 0x65, 0xbd, 0x9b,
+	0x01, 0xda, 0x9c, 0xb9, 0x7e, 0x3f, 0x6a, 0xc4,
+	0x7b, 0xea, 0xd4, 0x3c, 0xb9, 0xfb, 0x5c, 0x6b,
+	0x64, 0x33, 0x52, 0xba, 0x64, 0x78, 0x8f, 0xa4,
+	0xaf, 0x7a, 0x61, 0x8d, 0xbc, 0xc5, 0x73, 0xe9,
+	0x6b, 0x58, 0x97, 0x4b, 0xbf, 0x63, 0x22, 0xd3,
+	0x37, 0x02, 0x54, 0xc5, 0xb9, 0x16, 0x4a, 0xf0,
+	0x19, 0xd8, 0x94, 0x57, 0xb8, 0x8a, 0xb3, 0x16,
+	0x3b, 0xd0, 0x84, 0x8e, 0x67, 0xa6, 0xa3, 0x7d,
+	0x78, 0xec, 0x00
+};
+static const u8 dec_assoc012[] __initconst = {
+	0xb1, 0x69, 0x83, 0x87, 0x30, 0xaa, 0x5d, 0xb8,
+	0x77, 0xe8, 0x21, 0xff, 0x06, 0x59, 0x35, 0xce,
+	0x75, 0xfe, 0x38, 0xef, 0xb8, 0x91, 0x43, 0x8c,
+	0xcf, 0x70, 0xdd, 0x0a, 0x68, 0xbf, 0xd4, 0xbc,
+	0x16, 0x76, 0x99, 0x36, 0x1e, 0x58, 0x79, 0x5e,
+	0xd4, 0x29, 0xf7, 0x33, 0x93, 0x48, 0xdb, 0x5f,
+	0x01, 0xae, 0x9c, 0xb6, 0xe4, 0x88, 0x6d, 0x2b,
+	0x76, 0x75, 0xe0, 0xf3, 0x74, 0xe2, 0xc9
+};
+static const u8 dec_nonce012[] __initconst = {
+	0x05, 0xa3, 0x93, 0xed, 0x30, 0xc5, 0xa2, 0x06
+};
+static const u8 dec_key012[] __initconst = {
+	0xb3, 0x35, 0x50, 0x03, 0x54, 0x2e, 0x40, 0x5e,
+	0x8f, 0x59, 0x8e, 0xc5, 0x90, 0xd5, 0x27, 0x2d,
+	0xba, 0x29, 0x2e, 0xcb, 0x1b, 0x70, 0x44, 0x1e,
+	0x65, 0x91, 0x6e, 0x2a, 0x79, 0x22, 0xda, 0x64
+};
+
+static const u8 dec_input013[] __initconst = {
+	0x52, 0x34, 0xb3, 0x65, 0x3b, 0xb7, 0xe5, 0xd3,
+	0xab, 0x49, 0x17, 0x60, 0xd2, 0x52, 0x56, 0xdf,
+	0xdf, 0x34, 0x56, 0x82, 0xe2, 0xbe, 0xe5, 0xe1,
+	0x28, 0xd1, 0x4e, 0x5f, 0x4f, 0x01, 0x7d, 0x3f,
+	0x99, 0x6b, 0x30, 0x6e, 0x1a, 0x7c, 0x4c, 0x8e,
+	0x62, 0x81, 0xae, 0x86, 0x3f, 0x6b, 0xd0, 0xb5,
+	0xa9, 0xcf, 0x50, 0xf1, 0x02, 0x12, 0xa0, 0x0b,
+	0x24, 0xe9, 0xe6, 0x72, 0x89, 0x2c, 0x52, 0x1b,
+	0x34, 0x38, 0xf8, 0x75, 0x5f, 0xa0, 0x74, 0xe2,
+	0x99, 0xdd, 0xa6, 0x4b, 0x14, 0x50, 0x4e, 0xf1,
+	0xbe, 0xd6, 0x9e, 0xdb, 0xb2, 0x24, 0x27, 0x74,
+	0x12, 0x4a, 0x78, 0x78, 0x17, 0xa5, 0x58, 0x8e,
+	0x2f, 0xf9, 0xf4, 0x8d, 0xee, 0x03, 0x88, 0xae,
+	0xb8, 0x29, 0xa1, 0x2f, 0x4b, 0xee, 0x92, 0xbd,
+	0x87, 0xb3, 0xce, 0x34, 0x21, 0x57, 0x46, 0x04,
+	0x49, 0x0c, 0x80, 0xf2, 0x01, 0x13, 0xa1, 0x55,
+	0xb3, 0xff, 0x44, 0x30, 0x3c, 0x1c, 0xd0, 0xef,
+	0xbc, 0x18, 0x74, 0x26, 0xad, 0x41, 0x5b, 0x5b,
+	0x3e, 0x9a, 0x7a, 0x46, 0x4f, 0x16, 0xd6, 0x74,
+	0x5a, 0xb7, 0x3a, 0x28, 0x31, 0xd8, 0xae, 0x26,
+	0xac, 0x50, 0x53, 0x86, 0xf2, 0x56, 0xd7, 0x3f,
+	0x29, 0xbc, 0x45, 0x68, 0x8e, 0xcb, 0x98, 0x64,
+	0xdd, 0xc9, 0xba, 0xb8, 0x4b, 0x7b, 0x82, 0xdd,
+	0x14, 0xa7, 0xcb, 0x71, 0x72, 0x00, 0x5c, 0xad,
+	0x7b, 0x6a, 0x89, 0xa4, 0x3d, 0xbf, 0xb5, 0x4b,
+	0x3e, 0x7c, 0x5a, 0xcf, 0xb8, 0xa1, 0xc5, 0x6e,
+	0xc8, 0xb6, 0x31, 0x57, 0x7b, 0xdf, 0xa5, 0x7e,
+	0xb1, 0xd6, 0x42, 0x2a, 0x31, 0x36, 0xd1, 0xd0,
+	0x3f, 0x7a, 0xe5, 0x94, 0xd6, 0x36, 0xa0, 0x6f,
+	0xb7, 0x40, 0x7d, 0x37, 0xc6, 0x55, 0x7c, 0x50,
+	0x40, 0x6d, 0x29, 0x89, 0xe3, 0x5a, 0xae, 0x97,
+	0xe7, 0x44, 0x49, 0x6e, 0xbd, 0x81, 0x3d, 0x03,
+	0x93, 0x06, 0x12, 0x06, 0xe2, 0x41, 0x12, 0x4a,
+	0xf1, 0x6a, 0xa4, 0x58, 0xa2, 0xfb, 0xd2, 0x15,
+	0xba, 0xc9, 0x79, 0xc9, 0xce, 0x5e, 0x13, 0xbb,
+	0xf1, 0x09, 0x04, 0xcc, 0xfd, 0xe8, 0x51, 0x34,
+	0x6a, 0xe8, 0x61, 0x88, 0xda, 0xed, 0x01, 0x47,
+	0x84, 0xf5, 0x73, 0x25, 0xf9, 0x1c, 0x42, 0x86,
+	0x07, 0xf3, 0x5b, 0x1a, 0x01, 0xb3, 0xeb, 0x24,
+	0x32, 0x8d, 0xf6, 0xed, 0x7c, 0x4b, 0xeb, 0x3c,
+	0x36, 0x42, 0x28, 0xdf, 0xdf, 0xb6, 0xbe, 0xd9,
+	0x8c, 0x52, 0xd3, 0x2b, 0x08, 0x90, 0x8c, 0xe7,
+	0x98, 0x31, 0xe2, 0x32, 0x8e, 0xfc, 0x11, 0x48,
+	0x00, 0xa8, 0x6a, 0x42, 0x4a, 0x02, 0xc6, 0x4b,
+	0x09, 0xf1, 0xe3, 0x49, 0xf3, 0x45, 0x1f, 0x0e,
+	0xbc, 0x56, 0xe2, 0xe4, 0xdf, 0xfb, 0xeb, 0x61,
+	0xfa, 0x24, 0xc1, 0x63, 0x75, 0xbb, 0x47, 0x75,
+	0xaf, 0xe1, 0x53, 0x16, 0x96, 0x21, 0x85, 0x26,
+	0x11, 0xb3, 0x76, 0xe3, 0x23, 0xa1, 0x6b, 0x74,
+	0x37, 0xd0, 0xde, 0x06, 0x90, 0x71, 0x5d, 0x43,
+	0x88, 0x9b, 0x00, 0x54, 0xa6, 0x75, 0x2f, 0xa1,
+	0xc2, 0x0b, 0x73, 0x20, 0x1d, 0xb6, 0x21, 0x79,
+	0x57, 0x3f, 0xfa, 0x09, 0xbe, 0x8a, 0x33, 0xc3,
+	0x52, 0xf0, 0x1d, 0x82, 0x31, 0xd1, 0x55, 0xb5,
+	0x6c, 0x99, 0x25, 0xcf, 0x5c, 0x32, 0xce, 0xe9,
+	0x0d, 0xfa, 0x69, 0x2c, 0xd5, 0x0d, 0xc5, 0x6d,
+	0x86, 0xd0, 0x0c, 0x3b, 0x06, 0x50, 0x79, 0xe8,
+	0xc3, 0xae, 0x04, 0xe6, 0xcd, 0x51, 0xe4, 0x26,
+	0x9b, 0x4f, 0x7e, 0xa6, 0x0f, 0xab, 0xd8, 0xe5,
+	0xde, 0xa9, 0x00, 0x95, 0xbe, 0xa3, 0x9d, 0x5d,
+	0xb2, 0x09, 0x70, 0x18, 0x1c, 0xf0, 0xac, 0x29,
+	0x23, 0x02, 0x29, 0x28, 0xd2, 0x74, 0x35, 0x57,
+	0x62, 0x0f, 0x24, 0xea, 0x5e, 0x33, 0xc2, 0x92,
+	0xf3, 0x78, 0x4d, 0x30, 0x1e, 0xa1, 0x99, 0xa9,
+	0x82, 0xb0, 0x42, 0x31, 0x8d, 0xad, 0x8a, 0xbc,
+	0xfc, 0xd4, 0x57, 0x47, 0x3e, 0xb4, 0x50, 0xdd,
+	0x6e, 0x2c, 0x80, 0x4d, 0x22, 0xf1, 0xfb, 0x57,
+	0xc4, 0xdd, 0x17, 0xe1, 0x8a, 0x36, 0x4a, 0xb3,
+	0x37, 0xca, 0xc9, 0x4e, 0xab, 0xd5, 0x69, 0xc4,
+	0xf4, 0xbc, 0x0b, 0x3b, 0x44, 0x4b, 0x29, 0x9c,
+	0xee, 0xd4, 0x35, 0x22, 0x21, 0xb0, 0x1f, 0x27,
+	0x64, 0xa8, 0x51, 0x1b, 0xf0, 0x9f, 0x19, 0x5c,
+	0xfb, 0x5a, 0x64, 0x74, 0x70, 0x45, 0x09, 0xf5,
+	0x64, 0xfe, 0x1a, 0x2d, 0xc9, 0x14, 0x04, 0x14,
+	0xcf, 0xd5, 0x7d, 0x60, 0xaf, 0x94, 0x39, 0x94,
+	0xe2, 0x7d, 0x79, 0x82, 0xd0, 0x65, 0x3b, 0x6b,
+	0x9c, 0x19, 0x84, 0xb4, 0x6d, 0xb3, 0x0c, 0x99,
+	0xc0, 0x56, 0xa8, 0xbd, 0x73, 0xce, 0x05, 0x84,
+	0x3e, 0x30, 0xaa, 0xc4, 0x9b, 0x1b, 0x04, 0x2a,
+	0x9f, 0xd7, 0x43, 0x2b, 0x23, 0xdf, 0xbf, 0xaa,
+	0xd5, 0xc2, 0x43, 0x2d, 0x70, 0xab, 0xdc, 0x75,
+	0xad, 0xac, 0xf7, 0xc0, 0xbe, 0x67, 0xb2, 0x74,
+	0xed, 0x67, 0x10, 0x4a, 0x92, 0x60, 0xc1, 0x40,
+	0x50, 0x19, 0x8a, 0x8a, 0x8c, 0x09, 0x0e, 0x72,
+	0xe1, 0x73, 0x5e, 0xe8, 0x41, 0x85, 0x63, 0x9f,
+	0x3f, 0xd7, 0x7d, 0xc4, 0xfb, 0x22, 0x5d, 0x92,
+	0x6c, 0xb3, 0x1e, 0xe2, 0x50, 0x2f, 0x82, 0xa8,
+	0x28, 0xc0, 0xb5, 0xd7, 0x5f, 0x68, 0x0d, 0x2c,
+	0x2d, 0xaf, 0x7e, 0xfa, 0x2e, 0x08, 0x0f, 0x1f,
+	0x70, 0x9f, 0xe9, 0x19, 0x72, 0x55, 0xf8, 0xfb,
+	0x51, 0xd2, 0x33, 0x5d, 0xa0, 0xd3, 0x2b, 0x0a,
+	0x6c, 0xbc, 0x4e, 0xcf, 0x36, 0x4d, 0xdc, 0x3b,
+	0xe9, 0x3e, 0x81, 0x7c, 0x61, 0xdb, 0x20, 0x2d,
+	0x3a, 0xc3, 0xb3, 0x0c, 0x1e, 0x00, 0xb9, 0x7c,
+	0xf5, 0xca, 0x10, 0x5f, 0x3a, 0x71, 0xb3, 0xe4,
+	0x20, 0xdb, 0x0c, 0x2a, 0x98, 0x63, 0x45, 0x00,
+	0x58, 0xf6, 0x68, 0xe4, 0x0b, 0xda, 0x13, 0x3b,
+	0x60, 0x5c, 0x76, 0xdb, 0xb9, 0x97, 0x71, 0xe4,
+	0xd9, 0xb7, 0xdb, 0xbd, 0x68, 0xc7, 0x84, 0x84,
+	0xaa, 0x7c, 0x68, 0x62, 0x5e, 0x16, 0xfc, 0xba,
+	0x72, 0xaa, 0x9a, 0xa9, 0xeb, 0x7c, 0x75, 0x47,
+	0x97, 0x7e, 0xad, 0xe2, 0xd9, 0x91, 0xe8, 0xe4,
+	0xa5, 0x31, 0xd7, 0x01, 0x8e, 0xa2, 0x11, 0x88,
+	0x95, 0xb9, 0xf2, 0x9b, 0xd3, 0x7f, 0x1b, 0x81,
+	0x22, 0xf7, 0x98, 0x60, 0x0a, 0x64, 0xa6, 0xc1,
+	0xf6, 0x49, 0xc7, 0xe3, 0x07, 0x4d, 0x94, 0x7a,
+	0xcf, 0x6e, 0x68, 0x0c, 0x1b, 0x3f, 0x6e, 0x2e,
+	0xee, 0x92, 0xfa, 0x52, 0xb3, 0x59, 0xf8, 0xf1,
+	0x8f, 0x6a, 0x66, 0xa3, 0x82, 0x76, 0x4a, 0x07,
+	0x1a, 0xc7, 0xdd, 0xf5, 0xda, 0x9c, 0x3c, 0x24,
+	0xbf, 0xfd, 0x42, 0xa1, 0x10, 0x64, 0x6a, 0x0f,
+	0x89, 0xee, 0x36, 0xa5, 0xce, 0x99, 0x48, 0x6a,
+	0xf0, 0x9f, 0x9e, 0x69, 0xa4, 0x40, 0x20, 0xe9,
+	0x16, 0x15, 0xf7, 0xdb, 0x75, 0x02, 0xcb, 0xe9,
+	0x73, 0x8b, 0x3b, 0x49, 0x2f, 0xf0, 0xaf, 0x51,
+	0x06, 0x5c, 0xdf, 0x27, 0x27, 0x49, 0x6a, 0xd1,
+	0xcc, 0xc7, 0xb5, 0x63, 0xb5, 0xfc, 0xb8, 0x5c,
+	0x87, 0x7f, 0x84, 0xb4, 0xcc, 0x14, 0xa9, 0x53,
+	0xda, 0xa4, 0x56, 0xf8, 0xb6, 0x1b, 0xcc, 0x40,
+	0x27, 0x52, 0x06, 0x5a, 0x13, 0x81, 0xd7, 0x3a,
+	0xd4, 0x3b, 0xfb, 0x49, 0x65, 0x31, 0x33, 0xb2,
+	0xfa, 0xcd, 0xad, 0x58, 0x4e, 0x2b, 0xae, 0xd2,
+	0x20, 0xfb, 0x1a, 0x48, 0xb4, 0x3f, 0x9a, 0xd8,
+	0x7a, 0x35, 0x4a, 0xc8, 0xee, 0x88, 0x5e, 0x07,
+	0x66, 0x54, 0xb9, 0xec, 0x9f, 0xa3, 0xe3, 0xb9,
+	0x37, 0xaa, 0x49, 0x76, 0x31, 0xda, 0x74, 0x2d,
+	0x3c, 0xa4, 0x65, 0x10, 0x32, 0x38, 0xf0, 0xde,
+	0xd3, 0x99, 0x17, 0xaa, 0x71, 0xaa, 0x8f, 0x0f,
+	0x8c, 0xaf, 0xa2, 0xf8, 0x5d, 0x64, 0xba, 0x1d,
+	0xa3, 0xef, 0x96, 0x73, 0xe8, 0xa1, 0x02, 0x8d,
+	0x0c, 0x6d, 0xb8, 0x06, 0x90, 0xb8, 0x08, 0x56,
+	0x2c, 0xa7, 0x06, 0xc9, 0xc2, 0x38, 0xdb, 0x7c,
+	0x63, 0xb1, 0x57, 0x8e, 0xea, 0x7c, 0x79, 0xf3,
+	0x49, 0x1d, 0xfe, 0x9f, 0xf3, 0x6e, 0xb1, 0x1d,
+	0xba, 0x19, 0x80, 0x1a, 0x0a, 0xd3, 0xb0, 0x26,
+	0x21, 0x40, 0xb1, 0x7c, 0xf9, 0x4d, 0x8d, 0x10,
+	0xc1, 0x7e, 0xf4, 0xf6, 0x3c, 0xa8, 0xfd, 0x7c,
+	0xa3, 0x92, 0xb2, 0x0f, 0xaa, 0xcc, 0xa6, 0x11,
+	0xfe, 0x04, 0xe3, 0xd1, 0x7a, 0x32, 0x89, 0xdf,
+	0x0d, 0xc4, 0x8f, 0x79, 0x6b, 0xca, 0x16, 0x7c,
+	0x6e, 0xf9, 0xad, 0x0f, 0xf6, 0xfe, 0x27, 0xdb,
+	0xc4, 0x13, 0x70, 0xf1, 0x62, 0x1a, 0x4f, 0x79,
+	0x40, 0xc9, 0x9b, 0x8b, 0x21, 0xea, 0x84, 0xfa,
+	0xf5, 0xf1, 0x89, 0xce, 0xb7, 0x55, 0x0a, 0x80,
+	0x39, 0x2f, 0x55, 0x36, 0x16, 0x9c, 0x7b, 0x08,
+	0xbd, 0x87, 0x0d, 0xa5, 0x32, 0xf1, 0x52, 0x7c,
+	0xe8, 0x55, 0x60, 0x5b, 0xd7, 0x69, 0xe4, 0xfc,
+	0xfa, 0x12, 0x85, 0x96, 0xea, 0x50, 0x28, 0xab,
+	0x8a, 0xf7, 0xbb, 0x0e, 0x53, 0x74, 0xca, 0xa6,
+	0x27, 0x09, 0xc2, 0xb5, 0xde, 0x18, 0x14, 0xd9,
+	0xea, 0xe5, 0x29, 0x1c, 0x40, 0x56, 0xcf, 0xd7,
+	0xae, 0x05, 0x3f, 0x65, 0xaf, 0x05, 0x73, 0xe2,
+	0x35, 0x96, 0x27, 0x07, 0x14, 0xc0, 0xad, 0x33,
+	0xf1, 0xdc, 0x44, 0x7a, 0x89, 0x17, 0x77, 0xd2,
+	0x9c, 0x58, 0x60, 0xf0, 0x3f, 0x7b, 0x2d, 0x2e,
+	0x57, 0x95, 0x54, 0x87, 0xed, 0xf2, 0xc7, 0x4c,
+	0xf0, 0xae, 0x56, 0x29, 0x19, 0x7d, 0x66, 0x4b,
+	0x9b, 0x83, 0x84, 0x42, 0x3b, 0x01, 0x25, 0x66,
+	0x8e, 0x02, 0xde, 0xb9, 0x83, 0x54, 0x19, 0xf6,
+	0x9f, 0x79, 0x0d, 0x67, 0xc5, 0x1d, 0x7a, 0x44,
+	0x02, 0x98, 0xa7, 0x16, 0x1c, 0x29, 0x0d, 0x74,
+	0xff, 0x85, 0x40, 0x06, 0xef, 0x2c, 0xa9, 0xc6,
+	0xf5, 0x53, 0x07, 0x06, 0xae, 0xe4, 0xfa, 0x5f,
+	0xd8, 0x39, 0x4d, 0xf1, 0x9b, 0x6b, 0xd9, 0x24,
+	0x84, 0xfe, 0x03, 0x4c, 0xb2, 0x3f, 0xdf, 0xa1,
+	0x05, 0x9e, 0x50, 0x14, 0x5a, 0xd9, 0x1a, 0xa2,
+	0xa7, 0xfa, 0xfa, 0x17, 0xf7, 0x78, 0xd6, 0xb5,
+	0x92, 0x61, 0x91, 0xac, 0x36, 0xfa, 0x56, 0x0d,
+	0x38, 0x32, 0x18, 0x85, 0x08, 0x58, 0x37, 0xf0,
+	0x4b, 0xdb, 0x59, 0xe7, 0xa4, 0x34, 0xc0, 0x1b,
+	0x01, 0xaf, 0x2d, 0xde, 0xa1, 0xaa, 0x5d, 0xd3,
+	0xec, 0xe1, 0xd4, 0xf7, 0xe6, 0x54, 0x68, 0xf0,
+	0x51, 0x97, 0xa7, 0x89, 0xea, 0x24, 0xad, 0xd3,
+	0x6e, 0x47, 0x93, 0x8b, 0x4b, 0xb4, 0xf7, 0x1c,
+	0x42, 0x06, 0x67, 0xe8, 0x99, 0xf6, 0xf5, 0x7b,
+	0x85, 0xb5, 0x65, 0xb5, 0xb5, 0xd2, 0x37, 0xf5,
+	0xf3, 0x02, 0xa6, 0x4d, 0x11, 0xa7, 0xdc, 0x51,
+	0x09, 0x7f, 0xa0, 0xd8, 0x88, 0x1c, 0x13, 0x71,
+	0xae, 0x9c, 0xb7, 0x7b, 0x34, 0xd6, 0x4e, 0x68,
+	0x26, 0x83, 0x51, 0xaf, 0x1d, 0xee, 0x8b, 0xbb,
+	0x69, 0x43, 0x2b, 0x9e, 0x8a, 0xbc, 0x02, 0x0e,
+	0xa0, 0x1b, 0xe0, 0xa8, 0x5f, 0x6f, 0xaf, 0x1b,
+	0x8f, 0xe7, 0x64, 0x71, 0x74, 0x11, 0x7e, 0xa8,
+	0xd8, 0xf9, 0x97, 0x06, 0xc3, 0xb6, 0xfb, 0xfb,
+	0xb7, 0x3d, 0x35, 0x9d, 0x3b, 0x52, 0xed, 0x54,
+	0xca, 0xf4, 0x81, 0x01, 0x2d, 0x1b, 0xc3, 0xa7,
+	0x00, 0x3d, 0x1a, 0x39, 0x54, 0xe1, 0xf6, 0xff,
+	0xed, 0x6f, 0x0b, 0x5a, 0x68, 0xda, 0x58, 0xdd,
+	0xa9, 0xcf, 0x5c, 0x4a, 0xe5, 0x09, 0x4e, 0xde,
+	0x9d, 0xbc, 0x3e, 0xee, 0x5a, 0x00, 0x3b, 0x2c,
+	0x87, 0x10, 0x65, 0x60, 0xdd, 0xd7, 0x56, 0xd1,
+	0x4c, 0x64, 0x45, 0xe4, 0x21, 0xec, 0x78, 0xf8,
+	0x25, 0x7a, 0x3e, 0x16, 0x5d, 0x09, 0x53, 0x14,
+	0xbe, 0x4f, 0xae, 0x87, 0xd8, 0xd1, 0xaa, 0x3c,
+	0xf6, 0x3e, 0xa4, 0x70, 0x8c, 0x5e, 0x70, 0xa4,
+	0xb3, 0x6b, 0x66, 0x73, 0xd3, 0xbf, 0x31, 0x06,
+	0x19, 0x62, 0x93, 0x15, 0xf2, 0x86, 0xe4, 0x52,
+	0x7e, 0x53, 0x4c, 0x12, 0x38, 0xcc, 0x34, 0x7d,
+	0x57, 0xf6, 0x42, 0x93, 0x8a, 0xc4, 0xee, 0x5c,
+	0x8a, 0xe1, 0x52, 0x8f, 0x56, 0x64, 0xf6, 0xa6,
+	0xd1, 0x91, 0x57, 0x70, 0xcd, 0x11, 0x76, 0xf5,
+	0x59, 0x60, 0x60, 0x3c, 0xc1, 0xc3, 0x0b, 0x7f,
+	0x58, 0x1a, 0x50, 0x91, 0xf1, 0x68, 0x8f, 0x6e,
+	0x74, 0x74, 0xa8, 0x51, 0x0b, 0xf7, 0x7a, 0x98,
+	0x37, 0xf2, 0x0a, 0x0e, 0xa4, 0x97, 0x04, 0xb8,
+	0x9b, 0xfd, 0xa0, 0xea, 0xf7, 0x0d, 0xe1, 0xdb,
+	0x03, 0xf0, 0x31, 0x29, 0xf8, 0xdd, 0x6b, 0x8b,
+	0x5d, 0xd8, 0x59, 0xa9, 0x29, 0xcf, 0x9a, 0x79,
+	0x89, 0x19, 0x63, 0x46, 0x09, 0x79, 0x6a, 0x11,
+	0xda, 0x63, 0x68, 0x48, 0x77, 0x23, 0xfb, 0x7d,
+	0x3a, 0x43, 0xcb, 0x02, 0x3b, 0x7a, 0x6d, 0x10,
+	0x2a, 0x9e, 0xac, 0xf1, 0xd4, 0x19, 0xf8, 0x23,
+	0x64, 0x1d, 0x2c, 0x5f, 0xf2, 0xb0, 0x5c, 0x23,
+	0x27, 0xf7, 0x27, 0x30, 0x16, 0x37, 0xb1, 0x90,
+	0xab, 0x38, 0xfb, 0x55, 0xcd, 0x78, 0x58, 0xd4,
+	0x7d, 0x43, 0xf6, 0x45, 0x5e, 0x55, 0x8d, 0xb1,
+	0x02, 0x65, 0x58, 0xb4, 0x13, 0x4b, 0x36, 0xf7,
+	0xcc, 0xfe, 0x3d, 0x0b, 0x82, 0xe2, 0x12, 0x11,
+	0xbb, 0xe6, 0xb8, 0x3a, 0x48, 0x71, 0xc7, 0x50,
+	0x06, 0x16, 0x3a, 0xe6, 0x7c, 0x05, 0xc7, 0xc8,
+	0x4d, 0x2f, 0x08, 0x6a, 0x17, 0x9a, 0x95, 0x97,
+	0x50, 0x68, 0xdc, 0x28, 0x18, 0xc4, 0x61, 0x38,
+	0xb9, 0xe0, 0x3e, 0x78, 0xdb, 0x29, 0xe0, 0x9f,
+	0x52, 0xdd, 0xf8, 0x4f, 0x91, 0xc1, 0xd0, 0x33,
+	0xa1, 0x7a, 0x8e, 0x30, 0x13, 0x82, 0x07, 0x9f,
+	0xd3, 0x31, 0x0f, 0x23, 0xbe, 0x32, 0x5a, 0x75,
+	0xcf, 0x96, 0xb2, 0xec, 0xb5, 0x32, 0xac, 0x21,
+	0xd1, 0x82, 0x33, 0xd3, 0x15, 0x74, 0xbd, 0x90,
+	0xf1, 0x2c, 0xe6, 0x5f, 0x8d, 0xe3, 0x02, 0xe8,
+	0xe9, 0xc4, 0xca, 0x96, 0xeb, 0x0e, 0xbc, 0x91,
+	0xf4, 0xb9, 0xea, 0xd9, 0x1b, 0x75, 0xbd, 0xe1,
+	0xac, 0x2a, 0x05, 0x37, 0x52, 0x9b, 0x1b, 0x3f,
+	0x5a, 0xdc, 0x21, 0xc3, 0x98, 0xbb, 0xaf, 0xa3,
+	0xf2, 0x00, 0xbf, 0x0d, 0x30, 0x89, 0x05, 0xcc,
+	0xa5, 0x76, 0xf5, 0x06, 0xf0, 0xc6, 0x54, 0x8a,
+	0x5d, 0xd4, 0x1e, 0xc1, 0xf2, 0xce, 0xb0, 0x62,
+	0xc8, 0xfc, 0x59, 0x42, 0x9a, 0x90, 0x60, 0x55,
+	0xfe, 0x88, 0xa5, 0x8b, 0xb8, 0x33, 0x0c, 0x23,
+	0x24, 0x0d, 0x15, 0x70, 0x37, 0x1e, 0x3d, 0xf6,
+	0xd2, 0xea, 0x92, 0x10, 0xb2, 0xc4, 0x51, 0xac,
+	0xf2, 0xac, 0xf3, 0x6b, 0x6c, 0xaa, 0xcf, 0x12,
+	0xc5, 0x6c, 0x90, 0x50, 0xb5, 0x0c, 0xfc, 0x1a,
+	0x15, 0x52, 0xe9, 0x26, 0xc6, 0x52, 0xa4, 0xe7,
+	0x81, 0x69, 0xe1, 0xe7, 0x9e, 0x30, 0x01, 0xec,
+	0x84, 0x89, 0xb2, 0x0d, 0x66, 0xdd, 0xce, 0x28,
+	0x5c, 0xec, 0x98, 0x46, 0x68, 0x21, 0x9f, 0x88,
+	0x3f, 0x1f, 0x42, 0x77, 0xce, 0xd0, 0x61, 0xd4,
+	0x20, 0xa7, 0xff, 0x53, 0xad, 0x37, 0xd0, 0x17,
+	0x35, 0xc9, 0xfc, 0xba, 0x0a, 0x78, 0x3f, 0xf2,
+	0xcc, 0x86, 0x89, 0xe8, 0x4b, 0x3c, 0x48, 0x33,
+	0x09, 0x7f, 0xc6, 0xc0, 0xdd, 0xb8, 0xfd, 0x7a,
+	0x66, 0x66, 0x65, 0xeb, 0x47, 0xa7, 0x04, 0x28,
+	0xa3, 0x19, 0x8e, 0xa9, 0xb1, 0x13, 0x67, 0x62,
+	0x70, 0xcf, 0xd7
+};
+static const u8 dec_output013[] __initconst = {
+	0x74, 0xa6, 0x3e, 0xe4, 0xb1, 0xcb, 0xaf, 0xb0,
+	0x40, 0xe5, 0x0f, 0x9e, 0xf1, 0xf2, 0x89, 0xb5,
+	0x42, 0x34, 0x8a, 0xa1, 0x03, 0xb7, 0xe9, 0x57,
+	0x46, 0xbe, 0x20, 0xe4, 0x6e, 0xb0, 0xeb, 0xff,
+	0xea, 0x07, 0x7e, 0xef, 0xe2, 0x55, 0x9f, 0xe5,
+	0x78, 0x3a, 0xb7, 0x83, 0xc2, 0x18, 0x40, 0x7b,
+	0xeb, 0xcd, 0x81, 0xfb, 0x90, 0x12, 0x9e, 0x46,
+	0xa9, 0xd6, 0x4a, 0xba, 0xb0, 0x62, 0xdb, 0x6b,
+	0x99, 0xc4, 0xdb, 0x54, 0x4b, 0xb8, 0xa5, 0x71,
+	0xcb, 0xcd, 0x63, 0x32, 0x55, 0xfb, 0x31, 0xf0,
+	0x38, 0xf5, 0xbe, 0x78, 0xe4, 0x45, 0xce, 0x1b,
+	0x6a, 0x5b, 0x0e, 0xf4, 0x16, 0xe4, 0xb1, 0x3d,
+	0xf6, 0x63, 0x7b, 0xa7, 0x0c, 0xde, 0x6f, 0x8f,
+	0x74, 0xdf, 0xe0, 0x1e, 0x9d, 0xce, 0x8f, 0x24,
+	0xef, 0x23, 0x35, 0x33, 0x7b, 0x83, 0x34, 0x23,
+	0x58, 0x74, 0x14, 0x77, 0x1f, 0xc2, 0x4f, 0x4e,
+	0xc6, 0x89, 0xf9, 0x52, 0x09, 0x37, 0x64, 0x14,
+	0xc4, 0x01, 0x6b, 0x9d, 0x77, 0xe8, 0x90, 0x5d,
+	0xa8, 0x4a, 0x2a, 0xef, 0x5c, 0x7f, 0xeb, 0xbb,
+	0xb2, 0xc6, 0x93, 0x99, 0x66, 0xdc, 0x7f, 0xd4,
+	0x9e, 0x2a, 0xca, 0x8d, 0xdb, 0xe7, 0x20, 0xcf,
+	0xe4, 0x73, 0xae, 0x49, 0x7d, 0x64, 0x0f, 0x0e,
+	0x28, 0x46, 0xa9, 0xa8, 0x32, 0xe4, 0x0e, 0xf6,
+	0x51, 0x53, 0xb8, 0x3c, 0xb1, 0xff, 0xa3, 0x33,
+	0x41, 0x75, 0xff, 0xf1, 0x6f, 0xf1, 0xfb, 0xbb,
+	0x83, 0x7f, 0x06, 0x9b, 0xe7, 0x1b, 0x0a, 0xe0,
+	0x5c, 0x33, 0x60, 0x5b, 0xdb, 0x5b, 0xed, 0xfe,
+	0xa5, 0x16, 0x19, 0x72, 0xa3, 0x64, 0x23, 0x00,
+	0x02, 0xc7, 0xf3, 0x6a, 0x81, 0x3e, 0x44, 0x1d,
+	0x79, 0x15, 0x5f, 0x9a, 0xde, 0xe2, 0xfd, 0x1b,
+	0x73, 0xc1, 0xbc, 0x23, 0xba, 0x31, 0xd2, 0x50,
+	0xd5, 0xad, 0x7f, 0x74, 0xa7, 0xc9, 0xf8, 0x3e,
+	0x2b, 0x26, 0x10, 0xf6, 0x03, 0x36, 0x74, 0xe4,
+	0x0e, 0x6a, 0x72, 0xb7, 0x73, 0x0a, 0x42, 0x28,
+	0xc2, 0xad, 0x5e, 0x03, 0xbe, 0xb8, 0x0b, 0xa8,
+	0x5b, 0xd4, 0xb8, 0xba, 0x52, 0x89, 0xb1, 0x9b,
+	0xc1, 0xc3, 0x65, 0x87, 0xed, 0xa5, 0xf4, 0x86,
+	0xfd, 0x41, 0x80, 0x91, 0x27, 0x59, 0x53, 0x67,
+	0x15, 0x78, 0x54, 0x8b, 0x2d, 0x3d, 0xc7, 0xff,
+	0x02, 0x92, 0x07, 0x5f, 0x7a, 0x4b, 0x60, 0x59,
+	0x3c, 0x6f, 0x5c, 0xd8, 0xec, 0x95, 0xd2, 0xfe,
+	0xa0, 0x3b, 0xd8, 0x3f, 0xd1, 0x69, 0xa6, 0xd6,
+	0x41, 0xb2, 0xf4, 0x4d, 0x12, 0xf4, 0x58, 0x3e,
+	0x66, 0x64, 0x80, 0x31, 0x9b, 0xa8, 0x4c, 0x8b,
+	0x07, 0xb2, 0xec, 0x66, 0x94, 0x66, 0x47, 0x50,
+	0x50, 0x5f, 0x18, 0x0b, 0x0e, 0xd6, 0xc0, 0x39,
+	0x21, 0x13, 0x9e, 0x33, 0xbc, 0x79, 0x36, 0x02,
+	0x96, 0x70, 0xf0, 0x48, 0x67, 0x2f, 0x26, 0xe9,
+	0x6d, 0x10, 0xbb, 0xd6, 0x3f, 0xd1, 0x64, 0x7a,
+	0x2e, 0xbe, 0x0c, 0x61, 0xf0, 0x75, 0x42, 0x38,
+	0x23, 0xb1, 0x9e, 0x9f, 0x7c, 0x67, 0x66, 0xd9,
+	0x58, 0x9a, 0xf1, 0xbb, 0x41, 0x2a, 0x8d, 0x65,
+	0x84, 0x94, 0xfc, 0xdc, 0x6a, 0x50, 0x64, 0xdb,
+	0x56, 0x33, 0x76, 0x00, 0x10, 0xed, 0xbe, 0xd2,
+	0x12, 0xf6, 0xf6, 0x1b, 0xa2, 0x16, 0xde, 0xae,
+	0x31, 0x95, 0xdd, 0xb1, 0x08, 0x7e, 0x4e, 0xee,
+	0xe7, 0xf9, 0xa5, 0xfb, 0x5b, 0x61, 0x43, 0x00,
+	0x40, 0xf6, 0x7e, 0x02, 0x04, 0x32, 0x4e, 0x0c,
+	0xe2, 0x66, 0x0d, 0xd7, 0x07, 0x98, 0x0e, 0xf8,
+	0x72, 0x34, 0x6d, 0x95, 0x86, 0xd7, 0xcb, 0x31,
+	0x54, 0x47, 0xd0, 0x38, 0x29, 0x9c, 0x5a, 0x68,
+	0xd4, 0x87, 0x76, 0xc9, 0xe7, 0x7e, 0xe3, 0xf4,
+	0x81, 0x6d, 0x18, 0xcb, 0xc9, 0x05, 0xaf, 0xa0,
+	0xfb, 0x66, 0xf7, 0xf1, 0x1c, 0xc6, 0x14, 0x11,
+	0x4f, 0x2b, 0x79, 0x42, 0x8b, 0xbc, 0xac, 0xe7,
+	0x6c, 0xfe, 0x0f, 0x58, 0xe7, 0x7c, 0x78, 0x39,
+	0x30, 0xb0, 0x66, 0x2c, 0x9b, 0x6d, 0x3a, 0xe1,
+	0xcf, 0xc9, 0xa4, 0x0e, 0x6d, 0x6d, 0x8a, 0xa1,
+	0x3a, 0xe7, 0x28, 0xd4, 0x78, 0x4c, 0xa6, 0xa2,
+	0x2a, 0xa6, 0x03, 0x30, 0xd7, 0xa8, 0x25, 0x66,
+	0x87, 0x2f, 0x69, 0x5c, 0x4e, 0xdd, 0xa5, 0x49,
+	0x5d, 0x37, 0x4a, 0x59, 0xc4, 0xaf, 0x1f, 0xa2,
+	0xe4, 0xf8, 0xa6, 0x12, 0x97, 0xd5, 0x79, 0xf5,
+	0xe2, 0x4a, 0x2b, 0x5f, 0x61, 0xe4, 0x9e, 0xe3,
+	0xee, 0xb8, 0xa7, 0x5b, 0x2f, 0xf4, 0x9e, 0x6c,
+	0xfb, 0xd1, 0xc6, 0x56, 0x77, 0xba, 0x75, 0xaa,
+	0x3d, 0x1a, 0xa8, 0x0b, 0xb3, 0x68, 0x24, 0x00,
+	0x10, 0x7f, 0xfd, 0xd7, 0xa1, 0x8d, 0x83, 0x54,
+	0x4f, 0x1f, 0xd8, 0x2a, 0xbe, 0x8a, 0x0c, 0x87,
+	0xab, 0xa2, 0xde, 0xc3, 0x39, 0xbf, 0x09, 0x03,
+	0xa5, 0xf3, 0x05, 0x28, 0xe1, 0xe1, 0xee, 0x39,
+	0x70, 0x9c, 0xd8, 0x81, 0x12, 0x1e, 0x02, 0x40,
+	0xd2, 0x6e, 0xf0, 0xeb, 0x1b, 0x3d, 0x22, 0xc6,
+	0xe5, 0xe3, 0xb4, 0x5a, 0x98, 0xbb, 0xf0, 0x22,
+	0x28, 0x8d, 0xe5, 0xd3, 0x16, 0x48, 0x24, 0xa5,
+	0xe6, 0x66, 0x0c, 0xf9, 0x08, 0xf9, 0x7e, 0x1e,
+	0xe1, 0x28, 0x26, 0x22, 0xc7, 0xc7, 0x0a, 0x32,
+	0x47, 0xfa, 0xa3, 0xbe, 0x3c, 0xc4, 0xc5, 0x53,
+	0x0a, 0xd5, 0x94, 0x4a, 0xd7, 0x93, 0xd8, 0x42,
+	0x99, 0xb9, 0x0a, 0xdb, 0x56, 0xf7, 0xb9, 0x1c,
+	0x53, 0x4f, 0xfa, 0xd3, 0x74, 0xad, 0xd9, 0x68,
+	0xf1, 0x1b, 0xdf, 0x61, 0xc6, 0x5e, 0xa8, 0x48,
+	0xfc, 0xd4, 0x4a, 0x4c, 0x3c, 0x32, 0xf7, 0x1c,
+	0x96, 0x21, 0x9b, 0xf9, 0xa3, 0xcc, 0x5a, 0xce,
+	0xd5, 0xd7, 0x08, 0x24, 0xf6, 0x1c, 0xfd, 0xdd,
+	0x38, 0xc2, 0x32, 0xe9, 0xb8, 0xe7, 0xb6, 0xfa,
+	0x9d, 0x45, 0x13, 0x2c, 0x83, 0xfd, 0x4a, 0x69,
+	0x82, 0xcd, 0xdc, 0xb3, 0x76, 0x0c, 0x9e, 0xd8,
+	0xf4, 0x1b, 0x45, 0x15, 0xb4, 0x97, 0xe7, 0x58,
+	0x34, 0xe2, 0x03, 0x29, 0x5a, 0xbf, 0xb6, 0xe0,
+	0x5d, 0x13, 0xd9, 0x2b, 0xb4, 0x80, 0xb2, 0x45,
+	0x81, 0x6a, 0x2e, 0x6c, 0x89, 0x7d, 0xee, 0xbb,
+	0x52, 0xdd, 0x1f, 0x18, 0xe7, 0x13, 0x6b, 0x33,
+	0x0e, 0xea, 0x36, 0x92, 0x77, 0x7b, 0x6d, 0x9c,
+	0x5a, 0x5f, 0x45, 0x7b, 0x7b, 0x35, 0x62, 0x23,
+	0xd1, 0xbf, 0x0f, 0xd0, 0x08, 0x1b, 0x2b, 0x80,
+	0x6b, 0x7e, 0xf1, 0x21, 0x47, 0xb0, 0x57, 0xd1,
+	0x98, 0x72, 0x90, 0x34, 0x1c, 0x20, 0x04, 0xff,
+	0x3d, 0x5c, 0xee, 0x0e, 0x57, 0x5f, 0x6f, 0x24,
+	0x4e, 0x3c, 0xea, 0xfc, 0xa5, 0xa9, 0x83, 0xc9,
+	0x61, 0xb4, 0x51, 0x24, 0xf8, 0x27, 0x5e, 0x46,
+	0x8c, 0xb1, 0x53, 0x02, 0x96, 0x35, 0xba, 0xb8,
+	0x4c, 0x71, 0xd3, 0x15, 0x59, 0x35, 0x22, 0x20,
+	0xad, 0x03, 0x9f, 0x66, 0x44, 0x3b, 0x9c, 0x35,
+	0x37, 0x1f, 0x9b, 0xbb, 0xf3, 0xdb, 0x35, 0x63,
+	0x30, 0x64, 0xaa, 0xa2, 0x06, 0xa8, 0x5d, 0xbb,
+	0xe1, 0x9f, 0x70, 0xec, 0x82, 0x11, 0x06, 0x36,
+	0xec, 0x8b, 0x69, 0x66, 0x24, 0x44, 0xc9, 0x4a,
+	0x57, 0xbb, 0x9b, 0x78, 0x13, 0xce, 0x9c, 0x0c,
+	0xba, 0x92, 0x93, 0x63, 0xb8, 0xe2, 0x95, 0x0f,
+	0x0f, 0x16, 0x39, 0x52, 0xfd, 0x3a, 0x6d, 0x02,
+	0x4b, 0xdf, 0x13, 0xd3, 0x2a, 0x22, 0xb4, 0x03,
+	0x7c, 0x54, 0x49, 0x96, 0x68, 0x54, 0x10, 0xfa,
+	0xef, 0xaa, 0x6c, 0xe8, 0x22, 0xdc, 0x71, 0x16,
+	0x13, 0x1a, 0xf6, 0x28, 0xe5, 0x6d, 0x77, 0x3d,
+	0xcd, 0x30, 0x63, 0xb1, 0x70, 0x52, 0xa1, 0xc5,
+	0x94, 0x5f, 0xcf, 0xe8, 0xb8, 0x26, 0x98, 0xf7,
+	0x06, 0xa0, 0x0a, 0x70, 0xfa, 0x03, 0x80, 0xac,
+	0xc1, 0xec, 0xd6, 0x4c, 0x54, 0xd7, 0xfe, 0x47,
+	0xb6, 0x88, 0x4a, 0xf7, 0x71, 0x24, 0xee, 0xf3,
+	0xd2, 0xc2, 0x4a, 0x7f, 0xfe, 0x61, 0xc7, 0x35,
+	0xc9, 0x37, 0x67, 0xcb, 0x24, 0x35, 0xda, 0x7e,
+	0xca, 0x5f, 0xf3, 0x8d, 0xd4, 0x13, 0x8e, 0xd6,
+	0xcb, 0x4d, 0x53, 0x8f, 0x53, 0x1f, 0xc0, 0x74,
+	0xf7, 0x53, 0xb9, 0x5e, 0x23, 0x37, 0xba, 0x6e,
+	0xe3, 0x9d, 0x07, 0x55, 0x25, 0x7b, 0xe6, 0x2a,
+	0x64, 0xd1, 0x32, 0xdd, 0x54, 0x1b, 0x4b, 0xc0,
+	0xe1, 0xd7, 0x69, 0x58, 0xf8, 0x93, 0x29, 0xc4,
+	0xdd, 0x23, 0x2f, 0xa5, 0xfc, 0x9d, 0x7e, 0xf8,
+	0xd4, 0x90, 0xcd, 0x82, 0x55, 0xdc, 0x16, 0x16,
+	0x9f, 0x07, 0x52, 0x9b, 0x9d, 0x25, 0xed, 0x32,
+	0xc5, 0x7b, 0xdf, 0xf6, 0x83, 0x46, 0x3d, 0x65,
+	0xb7, 0xef, 0x87, 0x7a, 0x12, 0x69, 0x8f, 0x06,
+	0x7c, 0x51, 0x15, 0x4a, 0x08, 0xe8, 0xac, 0x9a,
+	0x0c, 0x24, 0xa7, 0x27, 0xd8, 0x46, 0x2f, 0xe7,
+	0x01, 0x0e, 0x1c, 0xc6, 0x91, 0xb0, 0x6e, 0x85,
+	0x65, 0xf0, 0x29, 0x0d, 0x2e, 0x6b, 0x3b, 0xfb,
+	0x4b, 0xdf, 0xe4, 0x80, 0x93, 0x03, 0x66, 0x46,
+	0x3e, 0x8a, 0x6e, 0xf3, 0x5e, 0x4d, 0x62, 0x0e,
+	0x49, 0x05, 0xaf, 0xd4, 0xf8, 0x21, 0x20, 0x61,
+	0x1d, 0x39, 0x17, 0xf4, 0x61, 0x47, 0x95, 0xfb,
+	0x15, 0x2e, 0xb3, 0x4f, 0xd0, 0x5d, 0xf5, 0x7d,
+	0x40, 0xda, 0x90, 0x3c, 0x6b, 0xcb, 0x17, 0x00,
+	0x13, 0x3b, 0x64, 0x34, 0x1b, 0xf0, 0xf2, 0xe5,
+	0x3b, 0xb2, 0xc7, 0xd3, 0x5f, 0x3a, 0x44, 0xa6,
+	0x9b, 0xb7, 0x78, 0x0e, 0x42, 0x5d, 0x4c, 0xc1,
+	0xe9, 0xd2, 0xcb, 0xb7, 0x78, 0xd1, 0xfe, 0x9a,
+	0xb5, 0x07, 0xe9, 0xe0, 0xbe, 0xe2, 0x8a, 0xa7,
+	0x01, 0x83, 0x00, 0x8c, 0x5c, 0x08, 0xe6, 0x63,
+	0x12, 0x92, 0xb7, 0xb7, 0xa6, 0x19, 0x7d, 0x38,
+	0x13, 0x38, 0x92, 0x87, 0x24, 0xf9, 0x48, 0xb3,
+	0x5e, 0x87, 0x6a, 0x40, 0x39, 0x5c, 0x3f, 0xed,
+	0x8f, 0xee, 0xdb, 0x15, 0x82, 0x06, 0xda, 0x49,
+	0x21, 0x2b, 0xb5, 0xbf, 0x32, 0x7c, 0x9f, 0x42,
+	0x28, 0x63, 0xcf, 0xaf, 0x1e, 0xf8, 0xc6, 0xa0,
+	0xd1, 0x02, 0x43, 0x57, 0x62, 0xec, 0x9b, 0x0f,
+	0x01, 0x9e, 0x71, 0xd8, 0x87, 0x9d, 0x01, 0xc1,
+	0x58, 0x77, 0xd9, 0xaf, 0xb1, 0x10, 0x7e, 0xdd,
+	0xa6, 0x50, 0x96, 0xe5, 0xf0, 0x72, 0x00, 0x6d,
+	0x4b, 0xf8, 0x2a, 0x8f, 0x19, 0xf3, 0x22, 0x88,
+	0x11, 0x4a, 0x8b, 0x7c, 0xfd, 0xb7, 0xed, 0xe1,
+	0xf6, 0x40, 0x39, 0xe0, 0xe9, 0xf6, 0x3d, 0x25,
+	0xe6, 0x74, 0x3c, 0x58, 0x57, 0x7f, 0xe1, 0x22,
+	0x96, 0x47, 0x31, 0x91, 0xba, 0x70, 0x85, 0x28,
+	0x6b, 0x9f, 0x6e, 0x25, 0xac, 0x23, 0x66, 0x2f,
+	0x29, 0x88, 0x28, 0xce, 0x8c, 0x5c, 0x88, 0x53,
+	0xd1, 0x3b, 0xcc, 0x6a, 0x51, 0xb2, 0xe1, 0x28,
+	0x3f, 0x91, 0xb4, 0x0d, 0x00, 0x3a, 0xe3, 0xf8,
+	0xc3, 0x8f, 0xd7, 0x96, 0x62, 0x0e, 0x2e, 0xfc,
+	0xc8, 0x6c, 0x77, 0xa6, 0x1d, 0x22, 0xc1, 0xb8,
+	0xe6, 0x61, 0xd7, 0x67, 0x36, 0x13, 0x7b, 0xbb,
+	0x9b, 0x59, 0x09, 0xa6, 0xdf, 0xf7, 0x6b, 0xa3,
+	0x40, 0x1a, 0xf5, 0x4f, 0xb4, 0xda, 0xd3, 0xf3,
+	0x81, 0x93, 0xc6, 0x18, 0xd9, 0x26, 0xee, 0xac,
+	0xf0, 0xaa, 0xdf, 0xc5, 0x9c, 0xca, 0xc2, 0xa2,
+	0xcc, 0x7b, 0x5c, 0x24, 0xb0, 0xbc, 0xd0, 0x6a,
+	0x4d, 0x89, 0x09, 0xb8, 0x07, 0xfe, 0x87, 0xad,
+	0x0a, 0xea, 0xb8, 0x42, 0xf9, 0x5e, 0xb3, 0x3e,
+	0x36, 0x4c, 0xaf, 0x75, 0x9e, 0x1c, 0xeb, 0xbd,
+	0xbc, 0xbb, 0x80, 0x40, 0xa7, 0x3a, 0x30, 0xbf,
+	0xa8, 0x44, 0xf4, 0xeb, 0x38, 0xad, 0x29, 0xba,
+	0x23, 0xed, 0x41, 0x0c, 0xea, 0xd2, 0xbb, 0x41,
+	0x18, 0xd6, 0xb9, 0xba, 0x65, 0x2b, 0xa3, 0x91,
+	0x6d, 0x1f, 0xa9, 0xf4, 0xd1, 0x25, 0x8d, 0x4d,
+	0x38, 0xff, 0x64, 0xa0, 0xec, 0xde, 0xa6, 0xb6,
+	0x79, 0xab, 0x8e, 0x33, 0x6c, 0x47, 0xde, 0xaf,
+	0x94, 0xa4, 0xa5, 0x86, 0x77, 0x55, 0x09, 0x92,
+	0x81, 0x31, 0x76, 0xc7, 0x34, 0x22, 0x89, 0x8e,
+	0x3d, 0x26, 0x26, 0xd7, 0xfc, 0x1e, 0x16, 0x72,
+	0x13, 0x33, 0x63, 0xd5, 0x22, 0xbe, 0xb8, 0x04,
+	0x34, 0x84, 0x41, 0xbb, 0x80, 0xd0, 0x9f, 0x46,
+	0x48, 0x07, 0xa7, 0xfc, 0x2b, 0x3a, 0x75, 0x55,
+	0x8c, 0xc7, 0x6a, 0xbd, 0x7e, 0x46, 0x08, 0x84,
+	0x0f, 0xd5, 0x74, 0xc0, 0x82, 0x8e, 0xaa, 0x61,
+	0x05, 0x01, 0xb2, 0x47, 0x6e, 0x20, 0x6a, 0x2d,
+	0x58, 0x70, 0x48, 0x32, 0xa7, 0x37, 0xd2, 0xb8,
+	0x82, 0x1a, 0x51, 0xb9, 0x61, 0xdd, 0xfd, 0x9d,
+	0x6b, 0x0e, 0x18, 0x97, 0xf8, 0x45, 0x5f, 0x87,
+	0x10, 0xcf, 0x34, 0x72, 0x45, 0x26, 0x49, 0x70,
+	0xe7, 0xa3, 0x78, 0xe0, 0x52, 0x89, 0x84, 0x94,
+	0x83, 0x82, 0xc2, 0x69, 0x8f, 0xe3, 0xe1, 0x3f,
+	0x60, 0x74, 0x88, 0xc4, 0xf7, 0x75, 0x2c, 0xfb,
+	0xbd, 0xb6, 0xc4, 0x7e, 0x10, 0x0a, 0x6c, 0x90,
+	0x04, 0x9e, 0xc3, 0x3f, 0x59, 0x7c, 0xce, 0x31,
+	0x18, 0x60, 0x57, 0x73, 0x46, 0x94, 0x7d, 0x06,
+	0xa0, 0x6d, 0x44, 0xec, 0xa2, 0x0a, 0x9e, 0x05,
+	0x15, 0xef, 0xca, 0x5c, 0xbf, 0x00, 0xeb, 0xf7,
+	0x3d, 0x32, 0xd4, 0xa5, 0xef, 0x49, 0x89, 0x5e,
+	0x46, 0xb0, 0xa6, 0x63, 0x5b, 0x8a, 0x73, 0xae,
+	0x6f, 0xd5, 0x9d, 0xf8, 0x4f, 0x40, 0xb5, 0xb2,
+	0x6e, 0xd3, 0xb6, 0x01, 0xa9, 0x26, 0xa2, 0x21,
+	0xcf, 0x33, 0x7a, 0x3a, 0xa4, 0x23, 0x13, 0xb0,
+	0x69, 0x6a, 0xee, 0xce, 0xd8, 0x9d, 0x01, 0x1d,
+	0x50, 0xc1, 0x30, 0x6c, 0xb1, 0xcd, 0xa0, 0xf0,
+	0xf0, 0xa2, 0x64, 0x6f, 0xbb, 0xbf, 0x5e, 0xe6,
+	0xab, 0x87, 0xb4, 0x0f, 0x4f, 0x15, 0xaf, 0xb5,
+	0x25, 0xa1, 0xb2, 0xd0, 0x80, 0x2c, 0xfb, 0xf9,
+	0xfe, 0xd2, 0x33, 0xbb, 0x76, 0xfe, 0x7c, 0xa8,
+	0x66, 0xf7, 0xe7, 0x85, 0x9f, 0x1f, 0x85, 0x57,
+	0x88, 0xe1, 0xe9, 0x63, 0xe4, 0xd8, 0x1c, 0xa1,
+	0xfb, 0xda, 0x44, 0x05, 0x2e, 0x1d, 0x3a, 0x1c,
+	0xff, 0xc8, 0x3b, 0xc0, 0xfe, 0xda, 0x22, 0x0b,
+	0x43, 0xd6, 0x88, 0x39, 0x4c, 0x4a, 0xa6, 0x69,
+	0x18, 0x93, 0x42, 0x4e, 0xb5, 0xcc, 0x66, 0x0d,
+	0x09, 0xf8, 0x1e, 0x7c, 0xd3, 0x3c, 0x99, 0x0d,
+	0x50, 0x1d, 0x62, 0xe9, 0x57, 0x06, 0xbf, 0x19,
+	0x88, 0xdd, 0xad, 0x7b, 0x4f, 0xf9, 0xc7, 0x82,
+	0x6d, 0x8d, 0xc8, 0xc4, 0xc5, 0x78, 0x17, 0x20,
+	0x15, 0xc5, 0x52, 0x41, 0xcf, 0x5b, 0xd6, 0x7f,
+	0x94, 0x02, 0x41, 0xe0, 0x40, 0x22, 0x03, 0x5e,
+	0xd1, 0x53, 0xd4, 0x86, 0xd3, 0x2c, 0x9f, 0x0f,
+	0x96, 0xe3, 0x6b, 0x9a, 0x76, 0x32, 0x06, 0x47,
+	0x4b, 0x11, 0xb3, 0xdd, 0x03, 0x65, 0xbd, 0x9b,
+	0x01, 0xda, 0x9c, 0xb9, 0x7e, 0x3f, 0x6a, 0xc4,
+	0x7b, 0xea, 0xd4, 0x3c, 0xb9, 0xfb, 0x5c, 0x6b,
+	0x64, 0x33, 0x52, 0xba, 0x64, 0x78, 0x8f, 0xa4,
+	0xaf, 0x7a, 0x61, 0x8d, 0xbc, 0xc5, 0x73, 0xe9,
+	0x6b, 0x58, 0x97, 0x4b, 0xbf, 0x63, 0x22, 0xd3,
+	0x37, 0x02, 0x54, 0xc5, 0xb9, 0x16, 0x4a, 0xf0,
+	0x19, 0xd8, 0x94, 0x57, 0xb8, 0x8a, 0xb3, 0x16,
+	0x3b, 0xd0, 0x84, 0x8e, 0x67, 0xa6, 0xa3, 0x7d,
+	0x78, 0xec, 0x00
+};
+static const u8 dec_assoc013[] __initconst = {
+	0xb1, 0x69, 0x83, 0x87, 0x30, 0xaa, 0x5d, 0xb8,
+	0x77, 0xe8, 0x21, 0xff, 0x06, 0x59, 0x35, 0xce,
+	0x75, 0xfe, 0x38, 0xef, 0xb8, 0x91, 0x43, 0x8c,
+	0xcf, 0x70, 0xdd, 0x0a, 0x68, 0xbf, 0xd4, 0xbc,
+	0x16, 0x76, 0x99, 0x36, 0x1e, 0x58, 0x79, 0x5e,
+	0xd4, 0x29, 0xf7, 0x33, 0x93, 0x48, 0xdb, 0x5f,
+	0x01, 0xae, 0x9c, 0xb6, 0xe4, 0x88, 0x6d, 0x2b,
+	0x76, 0x75, 0xe0, 0xf3, 0x74, 0xe2, 0xc9
+};
+static const u8 dec_nonce013[] __initconst = {
+	0x05, 0xa3, 0x93, 0xed, 0x30, 0xc5, 0xa2, 0x06
+};
+static const u8 dec_key013[] __initconst = {
+	0xb3, 0x35, 0x50, 0x03, 0x54, 0x2e, 0x40, 0x5e,
+	0x8f, 0x59, 0x8e, 0xc5, 0x90, 0xd5, 0x27, 0x2d,
+	0xba, 0x29, 0x2e, 0xcb, 0x1b, 0x70, 0x44, 0x1e,
+	0x65, 0x91, 0x6e, 0x2a, 0x79, 0x22, 0xda, 0x64
+};
+
+static const struct chacha20poly1305_testvec
+chacha20poly1305_dec_vectors[] __initconst = {
+	{ dec_input001, dec_output001, dec_assoc001, dec_nonce001, dec_key001,
+	  sizeof(dec_input001), sizeof(dec_assoc001), sizeof(dec_nonce001) },
+	{ dec_input002, dec_output002, dec_assoc002, dec_nonce002, dec_key002,
+	  sizeof(dec_input002), sizeof(dec_assoc002), sizeof(dec_nonce002) },
+	{ dec_input003, dec_output003, dec_assoc003, dec_nonce003, dec_key003,
+	  sizeof(dec_input003), sizeof(dec_assoc003), sizeof(dec_nonce003) },
+	{ dec_input004, dec_output004, dec_assoc004, dec_nonce004, dec_key004,
+	  sizeof(dec_input004), sizeof(dec_assoc004), sizeof(dec_nonce004) },
+	{ dec_input005, dec_output005, dec_assoc005, dec_nonce005, dec_key005,
+	  sizeof(dec_input005), sizeof(dec_assoc005), sizeof(dec_nonce005) },
+	{ dec_input006, dec_output006, dec_assoc006, dec_nonce006, dec_key006,
+	  sizeof(dec_input006), sizeof(dec_assoc006), sizeof(dec_nonce006) },
+	{ dec_input007, dec_output007, dec_assoc007, dec_nonce007, dec_key007,
+	  sizeof(dec_input007), sizeof(dec_assoc007), sizeof(dec_nonce007) },
+	{ dec_input008, dec_output008, dec_assoc008, dec_nonce008, dec_key008,
+	  sizeof(dec_input008), sizeof(dec_assoc008), sizeof(dec_nonce008) },
+	{ dec_input009, dec_output009, dec_assoc009, dec_nonce009, dec_key009,
+	  sizeof(dec_input009), sizeof(dec_assoc009), sizeof(dec_nonce009) },
+	{ dec_input010, dec_output010, dec_assoc010, dec_nonce010, dec_key010,
+	  sizeof(dec_input010), sizeof(dec_assoc010), sizeof(dec_nonce010) },
+	{ dec_input011, dec_output011, dec_assoc011, dec_nonce011, dec_key011,
+	  sizeof(dec_input011), sizeof(dec_assoc011), sizeof(dec_nonce011) },
+	{ dec_input012, dec_output012, dec_assoc012, dec_nonce012, dec_key012,
+	  sizeof(dec_input012), sizeof(dec_assoc012), sizeof(dec_nonce012) },
+	{ dec_input013, dec_output013, dec_assoc013, dec_nonce013, dec_key013,
+	  sizeof(dec_input013), sizeof(dec_assoc013), sizeof(dec_nonce013),
+	  true }
+};
+
+static const u8 xenc_input001[] __initconst = {
+	0x49, 0x6e, 0x74, 0x65, 0x72, 0x6e, 0x65, 0x74,
+	0x2d, 0x44, 0x72, 0x61, 0x66, 0x74, 0x73, 0x20,
+	0x61, 0x72, 0x65, 0x20, 0x64, 0x72, 0x61, 0x66,
+	0x74, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65,
+	0x6e, 0x74, 0x73, 0x20, 0x76, 0x61, 0x6c, 0x69,
+	0x64, 0x20, 0x66, 0x6f, 0x72, 0x20, 0x61, 0x20,
+	0x6d, 0x61, 0x78, 0x69, 0x6d, 0x75, 0x6d, 0x20,
+	0x6f, 0x66, 0x20, 0x73, 0x69, 0x78, 0x20, 0x6d,
+	0x6f, 0x6e, 0x74, 0x68, 0x73, 0x20, 0x61, 0x6e,
+	0x64, 0x20, 0x6d, 0x61, 0x79, 0x20, 0x62, 0x65,
+	0x20, 0x75, 0x70, 0x64, 0x61, 0x74, 0x65, 0x64,
+	0x2c, 0x20, 0x72, 0x65, 0x70, 0x6c, 0x61, 0x63,
+	0x65, 0x64, 0x2c, 0x20, 0x6f, 0x72, 0x20, 0x6f,
+	0x62, 0x73, 0x6f, 0x6c, 0x65, 0x74, 0x65, 0x64,
+	0x20, 0x62, 0x79, 0x20, 0x6f, 0x74, 0x68, 0x65,
+	0x72, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65,
+	0x6e, 0x74, 0x73, 0x20, 0x61, 0x74, 0x20, 0x61,
+	0x6e, 0x79, 0x20, 0x74, 0x69, 0x6d, 0x65, 0x2e,
+	0x20, 0x49, 0x74, 0x20, 0x69, 0x73, 0x20, 0x69,
+	0x6e, 0x61, 0x70, 0x70, 0x72, 0x6f, 0x70, 0x72,
+	0x69, 0x61, 0x74, 0x65, 0x20, 0x74, 0x6f, 0x20,
+	0x75, 0x73, 0x65, 0x20, 0x49, 0x6e, 0x74, 0x65,
+	0x72, 0x6e, 0x65, 0x74, 0x2d, 0x44, 0x72, 0x61,
+	0x66, 0x74, 0x73, 0x20, 0x61, 0x73, 0x20, 0x72,
+	0x65, 0x66, 0x65, 0x72, 0x65, 0x6e, 0x63, 0x65,
+	0x20, 0x6d, 0x61, 0x74, 0x65, 0x72, 0x69, 0x61,
+	0x6c, 0x20, 0x6f, 0x72, 0x20, 0x74, 0x6f, 0x20,
+	0x63, 0x69, 0x74, 0x65, 0x20, 0x74, 0x68, 0x65,
+	0x6d, 0x20, 0x6f, 0x74, 0x68, 0x65, 0x72, 0x20,
+	0x74, 0x68, 0x61, 0x6e, 0x20, 0x61, 0x73, 0x20,
+	0x2f, 0xe2, 0x80, 0x9c, 0x77, 0x6f, 0x72, 0x6b,
+	0x20, 0x69, 0x6e, 0x20, 0x70, 0x72, 0x6f, 0x67,
+	0x72, 0x65, 0x73, 0x73, 0x2e, 0x2f, 0xe2, 0x80,
+	0x9d
+};
+static const u8 xenc_output001[] __initconst = {
+	0x1a, 0x6e, 0x3a, 0xd9, 0xfd, 0x41, 0x3f, 0x77,
+	0x54, 0x72, 0x0a, 0x70, 0x9a, 0xa0, 0x29, 0x92,
+	0x2e, 0xed, 0x93, 0xcf, 0x0f, 0x71, 0x88, 0x18,
+	0x7a, 0x9d, 0x2d, 0x24, 0xe0, 0xf5, 0xea, 0x3d,
+	0x55, 0x64, 0xd7, 0xad, 0x2a, 0x1a, 0x1f, 0x7e,
+	0x86, 0x6d, 0xb0, 0xce, 0x80, 0x41, 0x72, 0x86,
+	0x26, 0xee, 0x84, 0xd7, 0xef, 0x82, 0x9e, 0xe2,
+	0x60, 0x9d, 0x5a, 0xfc, 0xf0, 0xe4, 0x19, 0x85,
+	0xea, 0x09, 0xc6, 0xfb, 0xb3, 0xa9, 0x50, 0x09,
+	0xec, 0x5e, 0x11, 0x90, 0xa1, 0xc5, 0x4e, 0x49,
+	0xef, 0x50, 0xd8, 0x8f, 0xe0, 0x78, 0xd7, 0xfd,
+	0xb9, 0x3b, 0xc9, 0xf2, 0x91, 0xc8, 0x25, 0xc8,
+	0xa7, 0x63, 0x60, 0xce, 0x10, 0xcd, 0xc6, 0x7f,
+	0xf8, 0x16, 0xf8, 0xe1, 0x0a, 0xd9, 0xde, 0x79,
+	0x50, 0x33, 0xf2, 0x16, 0x0f, 0x17, 0xba, 0xb8,
+	0x5d, 0xd8, 0xdf, 0x4e, 0x51, 0xa8, 0x39, 0xd0,
+	0x85, 0xca, 0x46, 0x6a, 0x10, 0xa7, 0xa3, 0x88,
+	0xef, 0x79, 0xb9, 0xf8, 0x24, 0xf3, 0xe0, 0x71,
+	0x7b, 0x76, 0x28, 0x46, 0x3a, 0x3a, 0x1b, 0x91,
+	0xb6, 0xd4, 0x3e, 0x23, 0xe5, 0x44, 0x15, 0xbf,
+	0x60, 0x43, 0x9d, 0xa4, 0xbb, 0xd5, 0x5f, 0x89,
+	0xeb, 0xef, 0x8e, 0xfd, 0xdd, 0xb4, 0x0d, 0x46,
+	0xf0, 0x69, 0x23, 0x63, 0xae, 0x94, 0xf5, 0x5e,
+	0xa5, 0xad, 0x13, 0x1c, 0x41, 0x76, 0xe6, 0x90,
+	0xd6, 0x6d, 0xa2, 0x8f, 0x97, 0x4c, 0xa8, 0x0b,
+	0xcf, 0x8d, 0x43, 0x2b, 0x9c, 0x9b, 0xc5, 0x58,
+	0xa5, 0xb6, 0x95, 0x9a, 0xbf, 0x81, 0xc6, 0x54,
+	0xc9, 0x66, 0x0c, 0xe5, 0x4f, 0x6a, 0x53, 0xa1,
+	0xe5, 0x0c, 0xba, 0x31, 0xde, 0x34, 0x64, 0x73,
+	0x8a, 0x3b, 0xbd, 0x92, 0x01, 0xdb, 0x71, 0x69,
+	0xf3, 0x58, 0x99, 0xbc, 0xd1, 0xcb, 0x4a, 0x05,
+	0xe2, 0x58, 0x9c, 0x25, 0x17, 0xcd, 0xdc, 0x83,
+	0xb7, 0xff, 0xfb, 0x09, 0x61, 0xad, 0xbf, 0x13,
+	0x5b, 0x5e, 0xed, 0x46, 0x82, 0x6f, 0x22, 0xd8,
+	0x93, 0xa6, 0x85, 0x5b, 0x40, 0x39, 0x5c, 0xc5,
+	0x9c
+};
+static const u8 xenc_assoc001[] __initconst = {
+	0xf3, 0x33, 0x88, 0x86, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x4e, 0x91
+};
+static const u8 xenc_nonce001[] __initconst = {
+	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
+	0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
+	0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17
+};
+static const u8 xenc_key001[] __initconst = {
+	0x1c, 0x92, 0x40, 0xa5, 0xeb, 0x55, 0xd3, 0x8a,
+	0xf3, 0x33, 0x88, 0x86, 0x04, 0xf6, 0xb5, 0xf0,
+	0x47, 0x39, 0x17, 0xc1, 0x40, 0x2b, 0x80, 0x09,
+	0x9d, 0xca, 0x5c, 0xbc, 0x20, 0x70, 0x75, 0xc0
+};
+
+static const struct chacha20poly1305_testvec
+xchacha20poly1305_enc_vectors[] __initconst = {
+	{ xenc_input001, xenc_output001, xenc_assoc001, xenc_nonce001, xenc_key001,
+	  sizeof(xenc_input001), sizeof(xenc_assoc001), sizeof(xenc_nonce001) }
+};
+
+static const u8 xdec_input001[] __initconst = {
+	0x1a, 0x6e, 0x3a, 0xd9, 0xfd, 0x41, 0x3f, 0x77,
+	0x54, 0x72, 0x0a, 0x70, 0x9a, 0xa0, 0x29, 0x92,
+	0x2e, 0xed, 0x93, 0xcf, 0x0f, 0x71, 0x88, 0x18,
+	0x7a, 0x9d, 0x2d, 0x24, 0xe0, 0xf5, 0xea, 0x3d,
+	0x55, 0x64, 0xd7, 0xad, 0x2a, 0x1a, 0x1f, 0x7e,
+	0x86, 0x6d, 0xb0, 0xce, 0x80, 0x41, 0x72, 0x86,
+	0x26, 0xee, 0x84, 0xd7, 0xef, 0x82, 0x9e, 0xe2,
+	0x60, 0x9d, 0x5a, 0xfc, 0xf0, 0xe4, 0x19, 0x85,
+	0xea, 0x09, 0xc6, 0xfb, 0xb3, 0xa9, 0x50, 0x09,
+	0xec, 0x5e, 0x11, 0x90, 0xa1, 0xc5, 0x4e, 0x49,
+	0xef, 0x50, 0xd8, 0x8f, 0xe0, 0x78, 0xd7, 0xfd,
+	0xb9, 0x3b, 0xc9, 0xf2, 0x91, 0xc8, 0x25, 0xc8,
+	0xa7, 0x63, 0x60, 0xce, 0x10, 0xcd, 0xc6, 0x7f,
+	0xf8, 0x16, 0xf8, 0xe1, 0x0a, 0xd9, 0xde, 0x79,
+	0x50, 0x33, 0xf2, 0x16, 0x0f, 0x17, 0xba, 0xb8,
+	0x5d, 0xd8, 0xdf, 0x4e, 0x51, 0xa8, 0x39, 0xd0,
+	0x85, 0xca, 0x46, 0x6a, 0x10, 0xa7, 0xa3, 0x88,
+	0xef, 0x79, 0xb9, 0xf8, 0x24, 0xf3, 0xe0, 0x71,
+	0x7b, 0x76, 0x28, 0x46, 0x3a, 0x3a, 0x1b, 0x91,
+	0xb6, 0xd4, 0x3e, 0x23, 0xe5, 0x44, 0x15, 0xbf,
+	0x60, 0x43, 0x9d, 0xa4, 0xbb, 0xd5, 0x5f, 0x89,
+	0xeb, 0xef, 0x8e, 0xfd, 0xdd, 0xb4, 0x0d, 0x46,
+	0xf0, 0x69, 0x23, 0x63, 0xae, 0x94, 0xf5, 0x5e,
+	0xa5, 0xad, 0x13, 0x1c, 0x41, 0x76, 0xe6, 0x90,
+	0xd6, 0x6d, 0xa2, 0x8f, 0x97, 0x4c, 0xa8, 0x0b,
+	0xcf, 0x8d, 0x43, 0x2b, 0x9c, 0x9b, 0xc5, 0x58,
+	0xa5, 0xb6, 0x95, 0x9a, 0xbf, 0x81, 0xc6, 0x54,
+	0xc9, 0x66, 0x0c, 0xe5, 0x4f, 0x6a, 0x53, 0xa1,
+	0xe5, 0x0c, 0xba, 0x31, 0xde, 0x34, 0x64, 0x73,
+	0x8a, 0x3b, 0xbd, 0x92, 0x01, 0xdb, 0x71, 0x69,
+	0xf3, 0x58, 0x99, 0xbc, 0xd1, 0xcb, 0x4a, 0x05,
+	0xe2, 0x58, 0x9c, 0x25, 0x17, 0xcd, 0xdc, 0x83,
+	0xb7, 0xff, 0xfb, 0x09, 0x61, 0xad, 0xbf, 0x13,
+	0x5b, 0x5e, 0xed, 0x46, 0x82, 0x6f, 0x22, 0xd8,
+	0x93, 0xa6, 0x85, 0x5b, 0x40, 0x39, 0x5c, 0xc5,
+	0x9c
+};
+static const u8 xdec_output001[] __initconst = {
+	0x49, 0x6e, 0x74, 0x65, 0x72, 0x6e, 0x65, 0x74,
+	0x2d, 0x44, 0x72, 0x61, 0x66, 0x74, 0x73, 0x20,
+	0x61, 0x72, 0x65, 0x20, 0x64, 0x72, 0x61, 0x66,
+	0x74, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65,
+	0x6e, 0x74, 0x73, 0x20, 0x76, 0x61, 0x6c, 0x69,
+	0x64, 0x20, 0x66, 0x6f, 0x72, 0x20, 0x61, 0x20,
+	0x6d, 0x61, 0x78, 0x69, 0x6d, 0x75, 0x6d, 0x20,
+	0x6f, 0x66, 0x20, 0x73, 0x69, 0x78, 0x20, 0x6d,
+	0x6f, 0x6e, 0x74, 0x68, 0x73, 0x20, 0x61, 0x6e,
+	0x64, 0x20, 0x6d, 0x61, 0x79, 0x20, 0x62, 0x65,
+	0x20, 0x75, 0x70, 0x64, 0x61, 0x74, 0x65, 0x64,
+	0x2c, 0x20, 0x72, 0x65, 0x70, 0x6c, 0x61, 0x63,
+	0x65, 0x64, 0x2c, 0x20, 0x6f, 0x72, 0x20, 0x6f,
+	0x62, 0x73, 0x6f, 0x6c, 0x65, 0x74, 0x65, 0x64,
+	0x20, 0x62, 0x79, 0x20, 0x6f, 0x74, 0x68, 0x65,
+	0x72, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65,
+	0x6e, 0x74, 0x73, 0x20, 0x61, 0x74, 0x20, 0x61,
+	0x6e, 0x79, 0x20, 0x74, 0x69, 0x6d, 0x65, 0x2e,
+	0x20, 0x49, 0x74, 0x20, 0x69, 0x73, 0x20, 0x69,
+	0x6e, 0x61, 0x70, 0x70, 0x72, 0x6f, 0x70, 0x72,
+	0x69, 0x61, 0x74, 0x65, 0x20, 0x74, 0x6f, 0x20,
+	0x75, 0x73, 0x65, 0x20, 0x49, 0x6e, 0x74, 0x65,
+	0x72, 0x6e, 0x65, 0x74, 0x2d, 0x44, 0x72, 0x61,
+	0x66, 0x74, 0x73, 0x20, 0x61, 0x73, 0x20, 0x72,
+	0x65, 0x66, 0x65, 0x72, 0x65, 0x6e, 0x63, 0x65,
+	0x20, 0x6d, 0x61, 0x74, 0x65, 0x72, 0x69, 0x61,
+	0x6c, 0x20, 0x6f, 0x72, 0x20, 0x74, 0x6f, 0x20,
+	0x63, 0x69, 0x74, 0x65, 0x20, 0x74, 0x68, 0x65,
+	0x6d, 0x20, 0x6f, 0x74, 0x68, 0x65, 0x72, 0x20,
+	0x74, 0x68, 0x61, 0x6e, 0x20, 0x61, 0x73, 0x20,
+	0x2f, 0xe2, 0x80, 0x9c, 0x77, 0x6f, 0x72, 0x6b,
+	0x20, 0x69, 0x6e, 0x20, 0x70, 0x72, 0x6f, 0x67,
+	0x72, 0x65, 0x73, 0x73, 0x2e, 0x2f, 0xe2, 0x80,
+	0x9d
+};
+static const u8 xdec_assoc001[] __initconst = {
+	0xf3, 0x33, 0x88, 0x86, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x4e, 0x91
+};
+static const u8 xdec_nonce001[] __initconst = {
+	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
+	0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
+	0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17
+};
+static const u8 xdec_key001[] __initconst = {
+	0x1c, 0x92, 0x40, 0xa5, 0xeb, 0x55, 0xd3, 0x8a,
+	0xf3, 0x33, 0x88, 0x86, 0x04, 0xf6, 0xb5, 0xf0,
+	0x47, 0x39, 0x17, 0xc1, 0x40, 0x2b, 0x80, 0x09,
+	0x9d, 0xca, 0x5c, 0xbc, 0x20, 0x70, 0x75, 0xc0
+};
+
+static const struct chacha20poly1305_testvec
+xchacha20poly1305_dec_vectors[] __initconst = {
+	{ xdec_input001, xdec_output001, xdec_assoc001, xdec_nonce001, xdec_key001,
+	  sizeof(xdec_input001), sizeof(xdec_assoc001), sizeof(xdec_nonce001) }
+};
+
+static void __init
+chacha20poly1305_selftest_encrypt(u8 *dst, const u8 *src, const size_t src_len,
+				  const u8 *ad, const size_t ad_len,
+				  const u8 *nonce, const size_t nonce_len,
+				  const u8 key[CHACHA20POLY1305_KEY_SIZE])
+{
+	if (nonce_len == 8)
+		chacha20poly1305_encrypt(dst, src, src_len, ad, ad_len,
+					 get_unaligned_le64(nonce), key);
+	else
+		BUG();
+}
+
+static bool __init
+decryption_success(bool func_ret, bool expect_failure, int memcmp_result)
+{
+	if (expect_failure)
+		return !func_ret;
+	return func_ret && !memcmp_result;
+}
+
+bool __init chacha20poly1305_selftest(void)
+{
+	enum { MAXIMUM_TEST_BUFFER_LEN = 1UL << 12 };
+	size_t i;
+	u8 *computed_output = NULL, *heap_src = NULL;
+	struct scatterlist sg_src;
+	bool success = true, ret;
+
+	heap_src = kmalloc(MAXIMUM_TEST_BUFFER_LEN, GFP_KERNEL);
+	computed_output = kmalloc(MAXIMUM_TEST_BUFFER_LEN, GFP_KERNEL);
+	if (!heap_src || !computed_output) {
+		pr_err("chacha20poly1305 self-test malloc: FAIL\n");
+		success = false;
+		goto out;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(chacha20poly1305_enc_vectors); ++i) {
+		memset(computed_output, 0, MAXIMUM_TEST_BUFFER_LEN);
+		chacha20poly1305_selftest_encrypt(computed_output,
+					chacha20poly1305_enc_vectors[i].input,
+					chacha20poly1305_enc_vectors[i].ilen,
+					chacha20poly1305_enc_vectors[i].assoc,
+					chacha20poly1305_enc_vectors[i].alen,
+					chacha20poly1305_enc_vectors[i].nonce,
+					chacha20poly1305_enc_vectors[i].nlen,
+					chacha20poly1305_enc_vectors[i].key);
+		if (memcmp(computed_output,
+			   chacha20poly1305_enc_vectors[i].output,
+			   chacha20poly1305_enc_vectors[i].ilen +
+							POLY1305_DIGEST_SIZE)) {
+			pr_err("chacha20poly1305 encryption self-test %zu: FAIL\n",
+			       i + 1);
+			success = false;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(chacha20poly1305_enc_vectors); ++i) {
+		if (chacha20poly1305_enc_vectors[i].nlen != 8)
+			continue;
+		memcpy(heap_src, chacha20poly1305_enc_vectors[i].input,
+		       chacha20poly1305_enc_vectors[i].ilen);
+		sg_init_one(&sg_src, heap_src,
+			    chacha20poly1305_enc_vectors[i].ilen + POLY1305_DIGEST_SIZE);
+		chacha20poly1305_encrypt_sg_inplace(&sg_src,
+			chacha20poly1305_enc_vectors[i].ilen,
+			chacha20poly1305_enc_vectors[i].assoc,
+			chacha20poly1305_enc_vectors[i].alen,
+			get_unaligned_le64(chacha20poly1305_enc_vectors[i].nonce),
+			chacha20poly1305_enc_vectors[i].key);
+		if (memcmp(heap_src,
+				   chacha20poly1305_enc_vectors[i].output,
+				   chacha20poly1305_enc_vectors[i].ilen +
+							POLY1305_DIGEST_SIZE)) {
+			pr_err("chacha20poly1305 sg encryption self-test %zu: FAIL\n",
+			       i + 1);
+			success = false;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(chacha20poly1305_dec_vectors); ++i) {
+		memset(computed_output, 0, MAXIMUM_TEST_BUFFER_LEN);
+		ret = chacha20poly1305_decrypt(computed_output,
+			chacha20poly1305_dec_vectors[i].input,
+			chacha20poly1305_dec_vectors[i].ilen,
+			chacha20poly1305_dec_vectors[i].assoc,
+			chacha20poly1305_dec_vectors[i].alen,
+			get_unaligned_le64(chacha20poly1305_dec_vectors[i].nonce),
+			chacha20poly1305_dec_vectors[i].key);
+		if (!decryption_success(ret,
+				chacha20poly1305_dec_vectors[i].failure,
+				memcmp(computed_output,
+				       chacha20poly1305_dec_vectors[i].output,
+				       chacha20poly1305_dec_vectors[i].ilen -
+							POLY1305_DIGEST_SIZE))) {
+			pr_err("chacha20poly1305 decryption self-test %zu: FAIL\n",
+			       i + 1);
+			success = false;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(chacha20poly1305_dec_vectors); ++i) {
+		memcpy(heap_src, chacha20poly1305_dec_vectors[i].input,
+		       chacha20poly1305_dec_vectors[i].ilen);
+		sg_init_one(&sg_src, heap_src,
+			    chacha20poly1305_dec_vectors[i].ilen);
+		ret = chacha20poly1305_decrypt_sg_inplace(&sg_src,
+			chacha20poly1305_dec_vectors[i].ilen,
+			chacha20poly1305_dec_vectors[i].assoc,
+			chacha20poly1305_dec_vectors[i].alen,
+			get_unaligned_le64(chacha20poly1305_dec_vectors[i].nonce),
+			chacha20poly1305_dec_vectors[i].key);
+		if (!decryption_success(ret,
+			chacha20poly1305_dec_vectors[i].failure,
+			memcmp(heap_src, chacha20poly1305_dec_vectors[i].output,
+			       chacha20poly1305_dec_vectors[i].ilen -
+							POLY1305_DIGEST_SIZE))) {
+			pr_err("chacha20poly1305 sg decryption self-test %zu: FAIL\n",
+			       i + 1);
+			success = false;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(xchacha20poly1305_enc_vectors); ++i) {
+		memset(computed_output, 0, MAXIMUM_TEST_BUFFER_LEN);
+		xchacha20poly1305_encrypt(computed_output,
+					xchacha20poly1305_enc_vectors[i].input,
+					xchacha20poly1305_enc_vectors[i].ilen,
+					xchacha20poly1305_enc_vectors[i].assoc,
+					xchacha20poly1305_enc_vectors[i].alen,
+					xchacha20poly1305_enc_vectors[i].nonce,
+					xchacha20poly1305_enc_vectors[i].key);
+		if (memcmp(computed_output,
+			   xchacha20poly1305_enc_vectors[i].output,
+			   xchacha20poly1305_enc_vectors[i].ilen +
+							POLY1305_DIGEST_SIZE)) {
+			pr_err("xchacha20poly1305 encryption self-test %zu: FAIL\n",
+			       i + 1);
+			success = false;
+		}
+	}
+	for (i = 0; i < ARRAY_SIZE(xchacha20poly1305_dec_vectors); ++i) {
+		memset(computed_output, 0, MAXIMUM_TEST_BUFFER_LEN);
+		ret = xchacha20poly1305_decrypt(computed_output,
+					xchacha20poly1305_dec_vectors[i].input,
+					xchacha20poly1305_dec_vectors[i].ilen,
+					xchacha20poly1305_dec_vectors[i].assoc,
+					xchacha20poly1305_dec_vectors[i].alen,
+					xchacha20poly1305_dec_vectors[i].nonce,
+					xchacha20poly1305_dec_vectors[i].key);
+		if (!decryption_success(ret,
+				xchacha20poly1305_dec_vectors[i].failure,
+				memcmp(computed_output,
+				       xchacha20poly1305_dec_vectors[i].output,
+				       xchacha20poly1305_dec_vectors[i].ilen -
+							POLY1305_DIGEST_SIZE))) {
+			pr_err("xchacha20poly1305 decryption self-test %zu: FAIL\n",
+			       i + 1);
+			success = false;
+		}
+	}
+
+out:
+	kfree(heap_src);
+	kfree(computed_output);
+	return success;
+}
diff --git a/lib/crypto/chacha20poly1305.c b/lib/crypto/chacha20poly1305.c
new file mode 100644
index 000000000000..6d83cafebc69
--- /dev/null
+++ b/lib/crypto/chacha20poly1305.c
@@ -0,0 +1,369 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This is an implementation of the ChaCha20Poly1305 AEAD construction.
+ *
+ * Information: https://tools.ietf.org/html/rfc8439
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/chacha20poly1305.h>
+#include <crypto/chacha.h>
+#include <crypto/poly1305.h>
+#include <crypto/scatterwalk.h>
+
+#include <asm/unaligned.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+
+#define CHACHA_KEY_WORDS	(CHACHA_KEY_SIZE / sizeof(u32))
+
+bool __init chacha20poly1305_selftest(void);
+
+static void chacha_load_key(u32 *k, const u8 *in)
+{
+	k[0] = get_unaligned_le32(in);
+	k[1] = get_unaligned_le32(in + 4);
+	k[2] = get_unaligned_le32(in + 8);
+	k[3] = get_unaligned_le32(in + 12);
+	k[4] = get_unaligned_le32(in + 16);
+	k[5] = get_unaligned_le32(in + 20);
+	k[6] = get_unaligned_le32(in + 24);
+	k[7] = get_unaligned_le32(in + 28);
+}
+
+static void xchacha_init(u32 *chacha_state, const u8 *key, const u8 *nonce)
+{
+	u32 k[CHACHA_KEY_WORDS];
+	u8 iv[CHACHA_IV_SIZE];
+
+	memset(iv, 0, 8);
+	memcpy(iv + 8, nonce + 16, 8);
+
+	chacha_load_key(k, key);
+
+	/* Compute the subkey given the original key and first 128 nonce bits */
+	chacha_init(chacha_state, k, nonce);
+	hchacha_block(chacha_state, k, 20);
+
+	chacha_init(chacha_state, k, iv);
+
+	memzero_explicit(k, sizeof(k));
+	memzero_explicit(iv, sizeof(iv));
+}
+
+static void
+__chacha20poly1305_encrypt(u8 *dst, const u8 *src, const size_t src_len,
+			   const u8 *ad, const size_t ad_len, u32 *chacha_state)
+{
+	const u8 *pad0 = page_address(ZERO_PAGE(0));
+	struct poly1305_desc_ctx poly1305_state;
+	union {
+		u8 block0[POLY1305_KEY_SIZE];
+		__le64 lens[2];
+	} b;
+
+	chacha20_crypt(chacha_state, b.block0, pad0, sizeof(b.block0));
+	poly1305_init(&poly1305_state, b.block0);
+
+	poly1305_update(&poly1305_state, ad, ad_len);
+	if (ad_len & 0xf)
+		poly1305_update(&poly1305_state, pad0, 0x10 - (ad_len & 0xf));
+
+	chacha20_crypt(chacha_state, dst, src, src_len);
+
+	poly1305_update(&poly1305_state, dst, src_len);
+	if (src_len & 0xf)
+		poly1305_update(&poly1305_state, pad0, 0x10 - (src_len & 0xf));
+
+	b.lens[0] = cpu_to_le64(ad_len);
+	b.lens[1] = cpu_to_le64(src_len);
+	poly1305_update(&poly1305_state, (u8 *)b.lens, sizeof(b.lens));
+
+	poly1305_final(&poly1305_state, dst + src_len);
+
+	memzero_explicit(chacha_state, CHACHA_STATE_WORDS * sizeof(u32));
+	memzero_explicit(&b, sizeof(b));
+}
+
+void chacha20poly1305_encrypt(u8 *dst, const u8 *src, const size_t src_len,
+			      const u8 *ad, const size_t ad_len,
+			      const u64 nonce,
+			      const u8 key[CHACHA20POLY1305_KEY_SIZE])
+{
+	u32 chacha_state[CHACHA_STATE_WORDS];
+	u32 k[CHACHA_KEY_WORDS];
+	__le64 iv[2];
+
+	chacha_load_key(k, key);
+
+	iv[0] = 0;
+	iv[1] = cpu_to_le64(nonce);
+
+	chacha_init(chacha_state, k, (u8 *)iv);
+	__chacha20poly1305_encrypt(dst, src, src_len, ad, ad_len, chacha_state);
+
+	memzero_explicit(iv, sizeof(iv));
+	memzero_explicit(k, sizeof(k));
+}
+EXPORT_SYMBOL(chacha20poly1305_encrypt);
+
+void xchacha20poly1305_encrypt(u8 *dst, const u8 *src, const size_t src_len,
+			       const u8 *ad, const size_t ad_len,
+			       const u8 nonce[XCHACHA20POLY1305_NONCE_SIZE],
+			       const u8 key[CHACHA20POLY1305_KEY_SIZE])
+{
+	u32 chacha_state[CHACHA_STATE_WORDS];
+
+	xchacha_init(chacha_state, key, nonce);
+	__chacha20poly1305_encrypt(dst, src, src_len, ad, ad_len, chacha_state);
+}
+EXPORT_SYMBOL(xchacha20poly1305_encrypt);
+
+static bool
+__chacha20poly1305_decrypt(u8 *dst, const u8 *src, const size_t src_len,
+			   const u8 *ad, const size_t ad_len, u32 *chacha_state)
+{
+	const u8 *pad0 = page_address(ZERO_PAGE(0));
+	struct poly1305_desc_ctx poly1305_state;
+	size_t dst_len;
+	int ret;
+	union {
+		u8 block0[POLY1305_KEY_SIZE];
+		u8 mac[POLY1305_DIGEST_SIZE];
+		__le64 lens[2];
+	} b;
+
+	if (unlikely(src_len < POLY1305_DIGEST_SIZE))
+		return false;
+
+	chacha20_crypt(chacha_state, b.block0, pad0, sizeof(b.block0));
+	poly1305_init(&poly1305_state, b.block0);
+
+	poly1305_update(&poly1305_state, ad, ad_len);
+	if (ad_len & 0xf)
+		poly1305_update(&poly1305_state, pad0, 0x10 - (ad_len & 0xf));
+
+	dst_len = src_len - POLY1305_DIGEST_SIZE;
+	poly1305_update(&poly1305_state, src, dst_len);
+	if (dst_len & 0xf)
+		poly1305_update(&poly1305_state, pad0, 0x10 - (dst_len & 0xf));
+
+	b.lens[0] = cpu_to_le64(ad_len);
+	b.lens[1] = cpu_to_le64(dst_len);
+	poly1305_update(&poly1305_state, (u8 *)b.lens, sizeof(b.lens));
+
+	poly1305_final(&poly1305_state, b.mac);
+
+	ret = crypto_memneq(b.mac, src + dst_len, POLY1305_DIGEST_SIZE);
+	if (likely(!ret))
+		chacha20_crypt(chacha_state, dst, src, dst_len);
+
+	memzero_explicit(&b, sizeof(b));
+
+	return !ret;
+}
+
+bool chacha20poly1305_decrypt(u8 *dst, const u8 *src, const size_t src_len,
+			      const u8 *ad, const size_t ad_len,
+			      const u64 nonce,
+			      const u8 key[CHACHA20POLY1305_KEY_SIZE])
+{
+	u32 chacha_state[CHACHA_STATE_WORDS];
+	u32 k[CHACHA_KEY_WORDS];
+	__le64 iv[2];
+	bool ret;
+
+	chacha_load_key(k, key);
+
+	iv[0] = 0;
+	iv[1] = cpu_to_le64(nonce);
+
+	chacha_init(chacha_state, k, (u8 *)iv);
+	ret = __chacha20poly1305_decrypt(dst, src, src_len, ad, ad_len,
+					 chacha_state);
+
+	memzero_explicit(chacha_state, sizeof(chacha_state));
+	memzero_explicit(iv, sizeof(iv));
+	memzero_explicit(k, sizeof(k));
+	return ret;
+}
+EXPORT_SYMBOL(chacha20poly1305_decrypt);
+
+bool xchacha20poly1305_decrypt(u8 *dst, const u8 *src, const size_t src_len,
+			       const u8 *ad, const size_t ad_len,
+			       const u8 nonce[XCHACHA20POLY1305_NONCE_SIZE],
+			       const u8 key[CHACHA20POLY1305_KEY_SIZE])
+{
+	u32 chacha_state[CHACHA_STATE_WORDS];
+
+	xchacha_init(chacha_state, key, nonce);
+	return __chacha20poly1305_decrypt(dst, src, src_len, ad, ad_len,
+					  chacha_state);
+}
+EXPORT_SYMBOL(xchacha20poly1305_decrypt);
+
+static
+bool chacha20poly1305_crypt_sg_inplace(struct scatterlist *src,
+				       const size_t src_len,
+				       const u8 *ad, const size_t ad_len,
+				       const u64 nonce,
+				       const u8 key[CHACHA20POLY1305_KEY_SIZE],
+				       int encrypt)
+{
+	const u8 *pad0 = page_address(ZERO_PAGE(0));
+	struct poly1305_desc_ctx poly1305_state;
+	u32 chacha_state[CHACHA_STATE_WORDS];
+	struct sg_mapping_iter miter;
+	size_t partial = 0;
+	unsigned int flags;
+	bool ret = true;
+	int sl;
+	union {
+		struct {
+			u32 k[CHACHA_KEY_WORDS];
+			__le64 iv[2];
+		};
+		u8 block0[POLY1305_KEY_SIZE];
+		u8 chacha_stream[CHACHA_BLOCK_SIZE];
+		struct {
+			u8 mac[2][POLY1305_DIGEST_SIZE];
+		};
+		__le64 lens[2];
+	} b __aligned(16);
+
+	chacha_load_key(b.k, key);
+
+	b.iv[0] = 0;
+	b.iv[1] = cpu_to_le64(nonce);
+
+	chacha_init(chacha_state, b.k, (u8 *)b.iv);
+	chacha20_crypt(chacha_state, b.block0, pad0, sizeof(b.block0));
+	poly1305_init(&poly1305_state, b.block0);
+
+	if (unlikely(ad_len)) {
+		poly1305_update(&poly1305_state, ad, ad_len);
+		if (ad_len & 0xf)
+			poly1305_update(&poly1305_state, pad0, 0x10 - (ad_len & 0xf));
+	}
+
+	flags = SG_MITER_TO_SG;
+	if (!preemptible())
+		flags |= SG_MITER_ATOMIC;
+
+	sg_miter_start(&miter, src, sg_nents(src), flags);
+
+	for (sl = src_len; sl > 0 && sg_miter_next(&miter); sl -= miter.length) {
+		u8 *addr = miter.addr;
+		size_t length = min_t(size_t, sl, miter.length);
+
+		if (!encrypt)
+			poly1305_update(&poly1305_state, addr, length);
+
+		if (unlikely(partial)) {
+			size_t l = min(length, CHACHA_BLOCK_SIZE - partial);
+
+			crypto_xor(addr, b.chacha_stream + partial, l);
+			partial = (partial + l) & (CHACHA_BLOCK_SIZE - 1);
+
+			addr += l;
+			length -= l;
+		}
+
+		if (likely(length >= CHACHA_BLOCK_SIZE || length == sl)) {
+			size_t l = length;
+
+			if (unlikely(length < sl))
+				l &= ~(CHACHA_BLOCK_SIZE - 1);
+			chacha20_crypt(chacha_state, addr, addr, l);
+			addr += l;
+			length -= l;
+		}
+
+		if (unlikely(length > 0)) {
+			chacha20_crypt(chacha_state, b.chacha_stream, pad0,
+				       CHACHA_BLOCK_SIZE);
+			crypto_xor(addr, b.chacha_stream, length);
+			partial = length;
+		}
+
+		if (encrypt)
+			poly1305_update(&poly1305_state, miter.addr,
+					min_t(size_t, sl, miter.length));
+	}
+
+	if (src_len & 0xf)
+		poly1305_update(&poly1305_state, pad0, 0x10 - (src_len & 0xf));
+
+	b.lens[0] = cpu_to_le64(ad_len);
+	b.lens[1] = cpu_to_le64(src_len);
+	poly1305_update(&poly1305_state, (u8 *)b.lens, sizeof(b.lens));
+
+	if (likely(sl <= -POLY1305_DIGEST_SIZE)) {
+		if (encrypt) {
+			poly1305_final(&poly1305_state,
+				       miter.addr + miter.length + sl);
+			ret = true;
+		} else {
+			poly1305_final(&poly1305_state, b.mac[0]);
+			ret = !crypto_memneq(b.mac[0],
+					     miter.addr + miter.length + sl,
+					     POLY1305_DIGEST_SIZE);
+		}
+	}
+
+	sg_miter_stop(&miter);
+
+	if (unlikely(sl > -POLY1305_DIGEST_SIZE)) {
+		poly1305_final(&poly1305_state, b.mac[1]);
+		scatterwalk_map_and_copy(b.mac[encrypt], src, src_len,
+					 sizeof(b.mac[1]), encrypt);
+		ret = encrypt ||
+		      !crypto_memneq(b.mac[0], b.mac[1], POLY1305_DIGEST_SIZE);
+	}
+
+	memzero_explicit(chacha_state, sizeof(chacha_state));
+	memzero_explicit(&b, sizeof(b));
+
+	return ret;
+}
+
+bool chacha20poly1305_encrypt_sg_inplace(struct scatterlist *src, size_t src_len,
+					 const u8 *ad, const size_t ad_len,
+					 const u64 nonce,
+					 const u8 key[CHACHA20POLY1305_KEY_SIZE])
+{
+	return chacha20poly1305_crypt_sg_inplace(src, src_len, ad, ad_len,
+						 nonce, key, 1);
+}
+EXPORT_SYMBOL(chacha20poly1305_encrypt_sg_inplace);
+
+bool chacha20poly1305_decrypt_sg_inplace(struct scatterlist *src, size_t src_len,
+					 const u8 *ad, const size_t ad_len,
+					 const u64 nonce,
+					 const u8 key[CHACHA20POLY1305_KEY_SIZE])
+{
+	if (unlikely(src_len < POLY1305_DIGEST_SIZE))
+		return false;
+
+	return chacha20poly1305_crypt_sg_inplace(src,
+						 src_len - POLY1305_DIGEST_SIZE,
+						 ad, ad_len, nonce, key, 0);
+}
+EXPORT_SYMBOL(chacha20poly1305_decrypt_sg_inplace);
+
+static int __init mod_init(void)
+{
+	if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) &&
+	    WARN_ON(!chacha20poly1305_selftest()))
+		return -ENODEV;
+	return 0;
+}
+
+module_init(mod_init);
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("ChaCha20Poly1305 AEAD construction");
+MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
diff --git a/lib/crypto/curve25519-fiat32.c b/lib/crypto/curve25519-fiat32.c
new file mode 100644
index 000000000000..2fde0ec33dbd
--- /dev/null
+++ b/lib/crypto/curve25519-fiat32.c
@@ -0,0 +1,864 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2016 The fiat-crypto Authors.
+ * Copyright (C) 2018-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This is a machine-generated formally verified implementation of Curve25519
+ * ECDH from: <https://github.com/mit-plv/fiat-crypto>. Though originally
+ * machine generated, it has been tweaked to be suitable for use in the kernel.
+ * It is optimized for 32-bit machines and machines that cannot work efficiently
+ * with 128-bit integer types.
+ */
+
+#include <asm/unaligned.h>
+#include <crypto/curve25519.h>
+#include <linux/string.h>
+
+/* fe means field element. Here the field is \Z/(2^255-19). An element t,
+ * entries t[0]...t[9], represents the integer t[0]+2^26 t[1]+2^51 t[2]+2^77
+ * t[3]+2^102 t[4]+...+2^230 t[9].
+ * fe limbs are bounded by 1.125*2^26,1.125*2^25,1.125*2^26,1.125*2^25,etc.
+ * Multiplication and carrying produce fe from fe_loose.
+ */
+typedef struct fe { u32 v[10]; } fe;
+
+/* fe_loose limbs are bounded by 3.375*2^26,3.375*2^25,3.375*2^26,3.375*2^25,etc
+ * Addition and subtraction produce fe_loose from (fe, fe).
+ */
+typedef struct fe_loose { u32 v[10]; } fe_loose;
+
+static __always_inline void fe_frombytes_impl(u32 h[10], const u8 *s)
+{
+	/* Ignores top bit of s. */
+	u32 a0 = get_unaligned_le32(s);
+	u32 a1 = get_unaligned_le32(s+4);
+	u32 a2 = get_unaligned_le32(s+8);
+	u32 a3 = get_unaligned_le32(s+12);
+	u32 a4 = get_unaligned_le32(s+16);
+	u32 a5 = get_unaligned_le32(s+20);
+	u32 a6 = get_unaligned_le32(s+24);
+	u32 a7 = get_unaligned_le32(s+28);
+	h[0] = a0&((1<<26)-1);                    /* 26 used, 32-26 left.   26 */
+	h[1] = (a0>>26) | ((a1&((1<<19)-1))<< 6); /* (32-26) + 19 =  6+19 = 25 */
+	h[2] = (a1>>19) | ((a2&((1<<13)-1))<<13); /* (32-19) + 13 = 13+13 = 26 */
+	h[3] = (a2>>13) | ((a3&((1<< 6)-1))<<19); /* (32-13) +  6 = 19+ 6 = 25 */
+	h[4] = (a3>> 6);                          /* (32- 6)              = 26 */
+	h[5] = a4&((1<<25)-1);                    /*                        25 */
+	h[6] = (a4>>25) | ((a5&((1<<19)-1))<< 7); /* (32-25) + 19 =  7+19 = 26 */
+	h[7] = (a5>>19) | ((a6&((1<<12)-1))<<13); /* (32-19) + 12 = 13+12 = 25 */
+	h[8] = (a6>>12) | ((a7&((1<< 6)-1))<<20); /* (32-12) +  6 = 20+ 6 = 26 */
+	h[9] = (a7>> 6)&((1<<25)-1); /*                                     25 */
+}
+
+static __always_inline void fe_frombytes(fe *h, const u8 *s)
+{
+	fe_frombytes_impl(h->v, s);
+}
+
+static __always_inline u8 /*bool*/
+addcarryx_u25(u8 /*bool*/ c, u32 a, u32 b, u32 *low)
+{
+	/* This function extracts 25 bits of result and 1 bit of carry
+	 * (26 total), so a 32-bit intermediate is sufficient.
+	 */
+	u32 x = a + b + c;
+	*low = x & ((1 << 25) - 1);
+	return (x >> 25) & 1;
+}
+
+static __always_inline u8 /*bool*/
+addcarryx_u26(u8 /*bool*/ c, u32 a, u32 b, u32 *low)
+{
+	/* This function extracts 26 bits of result and 1 bit of carry
+	 * (27 total), so a 32-bit intermediate is sufficient.
+	 */
+	u32 x = a + b + c;
+	*low = x & ((1 << 26) - 1);
+	return (x >> 26) & 1;
+}
+
+static __always_inline u8 /*bool*/
+subborrow_u25(u8 /*bool*/ c, u32 a, u32 b, u32 *low)
+{
+	/* This function extracts 25 bits of result and 1 bit of borrow
+	 * (26 total), so a 32-bit intermediate is sufficient.
+	 */
+	u32 x = a - b - c;
+	*low = x & ((1 << 25) - 1);
+	return x >> 31;
+}
+
+static __always_inline u8 /*bool*/
+subborrow_u26(u8 /*bool*/ c, u32 a, u32 b, u32 *low)
+{
+	/* This function extracts 26 bits of result and 1 bit of borrow
+	 *(27 total), so a 32-bit intermediate is sufficient.
+	 */
+	u32 x = a - b - c;
+	*low = x & ((1 << 26) - 1);
+	return x >> 31;
+}
+
+static __always_inline u32 cmovznz32(u32 t, u32 z, u32 nz)
+{
+	t = -!!t; /* all set if nonzero, 0 if 0 */
+	return (t&nz) | ((~t)&z);
+}
+
+static __always_inline void fe_freeze(u32 out[10], const u32 in1[10])
+{
+	{ const u32 x17 = in1[9];
+	{ const u32 x18 = in1[8];
+	{ const u32 x16 = in1[7];
+	{ const u32 x14 = in1[6];
+	{ const u32 x12 = in1[5];
+	{ const u32 x10 = in1[4];
+	{ const u32 x8 = in1[3];
+	{ const u32 x6 = in1[2];
+	{ const u32 x4 = in1[1];
+	{ const u32 x2 = in1[0];
+	{ u32 x20; u8/*bool*/ x21 = subborrow_u26(0x0, x2, 0x3ffffed, &x20);
+	{ u32 x23; u8/*bool*/ x24 = subborrow_u25(x21, x4, 0x1ffffff, &x23);
+	{ u32 x26; u8/*bool*/ x27 = subborrow_u26(x24, x6, 0x3ffffff, &x26);
+	{ u32 x29; u8/*bool*/ x30 = subborrow_u25(x27, x8, 0x1ffffff, &x29);
+	{ u32 x32; u8/*bool*/ x33 = subborrow_u26(x30, x10, 0x3ffffff, &x32);
+	{ u32 x35; u8/*bool*/ x36 = subborrow_u25(x33, x12, 0x1ffffff, &x35);
+	{ u32 x38; u8/*bool*/ x39 = subborrow_u26(x36, x14, 0x3ffffff, &x38);
+	{ u32 x41; u8/*bool*/ x42 = subborrow_u25(x39, x16, 0x1ffffff, &x41);
+	{ u32 x44; u8/*bool*/ x45 = subborrow_u26(x42, x18, 0x3ffffff, &x44);
+	{ u32 x47; u8/*bool*/ x48 = subborrow_u25(x45, x17, 0x1ffffff, &x47);
+	{ u32 x49 = cmovznz32(x48, 0x0, 0xffffffff);
+	{ u32 x50 = (x49 & 0x3ffffed);
+	{ u32 x52; u8/*bool*/ x53 = addcarryx_u26(0x0, x20, x50, &x52);
+	{ u32 x54 = (x49 & 0x1ffffff);
+	{ u32 x56; u8/*bool*/ x57 = addcarryx_u25(x53, x23, x54, &x56);
+	{ u32 x58 = (x49 & 0x3ffffff);
+	{ u32 x60; u8/*bool*/ x61 = addcarryx_u26(x57, x26, x58, &x60);
+	{ u32 x62 = (x49 & 0x1ffffff);
+	{ u32 x64; u8/*bool*/ x65 = addcarryx_u25(x61, x29, x62, &x64);
+	{ u32 x66 = (x49 & 0x3ffffff);
+	{ u32 x68; u8/*bool*/ x69 = addcarryx_u26(x65, x32, x66, &x68);
+	{ u32 x70 = (x49 & 0x1ffffff);
+	{ u32 x72; u8/*bool*/ x73 = addcarryx_u25(x69, x35, x70, &x72);
+	{ u32 x74 = (x49 & 0x3ffffff);
+	{ u32 x76; u8/*bool*/ x77 = addcarryx_u26(x73, x38, x74, &x76);
+	{ u32 x78 = (x49 & 0x1ffffff);
+	{ u32 x80; u8/*bool*/ x81 = addcarryx_u25(x77, x41, x78, &x80);
+	{ u32 x82 = (x49 & 0x3ffffff);
+	{ u32 x84; u8/*bool*/ x85 = addcarryx_u26(x81, x44, x82, &x84);
+	{ u32 x86 = (x49 & 0x1ffffff);
+	{ u32 x88; addcarryx_u25(x85, x47, x86, &x88);
+	out[0] = x52;
+	out[1] = x56;
+	out[2] = x60;
+	out[3] = x64;
+	out[4] = x68;
+	out[5] = x72;
+	out[6] = x76;
+	out[7] = x80;
+	out[8] = x84;
+	out[9] = x88;
+	}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}
+}
+
+static __always_inline void fe_tobytes(u8 s[32], const fe *f)
+{
+	u32 h[10];
+	fe_freeze(h, f->v);
+	s[0] = h[0] >> 0;
+	s[1] = h[0] >> 8;
+	s[2] = h[0] >> 16;
+	s[3] = (h[0] >> 24) | (h[1] << 2);
+	s[4] = h[1] >> 6;
+	s[5] = h[1] >> 14;
+	s[6] = (h[1] >> 22) | (h[2] << 3);
+	s[7] = h[2] >> 5;
+	s[8] = h[2] >> 13;
+	s[9] = (h[2] >> 21) | (h[3] << 5);
+	s[10] = h[3] >> 3;
+	s[11] = h[3] >> 11;
+	s[12] = (h[3] >> 19) | (h[4] << 6);
+	s[13] = h[4] >> 2;
+	s[14] = h[4] >> 10;
+	s[15] = h[4] >> 18;
+	s[16] = h[5] >> 0;
+	s[17] = h[5] >> 8;
+	s[18] = h[5] >> 16;
+	s[19] = (h[5] >> 24) | (h[6] << 1);
+	s[20] = h[6] >> 7;
+	s[21] = h[6] >> 15;
+	s[22] = (h[6] >> 23) | (h[7] << 3);
+	s[23] = h[7] >> 5;
+	s[24] = h[7] >> 13;
+	s[25] = (h[7] >> 21) | (h[8] << 4);
+	s[26] = h[8] >> 4;
+	s[27] = h[8] >> 12;
+	s[28] = (h[8] >> 20) | (h[9] << 6);
+	s[29] = h[9] >> 2;
+	s[30] = h[9] >> 10;
+	s[31] = h[9] >> 18;
+}
+
+/* h = f */
+static __always_inline void fe_copy(fe *h, const fe *f)
+{
+	memmove(h, f, sizeof(u32) * 10);
+}
+
+static __always_inline void fe_copy_lt(fe_loose *h, const fe *f)
+{
+	memmove(h, f, sizeof(u32) * 10);
+}
+
+/* h = 0 */
+static __always_inline void fe_0(fe *h)
+{
+	memset(h, 0, sizeof(u32) * 10);
+}
+
+/* h = 1 */
+static __always_inline void fe_1(fe *h)
+{
+	memset(h, 0, sizeof(u32) * 10);
+	h->v[0] = 1;
+}
+
+static noinline void fe_add_impl(u32 out[10], const u32 in1[10], const u32 in2[10])
+{
+	{ const u32 x20 = in1[9];
+	{ const u32 x21 = in1[8];
+	{ const u32 x19 = in1[7];
+	{ const u32 x17 = in1[6];
+	{ const u32 x15 = in1[5];
+	{ const u32 x13 = in1[4];
+	{ const u32 x11 = in1[3];
+	{ const u32 x9 = in1[2];
+	{ const u32 x7 = in1[1];
+	{ const u32 x5 = in1[0];
+	{ const u32 x38 = in2[9];
+	{ const u32 x39 = in2[8];
+	{ const u32 x37 = in2[7];
+	{ const u32 x35 = in2[6];
+	{ const u32 x33 = in2[5];
+	{ const u32 x31 = in2[4];
+	{ const u32 x29 = in2[3];
+	{ const u32 x27 = in2[2];
+	{ const u32 x25 = in2[1];
+	{ const u32 x23 = in2[0];
+	out[0] = (x5 + x23);
+	out[1] = (x7 + x25);
+	out[2] = (x9 + x27);
+	out[3] = (x11 + x29);
+	out[4] = (x13 + x31);
+	out[5] = (x15 + x33);
+	out[6] = (x17 + x35);
+	out[7] = (x19 + x37);
+	out[8] = (x21 + x39);
+	out[9] = (x20 + x38);
+	}}}}}}}}}}}}}}}}}}}}
+}
+
+/* h = f + g
+ * Can overlap h with f or g.
+ */
+static __always_inline void fe_add(fe_loose *h, const fe *f, const fe *g)
+{
+	fe_add_impl(h->v, f->v, g->v);
+}
+
+static noinline void fe_sub_impl(u32 out[10], const u32 in1[10], const u32 in2[10])
+{
+	{ const u32 x20 = in1[9];
+	{ const u32 x21 = in1[8];
+	{ const u32 x19 = in1[7];
+	{ const u32 x17 = in1[6];
+	{ const u32 x15 = in1[5];
+	{ const u32 x13 = in1[4];
+	{ const u32 x11 = in1[3];
+	{ const u32 x9 = in1[2];
+	{ const u32 x7 = in1[1];
+	{ const u32 x5 = in1[0];
+	{ const u32 x38 = in2[9];
+	{ const u32 x39 = in2[8];
+	{ const u32 x37 = in2[7];
+	{ const u32 x35 = in2[6];
+	{ const u32 x33 = in2[5];
+	{ const u32 x31 = in2[4];
+	{ const u32 x29 = in2[3];
+	{ const u32 x27 = in2[2];
+	{ const u32 x25 = in2[1];
+	{ const u32 x23 = in2[0];
+	out[0] = ((0x7ffffda + x5) - x23);
+	out[1] = ((0x3fffffe + x7) - x25);
+	out[2] = ((0x7fffffe + x9) - x27);
+	out[3] = ((0x3fffffe + x11) - x29);
+	out[4] = ((0x7fffffe + x13) - x31);
+	out[5] = ((0x3fffffe + x15) - x33);
+	out[6] = ((0x7fffffe + x17) - x35);
+	out[7] = ((0x3fffffe + x19) - x37);
+	out[8] = ((0x7fffffe + x21) - x39);
+	out[9] = ((0x3fffffe + x20) - x38);
+	}}}}}}}}}}}}}}}}}}}}
+}
+
+/* h = f - g
+ * Can overlap h with f or g.
+ */
+static __always_inline void fe_sub(fe_loose *h, const fe *f, const fe *g)
+{
+	fe_sub_impl(h->v, f->v, g->v);
+}
+
+static noinline void fe_mul_impl(u32 out[10], const u32 in1[10], const u32 in2[10])
+{
+	{ const u32 x20 = in1[9];
+	{ const u32 x21 = in1[8];
+	{ const u32 x19 = in1[7];
+	{ const u32 x17 = in1[6];
+	{ const u32 x15 = in1[5];
+	{ const u32 x13 = in1[4];
+	{ const u32 x11 = in1[3];
+	{ const u32 x9 = in1[2];
+	{ const u32 x7 = in1[1];
+	{ const u32 x5 = in1[0];
+	{ const u32 x38 = in2[9];
+	{ const u32 x39 = in2[8];
+	{ const u32 x37 = in2[7];
+	{ const u32 x35 = in2[6];
+	{ const u32 x33 = in2[5];
+	{ const u32 x31 = in2[4];
+	{ const u32 x29 = in2[3];
+	{ const u32 x27 = in2[2];
+	{ const u32 x25 = in2[1];
+	{ const u32 x23 = in2[0];
+	{ u64 x40 = ((u64)x23 * x5);
+	{ u64 x41 = (((u64)x23 * x7) + ((u64)x25 * x5));
+	{ u64 x42 = ((((u64)(0x2 * x25) * x7) + ((u64)x23 * x9)) + ((u64)x27 * x5));
+	{ u64 x43 = (((((u64)x25 * x9) + ((u64)x27 * x7)) + ((u64)x23 * x11)) + ((u64)x29 * x5));
+	{ u64 x44 = (((((u64)x27 * x9) + (0x2 * (((u64)x25 * x11) + ((u64)x29 * x7)))) + ((u64)x23 * x13)) + ((u64)x31 * x5));
+	{ u64 x45 = (((((((u64)x27 * x11) + ((u64)x29 * x9)) + ((u64)x25 * x13)) + ((u64)x31 * x7)) + ((u64)x23 * x15)) + ((u64)x33 * x5));
+	{ u64 x46 = (((((0x2 * ((((u64)x29 * x11) + ((u64)x25 * x15)) + ((u64)x33 * x7))) + ((u64)x27 * x13)) + ((u64)x31 * x9)) + ((u64)x23 * x17)) + ((u64)x35 * x5));
+	{ u64 x47 = (((((((((u64)x29 * x13) + ((u64)x31 * x11)) + ((u64)x27 * x15)) + ((u64)x33 * x9)) + ((u64)x25 * x17)) + ((u64)x35 * x7)) + ((u64)x23 * x19)) + ((u64)x37 * x5));
+	{ u64 x48 = (((((((u64)x31 * x13) + (0x2 * (((((u64)x29 * x15) + ((u64)x33 * x11)) + ((u64)x25 * x19)) + ((u64)x37 * x7)))) + ((u64)x27 * x17)) + ((u64)x35 * x9)) + ((u64)x23 * x21)) + ((u64)x39 * x5));
+	{ u64 x49 = (((((((((((u64)x31 * x15) + ((u64)x33 * x13)) + ((u64)x29 * x17)) + ((u64)x35 * x11)) + ((u64)x27 * x19)) + ((u64)x37 * x9)) + ((u64)x25 * x21)) + ((u64)x39 * x7)) + ((u64)x23 * x20)) + ((u64)x38 * x5));
+	{ u64 x50 = (((((0x2 * ((((((u64)x33 * x15) + ((u64)x29 * x19)) + ((u64)x37 * x11)) + ((u64)x25 * x20)) + ((u64)x38 * x7))) + ((u64)x31 * x17)) + ((u64)x35 * x13)) + ((u64)x27 * x21)) + ((u64)x39 * x9));
+	{ u64 x51 = (((((((((u64)x33 * x17) + ((u64)x35 * x15)) + ((u64)x31 * x19)) + ((u64)x37 * x13)) + ((u64)x29 * x21)) + ((u64)x39 * x11)) + ((u64)x27 * x20)) + ((u64)x38 * x9));
+	{ u64 x52 = (((((u64)x35 * x17) + (0x2 * (((((u64)x33 * x19) + ((u64)x37 * x15)) + ((u64)x29 * x20)) + ((u64)x38 * x11)))) + ((u64)x31 * x21)) + ((u64)x39 * x13));
+	{ u64 x53 = (((((((u64)x35 * x19) + ((u64)x37 * x17)) + ((u64)x33 * x21)) + ((u64)x39 * x15)) + ((u64)x31 * x20)) + ((u64)x38 * x13));
+	{ u64 x54 = (((0x2 * ((((u64)x37 * x19) + ((u64)x33 * x20)) + ((u64)x38 * x15))) + ((u64)x35 * x21)) + ((u64)x39 * x17));
+	{ u64 x55 = (((((u64)x37 * x21) + ((u64)x39 * x19)) + ((u64)x35 * x20)) + ((u64)x38 * x17));
+	{ u64 x56 = (((u64)x39 * x21) + (0x2 * (((u64)x37 * x20) + ((u64)x38 * x19))));
+	{ u64 x57 = (((u64)x39 * x20) + ((u64)x38 * x21));
+	{ u64 x58 = ((u64)(0x2 * x38) * x20);
+	{ u64 x59 = (x48 + (x58 << 0x4));
+	{ u64 x60 = (x59 + (x58 << 0x1));
+	{ u64 x61 = (x60 + x58);
+	{ u64 x62 = (x47 + (x57 << 0x4));
+	{ u64 x63 = (x62 + (x57 << 0x1));
+	{ u64 x64 = (x63 + x57);
+	{ u64 x65 = (x46 + (x56 << 0x4));
+	{ u64 x66 = (x65 + (x56 << 0x1));
+	{ u64 x67 = (x66 + x56);
+	{ u64 x68 = (x45 + (x55 << 0x4));
+	{ u64 x69 = (x68 + (x55 << 0x1));
+	{ u64 x70 = (x69 + x55);
+	{ u64 x71 = (x44 + (x54 << 0x4));
+	{ u64 x72 = (x71 + (x54 << 0x1));
+	{ u64 x73 = (x72 + x54);
+	{ u64 x74 = (x43 + (x53 << 0x4));
+	{ u64 x75 = (x74 + (x53 << 0x1));
+	{ u64 x76 = (x75 + x53);
+	{ u64 x77 = (x42 + (x52 << 0x4));
+	{ u64 x78 = (x77 + (x52 << 0x1));
+	{ u64 x79 = (x78 + x52);
+	{ u64 x80 = (x41 + (x51 << 0x4));
+	{ u64 x81 = (x80 + (x51 << 0x1));
+	{ u64 x82 = (x81 + x51);
+	{ u64 x83 = (x40 + (x50 << 0x4));
+	{ u64 x84 = (x83 + (x50 << 0x1));
+	{ u64 x85 = (x84 + x50);
+	{ u64 x86 = (x85 >> 0x1a);
+	{ u32 x87 = ((u32)x85 & 0x3ffffff);
+	{ u64 x88 = (x86 + x82);
+	{ u64 x89 = (x88 >> 0x19);
+	{ u32 x90 = ((u32)x88 & 0x1ffffff);
+	{ u64 x91 = (x89 + x79);
+	{ u64 x92 = (x91 >> 0x1a);
+	{ u32 x93 = ((u32)x91 & 0x3ffffff);
+	{ u64 x94 = (x92 + x76);
+	{ u64 x95 = (x94 >> 0x19);
+	{ u32 x96 = ((u32)x94 & 0x1ffffff);
+	{ u64 x97 = (x95 + x73);
+	{ u64 x98 = (x97 >> 0x1a);
+	{ u32 x99 = ((u32)x97 & 0x3ffffff);
+	{ u64 x100 = (x98 + x70);
+	{ u64 x101 = (x100 >> 0x19);
+	{ u32 x102 = ((u32)x100 & 0x1ffffff);
+	{ u64 x103 = (x101 + x67);
+	{ u64 x104 = (x103 >> 0x1a);
+	{ u32 x105 = ((u32)x103 & 0x3ffffff);
+	{ u64 x106 = (x104 + x64);
+	{ u64 x107 = (x106 >> 0x19);
+	{ u32 x108 = ((u32)x106 & 0x1ffffff);
+	{ u64 x109 = (x107 + x61);
+	{ u64 x110 = (x109 >> 0x1a);
+	{ u32 x111 = ((u32)x109 & 0x3ffffff);
+	{ u64 x112 = (x110 + x49);
+	{ u64 x113 = (x112 >> 0x19);
+	{ u32 x114 = ((u32)x112 & 0x1ffffff);
+	{ u64 x115 = (x87 + (0x13 * x113));
+	{ u32 x116 = (u32) (x115 >> 0x1a);
+	{ u32 x117 = ((u32)x115 & 0x3ffffff);
+	{ u32 x118 = (x116 + x90);
+	{ u32 x119 = (x118 >> 0x19);
+	{ u32 x120 = (x118 & 0x1ffffff);
+	out[0] = x117;
+	out[1] = x120;
+	out[2] = (x119 + x93);
+	out[3] = x96;
+	out[4] = x99;
+	out[5] = x102;
+	out[6] = x105;
+	out[7] = x108;
+	out[8] = x111;
+	out[9] = x114;
+	}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}
+}
+
+static __always_inline void fe_mul_ttt(fe *h, const fe *f, const fe *g)
+{
+	fe_mul_impl(h->v, f->v, g->v);
+}
+
+static __always_inline void fe_mul_tlt(fe *h, const fe_loose *f, const fe *g)
+{
+	fe_mul_impl(h->v, f->v, g->v);
+}
+
+static __always_inline void
+fe_mul_tll(fe *h, const fe_loose *f, const fe_loose *g)
+{
+	fe_mul_impl(h->v, f->v, g->v);
+}
+
+static noinline void fe_sqr_impl(u32 out[10], const u32 in1[10])
+{
+	{ const u32 x17 = in1[9];
+	{ const u32 x18 = in1[8];
+	{ const u32 x16 = in1[7];
+	{ const u32 x14 = in1[6];
+	{ const u32 x12 = in1[5];
+	{ const u32 x10 = in1[4];
+	{ const u32 x8 = in1[3];
+	{ const u32 x6 = in1[2];
+	{ const u32 x4 = in1[1];
+	{ const u32 x2 = in1[0];
+	{ u64 x19 = ((u64)x2 * x2);
+	{ u64 x20 = ((u64)(0x2 * x2) * x4);
+	{ u64 x21 = (0x2 * (((u64)x4 * x4) + ((u64)x2 * x6)));
+	{ u64 x22 = (0x2 * (((u64)x4 * x6) + ((u64)x2 * x8)));
+	{ u64 x23 = ((((u64)x6 * x6) + ((u64)(0x4 * x4) * x8)) + ((u64)(0x2 * x2) * x10));
+	{ u64 x24 = (0x2 * ((((u64)x6 * x8) + ((u64)x4 * x10)) + ((u64)x2 * x12)));
+	{ u64 x25 = (0x2 * (((((u64)x8 * x8) + ((u64)x6 * x10)) + ((u64)x2 * x14)) + ((u64)(0x2 * x4) * x12)));
+	{ u64 x26 = (0x2 * (((((u64)x8 * x10) + ((u64)x6 * x12)) + ((u64)x4 * x14)) + ((u64)x2 * x16)));
+	{ u64 x27 = (((u64)x10 * x10) + (0x2 * ((((u64)x6 * x14) + ((u64)x2 * x18)) + (0x2 * (((u64)x4 * x16) + ((u64)x8 * x12))))));
+	{ u64 x28 = (0x2 * ((((((u64)x10 * x12) + ((u64)x8 * x14)) + ((u64)x6 * x16)) + ((u64)x4 * x18)) + ((u64)x2 * x17)));
+	{ u64 x29 = (0x2 * (((((u64)x12 * x12) + ((u64)x10 * x14)) + ((u64)x6 * x18)) + (0x2 * (((u64)x8 * x16) + ((u64)x4 * x17)))));
+	{ u64 x30 = (0x2 * (((((u64)x12 * x14) + ((u64)x10 * x16)) + ((u64)x8 * x18)) + ((u64)x6 * x17)));
+	{ u64 x31 = (((u64)x14 * x14) + (0x2 * (((u64)x10 * x18) + (0x2 * (((u64)x12 * x16) + ((u64)x8 * x17))))));
+	{ u64 x32 = (0x2 * ((((u64)x14 * x16) + ((u64)x12 * x18)) + ((u64)x10 * x17)));
+	{ u64 x33 = (0x2 * ((((u64)x16 * x16) + ((u64)x14 * x18)) + ((u64)(0x2 * x12) * x17)));
+	{ u64 x34 = (0x2 * (((u64)x16 * x18) + ((u64)x14 * x17)));
+	{ u64 x35 = (((u64)x18 * x18) + ((u64)(0x4 * x16) * x17));
+	{ u64 x36 = ((u64)(0x2 * x18) * x17);
+	{ u64 x37 = ((u64)(0x2 * x17) * x17);
+	{ u64 x38 = (x27 + (x37 << 0x4));
+	{ u64 x39 = (x38 + (x37 << 0x1));
+	{ u64 x40 = (x39 + x37);
+	{ u64 x41 = (x26 + (x36 << 0x4));
+	{ u64 x42 = (x41 + (x36 << 0x1));
+	{ u64 x43 = (x42 + x36);
+	{ u64 x44 = (x25 + (x35 << 0x4));
+	{ u64 x45 = (x44 + (x35 << 0x1));
+	{ u64 x46 = (x45 + x35);
+	{ u64 x47 = (x24 + (x34 << 0x4));
+	{ u64 x48 = (x47 + (x34 << 0x1));
+	{ u64 x49 = (x48 + x34);
+	{ u64 x50 = (x23 + (x33 << 0x4));
+	{ u64 x51 = (x50 + (x33 << 0x1));
+	{ u64 x52 = (x51 + x33);
+	{ u64 x53 = (x22 + (x32 << 0x4));
+	{ u64 x54 = (x53 + (x32 << 0x1));
+	{ u64 x55 = (x54 + x32);
+	{ u64 x56 = (x21 + (x31 << 0x4));
+	{ u64 x57 = (x56 + (x31 << 0x1));
+	{ u64 x58 = (x57 + x31);
+	{ u64 x59 = (x20 + (x30 << 0x4));
+	{ u64 x60 = (x59 + (x30 << 0x1));
+	{ u64 x61 = (x60 + x30);
+	{ u64 x62 = (x19 + (x29 << 0x4));
+	{ u64 x63 = (x62 + (x29 << 0x1));
+	{ u64 x64 = (x63 + x29);
+	{ u64 x65 = (x64 >> 0x1a);
+	{ u32 x66 = ((u32)x64 & 0x3ffffff);
+	{ u64 x67 = (x65 + x61);
+	{ u64 x68 = (x67 >> 0x19);
+	{ u32 x69 = ((u32)x67 & 0x1ffffff);
+	{ u64 x70 = (x68 + x58);
+	{ u64 x71 = (x70 >> 0x1a);
+	{ u32 x72 = ((u32)x70 & 0x3ffffff);
+	{ u64 x73 = (x71 + x55);
+	{ u64 x74 = (x73 >> 0x19);
+	{ u32 x75 = ((u32)x73 & 0x1ffffff);
+	{ u64 x76 = (x74 + x52);
+	{ u64 x77 = (x76 >> 0x1a);
+	{ u32 x78 = ((u32)x76 & 0x3ffffff);
+	{ u64 x79 = (x77 + x49);
+	{ u64 x80 = (x79 >> 0x19);
+	{ u32 x81 = ((u32)x79 & 0x1ffffff);
+	{ u64 x82 = (x80 + x46);
+	{ u64 x83 = (x82 >> 0x1a);
+	{ u32 x84 = ((u32)x82 & 0x3ffffff);
+	{ u64 x85 = (x83 + x43);
+	{ u64 x86 = (x85 >> 0x19);
+	{ u32 x87 = ((u32)x85 & 0x1ffffff);
+	{ u64 x88 = (x86 + x40);
+	{ u64 x89 = (x88 >> 0x1a);
+	{ u32 x90 = ((u32)x88 & 0x3ffffff);
+	{ u64 x91 = (x89 + x28);
+	{ u64 x92 = (x91 >> 0x19);
+	{ u32 x93 = ((u32)x91 & 0x1ffffff);
+	{ u64 x94 = (x66 + (0x13 * x92));
+	{ u32 x95 = (u32) (x94 >> 0x1a);
+	{ u32 x96 = ((u32)x94 & 0x3ffffff);
+	{ u32 x97 = (x95 + x69);
+	{ u32 x98 = (x97 >> 0x19);
+	{ u32 x99 = (x97 & 0x1ffffff);
+	out[0] = x96;
+	out[1] = x99;
+	out[2] = (x98 + x72);
+	out[3] = x75;
+	out[4] = x78;
+	out[5] = x81;
+	out[6] = x84;
+	out[7] = x87;
+	out[8] = x90;
+	out[9] = x93;
+	}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}
+}
+
+static __always_inline void fe_sq_tl(fe *h, const fe_loose *f)
+{
+	fe_sqr_impl(h->v, f->v);
+}
+
+static __always_inline void fe_sq_tt(fe *h, const fe *f)
+{
+	fe_sqr_impl(h->v, f->v);
+}
+
+static __always_inline void fe_loose_invert(fe *out, const fe_loose *z)
+{
+	fe t0;
+	fe t1;
+	fe t2;
+	fe t3;
+	int i;
+
+	fe_sq_tl(&t0, z);
+	fe_sq_tt(&t1, &t0);
+	for (i = 1; i < 2; ++i)
+		fe_sq_tt(&t1, &t1);
+	fe_mul_tlt(&t1, z, &t1);
+	fe_mul_ttt(&t0, &t0, &t1);
+	fe_sq_tt(&t2, &t0);
+	fe_mul_ttt(&t1, &t1, &t2);
+	fe_sq_tt(&t2, &t1);
+	for (i = 1; i < 5; ++i)
+		fe_sq_tt(&t2, &t2);
+	fe_mul_ttt(&t1, &t2, &t1);
+	fe_sq_tt(&t2, &t1);
+	for (i = 1; i < 10; ++i)
+		fe_sq_tt(&t2, &t2);
+	fe_mul_ttt(&t2, &t2, &t1);
+	fe_sq_tt(&t3, &t2);
+	for (i = 1; i < 20; ++i)
+		fe_sq_tt(&t3, &t3);
+	fe_mul_ttt(&t2, &t3, &t2);
+	fe_sq_tt(&t2, &t2);
+	for (i = 1; i < 10; ++i)
+		fe_sq_tt(&t2, &t2);
+	fe_mul_ttt(&t1, &t2, &t1);
+	fe_sq_tt(&t2, &t1);
+	for (i = 1; i < 50; ++i)
+		fe_sq_tt(&t2, &t2);
+	fe_mul_ttt(&t2, &t2, &t1);
+	fe_sq_tt(&t3, &t2);
+	for (i = 1; i < 100; ++i)
+		fe_sq_tt(&t3, &t3);
+	fe_mul_ttt(&t2, &t3, &t2);
+	fe_sq_tt(&t2, &t2);
+	for (i = 1; i < 50; ++i)
+		fe_sq_tt(&t2, &t2);
+	fe_mul_ttt(&t1, &t2, &t1);
+	fe_sq_tt(&t1, &t1);
+	for (i = 1; i < 5; ++i)
+		fe_sq_tt(&t1, &t1);
+	fe_mul_ttt(out, &t1, &t0);
+}
+
+static __always_inline void fe_invert(fe *out, const fe *z)
+{
+	fe_loose l;
+	fe_copy_lt(&l, z);
+	fe_loose_invert(out, &l);
+}
+
+/* Replace (f,g) with (g,f) if b == 1;
+ * replace (f,g) with (f,g) if b == 0.
+ *
+ * Preconditions: b in {0,1}
+ */
+static noinline void fe_cswap(fe *f, fe *g, unsigned int b)
+{
+	unsigned i;
+	b = 0 - b;
+	for (i = 0; i < 10; i++) {
+		u32 x = f->v[i] ^ g->v[i];
+		x &= b;
+		f->v[i] ^= x;
+		g->v[i] ^= x;
+	}
+}
+
+/* NOTE: based on fiat-crypto fe_mul, edited for in2=121666, 0, 0.*/
+static __always_inline void fe_mul_121666_impl(u32 out[10], const u32 in1[10])
+{
+	{ const u32 x20 = in1[9];
+	{ const u32 x21 = in1[8];
+	{ const u32 x19 = in1[7];
+	{ const u32 x17 = in1[6];
+	{ const u32 x15 = in1[5];
+	{ const u32 x13 = in1[4];
+	{ const u32 x11 = in1[3];
+	{ const u32 x9 = in1[2];
+	{ const u32 x7 = in1[1];
+	{ const u32 x5 = in1[0];
+	{ const u32 x38 = 0;
+	{ const u32 x39 = 0;
+	{ const u32 x37 = 0;
+	{ const u32 x35 = 0;
+	{ const u32 x33 = 0;
+	{ const u32 x31 = 0;
+	{ const u32 x29 = 0;
+	{ const u32 x27 = 0;
+	{ const u32 x25 = 0;
+	{ const u32 x23 = 121666;
+	{ u64 x40 = ((u64)x23 * x5);
+	{ u64 x41 = (((u64)x23 * x7) + ((u64)x25 * x5));
+	{ u64 x42 = ((((u64)(0x2 * x25) * x7) + ((u64)x23 * x9)) + ((u64)x27 * x5));
+	{ u64 x43 = (((((u64)x25 * x9) + ((u64)x27 * x7)) + ((u64)x23 * x11)) + ((u64)x29 * x5));
+	{ u64 x44 = (((((u64)x27 * x9) + (0x2 * (((u64)x25 * x11) + ((u64)x29 * x7)))) + ((u64)x23 * x13)) + ((u64)x31 * x5));
+	{ u64 x45 = (((((((u64)x27 * x11) + ((u64)x29 * x9)) + ((u64)x25 * x13)) + ((u64)x31 * x7)) + ((u64)x23 * x15)) + ((u64)x33 * x5));
+	{ u64 x46 = (((((0x2 * ((((u64)x29 * x11) + ((u64)x25 * x15)) + ((u64)x33 * x7))) + ((u64)x27 * x13)) + ((u64)x31 * x9)) + ((u64)x23 * x17)) + ((u64)x35 * x5));
+	{ u64 x47 = (((((((((u64)x29 * x13) + ((u64)x31 * x11)) + ((u64)x27 * x15)) + ((u64)x33 * x9)) + ((u64)x25 * x17)) + ((u64)x35 * x7)) + ((u64)x23 * x19)) + ((u64)x37 * x5));
+	{ u64 x48 = (((((((u64)x31 * x13) + (0x2 * (((((u64)x29 * x15) + ((u64)x33 * x11)) + ((u64)x25 * x19)) + ((u64)x37 * x7)))) + ((u64)x27 * x17)) + ((u64)x35 * x9)) + ((u64)x23 * x21)) + ((u64)x39 * x5));
+	{ u64 x49 = (((((((((((u64)x31 * x15) + ((u64)x33 * x13)) + ((u64)x29 * x17)) + ((u64)x35 * x11)) + ((u64)x27 * x19)) + ((u64)x37 * x9)) + ((u64)x25 * x21)) + ((u64)x39 * x7)) + ((u64)x23 * x20)) + ((u64)x38 * x5));
+	{ u64 x50 = (((((0x2 * ((((((u64)x33 * x15) + ((u64)x29 * x19)) + ((u64)x37 * x11)) + ((u64)x25 * x20)) + ((u64)x38 * x7))) + ((u64)x31 * x17)) + ((u64)x35 * x13)) + ((u64)x27 * x21)) + ((u64)x39 * x9));
+	{ u64 x51 = (((((((((u64)x33 * x17) + ((u64)x35 * x15)) + ((u64)x31 * x19)) + ((u64)x37 * x13)) + ((u64)x29 * x21)) + ((u64)x39 * x11)) + ((u64)x27 * x20)) + ((u64)x38 * x9));
+	{ u64 x52 = (((((u64)x35 * x17) + (0x2 * (((((u64)x33 * x19) + ((u64)x37 * x15)) + ((u64)x29 * x20)) + ((u64)x38 * x11)))) + ((u64)x31 * x21)) + ((u64)x39 * x13));
+	{ u64 x53 = (((((((u64)x35 * x19) + ((u64)x37 * x17)) + ((u64)x33 * x21)) + ((u64)x39 * x15)) + ((u64)x31 * x20)) + ((u64)x38 * x13));
+	{ u64 x54 = (((0x2 * ((((u64)x37 * x19) + ((u64)x33 * x20)) + ((u64)x38 * x15))) + ((u64)x35 * x21)) + ((u64)x39 * x17));
+	{ u64 x55 = (((((u64)x37 * x21) + ((u64)x39 * x19)) + ((u64)x35 * x20)) + ((u64)x38 * x17));
+	{ u64 x56 = (((u64)x39 * x21) + (0x2 * (((u64)x37 * x20) + ((u64)x38 * x19))));
+	{ u64 x57 = (((u64)x39 * x20) + ((u64)x38 * x21));
+	{ u64 x58 = ((u64)(0x2 * x38) * x20);
+	{ u64 x59 = (x48 + (x58 << 0x4));
+	{ u64 x60 = (x59 + (x58 << 0x1));
+	{ u64 x61 = (x60 + x58);
+	{ u64 x62 = (x47 + (x57 << 0x4));
+	{ u64 x63 = (x62 + (x57 << 0x1));
+	{ u64 x64 = (x63 + x57);
+	{ u64 x65 = (x46 + (x56 << 0x4));
+	{ u64 x66 = (x65 + (x56 << 0x1));
+	{ u64 x67 = (x66 + x56);
+	{ u64 x68 = (x45 + (x55 << 0x4));
+	{ u64 x69 = (x68 + (x55 << 0x1));
+	{ u64 x70 = (x69 + x55);
+	{ u64 x71 = (x44 + (x54 << 0x4));
+	{ u64 x72 = (x71 + (x54 << 0x1));
+	{ u64 x73 = (x72 + x54);
+	{ u64 x74 = (x43 + (x53 << 0x4));
+	{ u64 x75 = (x74 + (x53 << 0x1));
+	{ u64 x76 = (x75 + x53);
+	{ u64 x77 = (x42 + (x52 << 0x4));
+	{ u64 x78 = (x77 + (x52 << 0x1));
+	{ u64 x79 = (x78 + x52);
+	{ u64 x80 = (x41 + (x51 << 0x4));
+	{ u64 x81 = (x80 + (x51 << 0x1));
+	{ u64 x82 = (x81 + x51);
+	{ u64 x83 = (x40 + (x50 << 0x4));
+	{ u64 x84 = (x83 + (x50 << 0x1));
+	{ u64 x85 = (x84 + x50);
+	{ u64 x86 = (x85 >> 0x1a);
+	{ u32 x87 = ((u32)x85 & 0x3ffffff);
+	{ u64 x88 = (x86 + x82);
+	{ u64 x89 = (x88 >> 0x19);
+	{ u32 x90 = ((u32)x88 & 0x1ffffff);
+	{ u64 x91 = (x89 + x79);
+	{ u64 x92 = (x91 >> 0x1a);
+	{ u32 x93 = ((u32)x91 & 0x3ffffff);
+	{ u64 x94 = (x92 + x76);
+	{ u64 x95 = (x94 >> 0x19);
+	{ u32 x96 = ((u32)x94 & 0x1ffffff);
+	{ u64 x97 = (x95 + x73);
+	{ u64 x98 = (x97 >> 0x1a);
+	{ u32 x99 = ((u32)x97 & 0x3ffffff);
+	{ u64 x100 = (x98 + x70);
+	{ u64 x101 = (x100 >> 0x19);
+	{ u32 x102 = ((u32)x100 & 0x1ffffff);
+	{ u64 x103 = (x101 + x67);
+	{ u64 x104 = (x103 >> 0x1a);
+	{ u32 x105 = ((u32)x103 & 0x3ffffff);
+	{ u64 x106 = (x104 + x64);
+	{ u64 x107 = (x106 >> 0x19);
+	{ u32 x108 = ((u32)x106 & 0x1ffffff);
+	{ u64 x109 = (x107 + x61);
+	{ u64 x110 = (x109 >> 0x1a);
+	{ u32 x111 = ((u32)x109 & 0x3ffffff);
+	{ u64 x112 = (x110 + x49);
+	{ u64 x113 = (x112 >> 0x19);
+	{ u32 x114 = ((u32)x112 & 0x1ffffff);
+	{ u64 x115 = (x87 + (0x13 * x113));
+	{ u32 x116 = (u32) (x115 >> 0x1a);
+	{ u32 x117 = ((u32)x115 & 0x3ffffff);
+	{ u32 x118 = (x116 + x90);
+	{ u32 x119 = (x118 >> 0x19);
+	{ u32 x120 = (x118 & 0x1ffffff);
+	out[0] = x117;
+	out[1] = x120;
+	out[2] = (x119 + x93);
+	out[3] = x96;
+	out[4] = x99;
+	out[5] = x102;
+	out[6] = x105;
+	out[7] = x108;
+	out[8] = x111;
+	out[9] = x114;
+	}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}
+}
+
+static __always_inline void fe_mul121666(fe *h, const fe_loose *f)
+{
+	fe_mul_121666_impl(h->v, f->v);
+}
+
+void curve25519_generic(u8 out[CURVE25519_KEY_SIZE],
+			const u8 scalar[CURVE25519_KEY_SIZE],
+			const u8 point[CURVE25519_KEY_SIZE])
+{
+	fe x1, x2, z2, x3, z3;
+	fe_loose x2l, z2l, x3l;
+	unsigned swap = 0;
+	int pos;
+	u8 e[32];
+
+	memcpy(e, scalar, 32);
+	curve25519_clamp_secret(e);
+
+	/* The following implementation was transcribed to Coq and proven to
+	 * correspond to unary scalar multiplication in affine coordinates given
+	 * that x1 != 0 is the x coordinate of some point on the curve. It was
+	 * also checked in Coq that doing a ladderstep with x1 = x3 = 0 gives
+	 * z2' = z3' = 0, and z2 = z3 = 0 gives z2' = z3' = 0. The statement was
+	 * quantified over the underlying field, so it applies to Curve25519
+	 * itself and the quadratic twist of Curve25519. It was not proven in
+	 * Coq that prime-field arithmetic correctly simulates extension-field
+	 * arithmetic on prime-field values. The decoding of the byte array
+	 * representation of e was not considered.
+	 *
+	 * Specification of Montgomery curves in affine coordinates:
+	 * <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Spec/MontgomeryCurve.v#L27>
+	 *
+	 * Proof that these form a group that is isomorphic to a Weierstrass
+	 * curve:
+	 * <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Curves/Montgomery/AffineProofs.v#L35>
+	 *
+	 * Coq transcription and correctness proof of the loop
+	 * (where scalarbits=255):
+	 * <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Curves/Montgomery/XZ.v#L118>
+	 * <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Curves/Montgomery/XZProofs.v#L278>
+	 * preconditions: 0 <= e < 2^255 (not necessarily e < order),
+	 * fe_invert(0) = 0
+	 */
+	fe_frombytes(&x1, point);
+	fe_1(&x2);
+	fe_0(&z2);
+	fe_copy(&x3, &x1);
+	fe_1(&z3);
+
+	for (pos = 254; pos >= 0; --pos) {
+		fe tmp0, tmp1;
+		fe_loose tmp0l, tmp1l;
+		/* loop invariant as of right before the test, for the case
+		 * where x1 != 0:
+		 *   pos >= -1; if z2 = 0 then x2 is nonzero; if z3 = 0 then x3
+		 *   is nonzero
+		 *   let r := e >> (pos+1) in the following equalities of
+		 *   projective points:
+		 *   to_xz (r*P)     === if swap then (x3, z3) else (x2, z2)
+		 *   to_xz ((r+1)*P) === if swap then (x2, z2) else (x3, z3)
+		 *   x1 is the nonzero x coordinate of the nonzero
+		 *   point (r*P-(r+1)*P)
+		 */
+		unsigned b = 1 & (e[pos / 8] >> (pos & 7));
+		swap ^= b;
+		fe_cswap(&x2, &x3, swap);
+		fe_cswap(&z2, &z3, swap);
+		swap = b;
+		/* Coq transcription of ladderstep formula (called from
+		 * transcribed loop):
+		 * <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Curves/Montgomery/XZ.v#L89>
+		 * <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Curves/Montgomery/XZProofs.v#L131>
+		 * x1 != 0 <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Curves/Montgomery/XZProofs.v#L217>
+		 * x1  = 0 <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Curves/Montgomery/XZProofs.v#L147>
+		 */
+		fe_sub(&tmp0l, &x3, &z3);
+		fe_sub(&tmp1l, &x2, &z2);
+		fe_add(&x2l, &x2, &z2);
+		fe_add(&z2l, &x3, &z3);
+		fe_mul_tll(&z3, &tmp0l, &x2l);
+		fe_mul_tll(&z2, &z2l, &tmp1l);
+		fe_sq_tl(&tmp0, &tmp1l);
+		fe_sq_tl(&tmp1, &x2l);
+		fe_add(&x3l, &z3, &z2);
+		fe_sub(&z2l, &z3, &z2);
+		fe_mul_ttt(&x2, &tmp1, &tmp0);
+		fe_sub(&tmp1l, &tmp1, &tmp0);
+		fe_sq_tl(&z2, &z2l);
+		fe_mul121666(&z3, &tmp1l);
+		fe_sq_tl(&x3, &x3l);
+		fe_add(&tmp0l, &tmp0, &z3);
+		fe_mul_ttt(&z3, &x1, &z2);
+		fe_mul_tll(&z2, &tmp1l, &tmp0l);
+	}
+	/* here pos=-1, so r=e, so to_xz (e*P) === if swap then (x3, z3)
+	 * else (x2, z2)
+	 */
+	fe_cswap(&x2, &x3, swap);
+	fe_cswap(&z2, &z3, swap);
+
+	fe_invert(&z2, &z2);
+	fe_mul_ttt(&x2, &x2, &z2);
+	fe_tobytes(out, &x2);
+
+	memzero_explicit(&x1, sizeof(x1));
+	memzero_explicit(&x2, sizeof(x2));
+	memzero_explicit(&z2, sizeof(z2));
+	memzero_explicit(&x3, sizeof(x3));
+	memzero_explicit(&z3, sizeof(z3));
+	memzero_explicit(&x2l, sizeof(x2l));
+	memzero_explicit(&z2l, sizeof(z2l));
+	memzero_explicit(&x3l, sizeof(x3l));
+	memzero_explicit(&e, sizeof(e));
+}
diff --git a/lib/crypto/curve25519-hacl64.c b/lib/crypto/curve25519-hacl64.c
new file mode 100644
index 000000000000..771d82dc5f14
--- /dev/null
+++ b/lib/crypto/curve25519-hacl64.c
@@ -0,0 +1,788 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2016-2017 INRIA and Microsoft Corporation.
+ * Copyright (C) 2018-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This is a machine-generated formally verified implementation of Curve25519
+ * ECDH from: <https://github.com/mitls/hacl-star>. Though originally machine
+ * generated, it has been tweaked to be suitable for use in the kernel. It is
+ * optimized for 64-bit machines that can efficiently work with 128-bit
+ * integer types.
+ */
+
+#include <asm/unaligned.h>
+#include <crypto/curve25519.h>
+#include <linux/string.h>
+
+typedef __uint128_t u128;
+
+static __always_inline u64 u64_eq_mask(u64 a, u64 b)
+{
+	u64 x = a ^ b;
+	u64 minus_x = ~x + (u64)1U;
+	u64 x_or_minus_x = x | minus_x;
+	u64 xnx = x_or_minus_x >> (u32)63U;
+	u64 c = xnx - (u64)1U;
+	return c;
+}
+
+static __always_inline u64 u64_gte_mask(u64 a, u64 b)
+{
+	u64 x = a;
+	u64 y = b;
+	u64 x_xor_y = x ^ y;
+	u64 x_sub_y = x - y;
+	u64 x_sub_y_xor_y = x_sub_y ^ y;
+	u64 q = x_xor_y | x_sub_y_xor_y;
+	u64 x_xor_q = x ^ q;
+	u64 x_xor_q_ = x_xor_q >> (u32)63U;
+	u64 c = x_xor_q_ - (u64)1U;
+	return c;
+}
+
+static __always_inline void modulo_carry_top(u64 *b)
+{
+	u64 b4 = b[4];
+	u64 b0 = b[0];
+	u64 b4_ = b4 & 0x7ffffffffffffLLU;
+	u64 b0_ = b0 + 19 * (b4 >> 51);
+	b[4] = b4_;
+	b[0] = b0_;
+}
+
+static __always_inline void fproduct_copy_from_wide_(u64 *output, u128 *input)
+{
+	{
+		u128 xi = input[0];
+		output[0] = ((u64)(xi));
+	}
+	{
+		u128 xi = input[1];
+		output[1] = ((u64)(xi));
+	}
+	{
+		u128 xi = input[2];
+		output[2] = ((u64)(xi));
+	}
+	{
+		u128 xi = input[3];
+		output[3] = ((u64)(xi));
+	}
+	{
+		u128 xi = input[4];
+		output[4] = ((u64)(xi));
+	}
+}
+
+static __always_inline void
+fproduct_sum_scalar_multiplication_(u128 *output, u64 *input, u64 s)
+{
+	output[0] += (u128)input[0] * s;
+	output[1] += (u128)input[1] * s;
+	output[2] += (u128)input[2] * s;
+	output[3] += (u128)input[3] * s;
+	output[4] += (u128)input[4] * s;
+}
+
+static __always_inline void fproduct_carry_wide_(u128 *tmp)
+{
+	{
+		u32 ctr = 0;
+		u128 tctr = tmp[ctr];
+		u128 tctrp1 = tmp[ctr + 1];
+		u64 r0 = ((u64)(tctr)) & 0x7ffffffffffffLLU;
+		u128 c = ((tctr) >> (51));
+		tmp[ctr] = ((u128)(r0));
+		tmp[ctr + 1] = ((tctrp1) + (c));
+	}
+	{
+		u32 ctr = 1;
+		u128 tctr = tmp[ctr];
+		u128 tctrp1 = tmp[ctr + 1];
+		u64 r0 = ((u64)(tctr)) & 0x7ffffffffffffLLU;
+		u128 c = ((tctr) >> (51));
+		tmp[ctr] = ((u128)(r0));
+		tmp[ctr + 1] = ((tctrp1) + (c));
+	}
+
+	{
+		u32 ctr = 2;
+		u128 tctr = tmp[ctr];
+		u128 tctrp1 = tmp[ctr + 1];
+		u64 r0 = ((u64)(tctr)) & 0x7ffffffffffffLLU;
+		u128 c = ((tctr) >> (51));
+		tmp[ctr] = ((u128)(r0));
+		tmp[ctr + 1] = ((tctrp1) + (c));
+	}
+	{
+		u32 ctr = 3;
+		u128 tctr = tmp[ctr];
+		u128 tctrp1 = tmp[ctr + 1];
+		u64 r0 = ((u64)(tctr)) & 0x7ffffffffffffLLU;
+		u128 c = ((tctr) >> (51));
+		tmp[ctr] = ((u128)(r0));
+		tmp[ctr + 1] = ((tctrp1) + (c));
+	}
+}
+
+static __always_inline void fmul_shift_reduce(u64 *output)
+{
+	u64 tmp = output[4];
+	u64 b0;
+	{
+		u32 ctr = 5 - 0 - 1;
+		u64 z = output[ctr - 1];
+		output[ctr] = z;
+	}
+	{
+		u32 ctr = 5 - 1 - 1;
+		u64 z = output[ctr - 1];
+		output[ctr] = z;
+	}
+	{
+		u32 ctr = 5 - 2 - 1;
+		u64 z = output[ctr - 1];
+		output[ctr] = z;
+	}
+	{
+		u32 ctr = 5 - 3 - 1;
+		u64 z = output[ctr - 1];
+		output[ctr] = z;
+	}
+	output[0] = tmp;
+	b0 = output[0];
+	output[0] = 19 * b0;
+}
+
+static __always_inline void fmul_mul_shift_reduce_(u128 *output, u64 *input,
+						   u64 *input21)
+{
+	u32 i;
+	u64 input2i;
+	{
+		u64 input2i = input21[0];
+		fproduct_sum_scalar_multiplication_(output, input, input2i);
+		fmul_shift_reduce(input);
+	}
+	{
+		u64 input2i = input21[1];
+		fproduct_sum_scalar_multiplication_(output, input, input2i);
+		fmul_shift_reduce(input);
+	}
+	{
+		u64 input2i = input21[2];
+		fproduct_sum_scalar_multiplication_(output, input, input2i);
+		fmul_shift_reduce(input);
+	}
+	{
+		u64 input2i = input21[3];
+		fproduct_sum_scalar_multiplication_(output, input, input2i);
+		fmul_shift_reduce(input);
+	}
+	i = 4;
+	input2i = input21[i];
+	fproduct_sum_scalar_multiplication_(output, input, input2i);
+}
+
+static __always_inline void fmul_fmul(u64 *output, u64 *input, u64 *input21)
+{
+	u64 tmp[5] = { input[0], input[1], input[2], input[3], input[4] };
+	{
+		u128 b4;
+		u128 b0;
+		u128 b4_;
+		u128 b0_;
+		u64 i0;
+		u64 i1;
+		u64 i0_;
+		u64 i1_;
+		u128 t[5] = { 0 };
+		fmul_mul_shift_reduce_(t, tmp, input21);
+		fproduct_carry_wide_(t);
+		b4 = t[4];
+		b0 = t[0];
+		b4_ = ((b4) & (((u128)(0x7ffffffffffffLLU))));
+		b0_ = ((b0) + (((u128)(19) * (((u64)(((b4) >> (51))))))));
+		t[4] = b4_;
+		t[0] = b0_;
+		fproduct_copy_from_wide_(output, t);
+		i0 = output[0];
+		i1 = output[1];
+		i0_ = i0 & 0x7ffffffffffffLLU;
+		i1_ = i1 + (i0 >> 51);
+		output[0] = i0_;
+		output[1] = i1_;
+	}
+}
+
+static __always_inline void fsquare_fsquare__(u128 *tmp, u64 *output)
+{
+	u64 r0 = output[0];
+	u64 r1 = output[1];
+	u64 r2 = output[2];
+	u64 r3 = output[3];
+	u64 r4 = output[4];
+	u64 d0 = r0 * 2;
+	u64 d1 = r1 * 2;
+	u64 d2 = r2 * 2 * 19;
+	u64 d419 = r4 * 19;
+	u64 d4 = d419 * 2;
+	u128 s0 = ((((((u128)(r0) * (r0))) + (((u128)(d4) * (r1))))) +
+		   (((u128)(d2) * (r3))));
+	u128 s1 = ((((((u128)(d0) * (r1))) + (((u128)(d4) * (r2))))) +
+		   (((u128)(r3 * 19) * (r3))));
+	u128 s2 = ((((((u128)(d0) * (r2))) + (((u128)(r1) * (r1))))) +
+		   (((u128)(d4) * (r3))));
+	u128 s3 = ((((((u128)(d0) * (r3))) + (((u128)(d1) * (r2))))) +
+		   (((u128)(r4) * (d419))));
+	u128 s4 = ((((((u128)(d0) * (r4))) + (((u128)(d1) * (r3))))) +
+		   (((u128)(r2) * (r2))));
+	tmp[0] = s0;
+	tmp[1] = s1;
+	tmp[2] = s2;
+	tmp[3] = s3;
+	tmp[4] = s4;
+}
+
+static __always_inline void fsquare_fsquare_(u128 *tmp, u64 *output)
+{
+	u128 b4;
+	u128 b0;
+	u128 b4_;
+	u128 b0_;
+	u64 i0;
+	u64 i1;
+	u64 i0_;
+	u64 i1_;
+	fsquare_fsquare__(tmp, output);
+	fproduct_carry_wide_(tmp);
+	b4 = tmp[4];
+	b0 = tmp[0];
+	b4_ = ((b4) & (((u128)(0x7ffffffffffffLLU))));
+	b0_ = ((b0) + (((u128)(19) * (((u64)(((b4) >> (51))))))));
+	tmp[4] = b4_;
+	tmp[0] = b0_;
+	fproduct_copy_from_wide_(output, tmp);
+	i0 = output[0];
+	i1 = output[1];
+	i0_ = i0 & 0x7ffffffffffffLLU;
+	i1_ = i1 + (i0 >> 51);
+	output[0] = i0_;
+	output[1] = i1_;
+}
+
+static __always_inline void fsquare_fsquare_times_(u64 *output, u128 *tmp,
+						   u32 count1)
+{
+	u32 i;
+	fsquare_fsquare_(tmp, output);
+	for (i = 1; i < count1; ++i)
+		fsquare_fsquare_(tmp, output);
+}
+
+static __always_inline void fsquare_fsquare_times(u64 *output, u64 *input,
+						  u32 count1)
+{
+	u128 t[5];
+	memcpy(output, input, 5 * sizeof(*input));
+	fsquare_fsquare_times_(output, t, count1);
+}
+
+static __always_inline void fsquare_fsquare_times_inplace(u64 *output,
+							  u32 count1)
+{
+	u128 t[5];
+	fsquare_fsquare_times_(output, t, count1);
+}
+
+static __always_inline void crecip_crecip(u64 *out, u64 *z)
+{
+	u64 buf[20] = { 0 };
+	u64 *a0 = buf;
+	u64 *t00 = buf + 5;
+	u64 *b0 = buf + 10;
+	u64 *t01;
+	u64 *b1;
+	u64 *c0;
+	u64 *a;
+	u64 *t0;
+	u64 *b;
+	u64 *c;
+	fsquare_fsquare_times(a0, z, 1);
+	fsquare_fsquare_times(t00, a0, 2);
+	fmul_fmul(b0, t00, z);
+	fmul_fmul(a0, b0, a0);
+	fsquare_fsquare_times(t00, a0, 1);
+	fmul_fmul(b0, t00, b0);
+	fsquare_fsquare_times(t00, b0, 5);
+	t01 = buf + 5;
+	b1 = buf + 10;
+	c0 = buf + 15;
+	fmul_fmul(b1, t01, b1);
+	fsquare_fsquare_times(t01, b1, 10);
+	fmul_fmul(c0, t01, b1);
+	fsquare_fsquare_times(t01, c0, 20);
+	fmul_fmul(t01, t01, c0);
+	fsquare_fsquare_times_inplace(t01, 10);
+	fmul_fmul(b1, t01, b1);
+	fsquare_fsquare_times(t01, b1, 50);
+	a = buf;
+	t0 = buf + 5;
+	b = buf + 10;
+	c = buf + 15;
+	fmul_fmul(c, t0, b);
+	fsquare_fsquare_times(t0, c, 100);
+	fmul_fmul(t0, t0, c);
+	fsquare_fsquare_times_inplace(t0, 50);
+	fmul_fmul(t0, t0, b);
+	fsquare_fsquare_times_inplace(t0, 5);
+	fmul_fmul(out, t0, a);
+}
+
+static __always_inline void fsum(u64 *a, u64 *b)
+{
+	a[0] += b[0];
+	a[1] += b[1];
+	a[2] += b[2];
+	a[3] += b[3];
+	a[4] += b[4];
+}
+
+static __always_inline void fdifference(u64 *a, u64 *b)
+{
+	u64 tmp[5] = { 0 };
+	u64 b0;
+	u64 b1;
+	u64 b2;
+	u64 b3;
+	u64 b4;
+	memcpy(tmp, b, 5 * sizeof(*b));
+	b0 = tmp[0];
+	b1 = tmp[1];
+	b2 = tmp[2];
+	b3 = tmp[3];
+	b4 = tmp[4];
+	tmp[0] = b0 + 0x3fffffffffff68LLU;
+	tmp[1] = b1 + 0x3ffffffffffff8LLU;
+	tmp[2] = b2 + 0x3ffffffffffff8LLU;
+	tmp[3] = b3 + 0x3ffffffffffff8LLU;
+	tmp[4] = b4 + 0x3ffffffffffff8LLU;
+	{
+		u64 xi = a[0];
+		u64 yi = tmp[0];
+		a[0] = yi - xi;
+	}
+	{
+		u64 xi = a[1];
+		u64 yi = tmp[1];
+		a[1] = yi - xi;
+	}
+	{
+		u64 xi = a[2];
+		u64 yi = tmp[2];
+		a[2] = yi - xi;
+	}
+	{
+		u64 xi = a[3];
+		u64 yi = tmp[3];
+		a[3] = yi - xi;
+	}
+	{
+		u64 xi = a[4];
+		u64 yi = tmp[4];
+		a[4] = yi - xi;
+	}
+}
+
+static __always_inline void fscalar(u64 *output, u64 *b, u64 s)
+{
+	u128 tmp[5];
+	u128 b4;
+	u128 b0;
+	u128 b4_;
+	u128 b0_;
+	{
+		u64 xi = b[0];
+		tmp[0] = ((u128)(xi) * (s));
+	}
+	{
+		u64 xi = b[1];
+		tmp[1] = ((u128)(xi) * (s));
+	}
+	{
+		u64 xi = b[2];
+		tmp[2] = ((u128)(xi) * (s));
+	}
+	{
+		u64 xi = b[3];
+		tmp[3] = ((u128)(xi) * (s));
+	}
+	{
+		u64 xi = b[4];
+		tmp[4] = ((u128)(xi) * (s));
+	}
+	fproduct_carry_wide_(tmp);
+	b4 = tmp[4];
+	b0 = tmp[0];
+	b4_ = ((b4) & (((u128)(0x7ffffffffffffLLU))));
+	b0_ = ((b0) + (((u128)(19) * (((u64)(((b4) >> (51))))))));
+	tmp[4] = b4_;
+	tmp[0] = b0_;
+	fproduct_copy_from_wide_(output, tmp);
+}
+
+static __always_inline void fmul(u64 *output, u64 *a, u64 *b)
+{
+	fmul_fmul(output, a, b);
+}
+
+static __always_inline void crecip(u64 *output, u64 *input)
+{
+	crecip_crecip(output, input);
+}
+
+static __always_inline void point_swap_conditional_step(u64 *a, u64 *b,
+							u64 swap1, u32 ctr)
+{
+	u32 i = ctr - 1;
+	u64 ai = a[i];
+	u64 bi = b[i];
+	u64 x = swap1 & (ai ^ bi);
+	u64 ai1 = ai ^ x;
+	u64 bi1 = bi ^ x;
+	a[i] = ai1;
+	b[i] = bi1;
+}
+
+static __always_inline void point_swap_conditional5(u64 *a, u64 *b, u64 swap1)
+{
+	point_swap_conditional_step(a, b, swap1, 5);
+	point_swap_conditional_step(a, b, swap1, 4);
+	point_swap_conditional_step(a, b, swap1, 3);
+	point_swap_conditional_step(a, b, swap1, 2);
+	point_swap_conditional_step(a, b, swap1, 1);
+}
+
+static __always_inline void point_swap_conditional(u64 *a, u64 *b, u64 iswap)
+{
+	u64 swap1 = 0 - iswap;
+	point_swap_conditional5(a, b, swap1);
+	point_swap_conditional5(a + 5, b + 5, swap1);
+}
+
+static __always_inline void point_copy(u64 *output, u64 *input)
+{
+	memcpy(output, input, 5 * sizeof(*input));
+	memcpy(output + 5, input + 5, 5 * sizeof(*input));
+}
+
+static __always_inline void addanddouble_fmonty(u64 *pp, u64 *ppq, u64 *p,
+						u64 *pq, u64 *qmqp)
+{
+	u64 *qx = qmqp;
+	u64 *x2 = pp;
+	u64 *z2 = pp + 5;
+	u64 *x3 = ppq;
+	u64 *z3 = ppq + 5;
+	u64 *x = p;
+	u64 *z = p + 5;
+	u64 *xprime = pq;
+	u64 *zprime = pq + 5;
+	u64 buf[40] = { 0 };
+	u64 *origx = buf;
+	u64 *origxprime0 = buf + 5;
+	u64 *xxprime0;
+	u64 *zzprime0;
+	u64 *origxprime;
+	xxprime0 = buf + 25;
+	zzprime0 = buf + 30;
+	memcpy(origx, x, 5 * sizeof(*x));
+	fsum(x, z);
+	fdifference(z, origx);
+	memcpy(origxprime0, xprime, 5 * sizeof(*xprime));
+	fsum(xprime, zprime);
+	fdifference(zprime, origxprime0);
+	fmul(xxprime0, xprime, z);
+	fmul(zzprime0, x, zprime);
+	origxprime = buf + 5;
+	{
+		u64 *xx0;
+		u64 *zz0;
+		u64 *xxprime;
+		u64 *zzprime;
+		u64 *zzzprime;
+		xx0 = buf + 15;
+		zz0 = buf + 20;
+		xxprime = buf + 25;
+		zzprime = buf + 30;
+		zzzprime = buf + 35;
+		memcpy(origxprime, xxprime, 5 * sizeof(*xxprime));
+		fsum(xxprime, zzprime);
+		fdifference(zzprime, origxprime);
+		fsquare_fsquare_times(x3, xxprime, 1);
+		fsquare_fsquare_times(zzzprime, zzprime, 1);
+		fmul(z3, zzzprime, qx);
+		fsquare_fsquare_times(xx0, x, 1);
+		fsquare_fsquare_times(zz0, z, 1);
+		{
+			u64 *zzz;
+			u64 *xx;
+			u64 *zz;
+			u64 scalar;
+			zzz = buf + 10;
+			xx = buf + 15;
+			zz = buf + 20;
+			fmul(x2, xx, zz);
+			fdifference(zz, xx);
+			scalar = 121665;
+			fscalar(zzz, zz, scalar);
+			fsum(zzz, xx);
+			fmul(z2, zzz, zz);
+		}
+	}
+}
+
+static __always_inline void
+ladder_smallloop_cmult_small_loop_step(u64 *nq, u64 *nqpq, u64 *nq2, u64 *nqpq2,
+				       u64 *q, u8 byt)
+{
+	u64 bit0 = (u64)(byt >> 7);
+	u64 bit;
+	point_swap_conditional(nq, nqpq, bit0);
+	addanddouble_fmonty(nq2, nqpq2, nq, nqpq, q);
+	bit = (u64)(byt >> 7);
+	point_swap_conditional(nq2, nqpq2, bit);
+}
+
+static __always_inline void
+ladder_smallloop_cmult_small_loop_double_step(u64 *nq, u64 *nqpq, u64 *nq2,
+					      u64 *nqpq2, u64 *q, u8 byt)
+{
+	u8 byt1;
+	ladder_smallloop_cmult_small_loop_step(nq, nqpq, nq2, nqpq2, q, byt);
+	byt1 = byt << 1;
+	ladder_smallloop_cmult_small_loop_step(nq2, nqpq2, nq, nqpq, q, byt1);
+}
+
+static __always_inline void
+ladder_smallloop_cmult_small_loop(u64 *nq, u64 *nqpq, u64 *nq2, u64 *nqpq2,
+				  u64 *q, u8 byt, u32 i)
+{
+	while (i--) {
+		ladder_smallloop_cmult_small_loop_double_step(nq, nqpq, nq2,
+							      nqpq2, q, byt);
+		byt <<= 2;
+	}
+}
+
+static __always_inline void ladder_bigloop_cmult_big_loop(u8 *n1, u64 *nq,
+							  u64 *nqpq, u64 *nq2,
+							  u64 *nqpq2, u64 *q,
+							  u32 i)
+{
+	while (i--) {
+		u8 byte = n1[i];
+		ladder_smallloop_cmult_small_loop(nq, nqpq, nq2, nqpq2, q,
+						  byte, 4);
+	}
+}
+
+static void ladder_cmult(u64 *result, u8 *n1, u64 *q)
+{
+	u64 point_buf[40] = { 0 };
+	u64 *nq = point_buf;
+	u64 *nqpq = point_buf + 10;
+	u64 *nq2 = point_buf + 20;
+	u64 *nqpq2 = point_buf + 30;
+	point_copy(nqpq, q);
+	nq[0] = 1;
+	ladder_bigloop_cmult_big_loop(n1, nq, nqpq, nq2, nqpq2, q, 32);
+	point_copy(result, nq);
+}
+
+static __always_inline void format_fexpand(u64 *output, const u8 *input)
+{
+	const u8 *x00 = input + 6;
+	const u8 *x01 = input + 12;
+	const u8 *x02 = input + 19;
+	const u8 *x0 = input + 24;
+	u64 i0, i1, i2, i3, i4, output0, output1, output2, output3, output4;
+	i0 = get_unaligned_le64(input);
+	i1 = get_unaligned_le64(x00);
+	i2 = get_unaligned_le64(x01);
+	i3 = get_unaligned_le64(x02);
+	i4 = get_unaligned_le64(x0);
+	output0 = i0 & 0x7ffffffffffffLLU;
+	output1 = i1 >> 3 & 0x7ffffffffffffLLU;
+	output2 = i2 >> 6 & 0x7ffffffffffffLLU;
+	output3 = i3 >> 1 & 0x7ffffffffffffLLU;
+	output4 = i4 >> 12 & 0x7ffffffffffffLLU;
+	output[0] = output0;
+	output[1] = output1;
+	output[2] = output2;
+	output[3] = output3;
+	output[4] = output4;
+}
+
+static __always_inline void format_fcontract_first_carry_pass(u64 *input)
+{
+	u64 t0 = input[0];
+	u64 t1 = input[1];
+	u64 t2 = input[2];
+	u64 t3 = input[3];
+	u64 t4 = input[4];
+	u64 t1_ = t1 + (t0 >> 51);
+	u64 t0_ = t0 & 0x7ffffffffffffLLU;
+	u64 t2_ = t2 + (t1_ >> 51);
+	u64 t1__ = t1_ & 0x7ffffffffffffLLU;
+	u64 t3_ = t3 + (t2_ >> 51);
+	u64 t2__ = t2_ & 0x7ffffffffffffLLU;
+	u64 t4_ = t4 + (t3_ >> 51);
+	u64 t3__ = t3_ & 0x7ffffffffffffLLU;
+	input[0] = t0_;
+	input[1] = t1__;
+	input[2] = t2__;
+	input[3] = t3__;
+	input[4] = t4_;
+}
+
+static __always_inline void format_fcontract_first_carry_full(u64 *input)
+{
+	format_fcontract_first_carry_pass(input);
+	modulo_carry_top(input);
+}
+
+static __always_inline void format_fcontract_second_carry_pass(u64 *input)
+{
+	u64 t0 = input[0];
+	u64 t1 = input[1];
+	u64 t2 = input[2];
+	u64 t3 = input[3];
+	u64 t4 = input[4];
+	u64 t1_ = t1 + (t0 >> 51);
+	u64 t0_ = t0 & 0x7ffffffffffffLLU;
+	u64 t2_ = t2 + (t1_ >> 51);
+	u64 t1__ = t1_ & 0x7ffffffffffffLLU;
+	u64 t3_ = t3 + (t2_ >> 51);
+	u64 t2__ = t2_ & 0x7ffffffffffffLLU;
+	u64 t4_ = t4 + (t3_ >> 51);
+	u64 t3__ = t3_ & 0x7ffffffffffffLLU;
+	input[0] = t0_;
+	input[1] = t1__;
+	input[2] = t2__;
+	input[3] = t3__;
+	input[4] = t4_;
+}
+
+static __always_inline void format_fcontract_second_carry_full(u64 *input)
+{
+	u64 i0;
+	u64 i1;
+	u64 i0_;
+	u64 i1_;
+	format_fcontract_second_carry_pass(input);
+	modulo_carry_top(input);
+	i0 = input[0];
+	i1 = input[1];
+	i0_ = i0 & 0x7ffffffffffffLLU;
+	i1_ = i1 + (i0 >> 51);
+	input[0] = i0_;
+	input[1] = i1_;
+}
+
+static __always_inline void format_fcontract_trim(u64 *input)
+{
+	u64 a0 = input[0];
+	u64 a1 = input[1];
+	u64 a2 = input[2];
+	u64 a3 = input[3];
+	u64 a4 = input[4];
+	u64 mask0 = u64_gte_mask(a0, 0x7ffffffffffedLLU);
+	u64 mask1 = u64_eq_mask(a1, 0x7ffffffffffffLLU);
+	u64 mask2 = u64_eq_mask(a2, 0x7ffffffffffffLLU);
+	u64 mask3 = u64_eq_mask(a3, 0x7ffffffffffffLLU);
+	u64 mask4 = u64_eq_mask(a4, 0x7ffffffffffffLLU);
+	u64 mask = (((mask0 & mask1) & mask2) & mask3) & mask4;
+	u64 a0_ = a0 - (0x7ffffffffffedLLU & mask);
+	u64 a1_ = a1 - (0x7ffffffffffffLLU & mask);
+	u64 a2_ = a2 - (0x7ffffffffffffLLU & mask);
+	u64 a3_ = a3 - (0x7ffffffffffffLLU & mask);
+	u64 a4_ = a4 - (0x7ffffffffffffLLU & mask);
+	input[0] = a0_;
+	input[1] = a1_;
+	input[2] = a2_;
+	input[3] = a3_;
+	input[4] = a4_;
+}
+
+static __always_inline void format_fcontract_store(u8 *output, u64 *input)
+{
+	u64 t0 = input[0];
+	u64 t1 = input[1];
+	u64 t2 = input[2];
+	u64 t3 = input[3];
+	u64 t4 = input[4];
+	u64 o0 = t1 << 51 | t0;
+	u64 o1 = t2 << 38 | t1 >> 13;
+	u64 o2 = t3 << 25 | t2 >> 26;
+	u64 o3 = t4 << 12 | t3 >> 39;
+	u8 *b0 = output;
+	u8 *b1 = output + 8;
+	u8 *b2 = output + 16;
+	u8 *b3 = output + 24;
+	put_unaligned_le64(o0, b0);
+	put_unaligned_le64(o1, b1);
+	put_unaligned_le64(o2, b2);
+	put_unaligned_le64(o3, b3);
+}
+
+static __always_inline void format_fcontract(u8 *output, u64 *input)
+{
+	format_fcontract_first_carry_full(input);
+	format_fcontract_second_carry_full(input);
+	format_fcontract_trim(input);
+	format_fcontract_store(output, input);
+}
+
+static __always_inline void format_scalar_of_point(u8 *scalar, u64 *point)
+{
+	u64 *x = point;
+	u64 *z = point + 5;
+	u64 buf[10] __aligned(32) = { 0 };
+	u64 *zmone = buf;
+	u64 *sc = buf + 5;
+	crecip(zmone, z);
+	fmul(sc, x, zmone);
+	format_fcontract(scalar, sc);
+}
+
+void curve25519_generic(u8 mypublic[CURVE25519_KEY_SIZE],
+			const u8 secret[CURVE25519_KEY_SIZE],
+			const u8 basepoint[CURVE25519_KEY_SIZE])
+{
+	u64 buf0[10] __aligned(32) = { 0 };
+	u64 *x0 = buf0;
+	u64 *z = buf0 + 5;
+	u64 *q;
+	format_fexpand(x0, basepoint);
+	z[0] = 1;
+	q = buf0;
+	{
+		u8 e[32] __aligned(32) = { 0 };
+		u8 *scalar;
+		memcpy(e, secret, 32);
+		curve25519_clamp_secret(e);
+		scalar = e;
+		{
+			u64 buf[15] = { 0 };
+			u64 *nq = buf;
+			u64 *x = nq;
+			x[0] = 1;
+			ladder_cmult(nq, scalar, q);
+			format_scalar_of_point(mypublic, nq);
+			memzero_explicit(buf, sizeof(buf));
+		}
+		memzero_explicit(e, sizeof(e));
+	}
+	memzero_explicit(buf0, sizeof(buf0));
+}
diff --git a/lib/crypto/curve25519.c b/lib/crypto/curve25519.c
new file mode 100644
index 000000000000..0106bebe6900
--- /dev/null
+++ b/lib/crypto/curve25519.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This is an implementation of the Curve25519 ECDH algorithm, using either
+ * a 32-bit implementation or a 64-bit implementation with 128-bit integers,
+ * depending on what is supported by the target compiler.
+ *
+ * Information: https://cr.yp.to/ecdh.html
+ */
+
+#include <crypto/curve25519.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+const u8 curve25519_null_point[CURVE25519_KEY_SIZE] __aligned(32) = { 0 };
+const u8 curve25519_base_point[CURVE25519_KEY_SIZE] __aligned(32) = { 9 };
+
+EXPORT_SYMBOL(curve25519_null_point);
+EXPORT_SYMBOL(curve25519_base_point);
+EXPORT_SYMBOL(curve25519_generic);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Curve25519 scalar multiplication");
+MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
diff --git a/lib/crypto/libchacha.c b/lib/crypto/libchacha.c
new file mode 100644
index 000000000000..dabc3accae05
--- /dev/null
+++ b/lib/crypto/libchacha.c
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * The ChaCha stream cipher (RFC7539)
+ *
+ * Copyright (C) 2015 Martin Willi
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/module.h>
+
+#include <crypto/algapi.h> // for crypto_xor_cpy
+#include <crypto/chacha.h>
+
+void chacha_crypt_generic(u32 *state, u8 *dst, const u8 *src,
+			  unsigned int bytes, int nrounds)
+{
+	/* aligned to potentially speed up crypto_xor() */
+	u8 stream[CHACHA_BLOCK_SIZE] __aligned(sizeof(long));
+
+	while (bytes >= CHACHA_BLOCK_SIZE) {
+		chacha_block_generic(state, stream, nrounds);
+		crypto_xor_cpy(dst, src, stream, CHACHA_BLOCK_SIZE);
+		bytes -= CHACHA_BLOCK_SIZE;
+		dst += CHACHA_BLOCK_SIZE;
+		src += CHACHA_BLOCK_SIZE;
+	}
+	if (bytes) {
+		chacha_block_generic(state, stream, nrounds);
+		crypto_xor_cpy(dst, src, stream, bytes);
+	}
+}
+EXPORT_SYMBOL(chacha_crypt_generic);
+
+MODULE_LICENSE("GPL");
diff --git a/lib/crypto/poly1305.c b/lib/crypto/poly1305.c
new file mode 100644
index 000000000000..32ec293c65ae
--- /dev/null
+++ b/lib/crypto/poly1305.c
@@ -0,0 +1,232 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Poly1305 authenticator algorithm, RFC7539
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * Based on public domain code by Andrew Moon and Daniel J. Bernstein.
+ */
+
+#include <crypto/internal/poly1305.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <asm/unaligned.h>
+
+static inline u64 mlt(u64 a, u64 b)
+{
+	return a * b;
+}
+
+static inline u32 sr(u64 v, u_char n)
+{
+	return v >> n;
+}
+
+static inline u32 and(u32 v, u32 mask)
+{
+	return v & mask;
+}
+
+void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key)
+{
+	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
+	key->r[0] = (get_unaligned_le32(raw_key +  0) >> 0) & 0x3ffffff;
+	key->r[1] = (get_unaligned_le32(raw_key +  3) >> 2) & 0x3ffff03;
+	key->r[2] = (get_unaligned_le32(raw_key +  6) >> 4) & 0x3ffc0ff;
+	key->r[3] = (get_unaligned_le32(raw_key +  9) >> 6) & 0x3f03fff;
+	key->r[4] = (get_unaligned_le32(raw_key + 12) >> 8) & 0x00fffff;
+}
+EXPORT_SYMBOL_GPL(poly1305_core_setkey);
+
+void poly1305_core_blocks(struct poly1305_state *state,
+			  const struct poly1305_key *key, const void *src,
+			  unsigned int nblocks, u32 hibit)
+{
+	u32 r0, r1, r2, r3, r4;
+	u32 s1, s2, s3, s4;
+	u32 h0, h1, h2, h3, h4;
+	u64 d0, d1, d2, d3, d4;
+
+	if (!nblocks)
+		return;
+
+	r0 = key->r[0];
+	r1 = key->r[1];
+	r2 = key->r[2];
+	r3 = key->r[3];
+	r4 = key->r[4];
+
+	s1 = r1 * 5;
+	s2 = r2 * 5;
+	s3 = r3 * 5;
+	s4 = r4 * 5;
+
+	h0 = state->h[0];
+	h1 = state->h[1];
+	h2 = state->h[2];
+	h3 = state->h[3];
+	h4 = state->h[4];
+
+	do {
+		/* h += m[i] */
+		h0 += (get_unaligned_le32(src +  0) >> 0) & 0x3ffffff;
+		h1 += (get_unaligned_le32(src +  3) >> 2) & 0x3ffffff;
+		h2 += (get_unaligned_le32(src +  6) >> 4) & 0x3ffffff;
+		h3 += (get_unaligned_le32(src +  9) >> 6) & 0x3ffffff;
+		h4 += (get_unaligned_le32(src + 12) >> 8) | (hibit << 24);
+
+		/* h *= r */
+		d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) +
+		     mlt(h3, s2) + mlt(h4, s1);
+		d1 = mlt(h0, r1) + mlt(h1, r0) + mlt(h2, s4) +
+		     mlt(h3, s3) + mlt(h4, s2);
+		d2 = mlt(h0, r2) + mlt(h1, r1) + mlt(h2, r0) +
+		     mlt(h3, s4) + mlt(h4, s3);
+		d3 = mlt(h0, r3) + mlt(h1, r2) + mlt(h2, r1) +
+		     mlt(h3, r0) + mlt(h4, s4);
+		d4 = mlt(h0, r4) + mlt(h1, r3) + mlt(h2, r2) +
+		     mlt(h3, r1) + mlt(h4, r0);
+
+		/* (partial) h %= p */
+		d1 += sr(d0, 26);     h0 = and(d0, 0x3ffffff);
+		d2 += sr(d1, 26);     h1 = and(d1, 0x3ffffff);
+		d3 += sr(d2, 26);     h2 = and(d2, 0x3ffffff);
+		d4 += sr(d3, 26);     h3 = and(d3, 0x3ffffff);
+		h0 += sr(d4, 26) * 5; h4 = and(d4, 0x3ffffff);
+		h1 += h0 >> 26;       h0 = h0 & 0x3ffffff;
+
+		src += POLY1305_BLOCK_SIZE;
+	} while (--nblocks);
+
+	state->h[0] = h0;
+	state->h[1] = h1;
+	state->h[2] = h2;
+	state->h[3] = h3;
+	state->h[4] = h4;
+}
+EXPORT_SYMBOL_GPL(poly1305_core_blocks);
+
+void poly1305_core_emit(const struct poly1305_state *state, void *dst)
+{
+	u32 h0, h1, h2, h3, h4;
+	u32 g0, g1, g2, g3, g4;
+	u32 mask;
+
+	/* fully carry h */
+	h0 = state->h[0];
+	h1 = state->h[1];
+	h2 = state->h[2];
+	h3 = state->h[3];
+	h4 = state->h[4];
+
+	h2 += (h1 >> 26);     h1 = h1 & 0x3ffffff;
+	h3 += (h2 >> 26);     h2 = h2 & 0x3ffffff;
+	h4 += (h3 >> 26);     h3 = h3 & 0x3ffffff;
+	h0 += (h4 >> 26) * 5; h4 = h4 & 0x3ffffff;
+	h1 += (h0 >> 26);     h0 = h0 & 0x3ffffff;
+
+	/* compute h + -p */
+	g0 = h0 + 5;
+	g1 = h1 + (g0 >> 26);             g0 &= 0x3ffffff;
+	g2 = h2 + (g1 >> 26);             g1 &= 0x3ffffff;
+	g3 = h3 + (g2 >> 26);             g2 &= 0x3ffffff;
+	g4 = h4 + (g3 >> 26) - (1 << 26); g3 &= 0x3ffffff;
+
+	/* select h if h < p, or h + -p if h >= p */
+	mask = (g4 >> ((sizeof(u32) * 8) - 1)) - 1;
+	g0 &= mask;
+	g1 &= mask;
+	g2 &= mask;
+	g3 &= mask;
+	g4 &= mask;
+	mask = ~mask;
+	h0 = (h0 & mask) | g0;
+	h1 = (h1 & mask) | g1;
+	h2 = (h2 & mask) | g2;
+	h3 = (h3 & mask) | g3;
+	h4 = (h4 & mask) | g4;
+
+	/* h = h % (2^128) */
+	put_unaligned_le32((h0 >>  0) | (h1 << 26), dst +  0);
+	put_unaligned_le32((h1 >>  6) | (h2 << 20), dst +  4);
+	put_unaligned_le32((h2 >> 12) | (h3 << 14), dst +  8);
+	put_unaligned_le32((h3 >> 18) | (h4 <<  8), dst + 12);
+}
+EXPORT_SYMBOL_GPL(poly1305_core_emit);
+
+void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 *key)
+{
+	poly1305_core_setkey(desc->r, key);
+	desc->s[0] = get_unaligned_le32(key + 16);
+	desc->s[1] = get_unaligned_le32(key + 20);
+	desc->s[2] = get_unaligned_le32(key + 24);
+	desc->s[3] = get_unaligned_le32(key + 28);
+	poly1305_core_init(&desc->h);
+	desc->buflen = 0;
+	desc->sset = true;
+	desc->rset = 1;
+}
+EXPORT_SYMBOL_GPL(poly1305_init_generic);
+
+void poly1305_update_generic(struct poly1305_desc_ctx *desc, const u8 *src,
+			     unsigned int nbytes)
+{
+	unsigned int bytes;
+
+	if (unlikely(desc->buflen)) {
+		bytes = min(nbytes, POLY1305_BLOCK_SIZE - desc->buflen);
+		memcpy(desc->buf + desc->buflen, src, bytes);
+		src += bytes;
+		nbytes -= bytes;
+		desc->buflen += bytes;
+
+		if (desc->buflen == POLY1305_BLOCK_SIZE) {
+			poly1305_core_blocks(&desc->h, desc->r, desc->buf, 1, 1);
+			desc->buflen = 0;
+		}
+	}
+
+	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
+		poly1305_core_blocks(&desc->h, desc->r, src,
+				     nbytes / POLY1305_BLOCK_SIZE, 1);
+		src += nbytes - (nbytes % POLY1305_BLOCK_SIZE);
+		nbytes %= POLY1305_BLOCK_SIZE;
+	}
+
+	if (unlikely(nbytes)) {
+		desc->buflen = nbytes;
+		memcpy(desc->buf, src, nbytes);
+	}
+}
+EXPORT_SYMBOL_GPL(poly1305_update_generic);
+
+void poly1305_final_generic(struct poly1305_desc_ctx *desc, u8 *dst)
+{
+	__le32 digest[4];
+	u64 f = 0;
+
+	if (unlikely(desc->buflen)) {
+		desc->buf[desc->buflen++] = 1;
+		memset(desc->buf + desc->buflen, 0,
+		       POLY1305_BLOCK_SIZE - desc->buflen);
+		poly1305_core_blocks(&desc->h, desc->r, desc->buf, 1, 0);
+	}
+
+	poly1305_core_emit(&desc->h, digest);
+
+	/* mac = (h + s) % (2^128) */
+	f = (f >> 32) + le32_to_cpu(digest[0]) + desc->s[0];
+	put_unaligned_le32(f, dst + 0);
+	f = (f >> 32) + le32_to_cpu(digest[1]) + desc->s[1];
+	put_unaligned_le32(f, dst + 4);
+	f = (f >> 32) + le32_to_cpu(digest[2]) + desc->s[2];
+	put_unaligned_le32(f, dst + 8);
+	f = (f >> 32) + le32_to_cpu(digest[3]) + desc->s[3];
+	put_unaligned_le32(f, dst + 12);
+
+	*desc = (struct poly1305_desc_ctx){};
+}
+EXPORT_SYMBOL_GPL(poly1305_final_generic);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
diff --git a/lib/errname.c b/lib/errname.c
new file mode 100644
index 000000000000..0c4d3e66170e
--- /dev/null
+++ b/lib/errname.c
@@ -0,0 +1,223 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/build_bug.h>
+#include <linux/errno.h>
+#include <linux/errname.h>
+#include <linux/kernel.h>
+
+/*
+ * Ensure these tables do not accidentally become gigantic if some
+ * huge errno makes it in. On most architectures, the first table will
+ * only have about 140 entries, but mips and parisc have more sparsely
+ * allocated errnos (with EHWPOISON = 257 on parisc, and EDQUOT = 1133
+ * on mips), so this wastes a bit of space on those - though we
+ * special case the EDQUOT case.
+ */
+#define E(err) [err + BUILD_BUG_ON_ZERO(err <= 0 || err > 300)] = "-" #err
+static const char *names_0[] = {
+	E(E2BIG),
+	E(EACCES),
+	E(EADDRINUSE),
+	E(EADDRNOTAVAIL),
+	E(EADV),
+	E(EAFNOSUPPORT),
+	E(EALREADY),
+	E(EBADE),
+	E(EBADF),
+	E(EBADFD),
+	E(EBADMSG),
+	E(EBADR),
+	E(EBADRQC),
+	E(EBADSLT),
+	E(EBFONT),
+	E(EBUSY),
+#ifdef ECANCELLED
+	E(ECANCELLED),
+#endif
+	E(ECHILD),
+	E(ECHRNG),
+	E(ECOMM),
+	E(ECONNABORTED),
+	E(ECONNRESET),
+	E(EDEADLOCK),
+	E(EDESTADDRREQ),
+	E(EDOM),
+	E(EDOTDOT),
+#ifndef CONFIG_MIPS
+	E(EDQUOT),
+#endif
+	E(EEXIST),
+	E(EFAULT),
+	E(EFBIG),
+	E(EHOSTDOWN),
+	E(EHOSTUNREACH),
+	E(EHWPOISON),
+	E(EIDRM),
+	E(EILSEQ),
+#ifdef EINIT
+	E(EINIT),
+#endif
+	E(EINPROGRESS),
+	E(EINTR),
+	E(EINVAL),
+	E(EIO),
+	E(EISCONN),
+	E(EISDIR),
+	E(EISNAM),
+	E(EKEYEXPIRED),
+	E(EKEYREJECTED),
+	E(EKEYREVOKED),
+	E(EL2HLT),
+	E(EL2NSYNC),
+	E(EL3HLT),
+	E(EL3RST),
+	E(ELIBACC),
+	E(ELIBBAD),
+	E(ELIBEXEC),
+	E(ELIBMAX),
+	E(ELIBSCN),
+	E(ELNRNG),
+	E(ELOOP),
+	E(EMEDIUMTYPE),
+	E(EMFILE),
+	E(EMLINK),
+	E(EMSGSIZE),
+	E(EMULTIHOP),
+	E(ENAMETOOLONG),
+	E(ENAVAIL),
+	E(ENETDOWN),
+	E(ENETRESET),
+	E(ENETUNREACH),
+	E(ENFILE),
+	E(ENOANO),
+	E(ENOBUFS),
+	E(ENOCSI),
+	E(ENODATA),
+	E(ENODEV),
+	E(ENOENT),
+	E(ENOEXEC),
+	E(ENOKEY),
+	E(ENOLCK),
+	E(ENOLINK),
+	E(ENOMEDIUM),
+	E(ENOMEM),
+	E(ENOMSG),
+	E(ENONET),
+	E(ENOPKG),
+	E(ENOPROTOOPT),
+	E(ENOSPC),
+	E(ENOSR),
+	E(ENOSTR),
+#ifdef ENOSYM
+	E(ENOSYM),
+#endif
+	E(ENOSYS),
+	E(ENOTBLK),
+	E(ENOTCONN),
+	E(ENOTDIR),
+	E(ENOTEMPTY),
+	E(ENOTNAM),
+	E(ENOTRECOVERABLE),
+	E(ENOTSOCK),
+	E(ENOTTY),
+	E(ENOTUNIQ),
+	E(ENXIO),
+	E(EOPNOTSUPP),
+	E(EOVERFLOW),
+	E(EOWNERDEAD),
+	E(EPERM),
+	E(EPFNOSUPPORT),
+	E(EPIPE),
+#ifdef EPROCLIM
+	E(EPROCLIM),
+#endif
+	E(EPROTO),
+	E(EPROTONOSUPPORT),
+	E(EPROTOTYPE),
+	E(ERANGE),
+	E(EREMCHG),
+#ifdef EREMDEV
+	E(EREMDEV),
+#endif
+	E(EREMOTE),
+	E(EREMOTEIO),
+#ifdef EREMOTERELEASE
+	E(EREMOTERELEASE),
+#endif
+	E(ERESTART),
+	E(ERFKILL),
+	E(EROFS),
+#ifdef ERREMOTE
+	E(ERREMOTE),
+#endif
+	E(ESHUTDOWN),
+	E(ESOCKTNOSUPPORT),
+	E(ESPIPE),
+	E(ESRCH),
+	E(ESRMNT),
+	E(ESTALE),
+	E(ESTRPIPE),
+	E(ETIME),
+	E(ETIMEDOUT),
+	E(ETOOMANYREFS),
+	E(ETXTBSY),
+	E(EUCLEAN),
+	E(EUNATCH),
+	E(EUSERS),
+	E(EXDEV),
+	E(EXFULL),
+
+	E(ECANCELED), /* ECANCELLED */
+	E(EAGAIN), /* EWOULDBLOCK */
+	E(ECONNREFUSED), /* EREFUSED */
+	E(EDEADLK), /* EDEADLOCK */
+};
+#undef E
+
+#define E(err) [err - 512 + BUILD_BUG_ON_ZERO(err < 512 || err > 550)] = "-" #err
+static const char *names_512[] = {
+	E(ERESTARTSYS),
+	E(ERESTARTNOINTR),
+	E(ERESTARTNOHAND),
+	E(ENOIOCTLCMD),
+	E(ERESTART_RESTARTBLOCK),
+	E(EPROBE_DEFER),
+	E(EOPENSTALE),
+	E(ENOPARAM),
+
+	E(EBADHANDLE),
+	E(ENOTSYNC),
+	E(EBADCOOKIE),
+	E(ENOTSUPP),
+	E(ETOOSMALL),
+	E(ESERVERFAULT),
+	E(EBADTYPE),
+	E(EJUKEBOX),
+	E(EIOCBQUEUED),
+	E(ERECALLCONFLICT),
+};
+#undef E
+
+static const char *__errname(unsigned err)
+{
+	if (err < ARRAY_SIZE(names_0))
+		return names_0[err];
+	if (err >= 512 && err - 512 < ARRAY_SIZE(names_512))
+		return names_512[err - 512];
+	/* But why? */
+	if (IS_ENABLED(CONFIG_MIPS) && err == EDQUOT) /* 1133 */
+		return "-EDQUOT";
+	return NULL;
+}
+
+/*
+ * errname(EIO) -> "EIO"
+ * errname(-EIO) -> "-EIO"
+ */
+const char *errname(int err)
+{
+	const char *name = __errname(abs(err));
+	if (!name)
+		return NULL;
+
+	return err > 0 ? name + 1 : name;
+}
diff --git a/lib/kunit/Kconfig b/lib/kunit/Kconfig
new file mode 100644
index 000000000000..af37016bfdd4
--- /dev/null
+++ b/lib/kunit/Kconfig
@@ -0,0 +1,36 @@
+#
+# KUnit base configuration
+#
+
+menuconfig KUNIT
+	bool "KUnit - Enable support for unit tests"
+	help
+	  Enables support for kernel unit tests (KUnit), a lightweight unit
+	  testing and mocking framework for the Linux kernel. These tests are
+	  able to be run locally on a developer's workstation without a VM or
+	  special hardware when using UML. Can also be used on most other
+	  architectures. For more information, please see
+	  Documentation/dev-tools/kunit/.
+
+if KUNIT
+
+config KUNIT_TEST
+	bool "KUnit test for KUnit"
+	help
+	  Enables the unit tests for the KUnit test framework. These tests test
+	  the KUnit test framework itself; the tests are both written using
+	  KUnit and test KUnit. This option should only be enabled for testing
+	  purposes by developers interested in testing that KUnit works as
+	  expected.
+
+config KUNIT_EXAMPLE_TEST
+	bool "Example test for KUnit"
+	help
+	  Enables an example unit test that illustrates some of the basic
+	  features of KUnit. This test only exists to help new users understand
+	  what KUnit is and how it is used. Please refer to the example test
+	  itself, lib/kunit/example-test.c, for more information. This option
+	  is intended for curious hackers who would like to understand how to
+	  use KUnit for kernel development.
+
+endif # KUNIT
diff --git a/lib/kunit/Makefile b/lib/kunit/Makefile
new file mode 100644
index 000000000000..769d9402b5d3
--- /dev/null
+++ b/lib/kunit/Makefile
@@ -0,0 +1,9 @@
+obj-$(CONFIG_KUNIT) +=			test.o \
+					string-stream.o \
+					assert.o \
+					try-catch.o
+
+obj-$(CONFIG_KUNIT_TEST) +=		test-test.o \
+					string-stream-test.o
+
+obj-$(CONFIG_KUNIT_EXAMPLE_TEST) +=	example-test.o
diff --git a/lib/kunit/assert.c b/lib/kunit/assert.c
new file mode 100644
index 000000000000..86013d4cf891
--- /dev/null
+++ b/lib/kunit/assert.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Assertion and expectation serialization API.
+ *
+ * Copyright (C) 2019, Google LLC.
+ * Author: Brendan Higgins <brendanhiggins@google.com>
+ */
+#include <kunit/assert.h>
+
+void kunit_base_assert_format(const struct kunit_assert *assert,
+			      struct string_stream *stream)
+{
+	const char *expect_or_assert = NULL;
+
+	switch (assert->type) {
+	case KUNIT_EXPECTATION:
+		expect_or_assert = "EXPECTATION";
+		break;
+	case KUNIT_ASSERTION:
+		expect_or_assert = "ASSERTION";
+		break;
+	}
+
+	string_stream_add(stream, "%s FAILED at %s:%d\n",
+			 expect_or_assert, assert->file, assert->line);
+}
+
+void kunit_assert_print_msg(const struct kunit_assert *assert,
+			    struct string_stream *stream)
+{
+	if (assert->message.fmt)
+		string_stream_add(stream, "\n%pV", &assert->message);
+}
+
+void kunit_fail_assert_format(const struct kunit_assert *assert,
+			      struct string_stream *stream)
+{
+	kunit_base_assert_format(assert, stream);
+	string_stream_add(stream, "%pV", &assert->message);
+}
+
+void kunit_unary_assert_format(const struct kunit_assert *assert,
+			       struct string_stream *stream)
+{
+	struct kunit_unary_assert *unary_assert = container_of(
+			assert, struct kunit_unary_assert, assert);
+
+	kunit_base_assert_format(assert, stream);
+	if (unary_assert->expected_true)
+		string_stream_add(stream,
+				 "\tExpected %s to be true, but is false\n",
+				 unary_assert->condition);
+	else
+		string_stream_add(stream,
+				 "\tExpected %s to be false, but is true\n",
+				 unary_assert->condition);
+	kunit_assert_print_msg(assert, stream);
+}
+
+void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert,
+				     struct string_stream *stream)
+{
+	struct kunit_ptr_not_err_assert *ptr_assert = container_of(
+			assert, struct kunit_ptr_not_err_assert, assert);
+
+	kunit_base_assert_format(assert, stream);
+	if (!ptr_assert->value) {
+		string_stream_add(stream,
+				 "\tExpected %s is not null, but is\n",
+				 ptr_assert->text);
+	} else if (IS_ERR(ptr_assert->value)) {
+		string_stream_add(stream,
+				 "\tExpected %s is not error, but is: %ld\n",
+				 ptr_assert->text,
+				 PTR_ERR(ptr_assert->value));
+	}
+	kunit_assert_print_msg(assert, stream);
+}
+
+void kunit_binary_assert_format(const struct kunit_assert *assert,
+				struct string_stream *stream)
+{
+	struct kunit_binary_assert *binary_assert = container_of(
+			assert, struct kunit_binary_assert, assert);
+
+	kunit_base_assert_format(assert, stream);
+	string_stream_add(stream,
+			 "\tExpected %s %s %s, but\n",
+			 binary_assert->left_text,
+			 binary_assert->operation,
+			 binary_assert->right_text);
+	string_stream_add(stream, "\t\t%s == %lld\n",
+			 binary_assert->left_text,
+			 binary_assert->left_value);
+	string_stream_add(stream, "\t\t%s == %lld",
+			 binary_assert->right_text,
+			 binary_assert->right_value);
+	kunit_assert_print_msg(assert, stream);
+}
+
+void kunit_binary_ptr_assert_format(const struct kunit_assert *assert,
+				    struct string_stream *stream)
+{
+	struct kunit_binary_ptr_assert *binary_assert = container_of(
+			assert, struct kunit_binary_ptr_assert, assert);
+
+	kunit_base_assert_format(assert, stream);
+	string_stream_add(stream,
+			 "\tExpected %s %s %s, but\n",
+			 binary_assert->left_text,
+			 binary_assert->operation,
+			 binary_assert->right_text);
+	string_stream_add(stream, "\t\t%s == %pK\n",
+			 binary_assert->left_text,
+			 binary_assert->left_value);
+	string_stream_add(stream, "\t\t%s == %pK",
+			 binary_assert->right_text,
+			 binary_assert->right_value);
+	kunit_assert_print_msg(assert, stream);
+}
+
+void kunit_binary_str_assert_format(const struct kunit_assert *assert,
+				    struct string_stream *stream)
+{
+	struct kunit_binary_str_assert *binary_assert = container_of(
+			assert, struct kunit_binary_str_assert, assert);
+
+	kunit_base_assert_format(assert, stream);
+	string_stream_add(stream,
+			 "\tExpected %s %s %s, but\n",
+			 binary_assert->left_text,
+			 binary_assert->operation,
+			 binary_assert->right_text);
+	string_stream_add(stream, "\t\t%s == %s\n",
+			 binary_assert->left_text,
+			 binary_assert->left_value);
+	string_stream_add(stream, "\t\t%s == %s",
+			 binary_assert->right_text,
+			 binary_assert->right_value);
+	kunit_assert_print_msg(assert, stream);
+}
diff --git a/lib/kunit/example-test.c b/lib/kunit/example-test.c
new file mode 100644
index 000000000000..f64a829aa441
--- /dev/null
+++ b/lib/kunit/example-test.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Example KUnit test to show how to use KUnit.
+ *
+ * Copyright (C) 2019, Google LLC.
+ * Author: Brendan Higgins <brendanhiggins@google.com>
+ */
+
+#include <kunit/test.h>
+
+/*
+ * This is the most fundamental element of KUnit, the test case. A test case
+ * makes a set EXPECTATIONs and ASSERTIONs about the behavior of some code; if
+ * any expectations or assertions are not met, the test fails; otherwise, the
+ * test passes.
+ *
+ * In KUnit, a test case is just a function with the signature
+ * `void (*)(struct kunit *)`. `struct kunit` is a context object that stores
+ * information about the current test.
+ */
+static void example_simple_test(struct kunit *test)
+{
+	/*
+	 * This is an EXPECTATION; it is how KUnit tests things. When you want
+	 * to test a piece of code, you set some expectations about what the
+	 * code should do. KUnit then runs the test and verifies that the code's
+	 * behavior matched what was expected.
+	 */
+	KUNIT_EXPECT_EQ(test, 1 + 1, 2);
+}
+
+/*
+ * This is run once before each test case, see the comment on
+ * example_test_suite for more information.
+ */
+static int example_test_init(struct kunit *test)
+{
+	kunit_info(test, "initializing\n");
+
+	return 0;
+}
+
+/*
+ * Here we make a list of all the test cases we want to add to the test suite
+ * below.
+ */
+static struct kunit_case example_test_cases[] = {
+	/*
+	 * This is a helper to create a test case object from a test case
+	 * function; its exact function is not important to understand how to
+	 * use KUnit, just know that this is how you associate test cases with a
+	 * test suite.
+	 */
+	KUNIT_CASE(example_simple_test),
+	{}
+};
+
+/*
+ * This defines a suite or grouping of tests.
+ *
+ * Test cases are defined as belonging to the suite by adding them to
+ * `kunit_cases`.
+ *
+ * Often it is desirable to run some function which will set up things which
+ * will be used by every test; this is accomplished with an `init` function
+ * which runs before each test case is invoked. Similarly, an `exit` function
+ * may be specified which runs after every test case and can be used to for
+ * cleanup. For clarity, running tests in a test suite would behave as follows:
+ *
+ * suite.init(test);
+ * suite.test_case[0](test);
+ * suite.exit(test);
+ * suite.init(test);
+ * suite.test_case[1](test);
+ * suite.exit(test);
+ * ...;
+ */
+static struct kunit_suite example_test_suite = {
+	.name = "example",
+	.init = example_test_init,
+	.test_cases = example_test_cases,
+};
+
+/*
+ * This registers the above test suite telling KUnit that this is a suite of
+ * tests that need to be run.
+ */
+kunit_test_suite(example_test_suite);
diff --git a/lib/kunit/string-stream-test.c b/lib/kunit/string-stream-test.c
new file mode 100644
index 000000000000..76cc05eb00ed
--- /dev/null
+++ b/lib/kunit/string-stream-test.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnit test for struct string_stream.
+ *
+ * Copyright (C) 2019, Google LLC.
+ * Author: Brendan Higgins <brendanhiggins@google.com>
+ */
+
+#include <kunit/string-stream.h>
+#include <kunit/test.h>
+#include <linux/slab.h>
+
+static void string_stream_test_empty_on_creation(struct kunit *test)
+{
+	struct string_stream *stream = alloc_string_stream(test, GFP_KERNEL);
+
+	KUNIT_EXPECT_TRUE(test, string_stream_is_empty(stream));
+}
+
+static void string_stream_test_not_empty_after_add(struct kunit *test)
+{
+	struct string_stream *stream = alloc_string_stream(test, GFP_KERNEL);
+
+	string_stream_add(stream, "Foo");
+
+	KUNIT_EXPECT_FALSE(test, string_stream_is_empty(stream));
+}
+
+static void string_stream_test_get_string(struct kunit *test)
+{
+	struct string_stream *stream = alloc_string_stream(test, GFP_KERNEL);
+	char *output;
+
+	string_stream_add(stream, "Foo");
+	string_stream_add(stream, " %s", "bar");
+
+	output = string_stream_get_string(stream);
+	KUNIT_ASSERT_STREQ(test, output, "Foo bar");
+}
+
+static struct kunit_case string_stream_test_cases[] = {
+	KUNIT_CASE(string_stream_test_empty_on_creation),
+	KUNIT_CASE(string_stream_test_not_empty_after_add),
+	KUNIT_CASE(string_stream_test_get_string),
+	{}
+};
+
+static struct kunit_suite string_stream_test_suite = {
+	.name = "string-stream-test",
+	.test_cases = string_stream_test_cases
+};
+kunit_test_suite(string_stream_test_suite);
diff --git a/lib/kunit/string-stream.c b/lib/kunit/string-stream.c
new file mode 100644
index 000000000000..e6d17aacca30
--- /dev/null
+++ b/lib/kunit/string-stream.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * C++ stream style string builder used in KUnit for building messages.
+ *
+ * Copyright (C) 2019, Google LLC.
+ * Author: Brendan Higgins <brendanhiggins@google.com>
+ */
+
+#include <kunit/string-stream.h>
+#include <kunit/test.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+
+struct string_stream_fragment_alloc_context {
+	struct kunit *test;
+	int len;
+	gfp_t gfp;
+};
+
+static int string_stream_fragment_init(struct kunit_resource *res,
+				       void *context)
+{
+	struct string_stream_fragment_alloc_context *ctx = context;
+	struct string_stream_fragment *frag;
+
+	frag = kunit_kzalloc(ctx->test, sizeof(*frag), ctx->gfp);
+	if (!frag)
+		return -ENOMEM;
+
+	frag->test = ctx->test;
+	frag->fragment = kunit_kmalloc(ctx->test, ctx->len, ctx->gfp);
+	if (!frag->fragment)
+		return -ENOMEM;
+
+	res->allocation = frag;
+
+	return 0;
+}
+
+static void string_stream_fragment_free(struct kunit_resource *res)
+{
+	struct string_stream_fragment *frag = res->allocation;
+
+	list_del(&frag->node);
+	kunit_kfree(frag->test, frag->fragment);
+	kunit_kfree(frag->test, frag);
+}
+
+static struct string_stream_fragment *alloc_string_stream_fragment(
+		struct kunit *test, int len, gfp_t gfp)
+{
+	struct string_stream_fragment_alloc_context context = {
+		.test = test,
+		.len = len,
+		.gfp = gfp
+	};
+
+	return kunit_alloc_resource(test,
+				    string_stream_fragment_init,
+				    string_stream_fragment_free,
+				    gfp,
+				    &context);
+}
+
+static int string_stream_fragment_destroy(struct string_stream_fragment *frag)
+{
+	return kunit_resource_destroy(frag->test,
+				      kunit_resource_instance_match,
+				      string_stream_fragment_free,
+				      frag);
+}
+
+int string_stream_vadd(struct string_stream *stream,
+		       const char *fmt,
+		       va_list args)
+{
+	struct string_stream_fragment *frag_container;
+	int len;
+	va_list args_for_counting;
+
+	/* Make a copy because `vsnprintf` could change it */
+	va_copy(args_for_counting, args);
+
+	/* Need space for null byte. */
+	len = vsnprintf(NULL, 0, fmt, args_for_counting) + 1;
+
+	va_end(args_for_counting);
+
+	frag_container = alloc_string_stream_fragment(stream->test,
+						      len,
+						      stream->gfp);
+	if (!frag_container)
+		return -ENOMEM;
+
+	len = vsnprintf(frag_container->fragment, len, fmt, args);
+	spin_lock(&stream->lock);
+	stream->length += len;
+	list_add_tail(&frag_container->node, &stream->fragments);
+	spin_unlock(&stream->lock);
+
+	return 0;
+}
+
+int string_stream_add(struct string_stream *stream, const char *fmt, ...)
+{
+	va_list args;
+	int result;
+
+	va_start(args, fmt);
+	result = string_stream_vadd(stream, fmt, args);
+	va_end(args);
+
+	return result;
+}
+
+static void string_stream_clear(struct string_stream *stream)
+{
+	struct string_stream_fragment *frag_container, *frag_container_safe;
+
+	spin_lock(&stream->lock);
+	list_for_each_entry_safe(frag_container,
+				 frag_container_safe,
+				 &stream->fragments,
+				 node) {
+		string_stream_fragment_destroy(frag_container);
+	}
+	stream->length = 0;
+	spin_unlock(&stream->lock);
+}
+
+char *string_stream_get_string(struct string_stream *stream)
+{
+	struct string_stream_fragment *frag_container;
+	size_t buf_len = stream->length + 1; /* +1 for null byte. */
+	char *buf;
+
+	buf = kunit_kzalloc(stream->test, buf_len, stream->gfp);
+	if (!buf)
+		return NULL;
+
+	spin_lock(&stream->lock);
+	list_for_each_entry(frag_container, &stream->fragments, node)
+		strlcat(buf, frag_container->fragment, buf_len);
+	spin_unlock(&stream->lock);
+
+	return buf;
+}
+
+int string_stream_append(struct string_stream *stream,
+			 struct string_stream *other)
+{
+	const char *other_content;
+
+	other_content = string_stream_get_string(other);
+
+	if (!other_content)
+		return -ENOMEM;
+
+	return string_stream_add(stream, other_content);
+}
+
+bool string_stream_is_empty(struct string_stream *stream)
+{
+	return list_empty(&stream->fragments);
+}
+
+struct string_stream_alloc_context {
+	struct kunit *test;
+	gfp_t gfp;
+};
+
+static int string_stream_init(struct kunit_resource *res, void *context)
+{
+	struct string_stream *stream;
+	struct string_stream_alloc_context *ctx = context;
+
+	stream = kunit_kzalloc(ctx->test, sizeof(*stream), ctx->gfp);
+	if (!stream)
+		return -ENOMEM;
+
+	res->allocation = stream;
+	stream->gfp = ctx->gfp;
+	stream->test = ctx->test;
+	INIT_LIST_HEAD(&stream->fragments);
+	spin_lock_init(&stream->lock);
+
+	return 0;
+}
+
+static void string_stream_free(struct kunit_resource *res)
+{
+	struct string_stream *stream = res->allocation;
+
+	string_stream_clear(stream);
+}
+
+struct string_stream *alloc_string_stream(struct kunit *test, gfp_t gfp)
+{
+	struct string_stream_alloc_context context = {
+		.test = test,
+		.gfp = gfp
+	};
+
+	return kunit_alloc_resource(test,
+				    string_stream_init,
+				    string_stream_free,
+				    gfp,
+				    &context);
+}
+
+int string_stream_destroy(struct string_stream *stream)
+{
+	return kunit_resource_destroy(stream->test,
+				      kunit_resource_instance_match,
+				      string_stream_free,
+				      stream);
+}
diff --git a/lib/kunit/test-test.c b/lib/kunit/test-test.c
new file mode 100644
index 000000000000..5ebe059d16e2
--- /dev/null
+++ b/lib/kunit/test-test.c
@@ -0,0 +1,331 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnit test for core test infrastructure.
+ *
+ * Copyright (C) 2019, Google LLC.
+ * Author: Brendan Higgins <brendanhiggins@google.com>
+ */
+#include <kunit/test.h>
+
+struct kunit_try_catch_test_context {
+	struct kunit_try_catch *try_catch;
+	bool function_called;
+};
+
+static void kunit_test_successful_try(void *data)
+{
+	struct kunit *test = data;
+	struct kunit_try_catch_test_context *ctx = test->priv;
+
+	ctx->function_called = true;
+}
+
+static void kunit_test_no_catch(void *data)
+{
+	struct kunit *test = data;
+
+	KUNIT_FAIL(test, "Catch should not be called\n");
+}
+
+static void kunit_test_try_catch_successful_try_no_catch(struct kunit *test)
+{
+	struct kunit_try_catch_test_context *ctx = test->priv;
+	struct kunit_try_catch *try_catch = ctx->try_catch;
+
+	kunit_try_catch_init(try_catch,
+			     test,
+			     kunit_test_successful_try,
+			     kunit_test_no_catch);
+	kunit_try_catch_run(try_catch, test);
+
+	KUNIT_EXPECT_TRUE(test, ctx->function_called);
+}
+
+static void kunit_test_unsuccessful_try(void *data)
+{
+	struct kunit *test = data;
+	struct kunit_try_catch_test_context *ctx = test->priv;
+	struct kunit_try_catch *try_catch = ctx->try_catch;
+
+	kunit_try_catch_throw(try_catch);
+	KUNIT_FAIL(test, "This line should never be reached\n");
+}
+
+static void kunit_test_catch(void *data)
+{
+	struct kunit *test = data;
+	struct kunit_try_catch_test_context *ctx = test->priv;
+
+	ctx->function_called = true;
+}
+
+static void kunit_test_try_catch_unsuccessful_try_does_catch(struct kunit *test)
+{
+	struct kunit_try_catch_test_context *ctx = test->priv;
+	struct kunit_try_catch *try_catch = ctx->try_catch;
+
+	kunit_try_catch_init(try_catch,
+			     test,
+			     kunit_test_unsuccessful_try,
+			     kunit_test_catch);
+	kunit_try_catch_run(try_catch, test);
+
+	KUNIT_EXPECT_TRUE(test, ctx->function_called);
+}
+
+static int kunit_try_catch_test_init(struct kunit *test)
+{
+	struct kunit_try_catch_test_context *ctx;
+
+	ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+	test->priv = ctx;
+
+	ctx->try_catch = kunit_kmalloc(test,
+				       sizeof(*ctx->try_catch),
+				       GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx->try_catch);
+
+	return 0;
+}
+
+static struct kunit_case kunit_try_catch_test_cases[] = {
+	KUNIT_CASE(kunit_test_try_catch_successful_try_no_catch),
+	KUNIT_CASE(kunit_test_try_catch_unsuccessful_try_does_catch),
+	{}
+};
+
+static struct kunit_suite kunit_try_catch_test_suite = {
+	.name = "kunit-try-catch-test",
+	.init = kunit_try_catch_test_init,
+	.test_cases = kunit_try_catch_test_cases,
+};
+kunit_test_suite(kunit_try_catch_test_suite);
+
+/*
+ * Context for testing test managed resources
+ * is_resource_initialized is used to test arbitrary resources
+ */
+struct kunit_test_resource_context {
+	struct kunit test;
+	bool is_resource_initialized;
+	int allocate_order[2];
+	int free_order[2];
+};
+
+static int fake_resource_init(struct kunit_resource *res, void *context)
+{
+	struct kunit_test_resource_context *ctx = context;
+
+	res->allocation = &ctx->is_resource_initialized;
+	ctx->is_resource_initialized = true;
+	return 0;
+}
+
+static void fake_resource_free(struct kunit_resource *res)
+{
+	bool *is_resource_initialized = res->allocation;
+
+	*is_resource_initialized = false;
+}
+
+static void kunit_resource_test_init_resources(struct kunit *test)
+{
+	struct kunit_test_resource_context *ctx = test->priv;
+
+	kunit_init_test(&ctx->test, "testing_test_init_test");
+
+	KUNIT_EXPECT_TRUE(test, list_empty(&ctx->test.resources));
+}
+
+static void kunit_resource_test_alloc_resource(struct kunit *test)
+{
+	struct kunit_test_resource_context *ctx = test->priv;
+	struct kunit_resource *res;
+	kunit_resource_free_t free = fake_resource_free;
+
+	res = kunit_alloc_and_get_resource(&ctx->test,
+					   fake_resource_init,
+					   fake_resource_free,
+					   GFP_KERNEL,
+					   ctx);
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, res);
+	KUNIT_EXPECT_PTR_EQ(test,
+			    &ctx->is_resource_initialized,
+			    (bool *) res->allocation);
+	KUNIT_EXPECT_TRUE(test, list_is_last(&res->node, &ctx->test.resources));
+	KUNIT_EXPECT_PTR_EQ(test, free, res->free);
+}
+
+static void kunit_resource_test_destroy_resource(struct kunit *test)
+{
+	struct kunit_test_resource_context *ctx = test->priv;
+	struct kunit_resource *res = kunit_alloc_and_get_resource(
+			&ctx->test,
+			fake_resource_init,
+			fake_resource_free,
+			GFP_KERNEL,
+			ctx);
+
+	KUNIT_ASSERT_FALSE(test,
+			   kunit_resource_destroy(&ctx->test,
+						  kunit_resource_instance_match,
+						  res->free,
+						  res->allocation));
+
+	KUNIT_EXPECT_FALSE(test, ctx->is_resource_initialized);
+	KUNIT_EXPECT_TRUE(test, list_empty(&ctx->test.resources));
+}
+
+static void kunit_resource_test_cleanup_resources(struct kunit *test)
+{
+	int i;
+	struct kunit_test_resource_context *ctx = test->priv;
+	struct kunit_resource *resources[5];
+
+	for (i = 0; i < ARRAY_SIZE(resources); i++) {
+		resources[i] = kunit_alloc_and_get_resource(&ctx->test,
+							    fake_resource_init,
+							    fake_resource_free,
+							    GFP_KERNEL,
+							    ctx);
+	}
+
+	kunit_cleanup(&ctx->test);
+
+	KUNIT_EXPECT_TRUE(test, list_empty(&ctx->test.resources));
+}
+
+static void kunit_resource_test_mark_order(int order_array[],
+					   size_t order_size,
+					   int key)
+{
+	int i;
+
+	for (i = 0; i < order_size && order_array[i]; i++)
+		;
+
+	order_array[i] = key;
+}
+
+#define KUNIT_RESOURCE_TEST_MARK_ORDER(ctx, order_field, key)		       \
+		kunit_resource_test_mark_order(ctx->order_field,	       \
+					       ARRAY_SIZE(ctx->order_field),   \
+					       key)
+
+static int fake_resource_2_init(struct kunit_resource *res, void *context)
+{
+	struct kunit_test_resource_context *ctx = context;
+
+	KUNIT_RESOURCE_TEST_MARK_ORDER(ctx, allocate_order, 2);
+
+	res->allocation = ctx;
+
+	return 0;
+}
+
+static void fake_resource_2_free(struct kunit_resource *res)
+{
+	struct kunit_test_resource_context *ctx = res->allocation;
+
+	KUNIT_RESOURCE_TEST_MARK_ORDER(ctx, free_order, 2);
+}
+
+static int fake_resource_1_init(struct kunit_resource *res, void *context)
+{
+	struct kunit_test_resource_context *ctx = context;
+
+	kunit_alloc_and_get_resource(&ctx->test,
+				     fake_resource_2_init,
+				     fake_resource_2_free,
+				     GFP_KERNEL,
+				     ctx);
+
+	KUNIT_RESOURCE_TEST_MARK_ORDER(ctx, allocate_order, 1);
+
+	res->allocation = ctx;
+
+	return 0;
+}
+
+static void fake_resource_1_free(struct kunit_resource *res)
+{
+	struct kunit_test_resource_context *ctx = res->allocation;
+
+	KUNIT_RESOURCE_TEST_MARK_ORDER(ctx, free_order, 1);
+}
+
+/*
+ * TODO(brendanhiggins@google.com): replace the arrays that keep track of the
+ * order of allocation and freeing with strict mocks using the IN_SEQUENCE macro
+ * to assert allocation and freeing order when the feature becomes available.
+ */
+static void kunit_resource_test_proper_free_ordering(struct kunit *test)
+{
+	struct kunit_test_resource_context *ctx = test->priv;
+
+	/* fake_resource_1 allocates a fake_resource_2 in its init. */
+	kunit_alloc_and_get_resource(&ctx->test,
+				     fake_resource_1_init,
+				     fake_resource_1_free,
+				     GFP_KERNEL,
+				     ctx);
+
+	/*
+	 * Since fake_resource_2_init calls KUNIT_RESOURCE_TEST_MARK_ORDER
+	 * before returning to fake_resource_1_init, it should be the first to
+	 * put its key in the allocate_order array.
+	 */
+	KUNIT_EXPECT_EQ(test, ctx->allocate_order[0], 2);
+	KUNIT_EXPECT_EQ(test, ctx->allocate_order[1], 1);
+
+	kunit_cleanup(&ctx->test);
+
+	/*
+	 * Because fake_resource_2 finishes allocation before fake_resource_1,
+	 * fake_resource_1 should be freed first since it could depend on
+	 * fake_resource_2.
+	 */
+	KUNIT_EXPECT_EQ(test, ctx->free_order[0], 1);
+	KUNIT_EXPECT_EQ(test, ctx->free_order[1], 2);
+}
+
+static int kunit_resource_test_init(struct kunit *test)
+{
+	struct kunit_test_resource_context *ctx =
+			kzalloc(sizeof(*ctx), GFP_KERNEL);
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
+	test->priv = ctx;
+
+	kunit_init_test(&ctx->test, "test_test_context");
+
+	return 0;
+}
+
+static void kunit_resource_test_exit(struct kunit *test)
+{
+	struct kunit_test_resource_context *ctx = test->priv;
+
+	kunit_cleanup(&ctx->test);
+	kfree(ctx);
+}
+
+static struct kunit_case kunit_resource_test_cases[] = {
+	KUNIT_CASE(kunit_resource_test_init_resources),
+	KUNIT_CASE(kunit_resource_test_alloc_resource),
+	KUNIT_CASE(kunit_resource_test_destroy_resource),
+	KUNIT_CASE(kunit_resource_test_cleanup_resources),
+	KUNIT_CASE(kunit_resource_test_proper_free_ordering),
+	{}
+};
+
+static struct kunit_suite kunit_resource_test_suite = {
+	.name = "kunit-resource-test",
+	.init = kunit_resource_test_init,
+	.exit = kunit_resource_test_exit,
+	.test_cases = kunit_resource_test_cases,
+};
+kunit_test_suite(kunit_resource_test_suite);
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
new file mode 100644
index 000000000000..c83c0fa59cbd
--- /dev/null
+++ b/lib/kunit/test.c
@@ -0,0 +1,478 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Base unit test (KUnit) API.
+ *
+ * Copyright (C) 2019, Google LLC.
+ * Author: Brendan Higgins <brendanhiggins@google.com>
+ */
+
+#include <kunit/test.h>
+#include <kunit/try-catch.h>
+#include <linux/kernel.h>
+#include <linux/sched/debug.h>
+
+static void kunit_set_failure(struct kunit *test)
+{
+	WRITE_ONCE(test->success, false);
+}
+
+static void kunit_print_tap_version(void)
+{
+	static bool kunit_has_printed_tap_version;
+
+	if (!kunit_has_printed_tap_version) {
+		pr_info("TAP version 14\n");
+		kunit_has_printed_tap_version = true;
+	}
+}
+
+static size_t kunit_test_cases_len(struct kunit_case *test_cases)
+{
+	struct kunit_case *test_case;
+	size_t len = 0;
+
+	for (test_case = test_cases; test_case->run_case; test_case++)
+		len++;
+
+	return len;
+}
+
+static void kunit_print_subtest_start(struct kunit_suite *suite)
+{
+	kunit_print_tap_version();
+	pr_info("\t# Subtest: %s\n", suite->name);
+	pr_info("\t1..%zd\n", kunit_test_cases_len(suite->test_cases));
+}
+
+static void kunit_print_ok_not_ok(bool should_indent,
+				  bool is_ok,
+				  size_t test_number,
+				  const char *description)
+{
+	const char *indent, *ok_not_ok;
+
+	if (should_indent)
+		indent = "\t";
+	else
+		indent = "";
+
+	if (is_ok)
+		ok_not_ok = "ok";
+	else
+		ok_not_ok = "not ok";
+
+	pr_info("%s%s %zd - %s\n", indent, ok_not_ok, test_number, description);
+}
+
+static bool kunit_suite_has_succeeded(struct kunit_suite *suite)
+{
+	const struct kunit_case *test_case;
+
+	for (test_case = suite->test_cases; test_case->run_case; test_case++)
+		if (!test_case->success)
+			return false;
+
+	return true;
+}
+
+static void kunit_print_subtest_end(struct kunit_suite *suite)
+{
+	static size_t kunit_suite_counter = 1;
+
+	kunit_print_ok_not_ok(false,
+			      kunit_suite_has_succeeded(suite),
+			      kunit_suite_counter++,
+			      suite->name);
+}
+
+static void kunit_print_test_case_ok_not_ok(struct kunit_case *test_case,
+					    size_t test_number)
+{
+	kunit_print_ok_not_ok(true,
+			      test_case->success,
+			      test_number,
+			      test_case->name);
+}
+
+static void kunit_print_string_stream(struct kunit *test,
+				      struct string_stream *stream)
+{
+	struct string_stream_fragment *fragment;
+	char *buf;
+
+	buf = string_stream_get_string(stream);
+	if (!buf) {
+		kunit_err(test,
+			  "Could not allocate buffer, dumping stream:\n");
+		list_for_each_entry(fragment, &stream->fragments, node) {
+			kunit_err(test, "%s", fragment->fragment);
+		}
+		kunit_err(test, "\n");
+	} else {
+		kunit_err(test, "%s", buf);
+		kunit_kfree(test, buf);
+	}
+}
+
+static void kunit_fail(struct kunit *test, struct kunit_assert *assert)
+{
+	struct string_stream *stream;
+
+	kunit_set_failure(test);
+
+	stream = alloc_string_stream(test, GFP_KERNEL);
+	if (!stream) {
+		WARN(true,
+		     "Could not allocate stream to print failed assertion in %s:%d\n",
+		     assert->file,
+		     assert->line);
+		return;
+	}
+
+	assert->format(assert, stream);
+
+	kunit_print_string_stream(test, stream);
+
+	WARN_ON(string_stream_destroy(stream));
+}
+
+static void __noreturn kunit_abort(struct kunit *test)
+{
+	kunit_try_catch_throw(&test->try_catch); /* Does not return. */
+
+	/*
+	 * Throw could not abort from test.
+	 *
+	 * XXX: we should never reach this line! As kunit_try_catch_throw is
+	 * marked __noreturn.
+	 */
+	WARN_ONCE(true, "Throw could not abort from test!\n");
+}
+
+void kunit_do_assertion(struct kunit *test,
+			struct kunit_assert *assert,
+			bool pass,
+			const char *fmt, ...)
+{
+	va_list args;
+
+	if (pass)
+		return;
+
+	va_start(args, fmt);
+
+	assert->message.fmt = fmt;
+	assert->message.va = &args;
+
+	kunit_fail(test, assert);
+
+	va_end(args);
+
+	if (assert->type == KUNIT_ASSERTION)
+		kunit_abort(test);
+}
+
+void kunit_init_test(struct kunit *test, const char *name)
+{
+	spin_lock_init(&test->lock);
+	INIT_LIST_HEAD(&test->resources);
+	test->name = name;
+	test->success = true;
+}
+
+/*
+ * Initializes and runs test case. Does not clean up or do post validations.
+ */
+static void kunit_run_case_internal(struct kunit *test,
+				    struct kunit_suite *suite,
+				    struct kunit_case *test_case)
+{
+	if (suite->init) {
+		int ret;
+
+		ret = suite->init(test);
+		if (ret) {
+			kunit_err(test, "failed to initialize: %d\n", ret);
+			kunit_set_failure(test);
+			return;
+		}
+	}
+
+	test_case->run_case(test);
+}
+
+static void kunit_case_internal_cleanup(struct kunit *test)
+{
+	kunit_cleanup(test);
+}
+
+/*
+ * Performs post validations and cleanup after a test case was run.
+ * XXX: Should ONLY BE CALLED AFTER kunit_run_case_internal!
+ */
+static void kunit_run_case_cleanup(struct kunit *test,
+				   struct kunit_suite *suite)
+{
+	if (suite->exit)
+		suite->exit(test);
+
+	kunit_case_internal_cleanup(test);
+}
+
+struct kunit_try_catch_context {
+	struct kunit *test;
+	struct kunit_suite *suite;
+	struct kunit_case *test_case;
+};
+
+static void kunit_try_run_case(void *data)
+{
+	struct kunit_try_catch_context *ctx = data;
+	struct kunit *test = ctx->test;
+	struct kunit_suite *suite = ctx->suite;
+	struct kunit_case *test_case = ctx->test_case;
+
+	/*
+	 * kunit_run_case_internal may encounter a fatal error; if it does,
+	 * abort will be called, this thread will exit, and finally the parent
+	 * thread will resume control and handle any necessary clean up.
+	 */
+	kunit_run_case_internal(test, suite, test_case);
+	/* This line may never be reached. */
+	kunit_run_case_cleanup(test, suite);
+}
+
+static void kunit_catch_run_case(void *data)
+{
+	struct kunit_try_catch_context *ctx = data;
+	struct kunit *test = ctx->test;
+	struct kunit_suite *suite = ctx->suite;
+	int try_exit_code = kunit_try_catch_get_result(&test->try_catch);
+
+	if (try_exit_code) {
+		kunit_set_failure(test);
+		/*
+		 * Test case could not finish, we have no idea what state it is
+		 * in, so don't do clean up.
+		 */
+		if (try_exit_code == -ETIMEDOUT) {
+			kunit_err(test, "test case timed out\n");
+		/*
+		 * Unknown internal error occurred preventing test case from
+		 * running, so there is nothing to clean up.
+		 */
+		} else {
+			kunit_err(test, "internal error occurred preventing test case from running: %d\n",
+				  try_exit_code);
+		}
+		return;
+	}
+
+	/*
+	 * Test case was run, but aborted. It is the test case's business as to
+	 * whether it failed or not, we just need to clean up.
+	 */
+	kunit_run_case_cleanup(test, suite);
+}
+
+/*
+ * Performs all logic to run a test case. It also catches most errors that
+ * occur in a test case and reports them as failures.
+ */
+static void kunit_run_case_catch_errors(struct kunit_suite *suite,
+					struct kunit_case *test_case)
+{
+	struct kunit_try_catch_context context;
+	struct kunit_try_catch *try_catch;
+	struct kunit test;
+
+	kunit_init_test(&test, test_case->name);
+	try_catch = &test.try_catch;
+
+	kunit_try_catch_init(try_catch,
+			     &test,
+			     kunit_try_run_case,
+			     kunit_catch_run_case);
+	context.test = &test;
+	context.suite = suite;
+	context.test_case = test_case;
+	kunit_try_catch_run(try_catch, &context);
+
+	test_case->success = test.success;
+}
+
+int kunit_run_tests(struct kunit_suite *suite)
+{
+	struct kunit_case *test_case;
+	size_t test_case_count = 1;
+
+	kunit_print_subtest_start(suite);
+
+	for (test_case = suite->test_cases; test_case->run_case; test_case++) {
+		kunit_run_case_catch_errors(suite, test_case);
+		kunit_print_test_case_ok_not_ok(test_case, test_case_count++);
+	}
+
+	kunit_print_subtest_end(suite);
+
+	return 0;
+}
+
+struct kunit_resource *kunit_alloc_and_get_resource(struct kunit *test,
+						    kunit_resource_init_t init,
+						    kunit_resource_free_t free,
+						    gfp_t internal_gfp,
+						    void *context)
+{
+	struct kunit_resource *res;
+	int ret;
+
+	res = kzalloc(sizeof(*res), internal_gfp);
+	if (!res)
+		return NULL;
+
+	ret = init(res, context);
+	if (ret)
+		return NULL;
+
+	res->free = free;
+	spin_lock(&test->lock);
+	list_add_tail(&res->node, &test->resources);
+	spin_unlock(&test->lock);
+
+	return res;
+}
+
+static void kunit_resource_free(struct kunit *test, struct kunit_resource *res)
+{
+	res->free(res);
+	kfree(res);
+}
+
+static struct kunit_resource *kunit_resource_find(struct kunit *test,
+						  kunit_resource_match_t match,
+						  kunit_resource_free_t free,
+						  void *match_data)
+{
+	struct kunit_resource *resource;
+
+	lockdep_assert_held(&test->lock);
+
+	list_for_each_entry_reverse(resource, &test->resources, node) {
+		if (resource->free != free)
+			continue;
+		if (match(test, resource->allocation, match_data))
+			return resource;
+	}
+
+	return NULL;
+}
+
+static struct kunit_resource *kunit_resource_remove(
+		struct kunit *test,
+		kunit_resource_match_t match,
+		kunit_resource_free_t free,
+		void *match_data)
+{
+	struct kunit_resource *resource;
+
+	spin_lock(&test->lock);
+	resource = kunit_resource_find(test, match, free, match_data);
+	if (resource)
+		list_del(&resource->node);
+	spin_unlock(&test->lock);
+
+	return resource;
+}
+
+int kunit_resource_destroy(struct kunit *test,
+			   kunit_resource_match_t match,
+			   kunit_resource_free_t free,
+			   void *match_data)
+{
+	struct kunit_resource *resource;
+
+	resource = kunit_resource_remove(test, match, free, match_data);
+
+	if (!resource)
+		return -ENOENT;
+
+	kunit_resource_free(test, resource);
+	return 0;
+}
+
+struct kunit_kmalloc_params {
+	size_t size;
+	gfp_t gfp;
+};
+
+static int kunit_kmalloc_init(struct kunit_resource *res, void *context)
+{
+	struct kunit_kmalloc_params *params = context;
+
+	res->allocation = kmalloc(params->size, params->gfp);
+	if (!res->allocation)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void kunit_kmalloc_free(struct kunit_resource *res)
+{
+	kfree(res->allocation);
+}
+
+void *kunit_kmalloc(struct kunit *test, size_t size, gfp_t gfp)
+{
+	struct kunit_kmalloc_params params = {
+		.size = size,
+		.gfp = gfp
+	};
+
+	return kunit_alloc_resource(test,
+				    kunit_kmalloc_init,
+				    kunit_kmalloc_free,
+				    gfp,
+				    &params);
+}
+
+void kunit_kfree(struct kunit *test, const void *ptr)
+{
+	int rc;
+
+	rc = kunit_resource_destroy(test,
+				    kunit_resource_instance_match,
+				    kunit_kmalloc_free,
+				    (void *)ptr);
+
+	WARN_ON(rc);
+}
+
+void kunit_cleanup(struct kunit *test)
+{
+	struct kunit_resource *resource;
+
+	/*
+	 * test->resources is a stack - each allocation must be freed in the
+	 * reverse order from which it was added since one resource may depend
+	 * on another for its entire lifetime.
+	 * Also, we cannot use the normal list_for_each constructs, even the
+	 * safe ones because *arbitrary* nodes may be deleted when
+	 * kunit_resource_free is called; the list_for_each_safe variants only
+	 * protect against the current node being deleted, not the next.
+	 */
+	while (true) {
+		spin_lock(&test->lock);
+		if (list_empty(&test->resources)) {
+			spin_unlock(&test->lock);
+			break;
+		}
+		resource = list_last_entry(&test->resources,
+					   struct kunit_resource,
+					   node);
+		list_del(&resource->node);
+		spin_unlock(&test->lock);
+
+		kunit_resource_free(test, resource);
+	}
+}
diff --git a/lib/kunit/try-catch.c b/lib/kunit/try-catch.c
new file mode 100644
index 000000000000..55686839eb61
--- /dev/null
+++ b/lib/kunit/try-catch.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * An API to allow a function, that may fail, to be executed, and recover in a
+ * controlled manner.
+ *
+ * Copyright (C) 2019, Google LLC.
+ * Author: Brendan Higgins <brendanhiggins@google.com>
+ */
+
+#include <kunit/test.h>
+#include <kunit/try-catch.h>
+#include <linux/completion.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/sched/sysctl.h>
+
+void __noreturn kunit_try_catch_throw(struct kunit_try_catch *try_catch)
+{
+	try_catch->try_result = -EFAULT;
+	complete_and_exit(try_catch->try_completion, -EFAULT);
+}
+
+static int kunit_generic_run_threadfn_adapter(void *data)
+{
+	struct kunit_try_catch *try_catch = data;
+
+	try_catch->try(try_catch->context);
+
+	complete_and_exit(try_catch->try_completion, 0);
+}
+
+static unsigned long kunit_test_timeout(void)
+{
+	unsigned long timeout_msecs;
+
+	/*
+	 * TODO(brendanhiggins@google.com): We should probably have some type of
+	 * variable timeout here. The only question is what that timeout value
+	 * should be.
+	 *
+	 * The intention has always been, at some point, to be able to label
+	 * tests with some type of size bucket (unit/small, integration/medium,
+	 * large/system/end-to-end, etc), where each size bucket would get a
+	 * default timeout value kind of like what Bazel does:
+	 * https://docs.bazel.build/versions/master/be/common-definitions.html#test.size
+	 * There is still some debate to be had on exactly how we do this. (For
+	 * one, we probably want to have some sort of test runner level
+	 * timeout.)
+	 *
+	 * For more background on this topic, see:
+	 * https://mike-bland.com/2011/11/01/small-medium-large.html
+	 */
+	if (sysctl_hung_task_timeout_secs) {
+		/*
+		 * If sysctl_hung_task is active, just set the timeout to some
+		 * value less than that.
+		 *
+		 * In regards to the above TODO, if we decide on variable
+		 * timeouts, this logic will likely need to change.
+		 */
+		timeout_msecs = (sysctl_hung_task_timeout_secs - 1) *
+				MSEC_PER_SEC;
+	} else {
+		timeout_msecs = 300 * MSEC_PER_SEC; /* 5 min */
+	}
+
+	return timeout_msecs;
+}
+
+void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context)
+{
+	DECLARE_COMPLETION_ONSTACK(try_completion);
+	struct kunit *test = try_catch->test;
+	struct task_struct *task_struct;
+	int exit_code, time_remaining;
+
+	try_catch->context = context;
+	try_catch->try_completion = &try_completion;
+	try_catch->try_result = 0;
+	task_struct = kthread_run(kunit_generic_run_threadfn_adapter,
+				  try_catch,
+				  "kunit_try_catch_thread");
+	if (IS_ERR(task_struct)) {
+		try_catch->catch(try_catch->context);
+		return;
+	}
+
+	time_remaining = wait_for_completion_timeout(&try_completion,
+						     kunit_test_timeout());
+	if (time_remaining == 0) {
+		kunit_err(test, "try timed out\n");
+		try_catch->try_result = -ETIMEDOUT;
+	}
+
+	exit_code = try_catch->try_result;
+
+	if (!exit_code)
+		return;
+
+	if (exit_code == -EFAULT)
+		try_catch->try_result = 0;
+	else if (exit_code == -EINTR)
+		kunit_err(test, "wake_up_process() was never called\n");
+	else if (exit_code)
+		kunit_err(test, "Unknown error: %d\n", exit_code);
+
+	try_catch->catch(try_catch->context);
+}
+
+void kunit_try_catch_init(struct kunit_try_catch *try_catch,
+			  struct kunit *test,
+			  kunit_try_catch_func_t try,
+			  kunit_try_catch_func_t catch)
+{
+	try_catch->test = test;
+	try_catch->try = try;
+	try_catch->catch = catch;
+}
diff --git a/lib/list-test.c b/lib/list-test.c
new file mode 100644
index 000000000000..363c600491c3
--- /dev/null
+++ b/lib/list-test.c
@@ -0,0 +1,746 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnit test for the Kernel Linked-list structures.
+ *
+ * Copyright (C) 2019, Google LLC.
+ * Author: David Gow <davidgow@google.com>
+ */
+#include <kunit/test.h>
+
+#include <linux/list.h>
+
+struct list_test_struct {
+	int data;
+	struct list_head list;
+};
+
+static void list_test_list_init(struct kunit *test)
+{
+	/* Test the different ways of initialising a list. */
+	struct list_head list1 = LIST_HEAD_INIT(list1);
+	struct list_head list2;
+	LIST_HEAD(list3);
+	struct list_head *list4;
+	struct list_head *list5;
+
+	INIT_LIST_HEAD(&list2);
+
+	list4 = kzalloc(sizeof(*list4), GFP_KERNEL | __GFP_NOFAIL);
+	INIT_LIST_HEAD(list4);
+
+	list5 = kmalloc(sizeof(*list5), GFP_KERNEL | __GFP_NOFAIL);
+	memset(list5, 0xFF, sizeof(*list5));
+	INIT_LIST_HEAD(list5);
+
+	/* list_empty_careful() checks both next and prev. */
+	KUNIT_EXPECT_TRUE(test, list_empty_careful(&list1));
+	KUNIT_EXPECT_TRUE(test, list_empty_careful(&list2));
+	KUNIT_EXPECT_TRUE(test, list_empty_careful(&list3));
+	KUNIT_EXPECT_TRUE(test, list_empty_careful(list4));
+	KUNIT_EXPECT_TRUE(test, list_empty_careful(list5));
+
+	kfree(list4);
+	kfree(list5);
+}
+
+static void list_test_list_add(struct kunit *test)
+{
+	struct list_head a, b;
+	LIST_HEAD(list);
+
+	list_add(&a, &list);
+	list_add(&b, &list);
+
+	/* should be [list] -> b -> a */
+	KUNIT_EXPECT_PTR_EQ(test, list.next, &b);
+	KUNIT_EXPECT_PTR_EQ(test, b.prev, &list);
+	KUNIT_EXPECT_PTR_EQ(test, b.next, &a);
+}
+
+static void list_test_list_add_tail(struct kunit *test)
+{
+	struct list_head a, b;
+	LIST_HEAD(list);
+
+	list_add_tail(&a, &list);
+	list_add_tail(&b, &list);
+
+	/* should be [list] -> a -> b */
+	KUNIT_EXPECT_PTR_EQ(test, list.next, &a);
+	KUNIT_EXPECT_PTR_EQ(test, a.prev, &list);
+	KUNIT_EXPECT_PTR_EQ(test, a.next, &b);
+}
+
+static void list_test_list_del(struct kunit *test)
+{
+	struct list_head a, b;
+	LIST_HEAD(list);
+
+	list_add_tail(&a, &list);
+	list_add_tail(&b, &list);
+
+	/* before: [list] -> a -> b */
+	list_del(&a);
+
+	/* now: [list] -> b */
+	KUNIT_EXPECT_PTR_EQ(test, list.next, &b);
+	KUNIT_EXPECT_PTR_EQ(test, b.prev, &list);
+}
+
+static void list_test_list_replace(struct kunit *test)
+{
+	struct list_head a_old, a_new, b;
+	LIST_HEAD(list);
+
+	list_add_tail(&a_old, &list);
+	list_add_tail(&b, &list);
+
+	/* before: [list] -> a_old -> b */
+	list_replace(&a_old, &a_new);
+
+	/* now: [list] -> a_new -> b */
+	KUNIT_EXPECT_PTR_EQ(test, list.next, &a_new);
+	KUNIT_EXPECT_PTR_EQ(test, b.prev, &a_new);
+}
+
+static void list_test_list_replace_init(struct kunit *test)
+{
+	struct list_head a_old, a_new, b;
+	LIST_HEAD(list);
+
+	list_add_tail(&a_old, &list);
+	list_add_tail(&b, &list);
+
+	/* before: [list] -> a_old -> b */
+	list_replace_init(&a_old, &a_new);
+
+	/* now: [list] -> a_new -> b */
+	KUNIT_EXPECT_PTR_EQ(test, list.next, &a_new);
+	KUNIT_EXPECT_PTR_EQ(test, b.prev, &a_new);
+
+	/* check a_old is empty (initialized) */
+	KUNIT_EXPECT_TRUE(test, list_empty_careful(&a_old));
+}
+
+static void list_test_list_swap(struct kunit *test)
+{
+	struct list_head a, b;
+	LIST_HEAD(list);
+
+	list_add_tail(&a, &list);
+	list_add_tail(&b, &list);
+
+	/* before: [list] -> a -> b */
+	list_swap(&a, &b);
+
+	/* after: [list] -> b -> a */
+	KUNIT_EXPECT_PTR_EQ(test, &b, list.next);
+	KUNIT_EXPECT_PTR_EQ(test, &a, list.prev);
+
+	KUNIT_EXPECT_PTR_EQ(test, &a, b.next);
+	KUNIT_EXPECT_PTR_EQ(test, &list, b.prev);
+
+	KUNIT_EXPECT_PTR_EQ(test, &list, a.next);
+	KUNIT_EXPECT_PTR_EQ(test, &b, a.prev);
+}
+
+static void list_test_list_del_init(struct kunit *test)
+{
+	struct list_head a, b;
+	LIST_HEAD(list);
+
+	list_add_tail(&a, &list);
+	list_add_tail(&b, &list);
+
+	/* before: [list] -> a -> b */
+	list_del_init(&a);
+	/* after: [list] -> b, a initialised */
+
+	KUNIT_EXPECT_PTR_EQ(test, list.next, &b);
+	KUNIT_EXPECT_PTR_EQ(test, b.prev, &list);
+	KUNIT_EXPECT_TRUE(test, list_empty_careful(&a));
+}
+
+static void list_test_list_move(struct kunit *test)
+{
+	struct list_head a, b;
+	LIST_HEAD(list1);
+	LIST_HEAD(list2);
+
+	list_add_tail(&a, &list1);
+	list_add_tail(&b, &list2);
+
+	/* before: [list1] -> a, [list2] -> b */
+	list_move(&a, &list2);
+	/* after: [list1] empty, [list2] -> a -> b */
+
+	KUNIT_EXPECT_TRUE(test, list_empty(&list1));
+
+	KUNIT_EXPECT_PTR_EQ(test, &a, list2.next);
+	KUNIT_EXPECT_PTR_EQ(test, &b, a.next);
+}
+
+static void list_test_list_move_tail(struct kunit *test)
+{
+	struct list_head a, b;
+	LIST_HEAD(list1);
+	LIST_HEAD(list2);
+
+	list_add_tail(&a, &list1);
+	list_add_tail(&b, &list2);
+
+	/* before: [list1] -> a, [list2] -> b */
+	list_move_tail(&a, &list2);
+	/* after: [list1] empty, [list2] -> b -> a */
+
+	KUNIT_EXPECT_TRUE(test, list_empty(&list1));
+
+	KUNIT_EXPECT_PTR_EQ(test, &b, list2.next);
+	KUNIT_EXPECT_PTR_EQ(test, &a, b.next);
+}
+
+static void list_test_list_bulk_move_tail(struct kunit *test)
+{
+	struct list_head a, b, c, d, x, y;
+	struct list_head *list1_values[] = { &x, &b, &c, &y };
+	struct list_head *list2_values[] = { &a, &d };
+	struct list_head *ptr;
+	LIST_HEAD(list1);
+	LIST_HEAD(list2);
+	int i = 0;
+
+	list_add_tail(&x, &list1);
+	list_add_tail(&y, &list1);
+
+	list_add_tail(&a, &list2);
+	list_add_tail(&b, &list2);
+	list_add_tail(&c, &list2);
+	list_add_tail(&d, &list2);
+
+	/* before: [list1] -> x -> y, [list2] -> a -> b -> c -> d */
+	list_bulk_move_tail(&y, &b, &c);
+	/* after: [list1] -> x -> b -> c -> y, [list2] -> a -> d */
+
+	list_for_each(ptr, &list1) {
+		KUNIT_EXPECT_PTR_EQ(test, ptr, list1_values[i]);
+		i++;
+	}
+	KUNIT_EXPECT_EQ(test, i, 4);
+	i = 0;
+	list_for_each(ptr, &list2) {
+		KUNIT_EXPECT_PTR_EQ(test, ptr, list2_values[i]);
+		i++;
+	}
+	KUNIT_EXPECT_EQ(test, i, 2);
+}
+
+static void list_test_list_is_first(struct kunit *test)
+{
+	struct list_head a, b;
+	LIST_HEAD(list);
+
+	list_add_tail(&a, &list);
+	list_add_tail(&b, &list);
+
+	KUNIT_EXPECT_TRUE(test, list_is_first(&a, &list));
+	KUNIT_EXPECT_FALSE(test, list_is_first(&b, &list));
+}
+
+static void list_test_list_is_last(struct kunit *test)
+{
+	struct list_head a, b;
+	LIST_HEAD(list);
+
+	list_add_tail(&a, &list);
+	list_add_tail(&b, &list);
+
+	KUNIT_EXPECT_FALSE(test, list_is_last(&a, &list));
+	KUNIT_EXPECT_TRUE(test, list_is_last(&b, &list));
+}
+
+static void list_test_list_empty(struct kunit *test)
+{
+	struct list_head a;
+	LIST_HEAD(list1);
+	LIST_HEAD(list2);
+
+	list_add_tail(&a, &list1);
+
+	KUNIT_EXPECT_FALSE(test, list_empty(&list1));
+	KUNIT_EXPECT_TRUE(test, list_empty(&list2));
+}
+
+static void list_test_list_empty_careful(struct kunit *test)
+{
+	/* This test doesn't check correctness under concurrent access */
+	struct list_head a;
+	LIST_HEAD(list1);
+	LIST_HEAD(list2);
+
+	list_add_tail(&a, &list1);
+
+	KUNIT_EXPECT_FALSE(test, list_empty_careful(&list1));
+	KUNIT_EXPECT_TRUE(test, list_empty_careful(&list2));
+}
+
+static void list_test_list_rotate_left(struct kunit *test)
+{
+	struct list_head a, b;
+	LIST_HEAD(list);
+
+	list_add_tail(&a, &list);
+	list_add_tail(&b, &list);
+
+	/* before: [list] -> a -> b */
+	list_rotate_left(&list);
+	/* after: [list] -> b -> a */
+
+	KUNIT_EXPECT_PTR_EQ(test, list.next, &b);
+	KUNIT_EXPECT_PTR_EQ(test, b.prev, &list);
+	KUNIT_EXPECT_PTR_EQ(test, b.next, &a);
+}
+
+static void list_test_list_rotate_to_front(struct kunit *test)
+{
+	struct list_head a, b, c, d;
+	struct list_head *list_values[] = { &c, &d, &a, &b };
+	struct list_head *ptr;
+	LIST_HEAD(list);
+	int i = 0;
+
+	list_add_tail(&a, &list);
+	list_add_tail(&b, &list);
+	list_add_tail(&c, &list);
+	list_add_tail(&d, &list);
+
+	/* before: [list] -> a -> b -> c -> d */
+	list_rotate_to_front(&c, &list);
+	/* after: [list] -> c -> d -> a -> b */
+
+	list_for_each(ptr, &list) {
+		KUNIT_EXPECT_PTR_EQ(test, ptr, list_values[i]);
+		i++;
+	}
+	KUNIT_EXPECT_EQ(test, i, 4);
+}
+
+static void list_test_list_is_singular(struct kunit *test)
+{
+	struct list_head a, b;
+	LIST_HEAD(list);
+
+	/* [list] empty */
+	KUNIT_EXPECT_FALSE(test, list_is_singular(&list));
+
+	list_add_tail(&a, &list);
+
+	/* [list] -> a */
+	KUNIT_EXPECT_TRUE(test, list_is_singular(&list));
+
+	list_add_tail(&b, &list);
+
+	/* [list] -> a -> b */
+	KUNIT_EXPECT_FALSE(test, list_is_singular(&list));
+}
+
+static void list_test_list_cut_position(struct kunit *test)
+{
+	struct list_head entries[3], *cur;
+	LIST_HEAD(list1);
+	LIST_HEAD(list2);
+	int i = 0;
+
+	list_add_tail(&entries[0], &list1);
+	list_add_tail(&entries[1], &list1);
+	list_add_tail(&entries[2], &list1);
+
+	/* before: [list1] -> entries[0] -> entries[1] -> entries[2] */
+	list_cut_position(&list2, &list1, &entries[1]);
+	/* after: [list2] -> entries[0] -> entries[1], [list1] -> entries[2] */
+
+	list_for_each(cur, &list2) {
+		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
+		i++;
+	}
+
+	KUNIT_EXPECT_EQ(test, i, 2);
+
+	list_for_each(cur, &list1) {
+		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
+		i++;
+	}
+}
+
+static void list_test_list_cut_before(struct kunit *test)
+{
+	struct list_head entries[3], *cur;
+	LIST_HEAD(list1);
+	LIST_HEAD(list2);
+	int i = 0;
+
+	list_add_tail(&entries[0], &list1);
+	list_add_tail(&entries[1], &list1);
+	list_add_tail(&entries[2], &list1);
+
+	/* before: [list1] -> entries[0] -> entries[1] -> entries[2] */
+	list_cut_before(&list2, &list1, &entries[1]);
+	/* after: [list2] -> entries[0], [list1] -> entries[1] -> entries[2] */
+
+	list_for_each(cur, &list2) {
+		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
+		i++;
+	}
+
+	KUNIT_EXPECT_EQ(test, i, 1);
+
+	list_for_each(cur, &list1) {
+		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
+		i++;
+	}
+}
+
+static void list_test_list_splice(struct kunit *test)
+{
+	struct list_head entries[5], *cur;
+	LIST_HEAD(list1);
+	LIST_HEAD(list2);
+	int i = 0;
+
+	list_add_tail(&entries[0], &list1);
+	list_add_tail(&entries[1], &list1);
+	list_add_tail(&entries[2], &list2);
+	list_add_tail(&entries[3], &list2);
+	list_add_tail(&entries[4], &list1);
+
+	/* before: [list1]->e[0]->e[1]->e[4], [list2]->e[2]->e[3] */
+	list_splice(&list2, &entries[1]);
+	/* after: [list1]->e[0]->e[1]->e[2]->e[3]->e[4], [list2] uninit */
+
+	list_for_each(cur, &list1) {
+		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
+		i++;
+	}
+
+	KUNIT_EXPECT_EQ(test, i, 5);
+}
+
+static void list_test_list_splice_tail(struct kunit *test)
+{
+	struct list_head entries[5], *cur;
+	LIST_HEAD(list1);
+	LIST_HEAD(list2);
+	int i = 0;
+
+	list_add_tail(&entries[0], &list1);
+	list_add_tail(&entries[1], &list1);
+	list_add_tail(&entries[2], &list2);
+	list_add_tail(&entries[3], &list2);
+	list_add_tail(&entries[4], &list1);
+
+	/* before: [list1]->e[0]->e[1]->e[4], [list2]->e[2]->e[3] */
+	list_splice_tail(&list2, &entries[4]);
+	/* after: [list1]->e[0]->e[1]->e[2]->e[3]->e[4], [list2] uninit */
+
+	list_for_each(cur, &list1) {
+		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
+		i++;
+	}
+
+	KUNIT_EXPECT_EQ(test, i, 5);
+}
+
+static void list_test_list_splice_init(struct kunit *test)
+{
+	struct list_head entries[5], *cur;
+	LIST_HEAD(list1);
+	LIST_HEAD(list2);
+	int i = 0;
+
+	list_add_tail(&entries[0], &list1);
+	list_add_tail(&entries[1], &list1);
+	list_add_tail(&entries[2], &list2);
+	list_add_tail(&entries[3], &list2);
+	list_add_tail(&entries[4], &list1);
+
+	/* before: [list1]->e[0]->e[1]->e[4], [list2]->e[2]->e[3] */
+	list_splice_init(&list2, &entries[1]);
+	/* after: [list1]->e[0]->e[1]->e[2]->e[3]->e[4], [list2] empty */
+
+	list_for_each(cur, &list1) {
+		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
+		i++;
+	}
+
+	KUNIT_EXPECT_EQ(test, i, 5);
+
+	KUNIT_EXPECT_TRUE(test, list_empty_careful(&list2));
+}
+
+static void list_test_list_splice_tail_init(struct kunit *test)
+{
+	struct list_head entries[5], *cur;
+	LIST_HEAD(list1);
+	LIST_HEAD(list2);
+	int i = 0;
+
+	list_add_tail(&entries[0], &list1);
+	list_add_tail(&entries[1], &list1);
+	list_add_tail(&entries[2], &list2);
+	list_add_tail(&entries[3], &list2);
+	list_add_tail(&entries[4], &list1);
+
+	/* before: [list1]->e[0]->e[1]->e[4], [list2]->e[2]->e[3] */
+	list_splice_tail_init(&list2, &entries[4]);
+	/* after: [list1]->e[0]->e[1]->e[2]->e[3]->e[4], [list2] empty */
+
+	list_for_each(cur, &list1) {
+		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
+		i++;
+	}
+
+	KUNIT_EXPECT_EQ(test, i, 5);
+
+	KUNIT_EXPECT_TRUE(test, list_empty_careful(&list2));
+}
+
+static void list_test_list_entry(struct kunit *test)
+{
+	struct list_test_struct test_struct;
+
+	KUNIT_EXPECT_PTR_EQ(test, &test_struct, list_entry(&(test_struct.list),
+				struct list_test_struct, list));
+}
+
+static void list_test_list_first_entry(struct kunit *test)
+{
+	struct list_test_struct test_struct1, test_struct2;
+	LIST_HEAD(list);
+
+	list_add_tail(&test_struct1.list, &list);
+	list_add_tail(&test_struct2.list, &list);
+
+
+	KUNIT_EXPECT_PTR_EQ(test, &test_struct1, list_first_entry(&list,
+				struct list_test_struct, list));
+}
+
+static void list_test_list_last_entry(struct kunit *test)
+{
+	struct list_test_struct test_struct1, test_struct2;
+	LIST_HEAD(list);
+
+	list_add_tail(&test_struct1.list, &list);
+	list_add_tail(&test_struct2.list, &list);
+
+
+	KUNIT_EXPECT_PTR_EQ(test, &test_struct2, list_last_entry(&list,
+				struct list_test_struct, list));
+}
+
+static void list_test_list_first_entry_or_null(struct kunit *test)
+{
+	struct list_test_struct test_struct1, test_struct2;
+	LIST_HEAD(list);
+
+	KUNIT_EXPECT_FALSE(test, list_first_entry_or_null(&list,
+				struct list_test_struct, list));
+
+	list_add_tail(&test_struct1.list, &list);
+	list_add_tail(&test_struct2.list, &list);
+
+	KUNIT_EXPECT_PTR_EQ(test, &test_struct1,
+			list_first_entry_or_null(&list,
+				struct list_test_struct, list));
+}
+
+static void list_test_list_next_entry(struct kunit *test)
+{
+	struct list_test_struct test_struct1, test_struct2;
+	LIST_HEAD(list);
+
+	list_add_tail(&test_struct1.list, &list);
+	list_add_tail(&test_struct2.list, &list);
+
+
+	KUNIT_EXPECT_PTR_EQ(test, &test_struct2, list_next_entry(&test_struct1,
+				list));
+}
+
+static void list_test_list_prev_entry(struct kunit *test)
+{
+	struct list_test_struct test_struct1, test_struct2;
+	LIST_HEAD(list);
+
+	list_add_tail(&test_struct1.list, &list);
+	list_add_tail(&test_struct2.list, &list);
+
+
+	KUNIT_EXPECT_PTR_EQ(test, &test_struct1, list_prev_entry(&test_struct2,
+				list));
+}
+
+static void list_test_list_for_each(struct kunit *test)
+{
+	struct list_head entries[3], *cur;
+	LIST_HEAD(list);
+	int i = 0;
+
+	list_add_tail(&entries[0], &list);
+	list_add_tail(&entries[1], &list);
+	list_add_tail(&entries[2], &list);
+
+	list_for_each(cur, &list) {
+		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
+		i++;
+	}
+
+	KUNIT_EXPECT_EQ(test, i, 3);
+}
+
+static void list_test_list_for_each_prev(struct kunit *test)
+{
+	struct list_head entries[3], *cur;
+	LIST_HEAD(list);
+	int i = 2;
+
+	list_add_tail(&entries[0], &list);
+	list_add_tail(&entries[1], &list);
+	list_add_tail(&entries[2], &list);
+
+	list_for_each_prev(cur, &list) {
+		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
+		i--;
+	}
+
+	KUNIT_EXPECT_EQ(test, i, -1);
+}
+
+static void list_test_list_for_each_safe(struct kunit *test)
+{
+	struct list_head entries[3], *cur, *n;
+	LIST_HEAD(list);
+	int i = 0;
+
+
+	list_add_tail(&entries[0], &list);
+	list_add_tail(&entries[1], &list);
+	list_add_tail(&entries[2], &list);
+
+	list_for_each_safe(cur, n, &list) {
+		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
+		list_del(&entries[i]);
+		i++;
+	}
+
+	KUNIT_EXPECT_EQ(test, i, 3);
+	KUNIT_EXPECT_TRUE(test, list_empty(&list));
+}
+
+static void list_test_list_for_each_prev_safe(struct kunit *test)
+{
+	struct list_head entries[3], *cur, *n;
+	LIST_HEAD(list);
+	int i = 2;
+
+	list_add_tail(&entries[0], &list);
+	list_add_tail(&entries[1], &list);
+	list_add_tail(&entries[2], &list);
+
+	list_for_each_prev_safe(cur, n, &list) {
+		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
+		list_del(&entries[i]);
+		i--;
+	}
+
+	KUNIT_EXPECT_EQ(test, i, -1);
+	KUNIT_EXPECT_TRUE(test, list_empty(&list));
+}
+
+static void list_test_list_for_each_entry(struct kunit *test)
+{
+	struct list_test_struct entries[5], *cur;
+	static LIST_HEAD(list);
+	int i = 0;
+
+	for (i = 0; i < 5; ++i) {
+		entries[i].data = i;
+		list_add_tail(&entries[i].list, &list);
+	}
+
+	i = 0;
+
+	list_for_each_entry(cur, &list, list) {
+		KUNIT_EXPECT_EQ(test, cur->data, i);
+		i++;
+	}
+
+	KUNIT_EXPECT_EQ(test, i, 5);
+}
+
+static void list_test_list_for_each_entry_reverse(struct kunit *test)
+{
+	struct list_test_struct entries[5], *cur;
+	static LIST_HEAD(list);
+	int i = 0;
+
+	for (i = 0; i < 5; ++i) {
+		entries[i].data = i;
+		list_add_tail(&entries[i].list, &list);
+	}
+
+	i = 4;
+
+	list_for_each_entry_reverse(cur, &list, list) {
+		KUNIT_EXPECT_EQ(test, cur->data, i);
+		i--;
+	}
+
+	KUNIT_EXPECT_EQ(test, i, -1);
+}
+
+static struct kunit_case list_test_cases[] = {
+	KUNIT_CASE(list_test_list_init),
+	KUNIT_CASE(list_test_list_add),
+	KUNIT_CASE(list_test_list_add_tail),
+	KUNIT_CASE(list_test_list_del),
+	KUNIT_CASE(list_test_list_replace),
+	KUNIT_CASE(list_test_list_replace_init),
+	KUNIT_CASE(list_test_list_swap),
+	KUNIT_CASE(list_test_list_del_init),
+	KUNIT_CASE(list_test_list_move),
+	KUNIT_CASE(list_test_list_move_tail),
+	KUNIT_CASE(list_test_list_bulk_move_tail),
+	KUNIT_CASE(list_test_list_is_first),
+	KUNIT_CASE(list_test_list_is_last),
+	KUNIT_CASE(list_test_list_empty),
+	KUNIT_CASE(list_test_list_empty_careful),
+	KUNIT_CASE(list_test_list_rotate_left),
+	KUNIT_CASE(list_test_list_rotate_to_front),
+	KUNIT_CASE(list_test_list_is_singular),
+	KUNIT_CASE(list_test_list_cut_position),
+	KUNIT_CASE(list_test_list_cut_before),
+	KUNIT_CASE(list_test_list_splice),
+	KUNIT_CASE(list_test_list_splice_tail),
+	KUNIT_CASE(list_test_list_splice_init),
+	KUNIT_CASE(list_test_list_splice_tail_init),
+	KUNIT_CASE(list_test_list_entry),
+	KUNIT_CASE(list_test_list_first_entry),
+	KUNIT_CASE(list_test_list_last_entry),
+	KUNIT_CASE(list_test_list_first_entry_or_null),
+	KUNIT_CASE(list_test_list_next_entry),
+	KUNIT_CASE(list_test_list_prev_entry),
+	KUNIT_CASE(list_test_list_for_each),
+	KUNIT_CASE(list_test_list_for_each_prev),
+	KUNIT_CASE(list_test_list_for_each_safe),
+	KUNIT_CASE(list_test_list_for_each_prev_safe),
+	KUNIT_CASE(list_test_list_for_each_entry),
+	KUNIT_CASE(list_test_list_for_each_entry_reverse),
+	{},
+};
+
+static struct kunit_suite list_test_module = {
+	.name = "list-kunit-test",
+	.test_cases = list_test_cases,
+};
+
+kunit_test_suite(list_test_module);
diff --git a/lib/livepatch/Makefile b/lib/livepatch/Makefile
index 26900ddaef82..295b94bff370 100644
--- a/lib/livepatch/Makefile
+++ b/lib/livepatch/Makefile
@@ -8,7 +8,10 @@ obj-$(CONFIG_TEST_LIVEPATCH) += test_klp_atomic_replace.o \
 				test_klp_callbacks_busy.o \
 				test_klp_callbacks_mod.o \
 				test_klp_livepatch.o \
-				test_klp_shadow_vars.o
+				test_klp_shadow_vars.o \
+				test_klp_state.o \
+				test_klp_state2.o \
+				test_klp_state3.o
 
 # Target modules to be livepatched require CC_FLAGS_FTRACE
 CFLAGS_test_klp_callbacks_busy.o	+= $(CC_FLAGS_FTRACE)
diff --git a/lib/livepatch/test_klp_state.c b/lib/livepatch/test_klp_state.c
new file mode 100644
index 000000000000..57a4253acb01
--- /dev/null
+++ b/lib/livepatch/test_klp_state.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 SUSE
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/printk.h>
+#include <linux/livepatch.h>
+
+#define CONSOLE_LOGLEVEL_STATE 1
+/* Version 1 does not support migration. */
+#define CONSOLE_LOGLEVEL_STATE_VERSION 1
+
+static const char *const module_state[] = {
+	[MODULE_STATE_LIVE]	= "[MODULE_STATE_LIVE] Normal state",
+	[MODULE_STATE_COMING]	= "[MODULE_STATE_COMING] Full formed, running module_init",
+	[MODULE_STATE_GOING]	= "[MODULE_STATE_GOING] Going away",
+	[MODULE_STATE_UNFORMED]	= "[MODULE_STATE_UNFORMED] Still setting it up",
+};
+
+static void callback_info(const char *callback, struct klp_object *obj)
+{
+	if (obj->mod)
+		pr_info("%s: %s -> %s\n", callback, obj->mod->name,
+			module_state[obj->mod->state]);
+	else
+		pr_info("%s: vmlinux\n", callback);
+}
+
+static struct klp_patch patch;
+
+static int allocate_loglevel_state(void)
+{
+	struct klp_state *loglevel_state;
+
+	loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE);
+	if (!loglevel_state)
+		return -EINVAL;
+
+	loglevel_state->data = kzalloc(sizeof(console_loglevel), GFP_KERNEL);
+	if (!loglevel_state->data)
+		return -ENOMEM;
+
+	pr_info("%s: allocating space to store console_loglevel\n",
+		__func__);
+	return 0;
+}
+
+static void fix_console_loglevel(void)
+{
+	struct klp_state *loglevel_state;
+
+	loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE);
+	if (!loglevel_state)
+		return;
+
+	pr_info("%s: fixing console_loglevel\n", __func__);
+	*(int *)loglevel_state->data = console_loglevel;
+	console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH;
+}
+
+static void restore_console_loglevel(void)
+{
+	struct klp_state *loglevel_state;
+
+	loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE);
+	if (!loglevel_state)
+		return;
+
+	pr_info("%s: restoring console_loglevel\n", __func__);
+	console_loglevel = *(int *)loglevel_state->data;
+}
+
+static void free_loglevel_state(void)
+{
+	struct klp_state *loglevel_state;
+
+	loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE);
+	if (!loglevel_state)
+		return;
+
+	pr_info("%s: freeing space for the stored console_loglevel\n",
+		__func__);
+	kfree(loglevel_state->data);
+}
+
+/* Executed on object patching (ie, patch enablement) */
+static int pre_patch_callback(struct klp_object *obj)
+{
+	callback_info(__func__, obj);
+	return allocate_loglevel_state();
+}
+
+/* Executed on object unpatching (ie, patch disablement) */
+static void post_patch_callback(struct klp_object *obj)
+{
+	callback_info(__func__, obj);
+	fix_console_loglevel();
+}
+
+/* Executed on object unpatching (ie, patch disablement) */
+static void pre_unpatch_callback(struct klp_object *obj)
+{
+	callback_info(__func__, obj);
+	restore_console_loglevel();
+}
+
+/* Executed on object unpatching (ie, patch disablement) */
+static void post_unpatch_callback(struct klp_object *obj)
+{
+	callback_info(__func__, obj);
+	free_loglevel_state();
+}
+
+static struct klp_func no_funcs[] = {
+	{}
+};
+
+static struct klp_object objs[] = {
+	{
+		.name = NULL,	/* vmlinux */
+		.funcs = no_funcs,
+		.callbacks = {
+			.pre_patch = pre_patch_callback,
+			.post_patch = post_patch_callback,
+			.pre_unpatch = pre_unpatch_callback,
+			.post_unpatch = post_unpatch_callback,
+		},
+	}, { }
+};
+
+static struct klp_state states[] = {
+	{
+		.id = CONSOLE_LOGLEVEL_STATE,
+		.version = CONSOLE_LOGLEVEL_STATE_VERSION,
+	}, { }
+};
+
+static struct klp_patch patch = {
+	.mod = THIS_MODULE,
+	.objs = objs,
+	.states = states,
+	.replace = true,
+};
+
+static int test_klp_callbacks_demo_init(void)
+{
+	return klp_enable_patch(&patch);
+}
+
+static void test_klp_callbacks_demo_exit(void)
+{
+}
+
+module_init(test_klp_callbacks_demo_init);
+module_exit(test_klp_callbacks_demo_exit);
+MODULE_LICENSE("GPL");
+MODULE_INFO(livepatch, "Y");
+MODULE_AUTHOR("Petr Mladek <pmladek@suse.com>");
+MODULE_DESCRIPTION("Livepatch test: system state modification");
diff --git a/lib/livepatch/test_klp_state2.c b/lib/livepatch/test_klp_state2.c
new file mode 100644
index 000000000000..c978ea4d5e67
--- /dev/null
+++ b/lib/livepatch/test_klp_state2.c
@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 SUSE
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/printk.h>
+#include <linux/livepatch.h>
+
+#define CONSOLE_LOGLEVEL_STATE 1
+/* Version 2 supports migration. */
+#define CONSOLE_LOGLEVEL_STATE_VERSION 2
+
+static const char *const module_state[] = {
+	[MODULE_STATE_LIVE]	= "[MODULE_STATE_LIVE] Normal state",
+	[MODULE_STATE_COMING]	= "[MODULE_STATE_COMING] Full formed, running module_init",
+	[MODULE_STATE_GOING]	= "[MODULE_STATE_GOING] Going away",
+	[MODULE_STATE_UNFORMED]	= "[MODULE_STATE_UNFORMED] Still setting it up",
+};
+
+static void callback_info(const char *callback, struct klp_object *obj)
+{
+	if (obj->mod)
+		pr_info("%s: %s -> %s\n", callback, obj->mod->name,
+			module_state[obj->mod->state]);
+	else
+		pr_info("%s: vmlinux\n", callback);
+}
+
+static struct klp_patch patch;
+
+static int allocate_loglevel_state(void)
+{
+	struct klp_state *loglevel_state, *prev_loglevel_state;
+
+	prev_loglevel_state = klp_get_prev_state(CONSOLE_LOGLEVEL_STATE);
+	if (prev_loglevel_state) {
+		pr_info("%s: space to store console_loglevel already allocated\n",
+		__func__);
+		return 0;
+	}
+
+	loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE);
+	if (!loglevel_state)
+		return -EINVAL;
+
+	loglevel_state->data = kzalloc(sizeof(console_loglevel), GFP_KERNEL);
+	if (!loglevel_state->data)
+		return -ENOMEM;
+
+	pr_info("%s: allocating space to store console_loglevel\n",
+		__func__);
+	return 0;
+}
+
+static void fix_console_loglevel(void)
+{
+	struct klp_state *loglevel_state, *prev_loglevel_state;
+
+	loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE);
+	if (!loglevel_state)
+		return;
+
+	prev_loglevel_state = klp_get_prev_state(CONSOLE_LOGLEVEL_STATE);
+	if (prev_loglevel_state) {
+		pr_info("%s: taking over the console_loglevel change\n",
+		__func__);
+		loglevel_state->data = prev_loglevel_state->data;
+		return;
+	}
+
+	pr_info("%s: fixing console_loglevel\n", __func__);
+	*(int *)loglevel_state->data = console_loglevel;
+	console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH;
+}
+
+static void restore_console_loglevel(void)
+{
+	struct klp_state *loglevel_state, *prev_loglevel_state;
+
+	prev_loglevel_state = klp_get_prev_state(CONSOLE_LOGLEVEL_STATE);
+	if (prev_loglevel_state) {
+		pr_info("%s: passing the console_loglevel change back to the old livepatch\n",
+		__func__);
+		return;
+	}
+
+	loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE);
+	if (!loglevel_state)
+		return;
+
+	pr_info("%s: restoring console_loglevel\n", __func__);
+	console_loglevel = *(int *)loglevel_state->data;
+}
+
+static void free_loglevel_state(void)
+{
+	struct klp_state *loglevel_state, *prev_loglevel_state;
+
+	prev_loglevel_state = klp_get_prev_state(CONSOLE_LOGLEVEL_STATE);
+	if (prev_loglevel_state) {
+		pr_info("%s: keeping space to store console_loglevel\n",
+		__func__);
+		return;
+	}
+
+	loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE);
+	if (!loglevel_state)
+		return;
+
+	pr_info("%s: freeing space for the stored console_loglevel\n",
+		__func__);
+	kfree(loglevel_state->data);
+}
+
+/* Executed on object patching (ie, patch enablement) */
+static int pre_patch_callback(struct klp_object *obj)
+{
+	callback_info(__func__, obj);
+	return allocate_loglevel_state();
+}
+
+/* Executed on object unpatching (ie, patch disablement) */
+static void post_patch_callback(struct klp_object *obj)
+{
+	callback_info(__func__, obj);
+	fix_console_loglevel();
+}
+
+/* Executed on object unpatching (ie, patch disablement) */
+static void pre_unpatch_callback(struct klp_object *obj)
+{
+	callback_info(__func__, obj);
+	restore_console_loglevel();
+}
+
+/* Executed on object unpatching (ie, patch disablement) */
+static void post_unpatch_callback(struct klp_object *obj)
+{
+	callback_info(__func__, obj);
+	free_loglevel_state();
+}
+
+static struct klp_func no_funcs[] = {
+	{}
+};
+
+static struct klp_object objs[] = {
+	{
+		.name = NULL,	/* vmlinux */
+		.funcs = no_funcs,
+		.callbacks = {
+			.pre_patch = pre_patch_callback,
+			.post_patch = post_patch_callback,
+			.pre_unpatch = pre_unpatch_callback,
+			.post_unpatch = post_unpatch_callback,
+		},
+	}, { }
+};
+
+static struct klp_state states[] = {
+	{
+		.id = CONSOLE_LOGLEVEL_STATE,
+		.version = CONSOLE_LOGLEVEL_STATE_VERSION,
+	}, { }
+};
+
+static struct klp_patch patch = {
+	.mod = THIS_MODULE,
+	.objs = objs,
+	.states = states,
+	.replace = true,
+};
+
+static int test_klp_callbacks_demo_init(void)
+{
+	return klp_enable_patch(&patch);
+}
+
+static void test_klp_callbacks_demo_exit(void)
+{
+}
+
+module_init(test_klp_callbacks_demo_init);
+module_exit(test_klp_callbacks_demo_exit);
+MODULE_LICENSE("GPL");
+MODULE_INFO(livepatch, "Y");
+MODULE_AUTHOR("Petr Mladek <pmladek@suse.com>");
+MODULE_DESCRIPTION("Livepatch test: system state modification");
diff --git a/lib/livepatch/test_klp_state3.c b/lib/livepatch/test_klp_state3.c
new file mode 100644
index 000000000000..9226579d10c5
--- /dev/null
+++ b/lib/livepatch/test_klp_state3.c
@@ -0,0 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 SUSE
+
+/* The console loglevel fix is the same in the next cumulative patch. */
+#include "test_klp_state2.c"
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 969e5400a615..33feec8989f1 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -236,23 +236,6 @@ bool sbitmap_any_bit_set(const struct sbitmap *sb)
 }
 EXPORT_SYMBOL_GPL(sbitmap_any_bit_set);
 
-bool sbitmap_any_bit_clear(const struct sbitmap *sb)
-{
-	unsigned int i;
-
-	for (i = 0; i < sb->map_nr; i++) {
-		const struct sbitmap_word *word = &sb->map[i];
-		unsigned long mask = word->word & ~word->cleared;
-		unsigned long ret;
-
-		ret = find_first_zero_bit(&mask, word->depth);
-		if (ret < word->depth)
-			return true;
-	}
-	return false;
-}
-EXPORT_SYMBOL_GPL(sbitmap_any_bit_clear);
-
 static unsigned int __sbitmap_weight(const struct sbitmap *sb, bool set)
 {
 	unsigned int i, weight = 0;
diff --git a/lib/test_printf.c b/lib/test_printf.c
index 5d94cbff2120..030daeb4fe21 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -594,6 +594,26 @@ flags(void)
 }
 
 static void __init
+errptr(void)
+{
+	test("-1234", "%pe", ERR_PTR(-1234));
+
+	/* Check that %pe with a non-ERR_PTR gets treated as ordinary %p. */
+	BUILD_BUG_ON(IS_ERR(PTR));
+	test_hashed("%pe", PTR);
+
+#ifdef CONFIG_SYMBOLIC_ERRNAME
+	test("(-ENOTSOCK)", "(%pe)", ERR_PTR(-ENOTSOCK));
+	test("(-EAGAIN)", "(%pe)", ERR_PTR(-EAGAIN));
+	BUILD_BUG_ON(EAGAIN != EWOULDBLOCK);
+	test("(-EAGAIN)", "(%pe)", ERR_PTR(-EWOULDBLOCK));
+	test("[-EIO    ]", "[%-8pe]", ERR_PTR(-EIO));
+	test("[    -EIO]", "[%8pe]", ERR_PTR(-EIO));
+	test("-EPROBE_DEFER", "%pe", ERR_PTR(-EPROBE_DEFER));
+#endif
+}
+
+static void __init
 test_pointer(void)
 {
 	plain();
@@ -615,6 +635,7 @@ test_pointer(void)
 	bitmap();
 	netdev_features();
 	flags();
+	errptr();
 }
 
 static void __init selftest(void)
diff --git a/lib/ubsan.c b/lib/ubsan.c
index e7d31735950d..b652cc14dd60 100644
--- a/lib/ubsan.c
+++ b/lib/ubsan.c
@@ -119,7 +119,7 @@ static void val_to_string(char *str, size_t size, struct type_descriptor *type,
 {
 	if (type_is_int(type)) {
 		if (type_bit_width(type) == 128) {
-#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+#if defined(CONFIG_ARCH_SUPPORTS_INT128)
 			u_max val = get_unsigned_val(type, value);
 
 			scnprintf(str, size, "0x%08x%08x%08x%08x",
diff --git a/lib/ubsan.h b/lib/ubsan.h
index b8fa83864467..7b56c09473a9 100644
--- a/lib/ubsan.h
+++ b/lib/ubsan.h
@@ -78,7 +78,7 @@ struct invalid_value_data {
 	struct type_descriptor *type;
 };
 
-#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+#if defined(CONFIG_ARCH_SUPPORTS_INT128)
 typedef __int128 s_max;
 typedef unsigned __int128 u_max;
 #else
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index e78017a3e1bd..b54d252b398e 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -21,6 +21,7 @@
 #include <linux/build_bug.h>
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
+#include <linux/errname.h>
 #include <linux/module.h>	/* for KSYM_SYMBOL_LEN */
 #include <linux/types.h>
 #include <linux/string.h>
@@ -613,6 +614,25 @@ static char *string_nocheck(char *buf, char *end, const char *s,
 	return widen_string(buf, len, end, spec);
 }
 
+static char *err_ptr(char *buf, char *end, void *ptr,
+		     struct printf_spec spec)
+{
+	int err = PTR_ERR(ptr);
+	const char *sym = errname(err);
+
+	if (sym)
+		return string_nocheck(buf, end, sym, spec);
+
+	/*
+	 * Somebody passed ERR_PTR(-1234) or some other non-existing
+	 * Efoo - or perhaps CONFIG_SYMBOLIC_ERRNAME=n. Fall back to
+	 * printing it as its decimal representation.
+	 */
+	spec.flags |= SIGN;
+	spec.base = 10;
+	return number(buf, end, err, spec);
+}
+
 /* Be careful: error messages must fit into the given buffer. */
 static char *error_string(char *buf, char *end, const char *s,
 			  struct printf_spec spec)
@@ -2187,6 +2207,11 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		return kobject_string(buf, end, ptr, spec, fmt);
 	case 'x':
 		return pointer_string(buf, end, ptr, spec);
+	case 'e':
+		/* %pe with a non-ERR_PTR gets treated as plain %p */
+		if (!IS_ERR(ptr))
+			break;
+		return err_ptr(buf, end, ptr, spec);
 	}
 
 	/* default is to _not_ leak addresses, hash before printing */
@@ -2823,6 +2848,7 @@ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args)
 			case 'f':
 			case 'x':
 			case 'K':
+			case 'e':
 				save_arg(void *);
 				break;
 			default:
@@ -2999,6 +3025,7 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf)
 			case 'f':
 			case 'x':
 			case 'K':
+			case 'e':
 				process = true;
 				break;
 			default:
diff --git a/mm/memory.c b/mm/memory.c
index b1ca51a079f2..b6a5d6a08438 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -118,6 +118,18 @@ int randomize_va_space __read_mostly =
 					2;
 #endif
 
+#ifndef arch_faults_on_old_pte
+static inline bool arch_faults_on_old_pte(void)
+{
+	/*
+	 * Those arches which don't have hw access flag feature need to
+	 * implement their own helper. By default, "true" means pagefault
+	 * will be hit on old pte.
+	 */
+	return true;
+}
+#endif
+
 static int __init disable_randmaps(char *s)
 {
 	randomize_va_space = 0;
@@ -2145,32 +2157,82 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
 	return same;
 }
 
-static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
+static inline bool cow_user_page(struct page *dst, struct page *src,
+				 struct vm_fault *vmf)
 {
+	bool ret;
+	void *kaddr;
+	void __user *uaddr;
+	bool force_mkyoung;
+	struct vm_area_struct *vma = vmf->vma;
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long addr = vmf->address;
+
 	debug_dma_assert_idle(src);
 
+	if (likely(src)) {
+		copy_user_highpage(dst, src, addr, vma);
+		return true;
+	}
+
 	/*
 	 * If the source page was a PFN mapping, we don't have
 	 * a "struct page" for it. We do a best-effort copy by
 	 * just copying from the original user address. If that
 	 * fails, we just zero-fill it. Live with it.
 	 */
-	if (unlikely(!src)) {
-		void *kaddr = kmap_atomic(dst);
-		void __user *uaddr = (void __user *)(va & PAGE_MASK);
+	kaddr = kmap_atomic(dst);
+	uaddr = (void __user *)(addr & PAGE_MASK);
+
+	/*
+	 * On architectures with software "accessed" bits, we would
+	 * take a double page fault, so mark it accessed here.
+	 */
+	force_mkyoung = arch_faults_on_old_pte() && !pte_young(vmf->orig_pte);
+	if (force_mkyoung) {
+		pte_t entry;
+
+		vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
+		if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
+			/*
+			 * Other thread has already handled the fault
+			 * and we don't need to do anything. If it's
+			 * not the case, the fault will be triggered
+			 * again on the same address.
+			 */
+			ret = false;
+			goto pte_unlock;
+		}
 
+		entry = pte_mkyoung(vmf->orig_pte);
+		if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0))
+			update_mmu_cache(vma, addr, vmf->pte);
+	}
+
+	/*
+	 * This really shouldn't fail, because the page is there
+	 * in the page tables. But it might just be unreadable,
+	 * in which case we just give up and fill the result with
+	 * zeroes.
+	 */
+	if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
 		/*
-		 * This really shouldn't fail, because the page is there
-		 * in the page tables. But it might just be unreadable,
-		 * in which case we just give up and fill the result with
-		 * zeroes.
+		 * Give a warn in case there can be some obscure
+		 * use-case
 		 */
-		if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
-			clear_page(kaddr);
-		kunmap_atomic(kaddr);
-		flush_dcache_page(dst);
-	} else
-		copy_user_highpage(dst, src, va, vma);
+		WARN_ON_ONCE(1);
+		clear_page(kaddr);
+	}
+
+	ret = true;
+
+pte_unlock:
+	if (force_mkyoung)
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+	kunmap_atomic(kaddr);
+	flush_dcache_page(dst);
+
+	return ret;
 }
 
 static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma)
@@ -2327,7 +2389,19 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 				vmf->address);
 		if (!new_page)
 			goto oom;
-		cow_user_page(new_page, old_page, vmf->address, vma);
+
+		if (!cow_user_page(new_page, old_page, vmf)) {
+			/*
+			 * COW failed, if the fault was solved by other,
+			 * it's fine. If not, userspace would re-fault on
+			 * the same address and we will handle the fault
+			 * from the second attempt.
+			 */
+			put_page(new_page);
+			if (old_page)
+				put_page(old_page);
+			return 0;
+		}
 	}
 
 	if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false))
diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig
index 3803135c88ff..165148c7c4ce 100644
--- a/net/bluetooth/Kconfig
+++ b/net/bluetooth/Kconfig
@@ -9,7 +9,7 @@ menuconfig BT
 	depends on RFKILL || !RFKILL
 	select CRC16
 	select CRYPTO
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_AES
 	imply CRYPTO_AES
 	select CRYPTO_CMAC
diff --git a/net/core/filter.c b/net/core/filter.c
index 49ded4a7588a..b0ed048585ba 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4102,7 +4102,7 @@ BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb)
 		return 0;
 
 	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
-	return cgrp->kn->id.id;
+	return cgroup_id(cgrp);
 }
 
 static const struct bpf_func_proto bpf_skb_cgroup_id_proto = {
@@ -4127,7 +4127,7 @@ BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
 	if (!ancestor)
 		return 0;
 
-	return ancestor->kn->id.id;
+	return cgroup_id(ancestor);
 }
 
 static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = {
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 256b7954b720..8881dd943dd0 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -93,7 +93,7 @@ static int extend_netdev_table(struct net_device *dev, u32 target_idx)
 static u32 netprio_prio(struct cgroup_subsys_state *css, struct net_device *dev)
 {
 	struct netprio_map *map = rcu_dereference_rtnl(dev->priomap);
-	int id = css->cgroup->id;
+	int id = css->id;
 
 	if (map && id < map->priomap_len)
 		return map->priomap[id];
@@ -113,7 +113,7 @@ static int netprio_set_prio(struct cgroup_subsys_state *css,
 			    struct net_device *dev, u32 prio)
 {
 	struct netprio_map *map;
-	int id = css->cgroup->id;
+	int id = css->id;
 	int ret;
 
 	/* avoid extending priomap for zero writes */
@@ -177,7 +177,7 @@ static void cgrp_css_free(struct cgroup_subsys_state *css)
 
 static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft)
 {
-	return css->cgroup->id;
+	return css->id;
 }
 
 static int read_priomap(struct seq_file *sf, void *v)
@@ -237,7 +237,7 @@ static void net_prio_attach(struct cgroup_taskset *tset)
 	struct cgroup_subsys_state *css;
 
 	cgroup_taskset_for_each(p, css, tset) {
-		void *v = (void *)(unsigned long)css->cgroup->id;
+		void *v = (void *)(unsigned long)css->id;
 
 		task_lock(p);
 		iterate_fd(p->files, 0, update_netprio, v);
diff --git a/net/rxrpc/Kconfig b/net/rxrpc/Kconfig
index 05610c3a3d25..57ebb29c26ad 100644
--- a/net/rxrpc/Kconfig
+++ b/net/rxrpc/Kconfig
@@ -49,7 +49,7 @@ config RXKAD
 	depends on AF_RXRPC
 	select CRYPTO
 	select CRYPTO_MANAGER
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_PCBC
 	select CRYPTO_FCRYPT
 	help
diff --git a/net/socket.c b/net/socket.c
index 6a9ab7a8b1d2..17bc1eee198a 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -404,6 +404,7 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
 
 	sock->file = file;
 	file->private_data = sock;
+	stream_open(SOCK_INODE(sock), file);
 	return file;
 }
 EXPORT_SYMBOL(sock_alloc_file);
@@ -1690,24 +1691,13 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog)
 	return __sys_listen(fd, backlog);
 }
 
-/*
- *	For accept, we attempt to create a new socket, set up the link
- *	with the client, wake up the client, then return the new
- *	connected fd. We collect the address of the connector in kernel
- *	space and move it to user at the very end. This is unclean because
- *	we open the socket then return an error.
- *
- *	1003.1g adds the ability to recvmsg() to query connection pending
- *	status to recvmsg. We need to add that support in a way thats
- *	clean when we restructure accept also.
- */
-
-int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
-		  int __user *upeer_addrlen, int flags)
+int __sys_accept4_file(struct file *file, unsigned file_flags,
+		       struct sockaddr __user *upeer_sockaddr,
+		       int __user *upeer_addrlen, int flags)
 {
 	struct socket *sock, *newsock;
 	struct file *newfile;
-	int err, len, newfd, fput_needed;
+	int err, len, newfd;
 	struct sockaddr_storage address;
 
 	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
@@ -1716,14 +1706,14 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
 		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
 
-	sock = sockfd_lookup_light(fd, &err, &fput_needed);
+	sock = sock_from_file(file, &err);
 	if (!sock)
 		goto out;
 
 	err = -ENFILE;
 	newsock = sock_alloc();
 	if (!newsock)
-		goto out_put;
+		goto out;
 
 	newsock->type = sock->type;
 	newsock->ops = sock->ops;
@@ -1738,20 +1728,21 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 	if (unlikely(newfd < 0)) {
 		err = newfd;
 		sock_release(newsock);
-		goto out_put;
+		goto out;
 	}
 	newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name);
 	if (IS_ERR(newfile)) {
 		err = PTR_ERR(newfile);
 		put_unused_fd(newfd);
-		goto out_put;
+		goto out;
 	}
 
 	err = security_socket_accept(sock, newsock);
 	if (err)
 		goto out_fd;
 
-	err = sock->ops->accept(sock, newsock, sock->file->f_flags, false);
+	err = sock->ops->accept(sock, newsock, sock->file->f_flags | file_flags,
+					false);
 	if (err < 0)
 		goto out_fd;
 
@@ -1772,15 +1763,42 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 
 	fd_install(newfd, newfile);
 	err = newfd;
-
-out_put:
-	fput_light(sock->file, fput_needed);
 out:
 	return err;
 out_fd:
 	fput(newfile);
 	put_unused_fd(newfd);
-	goto out_put;
+	goto out;
+
+}
+
+/*
+ *	For accept, we attempt to create a new socket, set up the link
+ *	with the client, wake up the client, then return the new
+ *	connected fd. We collect the address of the connector in kernel
+ *	space and move it to user at the very end. This is unclean because
+ *	we open the socket then return an error.
+ *
+ *	1003.1g adds the ability to recvmsg() to query connection pending
+ *	status to recvmsg. We need to add that support in a way thats
+ *	clean when we restructure accept also.
+ */
+
+int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
+		  int __user *upeer_addrlen, int flags)
+{
+	int ret = -EBADF;
+	struct fd f;
+
+	f = fdget(fd);
+	if (f.file) {
+		ret = __sys_accept4_file(f.file, 0, upeer_sockaddr,
+						upeer_addrlen, flags);
+		if (f.flags)
+			fput(f.file);
+	}
+
+	return ret;
 }
 
 SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
index 17b8a7d4b71b..6921a18201a0 100644
--- a/net/xfrm/Kconfig
+++ b/net/xfrm/Kconfig
@@ -16,7 +16,7 @@ config XFRM_ALGO
 	select XFRM
 	select CRYPTO
 	select CRYPTO_HASH
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 
 if INET
 config XFRM_USER
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
index 32a378e7011f..4dae3ab8d030 100644
--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -626,8 +626,8 @@ static const struct xfrm_algo_list xfrm_aalg_list = {
 static const struct xfrm_algo_list xfrm_ealg_list = {
 	.algs = ealg_list,
 	.entries = ARRAY_SIZE(ealg_list),
-	.type = CRYPTO_ALG_TYPE_BLKCIPHER,
-	.mask = CRYPTO_ALG_TYPE_BLKCIPHER_MASK,
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.mask = CRYPTO_ALG_TYPE_MASK,
 };
 
 static const struct xfrm_algo_list xfrm_calg_list = {
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 6fcc66afb088..4b40445938dc 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -6022,7 +6022,7 @@ sub process {
 				while ($fmt =~ /(\%[\*\d\.]*p(\w))/g) {
 					$specifier = $1;
 					$extension = $2;
-					if ($extension !~ /[SsBKRraEhMmIiUDdgVCbGNOxt]/) {
+					if ($extension !~ /[SsBKRraEehMmIiUDdgVCbGNOxt]/) {
 						$bad_specifier = $specifier;
 						last;
 					}
diff --git a/security/keys/Makefile b/security/keys/Makefile
index 9cef54064f60..074f27538f55 100644
--- a/security/keys/Makefile
+++ b/security/keys/Makefile
@@ -28,5 +28,5 @@ obj-$(CONFIG_ASYMMETRIC_KEY_TYPE) += keyctl_pkey.o
 # Key types
 #
 obj-$(CONFIG_BIG_KEYS) += big_key.o
-obj-$(CONFIG_TRUSTED_KEYS) += trusted.o
+obj-$(CONFIG_TRUSTED_KEYS) += trusted-keys/
 obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted-keys/
diff --git a/security/keys/trusted-keys/Makefile b/security/keys/trusted-keys/Makefile
new file mode 100644
index 000000000000..7b73cebbb378
--- /dev/null
+++ b/security/keys/trusted-keys/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for trusted keys
+#
+
+obj-$(CONFIG_TRUSTED_KEYS) += trusted.o
+trusted-y += trusted_tpm1.o
+trusted-y += trusted_tpm2.o
diff --git a/security/keys/trusted.c b/security/keys/trusted-keys/trusted_tpm1.c
index 1fbd77816610..d2c5ec1e040b 100644
--- a/security/keys/trusted.c
+++ b/security/keys/trusted-keys/trusted_tpm1.c
@@ -27,7 +27,7 @@
 #include <linux/tpm.h>
 #include <linux/tpm_command.h>
 
-#include <keys/trusted.h>
+#include <keys/trusted_tpm.h>
 
 static const char hmac_alg[] = "hmac(sha1)";
 static const char hash_alg[] = "sha1";
@@ -406,13 +406,10 @@ static int osap(struct tpm_buf *tb, struct osapsess *s,
 	if (ret != TPM_NONCE_SIZE)
 		return ret;
 
-	INIT_BUF(tb);
-	store16(tb, TPM_TAG_RQU_COMMAND);
-	store32(tb, TPM_OSAP_SIZE);
-	store32(tb, TPM_ORD_OSAP);
-	store16(tb, type);
-	store32(tb, handle);
-	storebytes(tb, ononce, TPM_NONCE_SIZE);
+	tpm_buf_reset(tb, TPM_TAG_RQU_COMMAND, TPM_ORD_OSAP);
+	tpm_buf_append_u16(tb, type);
+	tpm_buf_append_u32(tb, handle);
+	tpm_buf_append(tb, ononce, TPM_NONCE_SIZE);
 
 	ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE);
 	if (ret < 0)
@@ -437,10 +434,7 @@ int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce)
 	if (!chip)
 		return -ENODEV;
 
-	INIT_BUF(tb);
-	store16(tb, TPM_TAG_RQU_COMMAND);
-	store32(tb, TPM_OIAP_SIZE);
-	store32(tb, TPM_ORD_OIAP);
+	tpm_buf_reset(tb, TPM_TAG_RQU_COMMAND, TPM_ORD_OIAP);
 	ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE);
 	if (ret < 0)
 		return ret;
@@ -535,20 +529,17 @@ static int tpm_seal(struct tpm_buf *tb, uint16_t keytype,
 		goto out;
 
 	/* build and send the TPM request packet */
-	INIT_BUF(tb);
-	store16(tb, TPM_TAG_RQU_AUTH1_COMMAND);
-	store32(tb, TPM_SEAL_SIZE + pcrinfosize + datalen);
-	store32(tb, TPM_ORD_SEAL);
-	store32(tb, keyhandle);
-	storebytes(tb, td->encauth, SHA1_DIGEST_SIZE);
-	store32(tb, pcrinfosize);
-	storebytes(tb, pcrinfo, pcrinfosize);
-	store32(tb, datalen);
-	storebytes(tb, data, datalen);
-	store32(tb, sess.handle);
-	storebytes(tb, td->nonceodd, TPM_NONCE_SIZE);
-	store8(tb, cont);
-	storebytes(tb, td->pubauth, SHA1_DIGEST_SIZE);
+	tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_SEAL);
+	tpm_buf_append_u32(tb, keyhandle);
+	tpm_buf_append(tb, td->encauth, SHA1_DIGEST_SIZE);
+	tpm_buf_append_u32(tb, pcrinfosize);
+	tpm_buf_append(tb, pcrinfo, pcrinfosize);
+	tpm_buf_append_u32(tb, datalen);
+	tpm_buf_append(tb, data, datalen);
+	tpm_buf_append_u32(tb, sess.handle);
+	tpm_buf_append(tb, td->nonceodd, TPM_NONCE_SIZE);
+	tpm_buf_append_u8(tb, cont);
+	tpm_buf_append(tb, td->pubauth, SHA1_DIGEST_SIZE);
 
 	ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE);
 	if (ret < 0)
@@ -594,7 +585,6 @@ static int tpm_unseal(struct tpm_buf *tb,
 	uint32_t authhandle2 = 0;
 	unsigned char cont = 0;
 	uint32_t ordinal;
-	uint32_t keyhndl;
 	int ret;
 
 	/* sessions for unsealing key and data */
@@ -610,7 +600,6 @@ static int tpm_unseal(struct tpm_buf *tb,
 	}
 
 	ordinal = htonl(TPM_ORD_UNSEAL);
-	keyhndl = htonl(SRKHANDLE);
 	ret = tpm_get_random(chip, nonceodd, TPM_NONCE_SIZE);
 	if (ret != TPM_NONCE_SIZE) {
 		pr_info("trusted_key: tpm_get_random failed (%d)\n", ret);
@@ -628,20 +617,17 @@ static int tpm_unseal(struct tpm_buf *tb,
 		return ret;
 
 	/* build and send TPM request packet */
-	INIT_BUF(tb);
-	store16(tb, TPM_TAG_RQU_AUTH2_COMMAND);
-	store32(tb, TPM_UNSEAL_SIZE + bloblen);
-	store32(tb, TPM_ORD_UNSEAL);
-	store32(tb, keyhandle);
-	storebytes(tb, blob, bloblen);
-	store32(tb, authhandle1);
-	storebytes(tb, nonceodd, TPM_NONCE_SIZE);
-	store8(tb, cont);
-	storebytes(tb, authdata1, SHA1_DIGEST_SIZE);
-	store32(tb, authhandle2);
-	storebytes(tb, nonceodd, TPM_NONCE_SIZE);
-	store8(tb, cont);
-	storebytes(tb, authdata2, SHA1_DIGEST_SIZE);
+	tpm_buf_reset(tb, TPM_TAG_RQU_AUTH2_COMMAND, TPM_ORD_UNSEAL);
+	tpm_buf_append_u32(tb, keyhandle);
+	tpm_buf_append(tb, blob, bloblen);
+	tpm_buf_append_u32(tb, authhandle1);
+	tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE);
+	tpm_buf_append_u8(tb, cont);
+	tpm_buf_append(tb, authdata1, SHA1_DIGEST_SIZE);
+	tpm_buf_append_u32(tb, authhandle2);
+	tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE);
+	tpm_buf_append_u8(tb, cont);
+	tpm_buf_append(tb, authdata2, SHA1_DIGEST_SIZE);
 
 	ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE);
 	if (ret < 0) {
@@ -670,23 +656,23 @@ static int tpm_unseal(struct tpm_buf *tb,
 static int key_seal(struct trusted_key_payload *p,
 		    struct trusted_key_options *o)
 {
-	struct tpm_buf *tb;
+	struct tpm_buf tb;
 	int ret;
 
-	tb = kzalloc(sizeof *tb, GFP_KERNEL);
-	if (!tb)
-		return -ENOMEM;
+	ret = tpm_buf_init(&tb, 0, 0);
+	if (ret)
+		return ret;
 
 	/* include migratable flag at end of sealed key */
 	p->key[p->key_len] = p->migratable;
 
-	ret = tpm_seal(tb, o->keytype, o->keyhandle, o->keyauth,
+	ret = tpm_seal(&tb, o->keytype, o->keyhandle, o->keyauth,
 		       p->key, p->key_len + 1, p->blob, &p->blob_len,
 		       o->blobauth, o->pcrinfo, o->pcrinfo_len);
 	if (ret < 0)
 		pr_info("trusted_key: srkseal failed (%d)\n", ret);
 
-	kzfree(tb);
+	tpm_buf_destroy(&tb);
 	return ret;
 }
 
@@ -696,14 +682,14 @@ static int key_seal(struct trusted_key_payload *p,
 static int key_unseal(struct trusted_key_payload *p,
 		      struct trusted_key_options *o)
 {
-	struct tpm_buf *tb;
+	struct tpm_buf tb;
 	int ret;
 
-	tb = kzalloc(sizeof *tb, GFP_KERNEL);
-	if (!tb)
-		return -ENOMEM;
+	ret = tpm_buf_init(&tb, 0, 0);
+	if (ret)
+		return ret;
 
-	ret = tpm_unseal(tb, o->keyhandle, o->keyauth, p->blob, p->blob_len,
+	ret = tpm_unseal(&tb, o->keyhandle, o->keyauth, p->blob, p->blob_len,
 			 o->blobauth, p->key, &p->key_len);
 	if (ret < 0)
 		pr_info("trusted_key: srkunseal failed (%d)\n", ret);
@@ -711,7 +697,7 @@ static int key_unseal(struct trusted_key_payload *p,
 		/* pull migratable flag out of sealed key */
 		p->migratable = p->key[--p->key_len];
 
-	kzfree(tb);
+	tpm_buf_destroy(&tb);
 	return ret;
 }
 
@@ -1016,7 +1002,7 @@ static int trusted_instantiate(struct key *key,
 	switch (key_cmd) {
 	case Opt_load:
 		if (tpm2)
-			ret = tpm_unseal_trusted(chip, payload, options);
+			ret = tpm2_unseal_trusted(chip, payload, options);
 		else
 			ret = key_unseal(payload, options);
 		dump_payload(payload);
@@ -1032,7 +1018,7 @@ static int trusted_instantiate(struct key *key,
 			goto out;
 		}
 		if (tpm2)
-			ret = tpm_seal_trusted(chip, payload, options);
+			ret = tpm2_seal_trusted(chip, payload, options);
 		else
 			ret = key_seal(payload, options);
 		if (ret < 0)
diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c
new file mode 100644
index 000000000000..a9810ac2776f
--- /dev/null
+++ b/security/keys/trusted-keys/trusted_tpm2.c
@@ -0,0 +1,314 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004 IBM Corporation
+ * Copyright (C) 2014 Intel Corporation
+ */
+
+#include <linux/string.h>
+#include <linux/err.h>
+#include <linux/tpm.h>
+#include <linux/tpm_command.h>
+
+#include <keys/trusted-type.h>
+#include <keys/trusted_tpm.h>
+
+static struct tpm2_hash tpm2_hash_map[] = {
+	{HASH_ALGO_SHA1, TPM_ALG_SHA1},
+	{HASH_ALGO_SHA256, TPM_ALG_SHA256},
+	{HASH_ALGO_SHA384, TPM_ALG_SHA384},
+	{HASH_ALGO_SHA512, TPM_ALG_SHA512},
+	{HASH_ALGO_SM3_256, TPM_ALG_SM3_256},
+};
+
+/**
+ * tpm_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer.
+ *
+ * @buf: an allocated tpm_buf instance
+ * @session_handle: session handle
+ * @nonce: the session nonce, may be NULL if not used
+ * @nonce_len: the session nonce length, may be 0 if not used
+ * @attributes: the session attributes
+ * @hmac: the session HMAC or password, may be NULL if not used
+ * @hmac_len: the session HMAC or password length, maybe 0 if not used
+ */
+static void tpm2_buf_append_auth(struct tpm_buf *buf, u32 session_handle,
+				 const u8 *nonce, u16 nonce_len,
+				 u8 attributes,
+				 const u8 *hmac, u16 hmac_len)
+{
+	tpm_buf_append_u32(buf, 9 + nonce_len + hmac_len);
+	tpm_buf_append_u32(buf, session_handle);
+	tpm_buf_append_u16(buf, nonce_len);
+
+	if (nonce && nonce_len)
+		tpm_buf_append(buf, nonce, nonce_len);
+
+	tpm_buf_append_u8(buf, attributes);
+	tpm_buf_append_u16(buf, hmac_len);
+
+	if (hmac && hmac_len)
+		tpm_buf_append(buf, hmac, hmac_len);
+}
+
+/**
+ * tpm2_seal_trusted() - seal the payload of a trusted key
+ *
+ * @chip: TPM chip to use
+ * @payload: the key data in clear and encrypted form
+ * @options: authentication values and other options
+ *
+ * Return: < 0 on error and 0 on success.
+ */
+int tpm2_seal_trusted(struct tpm_chip *chip,
+		      struct trusted_key_payload *payload,
+		      struct trusted_key_options *options)
+{
+	unsigned int blob_len;
+	struct tpm_buf buf;
+	u32 hash;
+	int i;
+	int rc;
+
+	for (i = 0; i < ARRAY_SIZE(tpm2_hash_map); i++) {
+		if (options->hash == tpm2_hash_map[i].crypto_id) {
+			hash = tpm2_hash_map[i].tpm_id;
+			break;
+		}
+	}
+
+	if (i == ARRAY_SIZE(tpm2_hash_map))
+		return -EINVAL;
+
+	rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE);
+	if (rc)
+		return rc;
+
+	tpm_buf_append_u32(&buf, options->keyhandle);
+	tpm2_buf_append_auth(&buf, TPM2_RS_PW,
+			     NULL /* nonce */, 0,
+			     0 /* session_attributes */,
+			     options->keyauth /* hmac */,
+			     TPM_DIGEST_SIZE);
+
+	/* sensitive */
+	tpm_buf_append_u16(&buf, 4 + TPM_DIGEST_SIZE + payload->key_len + 1);
+
+	tpm_buf_append_u16(&buf, TPM_DIGEST_SIZE);
+	tpm_buf_append(&buf, options->blobauth, TPM_DIGEST_SIZE);
+	tpm_buf_append_u16(&buf, payload->key_len + 1);
+	tpm_buf_append(&buf, payload->key, payload->key_len);
+	tpm_buf_append_u8(&buf, payload->migratable);
+
+	/* public */
+	tpm_buf_append_u16(&buf, 14 + options->policydigest_len);
+	tpm_buf_append_u16(&buf, TPM_ALG_KEYEDHASH);
+	tpm_buf_append_u16(&buf, hash);
+
+	/* policy */
+	if (options->policydigest_len) {
+		tpm_buf_append_u32(&buf, 0);
+		tpm_buf_append_u16(&buf, options->policydigest_len);
+		tpm_buf_append(&buf, options->policydigest,
+			       options->policydigest_len);
+	} else {
+		tpm_buf_append_u32(&buf, TPM2_OA_USER_WITH_AUTH);
+		tpm_buf_append_u16(&buf, 0);
+	}
+
+	/* public parameters */
+	tpm_buf_append_u16(&buf, TPM_ALG_NULL);
+	tpm_buf_append_u16(&buf, 0);
+
+	/* outside info */
+	tpm_buf_append_u16(&buf, 0);
+
+	/* creation PCR */
+	tpm_buf_append_u32(&buf, 0);
+
+	if (buf.flags & TPM_BUF_OVERFLOW) {
+		rc = -E2BIG;
+		goto out;
+	}
+
+	rc = tpm_send(chip, buf.data, tpm_buf_length(&buf));
+	if (rc)
+		goto out;
+
+	blob_len = be32_to_cpup((__be32 *) &buf.data[TPM_HEADER_SIZE]);
+	if (blob_len > MAX_BLOB_SIZE) {
+		rc = -E2BIG;
+		goto out;
+	}
+	if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 4 + blob_len) {
+		rc = -EFAULT;
+		goto out;
+	}
+
+	memcpy(payload->blob, &buf.data[TPM_HEADER_SIZE + 4], blob_len);
+	payload->blob_len = blob_len;
+
+out:
+	tpm_buf_destroy(&buf);
+
+	if (rc > 0) {
+		if (tpm2_rc_value(rc) == TPM2_RC_HASH)
+			rc = -EINVAL;
+		else
+			rc = -EPERM;
+	}
+
+	return rc;
+}
+
+/**
+ * tpm2_load_cmd() - execute a TPM2_Load command
+ *
+ * @chip: TPM chip to use
+ * @payload: the key data in clear and encrypted form
+ * @options: authentication values and other options
+ * @blob_handle: returned blob handle
+ *
+ * Return: 0 on success.
+ *        -E2BIG on wrong payload size.
+ *        -EPERM on tpm error status.
+ *        < 0 error from tpm_send.
+ */
+static int tpm2_load_cmd(struct tpm_chip *chip,
+			 struct trusted_key_payload *payload,
+			 struct trusted_key_options *options,
+			 u32 *blob_handle)
+{
+	struct tpm_buf buf;
+	unsigned int private_len;
+	unsigned int public_len;
+	unsigned int blob_len;
+	int rc;
+
+	private_len = be16_to_cpup((__be16 *) &payload->blob[0]);
+	if (private_len > (payload->blob_len - 2))
+		return -E2BIG;
+
+	public_len = be16_to_cpup((__be16 *) &payload->blob[2 + private_len]);
+	blob_len = private_len + public_len + 4;
+	if (blob_len > payload->blob_len)
+		return -E2BIG;
+
+	rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_LOAD);
+	if (rc)
+		return rc;
+
+	tpm_buf_append_u32(&buf, options->keyhandle);
+	tpm2_buf_append_auth(&buf, TPM2_RS_PW,
+			     NULL /* nonce */, 0,
+			     0 /* session_attributes */,
+			     options->keyauth /* hmac */,
+			     TPM_DIGEST_SIZE);
+
+	tpm_buf_append(&buf, payload->blob, blob_len);
+
+	if (buf.flags & TPM_BUF_OVERFLOW) {
+		rc = -E2BIG;
+		goto out;
+	}
+
+	rc = tpm_send(chip, buf.data, tpm_buf_length(&buf));
+	if (!rc)
+		*blob_handle = be32_to_cpup(
+			(__be32 *) &buf.data[TPM_HEADER_SIZE]);
+
+out:
+	tpm_buf_destroy(&buf);
+
+	if (rc > 0)
+		rc = -EPERM;
+
+	return rc;
+}
+
+/**
+ * tpm2_unseal_cmd() - execute a TPM2_Unload command
+ *
+ * @chip: TPM chip to use
+ * @payload: the key data in clear and encrypted form
+ * @options: authentication values and other options
+ * @blob_handle: blob handle
+ *
+ * Return: 0 on success
+ *         -EPERM on tpm error status
+ *         < 0 error from tpm_send
+ */
+static int tpm2_unseal_cmd(struct tpm_chip *chip,
+			   struct trusted_key_payload *payload,
+			   struct trusted_key_options *options,
+			   u32 blob_handle)
+{
+	struct tpm_buf buf;
+	u16 data_len;
+	u8 *data;
+	int rc;
+
+	rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_UNSEAL);
+	if (rc)
+		return rc;
+
+	tpm_buf_append_u32(&buf, blob_handle);
+	tpm2_buf_append_auth(&buf,
+			     options->policyhandle ?
+			     options->policyhandle : TPM2_RS_PW,
+			     NULL /* nonce */, 0,
+			     TPM2_SA_CONTINUE_SESSION,
+			     options->blobauth /* hmac */,
+			     TPM_DIGEST_SIZE);
+
+	rc = tpm_send(chip, buf.data, tpm_buf_length(&buf));
+	if (rc > 0)
+		rc = -EPERM;
+
+	if (!rc) {
+		data_len = be16_to_cpup(
+			(__be16 *) &buf.data[TPM_HEADER_SIZE + 4]);
+		if (data_len < MIN_KEY_SIZE ||  data_len > MAX_KEY_SIZE + 1) {
+			rc = -EFAULT;
+			goto out;
+		}
+
+		if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 6 + data_len) {
+			rc = -EFAULT;
+			goto out;
+		}
+		data = &buf.data[TPM_HEADER_SIZE + 6];
+
+		memcpy(payload->key, data, data_len - 1);
+		payload->key_len = data_len - 1;
+		payload->migratable = data[data_len - 1];
+	}
+
+out:
+	tpm_buf_destroy(&buf);
+	return rc;
+}
+
+/**
+ * tpm2_unseal_trusted() - unseal the payload of a trusted key
+ *
+ * @chip: TPM chip to use
+ * @payload: the key data in clear and encrypted form
+ * @options: authentication values and other options
+ *
+ * Return: Same as with tpm_send.
+ */
+int tpm2_unseal_trusted(struct tpm_chip *chip,
+			struct trusted_key_payload *payload,
+			struct trusted_key_options *options)
+{
+	u32 blob_handle;
+	int rc;
+
+	rc = tpm2_load_cmd(chip, payload, options, &blob_handle);
+	if (rc)
+		return rc;
+
+	rc = tpm2_unseal_cmd(chip, payload, options, blob_handle);
+
+	return rc;
+}
diff --git a/sound/soc/samsung/s3c-i2s-v2.c b/sound/soc/samsung/s3c-i2s-v2.c
index 7e196b599be1..593be1b668d6 100644
--- a/sound/soc/samsung/s3c-i2s-v2.c
+++ b/sound/soc/samsung/s3c-i2s-v2.c
@@ -672,13 +672,13 @@ static int s3c2412_i2s_suspend(struct snd_soc_dai *dai)
 		iismod = readl(i2s->regs + S3C2412_IISMOD);
 
 		if (iismod & S3C2412_IISCON_RXDMA_ACTIVE)
-			pr_warning("%s: RXDMA active?\n", __func__);
+			pr_warn("%s: RXDMA active?\n", __func__);
 
 		if (iismod & S3C2412_IISCON_TXDMA_ACTIVE)
-			pr_warning("%s: TXDMA active?\n", __func__);
+			pr_warn("%s: TXDMA active?\n", __func__);
 
 		if (iismod & S3C2412_IISCON_IIS_ACTIVE)
-			pr_warning("%s: IIS active\n", __func__);
+			pr_warn("%s: IIS active\n", __func__);
 	}
 
 	return 0;
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 1d338357df8a..1f97b33c840e 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -58,7 +58,7 @@
  * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
  * used to clear any hints previously set.
  */
-#define RWF_WRITE_LIFE_NOT_SET	0
+#define RWH_WRITE_LIFE_NOT_SET	0
 #define RWH_WRITE_LIFE_NONE	1
 #define RWH_WRITE_LIFE_SHORT	2
 #define RWH_WRITE_LIFE_MEDIUM	3
@@ -66,6 +66,13 @@
 #define RWH_WRITE_LIFE_EXTREME	5
 
 /*
+ * The originally introduced spelling is remained from the first
+ * versions of the patch set that introduced the feature, see commit
+ * v4.13-rc1~212^2~51.
+ */
+#define RWF_WRITE_LIFE_NOT_SET	RWH_WRITE_LIFE_NOT_SET
+
+/*
  * Types of directory notifications that may be requested.
  */
 #define DN_ACCESS	0x00000001	/* File accessed */
diff --git a/tools/lib/api/debug-internal.h b/tools/lib/api/debug-internal.h
index 80c783497d25..5a5820c11db8 100644
--- a/tools/lib/api/debug-internal.h
+++ b/tools/lib/api/debug-internal.h
@@ -10,11 +10,11 @@ do {				\
 		(func)("libapi: " fmt, ##__VA_ARGS__); \
 } while (0)
 
-extern libapi_print_fn_t __pr_warning;
+extern libapi_print_fn_t __pr_warn;
 extern libapi_print_fn_t __pr_info;
 extern libapi_print_fn_t __pr_debug;
 
-#define pr_warning(fmt, ...)	__pr(__pr_warning, fmt, ##__VA_ARGS__)
+#define pr_warn(fmt, ...)	__pr(__pr_warn, fmt, ##__VA_ARGS__)
 #define pr_info(fmt, ...)	__pr(__pr_info, fmt, ##__VA_ARGS__)
 #define pr_debug(fmt, ...)	__pr(__pr_debug, fmt, ##__VA_ARGS__)
 
diff --git a/tools/lib/api/debug.c b/tools/lib/api/debug.c
index 69b1ba3d1ee3..7708f0558e8c 100644
--- a/tools/lib/api/debug.c
+++ b/tools/lib/api/debug.c
@@ -15,7 +15,7 @@ static int __base_pr(const char *format, ...)
 	return err;
 }
 
-libapi_print_fn_t __pr_warning = __base_pr;
+libapi_print_fn_t __pr_warn    = __base_pr;
 libapi_print_fn_t __pr_info    = __base_pr;
 libapi_print_fn_t __pr_debug;
 
@@ -23,7 +23,7 @@ void libapi_set_print(libapi_print_fn_t warn,
 		      libapi_print_fn_t info,
 		      libapi_print_fn_t debug)
 {
-	__pr_warning = warn;
+	__pr_warn    = warn;
 	__pr_info    = info;
 	__pr_debug   = debug;
 }
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 7aba8243a0e7..11b3885e833e 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -381,8 +381,8 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep)
 		n = read(fd, bf + size, alloc_size - size);
 		if (n < 0) {
 			if (size) {
-				pr_warning("read failed %d: %s\n", errno,
-					 strerror_r(errno, sbuf, sizeof(sbuf)));
+				pr_warn("read failed %d: %s\n", errno,
+					strerror_r(errno, sbuf, sizeof(sbuf)));
 				err = 0;
 			} else
 				err = -errno;
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 044c9a3cb247..543c068096b1 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -144,6 +144,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
 		"usercopy_abort",
 		"machine_real_restart",
 		"rewind_stack_do_exit",
+		"kunit_try_catch_throw",
 	};
 
 	if (!func)
diff --git a/tools/testing/kunit/.gitignore b/tools/testing/kunit/.gitignore
new file mode 100644
index 000000000000..c791ff59a37a
--- /dev/null
+++ b/tools/testing/kunit/.gitignore
@@ -0,0 +1,3 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
\ No newline at end of file
diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config
new file mode 100644
index 000000000000..9235b7d42d38
--- /dev/null
+++ b/tools/testing/kunit/configs/all_tests.config
@@ -0,0 +1,3 @@
+CONFIG_KUNIT=y
+CONFIG_KUNIT_TEST=y
+CONFIG_KUNIT_EXAMPLE_TEST=y
diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py
new file mode 100755
index 000000000000..efe06d621983
--- /dev/null
+++ b/tools/testing/kunit/kunit.py
@@ -0,0 +1,138 @@
+#!/usr/bin/python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# A thin wrapper on top of the KUnit Kernel
+#
+# Copyright (C) 2019, Google LLC.
+# Author: Felix Guo <felixguoxiuping@gmail.com>
+# Author: Brendan Higgins <brendanhiggins@google.com>
+
+import argparse
+import sys
+import os
+import time
+import shutil
+
+from collections import namedtuple
+from enum import Enum, auto
+
+import kunit_config
+import kunit_kernel
+import kunit_parser
+
+KunitResult = namedtuple('KunitResult', ['status','result'])
+
+KunitRequest = namedtuple('KunitRequest', ['raw_output','timeout', 'jobs', 'build_dir', 'defconfig'])
+
+class KunitStatus(Enum):
+	SUCCESS = auto()
+	CONFIG_FAILURE = auto()
+	BUILD_FAILURE = auto()
+	TEST_FAILURE = auto()
+
+def create_default_kunitconfig():
+	if not os.path.exists(kunit_kernel.KUNITCONFIG_PATH):
+		shutil.copyfile('arch/um/configs/kunit_defconfig',
+				kunit_kernel.KUNITCONFIG_PATH)
+
+def run_tests(linux: kunit_kernel.LinuxSourceTree,
+	      request: KunitRequest) -> KunitResult:
+	if request.defconfig:
+		create_default_kunitconfig()
+
+	config_start = time.time()
+	success = linux.build_reconfig(request.build_dir)
+	config_end = time.time()
+	if not success:
+		return KunitResult(KunitStatus.CONFIG_FAILURE, 'could not configure kernel')
+
+	kunit_parser.print_with_timestamp('Building KUnit Kernel ...')
+
+	build_start = time.time()
+	success = linux.build_um_kernel(request.jobs, request.build_dir)
+	build_end = time.time()
+	if not success:
+		return KunitResult(KunitStatus.BUILD_FAILURE, 'could not build kernel')
+
+	kunit_parser.print_with_timestamp('Starting KUnit Kernel ...')
+	test_start = time.time()
+
+	test_result = kunit_parser.TestResult(kunit_parser.TestStatus.SUCCESS,
+					      [],
+					      'Tests not Parsed.')
+	if request.raw_output:
+		kunit_parser.raw_output(
+			linux.run_kernel(timeout=request.timeout,
+					 build_dir=request.build_dir))
+	else:
+		kunit_output = linux.run_kernel(timeout=request.timeout,
+						build_dir=request.build_dir)
+		test_result = kunit_parser.parse_run_tests(kunit_output)
+	test_end = time.time()
+
+	kunit_parser.print_with_timestamp((
+		'Elapsed time: %.3fs total, %.3fs configuring, %.3fs ' +
+		'building, %.3fs running\n') % (
+				test_end - config_start,
+				config_end - config_start,
+				build_end - build_start,
+				test_end - test_start))
+
+	if test_result.status != kunit_parser.TestStatus.SUCCESS:
+		return KunitResult(KunitStatus.TEST_FAILURE, test_result)
+	else:
+		return KunitResult(KunitStatus.SUCCESS, test_result)
+
+def main(argv, linux=None):
+	parser = argparse.ArgumentParser(
+			description='Helps writing and running KUnit tests.')
+	subparser = parser.add_subparsers(dest='subcommand')
+
+	run_parser = subparser.add_parser('run', help='Runs KUnit tests.')
+	run_parser.add_argument('--raw_output', help='don\'t format output from kernel',
+				action='store_true')
+
+	run_parser.add_argument('--timeout',
+				help='maximum number of seconds to allow for all tests '
+				'to run. This does not include time taken to build the '
+				'tests.',
+				type=int,
+				default=300,
+				metavar='timeout')
+
+	run_parser.add_argument('--jobs',
+				help='As in the make command, "Specifies  the number of '
+				'jobs (commands) to run simultaneously."',
+				type=int, default=8, metavar='jobs')
+
+	run_parser.add_argument('--build_dir',
+				help='As in the make command, it specifies the build '
+				'directory.',
+				type=str, default=None, metavar='build_dir')
+
+	run_parser.add_argument('--defconfig',
+				help='Uses a default kunitconfig.',
+				action='store_true')
+
+	cli_args = parser.parse_args(argv)
+
+	if cli_args.subcommand == 'run':
+		if cli_args.defconfig:
+			create_default_kunitconfig()
+
+		if not linux:
+			linux = kunit_kernel.LinuxSourceTree()
+
+		request = KunitRequest(cli_args.raw_output,
+				       cli_args.timeout,
+				       cli_args.jobs,
+				       cli_args.build_dir,
+				       cli_args.defconfig)
+		result = run_tests(linux, request)
+		if result.status != KunitStatus.SUCCESS:
+			sys.exit(1)
+	else:
+		parser.print_help()
+
+if __name__ == '__main__':
+	main(sys.argv[1:])
diff --git a/tools/testing/kunit/kunit_config.py b/tools/testing/kunit/kunit_config.py
new file mode 100644
index 000000000000..ebf3942b23f5
--- /dev/null
+++ b/tools/testing/kunit/kunit_config.py
@@ -0,0 +1,66 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Builds a .config from a kunitconfig.
+#
+# Copyright (C) 2019, Google LLC.
+# Author: Felix Guo <felixguoxiuping@gmail.com>
+# Author: Brendan Higgins <brendanhiggins@google.com>
+
+import collections
+import re
+
+CONFIG_IS_NOT_SET_PATTERN = r'^# CONFIG_\w+ is not set$'
+CONFIG_PATTERN = r'^CONFIG_\w+=\S+$'
+
+KconfigEntryBase = collections.namedtuple('KconfigEntry', ['raw_entry'])
+
+
+class KconfigEntry(KconfigEntryBase):
+
+	def __str__(self) -> str:
+		return self.raw_entry
+
+
+class KconfigParseError(Exception):
+	"""Error parsing Kconfig defconfig or .config."""
+
+
+class Kconfig(object):
+	"""Represents defconfig or .config specified using the Kconfig language."""
+
+	def __init__(self):
+		self._entries = []
+
+	def entries(self):
+		return set(self._entries)
+
+	def add_entry(self, entry: KconfigEntry) -> None:
+		self._entries.append(entry)
+
+	def is_subset_of(self, other: 'Kconfig') -> bool:
+		return self.entries().issubset(other.entries())
+
+	def write_to_file(self, path: str) -> None:
+		with open(path, 'w') as f:
+			for entry in self.entries():
+				f.write(str(entry) + '\n')
+
+	def parse_from_string(self, blob: str) -> None:
+		"""Parses a string containing KconfigEntrys and populates this Kconfig."""
+		self._entries = []
+		is_not_set_matcher = re.compile(CONFIG_IS_NOT_SET_PATTERN)
+		config_matcher = re.compile(CONFIG_PATTERN)
+		for line in blob.split('\n'):
+			line = line.strip()
+			if not line:
+				continue
+			elif config_matcher.match(line) or is_not_set_matcher.match(line):
+				self._entries.append(KconfigEntry(line))
+			elif line[0] == '#':
+				continue
+			else:
+				raise KconfigParseError('Failed to parse: ' + line)
+
+	def read_from_file(self, path: str) -> None:
+		with open(path, 'r') as f:
+			self.parse_from_string(f.read())
diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py
new file mode 100644
index 000000000000..bf3876835331
--- /dev/null
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -0,0 +1,149 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Runs UML kernel, collects output, and handles errors.
+#
+# Copyright (C) 2019, Google LLC.
+# Author: Felix Guo <felixguoxiuping@gmail.com>
+# Author: Brendan Higgins <brendanhiggins@google.com>
+
+
+import logging
+import subprocess
+import os
+
+import kunit_config
+
+KCONFIG_PATH = '.config'
+KUNITCONFIG_PATH = 'kunitconfig'
+
+class ConfigError(Exception):
+	"""Represents an error trying to configure the Linux kernel."""
+
+
+class BuildError(Exception):
+	"""Represents an error trying to build the Linux kernel."""
+
+
+class LinuxSourceTreeOperations(object):
+	"""An abstraction over command line operations performed on a source tree."""
+
+	def make_mrproper(self):
+		try:
+			subprocess.check_output(['make', 'mrproper'])
+		except OSError as e:
+			raise ConfigError('Could not call make command: ' + e)
+		except subprocess.CalledProcessError as e:
+			raise ConfigError(e.output)
+
+	def make_olddefconfig(self, build_dir):
+		command = ['make', 'ARCH=um', 'olddefconfig']
+		if build_dir:
+			command += ['O=' + build_dir]
+		try:
+			subprocess.check_output(command)
+		except OSError as e:
+			raise ConfigError('Could not call make command: ' + e)
+		except subprocess.CalledProcessError as e:
+			raise ConfigError(e.output)
+
+	def make(self, jobs, build_dir):
+		command = ['make', 'ARCH=um', '--jobs=' + str(jobs)]
+		if build_dir:
+			command += ['O=' + build_dir]
+		try:
+			subprocess.check_output(command)
+		except OSError as e:
+			raise BuildError('Could not call execute make: ' + e)
+		except subprocess.CalledProcessError as e:
+			raise BuildError(e.output)
+
+	def linux_bin(self, params, timeout, build_dir):
+		"""Runs the Linux UML binary. Must be named 'linux'."""
+		linux_bin = './linux'
+		if build_dir:
+			linux_bin = os.path.join(build_dir, 'linux')
+		process = subprocess.Popen(
+			[linux_bin] + params,
+			stdin=subprocess.PIPE,
+			stdout=subprocess.PIPE,
+			stderr=subprocess.PIPE)
+		process.wait(timeout=timeout)
+		return process
+
+
+def get_kconfig_path(build_dir):
+	kconfig_path = KCONFIG_PATH
+	if build_dir:
+		kconfig_path = os.path.join(build_dir, KCONFIG_PATH)
+	return kconfig_path
+
+class LinuxSourceTree(object):
+	"""Represents a Linux kernel source tree with KUnit tests."""
+
+	def __init__(self):
+		self._kconfig = kunit_config.Kconfig()
+		self._kconfig.read_from_file(KUNITCONFIG_PATH)
+		self._ops = LinuxSourceTreeOperations()
+
+	def clean(self):
+		try:
+			self._ops.make_mrproper()
+		except ConfigError as e:
+			logging.error(e)
+			return False
+		return True
+
+	def build_config(self, build_dir):
+		kconfig_path = get_kconfig_path(build_dir)
+		if build_dir and not os.path.exists(build_dir):
+			os.mkdir(build_dir)
+		self._kconfig.write_to_file(kconfig_path)
+		try:
+			self._ops.make_olddefconfig(build_dir)
+		except ConfigError as e:
+			logging.error(e)
+			return False
+		validated_kconfig = kunit_config.Kconfig()
+		validated_kconfig.read_from_file(kconfig_path)
+		if not self._kconfig.is_subset_of(validated_kconfig):
+			logging.error('Provided Kconfig is not contained in validated .config!')
+			return False
+		return True
+
+	def build_reconfig(self, build_dir):
+		"""Creates a new .config if it is not a subset of the kunitconfig."""
+		kconfig_path = get_kconfig_path(build_dir)
+		if os.path.exists(kconfig_path):
+			existing_kconfig = kunit_config.Kconfig()
+			existing_kconfig.read_from_file(kconfig_path)
+			if not self._kconfig.is_subset_of(existing_kconfig):
+				print('Regenerating .config ...')
+				os.remove(kconfig_path)
+				return self.build_config(build_dir)
+			else:
+				return True
+		else:
+			print('Generating .config ...')
+			return self.build_config(build_dir)
+
+	def build_um_kernel(self, jobs, build_dir):
+		try:
+			self._ops.make_olddefconfig(build_dir)
+			self._ops.make(jobs, build_dir)
+		except (ConfigError, BuildError) as e:
+			logging.error(e)
+			return False
+		used_kconfig = kunit_config.Kconfig()
+		used_kconfig.read_from_file(get_kconfig_path(build_dir))
+		if not self._kconfig.is_subset_of(used_kconfig):
+			logging.error('Provided Kconfig is not contained in final config!')
+			return False
+		return True
+
+	def run_kernel(self, args=[], timeout=None, build_dir=None):
+		args.extend(['mem=256M'])
+		process = self._ops.linux_bin(args, timeout, build_dir)
+		with open('test.log', 'w') as f:
+			for line in process.stdout:
+				f.write(line.rstrip().decode('ascii') + '\n')
+				yield line.rstrip().decode('ascii')
diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py
new file mode 100644
index 000000000000..4ffbae0f6732
--- /dev/null
+++ b/tools/testing/kunit/kunit_parser.py
@@ -0,0 +1,310 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Parses test results from a kernel dmesg log.
+#
+# Copyright (C) 2019, Google LLC.
+# Author: Felix Guo <felixguoxiuping@gmail.com>
+# Author: Brendan Higgins <brendanhiggins@google.com>
+
+import re
+
+from collections import namedtuple
+from datetime import datetime
+from enum import Enum, auto
+from functools import reduce
+from typing import List
+
+TestResult = namedtuple('TestResult', ['status','suites','log'])
+
+class TestSuite(object):
+	def __init__(self):
+		self.status = None
+		self.name = None
+		self.cases = []
+
+	def __str__(self):
+		return 'TestSuite(' + self.status + ',' + self.name + ',' + str(self.cases) + ')'
+
+	def __repr__(self):
+		return str(self)
+
+class TestCase(object):
+	def __init__(self):
+		self.status = None
+		self.name = ''
+		self.log = []
+
+	def __str__(self):
+		return 'TestCase(' + self.status + ',' + self.name + ',' + str(self.log) + ')'
+
+	def __repr__(self):
+		return str(self)
+
+class TestStatus(Enum):
+	SUCCESS = auto()
+	FAILURE = auto()
+	TEST_CRASHED = auto()
+	NO_TESTS = auto()
+
+kunit_start_re = re.compile(r'^TAP version [0-9]+$')
+kunit_end_re = re.compile('List of all partitions:')
+
+def isolate_kunit_output(kernel_output):
+	started = False
+	for line in kernel_output:
+		if kunit_start_re.match(line):
+			started = True
+			yield line
+		elif kunit_end_re.match(line):
+			break
+		elif started:
+			yield line
+
+def raw_output(kernel_output):
+	for line in kernel_output:
+		print(line)
+
+DIVIDER = '=' * 60
+
+RESET = '\033[0;0m'
+
+def red(text):
+	return '\033[1;31m' + text + RESET
+
+def yellow(text):
+	return '\033[1;33m' + text + RESET
+
+def green(text):
+	return '\033[1;32m' + text + RESET
+
+def print_with_timestamp(message):
+	print('[%s] %s' % (datetime.now().strftime('%H:%M:%S'), message))
+
+def format_suite_divider(message):
+	return '======== ' + message + ' ========'
+
+def print_suite_divider(message):
+	print_with_timestamp(DIVIDER)
+	print_with_timestamp(format_suite_divider(message))
+
+def print_log(log):
+	for m in log:
+		print_with_timestamp(m)
+
+TAP_ENTRIES = re.compile(r'^(TAP|\t?ok|\t?not ok|\t?[0-9]+\.\.[0-9]+|\t?#).*$')
+
+def consume_non_diagnositic(lines: List[str]) -> None:
+	while lines and not TAP_ENTRIES.match(lines[0]):
+		lines.pop(0)
+
+def save_non_diagnositic(lines: List[str], test_case: TestCase) -> None:
+	while lines and not TAP_ENTRIES.match(lines[0]):
+		test_case.log.append(lines[0])
+		lines.pop(0)
+
+OkNotOkResult = namedtuple('OkNotOkResult', ['is_ok','description', 'text'])
+
+OK_NOT_OK_SUBTEST = re.compile(r'^\t(ok|not ok) [0-9]+ - (.*)$')
+
+OK_NOT_OK_MODULE = re.compile(r'^(ok|not ok) [0-9]+ - (.*)$')
+
+def parse_ok_not_ok_test_case(lines: List[str],
+			      test_case: TestCase,
+			      expecting_test_case: bool) -> bool:
+	save_non_diagnositic(lines, test_case)
+	if not lines:
+		if expecting_test_case:
+			test_case.status = TestStatus.TEST_CRASHED
+			return True
+		else:
+			return False
+	line = lines[0]
+	match = OK_NOT_OK_SUBTEST.match(line)
+	if match:
+		test_case.log.append(lines.pop(0))
+		test_case.name = match.group(2)
+		if test_case.status == TestStatus.TEST_CRASHED:
+			return True
+		if match.group(1) == 'ok':
+			test_case.status = TestStatus.SUCCESS
+		else:
+			test_case.status = TestStatus.FAILURE
+		return True
+	else:
+		return False
+
+SUBTEST_DIAGNOSTIC = re.compile(r'^\t# .*?: (.*)$')
+DIAGNOSTIC_CRASH_MESSAGE = 'kunit test case crashed!'
+
+def parse_diagnostic(lines: List[str], test_case: TestCase) -> bool:
+	save_non_diagnositic(lines, test_case)
+	if not lines:
+		return False
+	line = lines[0]
+	match = SUBTEST_DIAGNOSTIC.match(line)
+	if match:
+		test_case.log.append(lines.pop(0))
+		if match.group(1) == DIAGNOSTIC_CRASH_MESSAGE:
+			test_case.status = TestStatus.TEST_CRASHED
+		return True
+	else:
+		return False
+
+def parse_test_case(lines: List[str], expecting_test_case: bool) -> TestCase:
+	test_case = TestCase()
+	save_non_diagnositic(lines, test_case)
+	while parse_diagnostic(lines, test_case):
+		pass
+	if parse_ok_not_ok_test_case(lines, test_case, expecting_test_case):
+		return test_case
+	else:
+		return None
+
+SUBTEST_HEADER = re.compile(r'^\t# Subtest: (.*)$')
+
+def parse_subtest_header(lines: List[str]) -> str:
+	consume_non_diagnositic(lines)
+	if not lines:
+		return None
+	match = SUBTEST_HEADER.match(lines[0])
+	if match:
+		lines.pop(0)
+		return match.group(1)
+	else:
+		return None
+
+SUBTEST_PLAN = re.compile(r'\t[0-9]+\.\.([0-9]+)')
+
+def parse_subtest_plan(lines: List[str]) -> int:
+	consume_non_diagnositic(lines)
+	match = SUBTEST_PLAN.match(lines[0])
+	if match:
+		lines.pop(0)
+		return int(match.group(1))
+	else:
+		return None
+
+def max_status(left: TestStatus, right: TestStatus) -> TestStatus:
+	if left == TestStatus.TEST_CRASHED or right == TestStatus.TEST_CRASHED:
+		return TestStatus.TEST_CRASHED
+	elif left == TestStatus.FAILURE or right == TestStatus.FAILURE:
+		return TestStatus.FAILURE
+	elif left != TestStatus.SUCCESS:
+		return left
+	elif right != TestStatus.SUCCESS:
+		return right
+	else:
+		return TestStatus.SUCCESS
+
+def parse_ok_not_ok_test_suite(lines: List[str], test_suite: TestSuite) -> bool:
+	consume_non_diagnositic(lines)
+	if not lines:
+		test_suite.status = TestStatus.TEST_CRASHED
+		return False
+	line = lines[0]
+	match = OK_NOT_OK_MODULE.match(line)
+	if match:
+		lines.pop(0)
+		if match.group(1) == 'ok':
+			test_suite.status = TestStatus.SUCCESS
+		else:
+			test_suite.status = TestStatus.FAILURE
+		return True
+	else:
+		return False
+
+def bubble_up_errors(to_status, status_container_list) -> TestStatus:
+	status_list = map(to_status, status_container_list)
+	return reduce(max_status, status_list, TestStatus.SUCCESS)
+
+def bubble_up_test_case_errors(test_suite: TestSuite) -> TestStatus:
+	max_test_case_status = bubble_up_errors(lambda x: x.status, test_suite.cases)
+	return max_status(max_test_case_status, test_suite.status)
+
+def parse_test_suite(lines: List[str]) -> TestSuite:
+	if not lines:
+		return None
+	consume_non_diagnositic(lines)
+	test_suite = TestSuite()
+	test_suite.status = TestStatus.SUCCESS
+	name = parse_subtest_header(lines)
+	if not name:
+		return None
+	test_suite.name = name
+	expected_test_case_num = parse_subtest_plan(lines)
+	if not expected_test_case_num:
+		return None
+	test_case = parse_test_case(lines, expected_test_case_num > 0)
+	expected_test_case_num -= 1
+	while test_case:
+		test_suite.cases.append(test_case)
+		test_case = parse_test_case(lines, expected_test_case_num > 0)
+		expected_test_case_num -= 1
+	if parse_ok_not_ok_test_suite(lines, test_suite):
+		test_suite.status = bubble_up_test_case_errors(test_suite)
+		return test_suite
+	elif not lines:
+		print_with_timestamp(red('[ERROR] ') + 'ran out of lines before end token')
+		return test_suite
+	else:
+		print('failed to parse end of suite' + lines[0])
+		return None
+
+TAP_HEADER = re.compile(r'^TAP version 14$')
+
+def parse_tap_header(lines: List[str]) -> bool:
+	consume_non_diagnositic(lines)
+	if TAP_HEADER.match(lines[0]):
+		lines.pop(0)
+		return True
+	else:
+		return False
+
+def bubble_up_suite_errors(test_suite_list: List[TestSuite]) -> TestStatus:
+	return bubble_up_errors(lambda x: x.status, test_suite_list)
+
+def parse_test_result(lines: List[str]) -> TestResult:
+	if not lines:
+		return TestResult(TestStatus.NO_TESTS, [], lines)
+	consume_non_diagnositic(lines)
+	if not parse_tap_header(lines):
+		return None
+	test_suites = []
+	test_suite = parse_test_suite(lines)
+	while test_suite:
+		test_suites.append(test_suite)
+		test_suite = parse_test_suite(lines)
+	return TestResult(bubble_up_suite_errors(test_suites), test_suites, lines)
+
+def parse_run_tests(kernel_output) -> TestResult:
+	total_tests = 0
+	failed_tests = 0
+	crashed_tests = 0
+	test_result = parse_test_result(list(isolate_kunit_output(kernel_output)))
+	for test_suite in test_result.suites:
+		if test_suite.status == TestStatus.SUCCESS:
+			print_suite_divider(green('[PASSED] ') + test_suite.name)
+		elif test_suite.status == TestStatus.TEST_CRASHED:
+			print_suite_divider(red('[CRASHED] ' + test_suite.name))
+		else:
+			print_suite_divider(red('[FAILED] ') + test_suite.name)
+		for test_case in test_suite.cases:
+			total_tests += 1
+			if test_case.status == TestStatus.SUCCESS:
+				print_with_timestamp(green('[PASSED] ') + test_case.name)
+			elif test_case.status == TestStatus.TEST_CRASHED:
+				crashed_tests += 1
+				print_with_timestamp(red('[CRASHED] ' + test_case.name))
+				print_log(map(yellow, test_case.log))
+				print_with_timestamp('')
+			else:
+				failed_tests += 1
+				print_with_timestamp(red('[FAILED] ') + test_case.name)
+				print_log(map(yellow, test_case.log))
+				print_with_timestamp('')
+	print_with_timestamp(DIVIDER)
+	fmt = green if test_result.status == TestStatus.SUCCESS else red
+	print_with_timestamp(
+		fmt('Testing complete. %d tests run. %d failed. %d crashed.' %
+		    (total_tests, failed_tests, crashed_tests)))
+	return test_result
diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py
new file mode 100755
index 000000000000..4a12baa0cd4e
--- /dev/null
+++ b/tools/testing/kunit/kunit_tool_test.py
@@ -0,0 +1,206 @@
+#!/usr/bin/python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# A collection of tests for tools/testing/kunit/kunit.py
+#
+# Copyright (C) 2019, Google LLC.
+# Author: Brendan Higgins <brendanhiggins@google.com>
+
+import unittest
+from unittest import mock
+
+import tempfile, shutil # Handling test_tmpdir
+
+import os
+
+import kunit_config
+import kunit_parser
+import kunit_kernel
+import kunit
+
+test_tmpdir = ''
+
+def setUpModule():
+	global test_tmpdir
+	test_tmpdir = tempfile.mkdtemp()
+
+def tearDownModule():
+	shutil.rmtree(test_tmpdir)
+
+def get_absolute_path(path):
+	return os.path.join(os.path.dirname(__file__), path)
+
+class KconfigTest(unittest.TestCase):
+
+	def test_is_subset_of(self):
+		kconfig0 = kunit_config.Kconfig()
+		self.assertTrue(kconfig0.is_subset_of(kconfig0))
+
+		kconfig1 = kunit_config.Kconfig()
+		kconfig1.add_entry(kunit_config.KconfigEntry('CONFIG_TEST=y'))
+		self.assertTrue(kconfig1.is_subset_of(kconfig1))
+		self.assertTrue(kconfig0.is_subset_of(kconfig1))
+		self.assertFalse(kconfig1.is_subset_of(kconfig0))
+
+	def test_read_from_file(self):
+		kconfig = kunit_config.Kconfig()
+		kconfig_path = get_absolute_path(
+			'test_data/test_read_from_file.kconfig')
+
+		kconfig.read_from_file(kconfig_path)
+
+		expected_kconfig = kunit_config.Kconfig()
+		expected_kconfig.add_entry(
+			kunit_config.KconfigEntry('CONFIG_UML=y'))
+		expected_kconfig.add_entry(
+			kunit_config.KconfigEntry('CONFIG_MMU=y'))
+		expected_kconfig.add_entry(
+			kunit_config.KconfigEntry('CONFIG_TEST=y'))
+		expected_kconfig.add_entry(
+			kunit_config.KconfigEntry('CONFIG_EXAMPLE_TEST=y'))
+		expected_kconfig.add_entry(
+			kunit_config.KconfigEntry('# CONFIG_MK8 is not set'))
+
+		self.assertEqual(kconfig.entries(), expected_kconfig.entries())
+
+	def test_write_to_file(self):
+		kconfig_path = os.path.join(test_tmpdir, '.config')
+
+		expected_kconfig = kunit_config.Kconfig()
+		expected_kconfig.add_entry(
+			kunit_config.KconfigEntry('CONFIG_UML=y'))
+		expected_kconfig.add_entry(
+			kunit_config.KconfigEntry('CONFIG_MMU=y'))
+		expected_kconfig.add_entry(
+			kunit_config.KconfigEntry('CONFIG_TEST=y'))
+		expected_kconfig.add_entry(
+			kunit_config.KconfigEntry('CONFIG_EXAMPLE_TEST=y'))
+		expected_kconfig.add_entry(
+			kunit_config.KconfigEntry('# CONFIG_MK8 is not set'))
+
+		expected_kconfig.write_to_file(kconfig_path)
+
+		actual_kconfig = kunit_config.Kconfig()
+		actual_kconfig.read_from_file(kconfig_path)
+
+		self.assertEqual(actual_kconfig.entries(),
+				 expected_kconfig.entries())
+
+class KUnitParserTest(unittest.TestCase):
+
+	def assertContains(self, needle, haystack):
+		for line in haystack:
+			if needle in line:
+				return
+		raise AssertionError('"' +
+			str(needle) + '" not found in "' + str(haystack) + '"!')
+
+	def test_output_isolated_correctly(self):
+		log_path = get_absolute_path(
+			'test_data/test_output_isolated_correctly.log')
+		file = open(log_path)
+		result = kunit_parser.isolate_kunit_output(file.readlines())
+		self.assertContains('TAP version 14\n', result)
+		self.assertContains('	# Subtest: example', result)
+		self.assertContains('	1..2', result)
+		self.assertContains('	ok 1 - example_simple_test', result)
+		self.assertContains('	ok 2 - example_mock_test', result)
+		self.assertContains('ok 1 - example', result)
+		file.close()
+
+	def test_parse_successful_test_log(self):
+		all_passed_log = get_absolute_path(
+			'test_data/test_is_test_passed-all_passed.log')
+		file = open(all_passed_log)
+		result = kunit_parser.parse_run_tests(file.readlines())
+		self.assertEqual(
+			kunit_parser.TestStatus.SUCCESS,
+			result.status)
+		file.close()
+
+	def test_parse_failed_test_log(self):
+		failed_log = get_absolute_path(
+			'test_data/test_is_test_passed-failure.log')
+		file = open(failed_log)
+		result = kunit_parser.parse_run_tests(file.readlines())
+		self.assertEqual(
+			kunit_parser.TestStatus.FAILURE,
+			result.status)
+		file.close()
+
+	def test_no_tests(self):
+		empty_log = get_absolute_path(
+			'test_data/test_is_test_passed-no_tests_run.log')
+		file = open(empty_log)
+		result = kunit_parser.parse_run_tests(
+			kunit_parser.isolate_kunit_output(file.readlines()))
+		self.assertEqual(0, len(result.suites))
+		self.assertEqual(
+			kunit_parser.TestStatus.NO_TESTS,
+			result.status)
+		file.close()
+
+	def test_crashed_test(self):
+		crashed_log = get_absolute_path(
+			'test_data/test_is_test_passed-crash.log')
+		file = open(crashed_log)
+		result = kunit_parser.parse_run_tests(file.readlines())
+		self.assertEqual(
+			kunit_parser.TestStatus.TEST_CRASHED,
+			result.status)
+		file.close()
+
+class StrContains(str):
+	def __eq__(self, other):
+		return self in other
+
+class KUnitMainTest(unittest.TestCase):
+	def setUp(self):
+		path = get_absolute_path('test_data/test_is_test_passed-all_passed.log')
+		file = open(path)
+		all_passed_log = file.readlines()
+		self.print_patch = mock.patch('builtins.print')
+		self.print_mock = self.print_patch.start()
+		self.linux_source_mock = mock.Mock()
+		self.linux_source_mock.build_reconfig = mock.Mock(return_value=True)
+		self.linux_source_mock.build_um_kernel = mock.Mock(return_value=True)
+		self.linux_source_mock.run_kernel = mock.Mock(return_value=all_passed_log)
+
+	def tearDown(self):
+		self.print_patch.stop()
+		pass
+
+	def test_run_passes_args_pass(self):
+		kunit.main(['run'], self.linux_source_mock)
+		assert self.linux_source_mock.build_reconfig.call_count == 1
+		assert self.linux_source_mock.run_kernel.call_count == 1
+		self.print_mock.assert_any_call(StrContains('Testing complete.'))
+
+	def test_run_passes_args_fail(self):
+		self.linux_source_mock.run_kernel = mock.Mock(return_value=[])
+		with self.assertRaises(SystemExit) as e:
+			kunit.main(['run'], self.linux_source_mock)
+		assert type(e.exception) == SystemExit
+		assert e.exception.code == 1
+		assert self.linux_source_mock.build_reconfig.call_count == 1
+		assert self.linux_source_mock.run_kernel.call_count == 1
+		self.print_mock.assert_any_call(StrContains(' 0 tests run'))
+
+	def test_run_raw_output(self):
+		self.linux_source_mock.run_kernel = mock.Mock(return_value=[])
+		kunit.main(['run', '--raw_output'], self.linux_source_mock)
+		assert self.linux_source_mock.build_reconfig.call_count == 1
+		assert self.linux_source_mock.run_kernel.call_count == 1
+		for kall in self.print_mock.call_args_list:
+			assert kall != mock.call(StrContains('Testing complete.'))
+			assert kall != mock.call(StrContains(' 0 tests run'))
+
+	def test_run_timeout(self):
+		timeout = 3453
+		kunit.main(['run', '--timeout', str(timeout)], self.linux_source_mock)
+		assert self.linux_source_mock.build_reconfig.call_count == 1
+		self.linux_source_mock.run_kernel.assert_called_once_with(timeout=timeout)
+		self.print_mock.assert_any_call(StrContains('Testing complete.'))
+
+if __name__ == '__main__':
+	unittest.main()
diff --git a/tools/testing/kunit/test_data/test_is_test_passed-all_passed.log b/tools/testing/kunit/test_data/test_is_test_passed-all_passed.log
new file mode 100644
index 000000000000..62ebc0288355
--- /dev/null
+++ b/tools/testing/kunit/test_data/test_is_test_passed-all_passed.log
@@ -0,0 +1,32 @@
+TAP version 14
+	# Subtest: sysctl_test
+	1..8
+	# sysctl_test_dointvec_null_tbl_data: sysctl_test_dointvec_null_tbl_data passed
+	ok 1 - sysctl_test_dointvec_null_tbl_data
+	# sysctl_test_dointvec_table_maxlen_unset: sysctl_test_dointvec_table_maxlen_unset passed
+	ok 2 - sysctl_test_dointvec_table_maxlen_unset
+	# sysctl_test_dointvec_table_len_is_zero: sysctl_test_dointvec_table_len_is_zero passed
+	ok 3 - sysctl_test_dointvec_table_len_is_zero
+	# sysctl_test_dointvec_table_read_but_position_set: sysctl_test_dointvec_table_read_but_position_set passed
+	ok 4 - sysctl_test_dointvec_table_read_but_position_set
+	# sysctl_test_dointvec_happy_single_positive: sysctl_test_dointvec_happy_single_positive passed
+	ok 5 - sysctl_test_dointvec_happy_single_positive
+	# sysctl_test_dointvec_happy_single_negative: sysctl_test_dointvec_happy_single_negative passed
+	ok 6 - sysctl_test_dointvec_happy_single_negative
+	# sysctl_test_dointvec_single_less_int_min: sysctl_test_dointvec_single_less_int_min passed
+	ok 7 - sysctl_test_dointvec_single_less_int_min
+	# sysctl_test_dointvec_single_greater_int_max: sysctl_test_dointvec_single_greater_int_max passed
+	ok 8 - sysctl_test_dointvec_single_greater_int_max
+kunit sysctl_test: all tests passed
+ok 1 - sysctl_test
+	# Subtest: example
+	1..2
+init_suite
+	# example_simple_test: initializing
+	# example_simple_test: example_simple_test passed
+	ok 1 - example_simple_test
+	# example_mock_test: initializing
+	# example_mock_test: example_mock_test passed
+	ok 2 - example_mock_test
+kunit example: all tests passed
+ok 2 - example
diff --git a/tools/testing/kunit/test_data/test_is_test_passed-crash.log b/tools/testing/kunit/test_data/test_is_test_passed-crash.log
new file mode 100644
index 000000000000..0b249870c8be
--- /dev/null
+++ b/tools/testing/kunit/test_data/test_is_test_passed-crash.log
@@ -0,0 +1,69 @@
+printk: console [tty0] enabled
+printk: console [mc-1] enabled
+TAP version 14
+	# Subtest: sysctl_test
+	1..8
+	# sysctl_test_dointvec_null_tbl_data: sysctl_test_dointvec_null_tbl_data passed
+	ok 1 - sysctl_test_dointvec_null_tbl_data
+	# sysctl_test_dointvec_table_maxlen_unset: sysctl_test_dointvec_table_maxlen_unset passed
+	ok 2 - sysctl_test_dointvec_table_maxlen_unset
+	# sysctl_test_dointvec_table_len_is_zero: sysctl_test_dointvec_table_len_is_zero passed
+	ok 3 - sysctl_test_dointvec_table_len_is_zero
+	# sysctl_test_dointvec_table_read_but_position_set: sysctl_test_dointvec_table_read_but_position_set passed
+	ok 4 - sysctl_test_dointvec_table_read_but_position_set
+	# sysctl_test_dointvec_happy_single_positive: sysctl_test_dointvec_happy_single_positive passed
+	ok 5 - sysctl_test_dointvec_happy_single_positive
+	# sysctl_test_dointvec_happy_single_negative: sysctl_test_dointvec_happy_single_negative passed
+	ok 6 - sysctl_test_dointvec_happy_single_negative
+	# sysctl_test_dointvec_single_less_int_min: sysctl_test_dointvec_single_less_int_min passed
+	ok 7 - sysctl_test_dointvec_single_less_int_min
+	# sysctl_test_dointvec_single_greater_int_max: sysctl_test_dointvec_single_greater_int_max passed
+	ok 8 - sysctl_test_dointvec_single_greater_int_max
+kunit sysctl_test: all tests passed
+ok 1 - sysctl_test
+	# Subtest: example
+	1..2
+init_suite
+	# example_simple_test: initializing
+Stack:
+ 6016f7db 6f81bd30 6f81bdd0 60021450
+ 6024b0e8 60021440 60018bbe 16f81bdc0
+ 00000001 6f81bd30 6f81bd20 6f81bdd0
+Call Trace:
+ [<6016f7db>] ? kunit_try_run_case+0xab/0xf0
+ [<60021450>] ? set_signals+0x0/0x60
+ [<60021440>] ? get_signals+0x0/0x10
+ [<60018bbe>] ? kunit_um_run_try_catch+0x5e/0xc0
+ [<60021450>] ? set_signals+0x0/0x60
+ [<60021440>] ? get_signals+0x0/0x10
+ [<60018bb3>] ? kunit_um_run_try_catch+0x53/0xc0
+ [<6016f321>] ? kunit_run_case_catch_errors+0x121/0x1a0
+ [<60018b60>] ? kunit_um_run_try_catch+0x0/0xc0
+ [<600189e0>] ? kunit_um_throw+0x0/0x180
+ [<6016f730>] ? kunit_try_run_case+0x0/0xf0
+ [<6016f600>] ? kunit_catch_run_case+0x0/0x130
+ [<6016edd0>] ? kunit_vprintk+0x0/0x30
+ [<6016ece0>] ? kunit_fail+0x0/0x40
+ [<6016eca0>] ? kunit_abort+0x0/0x40
+ [<6016ed20>] ? kunit_printk_emit+0x0/0xb0
+ [<6016f200>] ? kunit_run_case_catch_errors+0x0/0x1a0
+ [<6016f46e>] ? kunit_run_tests+0xce/0x260
+ [<6005b390>] ? unregister_console+0x0/0x190
+ [<60175b70>] ? suite_kunit_initexample_test_suite+0x0/0x20
+ [<60001cbb>] ? do_one_initcall+0x0/0x197
+ [<60001d47>] ? do_one_initcall+0x8c/0x197
+ [<6005cd20>] ? irq_to_desc+0x0/0x30
+ [<60002005>] ? kernel_init_freeable+0x1b3/0x272
+ [<6005c5ec>] ? printk+0x0/0x9b
+ [<601c0086>] ? kernel_init+0x26/0x160
+ [<60014442>] ? new_thread_handler+0x82/0xc0
+
+	# example_simple_test: kunit test case crashed!
+	# example_simple_test: example_simple_test failed
+	not ok 1 - example_simple_test
+	# example_mock_test: initializing
+	# example_mock_test: example_mock_test passed
+	ok 2 - example_mock_test
+kunit example: one or more tests failed
+not ok 2 - example
+List of all partitions:
diff --git a/tools/testing/kunit/test_data/test_is_test_passed-failure.log b/tools/testing/kunit/test_data/test_is_test_passed-failure.log
new file mode 100644
index 000000000000..9e89d32d5667
--- /dev/null
+++ b/tools/testing/kunit/test_data/test_is_test_passed-failure.log
@@ -0,0 +1,36 @@
+TAP version 14
+	# Subtest: sysctl_test
+	1..8
+	# sysctl_test_dointvec_null_tbl_data: sysctl_test_dointvec_null_tbl_data passed
+	ok 1 - sysctl_test_dointvec_null_tbl_data
+	# sysctl_test_dointvec_table_maxlen_unset: sysctl_test_dointvec_table_maxlen_unset passed
+	ok 2 - sysctl_test_dointvec_table_maxlen_unset
+	# sysctl_test_dointvec_table_len_is_zero: sysctl_test_dointvec_table_len_is_zero passed
+	ok 3 - sysctl_test_dointvec_table_len_is_zero
+	# sysctl_test_dointvec_table_read_but_position_set: sysctl_test_dointvec_table_read_but_position_set passed
+	ok 4 - sysctl_test_dointvec_table_read_but_position_set
+	# sysctl_test_dointvec_happy_single_positive: sysctl_test_dointvec_happy_single_positive passed
+	ok 5 - sysctl_test_dointvec_happy_single_positive
+	# sysctl_test_dointvec_happy_single_negative: sysctl_test_dointvec_happy_single_negative passed
+	ok 6 - sysctl_test_dointvec_happy_single_negative
+	# sysctl_test_dointvec_single_less_int_min: sysctl_test_dointvec_single_less_int_min passed
+	ok 7 - sysctl_test_dointvec_single_less_int_min
+	# sysctl_test_dointvec_single_greater_int_max: sysctl_test_dointvec_single_greater_int_max passed
+	ok 8 - sysctl_test_dointvec_single_greater_int_max
+kunit sysctl_test: all tests passed
+ok 1 - sysctl_test
+	# Subtest: example
+	1..2
+init_suite
+	# example_simple_test: initializing
+	# example_simple_test: EXPECTATION FAILED at lib/kunit/example-test.c:30
+	Expected 1 + 1 == 3, but
+		1 + 1 == 2
+		3 == 3
+	# example_simple_test: example_simple_test failed
+	not ok 1 - example_simple_test
+	# example_mock_test: initializing
+	# example_mock_test: example_mock_test passed
+	ok 2 - example_mock_test
+kunit example: one or more tests failed
+not ok 2 - example
diff --git a/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run.log b/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run.log
new file mode 100644
index 000000000000..ba69f5c94b75
--- /dev/null
+++ b/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run.log
@@ -0,0 +1,75 @@
+Core dump limits :
+	soft - 0
+	hard - NONE
+Checking environment variables for a tempdir...none found
+Checking if /dev/shm is on tmpfs...OK
+Checking PROT_EXEC mmap in /dev/shm...OK
+Adding 24743936 bytes to physical memory to account for exec-shield gap
+Linux version 4.12.0-rc3-00010-g7319eb35f493-dirty (brendanhiggins@mactruck.svl.corp.google.com) (gcc version 7.3.0 (Debian 7.3.0-5) ) #29 Thu Mar 15 14:57:19 PDT 2018
+Built 1 zonelists in Zone order, mobility grouping on.  Total pages: 14038
+Kernel command line: root=98:0
+PID hash table entries: 256 (order: -1, 2048 bytes)
+Dentry cache hash table entries: 8192 (order: 4, 65536 bytes)
+Inode-cache hash table entries: 4096 (order: 3, 32768 bytes)
+Memory: 27868K/56932K available (1681K kernel code, 480K rwdata, 400K rodata, 89K init, 205K bss, 29064K reserved, 0K cma-reserved)
+SLUB: HWalign=64, Order=0-3, MinObjects=0, CPUs=1, Nodes=1
+NR_IRQS:15
+clocksource: timer: mask: 0xffffffffffffffff max_cycles: 0x1cd42e205, max_idle_ns: 881590404426 ns
+Calibrating delay loop... 7384.26 BogoMIPS (lpj=36921344)
+pid_max: default: 32768 minimum: 301
+Mount-cache hash table entries: 512 (order: 0, 4096 bytes)
+Mountpoint-cache hash table entries: 512 (order: 0, 4096 bytes)
+Checking that host ptys support output SIGIO...Yes
+Checking that host ptys support SIGIO on close...No, enabling workaround
+Using 2.6 host AIO
+clocksource: jiffies: mask: 0xffffffff max_cycles: 0xffffffff, max_idle_ns: 19112604462750000 ns
+futex hash table entries: 256 (order: 0, 6144 bytes)
+clocksource: Switched to clocksource timer
+console [stderr0] disabled
+mconsole (version 2) initialized on /usr/local/google/home/brendanhiggins/.uml/6Ijecl/mconsole
+Checking host MADV_REMOVE support...OK
+workingset: timestamp_bits=62 max_order=13 bucket_order=0
+Block layer SCSI generic (bsg) driver version 0.4 loaded (major 254)
+io scheduler noop registered
+io scheduler deadline registered
+io scheduler cfq registered (default)
+io scheduler mq-deadline registered
+io scheduler kyber registered
+Initialized stdio console driver
+Using a channel type which is configured out of UML
+setup_one_line failed for device 1 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 2 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 3 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 4 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 5 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 6 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 7 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 8 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 9 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 10 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 11 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 12 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 13 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 14 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 15 : Configuration failed
+Console initialized on /dev/tty0
+console [tty0] enabled
+console [mc-1] enabled
+List of all partitions:
+No filesystem could mount root, tried:
+
+Kernel panic - not syncing: VFS: Unable to mount root fs on unknown-block(98,0)
diff --git a/tools/testing/kunit/test_data/test_output_isolated_correctly.log b/tools/testing/kunit/test_data/test_output_isolated_correctly.log
new file mode 100644
index 000000000000..94a6b3aeaa92
--- /dev/null
+++ b/tools/testing/kunit/test_data/test_output_isolated_correctly.log
@@ -0,0 +1,106 @@
+Linux version 5.1.0-rc7-00061-g04652f1cb4aa0 (brendanhiggins@mactruck.svl.corp.google.com) (gcc version 7.3.0 (Debian 7.3.0-18)) #163 Wed May 8 16:18:20 PDT 2019
+Built 1 zonelists, mobility grouping on.  Total pages: 69906
+Kernel command line: mem=256M root=98:0
+Dentry cache hash table entries: 65536 (order: 7, 524288 bytes)
+Inode-cache hash table entries: 32768 (order: 6, 262144 bytes)
+Memory: 254468K/283500K available (1734K kernel code, 489K rwdata, 396K rodata, 85K init, 216K bss, 29032K reserved, 0K cma-reserved)
+SLUB: HWalign=64, Order=0-3, MinObjects=0, CPUs=1, Nodes=1
+NR_IRQS: 15
+clocksource: timer: mask: 0xffffffffffffffff max_cycles: 0x1cd42e205, max_idle_ns: 881590404426 ns
+------------[ cut here ]------------
+WARNING: CPU: 0 PID: 0 at kernel/time/clockevents.c:458 clockevents_register_device+0x143/0x160
+posix-timer cpumask == cpu_all_mask, using cpu_possible_mask instead
+CPU: 0 PID: 0 Comm: swapper Not tainted 5.1.0-rc7-00061-g04652f1cb4aa0 #163
+Stack:
+ 6005cc00 60233e18 60233e60 60233e18
+ 60233e60 00000009 00000000 6002a1b4
+ 1ca00000000 60071c23 60233e78 100000000000062
+Call Trace:
+ [<600214c5>] ? os_is_signal_stack+0x15/0x30
+ [<6005c5ec>] ? printk+0x0/0x9b
+ [<6001597e>] ? show_stack+0xbe/0x1c0
+ [<6005cc00>] ? __printk_safe_exit+0x0/0x40
+ [<6002a1b4>] ? __warn+0x144/0x170
+ [<60071c23>] ? clockevents_register_device+0x143/0x160
+ [<60021440>] ? get_signals+0x0/0x10
+ [<6005c5ec>] ? printk+0x0/0x9b
+ [<6002a27b>] ? warn_slowpath_fmt+0x9b/0xb0
+ [<6005c5ec>] ? printk+0x0/0x9b
+ [<6002a1e0>] ? warn_slowpath_fmt+0x0/0xb0
+ [<6005c5ec>] ? printk+0x0/0x9b
+ [<60021440>] ? get_signals+0x0/0x10
+ [<600213f0>] ? block_signals+0x0/0x20
+ [<60071c23>] ? clockevents_register_device+0x143/0x160
+ [<60021440>] ? get_signals+0x0/0x10
+ [<600213f0>] ? block_signals+0x0/0x20
+ [<6005c5ec>] ? printk+0x0/0x9b
+ [<60001bc8>] ? start_kernel+0x477/0x56a
+ [<600036f1>] ? start_kernel_proc+0x46/0x4d
+ [<60014442>] ? new_thread_handler+0x82/0xc0
+
+random: get_random_bytes called from print_oops_end_marker+0x4c/0x60 with crng_init=0
+---[ end trace c83434852b3702d3 ]---
+Calibrating delay loop... 6958.28 BogoMIPS (lpj=34791424)
+pid_max: default: 32768 minimum: 301
+Mount-cache hash table entries: 1024 (order: 1, 8192 bytes)
+Mountpoint-cache hash table entries: 1024 (order: 1, 8192 bytes)
+*** VALIDATE proc ***
+Checking that host ptys support output SIGIO...Yes
+Checking that host ptys support SIGIO on close...No, enabling workaround
+clocksource: jiffies: mask: 0xffffffff max_cycles: 0xffffffff, max_idle_ns: 19112604462750000 ns
+futex hash table entries: 256 (order: 0, 6144 bytes)
+clocksource: Switched to clocksource timer
+printk: console [stderr0] disabled
+mconsole (version 2) initialized on /usr/local/google/home/brendanhiggins/.uml/VZ2qMm/mconsole
+Checking host MADV_REMOVE support...OK
+workingset: timestamp_bits=62 max_order=16 bucket_order=0
+Block layer SCSI generic (bsg) driver version 0.4 loaded (major 254)
+io scheduler mq-deadline registered
+io scheduler kyber registered
+Initialized stdio console driver
+Using a channel type which is configured out of UML
+setup_one_line failed for device 1 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 2 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 3 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 4 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 5 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 6 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 7 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 8 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 9 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 10 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 11 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 12 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 13 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 14 : Configuration failed
+Using a channel type which is configured out of UML
+setup_one_line failed for device 15 : Configuration failed
+Console initialized on /dev/tty0
+printk: console [tty0] enabled
+printk: console [mc-1] enabled
+TAP version 14
+	# Subtest: example
+	1..2
+init_suite
+	# example_simple_test: initializing
+	# example_simple_test: example_simple_test passed
+	ok 1 - example_simple_test
+	# example_mock_test: initializing
+	# example_mock_test: example_mock_test passed
+	ok 2 - example_mock_test
+kunit example: all tests passed
+ok 1 - example
+List of all partitions:
diff --git a/tools/testing/kunit/test_data/test_read_from_file.kconfig b/tools/testing/kunit/test_data/test_read_from_file.kconfig
new file mode 100644
index 000000000000..d2a4928ac773
--- /dev/null
+++ b/tools/testing/kunit/test_data/test_read_from_file.kconfig
@@ -0,0 +1,17 @@
+#
+# Automatically generated file; DO NOT EDIT.
+# User Mode Linux/x86 4.12.0-rc3 Kernel Configuration
+#
+CONFIG_UML=y
+CONFIG_MMU=y
+
+#
+# UML-specific options
+#
+
+#
+# Host processor type and features
+#
+# CONFIG_MK8 is not set
+CONFIG_TEST=y
+CONFIG_EXAMPLE_TEST=y
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 4cdbae6f4e61..0fb95f25944d 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,9 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 TARGETS = android
+TARGETS += arm64
 TARGETS += bpf
 TARGETS += breakpoints
 TARGETS += capabilities
 TARGETS += cgroup
+TARGETS += clone3
 TARGETS += cpufreq
 TARGETS += cpu-hotplug
 TARGETS += drivers/dma-buf
@@ -86,10 +88,10 @@ override LDFLAGS =
 endif
 
 ifneq ($(O),)
-	BUILD := $(O)
+	BUILD := $(abs_objtree)
 else
 	ifneq ($(KBUILD_OUTPUT),)
-		BUILD := $(KBUILD_OUTPUT)/kselftest
+		BUILD := $(abs_objtree)/kselftest
 	else
 		BUILD := $(shell pwd)
 		DEFAULT_INSTALL_HDR_PATH := 1
@@ -102,6 +104,7 @@ include $(top_srcdir)/scripts/subarch.include
 ARCH           ?= $(SUBARCH)
 export KSFT_KHDR_INSTALL_DONE := 1
 export BUILD
+#$(info abd_objtree = $(abs_objtree) BUILD = $(BUILD))
 
 # build and run gpio when output directory is the src dir.
 # gpio has dependency on tools/gpio and builds tools/gpio
@@ -190,6 +193,7 @@ install: all
 ifdef INSTALL_PATH
 	@# Ask all targets to install their files
 	mkdir -p $(INSTALL_PATH)/kselftest
+	install -m 744 kselftest/module.sh $(INSTALL_PATH)/kselftest/
 	install -m 744 kselftest/runner.sh $(INSTALL_PATH)/kselftest/
 	install -m 744 kselftest/prefix.pl $(INSTALL_PATH)/kselftest/
 	@for TARGET in $(TARGETS); do \
@@ -213,7 +217,7 @@ ifdef INSTALL_PATH
 	@# included in the generated runlist.
 	for TARGET in $(TARGETS); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
-		[ ! -d $$INSTALL_PATH/$$TARGET ] && echo "Skipping non-existent dir: $$TARGET" && continue; \
+		[ ! -d $(INSTALL_PATH)/$$TARGET ] && echo "Skipping non-existent dir: $$TARGET" && continue; \
 		echo "[ -w /dev/kmsg ] && echo \"kselftest: Running tests in $$TARGET\" >> /dev/kmsg" >> $(ALL_SCRIPT); \
 		echo "cd $$TARGET" >> $(ALL_SCRIPT); \
 		echo -n "run_many" >> $(ALL_SCRIPT); \
diff --git a/tools/testing/selftests/arm64/Makefile b/tools/testing/selftests/arm64/Makefile
index f9f79fb272f0..93b567d23c8b 100644
--- a/tools/testing/selftests/arm64/Makefile
+++ b/tools/testing/selftests/arm64/Makefile
@@ -1,12 +1,66 @@
 # SPDX-License-Identifier: GPL-2.0
 
-# ARCH can be overridden by the user for cross compiling
+# When ARCH not overridden for crosscompiling, lookup machine
 ARCH ?= $(shell uname -m 2>/dev/null || echo not)
 
 ifneq (,$(filter $(ARCH),aarch64 arm64))
-CFLAGS += -I../../../../usr/include/
-TEST_GEN_PROGS := tags_test
-TEST_PROGS := run_tags_test.sh
+ARM64_SUBTARGETS ?= tags signal
+else
+ARM64_SUBTARGETS :=
 endif
 
-include ../lib.mk
+CFLAGS := -Wall -O2 -g
+
+# A proper top_srcdir is needed by KSFT(lib.mk)
+top_srcdir = $(realpath ../../../../)
+
+# Additional include paths needed by kselftest.h and local headers
+CFLAGS += -I$(top_srcdir)/tools/testing/selftests/
+
+# Guessing where the Kernel headers could have been installed
+# depending on ENV config
+ifeq ($(KBUILD_OUTPUT),)
+khdr_dir = $(top_srcdir)/usr/include
+else
+# the KSFT preferred location when KBUILD_OUTPUT is set
+khdr_dir = $(KBUILD_OUTPUT)/kselftest/usr/include
+endif
+
+CFLAGS += -I$(khdr_dir)
+
+export CFLAGS
+export top_srcdir
+
+all:
+	@for DIR in $(ARM64_SUBTARGETS); do				\
+		BUILD_TARGET=$(OUTPUT)/$$DIR;			\
+		mkdir -p $$BUILD_TARGET;			\
+		make OUTPUT=$$BUILD_TARGET -C $$DIR $@;		\
+	done
+
+install: all
+	@for DIR in $(ARM64_SUBTARGETS); do				\
+		BUILD_TARGET=$(OUTPUT)/$$DIR;			\
+		make OUTPUT=$$BUILD_TARGET -C $$DIR $@;		\
+	done
+
+run_tests: all
+	@for DIR in $(ARM64_SUBTARGETS); do				\
+		BUILD_TARGET=$(OUTPUT)/$$DIR;			\
+		make OUTPUT=$$BUILD_TARGET -C $$DIR $@;		\
+	done
+
+# Avoid any output on non arm64 on emit_tests
+emit_tests: all
+	@for DIR in $(ARM64_SUBTARGETS); do				\
+		BUILD_TARGET=$(OUTPUT)/$$DIR;			\
+		make OUTPUT=$$BUILD_TARGET -C $$DIR $@;		\
+	done
+
+clean:
+	@for DIR in $(ARM64_SUBTARGETS); do				\
+		BUILD_TARGET=$(OUTPUT)/$$DIR;			\
+		make OUTPUT=$$BUILD_TARGET -C $$DIR $@;		\
+	done
+
+.PHONY: all clean install run_tests emit_tests
diff --git a/tools/testing/selftests/arm64/README b/tools/testing/selftests/arm64/README
new file mode 100644
index 000000000000..a1badd882102
--- /dev/null
+++ b/tools/testing/selftests/arm64/README
@@ -0,0 +1,25 @@
+KSelfTest ARM64
+===============
+
+- These tests are arm64 specific and so not built or run but just skipped
+  completely when env-variable ARCH is found to be different than 'arm64'
+  and `uname -m` reports other than 'aarch64'.
+
+- Holding true the above, ARM64 KSFT tests can be run within the KSelfTest
+  framework using standard Linux top-level-makefile targets:
+
+      $ make TARGETS=arm64 kselftest-clean
+      $ make TARGETS=arm64 kselftest
+
+      or
+
+      $ make -C tools/testing/selftests TARGETS=arm64 \
+		INSTALL_PATH=<your-installation-path> install
+
+      or, alternatively, only specific arm64/ subtargets can be picked:
+
+      $ make -C tools/testing/selftests TARGETS=arm64 ARM64_SUBTARGETS="tags signal" \
+		INSTALL_PATH=<your-installation-path> install
+
+   Further details on building and running KFST can be found in:
+     Documentation/dev-tools/kselftest.rst
diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore
new file mode 100644
index 000000000000..3c5b4e8ff894
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/.gitignore
@@ -0,0 +1,3 @@
+mangle_*
+fake_sigreturn_*
+!*.[ch]
diff --git a/tools/testing/selftests/arm64/signal/Makefile b/tools/testing/selftests/arm64/signal/Makefile
new file mode 100644
index 000000000000..b497cfea4643
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/Makefile
@@ -0,0 +1,32 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2019 ARM Limited
+
+# Additional include paths needed by kselftest.h and local headers
+CFLAGS += -D_GNU_SOURCE -std=gnu99 -I.
+
+SRCS := $(filter-out testcases/testcases.c,$(wildcard testcases/*.c))
+PROGS := $(patsubst %.c,%,$(SRCS))
+
+# Generated binaries to be installed by top KSFT script
+TEST_GEN_PROGS := $(notdir $(PROGS))
+
+# Get Kernel headers installed and use them.
+KSFT_KHDR_INSTALL := 1
+
+# Including KSFT lib.mk here will also mangle the TEST_GEN_PROGS list
+# to account for any OUTPUT target-dirs optionally provided by
+# the toplevel makefile
+include ../../lib.mk
+
+$(TEST_GEN_PROGS): $(PROGS)
+	cp $(PROGS) $(OUTPUT)/
+
+clean:
+	$(CLEAN)
+	rm -f $(PROGS)
+
+# Common test-unit targets to build common-layout test-cases executables
+# Needs secondary expansion to properly include the testcase c-file in pre-reqs
+.SECONDEXPANSION:
+$(PROGS): test_signals.c test_signals_utils.c testcases/testcases.c signals.S $$@.c test_signals.h test_signals_utils.h testcases/testcases.h
+	$(CC) $(CFLAGS) $^ -o $@
diff --git a/tools/testing/selftests/arm64/signal/README b/tools/testing/selftests/arm64/signal/README
new file mode 100644
index 000000000000..967a531b245c
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/README
@@ -0,0 +1,59 @@
+KSelfTest arm64/signal/
+=======================
+
+Signals Tests
++++++++++++++
+
+- Tests are built around a common main compilation unit: such shared main
+  enforces a standard sequence of operations needed to perform a single
+  signal-test (setup/trigger/run/result/cleanup)
+
+- The above mentioned ops are configurable on a test-by-test basis: each test
+  is described (and configured) using the descriptor signals.h::struct tdescr
+
+- Each signal testcase is compiled into its own executable: a separate
+  executable is used for each test since many tests complete successfully
+  by receiving some kind of fatal signal from the Kernel, so it's safer
+  to run each test unit in its own standalone process, so as to start each
+  test from a clean slate.
+
+- New tests can be simply defined in testcases/ dir providing a proper struct
+  tdescr overriding all the defaults we wish to change (as of now providing a
+  custom run method is mandatory though)
+
+- Signals' test-cases hereafter defined belong currently to two
+  principal families:
+
+  - 'mangle_' tests: a real signal (SIGUSR1) is raised and used as a trigger
+    and then the test case code modifies the signal frame from inside the
+    signal handler itself.
+
+  - 'fake_sigreturn_' tests: a brand new custom artificial sigframe structure
+    is placed on the stack and a sigreturn syscall is called to simulate a
+    real signal return. This kind of tests does not use a trigger usually and
+    they are just fired using some simple included assembly trampoline code.
+
+ - Most of these tests are successfully passing if the process gets killed by
+   some fatal signal: usually SIGSEGV or SIGBUS. Since while writing this
+   kind of tests it is extremely easy in fact to end-up injecting other
+   unrelated SEGV bugs in the testcases, it becomes extremely tricky to
+   be really sure that the tests are really addressing what they are meant
+   to address and they are not instead falling apart due to unplanned bugs
+   in the test code.
+   In order to alleviate the misery of the life of such test-developer, a few
+   helpers are provided:
+
+   - a couple of ASSERT_BAD/GOOD_CONTEXT() macros to easily parse a ucontext_t
+     and verify if it is indeed GOOD or BAD (depending on what we were
+     expecting), using the same logic/perspective as in the arm64 Kernel signals
+     routines.
+
+   - a sanity mechanism to be used in 'fake_sigreturn_'-alike tests: enabled by
+     default it takes care to verify that the test-execution had at least
+     successfully progressed up to the stage of triggering the fake sigreturn
+     call.
+
+  In both cases test results are expected in terms of:
+   - some fatal signal sent by the Kernel to the test process
+  or
+  - analyzing some final regs state
diff --git a/tools/testing/selftests/arm64/signal/signals.S b/tools/testing/selftests/arm64/signal/signals.S
new file mode 100644
index 000000000000..9f8c1aefc3b9
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/signals.S
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 ARM Limited */
+
+#include <asm/unistd.h>
+
+.section        .rodata, "a"
+call_fmt:
+	.asciz "Calling sigreturn with fake sigframe sized:%zd at SP @%08lX\n"
+
+.text
+
+.globl fake_sigreturn
+
+/*	fake_sigreturn	x0:&sigframe,  x1:sigframe_size,  x2:misalign_bytes */
+fake_sigreturn:
+	stp	x29, x30, [sp, #-16]!
+	mov	x29, sp
+
+	mov	x20, x0
+	mov	x21, x1
+	mov	x22, x2
+
+	/* create space on the stack for fake sigframe 16 bytes-aligned */
+	add	x0, x21, x22
+	add	x0, x0, #15
+	bic	x0, x0, #15 /* round_up(sigframe_size + misalign_bytes, 16) */
+	sub	sp, sp, x0
+	add	x23, sp, x22 /* new sigframe base with misaligment if any */
+
+	ldr	x0, =call_fmt
+	mov	x1, x21
+	mov	x2, x23
+	bl	printf
+
+	/* memcpy the provided content, while still keeping SP aligned */
+	mov	x0, x23
+	mov	x1, x20
+	mov	x2, x21
+	bl	memcpy
+
+	/*
+	 * Here saving a last minute SP to current->token acts as a marker:
+	 * if we got here, we are successfully faking a sigreturn; in other
+	 * words we are sure no bad fatal signal has been raised till now
+	 * for unrelated reasons, so we should consider the possibly observed
+	 * fatal signal like SEGV coming from Kernel restore_sigframe() and
+	 * triggered as expected from our test-case.
+	 * For simplicity this assumes that current field 'token' is laid out
+	 * as first in struct tdescr
+	 */
+	ldr	x0, current
+	str	x23, [x0]
+	/* finally move SP to misaligned address...if any requested */
+	mov	sp, x23
+
+	mov	x8, #__NR_rt_sigreturn
+	svc	#0
+
+	/*
+	 * Above sigreturn should not return...looping here leads to a timeout
+	 * and ensure proper and clean test failure, instead of jumping around
+	 * on a potentially corrupted stack.
+	 */
+	b	.
diff --git a/tools/testing/selftests/arm64/signal/test_signals.c b/tools/testing/selftests/arm64/signal/test_signals.c
new file mode 100644
index 000000000000..416b1ff43199
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/test_signals.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Generic test wrapper for arm64 signal tests.
+ *
+ * Each test provides its own tde struct tdescr descriptor to link with
+ * this wrapper. Framework provides common helpers.
+ */
+#include <kselftest.h>
+
+#include "test_signals.h"
+#include "test_signals_utils.h"
+
+struct tdescr *current;
+
+int main(int argc, char *argv[])
+{
+	current = &tde;
+
+	ksft_print_msg("%s :: %s\n", current->name, current->descr);
+	if (test_setup(current) && test_init(current)) {
+		test_run(current);
+		test_cleanup(current);
+	}
+	test_result(current);
+
+	return current->result;
+}
diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h
new file mode 100644
index 000000000000..f96baf1cef1a
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/test_signals.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 ARM Limited */
+
+#ifndef __TEST_SIGNALS_H__
+#define __TEST_SIGNALS_H__
+
+#include <signal.h>
+#include <stdbool.h>
+#include <ucontext.h>
+
+/*
+ * Using ARCH specific and sanitized Kernel headers installed by KSFT
+ * framework since we asked for it by setting flag KSFT_KHDR_INSTALL
+ * in our Makefile.
+ */
+#include <asm/ptrace.h>
+#include <asm/hwcap.h>
+
+#define __stringify_1(x...)	#x
+#define __stringify(x...)	__stringify_1(x)
+
+#define get_regval(regname, out)			\
+{							\
+	asm volatile("mrs %0, " __stringify(regname)	\
+	: "=r" (out)					\
+	:						\
+	: "memory");					\
+}
+
+/*
+ * Feature flags used in tdescr.feats_required to specify
+ * any feature by the test
+ */
+enum {
+	FSSBS_BIT,
+	FMAX_END
+};
+
+#define FEAT_SSBS		(1UL << FSSBS_BIT)
+
+/*
+ * A descriptor used to describe and configure a test case.
+ * Fields with a non-trivial meaning are described inline in the following.
+ */
+struct tdescr {
+	/* KEEP THIS FIELD FIRST for easier lookup from assembly */
+	void			*token;
+	/* when disabled token based sanity checking is skipped in handler */
+	bool			sanity_disabled;
+	/* just a name for the test-case; manadatory field */
+	char			*name;
+	char			*descr;
+	unsigned long		feats_required;
+	/* bitmask of effectively supported feats: populated at run-time */
+	unsigned long		feats_supported;
+	bool			initialized;
+	unsigned int		minsigstksz;
+	/* signum used as a test trigger. Zero if no trigger-signal is used */
+	int			sig_trig;
+	/*
+	 * signum considered as a successful test completion.
+	 * Zero when no signal is expected on success
+	 */
+	int			sig_ok;
+	/* signum expected on unsupported CPU features. */
+	int			sig_unsupp;
+	/* a timeout in second for test completion */
+	unsigned int		timeout;
+	bool			triggered;
+	bool			pass;
+	unsigned int		result;
+	/* optional sa_flags for the installed handler */
+	int			sa_flags;
+	ucontext_t		saved_uc;
+	/* used by get_current_ctx() */
+	size_t			live_sz;
+	ucontext_t		*live_uc;
+	volatile sig_atomic_t	live_uc_valid;
+	/* optional test private data */
+	void			*priv;
+
+	/* a custom setup: called alternatively to default_setup */
+	int (*setup)(struct tdescr *td);
+	/* a custom init: called by default test init after test_setup */
+	bool (*init)(struct tdescr *td);
+	/* a custom cleanup function called before test exits */
+	void (*cleanup)(struct tdescr *td);
+	/* an optional function to be used as a trigger for starting test */
+	int (*trigger)(struct tdescr *td);
+	/*
+	 * the actual test-core: invoked differently depending on the
+	 * presence of the trigger function above; this is mandatory
+	 */
+	int (*run)(struct tdescr *td, siginfo_t *si, ucontext_t *uc);
+	/* an optional function for custom results' processing */
+	void (*check_result)(struct tdescr *td);
+};
+
+extern struct tdescr tde;
+#endif
diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c
new file mode 100644
index 000000000000..2de6e5ed5e25
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c
@@ -0,0 +1,328 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2019 ARM Limited */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <string.h>
+#include <unistd.h>
+#include <assert.h>
+#include <sys/auxv.h>
+#include <linux/auxvec.h>
+#include <ucontext.h>
+
+#include <asm/unistd.h>
+
+#include <kselftest.h>
+
+#include "test_signals.h"
+#include "test_signals_utils.h"
+#include "testcases/testcases.h"
+
+
+extern struct tdescr *current;
+
+static int sig_copyctx = SIGTRAP;
+
+static char const *const feats_names[FMAX_END] = {
+	" SSBS ",
+};
+
+#define MAX_FEATS_SZ	128
+static char feats_string[MAX_FEATS_SZ];
+
+static inline char *feats_to_string(unsigned long feats)
+{
+	size_t flen = MAX_FEATS_SZ - 1;
+
+	for (int i = 0; i < FMAX_END; i++) {
+		if (feats & (1UL << i)) {
+			size_t tlen = strlen(feats_names[i]);
+
+			assert(flen > tlen);
+			flen -= tlen;
+			strncat(feats_string, feats_names[i], flen);
+		}
+	}
+
+	return feats_string;
+}
+
+static void unblock_signal(int signum)
+{
+	sigset_t sset;
+
+	sigemptyset(&sset);
+	sigaddset(&sset, signum);
+	sigprocmask(SIG_UNBLOCK, &sset, NULL);
+}
+
+static void default_result(struct tdescr *td, bool force_exit)
+{
+	if (td->result == KSFT_SKIP) {
+		fprintf(stderr, "==>> completed. SKIP.\n");
+	} else if (td->pass) {
+		fprintf(stderr, "==>> completed. PASS(1)\n");
+		td->result = KSFT_PASS;
+	} else {
+		fprintf(stdout, "==>> completed. FAIL(0)\n");
+		td->result = KSFT_FAIL;
+	}
+
+	if (force_exit)
+		exit(td->result);
+}
+
+/*
+ * The following handle_signal_* helpers are used by main default_handler
+ * and are meant to return true when signal is handled successfully:
+ * when false is returned instead, it means that the signal was somehow
+ * unexpected in that context and it was NOT handled; default_handler will
+ * take care of such unexpected situations.
+ */
+
+static bool handle_signal_unsupported(struct tdescr *td,
+				      siginfo_t *si, void *uc)
+{
+	if (feats_ok(td))
+		return false;
+
+	/* Mangling PC to avoid loops on original SIGILL */
+	((ucontext_t *)uc)->uc_mcontext.pc += 4;
+
+	if (!td->initialized) {
+		fprintf(stderr,
+			"Got SIG_UNSUPP @test_init. Ignore.\n");
+	} else {
+		fprintf(stderr,
+			"-- RX SIG_UNSUPP on unsupported feat...OK\n");
+		td->pass = 1;
+		default_result(current, 1);
+	}
+
+	return true;
+}
+
+static bool handle_signal_trigger(struct tdescr *td,
+				  siginfo_t *si, void *uc)
+{
+	td->triggered = 1;
+	/* ->run was asserted NON-NULL in test_setup() already */
+	td->run(td, si, uc);
+
+	return true;
+}
+
+static bool handle_signal_ok(struct tdescr *td,
+			     siginfo_t *si, void *uc)
+{
+	/*
+	 * it's a bug in the test code when this assert fail:
+	 * if sig_trig was defined, it must have been used before getting here.
+	 */
+	assert(!td->sig_trig || td->triggered);
+	fprintf(stderr,
+		"SIG_OK -- SP:0x%llX  si_addr@:%p  si_code:%d  token@:%p  offset:%ld\n",
+		((ucontext_t *)uc)->uc_mcontext.sp,
+		si->si_addr, si->si_code, td->token, td->token - si->si_addr);
+	/*
+	 * fake_sigreturn tests, which have sanity_enabled=1, set, at the very
+	 * last time, the token field to the SP address used to place the fake
+	 * sigframe: so token==0 means we never made it to the end,
+	 * segfaulting well-before, and the test is possibly broken.
+	 */
+	if (!td->sanity_disabled && !td->token) {
+		fprintf(stdout,
+			"current->token ZEROED...test is probably broken!\n");
+		abort();
+	}
+	/*
+	 * Trying to narrow down the SEGV to the ones generated by Kernel itself
+	 * via arm64_notify_segfault(). This is a best-effort check anyway, and
+	 * the si_code check may need to change if this aspect of the kernel
+	 * ABI changes.
+	 */
+	if (td->sig_ok == SIGSEGV && si->si_code != SEGV_ACCERR) {
+		fprintf(stdout,
+			"si_code != SEGV_ACCERR...test is probably broken!\n");
+		abort();
+	}
+	td->pass = 1;
+	/*
+	 * Some tests can lead to SEGV loops: in such a case we want to
+	 * terminate immediately exiting straight away; some others are not
+	 * supposed to outlive the signal handler code, due to the content of
+	 * the fake sigframe which caused the signal itself.
+	 */
+	default_result(current, 1);
+
+	return true;
+}
+
+static bool handle_signal_copyctx(struct tdescr *td,
+				  siginfo_t *si, void *uc)
+{
+	/* Mangling PC to avoid loops on original BRK instr */
+	((ucontext_t *)uc)->uc_mcontext.pc += 4;
+	memcpy(td->live_uc, uc, td->live_sz);
+	ASSERT_GOOD_CONTEXT(td->live_uc);
+	td->live_uc_valid = 1;
+	fprintf(stderr,
+		"GOOD CONTEXT grabbed from sig_copyctx handler\n");
+
+	return true;
+}
+
+static void default_handler(int signum, siginfo_t *si, void *uc)
+{
+	if (current->sig_unsupp && signum == current->sig_unsupp &&
+	    handle_signal_unsupported(current, si, uc)) {
+		fprintf(stderr, "Handled SIG_UNSUPP\n");
+	} else if (current->sig_trig && signum == current->sig_trig &&
+		   handle_signal_trigger(current, si, uc)) {
+		fprintf(stderr, "Handled SIG_TRIG\n");
+	} else if (current->sig_ok && signum == current->sig_ok &&
+		   handle_signal_ok(current, si, uc)) {
+		fprintf(stderr, "Handled SIG_OK\n");
+	} else if (signum == sig_copyctx && current->live_uc &&
+		   handle_signal_copyctx(current, si, uc)) {
+		fprintf(stderr, "Handled SIG_COPYCTX\n");
+	} else {
+		if (signum == SIGALRM && current->timeout) {
+			fprintf(stderr, "-- Timeout !\n");
+		} else {
+			fprintf(stderr,
+				"-- RX UNEXPECTED SIGNAL: %d\n", signum);
+		}
+		default_result(current, 1);
+	}
+}
+
+static int default_setup(struct tdescr *td)
+{
+	struct sigaction sa;
+
+	sa.sa_sigaction = default_handler;
+	sa.sa_flags = SA_SIGINFO | SA_RESTART;
+	sa.sa_flags |= td->sa_flags;
+	sigemptyset(&sa.sa_mask);
+	/* uncatchable signals naturally skipped ... */
+	for (int sig = 1; sig < 32; sig++)
+		sigaction(sig, &sa, NULL);
+	/*
+	 * RT Signals default disposition is Term but they cannot be
+	 * generated by the Kernel in response to our tests; so just catch
+	 * them all and report them as UNEXPECTED signals.
+	 */
+	for (int sig = SIGRTMIN; sig <= SIGRTMAX; sig++)
+		sigaction(sig, &sa, NULL);
+
+	/* just in case...unblock explicitly all we need */
+	if (td->sig_trig)
+		unblock_signal(td->sig_trig);
+	if (td->sig_ok)
+		unblock_signal(td->sig_ok);
+	if (td->sig_unsupp)
+		unblock_signal(td->sig_unsupp);
+
+	if (td->timeout) {
+		unblock_signal(SIGALRM);
+		alarm(td->timeout);
+	}
+	fprintf(stderr, "Registered handlers for all signals.\n");
+
+	return 1;
+}
+
+static inline int default_trigger(struct tdescr *td)
+{
+	return !raise(td->sig_trig);
+}
+
+int test_init(struct tdescr *td)
+{
+	if (td->sig_trig == sig_copyctx) {
+		fprintf(stdout,
+			"Signal %d is RESERVED, cannot be used as a trigger. Aborting\n",
+			sig_copyctx);
+		return 0;
+	}
+	/* just in case */
+	unblock_signal(sig_copyctx);
+
+	td->minsigstksz = getauxval(AT_MINSIGSTKSZ);
+	if (!td->minsigstksz)
+		td->minsigstksz = MINSIGSTKSZ;
+	fprintf(stderr, "Detected MINSTKSIGSZ:%d\n", td->minsigstksz);
+
+	if (td->feats_required) {
+		td->feats_supported = 0;
+		/*
+		 * Checking for CPU required features using both the
+		 * auxval and the arm64 MRS Emulation to read sysregs.
+		 */
+		if (getauxval(AT_HWCAP) & HWCAP_SSBS)
+			td->feats_supported |= FEAT_SSBS;
+		if (feats_ok(td))
+			fprintf(stderr,
+				"Required Features: [%s] supported\n",
+				feats_to_string(td->feats_required &
+						td->feats_supported));
+		else
+			fprintf(stderr,
+				"Required Features: [%s] NOT supported\n",
+				feats_to_string(td->feats_required &
+						~td->feats_supported));
+	}
+
+	/* Perform test specific additional initialization */
+	if (td->init && !td->init(td)) {
+		fprintf(stderr, "FAILED Testcase initialization.\n");
+		return 0;
+	}
+	td->initialized = 1;
+	fprintf(stderr, "Testcase initialized.\n");
+
+	return 1;
+}
+
+int test_setup(struct tdescr *td)
+{
+	/* assert core invariants symptom of a rotten testcase */
+	assert(current);
+	assert(td);
+	assert(td->name);
+	assert(td->run);
+
+	/* Default result is FAIL if test setup fails */
+	td->result = KSFT_FAIL;
+	if (td->setup)
+		return td->setup(td);
+	else
+		return default_setup(td);
+}
+
+int test_run(struct tdescr *td)
+{
+	if (td->sig_trig) {
+		if (td->trigger)
+			return td->trigger(td);
+		else
+			return default_trigger(td);
+	} else {
+		return td->run(td, NULL, NULL);
+	}
+}
+
+void test_result(struct tdescr *td)
+{
+	if (td->initialized && td->result != KSFT_SKIP && td->check_result)
+		td->check_result(td);
+	default_result(td, 0);
+}
+
+void test_cleanup(struct tdescr *td)
+{
+	if (td->cleanup)
+		td->cleanup(td);
+}
diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.h b/tools/testing/selftests/arm64/signal/test_signals_utils.h
new file mode 100644
index 000000000000..6772b5c8d274
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/test_signals_utils.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 ARM Limited */
+
+#ifndef __TEST_SIGNALS_UTILS_H__
+#define __TEST_SIGNALS_UTILS_H__
+
+#include <assert.h>
+#include <stdio.h>
+#include <string.h>
+
+#include "test_signals.h"
+
+int test_init(struct tdescr *td);
+int test_setup(struct tdescr *td);
+void test_cleanup(struct tdescr *td);
+int test_run(struct tdescr *td);
+void test_result(struct tdescr *td);
+
+static inline bool feats_ok(struct tdescr *td)
+{
+	return (td->feats_required & td->feats_supported) == td->feats_required;
+}
+
+/*
+ * Obtaining a valid and full-blown ucontext_t from userspace is tricky:
+ * libc getcontext does() not save all the regs and messes with some of
+ * them (pstate value in particular is not reliable).
+ *
+ * Here we use a service signal to grab the ucontext_t from inside a
+ * dedicated signal handler, since there, it is populated by Kernel
+ * itself in setup_sigframe(). The grabbed context is then stored and
+ * made available in td->live_uc.
+ *
+ * As service-signal is used a SIGTRAP induced by a 'brk' instruction,
+ * because here we have to avoid syscalls to trigger the signal since
+ * they would cause any SVE sigframe content (if any) to be removed.
+ *
+ * Anyway this function really serves a dual purpose:
+ *
+ * 1. grab a valid sigcontext into td->live_uc for result analysis: in
+ * such case it returns 1.
+ *
+ * 2. detect if, somehow, a previously grabbed live_uc context has been
+ * used actively with a sigreturn: in such a case the execution would have
+ * magically resumed in the middle of this function itself (seen_already==1):
+ * in such a case return 0, since in fact we have not just simply grabbed
+ * the context.
+ *
+ * This latter case is useful to detect when a fake_sigreturn test-case has
+ * unexpectedly survived without hitting a SEGV.
+ *
+ * Note that the case of runtime dynamically sized sigframes (like in SVE
+ * context) is still NOT addressed: sigframe size is supposed to be fixed
+ * at sizeof(ucontext_t).
+ */
+static __always_inline bool get_current_context(struct tdescr *td,
+						ucontext_t *dest_uc)
+{
+	static volatile bool seen_already;
+
+	assert(td && dest_uc);
+	/* it's a genuine invocation..reinit */
+	seen_already = 0;
+	td->live_uc_valid = 0;
+	td->live_sz = sizeof(*dest_uc);
+	memset(dest_uc, 0x00, td->live_sz);
+	td->live_uc = dest_uc;
+	/*
+	 * Grab ucontext_t triggering a SIGTRAP.
+	 *
+	 * Note that:
+	 * - live_uc_valid is declared volatile sig_atomic_t in
+	 *   struct tdescr since it will be changed inside the
+	 *   sig_copyctx handler
+	 * - the additional 'memory' clobber is there to avoid possible
+	 *   compiler's assumption on live_uc_valid and the content
+	 *   pointed by dest_uc, which are all changed inside the signal
+	 *   handler
+	 * - BRK causes a debug exception which is handled by the Kernel
+	 *   and finally causes the SIGTRAP signal to be delivered to this
+	 *   test thread. Since such delivery happens on the ret_to_user()
+	 *   /do_notify_resume() debug exception return-path, we are sure
+	 *   that the registered SIGTRAP handler has been run to completion
+	 *   before the execution path is restored here: as a consequence
+	 *   we can be sure that the volatile sig_atomic_t live_uc_valid
+	 *   carries a meaningful result. Being in a single thread context
+	 *   we'll also be sure that any access to memory modified by the
+	 *   handler (namely ucontext_t) will be visible once returned.
+	 * - note that since we are using a breakpoint instruction here
+	 *   to cause a SIGTRAP, the ucontext_t grabbed from the signal
+	 *   handler would naturally contain a PC pointing exactly to this
+	 *   BRK line, which means that, on return from the signal handler,
+	 *   or if we place the ucontext_t on the stack to fake a sigreturn,
+	 *   we'll end up in an infinite loop of BRK-SIGTRAP-handler.
+	 *   For this reason we take care to artificially move forward the
+	 *   PC to the next instruction while inside the signal handler.
+	 */
+	asm volatile ("brk #666"
+		      : "+m" (*dest_uc)
+		      :
+		      : "memory");
+
+	/*
+	 * If we get here with seen_already==1 it implies the td->live_uc
+	 * context has been used to get back here....this probably means
+	 * a test has failed to cause a SEGV...anyway live_uc does not
+	 * point to a just acquired copy of ucontext_t...so return 0
+	 */
+	if (seen_already) {
+		fprintf(stdout,
+			"Unexpected successful sigreturn detected: live_uc is stale !\n");
+		return 0;
+	}
+	seen_already = 1;
+
+	return td->live_uc_valid;
+}
+
+int fake_sigreturn(void *sigframe, size_t sz, int misalign_bytes);
+#endif
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_magic.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_magic.c
new file mode 100644
index 000000000000..8dc600a7d4fd
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_magic.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Place a fake sigframe on the stack including a BAD Unknown magic
+ * record: on sigreturn Kernel must spot this attempt and the test
+ * case is expected to be terminated via SEGV.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+struct fake_sigframe sf;
+
+static int fake_sigreturn_bad_magic_run(struct tdescr *td,
+					siginfo_t *si, ucontext_t *uc)
+{
+	struct _aarch64_ctx *shead = GET_SF_RESV_HEAD(sf), *head;
+
+	/* just to fill the ucontext_t with something real */
+	if (!get_current_context(td, &sf.uc))
+		return 1;
+
+	/* need at least 2*HDR_SZ space: KSFT_BAD_MAGIC + terminator. */
+	head = get_starting_head(shead, HDR_SZ * 2, GET_SF_RESV_SIZE(sf), NULL);
+	if (!head)
+		return 0;
+
+	/*
+	 * use a well known NON existent bad magic...something
+	 * we should pretty sure won't be ever defined in Kernel
+	 */
+	head->magic = KSFT_BAD_MAGIC;
+	head->size = HDR_SZ;
+	write_terminator_record(GET_RESV_NEXT_HEAD(head));
+
+	ASSERT_BAD_CONTEXT(&sf.uc);
+	fake_sigreturn(&sf, sizeof(sf), 0);
+
+	return 1;
+}
+
+struct tdescr tde = {
+		.name = "FAKE_SIGRETURN_BAD_MAGIC",
+		.descr = "Trigger a sigreturn with a sigframe with a bad magic",
+		.sig_ok = SIGSEGV,
+		.timeout = 3,
+		.run = fake_sigreturn_bad_magic_run,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size.c
new file mode 100644
index 000000000000..b3c362100666
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Place a fake sigframe on the stack including a bad record overflowing
+ * the __reserved space: on sigreturn Kernel must spot this attempt and
+ * the test case is expected to be terminated via SEGV.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+struct fake_sigframe sf;
+
+#define MIN_SZ_ALIGN	16
+
+static int fake_sigreturn_bad_size_run(struct tdescr *td,
+				       siginfo_t *si, ucontext_t *uc)
+{
+	size_t resv_sz, need_sz, offset;
+	struct _aarch64_ctx *shead = GET_SF_RESV_HEAD(sf), *head;
+
+	/* just to fill the ucontext_t with something real */
+	if (!get_current_context(td, &sf.uc))
+		return 1;
+
+	resv_sz = GET_SF_RESV_SIZE(sf);
+	/* at least HDR_SZ + bad sized esr_context needed */
+	need_sz = sizeof(struct esr_context) + HDR_SZ;
+	head = get_starting_head(shead, need_sz, resv_sz, &offset);
+	if (!head)
+		return 0;
+
+	/*
+	 * Use an esr_context to build a fake header with a
+	 * size greater then the free __reserved area minus HDR_SZ;
+	 * using ESR_MAGIC here since it is not checked for size nor
+	 * is limited to one instance.
+	 *
+	 * At first inject an additional normal esr_context
+	 */
+	head->magic = ESR_MAGIC;
+	head->size = sizeof(struct esr_context);
+	/* and terminate properly */
+	write_terminator_record(GET_RESV_NEXT_HEAD(head));
+	ASSERT_GOOD_CONTEXT(&sf.uc);
+
+	/*
+	 * now mess with fake esr_context size: leaving less space than
+	 * needed while keeping size value 16-aligned
+	 *
+	 * It must trigger a SEGV from Kernel on:
+	 *
+	 *	resv_sz - offset < sizeof(*head)
+	 */
+	/* at first set the maximum good 16-aligned size */
+	head->size = (resv_sz - offset - need_sz + MIN_SZ_ALIGN) & ~0xfUL;
+	/* plus a bit more of 16-aligned sized stuff */
+	head->size += MIN_SZ_ALIGN;
+	/* and terminate properly */
+	write_terminator_record(GET_RESV_NEXT_HEAD(head));
+	ASSERT_BAD_CONTEXT(&sf.uc);
+	fake_sigreturn(&sf, sizeof(sf), 0);
+
+	return 1;
+}
+
+struct tdescr tde = {
+		.name = "FAKE_SIGRETURN_BAD_SIZE",
+		.descr = "Triggers a sigreturn with a overrun __reserved area",
+		.sig_ok = SIGSEGV,
+		.timeout = 3,
+		.run = fake_sigreturn_bad_size_run,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size_for_magic0.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size_for_magic0.c
new file mode 100644
index 000000000000..a44b88bfc81a
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size_for_magic0.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Place a fake sigframe on the stack including a badly sized terminator
+ * record: on sigreturn Kernel must spot this attempt and the test case
+ * is expected to be terminated via SEGV.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+struct fake_sigframe sf;
+
+static int fake_sigreturn_bad_size_for_magic0_run(struct tdescr *td,
+						  siginfo_t *si, ucontext_t *uc)
+{
+	struct _aarch64_ctx *shead = GET_SF_RESV_HEAD(sf), *head;
+
+	/* just to fill the ucontext_t with something real */
+	if (!get_current_context(td, &sf.uc))
+		return 1;
+
+	/* at least HDR_SZ for the badly sized terminator. */
+	head = get_starting_head(shead, HDR_SZ, GET_SF_RESV_SIZE(sf), NULL);
+	if (!head)
+		return 0;
+
+	head->magic = 0;
+	head->size = HDR_SZ;
+	ASSERT_BAD_CONTEXT(&sf.uc);
+	fake_sigreturn(&sf, sizeof(sf), 0);
+
+	return 1;
+}
+
+struct tdescr tde = {
+		.name = "FAKE_SIGRETURN_BAD_SIZE_FOR_TERMINATOR",
+		.descr = "Trigger a sigreturn using non-zero size terminator",
+		.sig_ok = SIGSEGV,
+		.timeout = 3,
+		.run = fake_sigreturn_bad_size_for_magic0_run,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_duplicated_fpsimd.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_duplicated_fpsimd.c
new file mode 100644
index 000000000000..afe8915f0998
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_duplicated_fpsimd.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Place a fake sigframe on the stack including an additional FPSIMD
+ * record: on sigreturn Kernel must spot this attempt and the test
+ * case is expected to be terminated via SEGV.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+struct fake_sigframe sf;
+
+static int fake_sigreturn_duplicated_fpsimd_run(struct tdescr *td,
+						siginfo_t *si, ucontext_t *uc)
+{
+	struct _aarch64_ctx *shead = GET_SF_RESV_HEAD(sf), *head;
+
+	/* just to fill the ucontext_t with something real */
+	if (!get_current_context(td, &sf.uc))
+		return 1;
+
+	head = get_starting_head(shead, sizeof(struct fpsimd_context) + HDR_SZ,
+				 GET_SF_RESV_SIZE(sf), NULL);
+	if (!head)
+		return 0;
+
+	/* Add a spurious fpsimd_context */
+	head->magic = FPSIMD_MAGIC;
+	head->size = sizeof(struct fpsimd_context);
+	/* and terminate */
+	write_terminator_record(GET_RESV_NEXT_HEAD(head));
+
+	ASSERT_BAD_CONTEXT(&sf.uc);
+	fake_sigreturn(&sf, sizeof(sf), 0);
+
+	return 1;
+}
+
+struct tdescr tde = {
+		.name = "FAKE_SIGRETURN_DUPLICATED_FPSIMD",
+		.descr = "Triggers a sigreturn including two fpsimd_context",
+		.sig_ok = SIGSEGV,
+		.timeout = 3,
+		.run = fake_sigreturn_duplicated_fpsimd_run,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_misaligned_sp.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_misaligned_sp.c
new file mode 100644
index 000000000000..1e089e66f9f3
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_misaligned_sp.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Place a fake sigframe on the stack at a misaligned SP: on sigreturn
+ * Kernel must spot this attempt and the test case is expected to be
+ * terminated via SEGV.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+struct fake_sigframe sf;
+
+static int fake_sigreturn_misaligned_run(struct tdescr *td,
+					 siginfo_t *si, ucontext_t *uc)
+{
+	/* just to fill the ucontext_t with something real */
+	if (!get_current_context(td, &sf.uc))
+		return 1;
+
+	/* Forcing sigframe on misaligned SP (16 + 3) */
+	fake_sigreturn(&sf, sizeof(sf), 3);
+
+	return 1;
+}
+
+struct tdescr tde = {
+		.name = "FAKE_SIGRETURN_MISALIGNED_SP",
+		.descr = "Triggers a sigreturn with a misaligned sigframe",
+		.sig_ok = SIGSEGV,
+		.timeout = 3,
+		.run = fake_sigreturn_misaligned_run,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_missing_fpsimd.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_missing_fpsimd.c
new file mode 100644
index 000000000000..08ecd8073a1a
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_missing_fpsimd.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Place a fake sigframe on the stack missing the mandatory FPSIMD
+ * record: on sigreturn Kernel must spot this attempt and the test
+ * case is expected to be terminated via SEGV.
+ */
+
+#include <stdio.h>
+#include <signal.h>
+#include <ucontext.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+struct fake_sigframe sf;
+
+static int fake_sigreturn_missing_fpsimd_run(struct tdescr *td,
+					     siginfo_t *si, ucontext_t *uc)
+{
+	size_t resv_sz, offset;
+	struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf);
+
+	/* just to fill the ucontext_t with something real */
+	if (!get_current_context(td, &sf.uc))
+		return 1;
+
+	resv_sz = GET_SF_RESV_SIZE(sf);
+	head = get_header(head, FPSIMD_MAGIC, resv_sz, &offset);
+	if (head && resv_sz - offset >= HDR_SZ) {
+		fprintf(stderr, "Mangling template header. Spare space:%zd\n",
+			resv_sz - offset);
+		/* Just overwrite fpsmid_context */
+		write_terminator_record(head);
+
+		ASSERT_BAD_CONTEXT(&sf.uc);
+		fake_sigreturn(&sf, sizeof(sf), 0);
+	}
+
+	return 1;
+}
+
+struct tdescr tde = {
+		.name = "FAKE_SIGRETURN_MISSING_FPSIMD",
+		.descr = "Triggers a sigreturn with a missing fpsimd_context",
+		.sig_ok = SIGSEGV,
+		.timeout = 3,
+		.run = fake_sigreturn_missing_fpsimd_run,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_compat_toggle.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_compat_toggle.c
new file mode 100644
index 000000000000..2cb118b0ba05
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_compat_toggle.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Try to mangle the ucontext from inside a signal handler, toggling
+ * the execution state bit: this attempt must be spotted by Kernel and
+ * the test case is expected to be terminated via SEGV.
+ */
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static int mangle_invalid_pstate_run(struct tdescr *td, siginfo_t *si,
+				     ucontext_t *uc)
+{
+	ASSERT_GOOD_CONTEXT(uc);
+
+	/* This config should trigger a SIGSEGV by Kernel */
+	uc->uc_mcontext.pstate ^= PSR_MODE32_BIT;
+
+	return 1;
+}
+
+struct tdescr tde = {
+		.sanity_disabled = true,
+		.name = "MANGLE_PSTATE_INVALID_STATE_TOGGLE",
+		.descr = "Mangling uc_mcontext with INVALID STATE_TOGGLE",
+		.sig_trig = SIGUSR1,
+		.sig_ok = SIGSEGV,
+		.run = mangle_invalid_pstate_run,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_daif_bits.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_daif_bits.c
new file mode 100644
index 000000000000..434b82597007
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_daif_bits.c
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Try to mangle the ucontext from inside a signal handler, mangling the
+ * DAIF bits in an illegal manner: this attempt must be spotted by Kernel
+ * and the test case is expected to be terminated via SEGV.
+ *
+ */
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static int mangle_invalid_pstate_run(struct tdescr *td, siginfo_t *si,
+				     ucontext_t *uc)
+{
+	ASSERT_GOOD_CONTEXT(uc);
+
+	/*
+	 * This config should trigger a SIGSEGV by Kernel when it checks
+	 * the sigframe consistency in valid_user_regs() routine.
+	 */
+	uc->uc_mcontext.pstate |= PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT;
+
+	return 1;
+}
+
+struct tdescr tde = {
+		.sanity_disabled = true,
+		.name = "MANGLE_PSTATE_INVALID_DAIF_BITS",
+		.descr = "Mangling uc_mcontext with INVALID DAIF_BITS",
+		.sig_trig = SIGUSR1,
+		.sig_ok = SIGSEGV,
+		.run = mangle_invalid_pstate_run,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el1h.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el1h.c
new file mode 100644
index 000000000000..95f821abdf46
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el1h.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Try to mangle the ucontext from inside a signal handler, toggling
+ * the mode bit to escalate exception level: this attempt must be spotted
+ * by Kernel and the test case is expected to be termninated via SEGV.
+ */
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+#include "mangle_pstate_invalid_mode_template.h"
+
+DEFINE_TESTCASE_MANGLE_PSTATE_INVALID_MODE(1h);
diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el1t.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el1t.c
new file mode 100644
index 000000000000..cc222d8a618a
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el1t.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Try to mangle the ucontext from inside a signal handler, toggling
+ * the mode bit to escalate exception level: this attempt must be spotted
+ * by Kernel and the test case is expected to be termninated via SEGV.
+ */
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+#include "mangle_pstate_invalid_mode_template.h"
+
+DEFINE_TESTCASE_MANGLE_PSTATE_INVALID_MODE(1t);
diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el2h.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el2h.c
new file mode 100644
index 000000000000..2188add7d28c
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el2h.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Try to mangle the ucontext from inside a signal handler, toggling
+ * the mode bit to escalate exception level: this attempt must be spotted
+ * by Kernel and the test case is expected to be termninated via SEGV.
+ */
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+#include "mangle_pstate_invalid_mode_template.h"
+
+DEFINE_TESTCASE_MANGLE_PSTATE_INVALID_MODE(2h);
diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el2t.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el2t.c
new file mode 100644
index 000000000000..df32dd5a479c
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el2t.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Try to mangle the ucontext from inside a signal handler, toggling
+ * the mode bit to escalate exception level: this attempt must be spotted
+ * by Kernel and the test case is expected to be termninated via SEGV.
+ */
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+#include "mangle_pstate_invalid_mode_template.h"
+
+DEFINE_TESTCASE_MANGLE_PSTATE_INVALID_MODE(2t);
diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el3h.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el3h.c
new file mode 100644
index 000000000000..9e6829b7e5db
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el3h.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Try to mangle the ucontext from inside a signal handler, toggling
+ * the mode bit to escalate exception level: this attempt must be spotted
+ * by Kernel and the test case is expected to be termninated via SEGV.
+ */
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+#include "mangle_pstate_invalid_mode_template.h"
+
+DEFINE_TESTCASE_MANGLE_PSTATE_INVALID_MODE(3h);
diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el3t.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el3t.c
new file mode 100644
index 000000000000..5685a4f10d06
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el3t.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Try to mangle the ucontext from inside a signal handler, toggling
+ * the mode bit to escalate exception level: this attempt must be spotted
+ * by Kernel and the test case is expected to be termninated via SEGV.
+ */
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+#include "mangle_pstate_invalid_mode_template.h"
+
+DEFINE_TESTCASE_MANGLE_PSTATE_INVALID_MODE(3t);
diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_template.h b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_template.h
new file mode 100644
index 000000000000..f5bf1804d858
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_template.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 ARM Limited
+ *
+ * Utility macro to ease definition of testcases toggling mode EL
+ */
+
+#define DEFINE_TESTCASE_MANGLE_PSTATE_INVALID_MODE(_mode)		\
+									\
+static int mangle_invalid_pstate_run(struct tdescr *td, siginfo_t *si,	\
+				     ucontext_t *uc)			\
+{									\
+	ASSERT_GOOD_CONTEXT(uc);					\
+									\
+	uc->uc_mcontext.pstate &= ~PSR_MODE_MASK;			\
+	uc->uc_mcontext.pstate |= PSR_MODE_EL ## _mode;			\
+									\
+	return 1;							\
+}									\
+									\
+struct tdescr tde = {							\
+		.sanity_disabled = true,				\
+		.name = "MANGLE_PSTATE_INVALID_MODE_EL"#_mode,		\
+		.descr = "Mangling uc_mcontext INVALID MODE EL"#_mode,	\
+		.sig_trig = SIGUSR1,					\
+		.sig_ok = SIGSEGV,					\
+		.run = mangle_invalid_pstate_run,			\
+}
diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c
new file mode 100644
index 000000000000..61ebcdf63831
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/testcases.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2019 ARM Limited */
+#include "testcases.h"
+
+struct _aarch64_ctx *get_header(struct _aarch64_ctx *head, uint32_t magic,
+				size_t resv_sz, size_t *offset)
+{
+	size_t offs = 0;
+	struct _aarch64_ctx *found = NULL;
+
+	if (!head || resv_sz < HDR_SZ)
+		return found;
+
+	while (offs <= resv_sz - HDR_SZ &&
+	       head->magic != magic && head->magic) {
+		offs += head->size;
+		head = GET_RESV_NEXT_HEAD(head);
+	}
+	if (head->magic == magic) {
+		found = head;
+		if (offset)
+			*offset = offs;
+	}
+
+	return found;
+}
+
+bool validate_extra_context(struct extra_context *extra, char **err)
+{
+	struct _aarch64_ctx *term;
+
+	if (!extra || !err)
+		return false;
+
+	fprintf(stderr, "Validating EXTRA...\n");
+	term = GET_RESV_NEXT_HEAD(extra);
+	if (!term || term->magic || term->size) {
+		*err = "Missing terminator after EXTRA context";
+		return false;
+	}
+	if (extra->datap & 0x0fUL)
+		*err = "Extra DATAP misaligned";
+	else if (extra->size & 0x0fUL)
+		*err = "Extra SIZE misaligned";
+	else if (extra->datap != (uint64_t)term + sizeof(*term))
+		*err = "Extra DATAP misplaced (not contiguous)";
+	if (*err)
+		return false;
+
+	return true;
+}
+
+bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
+{
+	bool terminated = false;
+	size_t offs = 0;
+	int flags = 0;
+	struct extra_context *extra = NULL;
+	struct _aarch64_ctx *head =
+		(struct _aarch64_ctx *)uc->uc_mcontext.__reserved;
+
+	if (!err)
+		return false;
+	/* Walk till the end terminator verifying __reserved contents */
+	while (head && !terminated && offs < resv_sz) {
+		if ((uint64_t)head & 0x0fUL) {
+			*err = "Misaligned HEAD";
+			return false;
+		}
+
+		switch (head->magic) {
+		case 0:
+			if (head->size)
+				*err = "Bad size for terminator";
+			else
+				terminated = true;
+			break;
+		case FPSIMD_MAGIC:
+			if (flags & FPSIMD_CTX)
+				*err = "Multiple FPSIMD_MAGIC";
+			else if (head->size !=
+				 sizeof(struct fpsimd_context))
+				*err = "Bad size for fpsimd_context";
+			flags |= FPSIMD_CTX;
+			break;
+		case ESR_MAGIC:
+			if (head->size != sizeof(struct esr_context))
+				*err = "Bad size for esr_context";
+			break;
+		case SVE_MAGIC:
+			if (flags & SVE_CTX)
+				*err = "Multiple SVE_MAGIC";
+			else if (head->size !=
+				 sizeof(struct sve_context))
+				*err = "Bad size for sve_context";
+			flags |= SVE_CTX;
+			break;
+		case EXTRA_MAGIC:
+			if (flags & EXTRA_CTX)
+				*err = "Multiple EXTRA_MAGIC";
+			else if (head->size !=
+				 sizeof(struct extra_context))
+				*err = "Bad size for extra_context";
+			flags |= EXTRA_CTX;
+			extra = (struct extra_context *)head;
+			break;
+		case KSFT_BAD_MAGIC:
+			/*
+			 * This is a BAD magic header defined
+			 * artificially by a testcase and surely
+			 * unknown to the Kernel parse_user_sigframe().
+			 * It MUST cause a Kernel induced SEGV
+			 */
+			*err = "BAD MAGIC !";
+			break;
+		default:
+			/*
+			 * A still unknown Magic: potentially freshly added
+			 * to the Kernel code and still unknown to the
+			 * tests.
+			 */
+			fprintf(stdout,
+				"SKIP Unknown MAGIC: 0x%X - Is KSFT arm64/signal up to date ?\n",
+				head->magic);
+			break;
+		}
+
+		if (*err)
+			return false;
+
+		offs += head->size;
+		if (resv_sz < offs + sizeof(*head)) {
+			*err = "HEAD Overrun";
+			return false;
+		}
+
+		if (flags & EXTRA_CTX)
+			if (!validate_extra_context(extra, err))
+				return false;
+
+		head = GET_RESV_NEXT_HEAD(head);
+	}
+
+	if (terminated && !(flags & FPSIMD_CTX)) {
+		*err = "Missing FPSIMD";
+		return false;
+	}
+
+	return true;
+}
+
+/*
+ * This function walks through the records inside the provided reserved area
+ * trying to find enough space to fit @need_sz bytes: if not enough space is
+ * available and an extra_context record is present, it throws away the
+ * extra_context record.
+ *
+ * It returns a pointer to a new header where it is possible to start storing
+ * our need_sz bytes.
+ *
+ * @shead: points to the start of reserved area
+ * @need_sz: needed bytes
+ * @resv_sz: reserved area size in bytes
+ * @offset: if not null, this will be filled with the offset of the return
+ *	    head pointer from @shead
+ *
+ * @return: pointer to a new head where to start storing need_sz bytes, or
+ *	    NULL if space could not be made available.
+ */
+struct _aarch64_ctx *get_starting_head(struct _aarch64_ctx *shead,
+				       size_t need_sz, size_t resv_sz,
+				       size_t *offset)
+{
+	size_t offs = 0;
+	struct _aarch64_ctx *head;
+
+	head = get_terminator(shead, resv_sz, &offs);
+	/* not found a terminator...no need to update offset if any */
+	if (!head)
+		return head;
+	if (resv_sz - offs < need_sz) {
+		fprintf(stderr, "Low on space:%zd. Discarding extra_context.\n",
+			resv_sz - offs);
+		head = get_header(shead, EXTRA_MAGIC, resv_sz, &offs);
+		if (!head || resv_sz - offs < need_sz) {
+			fprintf(stderr,
+				"Failed to reclaim space on sigframe.\n");
+			return NULL;
+		}
+	}
+
+	fprintf(stderr, "Available space:%zd\n", resv_sz - offs);
+	if (offset)
+		*offset = offs;
+	return head;
+}
diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.h b/tools/testing/selftests/arm64/signal/testcases/testcases.h
new file mode 100644
index 000000000000..ad884c135314
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/testcases.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 ARM Limited */
+#ifndef __TESTCASES_H__
+#define __TESTCASES_H__
+
+#include <stddef.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <ucontext.h>
+#include <signal.h>
+
+/* Architecture specific sigframe definitions */
+#include <asm/sigcontext.h>
+
+#define FPSIMD_CTX	(1 << 0)
+#define SVE_CTX		(1 << 1)
+#define EXTRA_CTX	(1 << 2)
+
+#define KSFT_BAD_MAGIC	0xdeadbeef
+
+#define HDR_SZ \
+	sizeof(struct _aarch64_ctx)
+
+#define GET_SF_RESV_HEAD(sf) \
+	(struct _aarch64_ctx *)(&(sf).uc.uc_mcontext.__reserved)
+
+#define GET_SF_RESV_SIZE(sf) \
+	sizeof((sf).uc.uc_mcontext.__reserved)
+
+#define GET_UCP_RESV_SIZE(ucp) \
+	sizeof((ucp)->uc_mcontext.__reserved)
+
+#define ASSERT_BAD_CONTEXT(uc) do {					\
+	char *err = NULL;						\
+	if (!validate_reserved((uc), GET_UCP_RESV_SIZE((uc)), &err)) {	\
+		if (err)						\
+			fprintf(stderr,					\
+				"Using badly built context - ERR: %s\n",\
+				err);					\
+	} else {							\
+		abort();						\
+	}								\
+} while (0)
+
+#define ASSERT_GOOD_CONTEXT(uc) do {					 \
+	char *err = NULL;						 \
+	if (!validate_reserved((uc), GET_UCP_RESV_SIZE((uc)), &err)) {	 \
+		if (err)						 \
+			fprintf(stderr,					 \
+				"Detected BAD context - ERR: %s\n", err);\
+		abort();						 \
+	} else {							 \
+		fprintf(stderr, "uc context validated.\n");		 \
+	}								 \
+} while (0)
+
+/*
+ * A simple record-walker for __reserved area: it walks through assuming
+ * only to find a proper struct __aarch64_ctx header descriptor.
+ *
+ * Instead it makes no assumptions on the content and ordering of the
+ * records, any needed bounds checking must be enforced by the caller
+ * if wanted: this way can be used by caller on any maliciously built bad
+ * contexts.
+ *
+ * head->size accounts both for payload and header _aarch64_ctx size !
+ */
+#define GET_RESV_NEXT_HEAD(h) \
+	(struct _aarch64_ctx *)((char *)(h) + (h)->size)
+
+struct fake_sigframe {
+	siginfo_t	info;
+	ucontext_t	uc;
+};
+
+
+bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err);
+
+bool validate_extra_context(struct extra_context *extra, char **err);
+
+struct _aarch64_ctx *get_header(struct _aarch64_ctx *head, uint32_t magic,
+				size_t resv_sz, size_t *offset);
+
+static inline struct _aarch64_ctx *get_terminator(struct _aarch64_ctx *head,
+						  size_t resv_sz,
+						  size_t *offset)
+{
+	return get_header(head, 0, resv_sz, offset);
+}
+
+static inline void write_terminator_record(struct _aarch64_ctx *tail)
+{
+	if (tail) {
+		tail->magic = 0;
+		tail->size = 0;
+	}
+}
+
+struct _aarch64_ctx *get_starting_head(struct _aarch64_ctx *shead,
+				       size_t need_sz, size_t resv_sz,
+				       size_t *offset);
+#endif
diff --git a/tools/testing/selftests/arm64/.gitignore b/tools/testing/selftests/arm64/tags/.gitignore
index e8fae8d61ed6..e8fae8d61ed6 100644
--- a/tools/testing/selftests/arm64/.gitignore
+++ b/tools/testing/selftests/arm64/tags/.gitignore
diff --git a/tools/testing/selftests/arm64/tags/Makefile b/tools/testing/selftests/arm64/tags/Makefile
new file mode 100644
index 000000000000..41cb75070511
--- /dev/null
+++ b/tools/testing/selftests/arm64/tags/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+
+CFLAGS += -I../../../../../usr/include/
+TEST_GEN_PROGS := tags_test
+TEST_PROGS := run_tags_test.sh
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/arm64/run_tags_test.sh b/tools/testing/selftests/arm64/tags/run_tags_test.sh
index 745f11379930..745f11379930 100755
--- a/tools/testing/selftests/arm64/run_tags_test.sh
+++ b/tools/testing/selftests/arm64/tags/run_tags_test.sh
diff --git a/tools/testing/selftests/arm64/tags_test.c b/tools/testing/selftests/arm64/tags/tags_test.c
index 5701163460ef..5701163460ef 100644
--- a/tools/testing/selftests/arm64/tags_test.c
+++ b/tools/testing/selftests/arm64/tags/tags_test.c
diff --git a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c
index 58ed5eeab709..ad41ea69001b 100644
--- a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c
+++ b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c
@@ -109,7 +109,7 @@ static bool set_watchpoint(pid_t pid, int size, int wp)
 	return false;
 }
 
-static bool arun_test(int wr_size, int wp_size, int wr, int wp)
+static bool run_test(int wr_size, int wp_size, int wr, int wp)
 {
 	int status;
 	siginfo_t siginfo;
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
index 8d369b6a2069..66aafe1f5746 100644
--- a/tools/testing/selftests/cgroup/Makefile
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -1,8 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
-CFLAGS += -Wall
+CFLAGS += -Wall -pthread
 
 all:
 
+TEST_FILES     := with_stress.sh
+TEST_PROGS     := test_stress.sh
 TEST_GEN_PROGS = test_memcontrol
 TEST_GEN_PROGS += test_core
 TEST_GEN_PROGS += test_freezer
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index bdb69599c4bd..8f7131dcf1ff 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -158,6 +158,22 @@ long cg_read_key_long(const char *cgroup, const char *control, const char *key)
 	return atol(ptr + strlen(key));
 }
 
+long cg_read_lc(const char *cgroup, const char *control)
+{
+	char buf[PAGE_SIZE];
+	const char delim[] = "\n";
+	char *line;
+	long cnt = 0;
+
+	if (cg_read(cgroup, control, buf, sizeof(buf)))
+		return -1;
+
+	for (line = strtok(buf, delim); line; line = strtok(NULL, delim))
+		cnt++;
+
+	return cnt;
+}
+
 int cg_write(const char *cgroup, const char *control, char *buf)
 {
 	char path[PATH_MAX];
@@ -282,10 +298,12 @@ int cg_enter(const char *cgroup, int pid)
 
 int cg_enter_current(const char *cgroup)
 {
-	char pidbuf[64];
+	return cg_write(cgroup, "cgroup.procs", "0");
+}
 
-	snprintf(pidbuf, sizeof(pidbuf), "%d", getpid());
-	return cg_write(cgroup, "cgroup.procs", pidbuf);
+int cg_enter_current_thread(const char *cgroup)
+{
+	return cg_write(cgroup, "cgroup.threads", "0");
 }
 
 int cg_run(const char *cgroup,
@@ -410,11 +428,25 @@ int set_oom_adj_score(int pid, int score)
 	return 0;
 }
 
-char proc_read_text(int pid, const char *item, char *buf, size_t size)
+ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size)
 {
 	char path[PATH_MAX];
 
-	snprintf(path, sizeof(path), "/proc/%d/%s", pid, item);
+	if (!pid)
+		snprintf(path, sizeof(path), "/proc/%s/%s",
+			 thread ? "thread-self" : "self", item);
+	else
+		snprintf(path, sizeof(path), "/proc/%d/%s", pid, item);
 
 	return read_text(path, buf, size);
 }
+
+int proc_read_strstr(int pid, bool thread, const char *item, const char *needle)
+{
+	char buf[PAGE_SIZE];
+
+	if (proc_read_text(pid, thread, item, buf, sizeof(buf)) < 0)
+		return -1;
+
+	return strstr(buf, needle) ? 0 : -1;
+}
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h
index c72f28046bfa..49c54fbdb229 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/cgroup_util.h
@@ -1,4 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#include <stdbool.h>
 #include <stdlib.h>
 
 #define PAGE_SIZE 4096
@@ -29,12 +30,14 @@ extern int cg_read_strstr(const char *cgroup, const char *control,
 			  const char *needle);
 extern long cg_read_long(const char *cgroup, const char *control);
 long cg_read_key_long(const char *cgroup, const char *control, const char *key);
+extern long cg_read_lc(const char *cgroup, const char *control);
 extern int cg_write(const char *cgroup, const char *control, char *buf);
 extern int cg_run(const char *cgroup,
 		  int (*fn)(const char *cgroup, void *arg),
 		  void *arg);
 extern int cg_enter(const char *cgroup, int pid);
 extern int cg_enter_current(const char *cgroup);
+extern int cg_enter_current_thread(const char *cgroup);
 extern int cg_run_nowait(const char *cgroup,
 			 int (*fn)(const char *cgroup, void *arg),
 			 void *arg);
@@ -45,4 +48,5 @@ extern int is_swap_enabled(void);
 extern int set_oom_adj_score(int pid, int score);
 extern int cg_wait_for_proc_count(const char *cgroup, int count);
 extern int cg_killall(const char *cgroup);
-extern char proc_read_text(int pid, const char *item, char *buf, size_t size);
+extern ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size);
+extern int proc_read_strstr(int pid, bool thread, const char *item, const char *needle);
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index 79053a4f4783..c5ca669feb2b 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -5,6 +5,9 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <errno.h>
+#include <signal.h>
+#include <string.h>
+#include <pthread.h>
 
 #include "../kselftest.h"
 #include "cgroup_util.h"
@@ -354,6 +357,147 @@ cleanup:
 	return ret;
 }
 
+static void *dummy_thread_fn(void *arg)
+{
+	return (void *)(size_t)pause();
+}
+
+/*
+ * Test threadgroup migration.
+ * All threads of a process are migrated together.
+ */
+static int test_cgcore_proc_migration(const char *root)
+{
+	int ret = KSFT_FAIL;
+	int t, c_threads, n_threads = 13;
+	char *src = NULL, *dst = NULL;
+	pthread_t threads[n_threads];
+
+	src = cg_name(root, "cg_src");
+	dst = cg_name(root, "cg_dst");
+	if (!src || !dst)
+		goto cleanup;
+
+	if (cg_create(src))
+		goto cleanup;
+	if (cg_create(dst))
+		goto cleanup;
+
+	if (cg_enter_current(src))
+		goto cleanup;
+
+	for (c_threads = 0; c_threads < n_threads; ++c_threads) {
+		if (pthread_create(&threads[c_threads], NULL, dummy_thread_fn, NULL))
+			goto cleanup;
+	}
+
+	cg_enter_current(dst);
+	if (cg_read_lc(dst, "cgroup.threads") != n_threads + 1)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	for (t = 0; t < c_threads; ++t) {
+		pthread_cancel(threads[t]);
+	}
+
+	for (t = 0; t < c_threads; ++t) {
+		pthread_join(threads[t], NULL);
+	}
+
+	cg_enter_current(root);
+
+	if (dst)
+		cg_destroy(dst);
+	if (src)
+		cg_destroy(src);
+	free(dst);
+	free(src);
+	return ret;
+}
+
+static void *migrating_thread_fn(void *arg)
+{
+	int g, i, n_iterations = 1000;
+	char **grps = arg;
+	char lines[3][PATH_MAX];
+
+	for (g = 1; g < 3; ++g)
+		snprintf(lines[g], sizeof(lines[g]), "0::%s", grps[g] + strlen(grps[0]));
+
+	for (i = 0; i < n_iterations; ++i) {
+		cg_enter_current_thread(grps[(i % 2) + 1]);
+
+		if (proc_read_strstr(0, 1, "cgroup", lines[(i % 2) + 1]))
+			return (void *)-1;
+	}
+	return NULL;
+}
+
+/*
+ * Test single thread migration.
+ * Threaded cgroups allow successful migration of a thread.
+ */
+static int test_cgcore_thread_migration(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *dom = NULL;
+	char line[PATH_MAX];
+	char *grps[3] = { (char *)root, NULL, NULL };
+	pthread_t thr;
+	void *retval;
+
+	dom = cg_name(root, "cg_dom");
+	grps[1] = cg_name(root, "cg_dom/cg_src");
+	grps[2] = cg_name(root, "cg_dom/cg_dst");
+	if (!grps[1] || !grps[2] || !dom)
+		goto cleanup;
+
+	if (cg_create(dom))
+		goto cleanup;
+	if (cg_create(grps[1]))
+		goto cleanup;
+	if (cg_create(grps[2]))
+		goto cleanup;
+
+	if (cg_write(grps[1], "cgroup.type", "threaded"))
+		goto cleanup;
+	if (cg_write(grps[2], "cgroup.type", "threaded"))
+		goto cleanup;
+
+	if (cg_enter_current(grps[1]))
+		goto cleanup;
+
+	if (pthread_create(&thr, NULL, migrating_thread_fn, grps))
+		goto cleanup;
+
+	if (pthread_join(thr, &retval))
+		goto cleanup;
+
+	if (retval)
+		goto cleanup;
+
+	snprintf(line, sizeof(line), "0::%s", grps[1] + strlen(grps[0]));
+	if (proc_read_strstr(0, 1, "cgroup", line))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_enter_current(root);
+	if (grps[2])
+		cg_destroy(grps[2]);
+	if (grps[1])
+		cg_destroy(grps[1]);
+	if (dom)
+		cg_destroy(dom);
+	free(grps[2]);
+	free(grps[1]);
+	free(dom);
+	return ret;
+}
+
 #define T(x) { x, #x }
 struct corecg_test {
 	int (*fn)(const char *root);
@@ -366,6 +510,8 @@ struct corecg_test {
 	T(test_cgcore_parent_becomes_threaded),
 	T(test_cgcore_invalid_domain),
 	T(test_cgcore_populated),
+	T(test_cgcore_proc_migration),
+	T(test_cgcore_thread_migration),
 };
 #undef T
 
diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c
index 0fc1b6d4b0f9..23d8fa4a3e4e 100644
--- a/tools/testing/selftests/cgroup/test_freezer.c
+++ b/tools/testing/selftests/cgroup/test_freezer.c
@@ -72,6 +72,7 @@ static int cg_prepare_for_wait(const char *cgroup)
 	if (ret == -1) {
 		debug("Error: inotify_add_watch() failed\n");
 		close(fd);
+		fd = -1;
 	}
 
 	return fd;
@@ -701,7 +702,7 @@ static int proc_check_stopped(int pid)
 	char buf[PAGE_SIZE];
 	int len;
 
-	len = proc_read_text(pid, "stat", buf, sizeof(buf));
+	len = proc_read_text(pid, 0, "stat", buf, sizeof(buf));
 	if (len == -1) {
 		debug("Can't get %d stat\n", pid);
 		return -1;
diff --git a/tools/testing/selftests/cgroup/test_stress.sh b/tools/testing/selftests/cgroup/test_stress.sh
new file mode 100755
index 000000000000..15d9d5896394
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_stress.sh
@@ -0,0 +1,4 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+./with_stress.sh -s subsys -s fork ./test_core
diff --git a/tools/testing/selftests/cgroup/with_stress.sh b/tools/testing/selftests/cgroup/with_stress.sh
new file mode 100755
index 000000000000..e28c35008f5b
--- /dev/null
+++ b/tools/testing/selftests/cgroup/with_stress.sh
@@ -0,0 +1,101 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+stress_fork()
+{
+	while true ; do
+		/usr/bin/true
+		sleep 0.01
+	done
+}
+
+stress_subsys()
+{
+	local verb=+
+	while true ; do
+		echo $verb$subsys_ctrl >$sysfs/cgroup.subtree_control
+		[ $verb = "+" ] && verb=- || verb=+
+		# incommensurable period with other stresses
+		sleep 0.011
+	done
+}
+
+init_and_check()
+{
+	sysfs=`mount -t cgroup2 | head -1 | awk '{ print $3 }'`
+	if [ ! -d "$sysfs" ]; then
+		echo "Skipping: cgroup2 is not mounted" >&2
+		exit $ksft_skip
+	fi
+
+	if ! echo +$subsys_ctrl >$sysfs/cgroup.subtree_control ; then
+		echo "Skipping: cannot enable $subsys_ctrl in $sysfs" >&2
+		exit $ksft_skip
+	fi
+
+	if ! echo -$subsys_ctrl >$sysfs/cgroup.subtree_control ; then
+		echo "Skipping: cannot disable $subsys_ctrl in $sysfs" >&2
+		exit $ksft_skip
+	fi
+}
+
+declare -a stresses
+declare -a stress_pids
+duration=5
+rc=0
+subsys_ctrl=cpuset
+sysfs=
+
+while getopts c:d:hs: opt; do
+	case $opt in
+	c)
+		subsys_ctrl=$OPTARG
+		;;
+	d)
+		duration=$OPTARG
+		;;
+	h)
+		echo "Usage $0 [ -s stress ] ... [ -d duration ] [-c controller] cmd args .."
+		echo -e "\t default duration $duration seconds"
+		echo -e "\t default controller $subsys_ctrl"
+		exit
+		;;
+	s)
+		func=stress_$OPTARG
+		if [ "x$(type -t $func)" != "xfunction" ] ; then
+			echo "Unknown stress $OPTARG"
+			exit 1
+		fi
+		stresses+=($func)
+		;;
+	esac
+done
+shift $((OPTIND - 1))
+
+init_and_check
+
+for s in ${stresses[*]} ; do
+	$s &
+	stress_pids+=($!)
+done
+
+
+time=0
+start=$(date +%s)
+
+while [ $time -lt $duration ] ; do
+	$*
+	rc=$?
+	[ $rc -eq 0 ] || break
+	time=$(($(date +%s) - $start))
+done
+
+for pid in ${stress_pids[*]} ; do
+	kill -SIGTERM $pid
+	wait $pid
+done
+
+exit $rc
diff --git a/tools/testing/selftests/clone3/.gitignore b/tools/testing/selftests/clone3/.gitignore
new file mode 100644
index 000000000000..0dc4f32c6cb8
--- /dev/null
+++ b/tools/testing/selftests/clone3/.gitignore
@@ -0,0 +1,3 @@
+clone3
+clone3_clear_sighand
+clone3_set_tid
diff --git a/tools/testing/selftests/clone3/Makefile b/tools/testing/selftests/clone3/Makefile
new file mode 100644
index 000000000000..cf976c732906
--- /dev/null
+++ b/tools/testing/selftests/clone3/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -g -I../../../../usr/include/
+
+TEST_GEN_PROGS := clone3 clone3_clear_sighand clone3_set_tid
+
+include ../lib.mk
diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c
new file mode 100644
index 000000000000..f14c269a5a18
--- /dev/null
+++ b/tools/testing/selftests/clone3/clone3.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Based on Christian Brauner's clone3() example */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <inttypes.h>
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <sched.h>
+
+#include "../kselftest.h"
+#include "clone3_selftests.h"
+
+/*
+ * Different sizes of struct clone_args
+ */
+#ifndef CLONE3_ARGS_SIZE_V0
+#define CLONE3_ARGS_SIZE_V0 64
+#endif
+
+enum test_mode {
+	CLONE3_ARGS_NO_TEST,
+	CLONE3_ARGS_ALL_0,
+	CLONE3_ARGS_INVAL_EXIT_SIGNAL_BIG,
+	CLONE3_ARGS_INVAL_EXIT_SIGNAL_NEG,
+	CLONE3_ARGS_INVAL_EXIT_SIGNAL_CSIG,
+	CLONE3_ARGS_INVAL_EXIT_SIGNAL_NSIG,
+};
+
+static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode)
+{
+	struct clone_args args = {
+		.flags = flags,
+		.exit_signal = SIGCHLD,
+	};
+
+	struct clone_args_extended {
+		struct clone_args args;
+		__aligned_u64 excess_space[2];
+	} args_ext;
+
+	pid_t pid = -1;
+	int status;
+
+	memset(&args_ext, 0, sizeof(args_ext));
+	if (size > sizeof(struct clone_args))
+		args_ext.excess_space[1] = 1;
+
+	if (size == 0)
+		size = sizeof(struct clone_args);
+
+	switch (test_mode) {
+	case CLONE3_ARGS_ALL_0:
+		args.flags = 0;
+		args.exit_signal = 0;
+		break;
+	case CLONE3_ARGS_INVAL_EXIT_SIGNAL_BIG:
+		args.exit_signal = 0xbadc0ded00000000ULL;
+		break;
+	case CLONE3_ARGS_INVAL_EXIT_SIGNAL_NEG:
+		args.exit_signal = 0x0000000080000000ULL;
+		break;
+	case CLONE3_ARGS_INVAL_EXIT_SIGNAL_CSIG:
+		args.exit_signal = 0x0000000000000100ULL;
+		break;
+	case CLONE3_ARGS_INVAL_EXIT_SIGNAL_NSIG:
+		args.exit_signal = 0x00000000000000f0ULL;
+		break;
+	}
+
+	memcpy(&args_ext.args, &args, sizeof(struct clone_args));
+
+	pid = sys_clone3((struct clone_args *)&args_ext, size);
+	if (pid < 0) {
+		ksft_print_msg("%s - Failed to create new process\n",
+				strerror(errno));
+		return -errno;
+	}
+
+	if (pid == 0) {
+		ksft_print_msg("I am the child, my PID is %d\n", getpid());
+		_exit(EXIT_SUCCESS);
+	}
+
+	ksft_print_msg("I am the parent (%d). My child's pid is %d\n",
+			getpid(), pid);
+
+	if (waitpid(-1, &status, __WALL) < 0) {
+		ksft_print_msg("Child returned %s\n", strerror(errno));
+		return -errno;
+	}
+	if (WEXITSTATUS(status))
+		return WEXITSTATUS(status);
+
+	return 0;
+}
+
+static void test_clone3(uint64_t flags, size_t size, int expected,
+		       enum test_mode test_mode)
+{
+	int ret;
+
+	ksft_print_msg(
+		"[%d] Trying clone3() with flags %#" PRIx64 " (size %zu)\n",
+		getpid(), flags, size);
+	ret = call_clone3(flags, size, test_mode);
+	ksft_print_msg("[%d] clone3() with flags says: %d expected %d\n",
+			getpid(), ret, expected);
+	if (ret != expected)
+		ksft_test_result_fail(
+			"[%d] Result (%d) is different than expected (%d)\n",
+			getpid(), ret, expected);
+	else
+		ksft_test_result_pass(
+			"[%d] Result (%d) matches expectation (%d)\n",
+			getpid(), ret, expected);
+}
+
+int main(int argc, char *argv[])
+{
+	pid_t pid;
+
+	uid_t uid = getuid();
+
+	test_clone3_supported();
+	ksft_print_header();
+	ksft_set_plan(17);
+
+	/* Just a simple clone3() should return 0.*/
+	test_clone3(0, 0, 0, CLONE3_ARGS_NO_TEST);
+
+	/* Do a clone3() in a new PID NS.*/
+	if (uid == 0)
+		test_clone3(CLONE_NEWPID, 0, 0, CLONE3_ARGS_NO_TEST);
+	else
+		ksft_test_result_skip("Skipping clone3() with CLONE_NEWPID\n");
+
+	/* Do a clone3() with CLONE3_ARGS_SIZE_V0. */
+	test_clone3(0, CLONE3_ARGS_SIZE_V0, 0, CLONE3_ARGS_NO_TEST);
+
+	/* Do a clone3() with CLONE3_ARGS_SIZE_V0 - 8 */
+	test_clone3(0, CLONE3_ARGS_SIZE_V0 - 8, -EINVAL, CLONE3_ARGS_NO_TEST);
+
+	/* Do a clone3() with sizeof(struct clone_args) + 8 */
+	test_clone3(0, sizeof(struct clone_args) + 8, 0, CLONE3_ARGS_NO_TEST);
+
+	/* Do a clone3() with exit_signal having highest 32 bits non-zero */
+	test_clone3(0, 0, -EINVAL, CLONE3_ARGS_INVAL_EXIT_SIGNAL_BIG);
+
+	/* Do a clone3() with negative 32-bit exit_signal */
+	test_clone3(0, 0, -EINVAL, CLONE3_ARGS_INVAL_EXIT_SIGNAL_NEG);
+
+	/* Do a clone3() with exit_signal not fitting into CSIGNAL mask */
+	test_clone3(0, 0, -EINVAL, CLONE3_ARGS_INVAL_EXIT_SIGNAL_CSIG);
+
+	/* Do a clone3() with NSIG < exit_signal < CSIG */
+	test_clone3(0, 0, -EINVAL, CLONE3_ARGS_INVAL_EXIT_SIGNAL_NSIG);
+
+	test_clone3(0, sizeof(struct clone_args) + 8, 0, CLONE3_ARGS_ALL_0);
+
+	test_clone3(0, sizeof(struct clone_args) + 16, -E2BIG,
+			CLONE3_ARGS_ALL_0);
+
+	test_clone3(0, sizeof(struct clone_args) * 2, -E2BIG,
+			CLONE3_ARGS_ALL_0);
+
+	/* Do a clone3() with > page size */
+	test_clone3(0, getpagesize() + 8, -E2BIG, CLONE3_ARGS_NO_TEST);
+
+	/* Do a clone3() with CLONE3_ARGS_SIZE_V0 in a new PID NS. */
+	if (uid == 0)
+		test_clone3(CLONE_NEWPID, CLONE3_ARGS_SIZE_V0, 0,
+				CLONE3_ARGS_NO_TEST);
+	else
+		ksft_test_result_skip("Skipping clone3() with CLONE_NEWPID\n");
+
+	/* Do a clone3() with CLONE3_ARGS_SIZE_V0 - 8 in a new PID NS */
+	test_clone3(CLONE_NEWPID, CLONE3_ARGS_SIZE_V0 - 8, -EINVAL,
+			CLONE3_ARGS_NO_TEST);
+
+	/* Do a clone3() with sizeof(struct clone_args) + 8 in a new PID NS */
+	if (uid == 0)
+		test_clone3(CLONE_NEWPID, sizeof(struct clone_args) + 8, 0,
+				CLONE3_ARGS_NO_TEST);
+	else
+		ksft_test_result_skip("Skipping clone3() with CLONE_NEWPID\n");
+
+	/* Do a clone3() with > page size in a new PID NS */
+	test_clone3(CLONE_NEWPID, getpagesize() + 8, -E2BIG,
+			CLONE3_ARGS_NO_TEST);
+
+	return !ksft_get_fail_cnt() ? ksft_exit_pass() : ksft_exit_fail();
+}
diff --git a/tools/testing/selftests/clone3/clone3_clear_sighand.c b/tools/testing/selftests/clone3/clone3_clear_sighand.c
new file mode 100644
index 000000000000..9e1af8aa7698
--- /dev/null
+++ b/tools/testing/selftests/clone3/clone3_clear_sighand.c
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+
+#include "../kselftest.h"
+#include "clone3_selftests.h"
+
+#ifndef CLONE_CLEAR_SIGHAND
+#define CLONE_CLEAR_SIGHAND 0x100000000ULL
+#endif
+
+static void nop_handler(int signo)
+{
+}
+
+static int wait_for_pid(pid_t pid)
+{
+	int status, ret;
+
+again:
+	ret = waitpid(pid, &status, 0);
+	if (ret == -1) {
+		if (errno == EINTR)
+			goto again;
+
+		return -1;
+	}
+
+	if (!WIFEXITED(status))
+		return -1;
+
+	return WEXITSTATUS(status);
+}
+
+static void test_clone3_clear_sighand(void)
+{
+	int ret;
+	pid_t pid;
+	struct clone_args args = {};
+	struct sigaction act;
+
+	/*
+	 * Check that CLONE_CLEAR_SIGHAND and CLONE_SIGHAND are mutually
+	 * exclusive.
+	 */
+	args.flags |= CLONE_CLEAR_SIGHAND | CLONE_SIGHAND;
+	args.exit_signal = SIGCHLD;
+	pid = sys_clone3(&args, sizeof(args));
+	if (pid > 0)
+		ksft_exit_fail_msg(
+			"clone3(CLONE_CLEAR_SIGHAND | CLONE_SIGHAND) succeeded\n");
+
+	act.sa_handler = nop_handler;
+	ret = sigemptyset(&act.sa_mask);
+	if (ret < 0)
+		ksft_exit_fail_msg("%s - sigemptyset() failed\n",
+				   strerror(errno));
+
+	act.sa_flags = 0;
+
+	/* Register signal handler for SIGUSR1 */
+	ret = sigaction(SIGUSR1, &act, NULL);
+	if (ret < 0)
+		ksft_exit_fail_msg(
+			"%s - sigaction(SIGUSR1, &act, NULL) failed\n",
+			strerror(errno));
+
+	/* Register signal handler for SIGUSR2 */
+	ret = sigaction(SIGUSR2, &act, NULL);
+	if (ret < 0)
+		ksft_exit_fail_msg(
+			"%s - sigaction(SIGUSR2, &act, NULL) failed\n",
+			strerror(errno));
+
+	/* Check that CLONE_CLEAR_SIGHAND works. */
+	args.flags = CLONE_CLEAR_SIGHAND;
+	pid = sys_clone3(&args, sizeof(args));
+	if (pid < 0)
+		ksft_exit_fail_msg("%s - clone3(CLONE_CLEAR_SIGHAND) failed\n",
+				   strerror(errno));
+
+	if (pid == 0) {
+		ret = sigaction(SIGUSR1, NULL, &act);
+		if (ret < 0)
+			exit(EXIT_FAILURE);
+
+		if (act.sa_handler != SIG_DFL)
+			exit(EXIT_FAILURE);
+
+		ret = sigaction(SIGUSR2, NULL, &act);
+		if (ret < 0)
+			exit(EXIT_FAILURE);
+
+		if (act.sa_handler != SIG_DFL)
+			exit(EXIT_FAILURE);
+
+		exit(EXIT_SUCCESS);
+	}
+
+	ret = wait_for_pid(pid);
+	if (ret)
+		ksft_exit_fail_msg(
+			"Failed to clear signal handler for child process\n");
+
+	ksft_test_result_pass("Cleared signal handlers for child process\n");
+}
+
+int main(int argc, char **argv)
+{
+	ksft_print_header();
+	test_clone3_supported();
+
+	ksft_set_plan(1);
+
+	test_clone3_clear_sighand();
+
+	return ksft_exit_pass();
+}
diff --git a/tools/testing/selftests/clone3/clone3_selftests.h b/tools/testing/selftests/clone3/clone3_selftests.h
new file mode 100644
index 000000000000..a3f2c8ad8bcc
--- /dev/null
+++ b/tools/testing/selftests/clone3/clone3_selftests.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _CLONE3_SELFTESTS_H
+#define _CLONE3_SELFTESTS_H
+
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdint.h>
+#include <syscall.h>
+#include <linux/types.h>
+
+#define ptr_to_u64(ptr) ((__u64)((uintptr_t)(ptr)))
+
+#ifndef __NR_clone3
+#define __NR_clone3 -1
+struct clone_args {
+	__aligned_u64 flags;
+	__aligned_u64 pidfd;
+	__aligned_u64 child_tid;
+	__aligned_u64 parent_tid;
+	__aligned_u64 exit_signal;
+	__aligned_u64 stack;
+	__aligned_u64 stack_size;
+	__aligned_u64 tls;
+	__aligned_u64 set_tid;
+	__aligned_u64 set_tid_size;
+};
+#endif
+
+static pid_t sys_clone3(struct clone_args *args, size_t size)
+{
+	fflush(stdout);
+	fflush(stderr);
+	return syscall(__NR_clone3, args, size);
+}
+
+static inline void test_clone3_supported(void)
+{
+	pid_t pid;
+	struct clone_args args = {};
+
+	if (__NR_clone3 < 0)
+		ksft_exit_skip("clone3() syscall is not supported\n");
+
+	/* Set to something that will always cause EINVAL. */
+	args.exit_signal = -1;
+	pid = sys_clone3(&args, sizeof(args));
+	if (!pid)
+		exit(EXIT_SUCCESS);
+
+	if (pid > 0) {
+		wait(NULL);
+		ksft_exit_fail_msg(
+			"Managed to create child process with invalid exit_signal\n");
+	}
+
+	if (errno == ENOSYS)
+		ksft_exit_skip("clone3() syscall is not supported\n");
+
+	ksft_print_msg("clone3() syscall supported\n");
+}
+
+#endif /* _CLONE3_SELFTESTS_H */
diff --git a/tools/testing/selftests/clone3/clone3_set_tid.c b/tools/testing/selftests/clone3/clone3_set_tid.c
new file mode 100644
index 000000000000..25beb22f35b5
--- /dev/null
+++ b/tools/testing/selftests/clone3/clone3_set_tid.c
@@ -0,0 +1,397 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Based on Christian Brauner's clone3() example.
+ * These tests are assuming to be running in the host's
+ * PID namespace.
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <sched.h>
+
+#include "../kselftest.h"
+#include "clone3_selftests.h"
+
+#ifndef MAX_PID_NS_LEVEL
+#define MAX_PID_NS_LEVEL 32
+#endif
+
+static int pipe_1[2];
+static int pipe_2[2];
+
+static void child_exit(int ret)
+{
+	fflush(stdout);
+	fflush(stderr);
+	_exit(ret);
+}
+
+static int call_clone3_set_tid(pid_t *set_tid,
+			       size_t set_tid_size,
+			       int flags,
+			       int expected_pid,
+			       bool wait_for_it)
+{
+	int status;
+	pid_t pid = -1;
+
+	struct clone_args args = {
+		.flags = flags,
+		.exit_signal = SIGCHLD,
+		.set_tid = ptr_to_u64(set_tid),
+		.set_tid_size = set_tid_size,
+	};
+
+	pid = sys_clone3(&args, sizeof(struct clone_args));
+	if (pid < 0) {
+		ksft_print_msg("%s - Failed to create new process\n",
+			       strerror(errno));
+		return -errno;
+	}
+
+	if (pid == 0) {
+		int ret;
+		char tmp = 0;
+		int exit_code = EXIT_SUCCESS;
+
+		ksft_print_msg("I am the child, my PID is %d (expected %d)\n",
+			       getpid(), set_tid[0]);
+		if (wait_for_it) {
+			ksft_print_msg("[%d] Child is ready and waiting\n",
+				       getpid());
+
+			/* Signal the parent that the child is ready */
+			close(pipe_1[0]);
+			ret = write(pipe_1[1], &tmp, 1);
+			if (ret != 1) {
+				ksft_print_msg(
+					"Writing to pipe returned %d", ret);
+				exit_code = EXIT_FAILURE;
+			}
+			close(pipe_1[1]);
+			close(pipe_2[1]);
+			ret = read(pipe_2[0], &tmp, 1);
+			if (ret != 1) {
+				ksft_print_msg(
+					"Reading from pipe returned %d", ret);
+				exit_code = EXIT_FAILURE;
+			}
+			close(pipe_2[0]);
+		}
+
+		if (set_tid[0] != getpid())
+			child_exit(EXIT_FAILURE);
+		child_exit(exit_code);
+	}
+
+	if (expected_pid == 0 || expected_pid == pid) {
+		ksft_print_msg("I am the parent (%d). My child's pid is %d\n",
+			       getpid(), pid);
+	} else {
+		ksft_print_msg(
+			"Expected child pid %d does not match actual pid %d\n",
+			expected_pid, pid);
+		return -1;
+	}
+
+	if (waitpid(pid, &status, 0) < 0) {
+		ksft_print_msg("Child returned %s\n", strerror(errno));
+		return -errno;
+	}
+
+	if (!WIFEXITED(status))
+		return -1;
+
+	return WEXITSTATUS(status);
+}
+
+static void test_clone3_set_tid(pid_t *set_tid,
+				size_t set_tid_size,
+				int flags,
+				int expected,
+				int expected_pid,
+				bool wait_for_it)
+{
+	int ret;
+
+	ksft_print_msg(
+		"[%d] Trying clone3() with CLONE_SET_TID to %d and 0x%x\n",
+		getpid(), set_tid[0], flags);
+	ret = call_clone3_set_tid(set_tid, set_tid_size, flags, expected_pid,
+				  wait_for_it);
+	ksft_print_msg(
+		"[%d] clone3() with CLONE_SET_TID %d says :%d - expected %d\n",
+		getpid(), set_tid[0], ret, expected);
+	if (ret != expected)
+		ksft_test_result_fail(
+			"[%d] Result (%d) is different than expected (%d)\n",
+			getpid(), ret, expected);
+	else
+		ksft_test_result_pass(
+			"[%d] Result (%d) matches expectation (%d)\n",
+			getpid(), ret, expected);
+}
+int main(int argc, char *argv[])
+{
+	FILE *f;
+	char buf;
+	char *line;
+	int status;
+	int ret = -1;
+	size_t len = 0;
+	int pid_max = 0;
+	uid_t uid = getuid();
+	char proc_path[100] = {0};
+	pid_t pid, ns1, ns2, ns3, ns_pid;
+	pid_t set_tid[MAX_PID_NS_LEVEL * 2];
+
+	ksft_print_header();
+	test_clone3_supported();
+	ksft_set_plan(29);
+
+	if (pipe(pipe_1) < 0 || pipe(pipe_2) < 0)
+		ksft_exit_fail_msg("pipe() failed\n");
+
+	f = fopen("/proc/sys/kernel/pid_max", "r");
+	if (f == NULL)
+		ksft_exit_fail_msg(
+			"%s - Could not open /proc/sys/kernel/pid_max\n",
+			strerror(errno));
+	fscanf(f, "%d", &pid_max);
+	fclose(f);
+	ksft_print_msg("/proc/sys/kernel/pid_max %d\n", pid_max);
+
+	/* Try invalid settings */
+	memset(&set_tid, 0, sizeof(set_tid));
+	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL + 1, 0, -EINVAL, 0, 0);
+
+	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL * 2, 0, -EINVAL, 0, 0);
+
+	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL * 2 + 1, 0,
+			-EINVAL, 0, 0);
+
+	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL * 42, 0, -EINVAL, 0, 0);
+
+	/*
+	 * This can actually work if this test running in a MAX_PID_NS_LEVEL - 1
+	 * nested PID namespace.
+	 */
+	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL - 1, 0, -EINVAL, 0, 0);
+
+	memset(&set_tid, 0xff, sizeof(set_tid));
+	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL + 1, 0, -EINVAL, 0, 0);
+
+	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL * 2, 0, -EINVAL, 0, 0);
+
+	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL * 2 + 1, 0,
+			-EINVAL, 0, 0);
+
+	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL * 42, 0, -EINVAL, 0, 0);
+
+	/*
+	 * This can actually work if this test running in a MAX_PID_NS_LEVEL - 1
+	 * nested PID namespace.
+	 */
+	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL - 1, 0, -EINVAL, 0, 0);
+
+	memset(&set_tid, 0, sizeof(set_tid));
+	/* Try with an invalid PID */
+	set_tid[0] = 0;
+	test_clone3_set_tid(set_tid, 1, 0, -EINVAL, 0, 0);
+
+	set_tid[0] = -1;
+	test_clone3_set_tid(set_tid, 1, 0, -EINVAL, 0, 0);
+
+	/* Claim that the set_tid array actually contains 2 elements. */
+	test_clone3_set_tid(set_tid, 2, 0, -EINVAL, 0, 0);
+
+	/* Try it in a new PID namespace */
+	if (uid == 0)
+		test_clone3_set_tid(set_tid, 1, CLONE_NEWPID, -EINVAL, 0, 0);
+	else
+		ksft_test_result_skip("Clone3() with set_tid requires root\n");
+
+	/* Try with a valid PID (1) this should return -EEXIST. */
+	set_tid[0] = 1;
+	if (uid == 0)
+		test_clone3_set_tid(set_tid, 1, 0, -EEXIST, 0, 0);
+	else
+		ksft_test_result_skip("Clone3() with set_tid requires root\n");
+
+	/* Try it in a new PID namespace */
+	if (uid == 0)
+		test_clone3_set_tid(set_tid, 1, CLONE_NEWPID, 0, 0, 0);
+	else
+		ksft_test_result_skip("Clone3() with set_tid requires root\n");
+
+	/* pid_max should fail everywhere */
+	set_tid[0] = pid_max;
+	test_clone3_set_tid(set_tid, 1, 0, -EINVAL, 0, 0);
+
+	if (uid == 0)
+		test_clone3_set_tid(set_tid, 1, CLONE_NEWPID, -EINVAL, 0, 0);
+	else
+		ksft_test_result_skip("Clone3() with set_tid requires root\n");
+
+	if (uid != 0) {
+		/*
+		 * All remaining tests require root. Tell the framework
+		 * that all those tests are skipped as non-root.
+		 */
+		ksft_cnt.ksft_xskip += ksft_plan - ksft_test_num();
+		goto out;
+	}
+
+	/* Find the current active PID */
+	pid = fork();
+	if (pid == 0) {
+		ksft_print_msg("Child has PID %d\n", getpid());
+		child_exit(EXIT_SUCCESS);
+	}
+	if (waitpid(pid, &status, 0) < 0)
+		ksft_exit_fail_msg("Waiting for child %d failed", pid);
+
+	/* After the child has finished, its PID should be free. */
+	set_tid[0] = pid;
+	test_clone3_set_tid(set_tid, 1, 0, 0, 0, 0);
+
+	/* This should fail as there is no PID 1 in that namespace */
+	test_clone3_set_tid(set_tid, 1, CLONE_NEWPID, -EINVAL, 0, 0);
+
+	/*
+	 * Creating a process with PID 1 in the newly created most nested
+	 * PID namespace and PID 'pid' in the parent PID namespace. This
+	 * needs to work.
+	 */
+	set_tid[0] = 1;
+	set_tid[1] = pid;
+	test_clone3_set_tid(set_tid, 2, CLONE_NEWPID, 0, pid, 0);
+
+	ksft_print_msg("unshare PID namespace\n");
+	if (unshare(CLONE_NEWPID) == -1)
+		ksft_exit_fail_msg("unshare(CLONE_NEWPID) failed: %s\n",
+				strerror(errno));
+
+	set_tid[0] = pid;
+
+	/* This should fail as there is no PID 1 in that namespace */
+	test_clone3_set_tid(set_tid, 1, 0, -EINVAL, 0, 0);
+
+	/* Let's create a PID 1 */
+	ns_pid = fork();
+	if (ns_pid == 0) {
+		/*
+		 * This and the next test cases check that all pid-s are
+		 * released on error paths.
+		 */
+		set_tid[0] = 43;
+		set_tid[1] = -1;
+		test_clone3_set_tid(set_tid, 2, 0, -EINVAL, 0, 0);
+
+		set_tid[0] = 43;
+		set_tid[1] = pid;
+		test_clone3_set_tid(set_tid, 2, 0, 0, 43, 0);
+
+		ksft_print_msg("Child in PID namespace has PID %d\n", getpid());
+		set_tid[0] = 2;
+		test_clone3_set_tid(set_tid, 1, 0, 0, 2, 0);
+
+		set_tid[0] = 1;
+		set_tid[1] = -1;
+		set_tid[2] = pid;
+		/* This should fail as there is invalid PID at level '1'. */
+		test_clone3_set_tid(set_tid, 3, CLONE_NEWPID, -EINVAL, 0, 0);
+
+		set_tid[0] = 1;
+		set_tid[1] = 42;
+		set_tid[2] = pid;
+		/*
+		 * This should fail as there are not enough active PID
+		 * namespaces. Again assuming this is running in the host's
+		 * PID namespace. Not yet nested.
+		 */
+		test_clone3_set_tid(set_tid, 4, CLONE_NEWPID, -EINVAL, 0, 0);
+
+		/*
+		 * This should work and from the parent we should see
+		 * something like 'NSpid:	pid	42	1'.
+		 */
+		test_clone3_set_tid(set_tid, 3, CLONE_NEWPID, 0, 42, true);
+
+		child_exit(ksft_cnt.ksft_fail);
+	}
+
+	close(pipe_1[1]);
+	close(pipe_2[0]);
+	while (read(pipe_1[0], &buf, 1) > 0) {
+		ksft_print_msg("[%d] Child is ready and waiting\n", getpid());
+		break;
+	}
+
+	snprintf(proc_path, sizeof(proc_path), "/proc/%d/status", pid);
+	f = fopen(proc_path, "r");
+	if (f == NULL)
+		ksft_exit_fail_msg(
+			"%s - Could not open %s\n",
+			strerror(errno), proc_path);
+
+	while (getline(&line, &len, f) != -1) {
+		if (strstr(line, "NSpid")) {
+			int i;
+
+			/* Verify that all generated PIDs are as expected. */
+			i = sscanf(line, "NSpid:\t%d\t%d\t%d",
+				   &ns3, &ns2, &ns1);
+			if (i != 3) {
+				ksft_print_msg(
+					"Unexpected 'NSPid:' entry: %s",
+					line);
+				ns1 = ns2 = ns3 = 0;
+			}
+			break;
+		}
+	}
+	fclose(f);
+	free(line);
+	close(pipe_2[0]);
+
+	/* Tell the clone3()'d child to finish. */
+	write(pipe_2[1], &buf, 1);
+	close(pipe_2[1]);
+
+	if (waitpid(ns_pid, &status, 0) < 0) {
+		ksft_print_msg("Child returned %s\n", strerror(errno));
+		ret = -errno;
+		goto out;
+	}
+
+	if (!WIFEXITED(status))
+		ksft_test_result_fail("Child error\n");
+
+	ksft_cnt.ksft_pass += 6 - (ksft_cnt.ksft_fail - WEXITSTATUS(status));
+	ksft_cnt.ksft_fail = WEXITSTATUS(status);
+
+	if (ns3 == pid && ns2 == 42 && ns1 == 1)
+		ksft_test_result_pass(
+			"PIDs in all namespaces as expected (%d,%d,%d)\n",
+			ns3, ns2, ns1);
+	else
+		ksft_test_result_fail(
+			"PIDs in all namespaces not as expected (%d,%d,%d)\n",
+			ns3, ns2, ns1);
+out:
+	ret = 0;
+
+	return !ret ? ksft_exit_pass() : ksft_exit_fail();
+}
diff --git a/tools/testing/selftests/gen_kselftest_tar.sh b/tools/testing/selftests/gen_kselftest_tar.sh
index a27e2eec3586..8b2b6088540d 100755
--- a/tools/testing/selftests/gen_kselftest_tar.sh
+++ b/tools/testing/selftests/gen_kselftest_tar.sh
@@ -38,16 +38,21 @@ main()
 	esac
 	fi
 
-	install_dir=./kselftest
+	# Create working directory.
+	dest=`pwd`
+	install_work="$dest"/kselftest_install
+	install_name=kselftest
+	install_dir="$install_work"/"$install_name"
+	mkdir -p "$install_dir"
 
-# Run install using INSTALL_KSFT_PATH override to generate install
-# directory
-./kselftest_install.sh
-tar $copts kselftest${ext} $install_dir
-echo "Kselftest archive kselftest${ext} created!"
+	# Run install using INSTALL_KSFT_PATH override to generate install
+	# directory
+	./kselftest_install.sh "$install_dir"
+	(cd "$install_work"; tar $copts "$dest"/kselftest${ext} $install_name)
+	echo "Kselftest archive kselftest${ext} created!"
 
-# clean up install directory
-rm -rf kselftest
+	# clean up top-level install work directory
+	rm -rf "$install_work"
 }
 
 main "$@"
diff --git a/tools/testing/selftests/kselftest_module.sh b/tools/testing/selftests/kselftest/module.sh
index 18e1c7992d30..18e1c7992d30 100755
--- a/tools/testing/selftests/kselftest_module.sh
+++ b/tools/testing/selftests/kselftest/module.sh
diff --git a/tools/testing/selftests/kselftest_install.sh b/tools/testing/selftests/kselftest_install.sh
index e2e1911d62d5..407af7da7037 100755
--- a/tools/testing/selftests/kselftest_install.sh
+++ b/tools/testing/selftests/kselftest_install.sh
@@ -6,30 +6,30 @@
 # Author: Shuah Khan <shuahkh@osg.samsung.com>
 # Copyright (C) 2015 Samsung Electronics Co., Ltd.
 
-install_loc=`pwd`
-
 main()
 {
-	if [ $(basename $install_loc) !=  "selftests" ]; then
+	base_dir=`pwd`
+	install_dir="$base_dir"/kselftest_install
+
+	# Make sure we're in the selftests top-level directory.
+	if [ $(basename "$base_dir") !=  "selftests" ]; then
 		echo "$0: Please run it in selftests directory ..."
 		exit 1;
 	fi
+
+	# Only allow installation into an existing location.
 	if [ "$#" -eq 0 ]; then
-		echo "$0: Installing in default location - $install_loc ..."
+		echo "$0: Installing in default location - $install_dir ..."
 	elif [ ! -d "$1" ]; then
 		echo "$0: $1 doesn't exist!!"
 		exit 1;
 	else
-		install_loc=$1
-		echo "$0: Installing in specified location - $install_loc ..."
+		install_dir="$1"
+		echo "$0: Installing in specified location - $install_dir ..."
 	fi
 
-	install_dir=$install_loc/kselftest_install
-
-# Create install directory
-	mkdir -p $install_dir
-# Build tests
-	KSFT_INSTALL_PATH=$install_dir make install
+	# Build tests
+	KSFT_INSTALL_PATH="$install_dir" make install
 }
 
 main "$@"
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 409c1fa75e03..30072c3f52fb 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -13,6 +13,7 @@
 /x86_64/vmx_dirty_log_test
 /x86_64/vmx_set_nested_state_test
 /x86_64/vmx_tsc_adjust_test
+/x86_64/xss_msr_test
 /clear_dirty_log_test
 /dirty_log_test
 /kvm_create_max_vcpus
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index c5ec868fa1e5..3138a916574a 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -25,6 +25,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
+TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test
 TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index ff234018219c..635ee6c33ad2 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -308,6 +308,8 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid,
 		     struct kvm_x86_state *state);
 
+struct kvm_msr_list *kvm_get_msr_index_list(void);
+
 struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
 void vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid,
 		    struct kvm_cpuid2 *cpuid);
@@ -322,10 +324,13 @@ kvm_get_supported_cpuid_entry(uint32_t function)
 }
 
 uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index);
+int _vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
+		  uint64_t msr_value);
 void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
 	  	  uint64_t msr_value);
 
-uint32_t kvm_get_cpuid_max(void);
+uint32_t kvm_get_cpuid_max_basic(void);
+uint32_t kvm_get_cpuid_max_extended(void);
 void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits);
 
 /*
diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
index 231d79e57774..6f38c3dc0d56 100644
--- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
+++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
@@ -29,12 +29,9 @@ void test_vcpu_creation(int first_vcpu_id, int num_vcpus)
 
 	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
 
-	for (i = 0; i < num_vcpus; i++) {
-		int vcpu_id = first_vcpu_id + i;
-
+	for (i = first_vcpu_id; i < first_vcpu_id + num_vcpus; i++)
 		/* This asserts that the vCPU was created. */
-		vm_vcpu_add(vm, vcpu_id);
-	}
+		vm_vcpu_add(vm, i);
 
 	kvm_vm_free(vm);
 }
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 6698cb741e10..683d3bdb8f6a 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -869,7 +869,7 @@ uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index)
 	return buffer.entry.data;
 }
 
-/* VCPU Set MSR
+/* _VCPU Set MSR
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -879,12 +879,12 @@ uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index)
  *
  * Output Args: None
  *
- * Return: On success, nothing. On failure a TEST_ASSERT is produced.
+ * Return: The result of KVM_SET_MSRS.
  *
- * Set value of MSR for VCPU.
+ * Sets the value of an MSR for the given VCPU.
  */
-void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
-	uint64_t msr_value)
+int _vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
+		  uint64_t msr_value)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	struct {
@@ -899,6 +899,29 @@ void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
 	buffer.entry.index = msr_index;
 	buffer.entry.data = msr_value;
 	r = ioctl(vcpu->fd, KVM_SET_MSRS, &buffer.header);
+	return r;
+}
+
+/* VCPU Set MSR
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *   msr_index - Index of MSR
+ *   msr_value - New value of MSR
+ *
+ * Output Args: None
+ *
+ * Return: On success, nothing. On failure a TEST_ASSERT is produced.
+ *
+ * Set value of MSR for VCPU.
+ */
+void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
+	uint64_t msr_value)
+{
+	int r;
+
+	r = _vcpu_set_msr(vm, vcpuid, msr_index, msr_value);
 	TEST_ASSERT(r == 1, "KVM_SET_MSRS IOCTL failed,\n"
 		"  rc: %i errno: %i", r, errno);
 }
@@ -1000,19 +1023,45 @@ struct kvm_x86_state {
 	struct kvm_msrs msrs;
 };
 
-static int kvm_get_num_msrs(struct kvm_vm *vm)
+static int kvm_get_num_msrs_fd(int kvm_fd)
 {
 	struct kvm_msr_list nmsrs;
 	int r;
 
 	nmsrs.nmsrs = 0;
-	r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, &nmsrs);
+	r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, &nmsrs);
 	TEST_ASSERT(r == -1 && errno == E2BIG, "Unexpected result from KVM_GET_MSR_INDEX_LIST probe, r: %i",
 		r);
 
 	return nmsrs.nmsrs;
 }
 
+static int kvm_get_num_msrs(struct kvm_vm *vm)
+{
+	return kvm_get_num_msrs_fd(vm->kvm_fd);
+}
+
+struct kvm_msr_list *kvm_get_msr_index_list(void)
+{
+	struct kvm_msr_list *list;
+	int nmsrs, r, kvm_fd;
+
+	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+	if (kvm_fd < 0)
+		exit(KSFT_SKIP);
+
+	nmsrs = kvm_get_num_msrs_fd(kvm_fd);
+	list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+	list->nmsrs = nmsrs;
+	r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
+	close(kvm_fd);
+
+	TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i",
+		r);
+
+	return list;
+}
+
 struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
@@ -1158,7 +1207,12 @@ bool is_intel_cpu(void)
 	return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]);
 }
 
-uint32_t kvm_get_cpuid_max(void)
+uint32_t kvm_get_cpuid_max_basic(void)
+{
+	return kvm_get_supported_cpuid_entry(0)->eax;
+}
+
+uint32_t kvm_get_cpuid_max_extended(void)
 {
 	return kvm_get_supported_cpuid_entry(0x80000000)->eax;
 }
@@ -1169,7 +1223,7 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits)
 	bool pae;
 
 	/* SDM 4.1.4 */
-	if (kvm_get_cpuid_max() < 0x80000008) {
+	if (kvm_get_cpuid_max_extended() < 0x80000008) {
 		pae = kvm_get_supported_cpuid_entry(1)->edx & (1 << 6);
 		*pa_bits = pae ? 36 : 32;
 		*va_bits = 32;
diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
index d5290b4ad636..b705637ca14b 100644
--- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
@@ -25,12 +25,15 @@
 
 static void guest_code(void)
 {
-	register u64 stage asm("11") = 0;
-
-	for (;;) {
-		GUEST_SYNC(0);
-		asm volatile ("ahi %0,1" : : "r"(stage));
-	}
+	/*
+	 * We embed diag 501 here instead of doing a ucall to avoid that
+	 * the compiler has messed with r11 at the time of the ucall.
+	 */
+	asm volatile (
+		"0:	diag 0,0,0x501\n"
+		"	ahi 11,1\n"
+		"	j 0b\n"
+	);
 }
 
 #define REG_COMPARE(reg) \
diff --git a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
new file mode 100644
index 000000000000..851ea81b9d9f
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019, Google LLC.
+ *
+ * Tests for the IA32_XSS MSR.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "vmx.h"
+
+#define VCPU_ID	      1
+#define MSR_BITS      64
+
+#define X86_FEATURE_XSAVES	(1<<3)
+
+bool is_supported_msr(u32 msr_index)
+{
+	struct kvm_msr_list *list;
+	bool found = false;
+	int i;
+
+	list = kvm_get_msr_index_list();
+	for (i = 0; i < list->nmsrs; ++i) {
+		if (list->indices[i] == msr_index) {
+			found = true;
+			break;
+		}
+	}
+
+	free(list);
+	return found;
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_cpuid_entry2 *entry;
+	bool xss_supported = false;
+	struct kvm_vm *vm;
+	uint64_t xss_val;
+	int i, r;
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, 0);
+
+	if (kvm_get_cpuid_max_basic() >= 0xd) {
+		entry = kvm_get_supported_cpuid_index(0xd, 1);
+		xss_supported = entry && !!(entry->eax & X86_FEATURE_XSAVES);
+	}
+	if (!xss_supported) {
+		printf("IA32_XSS is not supported by the vCPU.\n");
+		exit(KSFT_SKIP);
+	}
+
+	xss_val = vcpu_get_msr(vm, VCPU_ID, MSR_IA32_XSS);
+	TEST_ASSERT(xss_val == 0,
+		    "MSR_IA32_XSS should be initialized to zero\n");
+
+	vcpu_set_msr(vm, VCPU_ID, MSR_IA32_XSS, xss_val);
+	/*
+	 * At present, KVM only supports a guest IA32_XSS value of 0. Verify
+	 * that trying to set the guest IA32_XSS to an unsupported value fails.
+	 * Also, in the future when a non-zero value succeeds check that
+	 * IA32_XSS is in the KVM_GET_MSR_INDEX_LIST.
+	 */
+	for (i = 0; i < MSR_BITS; ++i) {
+		r = _vcpu_set_msr(vm, VCPU_ID, MSR_IA32_XSS, 1ull << i);
+		TEST_ASSERT(r == 0 || is_supported_msr(MSR_IA32_XSS),
+			    "IA32_XSS was able to be set, but was not found in KVM_GET_MSR_INDEX_LIST.\n");
+	}
+
+	kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/lib/bitmap.sh b/tools/testing/selftests/lib/bitmap.sh
index 5511dddc5c2d..00a416fbc0ef 100755
--- a/tools/testing/selftests/lib/bitmap.sh
+++ b/tools/testing/selftests/lib/bitmap.sh
@@ -1,3 +1,3 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
-$(dirname $0)/../kselftest_module.sh "bitmap" test_bitmap
+$(dirname $0)/../kselftest/module.sh "bitmap" test_bitmap
diff --git a/tools/testing/selftests/lib/prime_numbers.sh b/tools/testing/selftests/lib/prime_numbers.sh
index 43b28f24e453..370b79a9cb2e 100755
--- a/tools/testing/selftests/lib/prime_numbers.sh
+++ b/tools/testing/selftests/lib/prime_numbers.sh
@@ -1,4 +1,4 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 # Checks fast/slow prime_number generation for inconsistencies
-$(dirname $0)/../kselftest_module.sh "prime numbers" prime_numbers selftest=65536
+$(dirname $0)/../kselftest/module.sh "prime numbers" prime_numbers selftest=65536
diff --git a/tools/testing/selftests/lib/printf.sh b/tools/testing/selftests/lib/printf.sh
index 2ffa61da0296..05f4544e87f9 100755
--- a/tools/testing/selftests/lib/printf.sh
+++ b/tools/testing/selftests/lib/printf.sh
@@ -1,4 +1,4 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 # Tests the printf infrastructure using test_printf kernel module.
-$(dirname $0)/../kselftest_module.sh "printf" test_printf
+$(dirname $0)/../kselftest/module.sh "printf" test_printf
diff --git a/tools/testing/selftests/lib/strscpy.sh b/tools/testing/selftests/lib/strscpy.sh
index 71f2be6afba6..be60ef6e1a7f 100755
--- a/tools/testing/selftests/lib/strscpy.sh
+++ b/tools/testing/selftests/lib/strscpy.sh
@@ -1,3 +1,3 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0+
-$(dirname $0)/../kselftest_module.sh "strscpy*" test_strscpy
+$(dirname $0)/../kselftest/module.sh "strscpy*" test_strscpy
diff --git a/tools/testing/selftests/livepatch/Makefile b/tools/testing/selftests/livepatch/Makefile
index fd405402c3ff..1cf40a9e7185 100644
--- a/tools/testing/selftests/livepatch/Makefile
+++ b/tools/testing/selftests/livepatch/Makefile
@@ -4,6 +4,7 @@ TEST_PROGS_EXTENDED := functions.sh
 TEST_PROGS := \
 	test-livepatch.sh \
 	test-callbacks.sh \
-	test-shadow-vars.sh
+	test-shadow-vars.sh \
+	test-state.sh
 
 include ../lib.mk
diff --git a/tools/testing/selftests/livepatch/settings b/tools/testing/selftests/livepatch/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/livepatch/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/livepatch/test-state.sh b/tools/testing/selftests/livepatch/test-state.sh
new file mode 100755
index 000000000000..dc2908c22c26
--- /dev/null
+++ b/tools/testing/selftests/livepatch/test-state.sh
@@ -0,0 +1,180 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2019 SUSE
+
+. $(dirname $0)/functions.sh
+
+MOD_LIVEPATCH=test_klp_state
+MOD_LIVEPATCH2=test_klp_state2
+MOD_LIVEPATCH3=test_klp_state3
+
+set_dynamic_debug
+
+
+# TEST: Loading and removing a module that modifies the system state
+
+echo -n "TEST: system state modification ... "
+dmesg -C
+
+load_lp $MOD_LIVEPATCH
+disable_lp $MOD_LIVEPATCH
+unload_lp $MOD_LIVEPATCH
+
+check_result "% modprobe $MOD_LIVEPATCH
+livepatch: enabling patch '$MOD_LIVEPATCH'
+livepatch: '$MOD_LIVEPATCH': initializing patching transition
+$MOD_LIVEPATCH: pre_patch_callback: vmlinux
+$MOD_LIVEPATCH: allocate_loglevel_state: allocating space to store console_loglevel
+livepatch: '$MOD_LIVEPATCH': starting patching transition
+livepatch: '$MOD_LIVEPATCH': completing patching transition
+$MOD_LIVEPATCH: post_patch_callback: vmlinux
+$MOD_LIVEPATCH: fix_console_loglevel: fixing console_loglevel
+livepatch: '$MOD_LIVEPATCH': patching complete
+% echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH/enabled
+livepatch: '$MOD_LIVEPATCH': initializing unpatching transition
+$MOD_LIVEPATCH: pre_unpatch_callback: vmlinux
+$MOD_LIVEPATCH: restore_console_loglevel: restoring console_loglevel
+livepatch: '$MOD_LIVEPATCH': starting unpatching transition
+livepatch: '$MOD_LIVEPATCH': completing unpatching transition
+$MOD_LIVEPATCH: post_unpatch_callback: vmlinux
+$MOD_LIVEPATCH: free_loglevel_state: freeing space for the stored console_loglevel
+livepatch: '$MOD_LIVEPATCH': unpatching complete
+% rmmod $MOD_LIVEPATCH"
+
+
+# TEST: Take over system state change by a cumulative patch
+
+echo -n "TEST: taking over system state modification ... "
+dmesg -C
+
+load_lp $MOD_LIVEPATCH
+load_lp $MOD_LIVEPATCH2
+unload_lp $MOD_LIVEPATCH
+disable_lp $MOD_LIVEPATCH2
+unload_lp $MOD_LIVEPATCH2
+
+check_result "% modprobe $MOD_LIVEPATCH
+livepatch: enabling patch '$MOD_LIVEPATCH'
+livepatch: '$MOD_LIVEPATCH': initializing patching transition
+$MOD_LIVEPATCH: pre_patch_callback: vmlinux
+$MOD_LIVEPATCH: allocate_loglevel_state: allocating space to store console_loglevel
+livepatch: '$MOD_LIVEPATCH': starting patching transition
+livepatch: '$MOD_LIVEPATCH': completing patching transition
+$MOD_LIVEPATCH: post_patch_callback: vmlinux
+$MOD_LIVEPATCH: fix_console_loglevel: fixing console_loglevel
+livepatch: '$MOD_LIVEPATCH': patching complete
+% modprobe $MOD_LIVEPATCH2
+livepatch: enabling patch '$MOD_LIVEPATCH2'
+livepatch: '$MOD_LIVEPATCH2': initializing patching transition
+$MOD_LIVEPATCH2: pre_patch_callback: vmlinux
+$MOD_LIVEPATCH2: allocate_loglevel_state: space to store console_loglevel already allocated
+livepatch: '$MOD_LIVEPATCH2': starting patching transition
+livepatch: '$MOD_LIVEPATCH2': completing patching transition
+$MOD_LIVEPATCH2: post_patch_callback: vmlinux
+$MOD_LIVEPATCH2: fix_console_loglevel: taking over the console_loglevel change
+livepatch: '$MOD_LIVEPATCH2': patching complete
+% rmmod $MOD_LIVEPATCH
+% echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH2/enabled
+livepatch: '$MOD_LIVEPATCH2': initializing unpatching transition
+$MOD_LIVEPATCH2: pre_unpatch_callback: vmlinux
+$MOD_LIVEPATCH2: restore_console_loglevel: restoring console_loglevel
+livepatch: '$MOD_LIVEPATCH2': starting unpatching transition
+livepatch: '$MOD_LIVEPATCH2': completing unpatching transition
+$MOD_LIVEPATCH2: post_unpatch_callback: vmlinux
+$MOD_LIVEPATCH2: free_loglevel_state: freeing space for the stored console_loglevel
+livepatch: '$MOD_LIVEPATCH2': unpatching complete
+% rmmod $MOD_LIVEPATCH2"
+
+
+# TEST: Take over system state change by a cumulative patch
+
+echo -n "TEST: compatible cumulative livepatches ... "
+dmesg -C
+
+load_lp $MOD_LIVEPATCH2
+load_lp $MOD_LIVEPATCH3
+unload_lp $MOD_LIVEPATCH2
+load_lp $MOD_LIVEPATCH2
+disable_lp $MOD_LIVEPATCH2
+unload_lp $MOD_LIVEPATCH2
+unload_lp $MOD_LIVEPATCH3
+
+check_result "% modprobe $MOD_LIVEPATCH2
+livepatch: enabling patch '$MOD_LIVEPATCH2'
+livepatch: '$MOD_LIVEPATCH2': initializing patching transition
+$MOD_LIVEPATCH2: pre_patch_callback: vmlinux
+$MOD_LIVEPATCH2: allocate_loglevel_state: allocating space to store console_loglevel
+livepatch: '$MOD_LIVEPATCH2': starting patching transition
+livepatch: '$MOD_LIVEPATCH2': completing patching transition
+$MOD_LIVEPATCH2: post_patch_callback: vmlinux
+$MOD_LIVEPATCH2: fix_console_loglevel: fixing console_loglevel
+livepatch: '$MOD_LIVEPATCH2': patching complete
+% modprobe $MOD_LIVEPATCH3
+livepatch: enabling patch '$MOD_LIVEPATCH3'
+livepatch: '$MOD_LIVEPATCH3': initializing patching transition
+$MOD_LIVEPATCH3: pre_patch_callback: vmlinux
+$MOD_LIVEPATCH3: allocate_loglevel_state: space to store console_loglevel already allocated
+livepatch: '$MOD_LIVEPATCH3': starting patching transition
+livepatch: '$MOD_LIVEPATCH3': completing patching transition
+$MOD_LIVEPATCH3: post_patch_callback: vmlinux
+$MOD_LIVEPATCH3: fix_console_loglevel: taking over the console_loglevel change
+livepatch: '$MOD_LIVEPATCH3': patching complete
+% rmmod $MOD_LIVEPATCH2
+% modprobe $MOD_LIVEPATCH2
+livepatch: enabling patch '$MOD_LIVEPATCH2'
+livepatch: '$MOD_LIVEPATCH2': initializing patching transition
+$MOD_LIVEPATCH2: pre_patch_callback: vmlinux
+$MOD_LIVEPATCH2: allocate_loglevel_state: space to store console_loglevel already allocated
+livepatch: '$MOD_LIVEPATCH2': starting patching transition
+livepatch: '$MOD_LIVEPATCH2': completing patching transition
+$MOD_LIVEPATCH2: post_patch_callback: vmlinux
+$MOD_LIVEPATCH2: fix_console_loglevel: taking over the console_loglevel change
+livepatch: '$MOD_LIVEPATCH2': patching complete
+% echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH2/enabled
+livepatch: '$MOD_LIVEPATCH2': initializing unpatching transition
+$MOD_LIVEPATCH2: pre_unpatch_callback: vmlinux
+$MOD_LIVEPATCH2: restore_console_loglevel: restoring console_loglevel
+livepatch: '$MOD_LIVEPATCH2': starting unpatching transition
+livepatch: '$MOD_LIVEPATCH2': completing unpatching transition
+$MOD_LIVEPATCH2: post_unpatch_callback: vmlinux
+$MOD_LIVEPATCH2: free_loglevel_state: freeing space for the stored console_loglevel
+livepatch: '$MOD_LIVEPATCH2': unpatching complete
+% rmmod $MOD_LIVEPATCH2
+% rmmod $MOD_LIVEPATCH3"
+
+
+# TEST: Failure caused by incompatible cumulative livepatches
+
+echo -n "TEST: incompatible cumulative livepatches ... "
+dmesg -C
+
+load_lp $MOD_LIVEPATCH2
+load_failing_mod $MOD_LIVEPATCH
+disable_lp $MOD_LIVEPATCH2
+unload_lp $MOD_LIVEPATCH2
+
+check_result "% modprobe $MOD_LIVEPATCH2
+livepatch: enabling patch '$MOD_LIVEPATCH2'
+livepatch: '$MOD_LIVEPATCH2': initializing patching transition
+$MOD_LIVEPATCH2: pre_patch_callback: vmlinux
+$MOD_LIVEPATCH2: allocate_loglevel_state: allocating space to store console_loglevel
+livepatch: '$MOD_LIVEPATCH2': starting patching transition
+livepatch: '$MOD_LIVEPATCH2': completing patching transition
+$MOD_LIVEPATCH2: post_patch_callback: vmlinux
+$MOD_LIVEPATCH2: fix_console_loglevel: fixing console_loglevel
+livepatch: '$MOD_LIVEPATCH2': patching complete
+% modprobe $MOD_LIVEPATCH
+livepatch: Livepatch patch ($MOD_LIVEPATCH) is not compatible with the already installed livepatches.
+modprobe: ERROR: could not insert '$MOD_LIVEPATCH': Invalid argument
+% echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH2/enabled
+livepatch: '$MOD_LIVEPATCH2': initializing unpatching transition
+$MOD_LIVEPATCH2: pre_unpatch_callback: vmlinux
+$MOD_LIVEPATCH2: restore_console_loglevel: restoring console_loglevel
+livepatch: '$MOD_LIVEPATCH2': starting unpatching transition
+livepatch: '$MOD_LIVEPATCH2': completing unpatching transition
+$MOD_LIVEPATCH2: post_unpatch_callback: vmlinux
+$MOD_LIVEPATCH2: free_loglevel_state: freeing space for the stored console_loglevel
+livepatch: '$MOD_LIVEPATCH2': unpatching complete
+% rmmod $MOD_LIVEPATCH2"
+
+exit 0
diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c
index 53f598f06647..34df4c8882af 100644
--- a/tools/testing/selftests/net/so_txtime.c
+++ b/tools/testing/selftests/net/so_txtime.c
@@ -105,8 +105,8 @@ static void do_recv_one(int fdr, struct timed_send *ts)
 	tstop = (gettime_ns() - glob_tstart) / 1000;
 	texpect = ts->delay_us >= 0 ? ts->delay_us : 0;
 
-	fprintf(stderr, "payload:%c delay:%ld expected:%ld (us)\n",
-			rbuf[0], tstop, texpect);
+	fprintf(stderr, "payload:%c delay:%lld expected:%lld (us)\n",
+			rbuf[0], (long long)tstop, (long long)texpect);
 
 	if (rbuf[0] != ts->data)
 		error(1, 0, "payload mismatch. expected %c", ts->data);
diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
index 5bb370a0857e..35505b31e5cc 100644
--- a/tools/testing/selftests/net/tcp_mmap.c
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -71,7 +71,7 @@
 #define MSG_ZEROCOPY    0x4000000
 #endif
 
-#define FILE_SZ (1UL << 35)
+#define FILE_SZ (1ULL << 35)
 static int cfg_family = AF_INET6;
 static socklen_t cfg_alen = sizeof(struct sockaddr_in6);
 static int cfg_port = 8787;
@@ -165,7 +165,7 @@ void *child_thread(void *arg)
 			socklen_t zc_len = sizeof(zc);
 			int res;
 
-			zc.address = (__u64)addr;
+			zc.address = (__u64)((unsigned long)addr);
 			zc.length = chunk_size;
 			zc.recv_skip_hint = 0;
 			res = getsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE,
@@ -341,7 +341,7 @@ int main(int argc, char *argv[])
 {
 	struct sockaddr_storage listenaddr, addr;
 	unsigned int max_pacing_rate = 0;
-	unsigned long total = 0;
+	size_t total = 0;
 	char *host = NULL;
 	int fd, c, on = 1;
 	char *buffer;
@@ -470,7 +470,7 @@ int main(int argc, char *argv[])
 		zflg = 0;
 	}
 	while (total < FILE_SZ) {
-		long wr = FILE_SZ - total;
+		ssize_t wr = FILE_SZ - total;
 
 		if (wr > chunk_size)
 			wr = chunk_size;
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index 614b31aad168..c66da6ffd6d8 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -440,7 +440,8 @@ static bool __send_one(int fd, struct msghdr *msg, int flags)
 	if (ret == -1)
 		error(1, errno, "sendmsg");
 	if (ret != msg->msg_iov->iov_len)
-		error(1, 0, "sendto: %d != %lu", ret, msg->msg_iov->iov_len);
+		error(1, 0, "sendto: %d != %llu", ret,
+			(unsigned long long)msg->msg_iov->iov_len);
 	if (msg->msg_flags)
 		error(1, 0, "sendmsg: return flags 0x%x\n", msg->msg_flags);
 
diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c
index ada99496634a..17512a43885e 100644
--- a/tools/testing/selftests/net/udpgso_bench_tx.c
+++ b/tools/testing/selftests/net/udpgso_bench_tx.c
@@ -405,7 +405,8 @@ static int send_udp_segment(int fd, char *data)
 	if (ret == -1)
 		error(1, errno, "sendmsg");
 	if (ret != iov.iov_len)
-		error(1, 0, "sendmsg: %u != %lu\n", ret, iov.iov_len);
+		error(1, 0, "sendmsg: %u != %llu\n", ret,
+			(unsigned long long)iov.iov_len);
 
 	return 1;
 }
diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile
index 7550f08822a3..43db1b98e845 100644
--- a/tools/testing/selftests/pidfd/Makefile
+++ b/tools/testing/selftests/pidfd/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 CFLAGS += -g -I../../../../usr/include/ -pthread
 
-TEST_GEN_PROGS := pidfd_test pidfd_open_test pidfd_poll_test pidfd_wait
+TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test pidfd_poll_test pidfd_wait
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c
new file mode 100644
index 000000000000..22558524f71c
--- /dev/null
+++ b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c
@@ -0,0 +1,296 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/types.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <sys/wait.h>
+
+#include "pidfd.h"
+#include "../kselftest.h"
+
+struct error {
+	int  code;
+	char msg[512];
+};
+
+static int error_set(struct error *err, int code, const char *fmt, ...)
+{
+	va_list args;
+	int r;
+
+	if (code == PIDFD_PASS || !err || err->code != PIDFD_PASS)
+		return code;
+
+	err->code = code;
+	va_start(args, fmt);
+	r = vsnprintf(err->msg, sizeof(err->msg), fmt, args);
+	assert((size_t)r < sizeof(err->msg));
+	va_end(args);
+
+	return code;
+}
+
+static void error_report(struct error *err, const char *test_name)
+{
+	switch (err->code) {
+	case PIDFD_ERROR:
+		ksft_exit_fail_msg("%s test: Fatal: %s\n", test_name, err->msg);
+		break;
+
+	case PIDFD_FAIL:
+		/* will be: not ok %d # error %s test: %s */
+		ksft_test_result_error("%s test: %s\n", test_name, err->msg);
+		break;
+
+	case PIDFD_SKIP:
+		/* will be: not ok %d # SKIP %s test: %s */
+		ksft_test_result_skip("%s test: %s\n", test_name, err->msg);
+		break;
+
+	case PIDFD_XFAIL:
+		ksft_test_result_pass("%s test: Expected failure: %s\n",
+				      test_name, err->msg);
+		break;
+
+	case PIDFD_PASS:
+		ksft_test_result_pass("%s test: Passed\n");
+		break;
+
+	default:
+		ksft_exit_fail_msg("%s test: Unknown code: %d %s\n",
+				   test_name, err->code, err->msg);
+		break;
+	}
+}
+
+static inline int error_check(struct error *err, const char *test_name)
+{
+	/* In case of error we bail out and terminate the test program */
+	if (err->code == PIDFD_ERROR)
+		error_report(err, test_name);
+
+	return err->code;
+}
+
+struct child {
+	pid_t pid;
+	int   fd;
+};
+
+static struct child clone_newns(int (*fn)(void *), void *args,
+				struct error *err)
+{
+	static int flags = CLONE_PIDFD | CLONE_NEWPID | CLONE_NEWNS | SIGCHLD;
+	size_t stack_size = 1024;
+	char *stack[1024] = { 0 };
+	struct child ret;
+
+	if (!(flags & CLONE_NEWUSER) && geteuid() != 0)
+		flags |= CLONE_NEWUSER;
+
+#ifdef __ia64__
+	ret.pid = __clone2(fn, stack, stack_size, flags, args, &ret.fd);
+#else
+	ret.pid = clone(fn, stack + stack_size, flags, args, &ret.fd);
+#endif
+
+	if (ret.pid < 0) {
+		error_set(err, PIDFD_ERROR, "clone failed (ret %d, errno %d)",
+			  ret.fd, errno);
+		return ret;
+	}
+
+	ksft_print_msg("New child: %d, fd: %d\n", ret.pid, ret.fd);
+
+	return ret;
+}
+
+static inline void child_close(struct child *child)
+{
+	close(child->fd);
+}
+
+static inline int child_join(struct child *child, struct error *err)
+{
+	int r;
+
+	r = wait_for_pid(child->pid);
+	if (r < 0)
+		error_set(err, PIDFD_ERROR, "waitpid failed (ret %d, errno %d)",
+			  r, errno);
+	else if (r > 0)
+		error_set(err, r, "child %d reported: %d", child->pid, r);
+
+	return r;
+}
+
+static inline int child_join_close(struct child *child, struct error *err)
+{
+	child_close(child);
+	return child_join(child, err);
+}
+
+static inline void trim_newline(char *str)
+{
+	char *pos = strrchr(str, '\n');
+
+	if (pos)
+		*pos = '\0';
+}
+
+static int verify_fdinfo(int pidfd, struct error *err, const char *prefix,
+			 size_t prefix_len, const char *expect, ...)
+{
+	char buffer[512] = {0, };
+	char path[512] = {0, };
+	va_list args;
+	FILE *f;
+	char *line = NULL;
+	size_t n = 0;
+	int found = 0;
+	int r;
+
+	va_start(args, expect);
+	r = vsnprintf(buffer, sizeof(buffer), expect, args);
+	assert((size_t)r < sizeof(buffer));
+	va_end(args);
+
+	snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", pidfd);
+	f = fopen(path, "re");
+	if (!f)
+		return error_set(err, PIDFD_ERROR, "fdinfo open failed for %d",
+				 pidfd);
+
+	while (getline(&line, &n, f) != -1) {
+		char *val;
+
+		if (strncmp(line, prefix, prefix_len))
+			continue;
+
+		found = 1;
+
+		val = line + prefix_len;
+		r = strcmp(val, buffer);
+		if (r != 0) {
+			trim_newline(line);
+			trim_newline(buffer);
+			error_set(err, PIDFD_FAIL, "%s '%s' != '%s'",
+				  prefix, val, buffer);
+		}
+		break;
+	}
+
+	free(line);
+	fclose(f);
+
+	if (found == 0)
+		return error_set(err, PIDFD_FAIL, "%s not found for fd %d",
+				 prefix, pidfd);
+
+	return PIDFD_PASS;
+}
+
+static int child_fdinfo_nspid_test(void *args)
+{
+	struct error err;
+	int pidfd;
+	int r;
+
+	/* if we got no fd for the sibling, we are done */
+	if (!args)
+		return PIDFD_PASS;
+
+	/* verify that we can not resolve the pidfd for a process
+	 * in a sibling pid namespace, i.e. a pid namespace it is
+	 * not in our or a descended namespace
+	 */
+	r = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0);
+	if (r < 0) {
+		ksft_print_msg("Failed to remount / private\n");
+		return PIDFD_ERROR;
+	}
+
+	(void)umount2("/proc", MNT_DETACH);
+	r = mount("proc", "/proc", "proc", 0, NULL);
+	if (r < 0) {
+		ksft_print_msg("Failed to remount /proc\n");
+		return PIDFD_ERROR;
+	}
+
+	pidfd = *(int *)args;
+	r = verify_fdinfo(pidfd, &err, "NSpid:", 6, "\t0\n");
+
+	if (r != PIDFD_PASS)
+		ksft_print_msg("NSpid fdinfo check failed: %s\n", err.msg);
+
+	return r;
+}
+
+static void test_pidfd_fdinfo_nspid(void)
+{
+	struct child a, b;
+	struct error err = {0, };
+	const char *test_name = "pidfd check for NSpid in fdinfo";
+
+	/* Create a new child in a new pid and mount namespace */
+	a = clone_newns(child_fdinfo_nspid_test, NULL, &err);
+	error_check(&err, test_name);
+
+	/* Pass the pidfd representing the first child to the
+	 * second child, which will be in a sibling pid namespace,
+	 * which means that the fdinfo NSpid entry for the pidfd
+	 * should only contain '0'.
+	 */
+	b = clone_newns(child_fdinfo_nspid_test, &a.fd, &err);
+	error_check(&err, test_name);
+
+	/* The children will have pid 1 in the new pid namespace,
+	 * so the line must be 'NSPid:\t<pid>\t1'.
+	 */
+	verify_fdinfo(a.fd, &err, "NSpid:", 6, "\t%d\t%d\n", a.pid, 1);
+	verify_fdinfo(b.fd, &err, "NSpid:", 6, "\t%d\t%d\n", b.pid, 1);
+
+	/* wait for the process, check the exit status and set
+	 * 'err' accordingly, if it is not already set.
+	 */
+	child_join_close(&a, &err);
+	child_join_close(&b, &err);
+
+	error_report(&err, test_name);
+}
+
+static void test_pidfd_dead_fdinfo(void)
+{
+	struct child a;
+	struct error err = {0, };
+	const char *test_name = "pidfd check fdinfo for dead process";
+
+	/* Create a new child in a new pid and mount namespace */
+	a = clone_newns(child_fdinfo_nspid_test, NULL, &err);
+	error_check(&err, test_name);
+	child_join(&a, &err);
+
+	verify_fdinfo(a.fd, &err, "Pid:", 4, "\t-1\n");
+	verify_fdinfo(a.fd, &err, "NSpid:", 6, "\t-1\n");
+	child_close(&a);
+	error_report(&err, test_name);
+}
+
+int main(int argc, char **argv)
+{
+	ksft_print_header();
+	ksft_set_plan(2);
+
+	test_pidfd_fdinfo_nspid();
+	test_pidfd_dead_fdinfo();
+
+	return ksft_exit_pass();
+}
diff --git a/tools/testing/selftests/proc/proc-self-map-files-002.c b/tools/testing/selftests/proc/proc-self-map-files-002.c
index 47b7473dedef..e6aa00a183bc 100644
--- a/tools/testing/selftests/proc/proc-self-map-files-002.c
+++ b/tools/testing/selftests/proc/proc-self-map-files-002.c
@@ -47,7 +47,11 @@ static void fail(const char *fmt, unsigned long a, unsigned long b)
 int main(void)
 {
 	const int PAGE_SIZE = sysconf(_SC_PAGESIZE);
-	const unsigned long va_max = 1UL << 32;
+	/*
+	 * va_max must be enough bigger than vm.mmap_min_addr, which is
+	 * 64KB/32KB by default. (depends on CONFIG_LSM_MMAP_MIN_ADDR)
+	 */
+	const unsigned long va_max = 1UL << 20;
 	unsigned long va;
 	void *p;
 	int fd;
diff --git a/tools/testing/selftests/sync/sync.c b/tools/testing/selftests/sync/sync.c
index f3d599f249b9..7741c0518d18 100644
--- a/tools/testing/selftests/sync/sync.c
+++ b/tools/testing/selftests/sync/sync.c
@@ -109,7 +109,7 @@ static struct sync_file_info *sync_file_info(int fd)
 			return NULL;
 		}
 
-		info->sync_fence_info = (uint64_t)fence_info;
+		info->sync_fence_info = (uint64_t)(unsigned long)fence_info;
 
 		err = ioctl(fd, SYNC_IOC_FILE_INFO, info);
 		if (err < 0) {
@@ -124,7 +124,7 @@ static struct sync_file_info *sync_file_info(int fd)
 
 static void sync_file_info_free(struct sync_file_info *info)
 {
-	free((void *)info->sync_fence_info);
+	free((void *)(unsigned long)info->sync_fence_info);
 	free(info);
 }
 
@@ -152,7 +152,7 @@ int sync_fence_count_with_status(int fd, int status)
 	if (!info)
 		return -1;
 
-	fence_info = (struct sync_fence_info *)info->sync_fence_info;
+	fence_info = (struct sync_fence_info *)(unsigned long)info->sync_fence_info;
 	for (i = 0 ; i < info->num_fences ; i++) {
 		if (fence_info[i].status == status)
 			count++;
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 9534dc2bc929..7f9a8a8c31da 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for vm selftests
+uname_M := $(shell uname -m 2>/dev/null || echo not)
+ARCH ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/')
 
 CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
 LDLIBS = -lrt
@@ -16,8 +18,11 @@ TEST_GEN_FILES += on-fault-limit
 TEST_GEN_FILES += thuge-gen
 TEST_GEN_FILES += transhuge-stress
 TEST_GEN_FILES += userfaultfd
+
+ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64))
 TEST_GEN_FILES += va_128TBswitch
 TEST_GEN_FILES += virtual_address_range
+endif
 
 TEST_PROGS := run_vmtests
 
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index 951c507a27f7..a692ea828317 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -58,6 +58,14 @@ else
 	exit 1
 fi
 
+#filter 64bit architectures
+ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64"
+if [ -z $ARCH ]; then
+  ARCH=`uname -m 2>/dev/null | sed -e 's/aarch64.*/arm64/'`
+fi
+VADDR64=0
+echo "$ARCH64STR" | grep $ARCH && VADDR64=1
+
 mkdir $mnt
 mount -t hugetlbfs none $mnt
 
@@ -189,6 +197,7 @@ else
 	echo "[PASS]"
 fi
 
+if [ $VADDR64 -ne 0 ]; then
 echo "-----------------------------"
 echo "running virtual_address_range"
 echo "-----------------------------"
@@ -210,6 +219,7 @@ if [ $? -ne 0 ]; then
 else
     echo "[PASS]"
 fi
+fi # VADDR64
 
 echo "------------------------------------"
 echo "running vmalloc stability smoke test"
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index e2bb5bd60227..f182b2380345 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -80,7 +80,7 @@ static inline bool userspace_irqchip(struct kvm *kvm)
 static void soft_timer_start(struct hrtimer *hrt, u64 ns)
 {
 	hrtimer_start(hrt, ktime_add_ns(ktime_get(), ns),
-		      HRTIMER_MODE_ABS);
+		      HRTIMER_MODE_ABS_HARD);
 }
 
 static void soft_timer_cancel(struct hrtimer *hrt)
@@ -697,11 +697,11 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 	update_vtimer_cntvoff(vcpu, kvm_phys_timer_read());
 	ptimer->cntvoff = 0;
 
-	hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 	timer->bg_timer.function = kvm_bg_timer_expire;
 
-	hrtimer_init(&vtimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	hrtimer_init(&ptimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init(&vtimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
+	hrtimer_init(&ptimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 	vtimer->hrtimer.function = kvm_hrtimer_expire;
 	ptimer->hrtimer.function = kvm_hrtimer_expire;
 
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 86c6aa1cb58e..12e0280291ce 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -40,6 +40,10 @@
 #include <asm/kvm_coproc.h>
 #include <asm/sections.h>
 
+#include <kvm/arm_hypercalls.h>
+#include <kvm/arm_pmu.h>
+#include <kvm/arm_psci.h>
+
 #ifdef REQUIRES_VIRT
 __asm__(".arch_extension	virt");
 #endif
@@ -98,6 +102,26 @@ int kvm_arch_check_processor_compat(void)
 	return 0;
 }
 
+int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
+			    struct kvm_enable_cap *cap)
+{
+	int r;
+
+	if (cap->flags)
+		return -EINVAL;
+
+	switch (cap->cap) {
+	case KVM_CAP_ARM_NISV_TO_USER:
+		r = 0;
+		kvm->arch.return_nisv_io_abort_to_user = true;
+		break;
+	default:
+		r = -EINVAL;
+		break;
+	}
+
+	return r;
+}
 
 /**
  * kvm_arch_init_vm - initializes a VM data structure
@@ -197,6 +221,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_IMMEDIATE_EXIT:
 	case KVM_CAP_VCPU_EVENTS:
 	case KVM_CAP_ARM_IRQ_LINE_LAYOUT_2:
+	case KVM_CAP_ARM_NISV_TO_USER:
+	case KVM_CAP_ARM_INJECT_EXT_DABT:
 		r = 1;
 		break;
 	case KVM_CAP_ARM_SET_DEVICE_ADDR:
@@ -322,20 +348,24 @@ void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
 	/*
 	 * If we're about to block (most likely because we've just hit a
 	 * WFI), we need to sync back the state of the GIC CPU interface
-	 * so that we have the lastest PMR and group enables. This ensures
+	 * so that we have the latest PMR and group enables. This ensures
 	 * that kvm_arch_vcpu_runnable has up-to-date data to decide
 	 * whether we have pending interrupts.
+	 *
+	 * For the same reason, we want to tell GICv4 that we need
+	 * doorbells to be signalled, should an interrupt become pending.
 	 */
 	preempt_disable();
 	kvm_vgic_vmcr_sync(vcpu);
+	vgic_v4_put(vcpu, true);
 	preempt_enable();
-
-	kvm_vgic_v4_enable_doorbell(vcpu);
 }
 
 void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 {
-	kvm_vgic_v4_disable_doorbell(vcpu);
+	preempt_disable();
+	vgic_v4_load(vcpu);
+	preempt_enable();
 }
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
@@ -351,6 +381,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 	kvm_arm_reset_debug_ptr(vcpu);
 
+	kvm_arm_pvtime_vcpu_init(&vcpu->arch);
+
 	return kvm_vgic_vcpu_init(vcpu);
 }
 
@@ -380,11 +412,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	kvm_vcpu_load_sysregs(vcpu);
 	kvm_arch_vcpu_load_fp(vcpu);
 	kvm_vcpu_pmu_restore_guest(vcpu);
+	if (kvm_arm_is_pvtime_enabled(&vcpu->arch))
+		kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu);
 
 	if (single_task_running())
-		vcpu_clear_wfe_traps(vcpu);
+		vcpu_clear_wfx_traps(vcpu);
 	else
-		vcpu_set_wfe_traps(vcpu);
+		vcpu_set_wfx_traps(vcpu);
 
 	vcpu_ptrauth_setup_lazy(vcpu);
 }
@@ -645,6 +679,9 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
 		 * that a VCPU sees new virtual interrupts.
 		 */
 		kvm_check_request(KVM_REQ_IRQ_PENDING, vcpu);
+
+		if (kvm_check_request(KVM_REQ_RECORD_STEAL, vcpu))
+			kvm_update_stolen_time(vcpu);
 	}
 }
 
diff --git a/virt/kvm/arm/hypercalls.c b/virt/kvm/arm/hypercalls.c
new file mode 100644
index 000000000000..550dfa3e53cd
--- /dev/null
+++ b/virt/kvm/arm/hypercalls.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 Arm Ltd.
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_emulate.h>
+
+#include <kvm/arm_hypercalls.h>
+#include <kvm/arm_psci.h>
+
+int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
+{
+	u32 func_id = smccc_get_function(vcpu);
+	long val = SMCCC_RET_NOT_SUPPORTED;
+	u32 feature;
+	gpa_t gpa;
+
+	switch (func_id) {
+	case ARM_SMCCC_VERSION_FUNC_ID:
+		val = ARM_SMCCC_VERSION_1_1;
+		break;
+	case ARM_SMCCC_ARCH_FEATURES_FUNC_ID:
+		feature = smccc_get_arg1(vcpu);
+		switch (feature) {
+		case ARM_SMCCC_ARCH_WORKAROUND_1:
+			switch (kvm_arm_harden_branch_predictor()) {
+			case KVM_BP_HARDEN_UNKNOWN:
+				break;
+			case KVM_BP_HARDEN_WA_NEEDED:
+				val = SMCCC_RET_SUCCESS;
+				break;
+			case KVM_BP_HARDEN_NOT_REQUIRED:
+				val = SMCCC_RET_NOT_REQUIRED;
+				break;
+			}
+			break;
+		case ARM_SMCCC_ARCH_WORKAROUND_2:
+			switch (kvm_arm_have_ssbd()) {
+			case KVM_SSBD_FORCE_DISABLE:
+			case KVM_SSBD_UNKNOWN:
+				break;
+			case KVM_SSBD_KERNEL:
+				val = SMCCC_RET_SUCCESS;
+				break;
+			case KVM_SSBD_FORCE_ENABLE:
+			case KVM_SSBD_MITIGATED:
+				val = SMCCC_RET_NOT_REQUIRED;
+				break;
+			}
+			break;
+		case ARM_SMCCC_HV_PV_TIME_FEATURES:
+			val = SMCCC_RET_SUCCESS;
+			break;
+		}
+		break;
+	case ARM_SMCCC_HV_PV_TIME_FEATURES:
+		val = kvm_hypercall_pv_features(vcpu);
+		break;
+	case ARM_SMCCC_HV_PV_TIME_ST:
+		gpa = kvm_init_stolen_time(vcpu);
+		if (gpa != GPA_INVALID)
+			val = gpa;
+		break;
+	default:
+		return kvm_psci_call(vcpu);
+	}
+
+	smccc_set_retval(vcpu, val, 0, 0, 0);
+	return 1;
+}
diff --git a/virt/kvm/arm/mmio.c b/virt/kvm/arm/mmio.c
index 6af5c91337f2..70d3b449692c 100644
--- a/virt/kvm/arm/mmio.c
+++ b/virt/kvm/arm/mmio.c
@@ -167,7 +167,14 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		if (ret)
 			return ret;
 	} else {
-		kvm_err("load/store instruction decoding not implemented\n");
+		if (vcpu->kvm->arch.return_nisv_io_abort_to_user) {
+			run->exit_reason = KVM_EXIT_ARM_NISV;
+			run->arm_nisv.esr_iss = kvm_vcpu_dabt_iss_nisv_sanitized(vcpu);
+			run->arm_nisv.fault_ipa = fault_ipa;
+			return 0;
+		}
+
+		kvm_pr_unimpl("Data abort outside memslots with no valid syndrome info\n");
 		return -ENOSYS;
 	}
 
diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c
index 87927f7e1ee7..17e2bdd4b76f 100644
--- a/virt/kvm/arm/psci.c
+++ b/virt/kvm/arm/psci.c
@@ -15,6 +15,7 @@
 #include <asm/kvm_host.h>
 
 #include <kvm/arm_psci.h>
+#include <kvm/arm_hypercalls.h>
 
 /*
  * This is an implementation of the Power State Coordination Interface
@@ -23,38 +24,6 @@
 
 #define AFFINITY_MASK(level)	~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1)
 
-static u32 smccc_get_function(struct kvm_vcpu *vcpu)
-{
-	return vcpu_get_reg(vcpu, 0);
-}
-
-static unsigned long smccc_get_arg1(struct kvm_vcpu *vcpu)
-{
-	return vcpu_get_reg(vcpu, 1);
-}
-
-static unsigned long smccc_get_arg2(struct kvm_vcpu *vcpu)
-{
-	return vcpu_get_reg(vcpu, 2);
-}
-
-static unsigned long smccc_get_arg3(struct kvm_vcpu *vcpu)
-{
-	return vcpu_get_reg(vcpu, 3);
-}
-
-static void smccc_set_retval(struct kvm_vcpu *vcpu,
-			     unsigned long a0,
-			     unsigned long a1,
-			     unsigned long a2,
-			     unsigned long a3)
-{
-	vcpu_set_reg(vcpu, 0, a0);
-	vcpu_set_reg(vcpu, 1, a1);
-	vcpu_set_reg(vcpu, 2, a2);
-	vcpu_set_reg(vcpu, 3, a3);
-}
-
 static unsigned long psci_affinity_mask(unsigned long affinity_level)
 {
 	if (affinity_level <= 3)
@@ -373,7 +342,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
  * Errors:
  * -EINVAL: Unrecognized PSCI function
  */
-static int kvm_psci_call(struct kvm_vcpu *vcpu)
+int kvm_psci_call(struct kvm_vcpu *vcpu)
 {
 	switch (kvm_psci_version(vcpu, vcpu->kvm)) {
 	case KVM_ARM_PSCI_1_0:
@@ -387,55 +356,6 @@ static int kvm_psci_call(struct kvm_vcpu *vcpu)
 	};
 }
 
-int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
-{
-	u32 func_id = smccc_get_function(vcpu);
-	u32 val = SMCCC_RET_NOT_SUPPORTED;
-	u32 feature;
-
-	switch (func_id) {
-	case ARM_SMCCC_VERSION_FUNC_ID:
-		val = ARM_SMCCC_VERSION_1_1;
-		break;
-	case ARM_SMCCC_ARCH_FEATURES_FUNC_ID:
-		feature = smccc_get_arg1(vcpu);
-		switch(feature) {
-		case ARM_SMCCC_ARCH_WORKAROUND_1:
-			switch (kvm_arm_harden_branch_predictor()) {
-			case KVM_BP_HARDEN_UNKNOWN:
-				break;
-			case KVM_BP_HARDEN_WA_NEEDED:
-				val = SMCCC_RET_SUCCESS;
-				break;
-			case KVM_BP_HARDEN_NOT_REQUIRED:
-				val = SMCCC_RET_NOT_REQUIRED;
-				break;
-			}
-			break;
-		case ARM_SMCCC_ARCH_WORKAROUND_2:
-			switch (kvm_arm_have_ssbd()) {
-			case KVM_SSBD_FORCE_DISABLE:
-			case KVM_SSBD_UNKNOWN:
-				break;
-			case KVM_SSBD_KERNEL:
-				val = SMCCC_RET_SUCCESS;
-				break;
-			case KVM_SSBD_FORCE_ENABLE:
-			case KVM_SSBD_MITIGATED:
-				val = SMCCC_RET_NOT_REQUIRED;
-				break;
-			}
-			break;
-		}
-		break;
-	default:
-		return kvm_psci_call(vcpu);
-	}
-
-	smccc_set_retval(vcpu, val, 0, 0, 0);
-	return 1;
-}
-
 int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu)
 {
 	return 3;		/* PSCI version and two workaround registers */
diff --git a/virt/kvm/arm/pvtime.c b/virt/kvm/arm/pvtime.c
new file mode 100644
index 000000000000..1e0f4c284888
--- /dev/null
+++ b/virt/kvm/arm/pvtime.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 Arm Ltd.
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_mmu.h>
+#include <asm/pvclock-abi.h>
+
+#include <kvm/arm_hypercalls.h>
+
+void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	u64 steal;
+	__le64 steal_le;
+	u64 offset;
+	int idx;
+	u64 base = vcpu->arch.steal.base;
+
+	if (base == GPA_INVALID)
+		return;
+
+	/* Let's do the local bookkeeping */
+	steal = vcpu->arch.steal.steal;
+	steal += current->sched_info.run_delay - vcpu->arch.steal.last_steal;
+	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
+	vcpu->arch.steal.steal = steal;
+
+	steal_le = cpu_to_le64(steal);
+	idx = srcu_read_lock(&kvm->srcu);
+	offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
+	kvm_put_guest(kvm, base + offset, steal_le, u64);
+	srcu_read_unlock(&kvm->srcu, idx);
+}
+
+long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
+{
+	u32 feature = smccc_get_arg1(vcpu);
+	long val = SMCCC_RET_NOT_SUPPORTED;
+
+	switch (feature) {
+	case ARM_SMCCC_HV_PV_TIME_FEATURES:
+	case ARM_SMCCC_HV_PV_TIME_ST:
+		val = SMCCC_RET_SUCCESS;
+		break;
+	}
+
+	return val;
+}
+
+gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
+{
+	struct pvclock_vcpu_stolen_time init_values = {};
+	struct kvm *kvm = vcpu->kvm;
+	u64 base = vcpu->arch.steal.base;
+	int idx;
+
+	if (base == GPA_INVALID)
+		return base;
+
+	/*
+	 * Start counting stolen time from the time the guest requests
+	 * the feature enabled.
+	 */
+	vcpu->arch.steal.steal = 0;
+	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	kvm_write_guest(kvm, base, &init_values, sizeof(init_values));
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	return base;
+}
+
+int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr)
+{
+	u64 __user *user = (u64 __user *)attr->addr;
+	struct kvm *kvm = vcpu->kvm;
+	u64 ipa;
+	int ret = 0;
+	int idx;
+
+	if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
+		return -ENXIO;
+
+	if (get_user(ipa, user))
+		return -EFAULT;
+	if (!IS_ALIGNED(ipa, 64))
+		return -EINVAL;
+	if (vcpu->arch.steal.base != GPA_INVALID)
+		return -EEXIST;
+
+	/* Check the address is in a valid memslot */
+	idx = srcu_read_lock(&kvm->srcu);
+	if (kvm_is_error_hva(gfn_to_hva(kvm, ipa >> PAGE_SHIFT)))
+		ret = -EINVAL;
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	if (!ret)
+		vcpu->arch.steal.base = ipa;
+
+	return ret;
+}
+
+int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr)
+{
+	u64 __user *user = (u64 __user *)attr->addr;
+	u64 ipa;
+
+	if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
+		return -ENXIO;
+
+	ipa = vcpu->arch.steal.base;
+
+	if (put_user(ipa, user))
+		return -EFAULT;
+	return 0;
+}
+
+int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_PVTIME_IPA:
+		return 0;
+	}
+	return -ENXIO;
+}
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 6f50c429196d..b3c5de48064c 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -203,6 +203,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 
 	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
 	raw_spin_lock_init(&vgic_cpu->ap_list_lock);
+	atomic_set(&vgic_cpu->vgic_v3.its_vpe.vlpi_count, 0);
 
 	/*
 	 * Enable and configure all SGIs to be edge-triggered and
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index 2be6b66b3856..98c7360d9fb7 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -360,7 +360,10 @@ static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu)
 		if (ret)
 			return ret;
 
+		if (map.vpe)
+			atomic_dec(&map.vpe->vlpi_count);
 		map.vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
+		atomic_inc(&map.vpe->vlpi_count);
 
 		ret = its_map_vlpi(irq->host_irq, &map);
 	}
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index 8d69f007dd0c..f45635a6f0ec 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -357,14 +357,14 @@ retry:
 }
 
 /**
- * vgic_its_save_pending_tables - Save the pending tables into guest RAM
+ * vgic_v3_save_pending_tables - Save the pending tables into guest RAM
  * kvm lock and all vcpu lock must be held
  */
 int vgic_v3_save_pending_tables(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
-	int last_byte_offset = -1;
 	struct vgic_irq *irq;
+	gpa_t last_ptr = ~(gpa_t)0;
 	int ret;
 	u8 val;
 
@@ -384,11 +384,11 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 		bit_nr = irq->intid % BITS_PER_BYTE;
 		ptr = pendbase + byte_offset;
 
-		if (byte_offset != last_byte_offset) {
+		if (ptr != last_ptr) {
 			ret = kvm_read_guest_lock(kvm, ptr, &val, 1);
 			if (ret)
 				return ret;
-			last_byte_offset = byte_offset;
+			last_ptr = ptr;
 		}
 
 		stored = val & (1U << bit_nr);
@@ -664,6 +664,8 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 
 	if (has_vhe())
 		__vgic_v3_activate_traps(vcpu);
+
+	WARN_ON(vgic_v4_load(vcpu));
 }
 
 void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu)
@@ -676,6 +678,8 @@ void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu)
 
 void vgic_v3_put(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(vgic_v4_put(vcpu, false));
+
 	vgic_v3_vmcr_sync(vcpu);
 
 	kvm_call_hyp(__vgic_v3_save_aprs, vcpu);
diff --git a/virt/kvm/arm/vgic/vgic-v4.c b/virt/kvm/arm/vgic/vgic-v4.c
index 477af6aebb97..46f875589c47 100644
--- a/virt/kvm/arm/vgic/vgic-v4.c
+++ b/virt/kvm/arm/vgic/vgic-v4.c
@@ -85,6 +85,10 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info)
 {
 	struct kvm_vcpu *vcpu = info;
 
+	/* We got the message, no need to fire again */
+	if (!irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
+		disable_irq_nosync(irq);
+
 	vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true;
 	kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 	kvm_vcpu_kick(vcpu);
@@ -192,20 +196,30 @@ void vgic_v4_teardown(struct kvm *kvm)
 	its_vm->vpes = NULL;
 }
 
-int vgic_v4_sync_hwstate(struct kvm_vcpu *vcpu)
+int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db)
 {
-	if (!vgic_supports_direct_msis(vcpu->kvm))
+	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
+	struct irq_desc *desc = irq_to_desc(vpe->irq);
+
+	if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident)
 		return 0;
 
-	return its_schedule_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe, false);
+	/*
+	 * If blocking, a doorbell is required. Undo the nested
+	 * disable_irq() calls...
+	 */
+	while (need_db && irqd_irq_disabled(&desc->irq_data))
+		enable_irq(vpe->irq);
+
+	return its_schedule_vpe(vpe, false);
 }
 
-int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu)
+int vgic_v4_load(struct kvm_vcpu *vcpu)
 {
-	int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq;
+	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
 	int err;
 
-	if (!vgic_supports_direct_msis(vcpu->kvm))
+	if (!vgic_supports_direct_msis(vcpu->kvm) || vpe->resident)
 		return 0;
 
 	/*
@@ -214,11 +228,14 @@ int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu)
 	 * doc in drivers/irqchip/irq-gic-v4.c to understand how this
 	 * turns into a VMOVP command at the ITS level.
 	 */
-	err = irq_set_affinity(irq, cpumask_of(smp_processor_id()));
+	err = irq_set_affinity(vpe->irq, cpumask_of(smp_processor_id()));
 	if (err)
 		return err;
 
-	err = its_schedule_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe, true);
+	/* Disabled the doorbell, as we're about to enter the guest */
+	disable_irq_nosync(vpe->irq);
+
+	err = its_schedule_vpe(vpe, true);
 	if (err)
 		return err;
 
@@ -226,9 +243,7 @@ int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu)
 	 * Now that the VPE is resident, let's get rid of a potential
 	 * doorbell interrupt that would still be pending.
 	 */
-	err = irq_set_irqchip_state(irq, IRQCHIP_STATE_PENDING, false);
-
-	return err;
+	return irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false);
 }
 
 static struct vgic_its *vgic_get_its(struct kvm *kvm,
@@ -266,7 +281,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq,
 
 	mutex_lock(&its->its_lock);
 
-	/* Perform then actual DevID/EventID -> LPI translation. */
+	/* Perform the actual DevID/EventID -> LPI translation. */
 	ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid,
 				   irq_entry->msi.data, &irq);
 	if (ret)
@@ -294,6 +309,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq,
 
 	irq->hw		= true;
 	irq->host_irq	= virq;
+	atomic_inc(&map.vpe->vlpi_count);
 
 out:
 	mutex_unlock(&its->its_lock);
@@ -327,6 +343,7 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq,
 
 	WARN_ON(!(irq->hw && irq->host_irq == virq));
 	if (irq->hw) {
+		atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count);
 		irq->hw = false;
 		ret = its_unmap_vlpi(virq);
 	}
@@ -335,21 +352,3 @@ out:
 	mutex_unlock(&its->its_lock);
 	return ret;
 }
-
-void kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu)
-{
-	if (vgic_supports_direct_msis(vcpu->kvm)) {
-		int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq;
-		if (irq)
-			enable_irq(irq);
-	}
-}
-
-void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu)
-{
-	if (vgic_supports_direct_msis(vcpu->kvm)) {
-		int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq;
-		if (irq)
-			disable_irq(irq);
-	}
-}
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index 45a870cb63f5..99b02ca730a8 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -857,8 +857,6 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 
-	WARN_ON(vgic_v4_sync_hwstate(vcpu));
-
 	/* An empty ap_list_head implies used_lrs == 0 */
 	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
 		return;
@@ -882,8 +880,6 @@ static inline void vgic_restore_state(struct kvm_vcpu *vcpu)
 /* Flush our emulation state into the GIC hardware before entering the guest. */
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 {
-	WARN_ON(vgic_v4_flush_hwstate(vcpu));
-
 	/*
 	 * If there are no virtual interrupts active or pending for this
 	 * VCPU, then there is no work to do and we can bail out without
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index 83066a81b16a..c7fefd6b1c80 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -316,7 +316,5 @@ void vgic_its_invalidate_cache(struct kvm *kvm);
 bool vgic_supports_direct_msis(struct kvm *kvm);
 int vgic_v4_init(struct kvm *kvm);
 void vgic_v4_teardown(struct kvm *kvm);
-int vgic_v4_sync_hwstate(struct kvm_vcpu *vcpu);
-int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu);
 
 #endif
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index 8ffd07e2a160..00c747dbc82e 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -110,14 +110,11 @@ static const struct kvm_io_device_ops coalesced_mmio_ops = {
 int kvm_coalesced_mmio_init(struct kvm *kvm)
 {
 	struct page *page;
-	int ret;
 
-	ret = -ENOMEM;
 	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
 	if (!page)
-		goto out_err;
+		return -ENOMEM;
 
-	ret = 0;
 	kvm->coalesced_mmio_ring = page_address(page);
 
 	/*
@@ -128,8 +125,7 @@ int kvm_coalesced_mmio_init(struct kvm *kvm)
 	spin_lock_init(&kvm->ring_lock);
 	INIT_LIST_HEAD(&kvm->coalesced_zones);
 
-out_err:
-	return ret;
+	return 0;
 }
 
 void kvm_coalesced_mmio_free(struct kvm *kvm)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 13efc291b1c7..00268290dcbd 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -838,6 +838,18 @@ void kvm_put_kvm(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_put_kvm);
 
+/*
+ * Used to put a reference that was taken on behalf of an object associated
+ * with a user-visible file descriptor, e.g. a vcpu or device, if installation
+ * of the new file descriptor fails and the reference cannot be transferred to
+ * its final owner.  In such cases, the caller is still actively using @kvm and
+ * will fail miserably if the refcount unexpectedly hits zero.
+ */
+void kvm_put_kvm_no_destroy(struct kvm *kvm)
+{
+	WARN_ON(refcount_dec_and_test(&kvm->users_count));
+}
+EXPORT_SYMBOL_GPL(kvm_put_kvm_no_destroy);
 
 static int kvm_vm_release(struct inode *inode, struct file *filp)
 {
@@ -2739,17 +2751,18 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 		goto unlock_vcpu_destroy;
 	}
 
-	BUG_ON(kvm->vcpus[atomic_read(&kvm->online_vcpus)]);
+	vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus);
+	BUG_ON(kvm->vcpus[vcpu->vcpu_idx]);
 
 	/* Now it's all set up, let userspace reach it */
 	kvm_get_kvm(kvm);
 	r = create_vcpu_fd(vcpu);
 	if (r < 0) {
-		kvm_put_kvm(kvm);
+		kvm_put_kvm_no_destroy(kvm);
 		goto unlock_vcpu_destroy;
 	}
 
-	kvm->vcpus[atomic_read(&kvm->online_vcpus)] = vcpu;
+	kvm->vcpus[vcpu->vcpu_idx] = vcpu;
 
 	/*
 	 * Pairs with smp_rmb() in kvm_get_vcpu.  Write kvm->vcpus
@@ -3115,14 +3128,14 @@ struct kvm_device *kvm_device_from_filp(struct file *filp)
 	return filp->private_data;
 }
 
-static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
+static const struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
 #ifdef CONFIG_KVM_MPIC
 	[KVM_DEV_TYPE_FSL_MPIC_20]	= &kvm_mpic_ops,
 	[KVM_DEV_TYPE_FSL_MPIC_42]	= &kvm_mpic_ops,
 #endif
 };
 
-int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type)
+int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type)
 {
 	if (type >= ARRAY_SIZE(kvm_device_ops_table))
 		return -ENOSPC;
@@ -3143,7 +3156,7 @@ void kvm_unregister_device_ops(u32 type)
 static int kvm_ioctl_create_device(struct kvm *kvm,
 				   struct kvm_create_device *cd)
 {
-	struct kvm_device_ops *ops = NULL;
+	const struct kvm_device_ops *ops = NULL;
 	struct kvm_device *dev;
 	bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
 	int type;
@@ -3183,7 +3196,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 	kvm_get_kvm(kvm);
 	ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC);
 	if (ret < 0) {
-		kvm_put_kvm(kvm);
+		kvm_put_kvm_no_destroy(kvm);
 		mutex_lock(&kvm->lock);
 		list_del(&dev->vm_node);
 		mutex_unlock(&kvm->lock);
@@ -4341,12 +4354,12 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 
 	r = kvm_arch_hardware_setup();
 	if (r < 0)
-		goto out_free_0a;
+		goto out_free_1;
 
 	for_each_online_cpu(cpu) {
 		smp_call_function_single(cpu, check_processor_compat, &r, 1);
 		if (r < 0)
-			goto out_free_1;
+			goto out_free_2;
 	}
 
 	r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting",
@@ -4403,9 +4416,8 @@ out_free_3:
 	unregister_reboot_notifier(&kvm_reboot_notifier);
 	cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING);
 out_free_2:
-out_free_1:
 	kvm_arch_hardware_unsetup();
-out_free_0a:
+out_free_1:
 	free_cpumask_var(cpus_hardware_enabled);
 out_free_0:
 	kvm_irqfd_exit();